A multi-label learning based kernel automatic recommendation method for support vector machine.

PubMed

Zhang, Xueying; Song, Qinbao

2015-01-01

Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance.

A Multi-Label Learning Based Kernel Automatic Recommendation Method for Support Vector Machine

PubMed Central

Zhang, Xueying; Song, Qinbao

2015-01-01

Choosing an appropriate kernel is very important and critical when classifying a new problem with Support Vector Machine. So far, more attention has been paid on constructing new kernels and choosing suitable parameter values for a specific kernel function, but less on kernel selection. Furthermore, most of current kernel selection methods focus on seeking a best kernel with the highest classification accuracy via cross-validation, they are time consuming and ignore the differences among the number of support vectors and the CPU time of SVM with different kernels. Considering the tradeoff between classification success ratio and CPU time, there may be multiple kernel functions performing equally well on the same classification problem. Aiming to automatically select those appropriate kernel functions for a given data set, we propose a multi-label learning based kernel recommendation method built on the data characteristics. For each data set, the meta-knowledge data base is first created by extracting the feature vector of data characteristics and identifying the corresponding applicable kernel set. Then the kernel recommendation model is constructed on the generated meta-knowledge data base with the multi-label classification method. Finally, the appropriate kernel functions are recommended to a new data set by the recommendation model according to the characteristics of the new data set. Extensive experiments over 132 UCI benchmark data sets, with five different types of data set characteristics, eleven typical kernels (Linear, Polynomial, Radial Basis Function, Sigmoidal function, Laplace, Multiquadric, Rational Quadratic, Spherical, Spline, Wave and Circular), and five multi-label classification methods demonstrate that, compared with the existing kernel selection methods and the most widely used RBF kernel function, SVM with the kernel function recommended by our proposed method achieved the highest classification performance. PMID:25893896

Optimized extreme learning machine for urban land cover classification using hyperspectral imagery

NASA Astrophysics Data System (ADS)

Su, Hongjun; Tian, Shufang; Cai, Yue; Sheng, Yehua; Chen, Chen; Najafian, Maryam

2017-12-01

This work presents a new urban land cover classification framework using the firefly algorithm (FA) optimized extreme learning machine (ELM). FA is adopted to optimize the regularization coefficient C and Gaussian kernel σ for kernel ELM. Additionally, effectiveness of spectral features derived from an FA-based band selection algorithm is studied for the proposed classification task. Three sets of hyperspectral databases were recorded using different sensors, namely HYDICE, HyMap, and AVIRIS. Our study shows that the proposed method outperforms traditional classification algorithms such as SVM and reduces computational cost significantly.

Salient Feature Identification and Analysis using Kernel-Based Classification Techniques for Synthetic Aperture Radar Automatic Target Recognition

DTIC Science & Technology

2014-03-27

and machine learning for a range of research including such topics as medical imaging [10] and handwriting recognition [11]. The type of feature...1989. [11] C. Bahlmann, B. Haasdonk, and H. Burkhardt, “Online handwriting recognition with support vector machines-a kernel approach,” in Eighth...International Workshop on Frontiers in Handwriting Recognition, pp. 49–54, IEEE, 2002. [12] C. Cortes and V. Vapnik, “Support-vector networks,” Machine

An implementation of support vector machine on sentiment classification of movie reviews

NASA Astrophysics Data System (ADS)

Yulietha, I. M.; Faraby, S. A.; Adiwijaya; Widyaningtyas, W. C.

2018-03-01

With technological advances, all information about movie is available on the internet. If the information is processed properly, it will get the quality of the information. This research proposes to the classify sentiments on movie review documents. This research uses Support Vector Machine (SVM) method because it can classify high dimensional data in accordance with the data used in this research in the form of text. Support Vector Machine is a popular machine learning technique for text classification because it can classify by learning from a collection of documents that have been classified previously and can provide good result. Based on number of datasets, the 90-10 composition has the best result that is 85.6%. Based on SVM kernel, kernel linear with constant 1 has the best result that is 84.9%

Learn the Lagrangian: A Vector-Valued RKHS Approach to Identifying Lagrangian Systems.

PubMed

Cheng, Ching-An; Huang, Han-Pang

2016-12-01

We study the modeling of Lagrangian systems with multiple degrees of freedom. Based on system dynamics, canonical parametric models require ad hoc derivations and sometimes simplification for a computable solution; on the other hand, due to the lack of prior knowledge in the system's structure, modern nonparametric models in machine learning face the curse of dimensionality, especially in learning large systems. In this paper, we bridge this gap by unifying the theories of Lagrangian systems and vector-valued reproducing kernel Hilbert space. We reformulate Lagrangian systems with kernels that embed the governing Euler-Lagrange equation-the Lagrangian kernels-and show that these kernels span a subspace capturing the Lagrangian's projection as inverse dynamics. By such property, our model uses only inputs and outputs as in machine learning and inherits the structured form as in system dynamics, thereby removing the need for the mundane derivations for new systems as well as the generalization problem in learning from scratches. In effect, it learns the system's Lagrangian, a simpler task than directly learning the dynamics. To demonstrate, we applied the proposed kernel to identify the robot inverse dynamics in simulations and experiments. Our results present a competitive novel approach to identifying Lagrangian systems, despite using only inputs and outputs.

Alumina Concentration Detection Based on the Kernel Extreme Learning Machine.

PubMed

Zhang, Sen; Zhang, Tao; Yin, Yixin; Xiao, Wendong

2017-09-01

The concentration of alumina in the electrolyte is of great significance during the production of aluminum. The amount of the alumina concentration may lead to unbalanced material distribution and low production efficiency and affect the stability of the aluminum reduction cell and current efficiency. The existing methods cannot meet the needs for online measurement because industrial aluminum electrolysis has the characteristics of high temperature, strong magnetic field, coupled parameters, and high nonlinearity. Currently, there are no sensors or equipment that can detect the alumina concentration on line. Most companies acquire the alumina concentration from the electrolyte samples which are analyzed through an X-ray fluorescence spectrometer. To solve the problem, the paper proposes a soft sensing model based on a kernel extreme learning machine algorithm that takes the kernel function into the extreme learning machine. K-fold cross validation is used to estimate the generalization error. The proposed soft sensing algorithm can detect alumina concentration by the electrical signals such as voltages and currents of the anode rods. The predicted results show that the proposed approach can give more accurate estimations of alumina concentration with faster learning speed compared with the other methods such as the basic ELM, BP, and SVM.

Kernel learning at the first level of inference.

PubMed

Cawley, Gavin C; Talbot, Nicola L C

2014-05-01

Kernel learning methods, whether Bayesian or frequentist, typically involve multiple levels of inference, with the coefficients of the kernel expansion being determined at the first level and the kernel and regularisation parameters carefully tuned at the second level, a process known as model selection. Model selection for kernel machines is commonly performed via optimisation of a suitable model selection criterion, often based on cross-validation or theoretical performance bounds. However, if there are a large number of kernel parameters, as for instance in the case of automatic relevance determination (ARD), there is a substantial risk of over-fitting the model selection criterion, resulting in poor generalisation performance. In this paper we investigate the possibility of learning the kernel, for the Least-Squares Support Vector Machine (LS-SVM) classifier, at the first level of inference, i.e. parameter optimisation. The kernel parameters and the coefficients of the kernel expansion are jointly optimised at the first level of inference, minimising a training criterion with an additional regularisation term acting on the kernel parameters. The key advantage of this approach is that the values of only two regularisation parameters need be determined in model selection, substantially alleviating the problem of over-fitting the model selection criterion. The benefits of this approach are demonstrated using a suite of synthetic and real-world binary classification benchmark problems, where kernel learning at the first level of inference is shown to be statistically superior to the conventional approach, improves on our previous work (Cawley and Talbot, 2007) and is competitive with Multiple Kernel Learning approaches, but with reduced computational expense. Copyright © 2014 Elsevier Ltd. All rights reserved.

Prostate cancer detection using machine learning techniques by employing combination of features extracting strategies.

PubMed

Hussain, Lal; Ahmed, Adeel; Saeed, Sharjil; Rathore, Saima; Awan, Imtiaz Ahmed; Shah, Saeed Arif; Majid, Abdul; Idris, Adnan; Awan, Anees Ahmed

2018-02-06

Prostate is a second leading causes of cancer deaths among men. Early detection of cancer can effectively reduce the rate of mortality caused by Prostate cancer. Due to high and multiresolution of MRIs from prostate cancer require a proper diagnostic systems and tools. In the past researchers developed Computer aided diagnosis (CAD) systems that help the radiologist to detect the abnormalities. In this research paper, we have employed novel Machine learning techniques such as Bayesian approach, Support vector machine (SVM) kernels: polynomial, radial base function (RBF) and Gaussian and Decision Tree for detecting prostate cancer. Moreover, different features extracting strategies are proposed to improve the detection performance. The features extracting strategies are based on texture, morphological, scale invariant feature transform (SIFT), and elliptic Fourier descriptors (EFDs) features. The performance was evaluated based on single as well as combination of features using Machine Learning Classification techniques. The Cross validation (Jack-knife k-fold) was performed and performance was evaluated in term of receiver operating curve (ROC) and specificity, sensitivity, Positive predictive value (PPV), negative predictive value (NPV), false positive rate (FPR). Based on single features extracting strategies, SVM Gaussian Kernel gives the highest accuracy of 98.34% with AUC of 0.999. While, using combination of features extracting strategies, SVM Gaussian kernel with texture + morphological, and EFDs + morphological features give the highest accuracy of 99.71% and AUC of 1.00.

Learning molecular energies using localized graph kernels

DOE PAGES

Ferré, Grégoire; Haut, Terry Scot; Barros, Kipton Marcos

2017-03-21

We report that recent machine learning methods make it possible to model potential energy of atomic configurations with chemical-level accuracy (as calculated from ab initio calculations) and at speeds suitable for molecular dynamics simulation. Best performance is achieved when the known physical constraints are encoded in the machine learning models. For example, the atomic energy is invariant under global translations and rotations; it is also invariant to permutations of same-species atoms. Although simple to state, these symmetries are complicated to encode into machine learning algorithms. In this paper, we present a machine learning approach based on graph theory that naturallymore » incorporates translation, rotation, and permutation symmetries. Specifically, we use a random walk graph kernel to measure the similarity of two adjacency matrices, each of which represents a local atomic environment. This Graph Approximated Energy (GRAPE) approach is flexible and admits many possible extensions. Finally, we benchmark a simple version of GRAPE by predicting atomization energies on a standard dataset of organic molecules.« less

Learning molecular energies using localized graph kernels

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ferré, Grégoire; Haut, Terry Scot; Barros, Kipton Marcos

We report that recent machine learning methods make it possible to model potential energy of atomic configurations with chemical-level accuracy (as calculated from ab initio calculations) and at speeds suitable for molecular dynamics simulation. Best performance is achieved when the known physical constraints are encoded in the machine learning models. For example, the atomic energy is invariant under global translations and rotations; it is also invariant to permutations of same-species atoms. Although simple to state, these symmetries are complicated to encode into machine learning algorithms. In this paper, we present a machine learning approach based on graph theory that naturallymore » incorporates translation, rotation, and permutation symmetries. Specifically, we use a random walk graph kernel to measure the similarity of two adjacency matrices, each of which represents a local atomic environment. This Graph Approximated Energy (GRAPE) approach is flexible and admits many possible extensions. Finally, we benchmark a simple version of GRAPE by predicting atomization energies on a standard dataset of organic molecules.« less

Generalization Performance of Regularized Ranking With Multiscale Kernels.

PubMed

Zhou, Yicong; Chen, Hong; Lan, Rushi; Pan, Zhibin

2016-05-01

The regularized kernel method for the ranking problem has attracted increasing attentions in machine learning. The previous regularized ranking algorithms are usually based on reproducing kernel Hilbert spaces with a single kernel. In this paper, we go beyond this framework by investigating the generalization performance of the regularized ranking with multiscale kernels. A novel ranking algorithm with multiscale kernels is proposed and its representer theorem is proved. We establish the upper bound of the generalization error in terms of the complexity of hypothesis spaces. It shows that the multiscale ranking algorithm can achieve satisfactory learning rates under mild conditions. Experiments demonstrate the effectiveness of the proposed method for drug discovery and recommendation tasks.

Stochastic subset selection for learning with kernel machines.

PubMed

Rhinelander, Jason; Liu, Xiaoping P

2012-06-01

Kernel machines have gained much popularity in applications of machine learning. Support vector machines (SVMs) are a subset of kernel machines and generalize well for classification, regression, and anomaly detection tasks. The training procedure for traditional SVMs involves solving a quadratic programming (QP) problem. The QP problem scales super linearly in computational effort with the number of training samples and is often used for the offline batch processing of data. Kernel machines operate by retaining a subset of observed data during training. The data vectors contained within this subset are referred to as support vectors (SVs). The work presented in this paper introduces a subset selection method for the use of kernel machines in online, changing environments. Our algorithm works by using a stochastic indexing technique when selecting a subset of SVs when computing the kernel expansion. The work described here is novel because it separates the selection of kernel basis functions from the training algorithm used. The subset selection algorithm presented here can be used in conjunction with any online training technique. It is important for online kernel machines to be computationally efficient due to the real-time requirements of online environments. Our algorithm is an important contribution because it scales linearly with the number of training samples and is compatible with current training techniques. Our algorithm outperforms standard techniques in terms of computational efficiency and provides increased recognition accuracy in our experiments. We provide results from experiments using both simulated and real-world data sets to verify our algorithm.

Distributed smoothed tree kernel for protein-protein interaction extraction from the biomedical literature

PubMed Central

Murugesan, Gurusamy; Abdulkadhar, Sabenabanu; Natarajan, Jeyakumar

2017-01-01

Automatic extraction of protein-protein interaction (PPI) pairs from biomedical literature is a widely examined task in biological information extraction. Currently, many kernel based approaches such as linear kernel, tree kernel, graph kernel and combination of multiple kernels has achieved promising results in PPI task. However, most of these kernel methods fail to capture the semantic relation information between two entities. In this paper, we present a special type of tree kernel for PPI extraction which exploits both syntactic (structural) and semantic vectors information known as Distributed Smoothed Tree kernel (DSTK). DSTK comprises of distributed trees with syntactic information along with distributional semantic vectors representing semantic information of the sentences or phrases. To generate robust machine learning model composition of feature based kernel and DSTK were combined using ensemble support vector machine (SVM). Five different corpora (AIMed, BioInfer, HPRD50, IEPA, and LLL) were used for evaluating the performance of our system. Experimental results show that our system achieves better f-score with five different corpora compared to other state-of-the-art systems. PMID:29099838

Distributed smoothed tree kernel for protein-protein interaction extraction from the biomedical literature.

PubMed

Murugesan, Gurusamy; Abdulkadhar, Sabenabanu; Natarajan, Jeyakumar

2017-01-01

Automatic extraction of protein-protein interaction (PPI) pairs from biomedical literature is a widely examined task in biological information extraction. Currently, many kernel based approaches such as linear kernel, tree kernel, graph kernel and combination of multiple kernels has achieved promising results in PPI task. However, most of these kernel methods fail to capture the semantic relation information between two entities. In this paper, we present a special type of tree kernel for PPI extraction which exploits both syntactic (structural) and semantic vectors information known as Distributed Smoothed Tree kernel (DSTK). DSTK comprises of distributed trees with syntactic information along with distributional semantic vectors representing semantic information of the sentences or phrases. To generate robust machine learning model composition of feature based kernel and DSTK were combined using ensemble support vector machine (SVM). Five different corpora (AIMed, BioInfer, HPRD50, IEPA, and LLL) were used for evaluating the performance of our system. Experimental results show that our system achieves better f-score with five different corpora compared to other state-of-the-art systems.

Kernel Temporal Differences for Neural Decoding

PubMed Central

Bae, Jihye; Sanchez Giraldo, Luis G.; Pohlmeyer, Eric A.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2015-01-01

We study the feasibility and capability of the kernel temporal difference (KTD)(λ) algorithm for neural decoding. KTD(λ) is an online, kernel-based learning algorithm, which has been introduced to estimate value functions in reinforcement learning. This algorithm combines kernel-based representations with the temporal difference approach to learning. One of our key observations is that by using strictly positive definite kernels, algorithm's convergence can be guaranteed for policy evaluation. The algorithm's nonlinear functional approximation capabilities are shown in both simulations of policy evaluation and neural decoding problems (policy improvement). KTD can handle high-dimensional neural states containing spatial-temporal information at a reasonable computational complexity allowing real-time applications. When the algorithm seeks a proper mapping between a monkey's neural states and desired positions of a computer cursor or a robot arm, in both open-loop and closed-loop experiments, it can effectively learn the neural state to action mapping. Finally, a visualization of the coadaptation process between the decoder and the subject shows the algorithm's capabilities in reinforcement learning brain machine interfaces. PMID:25866504

Design of a multiple kernel learning algorithm for LS-SVM by convex programming.

PubMed

Jian, Ling; Xia, Zhonghang; Liang, Xijun; Gao, Chuanhou

2011-06-01

As a kernel based method, the performance of least squares support vector machine (LS-SVM) depends on the selection of the kernel as well as the regularization parameter (Duan, Keerthi, & Poo, 2003). Cross-validation is efficient in selecting a single kernel and the regularization parameter; however, it suffers from heavy computational cost and is not flexible to deal with multiple kernels. In this paper, we address the issue of multiple kernel learning for LS-SVM by formulating it as semidefinite programming (SDP). Furthermore, we show that the regularization parameter can be optimized in a unified framework with the kernel, which leads to an automatic process for model selection. Extensive experimental validations are performed and analyzed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Improving prediction of heterodimeric protein complexes using combination with pairwise kernel.

PubMed

Ruan, Peiying; Hayashida, Morihiro; Akutsu, Tatsuya; Vert, Jean-Philippe

2018-02-19

Since many proteins become functional only after they interact with their partner proteins and form protein complexes, it is essential to identify the sets of proteins that form complexes. Therefore, several computational methods have been proposed to predict complexes from the topology and structure of experimental protein-protein interaction (PPI) network. These methods work well to predict complexes involving at least three proteins, but generally fail at identifying complexes involving only two different proteins, called heterodimeric complexes or heterodimers. There is however an urgent need for efficient methods to predict heterodimers, since the majority of known protein complexes are precisely heterodimers. In this paper, we use three promising kernel functions, Min kernel and two pairwise kernels, which are Metric Learning Pairwise Kernel (MLPK) and Tensor Product Pairwise Kernel (TPPK). We also consider the normalization forms of Min kernel. Then, we combine Min kernel or its normalization form and one of the pairwise kernels by plugging. We applied kernels based on PPI, domain, phylogenetic profile, and subcellular localization properties to predicting heterodimers. Then, we evaluate our method by employing C-Support Vector Classification (C-SVC), carrying out 10-fold cross-validation, and calculating the average F-measures. The results suggest that the combination of normalized-Min-kernel and MLPK leads to the best F-measure and improved the performance of our previous work, which had been the best existing method so far. We propose new methods to predict heterodimers, using a machine learning-based approach. We train a support vector machine (SVM) to discriminate interacting vs non-interacting protein pairs, based on informations extracted from PPI, domain, phylogenetic profiles and subcellular localization. We evaluate in detail new kernel functions to encode these data, and report prediction performance that outperforms the state-of-the-art.

Optimizing Support Vector Machine Parameters with Genetic Algorithm for Credit Risk Assessment

NASA Astrophysics Data System (ADS)

Manurung, Jonson; Mawengkang, Herman; Zamzami, Elviawaty

2017-12-01

Support vector machine (SVM) is a popular classification method known to have strong generalization capabilities. SVM can solve the problem of classification and linear regression or nonlinear kernel which can be a learning algorithm for the ability of classification and regression. However, SVM also has a weakness that is difficult to determine the optimal parameter value. SVM calculates the best linear separator on the input feature space according to the training data. To classify data which are non-linearly separable, SVM uses kernel tricks to transform the data into a linearly separable data on a higher dimension feature space. The kernel trick using various kinds of kernel functions, such as : linear kernel, polynomial, radial base function (RBF) and sigmoid. Each function has parameters which affect the accuracy of SVM classification. To solve the problem genetic algorithms are proposed to be applied as the optimal parameter value search algorithm thus increasing the best classification accuracy on SVM. Data taken from UCI repository of machine learning database: Australian Credit Approval. The results show that the combination of SVM and genetic algorithms is effective in improving classification accuracy. Genetic algorithms has been shown to be effective in systematically finding optimal kernel parameters for SVM, instead of randomly selected kernel parameters. The best accuracy for data has been upgraded from kernel Linear: 85.12%, polynomial: 81.76%, RBF: 77.22% Sigmoid: 78.70%. However, for bigger data sizes, this method is not practical because it takes a lot of time.

Multiscale asymmetric orthogonal wavelet kernel for linear programming support vector learning and nonlinear dynamic systems identification.

PubMed

Lu, Zhao; Sun, Jing; Butts, Kenneth

2014-05-01

Support vector regression for approximating nonlinear dynamic systems is more delicate than the approximation of indicator functions in support vector classification, particularly for systems that involve multitudes of time scales in their sampled data. The kernel used for support vector learning determines the class of functions from which a support vector machine can draw its solution, and the choice of kernel significantly influences the performance of a support vector machine. In this paper, to bridge the gap between wavelet multiresolution analysis and kernel learning, the closed-form orthogonal wavelet is exploited to construct new multiscale asymmetric orthogonal wavelet kernels for linear programming support vector learning. The closed-form multiscale orthogonal wavelet kernel provides a systematic framework to implement multiscale kernel learning via dyadic dilations and also enables us to represent complex nonlinear dynamics effectively. To demonstrate the superiority of the proposed multiscale wavelet kernel in identifying complex nonlinear dynamic systems, two case studies are presented that aim at building parallel models on benchmark datasets. The development of parallel models that address the long-term/mid-term prediction issue is more intricate and challenging than the identification of series-parallel models where only one-step ahead prediction is required. Simulation results illustrate the effectiveness of the proposed multiscale kernel learning.

Candidate gene prioritization by network analysis of differential expression using machine learning approaches

PubMed Central

2010-01-01

Background Discovering novel disease genes is still challenging for diseases for which no prior knowledge - such as known disease genes or disease-related pathways - is available. Performing genetic studies frequently results in large lists of candidate genes of which only few can be followed up for further investigation. We have recently developed a computational method for constitutional genetic disorders that identifies the most promising candidate genes by replacing prior knowledge by experimental data of differential gene expression between affected and healthy individuals. To improve the performance of our prioritization strategy, we have extended our previous work by applying different machine learning approaches that identify promising candidate genes by determining whether a gene is surrounded by highly differentially expressed genes in a functional association or protein-protein interaction network. Results We have proposed three strategies scoring disease candidate genes relying on network-based machine learning approaches, such as kernel ridge regression, heat kernel, and Arnoldi kernel approximation. For comparison purposes, a local measure based on the expression of the direct neighbors is also computed. We have benchmarked these strategies on 40 publicly available knockout experiments in mice, and performance was assessed against results obtained using a standard procedure in genetics that ranks candidate genes based solely on their differential expression levels (Simple Expression Ranking). Our results showed that our four strategies could outperform this standard procedure and that the best results were obtained using the Heat Kernel Diffusion Ranking leading to an average ranking position of 8 out of 100 genes, an AUC value of 92.3% and an error reduction of 52.8% relative to the standard procedure approach which ranked the knockout gene on average at position 17 with an AUC value of 83.7%. Conclusion In this study we could identify promising candidate genes using network based machine learning approaches even if no knowledge is available about the disease or phenotype. PMID:20840752

Detection of Splice Sites Using Support Vector Machine

NASA Astrophysics Data System (ADS)

Varadwaj, Pritish; Purohit, Neetesh; Arora, Bhumika

Automatic identification and annotation of exon and intron region of gene, from DNA sequences has been an important research area in field of computational biology. Several approaches viz. Hidden Markov Model (HMM), Artificial Intelligence (AI) based machine learning and Digital Signal Processing (DSP) techniques have extensively and independently been used by various researchers to cater this challenging task. In this work, we propose a Support Vector Machine based kernel learning approach for detection of splice sites (the exon-intron boundary) in a gene. Electron-Ion Interaction Potential (EIIP) values of nucleotides have been used for mapping character sequences to corresponding numeric sequences. Radial Basis Function (RBF) SVM kernel is trained using EIIP numeric sequences. Furthermore this was tested on test gene dataset for detection of splice site by window (of 12 residues) shifting. Optimum values of window size, various important parameters of SVM kernel have been optimized for a better accuracy. Receiver Operating Characteristic (ROC) curves have been utilized for displaying the sensitivity rate of the classifier and results showed 94.82% accuracy for splice site detection on test dataset.

Ranking support vector machine for multiple kernels output combination in protein-protein interaction extraction from biomedical literature.

PubMed

Yang, Zhihao; Lin, Yuan; Wu, Jiajin; Tang, Nan; Lin, Hongfei; Li, Yanpeng

2011-10-01

Knowledge about protein-protein interactions (PPIs) unveils the molecular mechanisms of biological processes. However, the volume and content of published biomedical literature on protein interactions is expanding rapidly, making it increasingly difficult for interaction database curators to detect and curate protein interaction information manually. We present a multiple kernel learning-based approach for automatic PPI extraction from biomedical literature. The approach combines the following kernels: feature-based, tree, and graph and combines their output with Ranking support vector machine (SVM). Experimental evaluations show that the features in individual kernels are complementary and the kernel combined with Ranking SVM achieves better performance than those of the individual kernels, equal weight combination and optimal weight combination. Our approach can achieve state-of-the-art performance with respect to the comparable evaluations, with 64.88% F-score and 88.02% AUC on the AImed corpus. Copyright © 2011 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

CW-SSIM kernel based random forest for image classification

NASA Astrophysics Data System (ADS)

Fan, Guangzhe; Wang, Zhou; Wang, Jiheng

2010-07-01

Complex wavelet structural similarity (CW-SSIM) index has been proposed as a powerful image similarity metric that is robust to translation, scaling and rotation of images, but how to employ it in image classification applications has not been deeply investigated. In this paper, we incorporate CW-SSIM as a kernel function into a random forest learning algorithm. This leads to a novel image classification approach that does not require a feature extraction or dimension reduction stage at the front end. We use hand-written digit recognition as an example to demonstrate our algorithm. We compare the performance of the proposed approach with random forest learning based on other kernels, including the widely adopted Gaussian and the inner product kernels. Empirical evidences show that the proposed method is superior in its classification power. We also compared our proposed approach with the direct random forest method without kernel and the popular kernel-learning method support vector machine. Our test results based on both simulated and realworld data suggest that the proposed approach works superior to traditional methods without the feature selection procedure.

A Novel Weighted Kernel PCA-Based Method for Optimization and Uncertainty Quantification

NASA Astrophysics Data System (ADS)

Thimmisetty, C.; Talbot, C.; Chen, X.; Tong, C. H.

2016-12-01

It has been demonstrated that machine learning methods can be successfully applied to uncertainty quantification for geophysical systems through the use of the adjoint method coupled with kernel PCA-based optimization. In addition, it has been shown through weighted linear PCA how optimization with respect to both observation weights and feature space control variables can accelerate convergence of such methods. Linear machine learning methods, however, are inherently limited in their ability to represent features of non-Gaussian stochastic random fields, as they are based on only the first two statistical moments of the original data. Nonlinear spatial relationships and multipoint statistics leading to the tortuosity characteristic of channelized media, for example, are captured only to a limited extent by linear PCA. With the aim of coupling the kernel-based and weighted methods discussed, we present a novel mathematical formulation of kernel PCA, Weighted Kernel Principal Component Analysis (WKPCA), that both captures nonlinear relationships and incorporates the attribution of significance levels to different realizations of the stochastic random field of interest. We also demonstrate how new instantiations retaining defining characteristics of the random field can be generated using Bayesian methods. In particular, we present a novel WKPCA-based optimization method that minimizes a given objective function with respect to both feature space random variables and observation weights through which optimal snapshot significance levels and optimal features are learned. We showcase how WKPCA can be applied to nonlinear optimal control problems involving channelized media, and in particular demonstrate an application of the method to learning the spatial distribution of material parameter values in the context of linear elasticity, and discuss further extensions of the method to stochastic inversion.

Deep neural mapping support vector machines.

PubMed

Li, Yujian; Zhang, Ting

2017-09-01

The choice of kernel has an important effect on the performance of a support vector machine (SVM). The effect could be reduced by NEUROSVM, an architecture using multilayer perceptron for feature extraction and SVM for classification. In binary classification, a general linear kernel NEUROSVM can be theoretically simplified as an input layer, many hidden layers, and an SVM output layer. As a feature extractor, the sub-network composed of the input and hidden layers is first trained together with a virtual ordinary output layer by backpropagation, then with the output of its last hidden layer taken as input of the SVM classifier for further training separately. By taking the sub-network as a kernel mapping from the original input space into a feature space, we present a novel model, called deep neural mapping support vector machine (DNMSVM), from the viewpoint of deep learning. This model is also a new and general kernel learning method, where the kernel mapping is indeed an explicit function expressed as a sub-network, different from an implicit function induced by a kernel function traditionally. Moreover, we exploit a two-stage procedure of contrastive divergence learning and gradient descent for DNMSVM to jointly training an adaptive kernel mapping instead of a kernel function, without requirement of kernel tricks. As a whole of the sub-network and the SVM classifier, the joint training of DNMSVM is done by using gradient descent to optimize the objective function with the sub-network layer-wise pre-trained via contrastive divergence learning of restricted Boltzmann machines. Compared to the separate training of NEUROSVM, the joint training is a new algorithm for DNMSVM to have advantages over NEUROSVM. Experimental results show that DNMSVM can outperform NEUROSVM and RBFSVM (i.e., SVM with the kernel of radial basis function), demonstrating its effectiveness. Copyright © 2017 Elsevier Ltd. All rights reserved.

A low cost implementation of multi-parameter patient monitor using intersection kernel support vector machine classifier

NASA Astrophysics Data System (ADS)

Mohan, Dhanya; Kumar, C. Santhosh

2016-03-01

Predicting the physiological condition (normal/abnormal) of a patient is highly desirable to enhance the quality of health care. Multi-parameter patient monitors (MPMs) using heart rate, arterial blood pressure, respiration rate and oxygen saturation (S pO2) as input parameters were developed to monitor the condition of patients, with minimum human resource utilization. The Support vector machine (SVM), an advanced machine learning approach popularly used for classification and regression is used for the realization of MPMs. For making MPMs cost effective, we experiment on the hardware implementation of the MPM using support vector machine classifier. The training of the system is done using the matlab environment and the detection of the alarm/noalarm condition is implemented in hardware. We used different kernels for SVM classification and note that the best performance was obtained using intersection kernel SVM (IKSVM). The intersection kernel support vector machine classifier MPM has outperformed the best known MPM using radial basis function kernel by an absoute improvement of 2.74% in accuracy, 1.86% in sensitivity and 3.01% in specificity. The hardware model was developed based on the improved performance system using Verilog Hardware Description Language and was implemented on Altera cyclone-II development board.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine.

PubMed

Shang, Qiang; Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine

PubMed Central

Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust. PMID:27551829

Interaction with Machine Improvisation

NASA Astrophysics Data System (ADS)

Assayag, Gerard; Bloch, George; Cont, Arshia; Dubnov, Shlomo

We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive computer environment. In the second framework, the stylistic interaction is delegated to machine intelligence and therefore, knowledge propagation and decision are taken care of by the computer alone. The first framework involves a hybrid architecture using two popular composition/performance environments, Max and OpenMusic, that are put to work and communicate together, each one handling the process at a different time/memory scale. The second framework shares the same representational schemes with the first but uses an Active Learning architecture based on collaborative, competitive and memory-based learning to handle stylistic interactions. Both systems are capable of processing real-time audio/video as well as MIDI. After discussing the general cognitive background of improvisation practices, the statistical modelling tools and the concurrent agent architecture are presented. Then, an Active Learning scheme is described and considered in terms of using different improvisation regimes for improvisation planning. Finally, we provide more details about the different system implementations and describe several performances with the system.

Metabolic network prediction through pairwise rational kernels.

PubMed

Roche-Lima, Abiel; Domaratzki, Michael; Fristensky, Brian

2014-09-26

Metabolic networks are represented by the set of metabolic pathways. Metabolic pathways are a series of biochemical reactions, in which the product (output) from one reaction serves as the substrate (input) to another reaction. Many pathways remain incompletely characterized. One of the major challenges of computational biology is to obtain better models of metabolic pathways. Existing models are dependent on the annotation of the genes. This propagates error accumulation when the pathways are predicted by incorrectly annotated genes. Pairwise classification methods are supervised learning methods used to classify new pair of entities. Some of these classification methods, e.g., Pairwise Support Vector Machines (SVMs), use pairwise kernels. Pairwise kernels describe similarity measures between two pairs of entities. Using pairwise kernels to handle sequence data requires long processing times and large storage. Rational kernels are kernels based on weighted finite-state transducers that represent similarity measures between sequences or automata. They have been effectively used in problems that handle large amount of sequence information such as protein essentiality, natural language processing and machine translations. We create a new family of pairwise kernels using weighted finite-state transducers (called Pairwise Rational Kernel (PRK)) to predict metabolic pathways from a variety of biological data. PRKs take advantage of the simpler representations and faster algorithms of transducers. Because raw sequence data can be used, the predictor model avoids the errors introduced by incorrect gene annotations. We then developed several experiments with PRKs and Pairwise SVM to validate our methods using the metabolic network of Saccharomyces cerevisiae. As a result, when PRKs are used, our method executes faster in comparison with other pairwise kernels. Also, when we use PRKs combined with other simple kernels that include evolutionary information, the accuracy values have been improved, while maintaining lower construction and execution times. The power of using kernels is that almost any sort of data can be represented using kernels. Therefore, completely disparate types of data can be combined to add power to kernel-based machine learning methods. When we compared our proposal using PRKs with other similar kernel, the execution times were decreased, with no compromise of accuracy. We also proved that by combining PRKs with other kernels that include evolutionary information, the accuracy can also also be improved. As our proposal can use any type of sequence data, genes do not need to be properly annotated, avoiding accumulation errors because of incorrect previous annotations.

Predicting activity approach based on new atoms similarity kernel function.

PubMed

Abu El-Atta, Ahmed H; Moussa, M I; Hassanien, Aboul Ella

2015-07-01

Drug design is a high cost and long term process. To reduce time and costs for drugs discoveries, new techniques are needed. Chemoinformatics field implements the informational techniques and computer science like machine learning and graph theory to discover the chemical compounds properties, such as toxicity or biological activity. This is done through analyzing their molecular structure (molecular graph). To overcome this problem there is an increasing need for algorithms to analyze and classify graph data to predict the activity of molecules. Kernels methods provide a powerful framework which combines machine learning with graph theory techniques. These kernels methods have led to impressive performance results in many several chemoinformatics problems like biological activity prediction. This paper presents a new approach based on kernel functions to solve activity prediction problem for chemical compounds. First we encode all atoms depending on their neighbors then we use these codes to find a relationship between those atoms each other. Then we use relation between different atoms to find similarity between chemical compounds. The proposed approach was compared with many other classification methods and the results show competitive accuracy with these methods. Copyright © 2015 Elsevier Inc. All rights reserved.

Deep kernel learning method for SAR image target recognition

NASA Astrophysics Data System (ADS)

Chen, Xiuyuan; Peng, Xiyuan; Duan, Ran; Li, Junbao

2017-10-01

With the development of deep learning, research on image target recognition has made great progress in recent years. Remote sensing detection urgently requires target recognition for military, geographic, and other scientific research. This paper aims to solve the synthetic aperture radar image target recognition problem by combining deep and kernel learning. The model, which has a multilayer multiple kernel structure, is optimized layer by layer with the parameters of Support Vector Machine and a gradient descent algorithm. This new deep kernel learning method improves accuracy and achieves competitive recognition results compared with other learning methods.

Kernel machines for epilepsy diagnosis via EEG signal classification: a comparative study.

PubMed

Lima, Clodoaldo A M; Coelho, André L V

2011-10-01

We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely, Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). Copyright © 2011 Elsevier B.V. All rights reserved.

A feasibility study of automatic lung nodule detection in chest digital tomosynthesis with machine learning based on support vector machine

NASA Astrophysics Data System (ADS)

Lee, Donghoon; Kim, Ye-seul; Choi, Sunghoon; Lee, Haenghwa; Jo, Byungdu; Choi, Seungyeon; Shin, Jungwook; Kim, Hee-Joung

2017-03-01

The chest digital tomosynthesis(CDT) is recently developed medical device that has several advantage for diagnosing lung disease. For example, CDT provides depth information with relatively low radiation dose compared to computed tomography (CT). However, a major problem with CDT is the image artifacts associated with data incompleteness resulting from limited angle data acquisition in CDT geometry. For this reason, the sensitivity of lung disease was not clear compared to CT. In this study, to improve sensitivity of lung disease detection in CDT, we developed computer aided diagnosis (CAD) systems based on machine learning. For design CAD systems, we used 100 cases of lung nodules cropped images and 100 cases of normal lesion cropped images acquired by lung man phantoms and proto type CDT. We used machine learning techniques based on support vector machine and Gabor filter. The Gabor filter was used for extracting characteristics of lung nodules and we compared performance of feature extraction of Gabor filter with various scale and orientation parameters. We used 3, 4, 5 scales and 4, 6, 8 orientations. After extracting features, support vector machine (SVM) was used for classifying feature of lesions. The linear, polynomial and Gaussian kernels of SVM were compared to decide the best SVM conditions for CDT reconstruction images. The results of CAD system with machine learning showed the capability of automatically lung lesion detection. Furthermore detection performance was the best when Gabor filter with 5 scale and 8 orientation and SVM with Gaussian kernel were used. In conclusion, our suggested CAD system showed improving sensitivity of lung lesion detection in CDT and decide Gabor filter and SVM conditions to achieve higher detection performance of our developed CAD system for CDT.

Automated discrimination of dementia spectrum disorders using extreme learning machine and structural T1 MRI features.

PubMed

Jongin Kim; Boreom Lee

2017-07-01

The classification of neuroimaging data for the diagnosis of Alzheimer's Disease (AD) is one of the main research goals of the neuroscience and clinical fields. In this study, we performed extreme learning machine (ELM) classifier to discriminate the AD, mild cognitive impairment (MCI) from normal control (NC). We compared the performance of ELM with that of a linear kernel support vector machine (SVM) for 718 structural MRI images from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The data consisted of normal control, MCI converter (MCI-C), MCI non-converter (MCI-NC), and AD. We employed SVM-based recursive feature elimination (RFE-SVM) algorithm to find the optimal subset of features. In this study, we found that the RFE-SVM feature selection approach in combination with ELM shows the superior classification accuracy to that of linear kernel SVM for structural T1 MRI data.

Efficient Multiple Kernel Learning Algorithms Using Low-Rank Representation.

PubMed

Niu, Wenjia; Xia, Kewen; Zu, Baokai; Bai, Jianchuan

2017-01-01

Unlike Support Vector Machine (SVM), Multiple Kernel Learning (MKL) allows datasets to be free to choose the useful kernels based on their distribution characteristics rather than a precise one. It has been shown in the literature that MKL holds superior recognition accuracy compared with SVM, however, at the expense of time consuming computations. This creates analytical and computational difficulties in solving MKL algorithms. To overcome this issue, we first develop a novel kernel approximation approach for MKL and then propose an efficient Low-Rank MKL (LR-MKL) algorithm by using the Low-Rank Representation (LRR). It is well-acknowledged that LRR can reduce dimension while retaining the data features under a global low-rank constraint. Furthermore, we redesign the binary-class MKL as the multiclass MKL based on pairwise strategy. Finally, the recognition effect and efficiency of LR-MKL are verified on the datasets Yale, ORL, LSVT, and Digit. Experimental results show that the proposed LR-MKL algorithm is an efficient kernel weights allocation method in MKL and boosts the performance of MKL largely.

SVM and SVM Ensembles in Breast Cancer Prediction.

PubMed

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers.

SVM and SVM Ensembles in Breast Cancer Prediction

PubMed Central

Huang, Min-Wei; Chen, Chih-Wen; Lin, Wei-Chao; Ke, Shih-Wen; Tsai, Chih-Fong

2017-01-01

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers. PMID:28060807

Kernelized rank learning for personalized drug recommendation.

PubMed

He, Xiao; Folkman, Lukas; Borgwardt, Karsten

2018-03-08

Large-scale screenings of cancer cell lines with detailed molecular profiles against libraries of pharmacological compounds are currently being performed in order to gain a better understanding of the genetic component of drug response and to enhance our ability to recommend therapies given a patient's molecular profile. These comprehensive screens differ from the clinical setting in which (1) medical records only contain the response of a patient to very few drugs, (2) drugs are recommended by doctors based on their expert judgment, and (3) selecting the most promising therapy is often more important than accurately predicting the sensitivity to all potential drugs. Current regression models for drug sensitivity prediction fail to account for these three properties. We present a machine learning approach, named Kernelized Rank Learning (KRL), that ranks drugs based on their predicted effect per cell line (patient), circumventing the difficult problem of precisely predicting the sensitivity to the given drug. Our approach outperforms several state-of-the-art predictors in drug recommendation, particularly if the training dataset is sparse, and generalizes to patient data. Our work phrases personalized drug recommendation as a new type of machine learning problem with translational potential to the clinic. The Python implementation of KRL and scripts for running our experiments are available at https://github.com/BorgwardtLab/Kernelized-Rank-Learning. xiao.he@bsse.ethz.ch, lukas.folkman@bsse.ethz.ch. Supplementary data are available at Bioinformatics online.

Machine learning-based methods for prediction of linear B-cell epitopes.

PubMed

Wang, Hsin-Wei; Pai, Tun-Wen

2014-01-01

B-cell epitope prediction facilitates immunologists in designing peptide-based vaccine, diagnostic test, disease prevention, treatment, and antibody production. In comparison with T-cell epitope prediction, the performance of variable length B-cell epitope prediction is still yet to be satisfied. Fortunately, due to increasingly available verified epitope databases, bioinformaticians could adopt machine learning-based algorithms on all curated data to design an improved prediction tool for biomedical researchers. Here, we have reviewed related epitope prediction papers, especially those for linear B-cell epitope prediction. It should be noticed that a combination of selected propensity scales and statistics of epitope residues with machine learning-based tools formulated a general way for constructing linear B-cell epitope prediction systems. It is also observed from most of the comparison results that the kernel method of support vector machine (SVM) classifier outperformed other machine learning-based approaches. Hence, in this chapter, except reviewing recently published papers, we have introduced the fundamentals of B-cell epitope and SVM techniques. In addition, an example of linear B-cell prediction system based on physicochemical features and amino acid combinations is illustrated in details.

Machine Learning Intermolecular Potentials for 1,3,5-Triamino-2,4,6-trinitrobenzene (TATB) Using Symmetry-Adapted Perturbation Theory

DTIC Science & Technology

2018-04-25

unlimited. NOTICES Disclaimers The findings in this report are not to be construed as an official Department of the Army position unless so...this report, intermolecular potentials for 1,3,5-triamino-2,4,6-trinitrobenzene (TATB) are developed using machine learning techniques. Three...potentials based on support vector regression, kernel ridge regression, and a neural network are fit using symmetry-adapted perturbation theory. The

Molecule kernels: a descriptor- and alignment-free quantitative structure-activity relationship approach.

PubMed

Mohr, Johannes A; Jain, Brijnesh J; Obermayer, Klaus

2008-09-01

Quantitative structure activity relationship (QSAR) analysis is traditionally based on extracting a set of molecular descriptors and using them to build a predictive model. In this work, we propose a QSAR approach based directly on the similarity between the 3D structures of a set of molecules measured by a so-called molecule kernel, which is independent of the spatial prealignment of the compounds. Predictors can be build using the molecule kernel in conjunction with the potential support vector machine (P-SVM), a recently proposed machine learning method for dyadic data. The resulting models make direct use of the structural similarities between the compounds in the test set and a subset of the training set and do not require an explicit descriptor construction. We evaluated the predictive performance of the proposed method on one classification and four regression QSAR datasets and compared its results to the results reported in the literature for several state-of-the-art descriptor-based and 3D QSAR approaches. In this comparison, the proposed molecule kernel method performed better than the other QSAR methods.

Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms.

PubMed

Karthick, P A; Ghosh, Diptasree Maitra; Ramakrishnan, S

2018-02-01

Surface electromyography (sEMG) based muscle fatigue research is widely preferred in sports science and occupational/rehabilitation studies due to its noninvasiveness. However, these signals are complex, multicomponent and highly nonstationary with large inter-subject variations, particularly during dynamic contractions. Hence, time-frequency based machine learning methodologies can improve the design of automated system for these signals. In this work, the analysis based on high-resolution time-frequency methods, namely, Stockwell transform (S-transform), B-distribution (BD) and extended modified B-distribution (EMBD) are proposed to differentiate the dynamic muscle nonfatigue and fatigue conditions. The nonfatigue and fatigue segments of sEMG signals recorded from the biceps brachii of 52 healthy volunteers are preprocessed and subjected to S-transform, BD and EMBD. Twelve features are extracted from each method and prominent features are selected using genetic algorithm (GA) and binary particle swarm optimization (BPSO). Five machine learning algorithms, namely, naïve Bayes, support vector machine (SVM) of polynomial and radial basis kernel, random forest and rotation forests are used for the classification. The results show that all the proposed time-frequency distributions (TFDs) are able to show the nonstationary variations of sEMG signals. Most of the features exhibit statistically significant difference in the muscle fatigue and nonfatigue conditions. The maximum number of features (66%) is reduced by GA and BPSO for EMBD and BD-TFD respectively. The combination of EMBD- polynomial kernel based SVM is found to be most accurate (91% accuracy) in classifying the conditions with the features selected using GA. The proposed methods are found to be capable of handling the nonstationary and multicomponent variations of sEMG signals recorded in dynamic fatiguing contractions. Particularly, the combination of EMBD- polynomial kernel based SVM could be used to detect the dynamic muscle fatigue conditions. Copyright © 2017 Elsevier B.V. All rights reserved.

Identification of Alzheimer's disease and mild cognitive impairment using multimodal sparse hierarchical extreme learning machine.

PubMed

Kim, Jongin; Lee, Boreom

2018-05-07

Different modalities such as structural MRI, FDG-PET, and CSF have complementary information, which is likely to be very useful for diagnosis of AD and MCI. Therefore, it is possible to develop a more effective and accurate AD/MCI automatic diagnosis method by integrating complementary information of different modalities. In this paper, we propose multi-modal sparse hierarchical extreme leaning machine (MSH-ELM). We used volume and mean intensity extracted from 93 regions of interest (ROIs) as features of MRI and FDG-PET, respectively, and used p-tau, t-tau, and Aβ42 as CSF features. In detail, high-level representation was individually extracted from each of MRI, FDG-PET, and CSF using a stacked sparse extreme learning machine auto-encoder (sELM-AE). Then, another stacked sELM-AE was devised to acquire a joint hierarchical feature representation by fusing the high-level representations obtained from each modality. Finally, we classified joint hierarchical feature representation using a kernel-based extreme learning machine (KELM). The results of MSH-ELM were compared with those of conventional ELM, single kernel support vector machine (SK-SVM), multiple kernel support vector machine (MK-SVM) and stacked auto-encoder (SAE). Performance was evaluated through 10-fold cross-validation. In the classification of AD vs. HC and MCI vs. HC problem, the proposed MSH-ELM method showed mean balanced accuracies of 96.10% and 86.46%, respectively, which is much better than those of competing methods. In summary, the proposed algorithm exhibits consistently better performance than SK-SVM, ELM, MK-SVM and SAE in the two binary classification problems (AD vs. HC and MCI vs. HC). © 2018 Wiley Periodicals, Inc.

A Distributed Learning Method for ℓ1-Regularized Kernel Machine over Wireless Sensor Networks

PubMed Central

Ji, Xinrong; Hou, Cuiqin; Hou, Yibin; Gao, Fang; Wang, Shulong

2016-01-01

In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ1 norm regularization (ℓ1-regularized) is investigated, and a novel distributed learning algorithm for the ℓ1-regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost. PMID:27376298

Semisupervised learning using Bayesian interpretation: application to LS-SVM.

PubMed

Adankon, Mathias M; Cheriet, Mohamed; Biem, Alain

2011-04-01

Bayesian reasoning provides an ideal basis for representing and manipulating uncertain knowledge, with the result that many interesting algorithms in machine learning are based on Bayesian inference. In this paper, we use the Bayesian approach with one and two levels of inference to model the semisupervised learning problem and give its application to the successful kernel classifier support vector machine (SVM) and its variant least-squares SVM (LS-SVM). Taking advantage of Bayesian interpretation of LS-SVM, we develop a semisupervised learning algorithm for Bayesian LS-SVM using our approach based on two levels of inference. Experimental results on both artificial and real pattern recognition problems show the utility of our method.

Explaining Support Vector Machines: A Color Based Nomogram

PubMed Central

Van Belle, Vanya; Van Calster, Ben; Van Huffel, Sabine; Suykens, Johan A. K.; Lisboa, Paulo

2016-01-01

Problem setting Support vector machines (SVMs) are very popular tools for classification, regression and other problems. Due to the large choice of kernels they can be applied with, a large variety of data can be analysed using these tools. Machine learning thanks its popularity to the good performance of the resulting models. However, interpreting the models is far from obvious, especially when non-linear kernels are used. Hence, the methods are used as black boxes. As a consequence, the use of SVMs is less supported in areas where interpretability is important and where people are held responsible for the decisions made by models. Objective In this work, we investigate whether SVMs using linear, polynomial and RBF kernels can be explained such that interpretations for model-based decisions can be provided. We further indicate when SVMs can be explained and in which situations interpretation of SVMs is (hitherto) not possible. Here, explainability is defined as the ability to produce the final decision based on a sum of contributions which depend on one single or at most two input variables. Results Our experiments on simulated and real-life data show that explainability of an SVM depends on the chosen parameter values (degree of polynomial kernel, width of RBF kernel and regularization constant). When several combinations of parameter values yield the same cross-validation performance, combinations with a lower polynomial degree or a larger kernel width have a higher chance of being explainable. Conclusions This work summarizes SVM classifiers obtained with linear, polynomial and RBF kernels in a single plot. Linear and polynomial kernels up to the second degree are represented exactly. For other kernels an indication of the reliability of the approximation is presented. The complete methodology is available as an R package and two apps and a movie are provided to illustrate the possibilities offered by the method. PMID:27723811

Study of the convergence behavior of the complex kernel least mean square algorithm.

PubMed

Paul, Thomas K; Ogunfunmi, Tokunbo

2013-09-01

The complex kernel least mean square (CKLMS) algorithm is recently derived and allows for online kernel adaptive learning for complex data. Kernel adaptive methods can be used in finding solutions for neural network and machine learning applications. The derivation of CKLMS involved the development of a modified Wirtinger calculus for Hilbert spaces to obtain the cost function gradient. We analyze the convergence of the CKLMS with different kernel forms for complex data. The expressions obtained enable us to generate theory-predicted mean-square error curves considering the circularity of the complex input signals and their effect on nonlinear learning. Simulations are used for verifying the analysis results.

Fuzzy support vector machine: an efficient rule-based classification technique for microarrays.

PubMed

Hajiloo, Mohsen; Rabiee, Hamid R; Anooshahpour, Mahdi

2013-01-01

The abundance of gene expression microarray data has led to the development of machine learning algorithms applicable for tackling disease diagnosis, disease prognosis, and treatment selection problems. However, these algorithms often produce classifiers with weaknesses in terms of accuracy, robustness, and interpretability. This paper introduces fuzzy support vector machine which is a learning algorithm based on combination of fuzzy classifiers and kernel machines for microarray classification. Experimental results on public leukemia, prostate, and colon cancer datasets show that fuzzy support vector machine applied in combination with filter or wrapper feature selection methods develops a robust model with higher accuracy than the conventional microarray classification models such as support vector machine, artificial neural network, decision trees, k nearest neighbors, and diagonal linear discriminant analysis. Furthermore, the interpretable rule-base inferred from fuzzy support vector machine helps extracting biological knowledge from microarray data. Fuzzy support vector machine as a new classification model with high generalization power, robustness, and good interpretability seems to be a promising tool for gene expression microarray classification.

Support vector machines for nuclear reactor state estimation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zavaljevski, N.; Gross, K. C.

2000-02-14

Validation of nuclear power reactor signals is often performed by comparing signal prototypes with the actual reactor signals. The signal prototypes are often computed based on empirical data. The implementation of an estimation algorithm which can make predictions on limited data is an important issue. A new machine learning algorithm called support vector machines (SVMS) recently developed by Vladimir Vapnik and his coworkers enables a high level of generalization with finite high-dimensional data. The improved generalization in comparison with standard methods like neural networks is due mainly to the following characteristics of the method. The input data space is transformedmore » into a high-dimensional feature space using a kernel function, and the learning problem is formulated as a convex quadratic programming problem with a unique solution. In this paper the authors have applied the SVM method for data-based state estimation in nuclear power reactors. In particular, they implemented and tested kernels developed at Argonne National Laboratory for the Multivariate State Estimation Technique (MSET), a nonlinear, nonparametric estimation technique with a wide range of applications in nuclear reactors. The methodology has been applied to three data sets from experimental and commercial nuclear power reactor applications. The results are promising. The combination of MSET kernels with the SVM method has better noise reduction and generalization properties than the standard MSET algorithm.« less

Kernel-based whole-genome prediction of complex traits: a review.

PubMed

Morota, Gota; Gianola, Daniel

2014-01-01

Prediction of genetic values has been a focus of applied quantitative genetics since the beginning of the 20th century, with renewed interest following the advent of the era of whole genome-enabled prediction. Opportunities offered by the emergence of high-dimensional genomic data fueled by post-Sanger sequencing technologies, especially molecular markers, have driven researchers to extend Ronald Fisher and Sewall Wright's models to confront new challenges. In particular, kernel methods are gaining consideration as a regression method of choice for genome-enabled prediction. Complex traits are presumably influenced by many genomic regions working in concert with others (clearly so when considering pathways), thus generating interactions. Motivated by this view, a growing number of statistical approaches based on kernels attempt to capture non-additive effects, either parametrically or non-parametrically. This review centers on whole-genome regression using kernel methods applied to a wide range of quantitative traits of agricultural importance in animals and plants. We discuss various kernel-based approaches tailored to capturing total genetic variation, with the aim of arriving at an enhanced predictive performance in the light of available genome annotation information. Connections between prediction machines born in animal breeding, statistics, and machine learning are revisited, and their empirical prediction performance is discussed. Overall, while some encouraging results have been obtained with non-parametric kernels, recovering non-additive genetic variation in a validation dataset remains a challenge in quantitative genetics.

Reduced multiple empirical kernel learning machine.

PubMed

Wang, Zhe; Lu, MingZhe; Gao, Daqi

2015-02-01

Multiple kernel learning (MKL) is demonstrated to be flexible and effective in depicting heterogeneous data sources since MKL can introduce multiple kernels rather than a single fixed kernel into applications. However, MKL would get a high time and space complexity in contrast to single kernel learning, which is not expected in real-world applications. Meanwhile, it is known that the kernel mapping ways of MKL generally have two forms including implicit kernel mapping and empirical kernel mapping (EKM), where the latter is less attracted. In this paper, we focus on the MKL with the EKM, and propose a reduced multiple empirical kernel learning machine named RMEKLM for short. To the best of our knowledge, it is the first to reduce both time and space complexity of the MKL with EKM. Different from the existing MKL, the proposed RMEKLM adopts the Gauss Elimination technique to extract a set of feature vectors, which is validated that doing so does not lose much information of the original feature space. Then RMEKLM adopts the extracted feature vectors to span a reduced orthonormal subspace of the feature space, which is visualized in terms of the geometry structure. It can be demonstrated that the spanned subspace is isomorphic to the original feature space, which means that the dot product of two vectors in the original feature space is equal to that of the two corresponding vectors in the generated orthonormal subspace. More importantly, the proposed RMEKLM brings a simpler computation and meanwhile needs a less storage space, especially in the processing of testing. Finally, the experimental results show that RMEKLM owns a much efficient and effective performance in terms of both complexity and classification. The contributions of this paper can be given as follows: (1) by mapping the input space into an orthonormal subspace, the geometry of the generated subspace is visualized; (2) this paper first reduces both the time and space complexity of the EKM-based MKL; (3) this paper adopts the Gauss Elimination, one of the on-the-shelf techniques, to generate a basis of the original feature space, which is stable and efficient.

Detection of subjects and brain regions related to Alzheimer's disease using 3D MRI scans based on eigenbrain and machine learning

PubMed Central

Zhang, Yudong; Dong, Zhengchao; Phillips, Preetha; Wang, Shuihua; Ji, Genlin; Yang, Jiquan; Yuan, Ti-Fei

2015-01-01

Purpose: Early diagnosis or detection of Alzheimer's disease (AD) from the normal elder control (NC) is very important. However, the computer-aided diagnosis (CAD) was not widely used, and the classification performance did not reach the standard of practical use. We proposed a novel CAD system for MR brain images based on eigenbrains and machine learning with two goals: accurate detection of both AD subjects and AD-related brain regions. Method: First, we used maximum inter-class variance (ICV) to select key slices from 3D volumetric data. Second, we generated an eigenbrain set for each subject. Third, the most important eigenbrain (MIE) was obtained by Welch's t-test (WTT). Finally, kernel support-vector-machines with different kernels that were trained by particle swarm optimization, were used to make an accurate prediction of AD subjects. Coefficients of MIE with values higher than 0.98 quantile were highlighted to obtain the discriminant regions that distinguish AD from NC. Results: The experiments showed that the proposed method can predict AD subjects with a competitive performance with existing methods, especially the accuracy of the polynomial kernel (92.36 ± 0.94) was better than the linear kernel of 91.47 ± 1.02 and the radial basis function (RBF) kernel of 86.71 ± 1.93. The proposed eigenbrain-based CAD system detected 30 AD-related brain regions (Anterior Cingulate, Caudate Nucleus, Cerebellum, Cingulate Gyrus, Claustrum, Inferior Frontal Gyrus, Inferior Parietal Lobule, Insula, Lateral Ventricle, Lentiform Nucleus, Lingual Gyrus, Medial Frontal Gyrus, Middle Frontal Gyrus, Middle Occipital Gyrus, Middle Temporal Gyrus, Paracentral Lobule, Parahippocampal Gyrus, Postcentral Gyrus, Posterial Cingulate, Precentral Gyrus, Precuneus, Subcallosal Gyrus, Sub-Gyral, Superior Frontal Gyrus, Superior Parietal Lobule, Superior Temporal Gyrus, Supramarginal Gyrus, Thalamus, Transverse Temporal Gyrus, and Uncus). The results were coherent with existing literatures. Conclusion: The eigenbrain method was effective in AD subject prediction and discriminant brain-region detection in MRI scanning. PMID:26082713

Implementing Kernel Methods Incrementally by Incremental Nonlinear Projection Trick.

PubMed

Kwak, Nojun

2016-05-20

Recently, the nonlinear projection trick (NPT) was introduced enabling direct computation of coordinates of samples in a reproducing kernel Hilbert space. With NPT, any machine learning algorithm can be extended to a kernel version without relying on the so called kernel trick. However, NPT is inherently difficult to be implemented incrementally because an ever increasing kernel matrix should be treated as additional training samples are introduced. In this paper, an incremental version of the NPT (INPT) is proposed based on the observation that the centerization step in NPT is unnecessary. Because the proposed INPT does not change the coordinates of the old data, the coordinates obtained by INPT can directly be used in any incremental methods to implement a kernel version of the incremental methods. The effectiveness of the INPT is shown by applying it to implement incremental versions of kernel methods such as, kernel singular value decomposition, kernel principal component analysis, and kernel discriminant analysis which are utilized for problems of kernel matrix reconstruction, letter classification, and face image retrieval, respectively.

MLViS: A Web Tool for Machine Learning-Based Virtual Screening in Early-Phase of Drug Discovery and Development

PubMed Central

Korkmaz, Selcuk; Zararsiz, Gokmen; Goksuluk, Dincer

2015-01-01

Virtual screening is an important step in early-phase of drug discovery process. Since there are thousands of compounds, this step should be both fast and effective in order to distinguish drug-like and nondrug-like molecules. Statistical machine learning methods are widely used in drug discovery studies for classification purpose. Here, we aim to develop a new tool, which can classify molecules as drug-like and nondrug-like based on various machine learning methods, including discriminant, tree-based, kernel-based, ensemble and other algorithms. To construct this tool, first, performances of twenty-three different machine learning algorithms are compared by ten different measures, then, ten best performing algorithms have been selected based on principal component and hierarchical cluster analysis results. Besides classification, this application has also ability to create heat map and dendrogram for visual inspection of the molecules through hierarchical cluster analysis. Moreover, users can connect the PubChem database to download molecular information and to create two-dimensional structures of compounds. This application is freely available through www.biosoft.hacettepe.edu.tr/MLViS/. PMID:25928885

Adaptive hidden Markov model-based online learning framework for bearing faulty detection and performance degradation monitoring

NASA Astrophysics Data System (ADS)

Yu, Jianbo

2017-01-01

This study proposes an adaptive-learning-based method for machine faulty detection and health degradation monitoring. The kernel of the proposed method is an "evolving" model that uses an unsupervised online learning scheme, in which an adaptive hidden Markov model (AHMM) is used for online learning the dynamic health changes of machines in their full life. A statistical index is developed for recognizing the new health states in the machines. Those new health states are then described online by adding of new hidden states in AHMM. Furthermore, the health degradations in machines are quantified online by an AHMM-based health index (HI) that measures the similarity between two density distributions that describe the historic and current health states, respectively. When necessary, the proposed method characterizes the distinct operating modes of the machine and can learn online both abrupt as well as gradual health changes. Our method overcomes some drawbacks of the HIs (e.g., relatively low comprehensibility and applicability) based on fixed monitoring models constructed in the offline phase. Results from its application in a bearing life test reveal that the proposed method is effective in online detection and adaptive assessment of machine health degradation. This study provides a useful guide for developing a condition-based maintenance (CBM) system that uses an online learning method without considerable human intervention.

Protein Analysis Meets Visual Word Recognition: A Case for String Kernels in the Brain

ERIC Educational Resources Information Center

Hannagan, Thomas; Grainger, Jonathan

2012-01-01

It has been recently argued that some machine learning techniques known as Kernel methods could be relevant for capturing cognitive and neural mechanisms (Jakel, Scholkopf, & Wichmann, 2009). We point out that "String kernels," initially designed for protein function prediction and spam detection, are virtually identical to one contending proposal…

Spectral methods in machine learning and new strategies for very large datasets

PubMed Central

Belabbas, Mohamed-Ali; Wolfe, Patrick J.

2009-01-01

Spectral methods are of fundamental importance in statistics and machine learning, because they underlie algorithms from classical principal components analysis to more recent approaches that exploit manifold structure. In most cases, the core technical problem can be reduced to computing a low-rank approximation to a positive-definite kernel. For the growing number of applications dealing with very large or high-dimensional datasets, however, the optimal approximation afforded by an exact spectral decomposition is too costly, because its complexity scales as the cube of either the number of training examples or their dimensionality. Motivated by such applications, we present here 2 new algorithms for the approximation of positive-semidefinite kernels, together with error bounds that improve on results in the literature. We approach this problem by seeking to determine, in an efficient manner, the most informative subset of our data relative to the kernel approximation task at hand. This leads to two new strategies based on the Nyström method that are directly applicable to massive datasets. The first of these—based on sampling—leads to a randomized algorithm whereupon the kernel induces a probability distribution on its set of partitions, whereas the latter approach—based on sorting—provides for the selection of a partition in a deterministic way. We detail their numerical implementation and provide simulation results for a variety of representative problems in statistical data analysis, each of which demonstrates the improved performance of our approach relative to existing methods. PMID:19129490

An efficient diagnosis system for Parkinson's disease using kernel-based extreme learning machine with subtractive clustering features weighting approach.

PubMed

Ma, Chao; Ouyang, Jihong; Chen, Hui-Ling; Zhao, Xue-Hua

2014-01-01

A novel hybrid method named SCFW-KELM, which integrates effective subtractive clustering features weighting and a fast classifier kernel-based extreme learning machine (KELM), has been introduced for the diagnosis of PD. In the proposed method, SCFW is used as a data preprocessing tool, which aims at decreasing the variance in features of the PD dataset, in order to further improve the diagnostic accuracy of the KELM classifier. The impact of the type of kernel functions on the performance of KELM has been investigated in detail. The efficiency and effectiveness of the proposed method have been rigorously evaluated against the PD dataset in terms of classification accuracy, sensitivity, specificity, area under the receiver operating characteristic (ROC) curve (AUC), f-measure, and kappa statistics value. Experimental results have demonstrated that the proposed SCFW-KELM significantly outperforms SVM-based, KNN-based, and ELM-based approaches and other methods in the literature and achieved highest classification results reported so far via 10-fold cross validation scheme, with the classification accuracy of 99.49%, the sensitivity of 100%, the specificity of 99.39%, AUC of 99.69%, the f-measure value of 0.9964, and kappa value of 0.9867. Promisingly, the proposed method might serve as a new candidate of powerful methods for the diagnosis of PD with excellent performance.

An Efficient Diagnosis System for Parkinson's Disease Using Kernel-Based Extreme Learning Machine with Subtractive Clustering Features Weighting Approach

PubMed Central

Ma, Chao; Ouyang, Jihong; Chen, Hui-Ling; Zhao, Xue-Hua

2014-01-01

A novel hybrid method named SCFW-KELM, which integrates effective subtractive clustering features weighting and a fast classifier kernel-based extreme learning machine (KELM), has been introduced for the diagnosis of PD. In the proposed method, SCFW is used as a data preprocessing tool, which aims at decreasing the variance in features of the PD dataset, in order to further improve the diagnostic accuracy of the KELM classifier. The impact of the type of kernel functions on the performance of KELM has been investigated in detail. The efficiency and effectiveness of the proposed method have been rigorously evaluated against the PD dataset in terms of classification accuracy, sensitivity, specificity, area under the receiver operating characteristic (ROC) curve (AUC), f-measure, and kappa statistics value. Experimental results have demonstrated that the proposed SCFW-KELM significantly outperforms SVM-based, KNN-based, and ELM-based approaches and other methods in the literature and achieved highest classification results reported so far via 10-fold cross validation scheme, with the classification accuracy of 99.49%, the sensitivity of 100%, the specificity of 99.39%, AUC of 99.69%, the f-measure value of 0.9964, and kappa value of 0.9867. Promisingly, the proposed method might serve as a new candidate of powerful methods for the diagnosis of PD with excellent performance. PMID:25484912

Efficient nonparametric n -body force fields from machine learning

NASA Astrophysics Data System (ADS)

Glielmo, Aldo; Zeni, Claudio; De Vita, Alessandro

2018-05-01

We provide a definition and explicit expressions for n -body Gaussian process (GP) kernels, which can learn any interatomic interaction occurring in a physical system, up to n -body contributions, for any value of n . The series is complete, as it can be shown that the "universal approximator" squared exponential kernel can be written as a sum of n -body kernels. These recipes enable the choice of optimally efficient force models for each target system, as confirmed by extensive testing on various materials. We furthermore describe how the n -body kernels can be "mapped" on equivalent representations that provide database-size-independent predictions and are thus crucially more efficient. We explicitly carry out this mapping procedure for the first nontrivial (three-body) kernel of the series, and we show that this reproduces the GP-predicted forces with meV /Å accuracy while being orders of magnitude faster. These results pave the way to using novel force models (here named "M-FFs") that are computationally as fast as their corresponding standard parametrized n -body force fields, while retaining the nonparametric character, the ease of training and validation, and the accuracy of the best recently proposed machine-learning potentials.

Prototype Vector Machine for Large Scale Semi-Supervised Learning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Zhang, Kai; Kwok, James T.; Parvin, Bahram

2009-04-29

Practicaldataminingrarelyfalls exactlyinto the supervisedlearning scenario. Rather, the growing amount of unlabeled data poses a big challenge to large-scale semi-supervised learning (SSL). We note that the computationalintensivenessofgraph-based SSLarises largely from the manifold or graph regularization, which in turn lead to large models that are dificult to handle. To alleviate this, we proposed the prototype vector machine (PVM), a highlyscalable,graph-based algorithm for large-scale SSL. Our key innovation is the use of"prototypes vectors" for effcient approximation on both the graph-based regularizer and model representation. The choice of prototypes are grounded upon two important criteria: they not only perform effective low-rank approximation of themore » kernel matrix, but also span a model suffering the minimum information loss compared with the complete model. We demonstrate encouraging performance and appealing scaling properties of the PVM on a number of machine learning benchmark data sets.« less

What Would a Graph Look Like in this Layout? A Machine Learning Approach to Large Graph Visualization.

PubMed

Kwon, Oh-Hyun; Crnovrsanin, Tarik; Ma, Kwan-Liu

2018-01-01

Using different methods for laying out a graph can lead to very different visual appearances, with which the viewer perceives different information. Selecting a "good" layout method is thus important for visualizing a graph. The selection can be highly subjective and dependent on the given task. A common approach to selecting a good layout is to use aesthetic criteria and visual inspection. However, fully calculating various layouts and their associated aesthetic metrics is computationally expensive. In this paper, we present a machine learning approach to large graph visualization based on computing the topological similarity of graphs using graph kernels. For a given graph, our approach can show what the graph would look like in different layouts and estimate their corresponding aesthetic metrics. An important contribution of our work is the development of a new framework to design graph kernels. Our experimental study shows that our estimation calculation is considerably faster than computing the actual layouts and their aesthetic metrics. Also, our graph kernels outperform the state-of-the-art ones in both time and accuracy. In addition, we conducted a user study to demonstrate that the topological similarity computed with our graph kernel matches perceptual similarity assessed by human users.

Protein fold recognition using geometric kernel data fusion.

PubMed

Zakeri, Pooya; Jeuris, Ben; Vandebril, Raf; Moreau, Yves

2014-07-01

Various approaches based on features extracted from protein sequences and often machine learning methods have been used in the prediction of protein folds. Finding an efficient technique for integrating these different protein features has received increasing attention. In particular, kernel methods are an interesting class of techniques for integrating heterogeneous data. Various methods have been proposed to fuse multiple kernels. Most techniques for multiple kernel learning focus on learning a convex linear combination of base kernels. In addition to the limitation of linear combinations, working with such approaches could cause a loss of potentially useful information. We design several techniques to combine kernel matrices by taking more involved, geometry inspired means of these matrices instead of convex linear combinations. We consider various sequence-based protein features including information extracted directly from position-specific scoring matrices and local sequence alignment. We evaluate our methods for classification on the SCOP PDB-40D benchmark dataset for protein fold recognition. The best overall accuracy on the protein fold recognition test set obtained by our methods is ∼ 86.7%. This is an improvement over the results of the best existing approach. Moreover, our computational model has been developed by incorporating the functional domain composition of proteins through a hybridization model. It is observed that by using our proposed hybridization model, the protein fold recognition accuracy is further improved to 89.30%. Furthermore, we investigate the performance of our approach on the protein remote homology detection problem by fusing multiple string kernels. The MATLAB code used for our proposed geometric kernel fusion frameworks are publicly available at http://people.cs.kuleuven.be/∼raf.vandebril/homepage/software/geomean.php?menu=5/. © The Author 2014. Published by Oxford University Press.

On the role of cost-sensitive learning in multi-class brain-computer interfaces.

PubMed

Devlaminck, Dieter; Waegeman, Willem; Wyns, Bart; Otte, Georges; Santens, Patrick

2010-06-01

Brain-computer interfaces (BCIs) present an alternative way of communication for people with severe disabilities. One of the shortcomings in current BCI systems, recently put forward in the fourth BCI competition, is the asynchronous detection of motor imagery versus resting state. We investigated this extension to the three-class case, in which the resting state is considered virtually lying between two motor classes, resulting in a large penalty when one motor task is misclassified into the other motor class. We particularly focus on the behavior of different machine-learning techniques and on the role of multi-class cost-sensitive learning in such a context. To this end, four different kernel methods are empirically compared, namely pairwise multi-class support vector machines (SVMs), two cost-sensitive multi-class SVMs and kernel-based ordinal regression. The experimental results illustrate that ordinal regression performs better than the other three approaches when a cost-sensitive performance measure such as the mean-squared error is considered. By contrast, multi-class cost-sensitive learning enables us to control the number of large errors made between two motor tasks.

Gene function prediction with gene interaction networks: a context graph kernel approach.

PubMed

Li, Xin; Chen, Hsinchun; Li, Jiexun; Zhang, Zhu

2010-01-01

Predicting gene functions is a challenge for biologists in the postgenomic era. Interactions among genes and their products compose networks that can be used to infer gene functions. Most previous studies adopt a linkage assumption, i.e., they assume that gene interactions indicate functional similarities between connected genes. In this study, we propose to use a gene's context graph, i.e., the gene interaction network associated with the focal gene, to infer its functions. In a kernel-based machine-learning framework, we design a context graph kernel to capture the information in context graphs. Our experimental study on a testbed of p53-related genes demonstrates the advantage of using indirect gene interactions and shows the empirical superiority of the proposed approach over linkage-assumption-based methods, such as the algorithm to minimize inconsistent connected genes and diffusion kernels.

Machine Learning-based Texture Analysis of Contrast-enhanced MR Imaging to Differentiate between Glioblastoma and Primary Central Nervous System Lymphoma.

PubMed

Kunimatsu, Akira; Kunimatsu, Natsuko; Yasaka, Koichiro; Akai, Hiroyuki; Kamiya, Kouhei; Watadani, Takeyuki; Mori, Harushi; Abe, Osamu

2018-05-16

Although advanced MRI techniques are increasingly available, imaging differentiation between glioblastoma and primary central nervous system lymphoma (PCNSL) is sometimes confusing. We aimed to evaluate the performance of image classification by support vector machine, a method of traditional machine learning, using texture features computed from contrast-enhanced T 1 -weighted images. This retrospective study on preoperative brain tumor MRI included 76 consecutives, initially treated patients with glioblastoma (n = 55) or PCNSL (n = 21) from one institution, consisting of independent training group (n = 60: 44 glioblastomas and 16 PCNSLs) and test group (n = 16: 11 glioblastomas and 5 PCNSLs) sequentially separated by time periods. A total set of 67 texture features was computed on routine contrast-enhanced T 1 -weighted images of the training group, and the top four most discriminating features were selected as input variables to train support vector machine classifiers. These features were then evaluated on the test group with subsequent image classification. The area under the receiver operating characteristic curves on the training data was calculated at 0.99 (95% confidence interval [CI]: 0.96-1.00) for the classifier with a Gaussian kernel and 0.87 (95% CI: 0.77-0.95) for the classifier with a linear kernel. On the test data, both of the classifiers showed prediction accuracy of 75% (12/16) of the test images. Although further improvement is needed, our preliminary results suggest that machine learning-based image classification may provide complementary diagnostic information on routine brain MRI.

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine

PubMed Central

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam SM, Jahangir

2017-01-01

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems. PMID:28422080

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine.

PubMed

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam Sm, Jahangir

2017-04-19

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems.

Prioritizing individual genetic variants after kernel machine testing using variable selection.

PubMed

He, Qianchuan; Cai, Tianxi; Liu, Yang; Zhao, Ni; Harmon, Quaker E; Almli, Lynn M; Binder, Elisabeth B; Engel, Stephanie M; Ressler, Kerry J; Conneely, Karen N; Lin, Xihong; Wu, Michael C

2016-12-01

Kernel machine learning methods, such as the SNP-set kernel association test (SKAT), have been widely used to test associations between traits and genetic polymorphisms. In contrast to traditional single-SNP analysis methods, these methods are designed to examine the joint effect of a set of related SNPs (such as a group of SNPs within a gene or a pathway) and are able to identify sets of SNPs that are associated with the trait of interest. However, as with many multi-SNP testing approaches, kernel machine testing can draw conclusion only at the SNP-set level, and does not directly inform on which one(s) of the identified SNP set is actually driving the associations. A recently proposed procedure, KerNel Iterative Feature Extraction (KNIFE), provides a general framework for incorporating variable selection into kernel machine methods. In this article, we focus on quantitative traits and relatively common SNPs, and adapt the KNIFE procedure to genetic association studies and propose an approach to identify driver SNPs after the application of SKAT to gene set analysis. Our approach accommodates several kernels that are widely used in SNP analysis, such as the linear kernel and the Identity by State (IBS) kernel. The proposed approach provides practically useful utilities to prioritize SNPs, and fills the gap between SNP set analysis and biological functional studies. Both simulation studies and real data application are used to demonstrate the proposed approach. © 2016 WILEY PERIODICALS, INC.

Signal detection using support vector machines in the presence of ultrasonic speckle

NASA Astrophysics Data System (ADS)

Kotropoulos, Constantine L.; Pitas, Ioannis

2002-04-01

Support Vector Machines are a general algorithm based on guaranteed risk bounds of statistical learning theory. They have found numerous applications, such as in classification of brain PET images, optical character recognition, object detection, face verification, text categorization and so on. In this paper we propose the use of support vector machines to segment lesions in ultrasound images and we assess thoroughly their lesion detection ability. We demonstrate that trained support vector machines with a Radial Basis Function kernel segment satisfactorily (unseen) ultrasound B-mode images as well as clinical ultrasonic images.

A Temperature Compensation Method for Piezo-Resistive Pressure Sensor Utilizing Chaotic Ions Motion Algorithm Optimized Hybrid Kernel LSSVM.

PubMed

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam Sm, Jahangir

2016-10-14

A piezo-resistive pressure sensor is made of silicon, the nature of which is considerably influenced by ambient temperature. The effect of temperature should be eliminated during the working period in expectation of linear output. To deal with this issue, an approach consists of a hybrid kernel Least Squares Support Vector Machine (LSSVM) optimized by a chaotic ions motion algorithm presented. To achieve the learning and generalization for excellent performance, a hybrid kernel function, constructed by a local kernel as Radial Basis Function (RBF) kernel, and a global kernel as polynomial kernel is incorporated into the Least Squares Support Vector Machine. The chaotic ions motion algorithm is introduced to find the best hyper-parameters of the Least Squares Support Vector Machine. The temperature data from a calibration experiment is conducted to validate the proposed method. With attention on algorithm robustness and engineering applications, the compensation result shows the proposed scheme outperforms other compared methods on several performance measures as maximum absolute relative error, minimum absolute relative error mean and variance of the averaged value on fifty runs. Furthermore, the proposed temperature compensation approach lays a foundation for more extensive research.

L2-norm multiple kernel learning and its application to biomedical data fusion

PubMed Central

2010-01-01

Background This paper introduces the notion of optimizing different norms in the dual problem of support vector machines with multiple kernels. The selection of norms yields different extensions of multiple kernel learning (MKL) such as L∞, L1, and L2 MKL. In particular, L2 MKL is a novel method that leads to non-sparse optimal kernel coefficients, which is different from the sparse kernel coefficients optimized by the existing L∞ MKL method. In real biomedical applications, L2 MKL may have more advantages over sparse integration method for thoroughly combining complementary information in heterogeneous data sources. Results We provide a theoretical analysis of the relationship between the L2 optimization of kernels in the dual problem with the L2 coefficient regularization in the primal problem. Understanding the dual L2 problem grants a unified view on MKL and enables us to extend the L2 method to a wide range of machine learning problems. We implement L2 MKL for ranking and classification problems and compare its performance with the sparse L∞ and the averaging L1 MKL methods. The experiments are carried out on six real biomedical data sets and two large scale UCI data sets. L2 MKL yields better performance on most of the benchmark data sets. In particular, we propose a novel L2 MKL least squares support vector machine (LSSVM) algorithm, which is shown to be an efficient and promising classifier for large scale data sets processing. Conclusions This paper extends the statistical framework of genomic data fusion based on MKL. Allowing non-sparse weights on the data sources is an attractive option in settings where we believe most data sources to be relevant to the problem at hand and want to avoid a "winner-takes-all" effect seen in L∞ MKL, which can be detrimental to the performance in prospective studies. The notion of optimizing L2 kernels can be straightforwardly extended to ranking, classification, regression, and clustering algorithms. To tackle the computational burden of MKL, this paper proposes several novel LSSVM based MKL algorithms. Systematic comparison on real data sets shows that LSSVM MKL has comparable performance as the conventional SVM MKL algorithms. Moreover, large scale numerical experiments indicate that when cast as semi-infinite programming, LSSVM MKL can be solved more efficiently than SVM MKL. Availability The MATLAB code of algorithms implemented in this paper is downloadable from http://homes.esat.kuleuven.be/~sistawww/bioi/syu/l2lssvm.html. PMID:20529363

MultiDK: A Multiple Descriptor Multiple Kernel Approach for Molecular Discovery and Its Application to Organic Flow Battery Electrolytes.

PubMed

Kim, Sungjin; Jinich, Adrián; Aspuru-Guzik, Alán

2017-04-24

We propose a multiple descriptor multiple kernel (MultiDK) method for efficient molecular discovery using machine learning. We show that the MultiDK method improves both the speed and accuracy of molecular property prediction. We apply the method to the discovery of electrolyte molecules for aqueous redox flow batteries. Using multiple-type-as opposed to single-type-descriptors, we obtain more relevant features for machine learning. Following the principle of "wisdom of the crowds", the combination of multiple-type descriptors significantly boosts prediction performance. Moreover, by employing multiple kernels-more than one kernel function for a set of the input descriptors-MultiDK exploits nonlinear relations between molecular structure and properties better than a linear regression approach. The multiple kernels consist of a Tanimoto similarity kernel and a linear kernel for a set of binary descriptors and a set of nonbinary descriptors, respectively. Using MultiDK, we achieve an average performance of r 2 = 0.92 with a test set of molecules for solubility prediction. We also extend MultiDK to predict pH-dependent solubility and apply it to a set of quinone molecules with different ionizable functional groups to assess their performance as flow battery electrolytes.

Quantum Support Vector Machine for Big Data Classification

NASA Astrophysics Data System (ADS)

Rebentrost, Patrick; Mohseni, Masoud; Lloyd, Seth

2014-09-01

Supervised machine learning is the classification of new data based on already classified training examples. In this work, we show that the support vector machine, an optimized binary classifier, can be implemented on a quantum computer, with complexity logarithmic in the size of the vectors and the number of training examples. In cases where classical sampling algorithms require polynomial time, an exponential speedup is obtained. At the core of this quantum big data algorithm is a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion of the training data inner-product (kernel) matrix.

Machine-learning in grading of gliomas based on multi-parametric magnetic resonance imaging at 3T.

PubMed

Citak-Er, Fusun; Firat, Zeynep; Kovanlikaya, Ilhami; Ture, Ugur; Ozturk-Isik, Esin

2018-06-15

The objective of this study was to assess the contribution of multi-parametric (mp) magnetic resonance imaging (MRI) quantitative features in the machine learning-based grading of gliomas with a multi-region-of-interests approach. Forty-three patients who were newly diagnosed as having a glioma were included in this study. The patients were scanned prior to any therapy using a standard brain tumor magnetic resonance (MR) imaging protocol that included T1 and T2-weighted, diffusion-weighted, diffusion tensor, MR perfusion and MR spectroscopic imaging. Three different regions-of-interest were drawn for each subject to encompass tumor, immediate tumor periphery, and distant peritumoral edema/normal. The normalized mp-MRI features were used to build machine-learning models for differentiating low-grade gliomas (WHO grades I and II) from high grades (WHO grades III and IV). In order to assess the contribution of regional mp-MRI quantitative features to the classification models, a support vector machine-based recursive feature elimination method was applied prior to classification. A machine-learning model based on support vector machine algorithm with linear kernel achieved an accuracy of 93.0%, a specificity of 86.7%, and a sensitivity of 96.4% for the grading of gliomas using ten-fold cross validation based on the proposed subset of the mp-MRI features. In this study, machine-learning based on multiregional and multi-parametric MRI data has proven to be an important tool in grading glial tumors accurately even in this limited patient population. Future studies are needed to investigate the use of machine learning algorithms for brain tumor classification in a larger patient cohort. Copyright © 2018. Published by Elsevier Ltd.

Parsimonious kernel extreme learning machine in primal via Cholesky factorization.

PubMed

Zhao, Yong-Ping

2016-08-01

Recently, extreme learning machine (ELM) has become a popular topic in machine learning community. By replacing the so-called ELM feature mappings with the nonlinear mappings induced by kernel functions, two kernel ELMs, i.e., P-KELM and D-KELM, are obtained from primal and dual perspectives, respectively. Unfortunately, both P-KELM and D-KELM possess the dense solutions in direct proportion to the number of training data. To this end, a constructive algorithm for P-KELM (CCP-KELM) is first proposed by virtue of Cholesky factorization, in which the training data incurring the largest reductions on the objective function are recruited as significant vectors. To reduce its training cost further, PCCP-KELM is then obtained with the application of a probabilistic speedup scheme into CCP-KELM. Corresponding to CCP-KELM, a destructive P-KELM (CDP-KELM) is presented using a partial Cholesky factorization strategy, where the training data incurring the smallest reductions on the objective function after their removals are pruned from the current set of significant vectors. Finally, to verify the efficacy and feasibility of the proposed algorithms in this paper, experiments on both small and large benchmark data sets are investigated. Copyright © 2016 Elsevier Ltd. All rights reserved.

An Efficient Method Coupling Kernel Principal Component Analysis with Adjoint-Based Optimal Control and Its Goal-Oriented Extensions

NASA Astrophysics Data System (ADS)

Thimmisetty, C.; Talbot, C.; Tong, C. H.; Chen, X.

2016-12-01

The representativeness of available data poses a significant fundamental challenge to the quantification of uncertainty in geophysical systems. Furthermore, the successful application of machine learning methods to geophysical problems involving data assimilation is inherently constrained by the extent to which obtainable data represent the problem considered. We show how the adjoint method, coupled with optimization based on methods of machine learning, can facilitate the minimization of an objective function defined on a space of significantly reduced dimension. By considering uncertain parameters as constituting a stochastic process, the Karhunen-Loeve expansion and its nonlinear extensions furnish an optimal basis with respect to which optimization using L-BFGS can be carried out. In particular, we demonstrate that kernel PCA can be coupled with adjoint-based optimal control methods to successfully determine the distribution of material parameter values for problems in the context of channelized deformable media governed by the equations of linear elasticity. Since certain subsets of the original data are characterized by different features, the convergence rate of the method in part depends on, and may be limited by, the observations used to furnish the kernel principal component basis. By determining appropriate weights for realizations of the stochastic random field, then, one may accelerate the convergence of the method. To this end, we present a formulation of Weighted PCA combined with a gradient-based means using automatic differentiation to iteratively re-weight observations concurrent with the determination of an optimal reduced set control variables in the feature space. We demonstrate how improvements in the accuracy and computational efficiency of the weighted linear method can be achieved over existing unweighted kernel methods, and discuss nonlinear extensions of the algorithm.

A Genetic Algorithm Based Support Vector Machine Model for Blood-Brain Barrier Penetration Prediction

PubMed Central

Zhang, Daqing; Xiao, Jianfeng; Zhou, Nannan; Luo, Xiaomin; Jiang, Hualiang; Chen, Kaixian

2015-01-01

Blood-brain barrier (BBB) is a highly complex physical barrier determining what substances are allowed to enter the brain. Support vector machine (SVM) is a kernel-based machine learning method that is widely used in QSAR study. For a successful SVM model, the kernel parameters for SVM and feature subset selection are the most important factors affecting prediction accuracy. In most studies, they are treated as two independent problems, but it has been proven that they could affect each other. We designed and implemented genetic algorithm (GA) to optimize kernel parameters and feature subset selection for SVM regression and applied it to the BBB penetration prediction. The results show that our GA/SVM model is more accurate than other currently available log BB models. Therefore, to optimize both SVM parameters and feature subset simultaneously with genetic algorithm is a better approach than other methods that treat the two problems separately. Analysis of our log BB model suggests that carboxylic acid group, polar surface area (PSA)/hydrogen-bonding ability, lipophilicity, and molecular charge play important role in BBB penetration. Among those properties relevant to BBB penetration, lipophilicity could enhance the BBB penetration while all the others are negatively correlated with BBB penetration. PMID:26504797

A comparison of graph- and kernel-based -omics data integration algorithms for classifying complex traits.

PubMed

Yan, Kang K; Zhao, Hongyu; Pang, Herbert

2017-12-06

High-throughput sequencing data are widely collected and analyzed in the study of complex diseases in quest of improving human health. Well-studied algorithms mostly deal with single data source, and cannot fully utilize the potential of these multi-omics data sources. In order to provide a holistic understanding of human health and diseases, it is necessary to integrate multiple data sources. Several algorithms have been proposed so far, however, a comprehensive comparison of data integration algorithms for classification of binary traits is currently lacking. In this paper, we focus on two common classes of integration algorithms, graph-based that depict relationships with subjects denoted by nodes and relationships denoted by edges, and kernel-based that can generate a classifier in feature space. Our paper provides a comprehensive comparison of their performance in terms of various measurements of classification accuracy and computation time. Seven different integration algorithms, including graph-based semi-supervised learning, graph sharpening integration, composite association network, Bayesian network, semi-definite programming-support vector machine (SDP-SVM), relevance vector machine (RVM) and Ada-boost relevance vector machine are compared and evaluated with hypertension and two cancer data sets in our study. In general, kernel-based algorithms create more complex models and require longer computation time, but they tend to perform better than graph-based algorithms. The performance of graph-based algorithms has the advantage of being faster computationally. The empirical results demonstrate that composite association network, relevance vector machine, and Ada-boost RVM are the better performers. We provide recommendations on how to choose an appropriate algorithm for integrating data from multiple sources.

Bayesian Kernel Methods for Non-Gaussian Distributions: Binary and Multi-class Classification Problems

DTIC Science & Technology

2013-05-28

those of the support vector machine and relevance vector machine, and the model runs more quickly than the other algorithms . When one class occurs...incremental support vector machine algorithm for online learning when fewer than 50 data points are available. (a) Papers published in peer-reviewed journals...learning environments, where data processing occurs one observation at a time and the classification algorithm improves over time with new

Modeling adaptive kernels from probabilistic phylogenetic trees.

PubMed

Nicotra, Luca; Micheli, Alessio

2009-01-01

Modeling phylogenetic interactions is an open issue in many computational biology problems. In the context of gene function prediction we introduce a class of kernels for structured data leveraging on a hierarchical probabilistic modeling of phylogeny among species. We derive three kernels belonging to this setting: a sufficient statistics kernel, a Fisher kernel, and a probability product kernel. The new kernels are used in the context of support vector machine learning. The kernels adaptivity is obtained through the estimation of the parameters of a tree structured model of evolution using as observed data phylogenetic profiles encoding the presence or absence of specific genes in a set of fully sequenced genomes. We report results obtained in the prediction of the functional class of the proteins of the budding yeast Saccharomyces cerevisae which favorably compare to a standard vector based kernel and to a non-adaptive tree kernel function. A further comparative analysis is performed in order to assess the impact of the different components of the proposed approach. We show that the key features of the proposed kernels are the adaptivity to the input domain and the ability to deal with structured data interpreted through a graphical model representation.

Formation enthalpies for transition metal alloys using machine learning

NASA Astrophysics Data System (ADS)

Ubaru, Shashanka; Miedlar, Agnieszka; Saad, Yousef; Chelikowsky, James R.

2017-06-01

The enthalpy of formation is an important thermodynamic property. Developing fast and accurate methods for its prediction is of practical interest in a variety of applications. Material informatics techniques based on machine learning have recently been introduced in the literature as an inexpensive means of exploiting materials data, and can be used to examine a variety of thermodynamics properties. We investigate the use of such machine learning tools for predicting the formation enthalpies of binary intermetallic compounds that contain at least one transition metal. We consider certain easily available properties of the constituting elements complemented by some basic properties of the compounds, to predict the formation enthalpies. We show how choosing these properties (input features) based on a literature study (using prior physics knowledge) seems to outperform machine learning based feature selection methods such as sensitivity analysis and LASSO (least absolute shrinkage and selection operator) based methods. A nonlinear kernel based support vector regression method is employed to perform the predictions. The predictive ability of our model is illustrated via several experiments on a dataset containing 648 binary alloys. We train and validate the model using the formation enthalpies calculated using a model by Miedema, which is a popular semiempirical model used for the prediction of formation enthalpies of metal alloys.

Protein subcellular localization prediction using multiple kernel learning based support vector machine.

PubMed

Hasan, Md Al Mehedi; Ahmad, Shamim; Molla, Md Khademul Islam

2017-03-28

Predicting the subcellular locations of proteins can provide useful hints that reveal their functions, increase our understanding of the mechanisms of some diseases, and finally aid in the development of novel drugs. As the number of newly discovered proteins has been growing exponentially, which in turns, makes the subcellular localization prediction by purely laboratory tests prohibitively laborious and expensive. In this context, to tackle the challenges, computational methods are being developed as an alternative choice to aid biologists in selecting target proteins and designing related experiments. However, the success of protein subcellular localization prediction is still a complicated and challenging issue, particularly, when query proteins have multi-label characteristics, i.e., if they exist simultaneously in more than one subcellular location or if they move between two or more different subcellular locations. To date, to address this problem, several types of subcellular localization prediction methods with different levels of accuracy have been proposed. The support vector machine (SVM) has been employed to provide potential solutions to the protein subcellular localization prediction problem. However, the practicability of an SVM is affected by the challenges of selecting an appropriate kernel and selecting the parameters of the selected kernel. To address this difficulty, in this study, we aimed to develop an efficient multi-label protein subcellular localization prediction system, named as MKLoc, by introducing multiple kernel learning (MKL) based SVM. We evaluated MKLoc using a combined dataset containing 5447 single-localized proteins (originally published as part of the Höglund dataset) and 3056 multi-localized proteins (originally published as part of the DBMLoc set). Note that this dataset was used by Briesemeister et al. in their extensive comparison of multi-localization prediction systems. Finally, our experimental results indicate that MKLoc not only achieves higher accuracy than a single kernel based SVM system but also shows significantly better results than those obtained from other top systems (MDLoc, BNCs, YLoc+). Moreover, MKLoc requires less computation time to tune and train the system than that required for BNCs and single kernel based SVM.

Monitoring Hitting Load in Tennis Using Inertial Sensors and Machine Learning.

PubMed

Whiteside, David; Cant, Olivia; Connolly, Molly; Reid, Machar

2017-10-01

Quantifying external workload is fundamental to training prescription in sport. In tennis, global positioning data are imprecise and fail to capture hitting loads. The current gold standard (manual notation) is time intensive and often not possible given players' heavy travel schedules. To develop an automated stroke-classification system to help quantify hitting load in tennis. Nineteen athletes wore an inertial measurement unit (IMU) on their wrist during 66 video-recorded training sessions. Video footage was manually notated such that known shot type (serve, rally forehand, slice forehand, forehand volley, rally backhand, slice backhand, backhand volley, smash, or false positive) was associated with the corresponding IMU data for 28,582 shots. Six types of machine-learning models were then constructed to classify true shot type from the IMU signals. Across 10-fold cross-validation, a cubic-kernel support vector machine classified binned shots (overhead, forehand, or backhand) with an accuracy of 97.4%. A second cubic-kernel support vector machine achieved 93.2% accuracy when classifying all 9 shot types. With a view to monitoring external load, the combination of miniature inertial sensors and machine learning offers a practical and automated method of quantifying shot counts and discriminating shot types in elite tennis players.

Many Molecular Properties from One Kernel in Chemical Space

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole

We introduce property-independent kernels for machine learning modeling of arbitrarily many molecular properties. The kernels encode molecular structures for training sets of varying size, as well as similarity measures sufficiently diffuse in chemical space to sample over all training molecules. Corresponding molecular reference properties provided, they enable the instantaneous generation of ML models which can systematically be improved through the addition of more data. This idea is exemplified for single kernel based modeling of internal energy, enthalpy, free energy, heat capacity, polarizability, electronic spread, zero-point vibrational energy, energies of frontier orbitals, HOMOLUMO gap, and the highest fundamental vibrational wavenumber. Modelsmore » of these properties are trained and tested using 112 kilo organic molecules of similar size. Resulting models are discussed as well as the kernels’ use for generating and using other property models.« less

A review on machine learning principles for multi-view biological data integration.

PubMed

Li, Yifeng; Wu, Fang-Xiang; Ngom, Alioune

2018-03-01

Driven by high-throughput sequencing techniques, modern genomic and clinical studies are in a strong need of integrative machine learning models for better use of vast volumes of heterogeneous information in the deep understanding of biological systems and the development of predictive models. How data from multiple sources (called multi-view data) are incorporated in a learning system is a key step for successful analysis. In this article, we provide a comprehensive review on omics and clinical data integration techniques, from a machine learning perspective, for various analyses such as prediction, clustering, dimension reduction and association. We shall show that Bayesian models are able to use prior information and model measurements with various distributions; tree-based methods can either build a tree with all features or collectively make a final decision based on trees learned from each view; kernel methods fuse the similarity matrices learned from individual views together for a final similarity matrix or learning model; network-based fusion methods are capable of inferring direct and indirect associations in a heterogeneous network; matrix factorization models have potential to learn interactions among features from different views; and a range of deep neural networks can be integrated in multi-modal learning for capturing the complex mechanism of biological systems.

Application of kernel method in fluorescence molecular tomography

NASA Astrophysics Data System (ADS)

Zhao, Yue; Baikejiang, Reheman; Li, Changqing

2017-02-01

Reconstruction of fluorescence molecular tomography (FMT) is an ill-posed inverse problem. Anatomical guidance in the FMT reconstruction can improve FMT reconstruction efficiently. We have developed a kernel method to introduce the anatomical guidance into FMT robustly and easily. The kernel method is from machine learning for pattern analysis and is an efficient way to represent anatomical features. For the finite element method based FMT reconstruction, we calculate a kernel function for each finite element node from an anatomical image, such as a micro-CT image. Then the fluorophore concentration at each node is represented by a kernel coefficient vector and the corresponding kernel function. In the FMT forward model, we have a new system matrix by multiplying the sensitivity matrix with the kernel matrix. Thus, the kernel coefficient vector is the unknown to be reconstructed following a standard iterative reconstruction process. We convert the FMT reconstruction problem into the kernel coefficient reconstruction problem. The desired fluorophore concentration at each node can be calculated accordingly. Numerical simulation studies have demonstrated that the proposed kernel-based algorithm can improve the spatial resolution of the reconstructed FMT images. In the proposed kernel method, the anatomical guidance can be obtained directly from the anatomical image and is included in the forward modeling. One of the advantages is that we do not need to segment the anatomical image for the targets and background.

A framework for optimal kernel-based manifold embedding of medical image data.

PubMed

Zimmer, Veronika A; Lekadir, Karim; Hoogendoorn, Corné; Frangi, Alejandro F; Piella, Gemma

2015-04-01

Kernel-based dimensionality reduction is a widely used technique in medical image analysis. To fully unravel the underlying nonlinear manifold the selection of an adequate kernel function and of its free parameters is critical. In practice, however, the kernel function is generally chosen as Gaussian or polynomial and such standard kernels might not always be optimal for a given image dataset or application. In this paper, we present a study on the effect of the kernel functions in nonlinear manifold embedding of medical image data. To this end, we first carry out a literature review on existing advanced kernels developed in the statistics, machine learning, and signal processing communities. In addition, we implement kernel-based formulations of well-known nonlinear dimensional reduction techniques such as Isomap and Locally Linear Embedding, thus obtaining a unified framework for manifold embedding using kernels. Subsequently, we present a method to automatically choose a kernel function and its associated parameters from a pool of kernel candidates, with the aim to generate the most optimal manifold embeddings. Furthermore, we show how the calculated selection measures can be extended to take into account the spatial relationships in images, or used to combine several kernels to further improve the embedding results. Experiments are then carried out on various synthetic and phantom datasets for numerical assessment of the methods. Furthermore, the workflow is applied to real data that include brain manifolds and multispectral images to demonstrate the importance of the kernel selection in the analysis of high-dimensional medical images. Copyright © 2014 Elsevier Ltd. All rights reserved.

Support Vector Machines Trained with Evolutionary Algorithms Employing Kernel Adatron for Large Scale Classification of Protein Structures.

PubMed

Arana-Daniel, Nancy; Gallegos, Alberto A; López-Franco, Carlos; Alanís, Alma Y; Morales, Jacob; López-Franco, Adriana

2016-01-01

With the increasing power of computers, the amount of data that can be processed in small periods of time has grown exponentially, as has the importance of classifying large-scale data efficiently. Support vector machines have shown good results classifying large amounts of high-dimensional data, such as data generated by protein structure prediction, spam recognition, medical diagnosis, optical character recognition and text classification, etc. Most state of the art approaches for large-scale learning use traditional optimization methods, such as quadratic programming or gradient descent, which makes the use of evolutionary algorithms for training support vector machines an area to be explored. The present paper proposes an approach that is simple to implement based on evolutionary algorithms and Kernel-Adatron for solving large-scale classification problems, focusing on protein structure prediction. The functional properties of proteins depend upon their three-dimensional structures. Knowing the structures of proteins is crucial for biology and can lead to improvements in areas such as medicine, agriculture and biofuels.

All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning.

PubMed

Airola, Antti; Pyysalo, Sampo; Björne, Jari; Pahikkala, Tapio; Ginter, Filip; Salakoski, Tapio

2008-11-19

Automated extraction of protein-protein interactions (PPI) is an important and widely studied task in biomedical text mining. We propose a graph kernel based approach for this task. In contrast to earlier approaches to PPI extraction, the introduced all-paths graph kernel has the capability to make use of full, general dependency graphs representing the sentence structure. We evaluate the proposed method on five publicly available PPI corpora, providing the most comprehensive evaluation done for a machine learning based PPI-extraction system. We additionally perform a detailed evaluation of the effects of training and testing on different resources, providing insight into the challenges involved in applying a system beyond the data it was trained on. Our method is shown to achieve state-of-the-art performance with respect to comparable evaluations, with 56.4 F-score and 84.8 AUC on the AImed corpus. We show that the graph kernel approach performs on state-of-the-art level in PPI extraction, and note the possible extension to the task of extracting complex interactions. Cross-corpus results provide further insight into how the learning generalizes beyond individual corpora. Further, we identify several pitfalls that can make evaluations of PPI-extraction systems incomparable, or even invalid. These include incorrect cross-validation strategies and problems related to comparing F-score results achieved on different evaluation resources. Recommendations for avoiding these pitfalls are provided.

Tensor manifold-based extreme learning machine for 2.5-D face recognition

NASA Astrophysics Data System (ADS)

Chong, Lee Ying; Ong, Thian Song; Teoh, Andrew Beng Jin

2018-01-01

We explore the use of the Gabor regional covariance matrix (GRCM), a flexible matrix-based descriptor that embeds the Gabor features in the covariance matrix, as a 2.5-D facial descriptor and an effective means of feature fusion for 2.5-D face recognition problems. Despite its promise, matching is not a trivial problem for GRCM since it is a special instance of a symmetric positive definite (SPD) matrix that resides in non-Euclidean space as a tensor manifold. This implies that GRCM is incompatible with the existing vector-based classifiers and distance matchers. Therefore, we bridge the gap of the GRCM and extreme learning machine (ELM), a vector-based classifier for the 2.5-D face recognition problem. We put forward a tensor manifold-compliant ELM and its two variants by embedding the SPD matrix randomly into reproducing kernel Hilbert space (RKHS) via tensor kernel functions. To preserve the pair-wise distance of the embedded data, we orthogonalize the random-embedded SPD matrix. Hence, classification can be done using a simple ridge regressor, an integrated component of ELM, on the random orthogonal RKHS. Experimental results show that our proposed method is able to improve the recognition performance and further enhance the computational efficiency.

Automatic sleep staging using multi-dimensional feature extraction and multi-kernel fuzzy support vector machine.

PubMed

Zhang, Yanjun; Zhang, Xiangmin; Liu, Wenhui; Luo, Yuxi; Yu, Enjia; Zou, Keju; Liu, Xiaoliang

2014-01-01

This paper employed the clinical Polysomnographic (PSG) data, mainly including all-night Electroencephalogram (EEG), Electrooculogram (EOG) and Electromyogram (EMG) signals of subjects, and adopted the American Academy of Sleep Medicine (AASM) clinical staging manual as standards to realize automatic sleep staging. Authors extracted eighteen different features of EEG, EOG and EMG in time domains and frequency domains to construct the vectors according to the existing literatures as well as clinical experience. By adopting sleep samples self-learning, the linear combination of weights and parameters of multiple kernels of the fuzzy support vector machine (FSVM) were learned and the multi-kernel FSVM (MK-FSVM) was constructed. The overall agreement between the experts' scores and the results presented was 82.53%. Compared with previous results, the accuracy of N1 was improved to some extent while the accuracies of other stages were approximate, which well reflected the sleep structure. The staging algorithm proposed in this paper is transparent, and worth further investigation.

Machine learning with quantum relative entropy

NASA Astrophysics Data System (ADS)

Tsuda, Koji

2009-12-01

Density matrices are a central tool in quantum physics, but it is also used in machine learning. A positive definite matrix called kernel matrix is used to represent the similarities between examples. Positive definiteness assures that the examples are embedded in an Euclidean space. When a positive definite matrix is learned from data, one has to design an update rule that maintains the positive definiteness. Our update rule, called matrix exponentiated gradient update, is motivated by the quantum relative entropy. Notably, the relative entropy is an instance of Bregman divergences, which are asymmetric distance measures specifying theoretical properties of machine learning algorithms. Using the calculus commonly used in quantum physics, we prove an upperbound of the generalization error of online learning.

Approach to explosive hazard detection using sensor fusion and multiple kernel learning with downward-looking GPR and EMI sensor data

NASA Astrophysics Data System (ADS)

Pinar, Anthony; Masarik, Matthew; Havens, Timothy C.; Burns, Joseph; Thelen, Brian; Becker, John

2015-05-01

This paper explores the effectiveness of an anomaly detection algorithm for downward-looking ground penetrating radar (GPR) and electromagnetic inductance (EMI) data. Threat detection with GPR is challenged by high responses to non-target/clutter objects, leading to a large number of false alarms (FAs), and since the responses of target and clutter signatures are so similar, classifier design is not trivial. We suggest a method based on a Run Packing (RP) algorithm to fuse GPR and EMI data into a composite confidence map to improve detection as measured by the area-under-ROC (NAUC) metric. We examine the value of a multiple kernel learning (MKL) support vector machine (SVM) classifier using image features such as histogram of oriented gradients (HOG), local binary patterns (LBP), and local statistics. Experimental results on government furnished data show that use of our proposed fusion and classification methods improves the NAUC when compared with the results from individual sensors and a single kernel SVM classifier.

Dimensional feature weighting utilizing multiple kernel learning for single-channel talker location discrimination using the acoustic transfer function.

PubMed

Takashima, Ryoichi; Takiguchi, Tetsuya; Ariki, Yasuo

2013-02-01

This paper presents a method for discriminating the location of the sound source (talker) using only a single microphone. In a previous work, the single-channel approach for discriminating the location of the sound source was discussed, where the acoustic transfer function from a user's position is estimated by using a hidden Markov model of clean speech in the cepstral domain. In this paper, each cepstral dimension of the acoustic transfer function is newly weighted, in order to obtain the cepstral dimensions having information that is useful for classifying the user's position. Then, this paper proposes a feature-weighting method for the cepstral parameter using multiple kernel learning, defining the base kernels for each cepstral dimension of the acoustic transfer function. The user's position is trained and classified by support vector machine. The effectiveness of this method has been confirmed by sound source (talker) localization experiments performed in different room environments.

fRMSDPred: Predicting Local RMSD Between Structural Fragments Using Sequence Information

DTIC Science & Technology

2007-04-04

machine learning approaches for estimating the RMSD value of a pair of protein fragments. These estimated fragment-level RMSD values can be used to construct the alignment, assess the quality of an alignment, and identify high-quality alignment segments. We present algorithms to solve this fragment-level RMSD prediction problem using a supervised learning framework based on support vector regression and classification that incorporates protein profiles, predicted secondary structure, effective information encoding schemes, and novel second-order pairwise exponential kernel

Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels

NASA Astrophysics Data System (ADS)

Fang, Leyuan; Wang, Chong; Li, Shutao; Yan, Jun; Chen, Xiangdong; Rabbani, Hossein

2017-11-01

We present an automatic method, termed as the principal component analysis network with composite kernel (PCANet-CK), for the classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images. Specifically, the proposed PCANet-CK method first utilizes the PCANet to automatically learn features from each B-scan of the 3-D retinal OCT images. Then, multiple kernels are separately applied to a set of very important features of the B-scans and these kernels are fused together, which can jointly exploit the correlations among features of the 3-D OCT images. Finally, the fused (composite) kernel is incorporated into an extreme learning machine for the OCT image classification. We tested our proposed algorithm on two real 3-D spectral domain OCT (SD-OCT) datasets (of normal subjects and subjects with the macular edema and age-related macular degeneration), which demonstrated its effectiveness.

Compound analysis via graph kernels incorporating chirality.

PubMed

Brown, J B; Urata, Takashi; Tamura, Takeyuki; Arai, Midori A; Kawabata, Takeo; Akutsu, Tatsuya

2010-12-01

High accuracy is paramount when predicting biochemical characteristics using Quantitative Structural-Property Relationships (QSPRs). Although existing graph-theoretic kernel methods combined with machine learning techniques are efficient for QSPR model construction, they cannot distinguish topologically identical chiral compounds which often exhibit different biological characteristics. In this paper, we propose a new method that extends the recently developed tree pattern graph kernel to accommodate stereoisomers. We show that Support Vector Regression (SVR) with a chiral graph kernel is useful for target property prediction by demonstrating its application to a set of human vitamin D receptor ligands currently under consideration for their potential anti-cancer effects.

Oversampling the Minority Class in the Feature Space.

PubMed

Perez-Ortiz, Maria; Gutierrez, Pedro Antonio; Tino, Peter; Hervas-Martinez, Cesar

2016-09-01

The imbalanced nature of some real-world data is one of the current challenges for machine learning researchers. One common approach oversamples the minority class through convex combination of its patterns. We explore the general idea of synthetic oversampling in the feature space induced by a kernel function (as opposed to input space). If the kernel function matches the underlying problem, the classes will be linearly separable and synthetically generated patterns will lie on the minority class region. Since the feature space is not directly accessible, we use the empirical feature space (EFS) (a Euclidean space isomorphic to the feature space) for oversampling purposes. The proposed method is framed in the context of support vector machines, where the imbalanced data sets can pose a serious hindrance. The idea is investigated in three scenarios: 1) oversampling in the full and reduced-rank EFSs; 2) a kernel learning technique maximizing the data class separation to study the influence of the feature space structure (implicitly defined by the kernel function); and 3) a unified framework for preferential oversampling that spans some of the previous approaches in the literature. We support our investigation with extensive experiments over 50 imbalanced data sets.

Analyzing Kernel Matrices for the Identification of Differentially Expressed Genes

PubMed Central

Xia, Xiao-Lei; Xing, Huanlai; Liu, Xueqin

2013-01-01

One of the most important applications of microarray data is the class prediction of biological samples. For this purpose, statistical tests have often been applied to identify the differentially expressed genes (DEGs), followed by the employment of the state-of-the-art learning machines including the Support Vector Machines (SVM) in particular. The SVM is a typical sample-based classifier whose performance comes down to how discriminant samples are. However, DEGs identified by statistical tests are not guaranteed to result in a training dataset composed of discriminant samples. To tackle this problem, a novel gene ranking method namely the Kernel Matrix Gene Selection (KMGS) is proposed. The rationale of the method, which roots in the fundamental ideas of the SVM algorithm, is described. The notion of ''the separability of a sample'' which is estimated by performing -like statistics on each column of the kernel matrix, is first introduced. The separability of a classification problem is then measured, from which the significance of a specific gene is deduced. Also described is a method of Kernel Matrix Sequential Forward Selection (KMSFS) which shares the KMGS method's essential ideas but proceeds in a greedy manner. On three public microarray datasets, our proposed algorithms achieved noticeably competitive performance in terms of the B.632+ error rate. PMID:24349110

An Adaptive Genetic Association Test Using Double Kernel Machines.

PubMed

Zhan, Xiang; Epstein, Michael P; Ghosh, Debashis

2015-10-01

Recently, gene set-based approaches have become very popular in gene expression profiling studies for assessing how genetic variants are related to disease outcomes. Since most genes are not differentially expressed, existing pathway tests considering all genes within a pathway suffer from considerable noise and power loss. Moreover, for a differentially expressed pathway, it is of interest to select important genes that drive the effect of the pathway. In this article, we propose an adaptive association test using double kernel machines (DKM), which can both select important genes within the pathway as well as test for the overall genetic pathway effect. This DKM procedure first uses the garrote kernel machines (GKM) test for the purposes of subset selection and then the least squares kernel machine (LSKM) test for testing the effect of the subset of genes. An appealing feature of the kernel machine framework is that it can provide a flexible and unified method for multi-dimensional modeling of the genetic pathway effect allowing for both parametric and nonparametric components. This DKM approach is illustrated with application to simulated data as well as to data from a neuroimaging genetics study.

Distance Metric Learning via Iterated Support Vector Machines.

PubMed

Zuo, Wangmeng; Wang, Faqiang; Zhang, David; Lin, Liang; Huang, Yuchi; Meng, Deyu; Zhang, Lei

2017-07-11

Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification. Metric learning is often formulated as a convex or nonconvex optimization problem, while most existing methods are based on customized optimizers and become inefficient for large scale problems. In this paper, we formulate metric learning as a kernel classification problem with the positive semi-definite constraint, and solve it by iterated training of support vector machines (SVMs). The new formulation is easy to implement and efficient in training with the off-the-shelf SVM solvers. Two novel metric learning models, namely Positive-semidefinite Constrained Metric Learning (PCML) and Nonnegative-coefficient Constrained Metric Learning (NCML), are developed. Both PCML and NCML can guarantee the global optimality of their solutions. Experiments are conducted on general classification, face verification and person re-identification to evaluate our methods. Compared with the state-of-the-art approaches, our methods can achieve comparable classification accuracy and are efficient in training.

Approximate kernel competitive learning.

PubMed

Wu, Jian-Sheng; Zheng, Wei-Shi; Lai, Jian-Huang

2015-03-01

Kernel competitive learning has been successfully used to achieve robust clustering. However, kernel competitive learning (KCL) is not scalable for large scale data processing, because (1) it has to calculate and store the full kernel matrix that is too large to be calculated and kept in the memory and (2) it cannot be computed in parallel. In this paper we develop a framework of approximate kernel competitive learning for processing large scale dataset. The proposed framework consists of two parts. First, it derives an approximate kernel competitive learning (AKCL), which learns kernel competitive learning in a subspace via sampling. We provide solid theoretical analysis on why the proposed approximation modelling would work for kernel competitive learning, and furthermore, we show that the computational complexity of AKCL is largely reduced. Second, we propose a pseudo-parallelled approximate kernel competitive learning (PAKCL) based on a set-based kernel competitive learning strategy, which overcomes the obstacle of using parallel programming in kernel competitive learning and significantly accelerates the approximate kernel competitive learning for large scale clustering. The empirical evaluation on publicly available datasets shows that the proposed AKCL and PAKCL can perform comparably as KCL, with a large reduction on computational cost. Also, the proposed methods achieve more effective clustering performance in terms of clustering precision against related approximate clustering approaches. Copyright © 2014 Elsevier Ltd. All rights reserved.

Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials

NASA Astrophysics Data System (ADS)

Imbalzano, Giulio; Anelli, Andrea; Giofré, Daniele; Klees, Sinja; Behler, Jörg; Ceriotti, Michele

2018-06-01

Machine learning of atomic-scale properties is revolutionizing molecular modeling, making it possible to evaluate inter-atomic potentials with first-principles accuracy, at a fraction of the costs. The accuracy, speed, and reliability of machine learning potentials, however, depend strongly on the way atomic configurations are represented, i.e., the choice of descriptors used as input for the machine learning method. The raw Cartesian coordinates are typically transformed in "fingerprints," or "symmetry functions," that are designed to encode, in addition to the structure, important properties of the potential energy surface like its invariances with respect to rotation, translation, and permutation of like atoms. Here we discuss automatic protocols to select a number of fingerprints out of a large pool of candidates, based on the correlations that are intrinsic to the training data. This procedure can greatly simplify the construction of neural network potentials that strike the best balance between accuracy and computational efficiency and has the potential to accelerate by orders of magnitude the evaluation of Gaussian approximation potentials based on the smooth overlap of atomic positions kernel. We present applications to the construction of neural network potentials for water and for an Al-Mg-Si alloy and to the prediction of the formation energies of small organic molecules using Gaussian process regression.

A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease.

PubMed

Peng, Bo; Wang, Suhong; Zhou, Zhiyong; Liu, Yan; Tong, Baotong; Zhang, Tao; Dai, Yakang

2017-06-09

Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinson's disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinson's Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease. Copyright © 2017 Elsevier B.V. All rights reserved.

Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling

PubMed Central

Cuperlovic-Culf, Miroslava

2018-01-01

Machine learning uses experimental data to optimize clustering or classification of samples or features, or to develop, augment or verify models that can be used to predict behavior or properties of systems. It is expected that machine learning will help provide actionable knowledge from a variety of big data including metabolomics data, as well as results of metabolism models. A variety of machine learning methods has been applied in bioinformatics and metabolism analyses including self-organizing maps, support vector machines, the kernel machine, Bayesian networks or fuzzy logic. To a lesser extent, machine learning has also been utilized to take advantage of the increasing availability of genomics and metabolomics data for the optimization of metabolic network models and their analysis. In this context, machine learning has aided the development of metabolic networks, the calculation of parameters for stoichiometric and kinetic models, as well as the analysis of major features in the model for the optimal application of bioreactors. Examples of this very interesting, albeit highly complex, application of machine learning for metabolism modeling will be the primary focus of this review presenting several different types of applications for model optimization, parameter determination or system analysis using models, as well as the utilization of several different types of machine learning technologies. PMID:29324649

Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling.

PubMed

Cuperlovic-Culf, Miroslava

2018-01-11

Machine learning uses experimental data to optimize clustering or classification of samples or features, or to develop, augment or verify models that can be used to predict behavior or properties of systems. It is expected that machine learning will help provide actionable knowledge from a variety of big data including metabolomics data, as well as results of metabolism models. A variety of machine learning methods has been applied in bioinformatics and metabolism analyses including self-organizing maps, support vector machines, the kernel machine, Bayesian networks or fuzzy logic. To a lesser extent, machine learning has also been utilized to take advantage of the increasing availability of genomics and metabolomics data for the optimization of metabolic network models and their analysis. In this context, machine learning has aided the development of metabolic networks, the calculation of parameters for stoichiometric and kinetic models, as well as the analysis of major features in the model for the optimal application of bioreactors. Examples of this very interesting, albeit highly complex, application of machine learning for metabolism modeling will be the primary focus of this review presenting several different types of applications for model optimization, parameter determination or system analysis using models, as well as the utilization of several different types of machine learning technologies.

A trace ratio maximization approach to multiple kernel-based dimensionality reduction.

PubMed

Jiang, Wenhao; Chung, Fu-lai

2014-01-01

Most dimensionality reduction techniques are based on one metric or one kernel, hence it is necessary to select an appropriate kernel for kernel-based dimensionality reduction. Multiple kernel learning for dimensionality reduction (MKL-DR) has been recently proposed to learn a kernel from a set of base kernels which are seen as different descriptions of data. As MKL-DR does not involve regularization, it might be ill-posed under some conditions and consequently its applications are hindered. This paper proposes a multiple kernel learning framework for dimensionality reduction based on regularized trace ratio, termed as MKL-TR. Our method aims at learning a transformation into a space of lower dimension and a corresponding kernel from the given base kernels among which some may not be suitable for the given data. The solutions for the proposed framework can be found based on trace ratio maximization. The experimental results demonstrate its effectiveness in benchmark datasets, which include text, image and sound datasets, for supervised, unsupervised as well as semi-supervised settings. Copyright © 2013 Elsevier Ltd. All rights reserved.

Support vector machine with a Pearson VII function kernel for discriminating halophilic and non-halophilic proteins.

PubMed

Zhang, Guangya; Ge, Huihua

2013-10-01

Understanding of proteins adaptive to hypersaline environment and identifying them is a challenging task and would help to design stable proteins. Here, we have systematically analyzed the normalized amino acid compositions of 2121 halophilic and 2400 non-halophilic proteins. The results showed that halophilic protein contained more Asp at the expense of Lys, Ile, Cys and Met, fewer small and hydrophobic residues, and showed a large excess of acidic over basic amino acids. Then, we introduce a support vector machine method to discriminate the halophilic and non-halophilic proteins, by using a novel Pearson VII universal function based kernel. In the three validation check methods, it achieved an overall accuracy of 97.7%, 91.7% and 86.9% and outperformed other machine learning algorithms. We also address the influence of protein size on prediction accuracy and found the worse performance for small size proteins might be some significant residues (Cys and Lys) were missing in the proteins. Copyright © 2013 The Authors. Published by Elsevier Ltd.. All rights reserved.

Support Vector Hazards Machine: A Counting Process Framework for Learning Risk Scores for Censored Outcomes.

PubMed

Wang, Yuanjia; Chen, Tianle; Zeng, Donglin

2016-01-01

Learning risk scores to predict dichotomous or continuous outcomes using machine learning approaches has been studied extensively. However, how to learn risk scores for time-to-event outcomes subject to right censoring has received little attention until recently. Existing approaches rely on inverse probability weighting or rank-based regression, which may be inefficient. In this paper, we develop a new support vector hazards machine (SVHM) approach to predict censored outcomes. Our method is based on predicting the counting process associated with the time-to-event outcomes among subjects at risk via a series of support vector machines. Introducing counting processes to represent time-to-event data leads to a connection between support vector machines in supervised learning and hazards regression in standard survival analysis. To account for different at risk populations at observed event times, a time-varying offset is used in estimating risk scores. The resulting optimization is a convex quadratic programming problem that can easily incorporate non-linearity using kernel trick. We demonstrate an interesting link from the profiled empirical risk function of SVHM to the Cox partial likelihood. We then formally show that SVHM is optimal in discriminating covariate-specific hazard function from population average hazard function, and establish the consistency and learning rate of the predicted risk using the estimated risk scores. Simulation studies show improved prediction accuracy of the event times using SVHM compared to existing machine learning methods and standard conventional approaches. Finally, we analyze two real world biomedical study data where we use clinical markers and neuroimaging biomarkers to predict age-at-onset of a disease, and demonstrate superiority of SVHM in distinguishing high risk versus low risk subjects.

An Analysis of the Nonlinear Spectral Mixing of Didymium and Soda-Lime Glass Beads Using Hyperspectral Imagery (HSI) Microscopy

DTIC Science & Technology

2014-05-01

2001). Learning with Kernels: Support Vector Machines , Regularization, Optimization, and Beyond. The MIT Press, Cambridge, MA, 644 p. [26] Banerjee...A., Burlina, P., and Broadwater, J., (2007). A Machine Learning Approach for finding hyperspectral endmembers. Proceedings of the IEEE International... lime glass beads using hyperspectral imagery (HSI) microscopy Ronald G. Resmini1*, Robert S. Rand2, David W. Allen3, and Christopher J. Deloye1

Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems.

PubMed

Grisafi, Andrea; Wilkins, David M; Csányi, Gábor; Ceriotti, Michele

2018-01-19

Statistical learning methods show great promise in providing an accurate prediction of materials and molecular properties, while minimizing the need for computationally demanding electronic structure calculations. The accuracy and transferability of these models are increased significantly by encoding into the learning procedure the fundamental symmetries of rotational and permutational invariance of scalar properties. However, the prediction of tensorial properties requires that the model respects the appropriate geometric transformations, rather than invariance, when the reference frame is rotated. We introduce a formalism that extends existing schemes and makes it possible to perform machine learning of tensorial properties of arbitrary rank, and for general molecular geometries. To demonstrate it, we derive a tensor kernel adapted to rotational symmetry, which is the natural generalization of the smooth overlap of atomic positions kernel commonly used for the prediction of scalar properties at the atomic scale. The performance and generality of the approach is demonstrated by learning the instantaneous response to an external electric field of water oligomers of increasing complexity, from the isolated molecule to the condensed phase.

Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems

NASA Astrophysics Data System (ADS)

Grisafi, Andrea; Wilkins, David M.; Csányi, Gábor; Ceriotti, Michele

2018-01-01

Statistical learning methods show great promise in providing an accurate prediction of materials and molecular properties, while minimizing the need for computationally demanding electronic structure calculations. The accuracy and transferability of these models are increased significantly by encoding into the learning procedure the fundamental symmetries of rotational and permutational invariance of scalar properties. However, the prediction of tensorial properties requires that the model respects the appropriate geometric transformations, rather than invariance, when the reference frame is rotated. We introduce a formalism that extends existing schemes and makes it possible to perform machine learning of tensorial properties of arbitrary rank, and for general molecular geometries. To demonstrate it, we derive a tensor kernel adapted to rotational symmetry, which is the natural generalization of the smooth overlap of atomic positions kernel commonly used for the prediction of scalar properties at the atomic scale. The performance and generality of the approach is demonstrated by learning the instantaneous response to an external electric field of water oligomers of increasing complexity, from the isolated molecule to the condensed phase.

Kernel-imbedded Gaussian processes for disease classification using microarray gene expression data

PubMed Central

Zhao, Xin; Cheung, Leo Wang-Kit

2007-01-01

Background Designing appropriate machine learning methods for identifying genes that have a significant discriminating power for disease outcomes has become more and more important for our understanding of diseases at genomic level. Although many machine learning methods have been developed and applied to the area of microarray gene expression data analysis, the majority of them are based on linear models, which however are not necessarily appropriate for the underlying connection between the target disease and its associated explanatory genes. Linear model based methods usually also bring in false positive significant features more easily. Furthermore, linear model based algorithms often involve calculating the inverse of a matrix that is possibly singular when the number of potentially important genes is relatively large. This leads to problems of numerical instability. To overcome these limitations, a few non-linear methods have recently been introduced to the area. Many of the existing non-linear methods have a couple of critical problems, the model selection problem and the model parameter tuning problem, that remain unsolved or even untouched. In general, a unified framework that allows model parameters of both linear and non-linear models to be easily tuned is always preferred in real-world applications. Kernel-induced learning methods form a class of approaches that show promising potentials to achieve this goal. Results A hierarchical statistical model named kernel-imbedded Gaussian process (KIGP) is developed under a unified Bayesian framework for binary disease classification problems using microarray gene expression data. In particular, based on a probit regression setting, an adaptive algorithm with a cascading structure is designed to find the appropriate kernel, to discover the potentially significant genes, and to make the optimal class prediction accordingly. A Gibbs sampler is built as the core of the algorithm to make Bayesian inferences. Simulation studies showed that, even without any knowledge of the underlying generative model, the KIGP performed very close to the theoretical Bayesian bound not only in the case with a linear Bayesian classifier but also in the case with a very non-linear Bayesian classifier. This sheds light on its broader usability to microarray data analysis problems, especially to those that linear methods work awkwardly. The KIGP was also applied to four published microarray datasets, and the results showed that the KIGP performed better than or at least as well as any of the referred state-of-the-art methods did in all of these cases. Conclusion Mathematically built on the kernel-induced feature space concept under a Bayesian framework, the KIGP method presented in this paper provides a unified machine learning approach to explore both the linear and the possibly non-linear underlying relationship between the target features of a given binary disease classification problem and the related explanatory gene expression data. More importantly, it incorporates the model parameter tuning into the framework. The model selection problem is addressed in the form of selecting a proper kernel type. The KIGP method also gives Bayesian probabilistic predictions for disease classification. These properties and features are beneficial to most real-world applications. The algorithm is naturally robust in numerical computation. The simulation studies and the published data studies demonstrated that the proposed KIGP performs satisfactorily and consistently. PMID:17328811

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

PubMed Central

Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-01-01

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization. PMID:28599282

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features.

PubMed

Zhang, Xin; Yan, Lin-Feng; Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-07-18

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets.

PubMed

Pyo, Sujin; Lee, Jaewook; Cha, Mincheol; Jang, Huisu

2017-01-01

The prediction of the trends of stocks and index prices is one of the important issues to market participants. Investors have set trading or fiscal strategies based on the trends, and considerable research in various academic fields has been studied to forecast financial markets. This study predicts the trends of the Korea Composite Stock Price Index 200 (KOSPI 200) prices using nonparametric machine learning models: artificial neural network, support vector machines with polynomial and radial basis function kernels. In addition, this study states controversial issues and tests hypotheses about the issues. Accordingly, our results are inconsistent with those of the precedent research, which are generally considered to have high prediction performance. Moreover, Google Trends proved that they are not effective factors in predicting the KOSPI 200 index prices in our frameworks. Furthermore, the ensemble methods did not improve the accuracy of the prediction.

Predictability of machine learning techniques to forecast the trends of market index prices: Hypothesis testing for the Korean stock markets

PubMed Central

Pyo, Sujin; Lee, Jaewook; Cha, Mincheol

2017-01-01

The prediction of the trends of stocks and index prices is one of the important issues to market participants. Investors have set trading or fiscal strategies based on the trends, and considerable research in various academic fields has been studied to forecast financial markets. This study predicts the trends of the Korea Composite Stock Price Index 200 (KOSPI 200) prices using nonparametric machine learning models: artificial neural network, support vector machines with polynomial and radial basis function kernels. In addition, this study states controversial issues and tests hypotheses about the issues. Accordingly, our results are inconsistent with those of the precedent research, which are generally considered to have high prediction performance. Moreover, Google Trends proved that they are not effective factors in predicting the KOSPI 200 index prices in our frameworks. Furthermore, the ensemble methods did not improve the accuracy of the prediction. PMID:29136004

Combining Statistical and Geometric Features for Colonic Polyp Detection in CTC Based on Multiple Kernel Learning

PubMed Central

Wang, Shijun; Yao, Jianhua; Petrick, Nicholas; Summers, Ronald M.

2010-01-01

Colon cancer is the second leading cause of cancer-related deaths in the United States. Computed tomographic colonography (CTC) combined with a computer aided detection system provides a feasible approach for improving colonic polyps detection and increasing the use of CTC for colon cancer screening. To distinguish true polyps from false positives, various features extracted from polyp candidates have been proposed. Most of these traditional features try to capture the shape information of polyp candidates or neighborhood knowledge about the surrounding structures (fold, colon wall, etc.). In this paper, we propose a new set of shape descriptors for polyp candidates based on statistical curvature information. These features called histograms of curvature features are rotation, translation and scale invariant and can be treated as complementing existing feature set. Then in order to make full use of the traditional geometric features (defined as group A) and the new statistical features (group B) which are highly heterogeneous, we employed a multiple kernel learning method based on semi-definite programming to learn an optimized classification kernel from the two groups of features. We conducted leave-one-patient-out test on a CTC dataset which contained scans from 66 patients. Experimental results show that a support vector machine (SVM) based on the combined feature set and the semi-definite optimization kernel achieved higher FROC performance compared to SVMs using the two groups of features separately. At a false positive per scan rate of 5, the sensitivity of the SVM using the combined features improved from 0.77 (Group A) and 0.73 (Group B) to 0.83 (p ≤ 0.01). PMID:20953299

Analysis of the performance, emission and combustion characteristics of a turbocharged diesel engine fuelled with Jatropha curcas biodiesel-diesel blends using kernel-based extreme learning machine.

PubMed

Silitonga, Arridina Susan; Hassan, Masjuki Haji; Ong, Hwai Chyuan; Kusumo, Fitranto

2017-11-01

The purpose of this study is to investigate the performance, emission and combustion characteristics of a four-cylinder common-rail turbocharged diesel engine fuelled with Jatropha curcas biodiesel-diesel blends. A kernel-based extreme learning machine (KELM) model is developed in this study using MATLAB software in order to predict the performance, combustion and emission characteristics of the engine. To acquire the data for training and testing the KELM model, the engine speed was selected as the input parameter, whereas the performance, exhaust emissions and combustion characteristics were chosen as the output parameters of the KELM model. The performance, emissions and combustion characteristics predicted by the KELM model were validated by comparing the predicted data with the experimental data. The results show that the coefficient of determination of the parameters is within a range of 0.9805-0.9991 for both the KELM model and the experimental data. The mean absolute percentage error is within a range of 0.1259-2.3838. This study shows that KELM modelling is a useful technique in biodiesel production since it facilitates scientists and researchers to predict the performance, exhaust emissions and combustion characteristics of internal combustion engines with high accuracy.

Classifying Lower Extremity Muscle Fatigue during Walking using Machine Learning and Inertial Sensors

PubMed Central

Zhang, Jian; Lockhart, Thurmon E.; Soangra, Rahul

2013-01-01

Fatigue in lower extremity musculature is associated with decline in postural stability, motor performance and alters normal walking patterns in human subjects. Automated recognition of lower extremity muscle fatigue condition may be advantageous in early detection of fall and injury risks. Supervised machine learning methods such as Support Vector Machines (SVM) have been previously used for classifying healthy and pathological gait patterns and also for separating old and young gait patterns. In this study we explore the classification potential of SVM in recognition of gait patterns utilizing an inertial measurement unit associated with lower extremity muscular fatigue. Both kinematic and kinetic gait patterns of 17 participants (29±11 years) were recorded and analyzed in normal and fatigued state of walking. Lower extremities were fatigued by performance of a squatting exercise until the participants reached 60% of their baseline maximal voluntary exertion level. Feature selection methods were used to classify fatigue and no-fatigue conditions based on temporal and frequency information of the signals. Additionally, influences of three different kernel schemes (i.e., linear, polynomial, and radial basis function) were investigated for SVM classification. The results indicated that lower extremity muscle fatigue condition influenced gait and loading responses. In terms of the SVM classification results, an accuracy of 96% was reached in distinguishing the two gait patterns (fatigue and no-fatigue) within the same subject using the kinematic, time and frequency domain features. It is also found that linear kernel and RBF kernel were equally good to identify intra-individual fatigue characteristics. These results suggest that intra-subject fatigue classification using gait patterns from an inertial sensor holds considerable potential in identifying “at-risk” gait due to muscle fatigue. PMID:24081829

Accurate interatomic force fields via machine learning with covariant kernels

NASA Astrophysics Data System (ADS)

Glielmo, Aldo; Sollich, Peter; De Vita, Alessandro

2017-06-01

We present a novel scheme to accurately predict atomic forces as vector quantities, rather than sets of scalar components, by Gaussian process (GP) regression. This is based on matrix-valued kernel functions, on which we impose the requirements that the predicted force rotates with the target configuration and is independent of any rotations applied to the configuration database entries. We show that such covariant GP kernels can be obtained by integration over the elements of the rotation group SO (d ) for the relevant dimensionality d . Remarkably, in specific cases the integration can be carried out analytically and yields a conservative force field that can be recast into a pair interaction form. Finally, we show that restricting the integration to a summation over the elements of a finite point group relevant to the target system is sufficient to recover an accurate GP. The accuracy of our kernels in predicting quantum-mechanical forces in real materials is investigated by tests on pure and defective Ni, Fe, and Si crystalline systems.

PCA-based polling strategy in machine learning framework for coronary artery disease risk assessment in intravascular ultrasound: A link between carotid and coronary grayscale plaque morphology.

PubMed

Araki, Tadashi; Ikeda, Nobutaka; Shukla, Devarshi; Jain, Pankaj K; Londhe, Narendra D; Shrivastava, Vimal K; Banchhor, Sumit K; Saba, Luca; Nicolaides, Andrew; Shafique, Shoaib; Laird, John R; Suri, Jasjit S

2016-05-01

Percutaneous coronary interventional procedures need advance planning prior to stenting or an endarterectomy. Cardiologists use intravascular ultrasound (IVUS) for screening, risk assessment and stratification of coronary artery disease (CAD). We hypothesize that plaque components are vulnerable to rupture due to plaque progression. Currently, there are no standard grayscale IVUS tools for risk assessment of plaque rupture. This paper presents a novel strategy for risk stratification based on plaque morphology embedded with principal component analysis (PCA) for plaque feature dimensionality reduction and dominant feature selection technique. The risk assessment utilizes 56 grayscale coronary features in a machine learning framework while linking information from carotid and coronary plaque burdens due to their common genetic makeup. This system consists of a machine learning paradigm which uses a support vector machine (SVM) combined with PCA for optimal and dominant coronary artery morphological feature extraction. Carotid artery proven intima-media thickness (cIMT) biomarker is adapted as a gold standard during the training phase of the machine learning system. For the performance evaluation, K-fold cross validation protocol is adapted with 20 trials per fold. For choosing the dominant features out of the 56 grayscale features, a polling strategy of PCA is adapted where the original value of the features is unaltered. Different protocols are designed for establishing the stability and reliability criteria of the coronary risk assessment system (cRAS). Using the PCA-based machine learning paradigm and cross-validation protocol, a classification accuracy of 98.43% (AUC 0.98) with K=10 folds using an SVM radial basis function (RBF) kernel was achieved. A reliability index of 97.32% and machine learning stability criteria of 5% were met for the cRAS. This is the first Computer aided design (CADx) system of its kind that is able to demonstrate the ability of coronary risk assessment and stratification while demonstrating a successful design of the machine learning system based on our assumptions. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels.

PubMed

Fang, Leyuan; Wang, Chong; Li, Shutao; Yan, Jun; Chen, Xiangdong; Rabbani, Hossein

2017-11-01

We present an automatic method, termed as the principal component analysis network with composite kernel (PCANet-CK), for the classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images. Specifically, the proposed PCANet-CK method first utilizes the PCANet to automatically learn features from each B-scan of the 3-D retinal OCT images. Then, multiple kernels are separately applied to a set of very important features of the B-scans and these kernels are fused together, which can jointly exploit the correlations among features of the 3-D OCT images. Finally, the fused (composite) kernel is incorporated into an extreme learning machine for the OCT image classification. We tested our proposed algorithm on two real 3-D spectral domain OCT (SD-OCT) datasets (of normal subjects and subjects with the macular edema and age-related macular degeneration), which demonstrated its effectiveness. (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE).

An Adaptive Genetic Association Test Using Double Kernel Machines

PubMed Central

Zhan, Xiang; Epstein, Michael P.; Ghosh, Debashis

2014-01-01

Recently, gene set-based approaches have become very popular in gene expression profiling studies for assessing how genetic variants are related to disease outcomes. Since most genes are not differentially expressed, existing pathway tests considering all genes within a pathway suffer from considerable noise and power loss. Moreover, for a differentially expressed pathway, it is of interest to select important genes that drive the effect of the pathway. In this article, we propose an adaptive association test using double kernel machines (DKM), which can both select important genes within the pathway as well as test for the overall genetic pathway effect. This DKM procedure first uses the garrote kernel machines (GKM) test for the purposes of subset selection and then the least squares kernel machine (LSKM) test for testing the effect of the subset of genes. An appealing feature of the kernel machine framework is that it can provide a flexible and unified method for multi-dimensional modeling of the genetic pathway effect allowing for both parametric and nonparametric components. This DKM approach is illustrated with application to simulated data as well as to data from a neuroimaging genetics study. PMID:26640602

Classification of Phylogenetic Profiles for Protein Function Prediction: An SVM Approach

NASA Astrophysics Data System (ADS)

Kotaru, Appala Raju; Joshi, Ramesh C.

Predicting the function of an uncharacterized protein is a major challenge in post-genomic era due to problems complexity and scale. Having knowledge of protein function is a crucial link in the development of new drugs, better crops, and even the development of biochemicals such as biofuels. Recently numerous high-throughput experimental procedures have been invented to investigate the mechanisms leading to the accomplishment of a protein’s function and Phylogenetic profile is one of them. Phylogenetic profile is a way of representing a protein which encodes evolutionary history of proteins. In this paper we proposed a method for classification of phylogenetic profiles using supervised machine learning method, support vector machine classification along with radial basis function as kernel for identifying functionally linked proteins. We experimentally evaluated the performance of the classifier with the linear kernel, polynomial kernel and compared the results with the existing tree kernel. In our study we have used proteins of the budding yeast saccharomyces cerevisiae genome. We generated the phylogenetic profiles of 2465 yeast genes and for our study we used the functional annotations that are available in the MIPS database. Our experiments show that the performance of the radial basis kernel is similar to polynomial kernel is some functional classes together are better than linear, tree kernel and over all radial basis kernel outperformed the polynomial kernel, linear kernel and tree kernel. In analyzing these results we show that it will be feasible to make use of SVM classifier with radial basis function as kernel to predict the gene functionality using phylogenetic profiles.

The generalization ability of online SVM classification based on Markov sampling.

PubMed

Xu, Jie; Yan Tang, Yuan; Zou, Bin; Xu, Zongben; Li, Luoqing; Lu, Yang

2015-03-01

In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.

Multiple kernel SVR based on the MRE for remote sensing water depth fusion detection

NASA Astrophysics Data System (ADS)

Wang, Jinjin; Ma, Yi; Zhang, Jingyu

2018-03-01

Remote sensing has an important means of water depth detection in coastal shallow waters and reefs. Support vector regression (SVR) is a machine learning method which is widely used in data regression. In this paper, SVR is used to remote sensing multispectral bathymetry. Aiming at the problem that the single-kernel SVR method has a large error in shallow water depth inversion, the mean relative error (MRE) of different water depth is retrieved as a decision fusion factor with single kernel SVR method, a multi kernel SVR fusion method based on the MRE is put forward. And taking the North Island of the Xisha Islands in China as an experimentation area, the comparison experiments with the single kernel SVR method and the traditional multi-bands bathymetric method are carried out. The results show that: 1) In range of 0 to 25 meters, the mean absolute error(MAE)of the multi kernel SVR fusion method is 1.5m,the MRE is 13.2%; 2) Compared to the 4 single kernel SVR method, the MRE of the fusion method reduced 1.2% (1.9%) 3.4% (1.8%), and compared to traditional multi-bands method, the MRE reduced 1.9%; 3) In 0-5m depth section, compared to the single kernel method and the multi-bands method, the MRE of fusion method reduced 13.5% to 44.4%, and the distribution of points is more concentrated relative to y=x.

Stable Local Volatility Calibration Using Kernel Splines

NASA Astrophysics Data System (ADS)

Coleman, Thomas F.; Li, Yuying; Wang, Cheng

2010-09-01

We propose an optimization formulation using L1 norm to ensure accuracy and stability in calibrating a local volatility function for option pricing. Using a regularization parameter, the proposed objective function balances the calibration accuracy with the model complexity. Motivated by the support vector machine learning, the unknown local volatility function is represented by a kernel function generating splines and the model complexity is controlled by minimizing the 1-norm of the kernel coefficient vector. In the context of the support vector regression for function estimation based on a finite set of observations, this corresponds to minimizing the number of support vectors for predictability. We illustrate the ability of the proposed approach to reconstruct the local volatility function in a synthetic market. In addition, based on S&P 500 market index option data, we demonstrate that the calibrated local volatility surface is simple and resembles the observed implied volatility surface in shape. Stability is illustrated by calibrating local volatility functions using market option data from different dates.

An assessment of support vector machines for land cover classification

USGS Publications Warehouse

Huang, C.; Davis, L.S.; Townshend, J.R.G.

2002-01-01

The support vector machine (SVM) is a group of theoretically superior machine learning algorithms. It was found competitive with the best available machine learning algorithms in classifying high-dimensional data sets. This paper gives an introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classifications from satellite images. The SVM was compared to three other popular classifiers, including the maximum likelihood classifier (MLC), neural network classifiers (NNC) and decision tree classifiers (DTC). The impacts of kernel configuration on the performance of the SVM and of the selection of training data and input variables on the four classifiers were also evaluated in this experiment.

Kernel methods for large-scale genomic data analysis

PubMed Central

Xing, Eric P.; Schaid, Daniel J.

2015-01-01

Machine learning, particularly kernel methods, has been demonstrated as a promising new tool to tackle the challenges imposed by today’s explosive data growth in genomics. They provide a practical and principled approach to learning how a large number of genetic variants are associated with complex phenotypes, to help reveal the complexity in the relationship between the genetic markers and the outcome of interest. In this review, we highlight the potential key role it will have in modern genomic data processing, especially with regard to integration with classical methods for gene prioritizing, prediction and data fusion. PMID:25053743

Kernel Machine SNP-set Testing under Multiple Candidate Kernels

PubMed Central

Wu, Michael C.; Maity, Arnab; Lee, Seunggeun; Simmons, Elizabeth M.; Harmon, Quaker E.; Lin, Xinyi; Engel, Stephanie M.; Molldrem, Jeffrey J.; Armistead, Paul M.

2013-01-01

Joint testing for the cumulative effect of multiple single nucleotide polymorphisms grouped on the basis of prior biological knowledge has become a popular and powerful strategy for the analysis of large scale genetic association studies. The kernel machine (KM) testing framework is a useful approach that has been proposed for testing associations between multiple genetic variants and many different types of complex traits by comparing pairwise similarity in phenotype between subjects to pairwise similarity in genotype, with similarity in genotype defined via a kernel function. An advantage of the KM framework is its flexibility: choosing different kernel functions allows for different assumptions concerning the underlying model and can allow for improved power. In practice, it is difficult to know which kernel to use a priori since this depends on the unknown underlying trait architecture and selecting the kernel which gives the lowest p-value can lead to inflated type I error. Therefore, we propose practical strategies for KM testing when multiple candidate kernels are present based on constructing composite kernels and based on efficient perturbation procedures. We demonstrate through simulations and real data applications that the procedures protect the type I error rate and can lead to substantially improved power over poor choices of kernels and only modest differences in power versus using the best candidate kernel. PMID:23471868

SVM-Fold: a tool for discriminative multi-class protein fold and superfamily recognition

PubMed Central

Melvin, Iain; Ie, Eugene; Kuang, Rui; Weston, Jason; Stafford, William Noble; Leslie, Christina

2007-01-01

Background Predicting a protein's structural class from its amino acid sequence is a fundamental problem in computational biology. Much recent work has focused on developing new representations for protein sequences, called string kernels, for use with support vector machine (SVM) classifiers. However, while some of these approaches exhibit state-of-the-art performance at the binary protein classification problem, i.e. discriminating between a particular protein class and all other classes, few of these studies have addressed the real problem of multi-class superfamily or fold recognition. Moreover, there are only limited software tools and systems for SVM-based protein classification available to the bioinformatics community. Results We present a new multi-class SVM-based protein fold and superfamily recognition system and web server called SVM-Fold, which can be found at . Our system uses an efficient implementation of a state-of-the-art string kernel for sequence profiles, called the profile kernel, where the underlying feature representation is a histogram of inexact matching k-mer frequencies. We also employ a novel machine learning approach to solve the difficult multi-class problem of classifying a sequence of amino acids into one of many known protein structural classes. Binary one-vs-the-rest SVM classifiers that are trained to recognize individual structural classes yield prediction scores that are not comparable, so that standard "one-vs-all" classification fails to perform well. Moreover, SVMs for classes at different levels of the protein structural hierarchy may make useful predictions, but one-vs-all does not try to combine these multiple predictions. To deal with these problems, our method learns relative weights between one-vs-the-rest classifiers and encodes information about the protein structural hierarchy for multi-class prediction. In large-scale benchmark results based on the SCOP database, our code weighting approach significantly improves on the standard one-vs-all method for both the superfamily and fold prediction in the remote homology setting and on the fold recognition problem. Moreover, our code weight learning algorithm strongly outperforms nearest-neighbor methods based on PSI-BLAST in terms of prediction accuracy on every structure classification problem we consider. Conclusion By combining state-of-the-art SVM kernel methods with a novel multi-class algorithm, the SVM-Fold system delivers efficient and accurate protein fold and superfamily recognition. PMID:17570145

Improved Prediction of Blood-Brain Barrier Permeability Through Machine Learning with Combined Use of Molecular Property-Based Descriptors and Fingerprints.

PubMed

Yuan, Yaxia; Zheng, Fang; Zhan, Chang-Guo

2018-03-21

Blood-brain barrier (BBB) permeability of a compound determines whether the compound can effectively enter the brain. It is an essential property which must be accounted for in drug discovery with a target in the brain. Several computational methods have been used to predict the BBB permeability. In particular, support vector machine (SVM), which is a kernel-based machine learning method, has been used popularly in this field. For SVM training and prediction, the compounds are characterized by molecular descriptors. Some SVM models were based on the use of molecular property-based descriptors (including 1D, 2D, and 3D descriptors) or fragment-based descriptors (known as the fingerprints of a molecule). The selection of descriptors is critical for the performance of a SVM model. In this study, we aimed to develop a generally applicable new SVM model by combining all of the features of the molecular property-based descriptors and fingerprints to improve the accuracy for the BBB permeability prediction. The results indicate that our SVM model has improved accuracy compared to the currently available models of the BBB permeability prediction.

Multiscale Support Vector Learning With Projection Operator Wavelet Kernel for Nonlinear Dynamical System Identification.

PubMed

Lu, Zhao; Sun, Jing; Butts, Kenneth

2016-02-03

A giant leap has been made in the past couple of decades with the introduction of kernel-based learning as a mainstay for designing effective nonlinear computational learning algorithms. In view of the geometric interpretation of conditional expectation and the ubiquity of multiscale characteristics in highly complex nonlinear dynamic systems [1]-[3], this paper presents a new orthogonal projection operator wavelet kernel, aiming at developing an efficient computational learning approach for nonlinear dynamical system identification. In the framework of multiresolution analysis, the proposed projection operator wavelet kernel can fulfill the multiscale, multidimensional learning to estimate complex dependencies. The special advantage of the projection operator wavelet kernel developed in this paper lies in the fact that it has a closed-form expression, which greatly facilitates its application in kernel learning. To the best of our knowledge, it is the first closed-form orthogonal projection wavelet kernel reported in the literature. It provides a link between grid-based wavelets and mesh-free kernel-based methods. Simulation studies for identifying the parallel models of two benchmark nonlinear dynamical systems confirm its superiority in model accuracy and sparsity.

Fast Query-Optimized Kernel-Machine Classification

NASA Technical Reports Server (NTRS)

Mazzoni, Dominic; DeCoste, Dennis

2004-01-01

A recently developed algorithm performs kernel-machine classification via incremental approximate nearest support vectors. The algorithm implements support-vector machines (SVMs) at speeds 10 to 100 times those attainable by use of conventional SVM algorithms. The algorithm offers potential benefits for classification of images, recognition of speech, recognition of handwriting, and diverse other applications in which there are requirements to discern patterns in large sets of data. SVMs constitute a subset of kernel machines (KMs), which have become popular as models for machine learning and, more specifically, for automated classification of input data on the basis of labeled training data. While similar in many ways to k-nearest-neighbors (k-NN) models and artificial neural networks (ANNs), SVMs tend to be more accurate. Using representations that scale only linearly in the numbers of training examples, while exploring nonlinear (kernelized) feature spaces that are exponentially larger than the original input dimensionality, KMs elegantly and practically overcome the classic curse of dimensionality. However, the price that one must pay for the power of KMs is that query-time complexity scales linearly with the number of training examples, making KMs often orders of magnitude more computationally expensive than are ANNs, decision trees, and other popular machine learning alternatives. The present algorithm treats an SVM classifier as a special form of a k-NN. The algorithm is based partly on an empirical observation that one can often achieve the same classification as that of an exact KM by using only small fraction of the nearest support vectors (SVs) of a query. The exact KM output is a weighted sum over the kernel values between the query and the SVs. In this algorithm, the KM output is approximated with a k-NN classifier, the output of which is a weighted sum only over the kernel values involving k selected SVs. Before query time, there are gathered statistics about how misleading the output of the k-NN model can be, relative to the outputs of the exact KM for a representative set of examples, for each possible k from 1 to the total number of SVs. From these statistics, there are derived upper and lower thresholds for each step k. These thresholds identify output levels for which the particular variant of the k-NN model already leans so strongly positively or negatively that a reversal in sign is unlikely, given the weaker SV neighbors still remaining. At query time, the partial output of each query is incrementally updated, stopping as soon as it exceeds the predetermined statistical thresholds of the current step. For an easy query, stopping can occur as early as step k = 1. For more difficult queries, stopping might not occur until nearly all SVs are touched. A key empirical observation is that this approach can tolerate very approximate nearest-neighbor orderings. In experiments, SVs and queries were projected to a subspace comprising the top few principal- component dimensions and neighbor orderings were computed in that subspace. This approach ensured that the overhead of the nearest-neighbor computations was insignificant, relative to that of the exact KM computation.

Multiple Kernel Sparse Representation based Orthogonal Discriminative Projection and Its Cost-Sensitive Extension.

PubMed

Zhang, Guoqing; Sun, Huaijiang; Xia, Guiyu; Sun, Quansen

2016-07-07

Sparse representation based classification (SRC) has been developed and shown great potential for real-world application. Based on SRC, Yang et al. [10] devised a SRC steered discriminative projection (SRC-DP) method. However, as a linear algorithm, SRC-DP cannot handle the data with highly nonlinear distribution. Kernel sparse representation-based classifier (KSRC) is a non-linear extension of SRC and can remedy the drawback of SRC. KSRC requires the use of a predetermined kernel function and selection of the kernel function and its parameters is difficult. Recently, multiple kernel learning for SRC (MKL-SRC) [22] has been proposed to learn a kernel from a set of base kernels. However, MKL-SRC only considers the within-class reconstruction residual while ignoring the between-class relationship, when learning the kernel weights. In this paper, we propose a novel multiple kernel sparse representation-based classifier (MKSRC), and then we use it as a criterion to design a multiple kernel sparse representation based orthogonal discriminative projection method (MK-SR-ODP). The proposed algorithm aims at learning a projection matrix and a corresponding kernel from the given base kernels such that in the low dimension subspace the between-class reconstruction residual is maximized and the within-class reconstruction residual is minimized. Furthermore, to achieve a minimum overall loss by performing recognition in the learned low-dimensional subspace, we introduce cost information into the dimensionality reduction method. The solutions for the proposed method can be efficiently found based on trace ratio optimization method [33]. Extensive experimental results demonstrate the superiority of the proposed algorithm when compared with the state-of-the-art methods.

Many-Body Descriptors for Predicting Molecular Properties with Machine Learning: Analysis of Pairwise and Three-Body Interactions in Molecules.

PubMed

Pronobis, Wiktor; Tkatchenko, Alexandre; Müller, Klaus-Robert

2018-06-12

Machine learning (ML) based prediction of molecular properties across chemical compound space is an important and alternative approach to efficiently estimate the solutions of highly complex many-electron problems in chemistry and physics. Statistical methods represent molecules as descriptors that should encode molecular symmetries and interactions between atoms. Many such descriptors have been proposed; all of them have advantages and limitations. Here, we propose a set of general two-body and three-body interaction descriptors which are invariant to translation, rotation, and atomic indexing. By adapting the successfully used kernel ridge regression methods of machine learning, we evaluate our descriptors on predicting several properties of small organic molecules calculated using density-functional theory. We use two data sets. The GDB-7 set contains 6868 molecules with up to 7 heavy atoms of type CNO. The GDB-9 set is composed of 131722 molecules with up to 9 heavy atoms containing CNO. When trained on 5000 random molecules, our best model achieves an accuracy of 0.8 kcal/mol (on the remaining 1868 molecules of GDB-7) and 1.5 kcal/mol (on the remaining 126722 molecules of GDB-9) respectively. Applying a linear regression model on our novel many-body descriptors performs almost equal to a nonlinear kernelized model. Linear models are readily interpretable: a feature importance ranking measure helps to obtain qualitative and quantitative insights on the importance of two- and three-body molecular interactions for predicting molecular properties computed with quantum-mechanical methods.

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

PubMed

Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

2015-10-30

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.

Improved Online Support Vector Machines Spam Filtering Using String Kernels

NASA Astrophysics Data System (ADS)

Amayri, Ola; Bouguila, Nizar

A major bottleneck in electronic communications is the enormous dissemination of spam emails. Developing of suitable filters that can adequately capture those emails and achieve high performance rate become a main concern. Support vector machines (SVMs) have made a large contribution to the development of spam email filtering. Based on SVMs, the crucial problems in email classification are feature mapping of input emails and the choice of the kernels. In this paper, we present thorough investigation of several distance-based kernels and propose the use of string kernels and prove its efficiency in blocking spam emails. We detail a feature mapping variants in text classification (TC) that yield improved performance for the standard SVMs in filtering task. Furthermore, to cope for realtime scenarios we propose an online active framework for spam filtering.

Time-Frequency Learning Machines for Nonstationarity Detection Using Surrogates

NASA Astrophysics Data System (ADS)

Borgnat, Pierre; Flandrin, Patrick; Richard, Cédric; Ferrari, André; Amoud, Hassan; Honeine, Paul

2012-03-01

Time-frequency representations provide a powerful tool for nonstationary signal analysis and classification, supporting a wide range of applications [12]. As opposed to conventional Fourier analysis, these techniques reveal the evolution in time of the spectral content of signals. In Ref. [7,38], time-frequency analysis is used to test stationarity of any signal. The proposed method consists of a comparison between global and local time-frequency features. The originality is to make use of a family of stationary surrogate signals for defining the null hypothesis of stationarity and, based upon this information, to derive statistical tests. An open question remains, however, about how to choose relevant time-frequency features. Over the last decade, a number of new pattern recognition methods based on reproducing kernels have been introduced. These learning machines have gained popularity due to their conceptual simplicity and their outstanding performance [30]. Initiated by Vapnik’s support vector machines (SVM) [35], they offer now a wide class of supervised and unsupervised learning algorithms. In Ref. [17-19], the authors have shown how the most effective and innovative learning machines can be tuned to operate in the time-frequency domain. This chapter follows this line of research by taking advantage of learning machines to test and quantify stationarity. Based on one-class SVM, our approach uses the entire time-frequency representation and does not require arbitrary feature extraction. Applied to a set of surrogates, it provides the domain boundary that includes most of these stationarized signals. This allows us to test the stationarity of the signal under investigation. This chapter is organized as follows. In Section 22.2, we introduce the surrogate data method to generate stationarized signals, namely, the null hypothesis of stationarity. The concept of time-frequency learning machines is presented in Section 22.3, and applied to one-class SVM in order to derive a stationarity test in Section 22.4. The relevance of the latter is illustrated by simulation results in Section 22.5.

Machine Learning and Computer Vision System for Phenotype Data Acquisition and Analysis in Plants.

PubMed

Navarro, Pedro J; Pérez, Fernando; Weiss, Julia; Egea-Cortines, Marcos

2016-05-05

Phenomics is a technology-driven approach with promising future to obtain unbiased data of biological systems. Image acquisition is relatively simple. However data handling and analysis are not as developed compared to the sampling capacities. We present a system based on machine learning (ML) algorithms and computer vision intended to solve the automatic phenotype data analysis in plant material. We developed a growth-chamber able to accommodate species of various sizes. Night image acquisition requires near infrared lightning. For the ML process, we tested three different algorithms: k-nearest neighbour (kNN), Naive Bayes Classifier (NBC), and Support Vector Machine. Each ML algorithm was executed with different kernel functions and they were trained with raw data and two types of data normalisation. Different metrics were computed to determine the optimal configuration of the machine learning algorithms. We obtained a performance of 99.31% in kNN for RGB images and a 99.34% in SVM for NIR. Our results show that ML techniques can speed up phenomic data analysis. Furthermore, both RGB and NIR images can be segmented successfully but may require different ML algorithms for segmentation.

Application of Support Vector Machine to Forex Monitoring

NASA Astrophysics Data System (ADS)

Kamruzzaman, Joarder; Sarker, Ruhul A.

Previous studies have demonstrated superior performance of artificial neural network (ANN) based forex forecasting models over traditional regression models. This paper applies support vector machines to build a forecasting model from the historical data using six simple technical indicators and presents a comparison with an ANN based model trained by scaled conjugate gradient (SCG) learning algorithm. The models are evaluated and compared on the basis of five commonly used performance metrics that measure closeness of prediction as well as correctness in directional change. Forecasting results of six different currencies against Australian dollar reveal superior performance of SVM model using simple linear kernel over ANN-SCG model in terms of all the evaluation metrics. The effect of SVM parameter selection on prediction performance is also investigated and analyzed.

Oligo kernels for datamining on biological sequences: a case study on prokaryotic translation initiation sites

PubMed Central

Meinicke, Peter; Tech, Maike; Morgenstern, Burkhard; Merkl, Rainer

2004-01-01

Background Kernel-based learning algorithms are among the most advanced machine learning methods and have been successfully applied to a variety of sequence classification tasks within the field of bioinformatics. Conventional kernels utilized so far do not provide an easy interpretation of the learnt representations in terms of positional and compositional variability of the underlying biological signals. Results We propose a kernel-based approach to datamining on biological sequences. With our method it is possible to model and analyze positional variability of oligomers of any length in a natural way. On one hand this is achieved by mapping the sequences to an intuitive but high-dimensional feature space, well-suited for interpretation of the learnt models. On the other hand, by means of the kernel trick we can provide a general learning algorithm for that high-dimensional representation because all required statistics can be computed without performing an explicit feature space mapping of the sequences. By introducing a kernel parameter that controls the degree of position-dependency, our feature space representation can be tailored to the characteristics of the biological problem at hand. A regularized learning scheme enables application even to biological problems for which only small sets of example sequences are available. Our approach includes a visualization method for transparent representation of characteristic sequence features. Thereby importance of features can be measured in terms of discriminative strength with respect to classification of the underlying sequences. To demonstrate and validate our concept on a biochemically well-defined case, we analyze E. coli translation initiation sites in order to show that we can find biologically relevant signals. For that case, our results clearly show that the Shine-Dalgarno sequence is the most important signal upstream a start codon. The variability in position and composition we found for that signal is in accordance with previous biological knowledge. We also find evidence for signals downstream of the start codon, previously introduced as transcriptional enhancers. These signals are mainly characterized by occurrences of adenine in a region of about 4 nucleotides next to the start codon. Conclusions We showed that the oligo kernel can provide a valuable tool for the analysis of relevant signals in biological sequences. In the case of translation initiation sites we could clearly deduce the most discriminative motifs and their positional variation from example sequences. Attractive features of our approach are its flexibility with respect to oligomer length and position conservation. By means of these two parameters oligo kernels can easily be adapted to different biological problems. PMID:15511290

Quantum machine learning for quantum anomaly detection

NASA Astrophysics Data System (ADS)

Liu, Nana; Rebentrost, Patrick

2018-04-01

Anomaly detection is used for identifying data that deviate from "normal" data patterns. Its usage on classical data finds diverse applications in many important areas such as finance, fraud detection, medical diagnoses, data cleaning, and surveillance. With the advent of quantum technologies, anomaly detection of quantum data, in the form of quantum states, may become an important component of quantum applications. Machine-learning algorithms are playing pivotal roles in anomaly detection using classical data. Two widely used algorithms are the kernel principal component analysis and the one-class support vector machine. We find corresponding quantum algorithms to detect anomalies in quantum states. We show that these two quantum algorithms can be performed using resources that are logarithmic in the dimensionality of quantum states. For pure quantum states, these resources can also be logarithmic in the number of quantum states used for training the machine-learning algorithm. This makes these algorithms potentially applicable to big quantum data applications.

Epileptic seizure detection in EEG signal using machine learning techniques.

PubMed

Jaiswal, Abeg Kumar; Banka, Haider

2018-03-01

Epilepsy is a well-known nervous system disorder characterized by seizures. Electroencephalograms (EEGs), which capture brain neural activity, can detect epilepsy. Traditional methods for analyzing an EEG signal for epileptic seizure detection are time-consuming. Recently, several automated seizure detection frameworks using machine learning technique have been proposed to replace these traditional methods. The two basic steps involved in machine learning are feature extraction and classification. Feature extraction reduces the input pattern space by keeping informative features and the classifier assigns the appropriate class label. In this paper, we propose two effective approaches involving subpattern based PCA (SpPCA) and cross-subpattern correlation-based PCA (SubXPCA) with Support Vector Machine (SVM) for automated seizure detection in EEG signals. Feature extraction was performed using SpPCA and SubXPCA. Both techniques explore the subpattern correlation of EEG signals, which helps in decision-making process. SVM is used for classification of seizure and non-seizure EEG signals. The SVM was trained with radial basis kernel. All the experiments have been carried out on the benchmark epilepsy EEG dataset. The entire dataset consists of 500 EEG signals recorded under different scenarios. Seven different experimental cases for classification have been conducted. The classification accuracy was evaluated using tenfold cross validation. The classification results of the proposed approaches have been compared with the results of some of existing techniques proposed in the literature to establish the claim.

Lesion classification using clinical and visual data fusion by multiple kernel learning

NASA Astrophysics Data System (ADS)

Kisilev, Pavel; Hashoul, Sharbell; Walach, Eugene; Tzadok, Asaf

2014-03-01

To overcome operator dependency and to increase diagnosis accuracy in breast ultrasound (US), a lot of effort has been devoted to developing computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Unfortunately, the efficacy of such CAD systems is limited since they rely on correct automatic lesions detection and localization, and on robustness of features computed based on the detected areas. In this paper we propose a new approach to boost the performance of a Machine Learning based CAD system, by combining visual and clinical data from patient files. We compute a set of visual features from breast ultrasound images, and construct the textual descriptor of patients by extracting relevant keywords from patients' clinical data files. We then use the Multiple Kernel Learning (MKL) framework to train SVM based classifier to discriminate between benign and malignant cases. We investigate different types of data fusion methods, namely, early, late, and intermediate (MKL-based) fusion. Our database consists of 408 patient cases, each containing US images, textual description of complaints and symptoms filled by physicians, and confirmed diagnoses. We show experimentally that the proposed MKL-based approach is superior to other classification methods. Even though the clinical data is very sparse and noisy, its MKL-based fusion with visual features yields significant improvement of the classification accuracy, as compared to the image features only based classifier.

Omnibus Risk Assessment via Accelerated Failure Time Kernel Machine Modeling

PubMed Central

Sinnott, Jennifer A.; Cai, Tianxi

2013-01-01

Summary Integrating genomic information with traditional clinical risk factors to improve the prediction of disease outcomes could profoundly change the practice of medicine. However, the large number of potential markers and possible complexity of the relationship between markers and disease make it difficult to construct accurate risk prediction models. Standard approaches for identifying important markers often rely on marginal associations or linearity assumptions and may not capture non-linear or interactive effects. In recent years, much work has been done to group genes into pathways and networks. Integrating such biological knowledge into statistical learning could potentially improve model interpretability and reliability. One effective approach is to employ a kernel machine (KM) framework, which can capture nonlinear effects if nonlinear kernels are used (Scholkopf and Smola, 2002; Liu et al., 2007, 2008). For survival outcomes, KM regression modeling and testing procedures have been derived under a proportional hazards (PH) assumption (Li and Luan, 2003; Cai et al., 2011). In this paper, we derive testing and prediction methods for KM regression under the accelerated failure time model, a useful alternative to the PH model. We approximate the null distribution of our test statistic using resampling procedures. When multiple kernels are of potential interest, it may be unclear in advance which kernel to use for testing and estimation. We propose a robust Omnibus Test that combines information across kernels, and an approach for selecting the best kernel for estimation. The methods are illustrated with an application in breast cancer. PMID:24328713

Integration of Network Topological and Connectivity Properties for Neuroimaging Classification

PubMed Central

Jie, Biao; Gao, Wei; Wang, Qian; Wee, Chong-Yaw

2014-01-01

Rapid advances in neuroimaging techniques have provided an efficient and noninvasive way for exploring the structural and functional connectivity of the human brain. Quantitative measurement of abnormality of brain connectivity in patients with neurodegenerative diseases, such as mild cognitive impairment (MCI) and Alzheimer’s disease (AD), have also been widely reported, especially at a group level. Recently, machine learning techniques have been applied to the study of AD and MCI, i.e., to identify the individuals with AD/MCI from the healthy controls (HCs). However, most existing methods focus on using only a single property of a connectivity network, although multiple network properties, such as local connectivity and global topological properties, can potentially be used. In this paper, by employing multikernel based approach, we propose a novel connectivity based framework to integrate multiple properties of connectivity network for improving the classification performance. Specifically, two different types of kernels (i.e., vector-based kernel and graph kernel) are used to quantify two different yet complementary properties of the network, i.e., local connectivity and global topological properties. Then, multikernel learning (MKL) technique is adopted to fuse these heterogeneous kernels for neuroimaging classification. We test the performance of our proposed method on two different data sets. First, we test it on the functional connectivity networks of 12 MCI and 25 HC subjects. The results show that our method achieves significant performance improvement over those using only one type of network property. Specifically, our method achieves a classification accuracy of 91.9%, which is 10.8% better than those by single network-property-based methods. Then, we test our method for gender classification on a large set of functional connectivity networks with 133 infants scanned at birth, 1 year, and 2 years, also demonstrating very promising results. PMID:24108708

Common spatial pattern combined with kernel linear discriminate and generalized radial basis function for motor imagery-based brain computer interface applications

NASA Astrophysics Data System (ADS)

Hekmatmanesh, Amin; Jamaloo, Fatemeh; Wu, Huapeng; Handroos, Heikki; Kilpeläinen, Asko

2018-04-01

Brain Computer Interface (BCI) can be a challenge for developing of robotic, prosthesis and human-controlled systems. This work focuses on the implementation of a common spatial pattern (CSP) base algorithm to detect event related desynchronization patterns. Utilizing famous previous work in this area, features are extracted by filter bank with common spatial pattern (FBCSP) method, and then weighted by a sensitive learning vector quantization (SLVQ) algorithm. In the current work, application of the radial basis function (RBF) as a mapping kernel of linear discriminant analysis (KLDA) method on the weighted features, allows the transfer of data into a higher dimension for more discriminated data scattering by RBF kernel. Afterwards, support vector machine (SVM) with generalized radial basis function (GRBF) kernel is employed to improve the efficiency and robustness of the classification. Averagely, 89.60% accuracy and 74.19% robustness are achieved. BCI Competition III, Iva data set is used to evaluate the algorithm for detecting right hand and foot imagery movement patterns. Results show that combination of KLDA with SVM-GRBF classifier makes 8.9% and 14.19% improvements in accuracy and robustness, respectively. For all the subjects, it is concluded that mapping the CSP features into a higher dimension by RBF and utilization GRBF as a kernel of SVM, improve the accuracy and reliability of the proposed method.

A multiple kernel support vector machine scheme for feature selection and rule extraction from gene expression data of cancer tissue.

PubMed

Chen, Zhenyu; Li, Jianping; Wei, Liwei

2007-10-01

Recently, gene expression profiling using microarray techniques has been shown as a promising tool to improve the diagnosis and treatment of cancer. Gene expression data contain high level of noise and the overwhelming number of genes relative to the number of available samples. It brings out a great challenge for machine learning and statistic techniques. Support vector machine (SVM) has been successfully used to classify gene expression data of cancer tissue. In the medical field, it is crucial to deliver the user a transparent decision process. How to explain the computed solutions and present the extracted knowledge becomes a main obstacle for SVM. A multiple kernel support vector machine (MK-SVM) scheme, consisting of feature selection, rule extraction and prediction modeling is proposed to improve the explanation capacity of SVM. In this scheme, we show that the feature selection problem can be translated into an ordinary multiple parameters learning problem. And a shrinkage approach: 1-norm based linear programming is proposed to obtain the sparse parameters and the corresponding selected features. We propose a novel rule extraction approach using the information provided by the separating hyperplane and support vectors to improve the generalization capacity and comprehensibility of rules and reduce the computational complexity. Two public gene expression datasets: leukemia dataset and colon tumor dataset are used to demonstrate the performance of this approach. Using the small number of selected genes, MK-SVM achieves encouraging classification accuracy: more than 90% for both two datasets. Moreover, very simple rules with linguist labels are extracted. The rule sets have high diagnostic power because of their good classification performance.

Enhanced Data Representation by Kernel Metric Learning for Dementia Diagnosis

PubMed Central

Cárdenas-Peña, David; Collazos-Huertas, Diego; Castellanos-Dominguez, German

2017-01-01

Alzheimer's disease (AD) is the kind of dementia that affects the most people around the world. Therefore, an early identification supporting effective treatments is required to increase the life quality of a wide number of patients. Recently, computer-aided diagnosis tools for dementia using Magnetic Resonance Imaging scans have been successfully proposed to discriminate between patients with AD, mild cognitive impairment, and healthy controls. Most of the attention has been given to the clinical data, provided by initiatives as the ADNI, supporting reliable researches on intervention, prevention, and treatments of AD. Therefore, there is a need for improving the performance of classification machines. In this paper, we propose a kernel framework for learning metrics that enhances conventional machines and supports the diagnosis of dementia. Our framework aims at building discriminative spaces through the maximization of center kernel alignment function, aiming at improving the discrimination of the three considered neurological classes. The proposed metric learning performance is evaluated on the widely-known ADNI database using three supervised classification machines (k-nn, SVM and NNs) for multi-class and bi-class scenarios from structural MRIs. Specifically, from ADNI collection 286 AD patients, 379 MCI patients and 231 healthy controls are used for development and validation of our proposed metric learning framework. For the experimental validation, we split the data into two subsets: 30% of subjects used like a blindfolded assessment and 70% employed for parameter tuning. Then, in the preprocessing stage, each structural MRI scan a total of 310 morphological measurements are automatically extracted from by FreeSurfer software package and concatenated to build an input feature matrix. Obtained test performance results, show that including a supervised metric learning improves the compared baseline classifiers in both scenarios. In the multi-class scenario, we achieve the best performance (accuracy 60.1%) for pretrained 1-layered NN, and we obtain measures over 90% in the average for HC vs. AD task. From the machine learning point of view, our proposal enhances the classifier performance by building spaces with a better class separability. From the clinical application, our enhancement results in a more balanced performance in each class than the compared approaches from the CADDementia challenge by increasing the sensitivity of pathological groups and the specificity of healthy controls. PMID:28798659

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO

PubMed Central

Zhu, Zhichuan; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified. PMID:29853983

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO.

PubMed

Li, Yang; Zhu, Zhichuan; Hou, Alin; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified.

Kinase Identification with Supervised Laplacian Regularized Least Squares

PubMed Central

Zhang, He; Wang, Minghui

2015-01-01

Phosphorylation is catalyzed by protein kinases and is irreplaceable in regulating biological processes. Identification of phosphorylation sites with their corresponding kinases contributes to the understanding of molecular mechanisms. Mass spectrometry analysis of phosphor-proteomes generates a large number of phosphorylated sites. However, experimental methods are costly and time-consuming, and most phosphorylation sites determined by experimental methods lack kinase information. Therefore, computational methods are urgently needed to address the kinase identification problem. To this end, we propose a new kernel-based machine learning method called Supervised Laplacian Regularized Least Squares (SLapRLS), which adopts a new method to construct kernels based on the similarity matrix and minimizes both structure risk and overall inconsistency between labels and similarities. The results predicted using both Phospho.ELM and an additional independent test dataset indicate that SLapRLS can more effectively identify kinases compared to other existing algorithms. PMID:26448296

Kinase Identification with Supervised Laplacian Regularized Least Squares.

PubMed

Li, Ao; Xu, Xiaoyi; Zhang, He; Wang, Minghui

2015-01-01

Phosphorylation is catalyzed by protein kinases and is irreplaceable in regulating biological processes. Identification of phosphorylation sites with their corresponding kinases contributes to the understanding of molecular mechanisms. Mass spectrometry analysis of phosphor-proteomes generates a large number of phosphorylated sites. However, experimental methods are costly and time-consuming, and most phosphorylation sites determined by experimental methods lack kinase information. Therefore, computational methods are urgently needed to address the kinase identification problem. To this end, we propose a new kernel-based machine learning method called Supervised Laplacian Regularized Least Squares (SLapRLS), which adopts a new method to construct kernels based on the similarity matrix and minimizes both structure risk and overall inconsistency between labels and similarities. The results predicted using both Phospho.ELM and an additional independent test dataset indicate that SLapRLS can more effectively identify kinases compared to other existing algorithms.

Gradient-based adaptation of general gaussian kernels.

PubMed

Glasmachers, Tobias; Igel, Christian

2005-10-01

Gradient-based optimizing of gaussian kernel functions is considered. The gradient for the adaptation of scaling and rotation of the input space is computed to achieve invariance against linear transformations. This is done by using the exponential map as a parameterization of the kernel parameter manifold. By restricting the optimization to a constant trace subspace, the kernel size can be controlled. This is, for example, useful to prevent overfitting when minimizing radius-margin generalization performance measures. The concepts are demonstrated by training hard margin support vector machines on toy data.

Wilson and Domainwall Kernels on Oakforest-PACS

NASA Astrophysics Data System (ADS)

Kanamori, Issaku; Matsufuru, Hideo

2018-03-01

We report the performance of Wilson and Domainwall Kernels on a new Intel Xeon Phi Knights Landing based machine named Oakforest-PACS, which is co-hosted by University of Tokyo and Tsukuba University and is currently fastest in Japan. This machine uses Intel Omni-Path for the internode network. We compare performance with several types of implementation including that makes use of the Grid library. The code is incorporated with the code set Bridge++.

Learning a peptide-protein binding affinity predictor with kernel ridge regression

PubMed Central

2013-01-01

Background The cellular function of a vast majority of proteins is performed through physical interactions with other biomolecules, which, most of the time, are other proteins. Peptides represent templates of choice for mimicking a secondary structure in order to modulate protein-protein interaction. They are thus an interesting class of therapeutics since they also display strong activity, high selectivity, low toxicity and few drug-drug interactions. Furthermore, predicting peptides that would bind to a specific MHC alleles would be of tremendous benefit to improve vaccine based therapy and possibly generate antibodies with greater affinity. Modern computational methods have the potential to accelerate and lower the cost of drug and vaccine discovery by selecting potential compounds for testing in silico prior to biological validation. Results We propose a specialized string kernel for small bio-molecules, peptides and pseudo-sequences of binding interfaces. The kernel incorporates physico-chemical properties of amino acids and elegantly generalizes eight kernels, comprised of the Oligo, the Weighted Degree, the Blended Spectrum, and the Radial Basis Function. We provide a low complexity dynamic programming algorithm for the exact computation of the kernel and a linear time algorithm for it’s approximation. Combined with kernel ridge regression and SupCK, a novel binding pocket kernel, the proposed kernel yields biologically relevant and good prediction accuracy on the PepX database. For the first time, a machine learning predictor is capable of predicting the binding affinity of any peptide to any protein with reasonable accuracy. The method was also applied to both single-target and pan-specific Major Histocompatibility Complex class II benchmark datasets and three Quantitative Structure Affinity Model benchmark datasets. Conclusion On all benchmarks, our method significantly (p-value ≤ 0.057) outperforms the current state-of-the-art methods at predicting peptide-protein binding affinities. The proposed approach is flexible and can be applied to predict any quantitative biological activity. Moreover, generating reliable peptide-protein binding affinities will also improve system biology modelling of interaction pathways. Lastly, the method should be of value to a large segment of the research community with the potential to accelerate the discovery of peptide-based drugs and facilitate vaccine development. The proposed kernel is freely available at http://graal.ift.ulaval.ca/downloads/gs-kernel/. PMID:23497081

Future climate scenarios and rainfall--runoff modelling in the Upper Gallego catchment (Spain).

PubMed

Bürger, C M; Kolditz, O; Fowler, H J; Blenkinsop, S

2007-08-01

Global climate change may have large impacts on water supplies, drought or flood frequencies and magnitudes in local and regional hydrologic systems. Water authorities therefore rely on computer models for quantitative impact prediction. In this study we present kernel-based learning machine river flow models for the Upper Gallego catchment of the Ebro basin. Different learning machines were calibrated using daily gauge data. The models posed two major challenges: (1) estimation of the rainfall-runoff transfer function from the available time series is complicated by anthropogenic regulation and mountainous terrain and (2) the river flow model is weak when only climate data are used, but additional antecedent flow data seemed to lead to delayed peak flow estimation. These types of models, together with the presented downscaled climate scenarios, can be used for climate change impact assessment in the Gallego, which is important for the future management of the system.

Margin-maximizing feature elimination methods for linear and nonlinear kernel-based discriminant functions.

PubMed

Aksu, Yaman; Miller, David J; Kesidis, George; Yang, Qing X

2010-05-01

Feature selection for classification in high-dimensional spaces can improve generalization, reduce classifier complexity, and identify important, discriminating feature "markers." For support vector machine (SVM) classification, a widely used technique is recursive feature elimination (RFE). We demonstrate that RFE is not consistent with margin maximization, central to the SVM learning approach. We thus propose explicit margin-based feature elimination (MFE) for SVMs and demonstrate both improved margin and improved generalization, compared with RFE. Moreover, for the case of a nonlinear kernel, we show that RFE assumes that the squared weight vector 2-norm is strictly decreasing as features are eliminated. We demonstrate this is not true for the Gaussian kernel and, consequently, RFE may give poor results in this case. MFE for nonlinear kernels gives better margin and generalization. We also present an extension which achieves further margin gains, by optimizing only two degrees of freedom--the hyperplane's intercept and its squared 2-norm--with the weight vector orientation fixed. We finally introduce an extension that allows margin slackness. We compare against several alternatives, including RFE and a linear programming method that embeds feature selection within the classifier design. On high-dimensional gene microarray data sets, University of California at Irvine (UCI) repository data sets, and Alzheimer's disease brain image data, MFE methods give promising results.

Cepstrum based feature extraction method for fungus detection

NASA Astrophysics Data System (ADS)

Yorulmaz, Onur; Pearson, Tom C.; Çetin, A. Enis

2011-06-01

In this paper, a method for detection of popcorn kernels infected by a fungus is developed using image processing. The method is based on two dimensional (2D) mel and Mellin-cepstrum computation from popcorn kernel images. Cepstral features that were extracted from popcorn images are classified using Support Vector Machines (SVM). Experimental results show that high recognition rates of up to 93.93% can be achieved for both damaged and healthy popcorn kernels using 2D mel-cepstrum. The success rate for healthy popcorn kernels was found to be 97.41% and the recognition rate for damaged kernels was found to be 89.43%.

Detection of Stress Levels from Biosignals Measured in Virtual Reality Environments Using a Kernel-Based Extreme Learning Machine.

PubMed

Cho, Dongrae; Ham, Jinsil; Oh, Jooyoung; Park, Jeanho; Kim, Sayup; Lee, Nak-Kyu; Lee, Boreom

2017-10-24

Virtual reality (VR) is a computer technique that creates an artificial environment composed of realistic images, sounds, and other sensations. Many researchers have used VR devices to generate various stimuli, and have utilized them to perform experiments or to provide treatment. In this study, the participants performed mental tasks using a VR device while physiological signals were measured: a photoplethysmogram (PPG), electrodermal activity (EDA), and skin temperature (SKT). In general, stress is an important factor that can influence the autonomic nervous system (ANS). Heart-rate variability (HRV) is known to be related to ANS activity, so we used an HRV derived from the PPG peak interval. In addition, the peak characteristics of the skin conductance (SC) from EDA and SKT variation can also reflect ANS activity; we utilized them as well. Then, we applied a kernel-based extreme-learning machine (K-ELM) to correctly classify the stress levels induced by the VR task to reflect five different levels of stress situations: baseline, mild stress, moderate stress, severe stress, and recovery. Twelve healthy subjects voluntarily participated in the study. Three physiological signals were measured in stress environment generated by VR device. As a result, the average classification accuracy was over 95% using K-ELM and the integrated feature (IT = HRV + SC + SKT). In addition, the proposed algorithm can embed a microcontroller chip since K-ELM algorithm have very short computation time. Therefore, a compact wearable device classifying stress levels using physiological signals can be developed.

Online selective kernel-based temporal difference learning.

PubMed

Chen, Xingguo; Gao, Yang; Wang, Ruili

2013-12-01

In this paper, an online selective kernel-based temporal difference (OSKTD) learning algorithm is proposed to deal with large scale and/or continuous reinforcement learning problems. OSKTD includes two online procedures: online sparsification and parameter updating for the selective kernel-based value function. A new sparsification method (i.e., a kernel distance-based online sparsification method) is proposed based on selective ensemble learning, which is computationally less complex compared with other sparsification methods. With the proposed sparsification method, the sparsified dictionary of samples is constructed online by checking if a sample needs to be added to the sparsified dictionary. In addition, based on local validity, a selective kernel-based value function is proposed to select the best samples from the sample dictionary for the selective kernel-based value function approximator. The parameters of the selective kernel-based value function are iteratively updated by using the temporal difference (TD) learning algorithm combined with the gradient descent technique. The complexity of the online sparsification procedure in the OSKTD algorithm is O(n). In addition, two typical experiments (Maze and Mountain Car) are used to compare with both traditional and up-to-date O(n) algorithms (GTD, GTD2, and TDC using the kernel-based value function), and the results demonstrate the effectiveness of our proposed algorithm. In the Maze problem, OSKTD converges to an optimal policy and converges faster than both traditional and up-to-date algorithms. In the Mountain Car problem, OSKTD converges, requires less computation time compared with other sparsification methods, gets a better local optima than the traditional algorithms, and converges much faster than the up-to-date algorithms. In addition, OSKTD can reach a competitive ultimate optima compared with the up-to-date algorithms.

Notes on a storage manager for the Clouds kernel

NASA Technical Reports Server (NTRS)

Pitts, David V.; Spafford, Eugene H.

1986-01-01

The Clouds project is research directed towards producing a reliable distributed computing system. The initial goal is to produce a kernel which provides a reliable environment with which a distributed operating system can be built. The Clouds kernal consists of a set of replicated subkernels, each of which runs on a machine in the Clouds system. Each subkernel is responsible for the management of resources on its machine; the subkernal components communicate to provide the cooperation necessary to meld the various machines into one kernel. The implementation of a kernel-level storage manager that supports reliability is documented. The storage manager is a part of each subkernel and maintains the secondary storage residing at each machine in the distributed system. In addition to providing the usual data transfer services, the storage manager ensures that data being stored survives machine and system crashes, and that the secondary storage of a failed machine is recovered (made consistent) automatically when the machine is restarted. Since the storage manager is part of the Clouds kernel, efficiency of operation is also a concern.

Brain tumor image segmentation using kernel dictionary learning.

PubMed

Jeon Lee; Seung-Jun Kim; Rong Chen; Herskovits, Edward H

2015-08-01

Automated brain tumor image segmentation with high accuracy and reproducibility holds a big potential to enhance the current clinical practice. Dictionary learning (DL) techniques have been applied successfully to various image processing tasks recently. In this work, kernel extensions of the DL approach are adopted. Both reconstructive and discriminative versions of the kernel DL technique are considered, which can efficiently incorporate multi-modal nonlinear feature mappings based on the kernel trick. Our novel discriminative kernel DL formulation allows joint learning of a task-driven kernel-based dictionary and a linear classifier using a K-SVD-type algorithm. The proposed approaches were tested using real brain magnetic resonance (MR) images of patients with high-grade glioma. The obtained preliminary performances are competitive with the state of the art. The discriminative kernel DL approach is seen to reduce computational burden without much sacrifice in performance.

Omnibus risk assessment via accelerated failure time kernel machine modeling.

PubMed

Sinnott, Jennifer A; Cai, Tianxi

2013-12-01

Integrating genomic information with traditional clinical risk factors to improve the prediction of disease outcomes could profoundly change the practice of medicine. However, the large number of potential markers and possible complexity of the relationship between markers and disease make it difficult to construct accurate risk prediction models. Standard approaches for identifying important markers often rely on marginal associations or linearity assumptions and may not capture non-linear or interactive effects. In recent years, much work has been done to group genes into pathways and networks. Integrating such biological knowledge into statistical learning could potentially improve model interpretability and reliability. One effective approach is to employ a kernel machine (KM) framework, which can capture nonlinear effects if nonlinear kernels are used (Scholkopf and Smola, 2002; Liu et al., 2007, 2008). For survival outcomes, KM regression modeling and testing procedures have been derived under a proportional hazards (PH) assumption (Li and Luan, 2003; Cai, Tonini, and Lin, 2011). In this article, we derive testing and prediction methods for KM regression under the accelerated failure time (AFT) model, a useful alternative to the PH model. We approximate the null distribution of our test statistic using resampling procedures. When multiple kernels are of potential interest, it may be unclear in advance which kernel to use for testing and estimation. We propose a robust Omnibus Test that combines information across kernels, and an approach for selecting the best kernel for estimation. The methods are illustrated with an application in breast cancer. © 2013, The International Biometric Society.

A high performance parallel algorithm for 1-D FFT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Agarwal, R.C.; Gustavson, F.G.; Zubair, M.

1994-12-31

In this paper the authors propose a parallel high performance FFT algorithm based on a multi-dimensional formulation. They use this to solve a commonly encountered FFT based kernel on a distributed memory parallel machine, the IBM scalable parallel system, SP1. The kernel requires a forward FFT computation of an input sequence, multiplication of the transformed data by a coefficient array, and finally an inverse FFT computation of the resultant data. They show that the multi-dimensional formulation helps in reducing the communication costs and also improves the single node performance by effectively utilizing the memory system of the node. They implementedmore » this kernel on the IBM SP1 and observed a performance of 1.25 GFLOPS on a 64-node machine.« less

Scalable Kernel Methods and Algorithms for General Sequence Analysis

ERIC Educational Resources Information Center

Kuksa, Pavel

2011-01-01

Analysis of large-scale sequential data has become an important task in machine learning and pattern recognition, inspired in part by numerous scientific and technological applications such as the document and text classification or the analysis of biological sequences. However, current computational methods for sequence comparison still lack…

Alchemical and structural distribution based representation for universal quantum machine learning

NASA Astrophysics Data System (ADS)

Faber, Felix A.; Christensen, Anders S.; Huang, Bing; von Lilienfeld, O. Anatole

2018-06-01

We introduce a representation of any atom in any chemical environment for the automatized generation of universal kernel ridge regression-based quantum machine learning (QML) models of electronic properties, trained throughout chemical compound space. The representation is based on Gaussian distribution functions, scaled by power laws and explicitly accounting for structural as well as elemental degrees of freedom. The elemental components help us to lower the QML model's learning curve, and, through interpolation across the periodic table, even enable "alchemical extrapolation" to covalent bonding between elements not part of training. This point is demonstrated for the prediction of covalent binding in single, double, and triple bonds among main-group elements as well as for atomization energies in organic molecules. We present numerical evidence that resulting QML energy models, after training on a few thousand random training instances, reach chemical accuracy for out-of-sample compounds. Compound datasets studied include thousands of structurally and compositionally diverse organic molecules, non-covalently bonded protein side-chains, (H2O)40-clusters, and crystalline solids. Learning curves for QML models also indicate competitive predictive power for various other electronic ground state properties of organic molecules, calculated with hybrid density functional theory, including polarizability, heat-capacity, HOMO-LUMO eigenvalues and gap, zero point vibrational energy, dipole moment, and highest vibrational fundamental frequency.

Deep Recurrent Neural Networks for Human Activity Recognition

PubMed Central

Murad, Abdulmajid

2017-01-01

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs. PMID:29113103

Deep Recurrent Neural Networks for Human Activity Recognition.

PubMed

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

Classification of hadith into positive suggestion, negative suggestion, and information

NASA Astrophysics Data System (ADS)

Faraby, Said Al; Riviera Rachmawati Jasin, Eliza; Kusumaningrum, Andina; Adiwijaya

2018-03-01

As one of the Muslim life guidelines, based on the meaning of its sentence(s), a hadith can be viewed as a suggestion for doing something, or a suggestion for not doing something, or just information without any suggestion. In this paper, we tried to classify the Bahasa translation of hadith into the three categories using machine learning approach. We tried stemming and stopword removal in preprocessing, and TF-IDF of unigram, bigram, and trigram as the extracted features. As the classifier, we compared between SVM and Neural Network. Since the categories are new, so in order to compare the results of the previous pipelines, we created a baseline classifier using simple rule-based string matching technique. The rule-based algorithm conditions on the occurrence of words such as “janganlah, sholatlah, and so on” to determine the category. The baseline method achieved F1-Score of 0.69, while the best F1-Score from the machine learning approach was 0.88, and it was produced by SVM model with the linear kernel.

Scalable Machine Learning for Massive Astronomical Datasets

NASA Astrophysics Data System (ADS)

Ball, Nicholas M.; Gray, A.

2014-04-01

We present the ability to perform data mining and machine learning operations on a catalog of half a billion astronomical objects. This is the result of the combination of robust, highly accurate machine learning algorithms with linear scalability that renders the applications of these algorithms to massive astronomical data tractable. We demonstrate the core algorithms kernel density estimation, K-means clustering, linear regression, nearest neighbors, random forest and gradient-boosted decision tree, singular value decomposition, support vector machine, and two-point correlation function. Each of these is relevant for astronomical applications such as finding novel astrophysical objects, characterizing artifacts in data, object classification (including for rare objects), object distances, finding the important features describing objects, density estimation of distributions, probabilistic quantities, and exploring the unknown structure of new data. The software, Skytree Server, runs on any UNIX-based machine, a virtual machine, or cloud-based and distributed systems including Hadoop. We have integrated it on the cloud computing system of the Canadian Astronomical Data Centre, the Canadian Advanced Network for Astronomical Research (CANFAR), creating the world's first cloud computing data mining system for astronomy. We demonstrate results showing the scaling of each of our major algorithms on large astronomical datasets, including the full 470,992,970 objects of the 2 Micron All-Sky Survey (2MASS) Point Source Catalog. We demonstrate the ability to find outliers in the full 2MASS dataset utilizing multiple methods, e.g., nearest neighbors. This is likely of particular interest to the radio astronomy community given, for example, that survey projects contain groups dedicated to this topic. 2MASS is used as a proof-of-concept dataset due to its convenience and availability. These results are of interest to any astronomical project with large and/or complex datasets that wishes to extract the full scientific value from its data.

Scalable Machine Learning for Massive Astronomical Datasets

NASA Astrophysics Data System (ADS)

Ball, Nicholas M.; Astronomy Data Centre, Canadian

2014-01-01

We present the ability to perform data mining and machine learning operations on a catalog of half a billion astronomical objects. This is the result of the combination of robust, highly accurate machine learning algorithms with linear scalability that renders the applications of these algorithms to massive astronomical data tractable. We demonstrate the core algorithms kernel density estimation, K-means clustering, linear regression, nearest neighbors, random forest and gradient-boosted decision tree, singular value decomposition, support vector machine, and two-point correlation function. Each of these is relevant for astronomical applications such as finding novel astrophysical objects, characterizing artifacts in data, object classification (including for rare objects), object distances, finding the important features describing objects, density estimation of distributions, probabilistic quantities, and exploring the unknown structure of new data. The software, Skytree Server, runs on any UNIX-based machine, a virtual machine, or cloud-based and distributed systems including Hadoop. We have integrated it on the cloud computing system of the Canadian Astronomical Data Centre, the Canadian Advanced Network for Astronomical Research (CANFAR), creating the world's first cloud computing data mining system for astronomy. We demonstrate results showing the scaling of each of our major algorithms on large astronomical datasets, including the full 470,992,970 objects of the 2 Micron All-Sky Survey (2MASS) Point Source Catalog. We demonstrate the ability to find outliers in the full 2MASS dataset utilizing multiple methods, e.g., nearest neighbors, and the local outlier factor. 2MASS is used as a proof-of-concept dataset due to its convenience and availability. These results are of interest to any astronomical project with large and/or complex datasets that wishes to extract the full scientific value from its data.

Anytime query-tuned kernel machine classifiers via Cholesky factorization

NASA Technical Reports Server (NTRS)

DeCoste, D.

2002-01-01

We recently demonstrated 2 to 64-fold query-time speedups of Support Vector Machine and Kernel Fisher classifiers via a new computational geometry method for anytime output bounds (DeCoste,2002). This new paper refines our approach in two key ways. First, we introduce a simple linear algebra formulation based on Cholesky factorization, yielding simpler equations and lower computational overhead. Second, this new formulation suggests new methods for achieving additional speedups, including tuning on query samples. We demonstrate effectiveness on benchmark datasets.

Multi-task feature learning by using trace norm regularization

NASA Astrophysics Data System (ADS)

Jiangmei, Zhang; Binfeng, Yu; Haibo, Ji; Wang, Kunpeng

2017-11-01

Multi-task learning can extract the correlation of multiple related machine learning problems to improve performance. This paper considers applying the multi-task learning method to learn a single task. We propose a new learning approach, which employs the mixture of expert model to divide a learning task into several related sub-tasks, and then uses the trace norm regularization to extract common feature representation of these sub-tasks. A nonlinear extension of this approach by using kernel is also provided. Experiments conducted on both simulated and real data sets demonstrate the advantage of the proposed approach.

In silico toxicity prediction by support vector machine and SMILES representation-based string kernel.

PubMed

Cao, D-S; Zhao, J-C; Yang, Y-N; Zhao, C-X; Yan, J; Liu, S; Hu, Q-N; Xu, Q-S; Liang, Y-Z

2012-01-01

There is a great need to assess the harmful effects or toxicities of chemicals to which man is exposed. In the present paper, the simplified molecular input line entry specification (SMILES) representation-based string kernel, together with the state-of-the-art support vector machine (SVM) algorithm, were used to classify the toxicity of chemicals from the US Environmental Protection Agency Distributed Structure-Searchable Toxicity (DSSTox) database network. In this method, the molecular structure can be directly encoded by a series of SMILES substrings that represent the presence of some chemical elements and different kinds of chemical bonds (double, triple and stereochemistry) in the molecules. Thus, SMILES string kernel can accurately and directly measure the similarities of molecules by a series of local information hidden in the molecules. Two model validation approaches, five-fold cross-validation and independent validation set, were used for assessing the predictive capability of our developed models. The results obtained indicate that SVM based on the SMILES string kernel can be regarded as a very promising and alternative modelling approach for potential toxicity prediction of chemicals.

Development of a kernel function for clinical data.

PubMed

Daemen, Anneleen; De Moor, Bart

2009-01-01

For most diseases and examinations, clinical data such as age, gender and medical history guides clinical management, despite the rise of high-throughput technologies. To fully exploit such clinical information, appropriate modeling of relevant parameters is required. As the widely used linear kernel function has several disadvantages when applied to clinical data, we propose a new kernel function specifically developed for this data. This "clinical kernel function" more accurately represents similarities between patients. Evidently, three data sets were studied and significantly better performances were obtained with a Least Squares Support Vector Machine when based on the clinical kernel function compared to the linear kernel function.

Statistical analysis and machine learning algorithms for optical biopsy

NASA Astrophysics Data System (ADS)

Wu, Binlin; Liu, Cheng-hui; Boydston-White, Susie; Beckman, Hugh; Sriramoju, Vidyasagar; Sordillo, Laura; Zhang, Chunyuan; Zhang, Lin; Shi, Lingyan; Smith, Jason; Bailin, Jacob; Alfano, Robert R.

2018-02-01

Analyzing spectral or imaging data collected with various optical biopsy methods is often times difficult due to the complexity of the biological basis. Robust methods that can utilize the spectral or imaging data and detect the characteristic spectral or spatial signatures for different types of tissue is challenging but highly desired. In this study, we used various machine learning algorithms to analyze a spectral dataset acquired from human skin normal and cancerous tissue samples using resonance Raman spectroscopy with 532nm excitation. The algorithms including principal component analysis, nonnegative matrix factorization, and autoencoder artificial neural network are used to reduce dimension of the dataset and detect features. A support vector machine with a linear kernel is used to classify the normal tissue and cancerous tissue samples. The efficacies of the methods are compared.

Predicting radiotherapy outcomes using statistical learning techniques

NASA Astrophysics Data System (ADS)

El Naqa, Issam; Bradley, Jeffrey D.; Lindsay, Patricia E.; Hope, Andrew J.; Deasy, Joseph O.

2009-09-01

Radiotherapy outcomes are determined by complex interactions between treatment, anatomical and patient-related variables. A common obstacle to building maximally predictive outcome models for clinical practice is the failure to capture potential complexity of heterogeneous variable interactions and applicability beyond institutional data. We describe a statistical learning methodology that can automatically screen for nonlinear relations among prognostic variables and generalize to unseen data before. In this work, several types of linear and nonlinear kernels to generate interaction terms and approximate the treatment-response function are evaluated. Examples of institutional datasets of esophagitis, pneumonitis and xerostomia endpoints were used. Furthermore, an independent RTOG dataset was used for 'generalizabilty' validation. We formulated the discrimination between risk groups as a supervised learning problem. The distribution of patient groups was initially analyzed using principle components analysis (PCA) to uncover potential nonlinear behavior. The performance of the different methods was evaluated using bivariate correlations and actuarial analysis. Over-fitting was controlled via cross-validation resampling. Our results suggest that a modified support vector machine (SVM) kernel method provided superior performance on leave-one-out testing compared to logistic regression and neural networks in cases where the data exhibited nonlinear behavior on PCA. For instance, in prediction of esophagitis and pneumonitis endpoints, which exhibited nonlinear behavior on PCA, the method provided 21% and 60% improvements, respectively. Furthermore, evaluation on the independent pneumonitis RTOG dataset demonstrated good generalizabilty beyond institutional data in contrast with other models. This indicates that the prediction of treatment response can be improved by utilizing nonlinear kernel methods for discovering important nonlinear interactions among model variables. These models have the capacity to predict on unseen data. Part of this work was first presented at the Seventh International Conference on Machine Learning and Applications, San Diego, CA, USA, 11-13 December 2008.

A Network-Based Kernel Machine Test for the Identification of Risk Pathways in Genome-Wide Association Studies

PubMed Central

Freytag, Saskia; Manitz, Juliane; Schlather, Martin; Kneib, Thomas; Amos, Christopher I.; Risch, Angela; Chang-Claude, Jenny; Heinrich, Joachim; Bickeböller, Heike

2014-01-01

Biological pathways provide rich information and biological context on the genetic causes of complex diseases. The logistic kernel machine test integrates prior knowledge on pathways in order to analyze data from genome-wide association studies (GWAS). Here, the kernel converts genomic information of two individuals to a quantitative value reflecting their genetic similarity. With the selection of the kernel one implicitly chooses a genetic effect model. Like many other pathway methods, none of the available kernels accounts for topological structure of the pathway or gene-gene interaction types. However, evidence indicates that connectivity and neighborhood of genes are crucial in the context of GWAS, because genes associated with a disease often interact. Thus, we propose a novel kernel that incorporates the topology of pathways and information on interactions. Using simulation studies, we demonstrate that the proposed method maintains the type I error correctly and can be more effective in the identification of pathways associated with a disease than non-network-based methods. We apply our approach to genome-wide association case control data on lung cancer and rheumatoid arthritis. We identify some promising new pathways associated with these diseases, which may improve our current understanding of the genetic mechanisms. PMID:24434848

The identification of high potential archers based on fitness and motor ability variables: A Support Vector Machine approach.

PubMed

Taha, Zahari; Musa, Rabiu Muazu; P P Abdul Majeed, Anwar; Alim, Muhammad Muaz; Abdullah, Mohamad Razali

2018-02-01

Support Vector Machine (SVM) has been shown to be an effective learning algorithm for classification and prediction. However, the application of SVM for prediction and classification in specific sport has rarely been used to quantify/discriminate low and high-performance athletes. The present study classified and predicted high and low-potential archers from a set of fitness and motor ability variables trained on different SVMs kernel algorithms. 50 youth archers with the mean age and standard deviation of 17.0 ± 0.6 years drawn from various archery programmes completed a six arrows shooting score test. Standard fitness and ability measurements namely hand grip, vertical jump, standing broad jump, static balance, upper muscle strength and the core muscle strength were also recorded. Hierarchical agglomerative cluster analysis (HACA) was used to cluster the archers based on the performance variables tested. SVM models with linear, quadratic, cubic, fine RBF, medium RBF, as well as the coarse RBF kernel functions, were trained based on the measured performance variables. The HACA clustered the archers into high-potential archers (HPA) and low-potential archers (LPA), respectively. The linear, quadratic, cubic, as well as the medium RBF kernel functions models, demonstrated reasonably excellent classification accuracy of 97.5% and 2.5% error rate for the prediction of the HPA and the LPA. The findings of this investigation can be valuable to coaches and sports managers to recognise high potential athletes from a combination of the selected few measured fitness and motor ability performance variables examined which would consequently save cost, time and effort during talent identification programme. Copyright © 2017 Elsevier B.V. All rights reserved.

Improving Classification Performance through an Advanced Ensemble Based Heterogeneous Extreme Learning Machines.

PubMed

Abuassba, Adnan O M; Zhang, Dezheng; Luo, Xiong; Shaheryar, Ahmad; Ali, Hazrat

2017-01-01

Extreme Learning Machine (ELM) is a fast-learning algorithm for a single-hidden layer feedforward neural network (SLFN). It often has good generalization performance. However, there are chances that it might overfit the training data due to having more hidden nodes than needed. To address the generalization performance, we use a heterogeneous ensemble approach. We propose an Advanced ELM Ensemble (AELME) for classification, which includes Regularized-ELM, L 2 -norm-optimized ELM (ELML2), and Kernel-ELM. The ensemble is constructed by training a randomly chosen ELM classifier on a subset of training data selected through random resampling. The proposed AELM-Ensemble is evolved by employing an objective function of increasing diversity and accuracy among the final ensemble. Finally, the class label of unseen data is predicted using majority vote approach. Splitting the training data into subsets and incorporation of heterogeneous ELM classifiers result in higher prediction accuracy, better generalization, and a lower number of base classifiers, as compared to other models (Adaboost, Bagging, Dynamic ELM ensemble, data splitting ELM ensemble, and ELM ensemble). The validity of AELME is confirmed through classification on several real-world benchmark datasets.

Improving Classification Performance through an Advanced Ensemble Based Heterogeneous Extreme Learning Machines

PubMed Central

Abuassba, Adnan O. M.; Ali, Hazrat

2017-01-01

Extreme Learning Machine (ELM) is a fast-learning algorithm for a single-hidden layer feedforward neural network (SLFN). It often has good generalization performance. However, there are chances that it might overfit the training data due to having more hidden nodes than needed. To address the generalization performance, we use a heterogeneous ensemble approach. We propose an Advanced ELM Ensemble (AELME) for classification, which includes Regularized-ELM, L2-norm-optimized ELM (ELML2), and Kernel-ELM. The ensemble is constructed by training a randomly chosen ELM classifier on a subset of training data selected through random resampling. The proposed AELM-Ensemble is evolved by employing an objective function of increasing diversity and accuracy among the final ensemble. Finally, the class label of unseen data is predicted using majority vote approach. Splitting the training data into subsets and incorporation of heterogeneous ELM classifiers result in higher prediction accuracy, better generalization, and a lower number of base classifiers, as compared to other models (Adaboost, Bagging, Dynamic ELM ensemble, data splitting ELM ensemble, and ELM ensemble). The validity of AELME is confirmed through classification on several real-world benchmark datasets. PMID:28546808

Electron beam lithographic modeling assisted by artificial intelligence technology

NASA Astrophysics Data System (ADS)

Nakayamada, Noriaki; Nishimura, Rieko; Miura, Satoru; Nomura, Haruyuki; Kamikubo, Takashi

2017-07-01

We propose a new concept of tuning a point-spread function (a "kernel" function) in the modeling of electron beam lithography using the machine learning scheme. Normally in the work of artificial intelligence, the researchers focus on the output results from a neural network, such as success ratio in image recognition or improved production yield, etc. In this work, we put more focus on the weights connecting the nodes in a convolutional neural network, which are naturally the fractions of a point-spread function, and take out those weighted fractions after learning to be utilized as a tuned kernel. Proof-of-concept of the kernel tuning has been demonstrated using the examples of proximity effect correction with 2-layer network, and charging effect correction with 3-layer network. This type of new tuning method can be beneficial to give researchers more insights to come up with a better model, yet it might be too early to be deployed to production to give better critical dimension (CD) and positional accuracy almost instantly.

FLUXCOM - Overview and First Synthesis

NASA Astrophysics Data System (ADS)

Jung, M.; Ichii, K.; Tramontana, G.; Camps-Valls, G.; Schwalm, C. R.; Papale, D.; Reichstein, M.; Gans, F.; Weber, U.

2015-12-01

We present a community effort aiming at generating an ensemble of global gridded flux products by upscaling FLUXNET data using an array of different machine learning methods including regression/model tree ensembles, neural networks, and kernel machines. We produced products for gross primary production, terrestrial ecosystem respiration, net ecosystem exchange, latent heat, sensible heat, and net radiation for two experimental protocols: 1) at a high spatial and 8-daily temporal resolution (5 arc-minute) using only remote sensing based inputs for the MODIS era; 2) 30 year records of daily, 0.5 degree spatial resolution by incorporating meteorological driver data. Within each set-up, all machine learning methods were trained with the same input data for carbon and energy fluxes respectively. Sets of input driver variables were derived using an extensive formal variable selection exercise. The performance of the extrapolation capacities of the approaches is assessed with a fully internally consistent cross-validation. We perform cross-consistency checks of the gridded flux products with independent data streams from atmospheric inversions (NEE), sun-induced fluorescence (GPP), catchment water balances (LE, H), satellite products (Rn), and process-models. We analyze the uncertainties of the gridded flux products and for example provide a breakdown of the uncertainty of mean annual GPP originating from different machine learning methods, different climate input data sets, and different flux partitioning methods. The FLUXCOM archive will provide an unprecedented source of information for water, energy, and carbon cycle studies.

Bayesian Correlation Analysis for Sequence Count Data

PubMed Central

Lau, Nelson; Perkins, Theodore J.

2016-01-01

Evaluating the similarity of different measured variables is a fundamental task of statistics, and a key part of many bioinformatics algorithms. Here we propose a Bayesian scheme for estimating the correlation between different entities’ measurements based on high-throughput sequencing data. These entities could be different genes or miRNAs whose expression is measured by RNA-seq, different transcription factors or histone marks whose expression is measured by ChIP-seq, or even combinations of different types of entities. Our Bayesian formulation accounts for both measured signal levels and uncertainty in those levels, due to varying sequencing depth in different experiments and to varying absolute levels of individual entities, both of which affect the precision of the measurements. In comparison with a traditional Pearson correlation analysis, we show that our Bayesian correlation analysis retains high correlations when measurement confidence is high, but suppresses correlations when measurement confidence is low—especially for entities with low signal levels. In addition, we consider the influence of priors on the Bayesian correlation estimate. Perhaps surprisingly, we show that naive, uniform priors on entities’ signal levels can lead to highly biased correlation estimates, particularly when different experiments have widely varying sequencing depths. However, we propose two alternative priors that provably mitigate this problem. We also prove that, like traditional Pearson correlation, our Bayesian correlation calculation constitutes a kernel in the machine learning sense, and thus can be used as a similarity measure in any kernel-based machine learning algorithm. We demonstrate our approach on two RNA-seq datasets and one miRNA-seq dataset. PMID:27701449

Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm.

PubMed

Jinnouchi, Ryosuke; Asahi, Ryoji

2017-09-07

Catalytic activities are often dominated by a few specific surface sites, and designing active sites is the key to realize high-performance heterogeneous catalysts. The great triumphs of modern surface science lead to reproduce catalytic reaction rates by modeling the arrangement of surface atoms with well-defined single-crystal surfaces. However, this method has limitations in the case for highly inhomogeneous atomic configurations such as on alloy nanoparticles with atomic-scale defects, where the arrangement cannot be decomposed into single crystals. Here, we propose a universal machine-learning scheme using a local similarity kernel, which allows interrogation of catalytic activities based on local atomic configurations. We then apply it to direct NO decomposition on RhAu alloy nanoparticles. The proposed method can efficiently predict energetics of catalytic reactions on nanoparticles using DFT data on single crystals, and its combination with kinetic analysis can provide detailed information on structures of active sites and size- and composition-dependent catalytic activities.

Mexican Hat Wavelet Kernel ELM for Multiclass Classification.

PubMed

Wang, Jie; Song, Yi-Fan; Ma, Tian-Lei

2017-01-01

Kernel extreme learning machine (KELM) is a novel feedforward neural network, which is widely used in classification problems. To some extent, it solves the existing problems of the invalid nodes and the large computational complexity in ELM. However, the traditional KELM classifier usually has a low test accuracy when it faces multiclass classification problems. In order to solve the above problem, a new classifier, Mexican Hat wavelet KELM classifier, is proposed in this paper. The proposed classifier successfully improves the training accuracy and reduces the training time in the multiclass classification problems. Moreover, the validity of the Mexican Hat wavelet as a kernel function of ELM is rigorously proved. Experimental results on different data sets show that the performance of the proposed classifier is significantly superior to the compared classifiers.

G-Hash: Towards Fast Kernel-based Similarity Search in Large Graph Databases.

PubMed

Wang, Xiaohong; Smalter, Aaron; Huan, Jun; Lushington, Gerald H

2009-01-01

Structured data including sets, sequences, trees and graphs, pose significant challenges to fundamental aspects of data management such as efficient storage, indexing, and similarity search. With the fast accumulation of graph databases, similarity search in graph databases has emerged as an important research topic. Graph similarity search has applications in a wide range of domains including cheminformatics, bioinformatics, sensor network management, social network management, and XML documents, among others.Most of the current graph indexing methods focus on subgraph query processing, i.e. determining the set of database graphs that contains the query graph and hence do not directly support similarity search. In data mining and machine learning, various graph kernel functions have been designed to capture the intrinsic similarity of graphs. Though successful in constructing accurate predictive and classification models for supervised learning, graph kernel functions have (i) high computational complexity and (ii) non-trivial difficulty to be indexed in a graph database.Our objective is to bridge graph kernel function and similarity search in graph databases by proposing (i) a novel kernel-based similarity measurement and (ii) an efficient indexing structure for graph data management. Our method of similarity measurement builds upon local features extracted from each node and their neighboring nodes in graphs. A hash table is utilized to support efficient storage and fast search of the extracted local features. Using the hash table, a graph kernel function is defined to capture the intrinsic similarity of graphs and for fast similarity query processing. We have implemented our method, which we have named G-hash, and have demonstrated its utility on large chemical graph databases. Our results show that the G-hash method achieves state-of-the-art performance for k-nearest neighbor (k-NN) classification. Most importantly, the new similarity measurement and the index structure is scalable to large database with smaller indexing size, faster indexing construction time, and faster query processing time as compared to state-of-the-art indexing methods such as C-tree, gIndex, and GraphGrep.

Arbitrary norm support vector machines.

PubMed

Huang, Kaizhu; Zheng, Danian; King, Irwin; Lyu, Michael R

2009-02-01

Support vector machines (SVM) are state-of-the-art classifiers. Typically L2-norm or L1-norm is adopted as a regularization term in SVMs, while other norm-based SVMs, for example, the L0-norm SVM or even the L(infinity)-norm SVM, are rarely seen in the literature. The major reason is that L0-norm describes a discontinuous and nonconvex term, leading to a combinatorially NP-hard optimization problem. In this letter, motivated by Bayesian learning, we propose a novel framework that can implement arbitrary norm-based SVMs in polynomial time. One significant feature of this framework is that only a sequence of sequential minimal optimization problems needs to be solved, thus making it practical in many real applications. The proposed framework is important in the sense that Bayesian priors can be efficiently plugged into most learning methods without knowing the explicit form. Hence, this builds a connection between Bayesian learning and the kernel machines. We derive the theoretical framework, demonstrate how our approach works on the L0-norm SVM as a typical example, and perform a series of experiments to validate its advantages. Experimental results on nine benchmark data sets are very encouraging. The implemented L0-norm is competitive with or even better than the standard L2-norm SVM in terms of accuracy but with a reduced number of support vectors, -9.46% of the number on average. When compared with another sparse model, the relevance vector machine, our proposed algorithm also demonstrates better sparse properties with a training speed over seven times faster.

Fast Gaussian kernel learning for classification tasks based on specially structured global optimization.

PubMed

Zhong, Shangping; Chen, Tianshun; He, Fengying; Niu, Yuzhen

2014-09-01

For a practical pattern classification task solved by kernel methods, the computing time is mainly spent on kernel learning (or training). However, the current kernel learning approaches are based on local optimization techniques, and hard to have good time performances, especially for large datasets. Thus the existing algorithms cannot be easily extended to large-scale tasks. In this paper, we present a fast Gaussian kernel learning method by solving a specially structured global optimization (SSGO) problem. We optimize the Gaussian kernel function by using the formulated kernel target alignment criterion, which is a difference of increasing (d.i.) functions. Through using a power-transformation based convexification method, the objective criterion can be represented as a difference of convex (d.c.) functions with a fixed power-transformation parameter. And the objective programming problem can then be converted to a SSGO problem: globally minimizing a concave function over a convex set. The SSGO problem is classical and has good solvability. Thus, to find the global optimal solution efficiently, we can adopt the improved Hoffman's outer approximation method, which need not repeat the searching procedure with different starting points to locate the best local minimum. Also, the proposed method can be proven to converge to the global solution for any classification task. We evaluate the proposed method on twenty benchmark datasets, and compare it with four other Gaussian kernel learning methods. Experimental results show that the proposed method stably achieves both good time-efficiency performance and good classification performance. Copyright © 2014 Elsevier Ltd. All rights reserved.

Application of machine learning using support vector machines for crater detection from Martian digital topography data

NASA Astrophysics Data System (ADS)

Salamunićcar, Goran; Lončarić, Sven

In our previous work, in order to extend the GT-57633 catalogue [PSS, 56 (15), 1992-2008] with still uncatalogued impact-craters, the following has been done [GRS, 48 (5), in press, doi:10.1109/TGRS.2009.2037750]: (1) the crater detection algorithm (CDA) based on digital elevation model (DEM) was developed; (2) using 1/128° MOLA data, this CDA proposed 414631 crater-candidates; (3) each crater-candidate was analyzed manually; and (4) 57592 were confirmed as correct detections. The resulting GT-115225 catalog is the significant result of this effort. However, to check such a large number of crater-candidates manually was a demanding task. This was the main motivation for work on improvement of the CDA in order to provide better classification of craters as true and false detections. To achieve this, we extended the CDA with the machine learning capability, using support vector machines (SVM). In the first step, the CDA (re)calculates numerous terrain morphometric attributes from DEM. For this purpose, already existing modules of the CDA from our previous work were reused in order to be capable to prepare these attributes. In addition, new attributes were introduced such as ellipse eccentricity and tilt. For machine learning purpose, the CDA is additionally extended to provide 2-D topography-profile and 3-D shape for each crater-candidate. The latter two are a performance problem because of the large number of crater-candidates in combination with the large number of attributes. As a solution, we developed a CDA architecture wherein it is possible to combine the SVM with a radial basis function (RBF) or any other kernel (for initial set of attributes), with the SVM with linear kernel (for the cases when 2-D and 3-D data are included as well). Another challenge is that, in addition to diversity of possible crater types, there are numerous morphological differences between the smallest (mostly very circular bowl-shaped craters) and the largest (multi-ring) impact craters. As a solution to this problem, the CDA classifies crater-candidates according to their diameter into 7 groups (D smaller/larger then 2km, 4km, 8km, 16km, 32km and 64km), and for each group uses separate SVMs for training and prediction. For implementation of the machine-learning part and integration with the rest of the CDA, we used C.-J. Lin's et al. [http://www.csie.ntu.edu.tw/˜cjlin/] LIBSVM (A Library for Support Vector Machines) and LIBLINEAR (A Library for Large Linear Classification) libraries. According to the initial evaluation, now the CDA provides much better classification of craters as true and false detections.

Improving the performance of extreme learning machine for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Li, Jiaojiao; Du, Qian; Li, Wei; Li, Yunsong

2015-05-01

Extreme learning machine (ELM) and kernel ELM (KELM) can offer comparable performance as the standard powerful classifier―support vector machine (SVM), but with much lower computational cost due to extremely simple training step. However, their performance may be sensitive to several parameters, such as the number of hidden neurons. An empirical linear relationship between the number of training samples and the number of hidden neurons is proposed. Such a relationship can be easily estimated with two small training sets and extended to large training sets so as to greatly reduce computational cost. Other parameters, such as the steepness parameter in the sigmodal activation function and regularization parameter in the KELM, are also investigated. The experimental results show that classification performance is sensitive to these parameters; fortunately, simple selections will result in suboptimal performance.

A Classification of Remote Sensing Image Based on Improved Compound Kernels of Svm

NASA Astrophysics Data System (ADS)

Zhao, Jianing; Gao, Wanlin; Liu, Zili; Mou, Guifen; Lu, Lin; Yu, Lina

The accuracy of RS classification based on SVM which is developed from statistical learning theory is high under small number of train samples, which results in satisfaction of classification on RS using SVM methods. The traditional RS classification method combines visual interpretation with computer classification. The accuracy of the RS classification, however, is improved a lot based on SVM method, because it saves much labor and time which is used to interpret images and collect training samples. Kernel functions play an important part in the SVM algorithm. It uses improved compound kernel function and therefore has a higher accuracy of classification on RS images. Moreover, compound kernel improves the generalization and learning ability of the kernel.

A comparative study of surface EMG classification by fuzzy relevance vector machine and fuzzy support vector machine.

PubMed

Xie, Hong-Bo; Huang, Hu; Wu, Jianhua; Liu, Lei

2015-02-01

We present a multiclass fuzzy relevance vector machine (FRVM) learning mechanism and evaluate its performance to classify multiple hand motions using surface electromyographic (sEMG) signals. The relevance vector machine (RVM) is a sparse Bayesian kernel method which avoids some limitations of the support vector machine (SVM). However, RVM still suffers the difficulty of possible unclassifiable regions in multiclass problems. We propose two fuzzy membership function-based FRVM algorithms to solve such problems, based on experiments conducted on seven healthy subjects and two amputees with six hand motions. Two feature sets, namely, AR model coefficients and room mean square value (AR-RMS), and wavelet transform (WT) features, are extracted from the recorded sEMG signals. Fuzzy support vector machine (FSVM) analysis was also conducted for wide comparison in terms of accuracy, sparsity, training and testing time, as well as the effect of training sample sizes. FRVM yielded comparable classification accuracy with dramatically fewer support vectors in comparison with FSVM. Furthermore, the processing delay of FRVM was much less than that of FSVM, whilst training time of FSVM much faster than FRVM. The results indicate that FRVM classifier trained using sufficient samples can achieve comparable generalization capability as FSVM with significant sparsity in multi-channel sEMG classification, which is more suitable for sEMG-based real-time control applications.

Towards smart energy systems: application of kernel machine regression for medium term electricity load forecasting.

PubMed

Alamaniotis, Miltiadis; Bargiotas, Dimitrios; Tsoukalas, Lefteri H

2016-01-01

Integration of energy systems with information technologies has facilitated the realization of smart energy systems that utilize information to optimize system operation. To that end, crucial in optimizing energy system operation is the accurate, ahead-of-time forecasting of load demand. In particular, load forecasting allows planning of system expansion, and decision making for enhancing system safety and reliability. In this paper, the application of two types of kernel machines for medium term load forecasting (MTLF) is presented and their performance is recorded based on a set of historical electricity load demand data. The two kernel machine models and more specifically Gaussian process regression (GPR) and relevance vector regression (RVR) are utilized for making predictions over future load demand. Both models, i.e., GPR and RVR, are equipped with a Gaussian kernel and are tested on daily predictions for a 30-day-ahead horizon taken from the New England Area. Furthermore, their performance is compared to the ARMA(2,2) model with respect to mean average percentage error and squared correlation coefficient. Results demonstrate the superiority of RVR over the other forecasting models in performing MTLF.

Machine learning study for the prediction of transdermal peptide

NASA Astrophysics Data System (ADS)

Jung, Eunkyoung; Choi, Seung-Hoon; Lee, Nam Kyung; Kang, Sang-Kee; Choi, Yun-Jaie; Shin, Jae-Min; Choi, Kihang; Jung, Dong Hyun

2011-04-01

In order to develop a computational method to rapidly evaluate transdermal peptides, we report approaches for predicting the transdermal activity of peptides on the basis of peptide sequence information using Artificial Neural Network (ANN), Partial Least Squares (PLS) and Support Vector Machine (SVM). We identified 269 transdermal peptides by the phage display technique and use them as the positive controls to develop and test machine learning models. Combinations of three descriptors with neural network architectures, the number of latent variables and the kernel functions are tried in training to make appropriate predictions. The capacity of models is evaluated by means of statistical indicators including sensitivity, specificity, and the area under the receiver operating characteristic curve (ROC score). In the ROC score-based comparison, three methods proved capable of providing a reasonable prediction of transdermal peptide. The best result is obtained by SVM model with a radial basis function and VHSE descriptors. The results indicate that it is possible to discriminate between transdermal peptides and random sequences using our models. We anticipate that our models will be applicable to prediction of transdermal peptide for large peptide database for facilitating efficient transdermal drug delivery through intact skin.

Sitting Posture Monitoring System Based on a Low-Cost Load Cell Using Machine Learning

PubMed Central

Roh, Jongryun; Park, Hyeong-jun; Lee, Kwang Jin; Hyeong, Joonho; Kim, Sayup

2018-01-01

Sitting posture monitoring systems (SPMSs) help assess the posture of a seated person in real-time and improve sitting posture. To date, SPMS studies reported have required many sensors mounted on the backrest plate and seat plate of a chair. The present study, therefore, developed a system that measures a total of six sitting postures including the posture that applied a load to the backrest plate, with four load cells mounted only on the seat plate. Various machine learning algorithms were applied to the body weight ratio measured by the developed SPMS to identify the method that most accurately classified the actual sitting posture of the seated person. After classifying the sitting postures using several classifiers, average and maximum classification rates of 97.20% and 97.94%, respectively, were obtained from nine subjects with a support vector machine using the radial basis function kernel; the results obtained by this classifier showed a statistically significant difference from the results of multiple classifications using other classifiers. The proposed SPMS was able to classify six sitting postures including the posture with loading on the backrest and showed the possibility of classifying the sitting posture even though the number of sensors is reduced. PMID:29329261

Structured Kernel Subspace Learning for Autonomous Robot Navigation.

PubMed

Kim, Eunwoo; Choi, Sungjoon; Oh, Songhwai

2018-02-14

This paper considers two important problems for autonomous robot navigation in a dynamic environment, where the goal is to predict pedestrian motion and control a robot with the prediction for safe navigation. While there are several methods for predicting the motion of a pedestrian and controlling a robot to avoid incoming pedestrians, it is still difficult to safely navigate in a dynamic environment due to challenges, such as the varying quality and complexity of training data with unwanted noises. This paper addresses these challenges simultaneously by proposing a robust kernel subspace learning algorithm based on the recent advances in nuclear-norm and l 1 -norm minimization. We model the motion of a pedestrian and the robot controller using Gaussian processes. The proposed method efficiently approximates a kernel matrix used in Gaussian process regression by learning low-rank structured matrix (with symmetric positive semi-definiteness) to find an orthogonal basis, which eliminates the effects of erroneous and inconsistent data. Based on structured kernel subspace learning, we propose a robust motion model and motion controller for safe navigation in dynamic environments. We evaluate the proposed robust kernel learning in various tasks, including regression, motion prediction, and motion control problems, and demonstrate that the proposed learning-based systems are robust against outliers and outperform existing regression and navigation methods.

Screening Electronic Health Record-Related Patient Safety Reports Using Machine Learning.

PubMed

Marella, William M; Sparnon, Erin; Finley, Edward

2017-03-01

The objective of this study was to develop a semiautomated approach to screening cases that describe hazards associated with the electronic health record (EHR) from a mandatory, population-based patient safety reporting system. Potentially relevant cases were identified through a query of the Pennsylvania Patient Safety Reporting System. A random sample of cases were manually screened for relevance and divided into training, testing, and validation data sets to develop a machine learning model. This model was used to automate screening of remaining potentially relevant cases. Of the 4 algorithms tested, a naive Bayes kernel performed best, with an area under the receiver operating characteristic curve of 0.927 ± 0.023, accuracy of 0.855 ± 0.033, and F score of 0.877 ± 0.027. The machine learning model and text mining approach described here are useful tools for identifying and analyzing adverse event and near-miss reports. Although reporting systems are beginning to incorporate structured fields on health information technology and the EHR, these methods can identify related events that reporters classify in other ways. These methods can facilitate analysis of legacy safety reports by retrieving health information technology-related and EHR-related events from databases without fields and controlled values focused on this subject and distinguishing them from reports in which the EHR is mentioned only in passing. Machine learning and text mining are useful additions to the patient safety toolkit and can be used to semiautomate screening and analysis of unstructured text in safety reports from frontline staff.

The association between the availability of sugar-sweetened beverage in school vending machines and its consumption among adolescents in California: a propensity score matching approach.

PubMed

Shi, Lu

2010-01-01

There is controversy over to what degree banning sugar-sweetened beverage (SSB) sales at schools could decrease the SSB intake. This paper uses the adolescent sample of 2005 California Health Interview Survey to estimate the association between the availability of SSB from school vending machines and the amount of SSB consumption. Propensity score stratification and kernel-based propensity score matching are used to address the selection bias issue in cross-sectional data. Propensity score stratification shows that adolescents who had access to SSB through their school vending machines consumed 0.170 more drinks of SSB than those who did not (P < .05). Kernel-based propensity score matching shows the SSB consumption difference to be 0.158 on the prior day (P < .05). This paper strengthens the evidence for the association between SSB availability via school vending machines and the actual SSB consumption, while future studies are needed to explore changes in other beverages after SSB becomes less available.

a Comparison Study of Different Kernel Functions for Svm-Based Classification of Multi-Temporal Polarimetry SAR Data

NASA Astrophysics Data System (ADS)

Yekkehkhany, B.; Safari, A.; Homayouni, S.; Hasanlou, M.

2014-10-01

In this paper, a framework is developed based on Support Vector Machines (SVM) for crop classification using polarimetric features extracted from multi-temporal Synthetic Aperture Radar (SAR) imageries. The multi-temporal integration of data not only improves the overall retrieval accuracy but also provides more reliable estimates with respect to single-date data. Several kernel functions are employed and compared in this study for mapping the input space to higher Hilbert dimension space. These kernel functions include linear, polynomials and Radial Based Function (RBF). The method is applied to several UAVSAR L-band SAR images acquired over an agricultural area near Winnipeg, Manitoba, Canada. In this research, the temporal alpha features of H/A/α decomposition method are used in classification. The experimental tests show an SVM classifier with RBF kernel for three dates of data increases the Overall Accuracy (OA) to up to 3% in comparison to using linear kernel function, and up to 1% in comparison to a 3rd degree polynomial kernel function.

Automatic classification of written descriptions by healthy adults: An overview of the application of natural language processing and machine learning techniques to clinical discourse analysis.

PubMed

Toledo, Cíntia Matsuda; Cunha, Andre; Scarton, Carolina; Aluísio, Sandra

2014-01-01

Discourse production is an important aspect in the evaluation of brain-injured individuals. We believe that studies comparing the performance of brain-injured subjects with that of healthy controls must use groups with compatible education. A pioneering application of machine learning methods using Brazilian Portuguese for clinical purposes is described, highlighting education as an important variable in the Brazilian scenario. The aims were to describe how to:(i) develop machine learning classifiers using features generated by natural language processing tools to distinguish descriptions produced by healthy individuals into classes based on their years of education; and(ii) automatically identify the features that best distinguish the groups. The approach proposed here extracts linguistic features automatically from the written descriptions with the aid of two Natural Language Processing tools: Coh-Metrix-Port and AIC. It also includes nine task-specific features (three new ones, two extracted manually, besides description time; type of scene described - simple or complex; presentation order - which type of picture was described first; and age). In this study, the descriptions by 144 of the subjects studied in Toledo 18 were used,which included 200 healthy Brazilians of both genders. A Support Vector Machine (SVM) with a radial basis function (RBF) kernel is the most recommended approach for the binary classification of our data, classifying three of the four initial classes. CfsSubsetEval (CFS) is a strong candidate to replace manual feature selection methods.

Gabor-based kernel PCA with fractional power polynomial models for face recognition.

PubMed

Liu, Chengjun

2004-05-01

This paper presents a novel Gabor-based kernel Principal Component Analysis (PCA) method by integrating the Gabor wavelet representation of face images and the kernel PCA method for face recognition. Gabor wavelets first derive desirable facial features characterized by spatial frequency, spatial locality, and orientation selectivity to cope with the variations due to illumination and facial expression changes. The kernel PCA method is then extended to include fractional power polynomial models for enhanced face recognition performance. A fractional power polynomial, however, does not necessarily define a kernel function, as it might not define a positive semidefinite Gram matrix. Note that the sigmoid kernels, one of the three classes of widely used kernel functions (polynomial kernels, Gaussian kernels, and sigmoid kernels), do not actually define a positive semidefinite Gram matrix either. Nevertheless, the sigmoid kernels have been successfully used in practice, such as in building support vector machines. In order to derive real kernel PCA features, we apply only those kernel PCA eigenvectors that are associated with positive eigenvalues. The feasibility of the Gabor-based kernel PCA method with fractional power polynomial models has been successfully tested on both frontal and pose-angled face recognition, using two data sets from the FERET database and the CMU PIE database, respectively. The FERET data set contains 600 frontal face images of 200 subjects, while the PIE data set consists of 680 images across five poses (left and right profiles, left and right half profiles, and frontal view) with two different facial expressions (neutral and smiling) of 68 subjects. The effectiveness of the Gabor-based kernel PCA method with fractional power polynomial models is shown in terms of both absolute performance indices and comparative performance against the PCA method, the kernel PCA method with polynomial kernels, the kernel PCA method with fractional power polynomial models, the Gabor wavelet-based PCA method, and the Gabor wavelet-based kernel PCA method with polynomial kernels.

Weighted Feature Gaussian Kernel SVM for Emotion Recognition

PubMed Central

Jia, Qingxuan

2016-01-01

Emotion recognition with weighted feature based on facial expression is a challenging research topic and has attracted great attention in the past few years. This paper presents a novel method, utilizing subregion recognition rate to weight kernel function. First, we divide the facial expression image into some uniform subregions and calculate corresponding recognition rate and weight. Then, we get a weighted feature Gaussian kernel function and construct a classifier based on Support Vector Machine (SVM). At last, the experimental results suggest that the approach based on weighted feature Gaussian kernel function has good performance on the correct rate in emotion recognition. The experiments on the extended Cohn-Kanade (CK+) dataset show that our method has achieved encouraging recognition results compared to the state-of-the-art methods. PMID:27807443

Pathway-Based Kernel Boosting for the Analysis of Genome-Wide Association Studies

PubMed Central

Manitz, Juliane; Burger, Patricia; Amos, Christopher I.; Chang-Claude, Jenny; Wichmann, Heinz-Erich; Kneib, Thomas; Bickeböller, Heike

2017-01-01

The analysis of genome-wide association studies (GWAS) benefits from the investigation of biologically meaningful gene sets, such as gene-interaction networks (pathways). We propose an extension to a successful kernel-based pathway analysis approach by integrating kernel functions into a powerful algorithmic framework for variable selection, to enable investigation of multiple pathways simultaneously. We employ genetic similarity kernels from the logistic kernel machine test (LKMT) as base-learners in a boosting algorithm. A model to explain case-control status is created iteratively by selecting pathways that improve its prediction ability. We evaluated our method in simulation studies adopting 50 pathways for different sample sizes and genetic effect strengths. Additionally, we included an exemplary application of kernel boosting to a rheumatoid arthritis and a lung cancer dataset. Simulations indicate that kernel boosting outperforms the LKMT in certain genetic scenarios. Applications to GWAS data on rheumatoid arthritis and lung cancer resulted in sparse models which were based on pathways interpretable in a clinical sense. Kernel boosting is highly flexible in terms of considered variables and overcomes the problem of multiple testing. Additionally, it enables the prediction of clinical outcomes. Thus, kernel boosting constitutes a new, powerful tool in the analysis of GWAS data and towards the understanding of biological processes involved in disease susceptibility. PMID:28785300

Pathway-Based Kernel Boosting for the Analysis of Genome-Wide Association Studies.

PubMed

Friedrichs, Stefanie; Manitz, Juliane; Burger, Patricia; Amos, Christopher I; Risch, Angela; Chang-Claude, Jenny; Wichmann, Heinz-Erich; Kneib, Thomas; Bickeböller, Heike; Hofner, Benjamin

2017-01-01

The analysis of genome-wide association studies (GWAS) benefits from the investigation of biologically meaningful gene sets, such as gene-interaction networks (pathways). We propose an extension to a successful kernel-based pathway analysis approach by integrating kernel functions into a powerful algorithmic framework for variable selection, to enable investigation of multiple pathways simultaneously. We employ genetic similarity kernels from the logistic kernel machine test (LKMT) as base-learners in a boosting algorithm. A model to explain case-control status is created iteratively by selecting pathways that improve its prediction ability. We evaluated our method in simulation studies adopting 50 pathways for different sample sizes and genetic effect strengths. Additionally, we included an exemplary application of kernel boosting to a rheumatoid arthritis and a lung cancer dataset. Simulations indicate that kernel boosting outperforms the LKMT in certain genetic scenarios. Applications to GWAS data on rheumatoid arthritis and lung cancer resulted in sparse models which were based on pathways interpretable in a clinical sense. Kernel boosting is highly flexible in terms of considered variables and overcomes the problem of multiple testing. Additionally, it enables the prediction of clinical outcomes. Thus, kernel boosting constitutes a new, powerful tool in the analysis of GWAS data and towards the understanding of biological processes involved in disease susceptibility.

Differentially Private Empirical Risk Minimization

PubMed Central

Chaudhuri, Kamalika; Monteleoni, Claire; Sarwate, Anand D.

2011-01-01

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ε-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance. PMID:21892342

A scalable kernel-based semisupervised metric learning algorithm with out-of-sample generalization ability.

PubMed

Yeung, Dit-Yan; Chang, Hong; Dai, Guang

2008-11-01

In recent years, metric learning in the semisupervised setting has aroused a lot of research interest. One type of semisupervised metric learning utilizes supervisory information in the form of pairwise similarity or dissimilarity constraints. However, most methods proposed so far are either limited to linear metric learning or unable to scale well with the data set size. In this letter, we propose a nonlinear metric learning method based on the kernel approach. By applying low-rank approximation to the kernel matrix, our method can handle significantly larger data sets. Moreover, our low-rank approximation scheme can naturally lead to out-of-sample generalization. Experiments performed on both artificial and real-world data show very promising results.

Feature and Region Selection for Visual Learning.

PubMed

Zhao, Ji; Wang, Liantao; Cabral, Ricardo; De la Torre, Fernando

2016-03-01

Visual learning problems, such as object classification and action recognition, are typically approached using extensions of the popular bag-of-words (BoWs) model. Despite its great success, it is unclear what visual features the BoW model is learning. Which regions in the image or video are used to discriminate among classes? Which are the most discriminative visual words? Answering these questions is fundamental for understanding existing BoW models and inspiring better models for visual recognition. To answer these questions, this paper presents a method for feature selection and region selection in the visual BoW model. This allows for an intermediate visualization of the features and regions that are important for visual learning. The main idea is to assign latent weights to the features or regions, and jointly optimize these latent variables with the parameters of a classifier (e.g., support vector machine). There are four main benefits of our approach: 1) our approach accommodates non-linear additive kernels, such as the popular χ(2) and intersection kernel; 2) our approach is able to handle both regions in images and spatio-temporal regions in videos in a unified way; 3) the feature selection problem is convex, and both problems can be solved using a scalable reduced gradient method; and 4) we point out strong connections with multiple kernel learning and multiple instance learning approaches. Experimental results in the PASCAL VOC 2007, MSR Action Dataset II and YouTube illustrate the benefits of our approach.

Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming

NASA Astrophysics Data System (ADS)

Ilie, Iulia; Dittrich, Peter; Carvalhais, Nuno; Jung, Martin; Heinemeyer, Andreas; Migliavacca, Mirco; Morison, James I. L.; Sippel, Sebastian; Subke, Jens-Arne; Wilkinson, Matthew; Mahecha, Miguel D.

2017-09-01

Accurate model representation of land-atmosphere carbon fluxes is essential for climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments, complemented by a steadily evolving body of mechanistic theory, provides the main basis for developing such models. The strongly increasing availability of measurements may facilitate new ways of identifying suitable model structures using machine learning. Here, we explore the potential of gene expression programming (GEP) to derive relevant model formulations based solely on the signals present in data by automatically applying various mathematical transformations to potential predictors and repeatedly evolving the resulting model structures. In contrast to most other machine learning regression techniques, the GEP approach generates readable models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions, with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (random forests, support vector machines, artificial neural networks, and kernel ridge regressions). Based on real observations we explore the responses of the different components of terrestrial respiration at an oak forest in south-eastern England. We find that the GEP-retrieved models are often better in prediction than some established respiration models. Based on their structures, we find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. We noticed that the GEP models are only partly portable across respiration components, the identification of a general terrestrial respiration model possibly prevented by equifinality issues. Overall, GEP is a promising tool for uncovering new model structures for terrestrial ecology in the data-rich era, complementing more traditional modelling approaches.

CompareSVM: supervised, Support Vector Machine (SVM) inference of gene regularity networks.

PubMed

Gillani, Zeeshan; Akash, Muhammad Sajid Hamid; Rahaman, M D Matiur; Chen, Ming

2014-11-30

Predication of gene regularity network (GRN) from expression data is a challenging task. There are many methods that have been developed to address this challenge ranging from supervised to unsupervised methods. Most promising methods are based on support vector machine (SVM). There is a need for comprehensive analysis on prediction accuracy of supervised method SVM using different kernels on different biological experimental conditions and network size. We developed a tool (CompareSVM) based on SVM to compare different kernel methods for inference of GRN. Using CompareSVM, we investigated and evaluated different SVM kernel methods on simulated datasets of microarray of different sizes in detail. The results obtained from CompareSVM showed that accuracy of inference method depends upon the nature of experimental condition and size of the network. For network with nodes (<200) and average (over all sizes of networks), SVM Gaussian kernel outperform on knockout, knockdown, and multifactorial datasets compared to all the other inference methods. For network with large number of nodes (~500), choice of inference method depend upon nature of experimental condition. CompareSVM is available at http://bis.zju.edu.cn/CompareSVM/ .

Sparse kernel methods for high-dimensional survival data.

PubMed

Evers, Ludger; Messow, Claudia-Martina

2008-07-15

Sparse kernel methods like support vector machines (SVM) have been applied with great success to classification and (standard) regression settings. Existing support vector classification and regression techniques however are not suitable for partly censored survival data, which are typically analysed using Cox's proportional hazards model. As the partial likelihood of the proportional hazards model only depends on the covariates through inner products, it can be 'kernelized'. The kernelized proportional hazards model however yields a solution that is dense, i.e. the solution depends on all observations. One of the key features of an SVM is that it yields a sparse solution, depending only on a small fraction of the training data. We propose two methods. One is based on a geometric idea, where-akin to support vector classification-the margin between the failed observation and the observations currently at risk is maximised. The other approach is based on obtaining a sparse model by adding observations one after another akin to the Import Vector Machine (IVM). Data examples studied suggest that both methods can outperform competing approaches. Software is available under the GNU Public License as an R package and can be obtained from the first author's website http://www.maths.bris.ac.uk/~maxle/software.html.

Error analysis of stochastic gradient descent ranking.

PubMed

Chen, Hong; Tang, Yi; Li, Luoqing; Yuan, Yuan; Li, Xuelong; Tang, Yuanyan

2013-06-01

Ranking is always an important task in machine learning and information retrieval, e.g., collaborative filtering, recommender systems, drug discovery, etc. A kernel-based stochastic gradient descent algorithm with the least squares loss is proposed for ranking in this paper. The implementation of this algorithm is simple, and an expression of the solution is derived via a sampling operator and an integral operator. An explicit convergence rate for leaning a ranking function is given in terms of the suitable choices of the step size and the regularization parameter. The analysis technique used here is capacity independent and is novel in error analysis of ranking learning. Experimental results on real-world data have shown the effectiveness of the proposed algorithm in ranking tasks, which verifies the theoretical analysis in ranking error.

Nowcasting Cloud Fields for U.S. Air Force Special Operations

DTIC Science & Technology

2017-03-01

application of Bayes’ Rule offers many advantages over Kernel Density Estimation (KDE) and other commonly used statistical post-processing methods...reflectance and probability of cloud. A statistical post-processing technique is applied using Bayesian estimation to train the system from a set of past...nowcasting, low cloud forecasting, cloud reflectance, ISR, Bayesian estimation, statistical post-processing, machine learning 15. NUMBER OF PAGES

Statistics and Machine Learning based Outlier Detection Techniques for Exoplanets

NASA Astrophysics Data System (ADS)

Goel, Amit; Montgomery, Michele

2015-08-01

Architectures of planetary systems are observable snapshots in time that can indicate formation and dynamic evolution of planets. The observable key parameters that we consider are planetary mass and orbital period. If planet masses are significantly less than their host star masses, then Keplerian Motion is defined as P^2 = a^3 where P is the orbital period in units of years and a is the orbital period in units of Astronomical Units (AU). Keplerian motion works on small scales such as the size of the Solar System but not on large scales such as the size of the Milky Way Galaxy. In this work, for confirmed exoplanets of known stellar mass, planetary mass, orbital period, and stellar age, we analyze Keplerian motion of systems based on stellar age to seek if Keplerian motion has an age dependency and to identify outliers. For detecting outliers, we apply several techniques based on statistical and machine learning methods such as probabilistic, linear, and proximity based models. In probabilistic and statistical models of outliers, the parameters of a closed form probability distributions are learned in order to detect the outliers. Linear models use regression analysis based techniques for detecting outliers. Proximity based models use distance based algorithms such as k-nearest neighbour, clustering algorithms such as k-means, or density based algorithms such as kernel density estimation. In this work, we will use unsupervised learning algorithms with only the proximity based models. In addition, we explore the relative strengths and weaknesses of the various techniques by validating the outliers. The validation criteria for the outliers is if the ratio of planetary mass to stellar mass is less than 0.001. In this work, we present our statistical analysis of the outliers thus detected.

Differential evolution algorithm-based kernel parameter selection for Fukunaga-Koontz Transform subspaces construction

NASA Astrophysics Data System (ADS)

Binol, Hamidullah; Bal, Abdullah; Cukur, Huseyin

2015-10-01

The performance of the kernel based techniques depends on the selection of kernel parameters. That's why; suitable parameter selection is an important problem for many kernel based techniques. This article presents a novel technique to learn the kernel parameters in kernel Fukunaga-Koontz Transform based (KFKT) classifier. The proposed approach determines the appropriate values of kernel parameters through optimizing an objective function constructed based on discrimination ability of KFKT. For this purpose we have utilized differential evolution algorithm (DEA). The new technique overcomes some disadvantages such as high time consumption existing in the traditional cross-validation method, and it can be utilized in any type of data. The experiments for target detection applications on the hyperspectral images verify the effectiveness of the proposed method.

Human action recognition with group lasso regularized-support vector machine

NASA Astrophysics Data System (ADS)

Luo, Huiwu; Lu, Huanzhang; Wu, Yabei; Zhao, Fei

2016-05-01

The bag-of-visual-words (BOVW) and Fisher kernel are two popular models in human action recognition, and support vector machine (SVM) is the most commonly used classifier for the two models. We show two kinds of group structures in the feature representation constructed by BOVW and Fisher kernel, respectively, since the structural information of feature representation can be seen as a prior for the classifier and can improve the performance of the classifier, which has been verified in several areas. However, the standard SVM employs L2-norm regularization in its learning procedure, which penalizes each variable individually and cannot express the structural information of feature representation. We replace the L2-norm regularization with group lasso regularization in standard SVM, and a group lasso regularized-support vector machine (GLRSVM) is proposed. Then, we embed the group structural information of feature representation into GLRSVM. Finally, we introduce an algorithm to solve the optimization problem of GLRSVM by alternating directions method of multipliers. The experiments evaluated on KTH, YouTube, and Hollywood2 datasets show that our method achieves promising results and improves the state-of-the-art methods on KTH and YouTube datasets.

ADMET Evaluation in Drug Discovery. 18. Reliable Prediction of Chemical-Induced Urinary Tract Toxicity by Boosting Machine Learning Approaches.

PubMed

Lei, Tailong; Sun, Huiyong; Kang, Yu; Zhu, Feng; Liu, Hui; Zhou, Wenfang; Wang, Zhe; Li, Dan; Li, Youyong; Hou, Tingjun

2017-11-06

Xenobiotic chemicals and their metabolites are mainly excreted out of our bodies by the urinary tract through the urine. Chemical-induced urinary tract toxicity is one of the main reasons that cause failure during drug development, and it is a common adverse event for medications, natural supplements, and environmental chemicals. Despite its importance, there are only a few in silico models for assessing urinary tract toxicity for a large number of compounds with diverse chemical structures. Here, we developed a series of qualitative and quantitative structure-activity relationship (QSAR) models for predicting urinary tract toxicity. In our study, the recursive feature elimination method incorporated with random forests (RFE-RF) was used for dimension reduction, and then eight machine learning approaches were used for QSAR modeling, i.e., relevance vector machine (RVM), support vector machine (SVM), regularized random forest (RRF), C5.0 trees, eXtreme gradient boosting (XGBoost), AdaBoost.M1, SVM boosting (SVMBoost), and RVM boosting (RVMBoost). For building classification models, the synthetic minority oversampling technique was used to handle the imbalance data set problem. Among all the machine learning approaches, SVMBoost based on the RBF kernel achieves both the best quantitative (q ext 2 = 0.845) and qualitative predictions for the test set (MCC of 0.787, AUC of 0.893, sensitivity of 89.6%, specificity of 94.1%, and global accuracy of 90.8%). The application domains were then analyzed, and all of the tested chemicals fall within the application domain coverage. We also examined the structure features of the chemicals with large prediction errors. In brief, both the regression and classification models developed by the SVMBoost approach have reliable prediction capability for assessing chemical-induced urinary tract toxicity.

Product demand forecasts using wavelet kernel support vector machine and particle swarm optimization in manufacture system

NASA Astrophysics Data System (ADS)

Wu, Qi

2010-03-01

Demand forecasts play a crucial role in supply chain management. The future demand for a certain product is the basis for the respective replenishment systems. Aiming at demand series with small samples, seasonal character, nonlinearity, randomicity and fuzziness, the existing support vector kernel does not approach the random curve of the sales time series in the space (quadratic continuous integral space). In this paper, we present a hybrid intelligent system combining the wavelet kernel support vector machine and particle swarm optimization for demand forecasting. The results of application in car sale series forecasting show that the forecasting approach based on the hybrid PSOWv-SVM model is effective and feasible, the comparison between the method proposed in this paper and other ones is also given, which proves that this method is, for the discussed example, better than hybrid PSOv-SVM and other traditional methods.

Explosive hazard detection using MIMO forward-looking ground penetrating radar

NASA Astrophysics Data System (ADS)

Shaw, Darren; Ho, K. C.; Stone, Kevin; Keller, James M.; Popescu, Mihail; Anderson, Derek T.; Luke, Robert H.; Burns, Brian

2015-05-01

This paper proposes a machine learning algorithm for subsurface object detection on multiple-input-multiple-output (MIMO) forward-looking ground-penetrating radar (FLGPR). By detecting hazards using FLGPR, standoff distances of up to tens of meters can be acquired, but this is at the degradation of performance due to high false alarm rates. The proposed system utilizes an anomaly detection prescreener to identify potential object locations. Alarm locations have multiple one-dimensional (ML) spectral features, two-dimensional (2D) spectral features, and log-Gabor statistic features extracted. The ability of these features to reduce the number of false alarms and increase the probability of detection is evaluated for both co-polarizations present in the Akela MIMO array. Classification is performed by a Support Vector Machine (SVM) with lane-based cross-validation for training and testing. Class imbalance and optimized SVM kernel parameters are considered during classifier training.

Application of support vector machine for the separation of mineralised zones in the Takht-e-Gonbad porphyry deposit, SE Iran

NASA Astrophysics Data System (ADS)

Mahvash Mohammadi, Neda; Hezarkhani, Ardeshir

2018-07-01

Classification of mineralised zones is an important factor for the analysis of economic deposits. In this paper, the support vector machine (SVM), a supervised learning algorithm, based on subsurface data is proposed for classification of mineralised zones in the Takht-e-Gonbad porphyry Cu-deposit (SE Iran). The effects of the input features are evaluated via calculating the accuracy rates on the SVM performance. Ultimately, the SVM model, is developed based on input features namely lithology, alteration, mineralisation, the level and, radial basis function (RBF) as a kernel function. Moreover, the optimal amount of parameters λ and C, using n-fold cross-validation method, are calculated at level 0.001 and 0.01 respectively. The accuracy of this model is 0.931 for classification of mineralised zones in the Takht-e-Gonbad porphyry deposit. The results of the study confirm the efficiency of SVM method for classification the mineralised zones.

Kernel based machine learning algorithm for the efficient prediction of type III polyketide synthase family of proteins.

PubMed

Mallika, V; Sivakumar, K C; Jaichand, S; Soniya, E V

2010-07-13

Type III Polyketide synthases (PKS) are family of proteins considered to have significant roles in the biosynthesis of various polyketides in plants, fungi and bacteria. As these proteins shows positive effects to human health, more researches are going on regarding this particular protein. Developing a tool to identify the probability of sequence being a type III polyketide synthase will minimize the time consumption and manpower efforts. In this approach, we have designed and implemented PKSIIIpred, a high performance prediction server for type III PKS where the classifier is Support Vector Machines (SVMs). Based on the limited training dataset, the tool efficiently predicts the type III PKS superfamily of proteins with high sensitivity and specificity. The PKSIIIpred is available at http://type3pks.in/prediction/. We expect that this tool may serve as a useful resource for type III PKS researchers. Currently work is being progressed for further betterment of prediction accuracy by including more sequence features in the training dataset.

The Association between the Availability of Sugar-Sweetened Beverage in School Vending Machines and Its Consumption among Adolescents in California: A Propensity Score Matching Approach

PubMed Central

Shi, Lu

2010-01-01

There is controversy over to what degree banning sugar-sweetened beverage (SSB) sales at schools could decrease the SSB intake. This paper uses the adolescent sample of 2005 California Health Interview Survey to estimate the association between the availability of SSB from school vending machines and the amount of SSB consumption. Propensity score stratification and kernel-based propensity score matching are used to address the selection bias issue in cross-sectional data. Propensity score stratification shows that adolescents who had access to SSB through their school vending machines consumed 0.170 more drinks of SSB than those who did not (P < .05). Kernel-based propensity score matching shows the SSB consumption difference to be 0.158 on the prior day (P < .05). This paper strengthens the evidence for the association between SSB availability via school vending machines and the actual SSB consumption, while future studies are needed to explore changes in other beverages after SSB becomes less available. PMID:20976298

Multi-temporal Land Use Mapping of Coastal Wetlands Area using Machine Learning in Google Earth Engine

NASA Astrophysics Data System (ADS)

Farda, N. M.

2017-12-01

Coastal wetlands provide ecosystem services essential to people and the environment. Changes in coastal wetlands, especially on land use, are important to monitor by utilizing multi-temporal imagery. The Google Earth Engine (GEE) provides many machine learning algorithms (10 algorithms) that are very useful for extracting land use from imagery. The research objective is to explore machine learning in Google Earth Engine and its accuracy for multi-temporal land use mapping of coastal wetland area. Landsat 3 MSS (1978), Landsat 5 TM (1991), Landsat 7 ETM+ (2001), and Landsat 8 OLI (2014) images located in Segara Anakan lagoon are selected to represent multi temporal images. The input for machine learning are visible and near infrared bands, PCA band, invers PCA bands, bare soil index, vegetation index, wetness index, elevation from ASTER GDEM, and GLCM (Harralick) texture, and also polygon samples in 140 locations. There are 10 machine learning algorithms applied to extract coastal wetlands land use from Landsat imagery. The algorithms are Fast Naive Bayes, CART (Classification and Regression Tree), Random Forests, GMO Max Entropy, Perceptron (Multi Class Perceptron), Winnow, Voting SVM, Margin SVM, Pegasos (Primal Estimated sub-GrAdient SOlver for Svm), IKPamir (Intersection Kernel Passive Aggressive Method for Information Retrieval, SVM). Machine learning in Google Earth Engine are very helpful in multi-temporal land use mapping, the highest accuracy for land use mapping of coastal wetland is CART with 96.98 % Overall Accuracy using K-Fold Cross Validation (K = 10). GEE is particularly useful for multi-temporal land use mapping with ready used image and classification algorithms, and also very challenging for other applications.

Multiple kernel based feature and decision level fusion of iECO individuals for explosive hazard detection in FLIR imagery

NASA Astrophysics Data System (ADS)

Price, Stanton R.; Murray, Bryce; Hu, Lequn; Anderson, Derek T.; Havens, Timothy C.; Luke, Robert H.; Keller, James M.

2016-05-01

A serious threat to civilians and soldiers is buried and above ground explosive hazards. The automatic detection of such threats is highly desired. Many methods exist for explosive hazard detection, e.g., hand-held based sensors, downward and forward looking vehicle mounted platforms, etc. In addition, multiple sensors are used to tackle this extreme problem, such as radar and infrared (IR) imagery. In this article, we explore the utility of feature and decision level fusion of learned features for forward looking explosive hazard detection in IR imagery. Specifically, we investigate different ways to fuse learned iECO features pre and post multiple kernel (MK) support vector machine (SVM) based classification. Three MK strategies are explored; fixed rule, heuristics and optimization-based. Performance is assessed in the context of receiver operating characteristic (ROC) curves on data from a U.S. Army test site that contains multiple target and clutter types, burial depths and times of day. Specifically, the results reveal two interesting things. First, the different MK strategies appear to indicate that the different iECO individuals are all more-or-less important and there is not a dominant feature. This is reinforcing as our hypothesis was that iECO provides different ways to approach target detection. Last, we observe that while optimization-based MK is mathematically appealing, i.e., it connects the learning of the fusion to the underlying classification problem we are trying to solve, it appears to be highly susceptible to over fitting and simpler, e.g., fixed rule and heuristics approaches help us realize more generalizable iECO solutions.

Scaling Up Graph-Based Semisupervised Learning via Prototype Vector Machines

PubMed Central

Zhang, Kai; Lan, Liang; Kwok, James T.; Vucetic, Slobodan; Parvin, Bahram

2014-01-01

When the amount of labeled data are limited, semi-supervised learning can improve the learner's performance by also using the often easily available unlabeled data. In particular, a popular approach requires the learned function to be smooth on the underlying data manifold. By approximating this manifold as a weighted graph, such graph-based techniques can often achieve state-of-the-art performance. However, their high time and space complexities make them less attractive on large data sets. In this paper, we propose to scale up graph-based semisupervised learning using a set of sparse prototypes derived from the data. These prototypes serve as a small set of data representatives, which can be used to approximate the graph-based regularizer and to control model complexity. Consequently, both training and testing become much more efficient. Moreover, when the Gaussian kernel is used to define the graph affinity, a simple and principled method to select the prototypes can be obtained. Experiments on a number of real-world data sets demonstrate encouraging performance and scaling properties of the proposed approach. It also compares favorably with models learned via ℓ1-regularization at the same level of model sparsity. These results demonstrate the efficacy of the proposed approach in producing highly parsimonious and accurate models for semisupervised learning. PMID:25720002

Cost-sensitive AdaBoost algorithm for ordinal regression based on extreme learning machine.

PubMed

Riccardi, Annalisa; Fernández-Navarro, Francisco; Carloni, Sante

2014-10-01

In this paper, the well known stagewise additive modeling using a multiclass exponential (SAMME) boosting algorithm is extended to address problems where there exists a natural order in the targets using a cost-sensitive approach. The proposed ensemble model uses an extreme learning machine (ELM) model as a base classifier (with the Gaussian kernel and the additional regularization parameter). The closed form of the derived weighted least squares problem is provided, and it is employed to estimate analytically the parameters connecting the hidden layer to the output layer at each iteration of the boosting algorithm. Compared to the state-of-the-art boosting algorithms, in particular those using ELM as base classifier, the suggested technique does not require the generation of a new training dataset at each iteration. The adoption of the weighted least squares formulation of the problem has been presented as an unbiased and alternative approach to the already existing ELM boosting techniques. Moreover, the addition of a cost model for weighting the patterns, according to the order of the targets, enables the classifier to tackle ordinal regression problems further. The proposed method has been validated by an experimental study by comparing it with already existing ensemble methods and ELM techniques for ordinal regression, showing competitive results.

A Prototype SSVEP Based Real Time BCI Gaming System

PubMed Central

Martišius, Ignas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel. PMID:27051414

A Prototype SSVEP Based Real Time BCI Gaming System.

PubMed

Martišius, Ignas; Damaševičius, Robertas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel.

Automatic classification of written descriptions by healthy adults: An overview of the application of natural language processing and machine learning techniques to clinical discourse analysis

PubMed Central

Toledo, Cíntia Matsuda; Cunha, Andre; Scarton, Carolina; Aluísio, Sandra

2014-01-01

Discourse production is an important aspect in the evaluation of brain-injured individuals. We believe that studies comparing the performance of brain-injured subjects with that of healthy controls must use groups with compatible education. A pioneering application of machine learning methods using Brazilian Portuguese for clinical purposes is described, highlighting education as an important variable in the Brazilian scenario. Objective The aims were to describe how to: (i) develop machine learning classifiers using features generated by natural language processing tools to distinguish descriptions produced by healthy individuals into classes based on their years of education; and (ii) automatically identify the features that best distinguish the groups. Methods The approach proposed here extracts linguistic features automatically from the written descriptions with the aid of two Natural Language Processing tools: Coh-Metrix-Port and AIC. It also includes nine task-specific features (three new ones, two extracted manually, besides description time; type of scene described – simple or complex; presentation order – which type of picture was described first; and age). In this study, the descriptions by 144 of the subjects studied in Toledo18 were used,which included 200 healthy Brazilians of both genders. Results and Conclusion A Support Vector Machine (SVM) with a radial basis function (RBF) kernel is the most recommended approach for the binary classification of our data, classifying three of the four initial classes. CfsSubsetEval (CFS) is a strong candidate to replace manual feature selection methods. PMID:29213908

Discrimination of raw and processed Dipsacus asperoides by near infrared spectroscopy combined with least squares-support vector machine and random forests

NASA Astrophysics Data System (ADS)

Xin, Ni; Gu, Xiao-Feng; Wu, Hao; Hu, Yu-Zhu; Yang, Zhong-Lin

2012-04-01

Most herbal medicines could be processed to fulfill the different requirements of therapy. The purpose of this study was to discriminate between raw and processed Dipsacus asperoides, a common traditional Chinese medicine, based on their near infrared (NIR) spectra. Least squares-support vector machine (LS-SVM) and random forests (RF) were employed for full-spectrum classification. Three types of kernels, including linear kernel, polynomial kernel and radial basis function kernel (RBF), were checked for optimization of LS-SVM model. For comparison, a linear discriminant analysis (LDA) model was performed for classification, and the successive projections algorithm (SPA) was executed prior to building an LDA model to choose an appropriate subset of wavelengths. The three methods were applied to a dataset containing 40 raw herbs and 40 corresponding processed herbs. We ran 50 runs of 10-fold cross validation to evaluate the model's efficiency. The performance of the LS-SVM with RBF kernel (RBF LS-SVM) was better than the other two kernels. The RF, RBF LS-SVM and SPA-LDA successfully classified all test samples. The mean error rates for the 50 runs of 10-fold cross validation were 1.35% for RBF LS-SVM, 2.87% for RF, and 2.50% for SPA-LDA. The best classification results were obtained by using LS-SVM with RBF kernel, while RF was fast in the training and making predictions.

Wavelet SVM in Reproducing Kernel Hilbert Space for hyperspectral remote sensing image classification

NASA Astrophysics Data System (ADS)

Du, Peijun; Tan, Kun; Xing, Xiaoshi

2010-12-01

Combining Support Vector Machine (SVM) with wavelet analysis, we constructed wavelet SVM (WSVM) classifier based on wavelet kernel functions in Reproducing Kernel Hilbert Space (RKHS). In conventional kernel theory, SVM is faced with the bottleneck of kernel parameter selection which further results in time-consuming and low classification accuracy. The wavelet kernel in RKHS is a kind of multidimensional wavelet function that can approximate arbitrary nonlinear functions. Implications on semiparametric estimation are proposed in this paper. Airborne Operational Modular Imaging Spectrometer II (OMIS II) hyperspectral remote sensing image with 64 bands and Reflective Optics System Imaging Spectrometer (ROSIS) data with 115 bands were used to experiment the performance and accuracy of the proposed WSVM classifier. The experimental results indicate that the WSVM classifier can obtain the highest accuracy when using the Coiflet Kernel function in wavelet transform. In contrast with some traditional classifiers, including Spectral Angle Mapping (SAM) and Minimum Distance Classification (MDC), and SVM classifier using Radial Basis Function kernel, the proposed wavelet SVM classifier using the wavelet kernel function in Reproducing Kernel Hilbert Space is capable of improving classification accuracy obviously.

Hadamard Kernel SVM with applications for breast cancer outcome predictions.

PubMed

Jiang, Hao; Ching, Wai-Ki; Cheung, Wai-Shun; Hou, Wenpin; Yin, Hong

2017-12-21

Breast cancer is one of the leading causes of deaths for women. It is of great necessity to develop effective methods for breast cancer detection and diagnosis. Recent studies have focused on gene-based signatures for outcome predictions. Kernel SVM for its discriminative power in dealing with small sample pattern recognition problems has attracted a lot attention. But how to select or construct an appropriate kernel for a specified problem still needs further investigation. Here we propose a novel kernel (Hadamard Kernel) in conjunction with Support Vector Machines (SVMs) to address the problem of breast cancer outcome prediction using gene expression data. Hadamard Kernel outperform the classical kernels and correlation kernel in terms of Area under the ROC Curve (AUC) values where a number of real-world data sets are adopted to test the performance of different methods. Hadamard Kernel SVM is effective for breast cancer predictions, either in terms of prognosis or diagnosis. It may benefit patients by guiding therapeutic options. Apart from that, it would be a valuable addition to the current SVM kernel families. We hope it will contribute to the wider biology and related communities.

Novel images extraction model using improved delay vector variance feature extraction and multi-kernel neural network for EEG detection and prediction.

PubMed

Ge, Jing; Zhang, Guoping

2015-01-01

Advanced intelligent methodologies could help detect and predict diseases from the EEG signals in cases the manual analysis is inefficient available, for instance, the epileptic seizures detection and prediction. This is because the diversity and the evolution of the epileptic seizures make it very difficult in detecting and identifying the undergoing disease. Fortunately, the determinism and nonlinearity in a time series could characterize the state changes. Literature review indicates that the Delay Vector Variance (DVV) could examine the nonlinearity to gain insight into the EEG signals but very limited work has been done to address the quantitative DVV approach. Hence, the outcomes of the quantitative DVV should be evaluated to detect the epileptic seizures. To develop a new epileptic seizure detection method based on quantitative DVV. This new epileptic seizure detection method employed an improved delay vector variance (IDVV) to extract the nonlinearity value as a distinct feature. Then a multi-kernel functions strategy was proposed in the extreme learning machine (ELM) network to provide precise disease detection and prediction. The nonlinearity is more sensitive than the energy and entropy. 87.5% overall accuracy of recognition and 75.0% overall accuracy of forecasting were achieved. The proposed IDVV and multi-kernel ELM based method was feasible and effective for epileptic EEG detection. Hence, the newly proposed method has importance for practical applications.

Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS

NASA Astrophysics Data System (ADS)

Tehrany, Mahyat Shafapour; Pradhan, Biswajeet; Jebur, Mustafa Neamah

2014-05-01

Flood is one of the most devastating natural disasters that occur frequently in Terengganu, Malaysia. Recently, ensemble based techniques are getting extremely popular in flood modeling. In this paper, weights-of-evidence (WoE) model was utilized first, to assess the impact of classes of each conditioning factor on flooding through bivariate statistical analysis (BSA). Then, these factors were reclassified using the acquired weights and entered into the support vector machine (SVM) model to evaluate the correlation between flood occurrence and each conditioning factor. Through this integration, the weak point of WoE can be solved and the performance of the SVM will be enhanced. The spatial database included flood inventory, slope, stream power index (SPI), topographic wetness index (TWI), altitude, curvature, distance from the river, geology, rainfall, land use/cover (LULC), and soil type. Four kernel types of SVM (linear kernel (LN), polynomial kernel (PL), radial basis function kernel (RBF), and sigmoid kernel (SIG)) were used to investigate the performance of each kernel type. The efficiency of the new ensemble WoE and SVM method was tested using area under curve (AUC) which measured the prediction and success rates. The validation results proved the strength and efficiency of the ensemble method over the individual methods. The best results were obtained from RBF kernel when compared with the other kernel types. Success rate and prediction rate for ensemble WoE and RBF-SVM method were 96.48% and 95.67% respectively. The proposed ensemble flood susceptibility mapping method could assist researchers and local governments in flood mitigation strategies.

Machine learning of frustrated classical spin models. I. Principal component analysis

NASA Astrophysics Data System (ADS)

Wang, Ce; Zhai, Hui

2017-10-01

This work aims at determining whether artificial intelligence can recognize a phase transition without prior human knowledge. If this were successful, it could be applied to, for instance, analyzing data from the quantum simulation of unsolved physical models. Toward this goal, we first need to apply the machine learning algorithm to well-understood models and see whether the outputs are consistent with our prior knowledge, which serves as the benchmark for this approach. In this work, we feed the computer data generated by the classical Monte Carlo simulation for the X Y model in frustrated triangular and union jack lattices, which has two order parameters and exhibits two phase transitions. We show that the outputs of the principal component analysis agree very well with our understanding of different orders in different phases, and the temperature dependences of the major components detect the nature and the locations of the phase transitions. Our work offers promise for using machine learning techniques to study sophisticated statistical models, and our results can be further improved by using principal component analysis with kernel tricks and the neural network method.

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification.

PubMed

Siddiqui, Muhammad Faisal; Reza, Ahmed Wasif; Kanesan, Jeevan

2015-01-01

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients' benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

Seeing It All: Evaluating Supervised Machine Learning Methods for the Classification of Diverse Otariid Behaviours

PubMed Central

Slip, David J.; Hocking, David P.; Harcourt, Robert G.

2016-01-01

Constructing activity budgets for marine animals when they are at sea and cannot be directly observed is challenging, but recent advances in bio-logging technology offer solutions to this problem. Accelerometers can potentially identify a wide range of behaviours for animals based on unique patterns of acceleration. However, when analysing data derived from accelerometers, there are many statistical techniques available which when applied to different data sets produce different classification accuracies. We investigated a selection of supervised machine learning methods for interpreting behavioural data from captive otariids (fur seals and sea lions). We conducted controlled experiments with 12 seals, where their behaviours were filmed while they were wearing 3-axis accelerometers. From video we identified 26 behaviours that could be grouped into one of four categories (foraging, resting, travelling and grooming) representing key behaviour states for wild seals. We used data from 10 seals to train four predictive classification models: stochastic gradient boosting (GBM), random forests, support vector machine using four different kernels and a baseline model: penalised logistic regression. We then took the best parameters from each model and cross-validated the results on the two seals unseen so far. We also investigated the influence of feature statistics (describing some characteristic of the seal), testing the models both with and without these. Cross-validation accuracies were lower than training accuracy, but the SVM with a polynomial kernel was still able to classify seal behaviour with high accuracy (>70%). Adding feature statistics improved accuracies across all models tested. Most categories of behaviour -resting, grooming and feeding—were all predicted with reasonable accuracy (52–81%) by the SVM while travelling was poorly categorised (31–41%). These results show that model selection is important when classifying behaviour and that by using animal characteristics we can strengthen the overall accuracy. PMID:28002450

Discriminative graph embedding for label propagation.

PubMed

Nguyen, Canh Hao; Mamitsuka, Hiroshi

2011-09-01

In many applications, the available information is encoded in graph structures. This is a common problem in biological networks, social networks, web communities and document citations. We investigate the problem of classifying nodes' labels on a similarity graph given only a graph structure on the nodes. Conventional machine learning methods usually require data to reside in some Euclidean spaces or to have a kernel representation. Applying these methods to nodes on graphs would require embedding the graphs into these spaces. By embedding and then learning the nodes on graphs, most methods are either flexible with different learning objectives or efficient enough for large scale applications. We propose a method to embed a graph into a feature space for a discriminative purpose. Our idea is to include label information into the embedding process, making the space representation tailored to the task. We design embedding objective functions that the following learning formulations become spectral transforms. We then reformulate these spectral transforms into multiple kernel learning problems. Our method, while being tailored to the discriminative tasks, is efficient and can scale to massive data sets. We show the need of discriminative embedding on some simulations. Applying to biological network problems, our method is shown to outperform baselines.

Machine learning properties of materials and molecules with entropy-regularized kernels

NASA Astrophysics Data System (ADS)

Ceriotti, Michele; Bartók, Albert; CsáNyi, GáBor; de, Sandip

Application of machine-learning methods to physics, chemistry and materials science is gaining traction as a strategy to obtain accurate predictions of the properties of matter at a fraction of the typical cost of quantum mechanical electronic structure calculations. In this endeavor, one can leverage general-purpose frameworks for supervised-learning. It is however very important that the input data - for instance the positions of atoms in a molecule or solid - is processed into a form that reflects all the underlying physical symmetries of the problem, and that possesses the regularity properties that are required by machine-learning algorithms. Here we introduce a general strategy to build a representation of this kind. We will start from existing approaches to compare local environments (basically, groups of atoms), and combine them using techniques borrowed from optimal transport theory, discussing the relation between this idea and additive energy decompositions. We will present a few examples demonstrating the potential of this approach as a tool to predict molecular and materials' properties with an accuracy on par with state-of-the-art electronic structure methods. MARVEL NCCR (Swiss National Science Foundation) and ERC StG HBMAP (European Research Council, G.A. 677013).

Optimal projection method determination by Logdet Divergence and perturbed von-Neumann Divergence.

PubMed

Jiang, Hao; Ching, Wai-Ki; Qiu, Yushan; Cheng, Xiao-Qing

2017-12-14

Positive semi-definiteness is a critical property in kernel methods for Support Vector Machine (SVM) by which efficient solutions can be guaranteed through convex quadratic programming. However, a lot of similarity functions in applications do not produce positive semi-definite kernels. We propose projection method by constructing projection matrix on indefinite kernels. As a generalization of the spectrum method (denoising method and flipping method), the projection method shows better or comparable performance comparing to the corresponding indefinite kernel methods on a number of real world data sets. Under the Bregman matrix divergence theory, we can find suggested optimal λ in projection method using unconstrained optimization in kernel learning. In this paper we focus on optimal λ determination, in the pursuit of precise optimal λ determination method in unconstrained optimization framework. We developed a perturbed von-Neumann divergence to measure kernel relationships. We compared optimal λ determination with Logdet Divergence and perturbed von-Neumann Divergence, aiming at finding better λ in projection method. Results on a number of real world data sets show that projection method with optimal λ by Logdet divergence demonstrate near optimal performance. And the perturbed von-Neumann Divergence can help determine a relatively better optimal projection method. Projection method ia easy to use for dealing with indefinite kernels. And the parameter embedded in the method can be determined through unconstrained optimization under Bregman matrix divergence theory. This may provide a new way in kernel SVMs for varied objectives.

An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image.

PubMed

Qian, Chunjun; Yang, Xiaoping

2018-01-01

Carotid artery atherosclerosis is an important cause of stroke. Ultrasound imaging has been widely used in the diagnosis of atherosclerosis. Therefore, segmenting atherosclerotic carotid plaque in ultrasound image is an important task. Accurate plaque segmentation is helpful for the measurement of carotid plaque burden. In this paper, we propose and evaluate a novel learning-based integrated framework for plaque segmentation. In our study, four different classification algorithms, along with the auto-context iterative algorithm, were employed to effectively integrate features from ultrasound images and later also the iteratively estimated and refined probability maps together for pixel-wise classification. The four classification algorithms were support vector machine with linear kernel, support vector machine with radial basis function kernel, AdaBoost and random forest. The plaque segmentation was implemented in the generated probability map. The performance of the four different learning-based plaque segmentation methods was tested on 29 B-mode ultrasound images. The evaluation indices for our proposed methods were consisted of sensitivity, specificity, Dice similarity coefficient, overlap index, error of area, absolute error of area, point-to-point distance, and Hausdorff point-to-point distance, along with the area under the ROC curve. The segmentation method integrated the random forest and an auto-context model obtained the best results (sensitivity 80.4 ± 8.4%, specificity 96.5 ± 2.0%, Dice similarity coefficient 81.0 ± 4.1%, overlap index 68.3 ± 5.8%, error of area -1.02 ± 18.3%, absolute error of area 14.7 ± 10.9%, point-to-point distance 0.34 ± 0.10 mm, Hausdorff point-to-point distance 1.75 ± 1.02 mm, and area under the ROC curve 0.897), which were almost the best, compared with that from the existed methods. Our proposed learning-based integrated framework investigated in this study could be useful for atherosclerotic carotid plaque segmentation, which will be helpful for the measurement of carotid plaque burden. Copyright © 2017 Elsevier B.V. All rights reserved.

Fast metabolite identification with Input Output Kernel Regression.

PubMed

Brouard, Céline; Shen, Huibin; Dührkop, Kai; d'Alché-Buc, Florence; Böcker, Sebastian; Rousu, Juho

2016-06-15

An important problematic of metabolomics is to identify metabolites using tandem mass spectrometry data. Machine learning methods have been proposed recently to solve this problem by predicting molecular fingerprint vectors and matching these fingerprints against existing molecular structure databases. In this work we propose to address the metabolite identification problem using a structured output prediction approach. This type of approach is not limited to vector output space and can handle structured output space such as the molecule space. We use the Input Output Kernel Regression method to learn the mapping between tandem mass spectra and molecular structures. The principle of this method is to encode the similarities in the input (spectra) space and the similarities in the output (molecule) space using two kernel functions. This method approximates the spectra-molecule mapping in two phases. The first phase corresponds to a regression problem from the input space to the feature space associated to the output kernel. The second phase is a preimage problem, consisting in mapping back the predicted output feature vectors to the molecule space. We show that our approach achieves state-of-the-art accuracy in metabolite identification. Moreover, our method has the advantage of decreasing the running times for the training step and the test step by several orders of magnitude over the preceding methods. celine.brouard@aalto.fi Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.

Fast metabolite identification with Input Output Kernel Regression

PubMed Central

Brouard, Céline; Shen, Huibin; Dührkop, Kai; d'Alché-Buc, Florence; Böcker, Sebastian; Rousu, Juho

2016-01-01

Motivation: An important problematic of metabolomics is to identify metabolites using tandem mass spectrometry data. Machine learning methods have been proposed recently to solve this problem by predicting molecular fingerprint vectors and matching these fingerprints against existing molecular structure databases. In this work we propose to address the metabolite identification problem using a structured output prediction approach. This type of approach is not limited to vector output space and can handle structured output space such as the molecule space. Results: We use the Input Output Kernel Regression method to learn the mapping between tandem mass spectra and molecular structures. The principle of this method is to encode the similarities in the input (spectra) space and the similarities in the output (molecule) space using two kernel functions. This method approximates the spectra-molecule mapping in two phases. The first phase corresponds to a regression problem from the input space to the feature space associated to the output kernel. The second phase is a preimage problem, consisting in mapping back the predicted output feature vectors to the molecule space. We show that our approach achieves state-of-the-art accuracy in metabolite identification. Moreover, our method has the advantage of decreasing the running times for the training step and the test step by several orders of magnitude over the preceding methods. Availability and implementation: Contact: celine.brouard@aalto.fi Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307628

Encoding Dissimilarity Data for Statistical Model Building.

PubMed

Wahba, Grace

2010-12-01

We summarize, review and comment upon three papers which discuss the use of discrete, noisy, incomplete, scattered pairwise dissimilarity data in statistical model building. Convex cone optimization codes are used to embed the objects into a Euclidean space which respects the dissimilarity information while controlling the dimension of the space. A "newbie" algorithm is provided for embedding new objects into this space. This allows the dissimilarity information to be incorporated into a Smoothing Spline ANOVA penalized likelihood model, a Support Vector Machine, or any model that will admit Reproducing Kernel Hilbert Space components, for nonparametric regression, supervised learning, or semi-supervised learning. Future work and open questions are discussed. The papers are: F. Lu, S. Keles, S. Wright and G. Wahba 2005. A framework for kernel regularization with application to protein clustering. Proceedings of the National Academy of Sciences 102, 12332-1233.G. Corrada Bravo, G. Wahba, K. Lee, B. Klein, R. Klein and S. Iyengar 2009. Examining the relative influence of familial, genetic and environmental covariate information in flexible risk models. Proceedings of the National Academy of Sciences 106, 8128-8133F. Lu, Y. Lin and G. Wahba. Robust manifold unfolding with kernel regularization. TR 1008, Department of Statistics, University of Wisconsin-Madison.

The employment of Support Vector Machine to classify high and low performance archers based on bio-physiological variables

NASA Astrophysics Data System (ADS)

Taha, Zahari; Muazu Musa, Rabiu; Majeed, Anwar P. P. Abdul; Razali Abdullah, Mohamad; Amirul Abdullah, Muhammad; Hasnun Arif Hassan, Mohd; Khalil, Zubair

2018-04-01

The present study employs a machine learning algorithm namely support vector machine (SVM) to classify high and low potential archers from a collection of bio-physiological variables trained on different SVMs. 50 youth archers with the average age and standard deviation of (17.0 ±.056) gathered from various archery programmes completed a one end shooting score test. The bio-physiological variables namely resting heart rate, resting respiratory rate, resting diastolic blood pressure, resting systolic blood pressure, as well as calories intake, were measured prior to their shooting tests. k-means cluster analysis was applied to cluster the archers based on their scores on variables assessed. SVM models i.e. linear, quadratic and cubic kernel functions, were trained on the aforementioned variables. The k-means clustered the archers into high (HPA) and low potential archers (LPA), respectively. It was demonstrated that the linear SVM exhibited good accuracy with a classification accuracy of 94% in comparison the other tested models. The findings of this investigation can be valuable to coaches and sports managers to recognise high potential athletes from the selected bio-physiological variables examined.

Kernel-based least squares policy iteration for reinforcement learning.

PubMed

Xu, Xin; Hu, Dewen; Lu, Xicheng

2007-07-01

In this paper, we present a kernel-based least squares policy iteration (KLSPI) algorithm for reinforcement learning (RL) in large or continuous state spaces, which can be used to realize adaptive feedback control of uncertain dynamic systems. By using KLSPI, near-optimal control policies can be obtained without much a priori knowledge on dynamic models of control plants. In KLSPI, Mercer kernels are used in the policy evaluation of a policy iteration process, where a new kernel-based least squares temporal-difference algorithm called KLSTD-Q is proposed for efficient policy evaluation. To keep the sparsity and improve the generalization ability of KLSTD-Q solutions, a kernel sparsification procedure based on approximate linear dependency (ALD) is performed. Compared to the previous works on approximate RL methods, KLSPI makes two progresses to eliminate the main difficulties of existing results. One is the better convergence and (near) optimality guarantee by using the KLSTD-Q algorithm for policy evaluation with high precision. The other is the automatic feature selection using the ALD-based kernel sparsification. Therefore, the KLSPI algorithm provides a general RL method with generalization performance and convergence guarantee for large-scale Markov decision problems (MDPs). Experimental results on a typical RL task for a stochastic chain problem demonstrate that KLSPI can consistently achieve better learning efficiency and policy quality than the previous least squares policy iteration (LSPI) algorithm. Furthermore, the KLSPI method was also evaluated on two nonlinear feedback control problems, including a ship heading control problem and the swing up control of a double-link underactuated pendulum called acrobot. Simulation results illustrate that the proposed method can optimize controller performance using little a priori information of uncertain dynamic systems. It is also demonstrated that KLSPI can be applied to online learning control by incorporating an initial controller to ensure online performance.

VLSI Design of SVM-Based Seizure Detection System With On-Chip Learning Capability.

PubMed

Feng, Lichen; Li, Zunchao; Wang, Yuanfa

2018-02-01

Portable automatic seizure detection system is very convenient for epilepsy patients to carry. In order to make the system on-chip trainable with high efficiency and attain high detection accuracy, this paper presents a very large scale integration (VLSI) design based on the nonlinear support vector machine (SVM). The proposed design mainly consists of a feature extraction (FE) module and an SVM module. The FE module performs the three-level Daubechies discrete wavelet transform to fit the physiological bands of the electroencephalogram (EEG) signal and extracts the time-frequency domain features reflecting the nonstationary signal properties. The SVM module integrates the modified sequential minimal optimization algorithm with the table-driven-based Gaussian kernel to enable efficient on-chip learning. The presented design is verified on an Altera Cyclone II field-programmable gate array and tested using the two publicly available EEG datasets. Experiment results show that the designed VLSI system improves the detection accuracy and training efficiency.

Inference of Spatio-Temporal Functions Over Graphs via Multikernel Kriged Kalman Filtering

NASA Astrophysics Data System (ADS)

Ioannidis, Vassilis N.; Romero, Daniel; Giannakis, Georgios B.

2018-06-01

Inference of space-time varying signals on graphs emerges naturally in a plethora of network science related applications. A frequently encountered challenge pertains to reconstructing such dynamic processes, given their values over a subset of vertices and time instants. The present paper develops a graph-aware kernel-based kriged Kalman filter that accounts for the spatio-temporal variations, and offers efficient online reconstruction, even for dynamically evolving network topologies. The kernel-based learning framework bypasses the need for statistical information by capitalizing on the smoothness that graph signals exhibit with respect to the underlying graph. To address the challenge of selecting the appropriate kernel, the proposed filter is combined with a multi-kernel selection module. Such a data-driven method selects a kernel attuned to the signal dynamics on-the-fly within the linear span of a pre-selected dictionary. The novel multi-kernel learning algorithm exploits the eigenstructure of Laplacian kernel matrices to reduce computational complexity. Numerical tests with synthetic and real data demonstrate the superior reconstruction performance of the novel approach relative to state-of-the-art alternatives.

CLAss-Specific Subspace Kernel Representations and Adaptive Margin Slack Minimization for Large Scale Classification.

PubMed

Yu, Yinan; Diamantaras, Konstantinos I; McKelvey, Tomas; Kung, Sun-Yuan

2018-02-01

In kernel-based classification models, given limited computational power and storage capacity, operations over the full kernel matrix becomes prohibitive. In this paper, we propose a new supervised learning framework using kernel models for sequential data processing. The framework is based on two components that both aim at enhancing the classification capability with a subset selection scheme. The first part is a subspace projection technique in the reproducing kernel Hilbert space using a CLAss-specific Subspace Kernel representation for kernel approximation. In the second part, we propose a novel structural risk minimization algorithm called the adaptive margin slack minimization to iteratively improve the classification accuracy by an adaptive data selection. We motivate each part separately, and then integrate them into learning frameworks for large scale data. We propose two such frameworks: the memory efficient sequential processing for sequential data processing and the parallelized sequential processing for distributed computing with sequential data acquisition. We test our methods on several benchmark data sets and compared with the state-of-the-art techniques to verify the validity of the proposed techniques.

Exploiting graph kernels for high performance biomedical relation extraction.

PubMed

Panyam, Nagesh C; Verspoor, Karin; Cohn, Trevor; Ramamohanarao, Kotagiri

2018-01-30

Relation extraction from biomedical publications is an important task in the area of semantic mining of text. Kernel methods for supervised relation extraction are often preferred over manual feature engineering methods, when classifying highly ordered structures such as trees and graphs obtained from syntactic parsing of a sentence. Tree kernels such as the Subset Tree Kernel and Partial Tree Kernel have been shown to be effective for classifying constituency parse trees and basic dependency parse graphs of a sentence. Graph kernels such as the All Path Graph kernel (APG) and Approximate Subgraph Matching (ASM) kernel have been shown to be suitable for classifying general graphs with cycles, such as the enhanced dependency parse graph of a sentence. In this work, we present a high performance Chemical-Induced Disease (CID) relation extraction system. We present a comparative study of kernel methods for the CID task and also extend our study to the Protein-Protein Interaction (PPI) extraction task, an important biomedical relation extraction task. We discuss novel modifications to the ASM kernel to boost its performance and a method to apply graph kernels for extracting relations expressed in multiple sentences. Our system for CID relation extraction attains an F-score of 60%, without using external knowledge sources or task specific heuristic or rules. In comparison, the state of the art Chemical-Disease Relation Extraction system achieves an F-score of 56% using an ensemble of multiple machine learning methods, which is then boosted to 61% with a rule based system employing task specific post processing rules. For the CID task, graph kernels outperform tree kernels substantially, and the best performance is obtained with APG kernel that attains an F-score of 60%, followed by the ASM kernel at 57%. The performance difference between the ASM and APG kernels for CID sentence level relation extraction is not significant. In our evaluation of ASM for the PPI task, ASM performed better than APG kernel for the BioInfer dataset, in the Area Under Curve (AUC) measure (74% vs 69%). However, for all the other PPI datasets, namely AIMed, HPRD50, IEPA and LLL, ASM is substantially outperformed by the APG kernel in F-score and AUC measures. We demonstrate a high performance Chemical Induced Disease relation extraction, without employing external knowledge sources or task specific heuristics. Our work shows that graph kernels are effective in extracting relations that are expressed in multiple sentences. We also show that the graph kernels, namely the ASM and APG kernels, substantially outperform the tree kernels. Among the graph kernels, we showed the ASM kernel as effective for biomedical relation extraction, with comparable performance to the APG kernel for datasets such as the CID-sentence level relation extraction and BioInfer in PPI. Overall, the APG kernel is shown to be significantly more accurate than the ASM kernel, achieving better performance on most datasets.

Adaptive Shape Kernel-Based Mean Shift Tracker in Robot Vision System

PubMed Central

2016-01-01

This paper proposes an adaptive shape kernel-based mean shift tracker using a single static camera for the robot vision system. The question that we address in this paper is how to construct such a kernel shape that is adaptive to the object shape. We perform nonlinear manifold learning technique to obtain the low-dimensional shape space which is trained by training data with the same view as the tracking video. The proposed kernel searches the shape in the low-dimensional shape space obtained by nonlinear manifold learning technique and constructs the adaptive kernel shape in the high-dimensional shape space. It can improve mean shift tracker performance to track object position and object contour and avoid the background clutter. In the experimental part, we take the walking human as example to validate that our method is accurate and robust to track human position and describe human contour. PMID:27379165

Is extreme learning machine feasible? A theoretical assessment (part II).

PubMed

Lin, Shaobo; Liu, Xia; Fang, Jian; Xu, Zongben

2015-01-01

An extreme learning machine (ELM) can be regarded as a two-stage feed-forward neural network (FNN) learning system that randomly assigns the connections with and within hidden neurons in the first stage and tunes the connections with output neurons in the second stage. Therefore, ELM training is essentially a linear learning problem, which significantly reduces the computational burden. Numerous applications show that such a computation burden reduction does not degrade the generalization capability. It has, however, been open that whether this is true in theory. The aim of this paper is to study the theoretical feasibility of ELM by analyzing the pros and cons of ELM. In the previous part of this topic, we pointed out that via appropriately selected activation functions, ELM does not degrade the generalization capability in the sense of expectation. In this paper, we launch the study in a different direction and show that the randomness of ELM also leads to certain negative consequences. On one hand, we find that the randomness causes an additional uncertainty problem of ELM, both in approximation and learning. On the other hand, we theoretically justify that there also exist activation functions such that the corresponding ELM degrades the generalization capability. In particular, we prove that the generalization capability of ELM with Gaussian kernel is essentially worse than that of FNN with Gaussian kernel. To facilitate the use of ELM, we also provide a remedy to such a degradation. We find that the well-developed coefficient regularization technique can essentially improve the generalization capability. The obtained results reveal the essential characteristic of ELM in a certain sense and give theoretical guidance concerning how to use ELM.

A similarity based learning framework for interim analysis of outcome prediction of acupuncture for neck pain.

PubMed

Zhang, Gang; Liang, Zhaohui; Yin, Jian; Fu, Wenbin; Li, Guo-Zheng

2013-01-01

Chronic neck pain is a common morbid disorder in modern society. Acupuncture has been administered for treating chronic pain as an alternative therapy for a long time, with its effectiveness supported by the latest clinical evidence. However, the potential effective difference in different syndrome types is questioned due to the limits of sample size and statistical methods. We applied machine learning methods in an attempt to solve this problem. Through a multi-objective sorting of subjective measurements, outstanding samples are selected to form the base of our kernel-oriented model. With calculation of similarities between the concerned sample and base samples, we are able to make full use of information contained in the known samples, which is especially effective in the case of a small sample set. To tackle the parameters selection problem in similarity learning, we propose an ensemble version of slightly different parameter setting to obtain stronger learning. The experimental result on a real data set shows that compared to some previous well-known methods, the proposed algorithm is capable of discovering the underlying difference among different syndrome types and is feasible for predicting the effective tendency in clinical trials of large samples.

SVM Classifier - a comprehensive java interface for support vector machine classification of microarray data.

PubMed

Pirooznia, Mehdi; Deng, Youping

2006-12-12

Graphical user interface (GUI) software promotes novelty by allowing users to extend the functionality. SVM Classifier is a cross-platform graphical application that handles very large datasets well. The purpose of this study is to create a GUI application that allows SVM users to perform SVM training, classification and prediction. The GUI provides user-friendly access to state-of-the-art SVM methods embodied in the LIBSVM implementation of Support Vector Machine. We implemented the java interface using standard swing libraries. We used a sample data from a breast cancer study for testing classification accuracy. We achieved 100% accuracy in classification among the BRCA1-BRCA2 samples with RBF kernel of SVM. We have developed a java GUI application that allows SVM users to perform SVM training, classification and prediction. We have demonstrated that support vector machines can accurately classify genes into functional categories based upon expression data from DNA microarray hybridization experiments. Among the different kernel functions that we examined, the SVM that uses a radial basis kernel function provides the best performance. The SVM Classifier is available at http://mfgn.usm.edu/ebl/svm/.

LZW-Kernel: fast kernel utilizing variable length code blocks from LZW compressors for protein sequence classification.

PubMed

Filatov, Gleb; Bauwens, Bruno; Kertész-Farkas, Attila

2018-05-07

Bioinformatics studies often rely on similarity measures between sequence pairs, which often pose a bottleneck in large-scale sequence analysis. Here, we present a new convolutional kernel function for protein sequences called the LZW-Kernel. It is based on code words identified with the Lempel-Ziv-Welch (LZW) universal text compressor. The LZW-Kernel is an alignment-free method, it is always symmetric, is positive, always provides 1.0 for self-similarity and it can directly be used with Support Vector Machines (SVMs) in classification problems, contrary to normalized compression distance (NCD), which often violates the distance metric properties in practice and requires further techniques to be used with SVMs. The LZW-Kernel is a one-pass algorithm, which makes it particularly plausible for big data applications. Our experimental studies on remote protein homology detection and protein classification tasks reveal that the LZW-Kernel closely approaches the performance of the Local Alignment Kernel (LAK) and the SVM-pairwise method combined with Smith-Waterman (SW) scoring at a fraction of the time. Moreover, the LZW-Kernel outperforms the SVM-pairwise method when combined with BLAST scores, which indicates that the LZW code words might be a better basis for similarity measures than local alignment approximations found with BLAST. In addition, the LZW-Kernel outperforms n-gram based mismatch kernels, hidden Markov model based SAM and Fisher kernel, and protein family based PSI-BLAST, among others. Further advantages include the LZW-Kernel's reliance on a simple idea, its ease of implementation, and its high speed, three times faster than BLAST and several magnitudes faster than SW or LAK in our tests. LZW-Kernel is implemented as a standalone C code and is a free open-source program distributed under GPLv3 license and can be downloaded from https://github.com/kfattila/LZW-Kernel. akerteszfarkas@hse.ru. Supplementary data are available at Bioinformatics Online.

Bands selection and classification of hyperspectral images based on hybrid kernels SVM by evolutionary algorithm

NASA Astrophysics Data System (ADS)

Hu, Yan-Yan; Li, Dong-Sheng

2016-01-01

The hyperspectral images(HSI) consist of many closely spaced bands carrying the most object information. While due to its high dimensionality and high volume nature, it is hard to get satisfactory classification performance. In order to reduce HSI data dimensionality preparation for high classification accuracy, it is proposed to combine a band selection method of artificial immune systems (AIS) with a hybrid kernels support vector machine (SVM-HK) algorithm. In fact, after comparing different kernels for hyperspectral analysis, the approach mixed radial basis function kernel (RBF-K) with sigmoid kernel (Sig-K) and applied the optimized hybrid kernels in SVM classifiers. Then the SVM-HK algorithm used to induce the bands selection of an improved version of AIS. The AIS was composed of clonal selection and elite antibody mutation, including evaluation process with optional index factor (OIF). Experimental classification performance was on a San Diego Naval Base acquired by AVIRIS, the HRS dataset shows that the method is able to efficiently achieve bands redundancy removal while outperforming the traditional SVM classifier.

Detection of Abnormal Events via Optical Flow Feature Analysis

PubMed Central

Wang, Tian; Snoussi, Hichem

2015-01-01

In this paper, a novel algorithm is proposed to detect abnormal events in video streams. The algorithm is based on the histogram of the optical flow orientation descriptor and the classification method. The details of the histogram of the optical flow orientation descriptor are illustrated for describing movement information of the global video frame or foreground frame. By combining one-class support vector machine and kernel principal component analysis methods, the abnormal events in the current frame can be detected after a learning period characterizing normal behaviors. The difference abnormal detection results are analyzed and explained. The proposed detection method is tested on benchmark datasets, then the experimental results show the effectiveness of the algorithm. PMID:25811227

Generalization Analysis of Fredholm Kernel Regularized Classifiers.

PubMed

Gong, Tieliang; Xu, Zongben; Chen, Hong

2017-07-01

Recently, a new framework, Fredholm learning, was proposed for semisupervised learning problems based on solving a regularized Fredholm integral equation. It allows a natural way to incorporate unlabeled data into learning algorithms to improve their prediction performance. Despite rapid progress on implementable algorithms with theoretical guarantees, the generalization ability of Fredholm kernel learning has not been studied. In this letter, we focus on investigating the generalization performance of a family of classification algorithms, referred to as Fredholm kernel regularized classifiers. We prove that the corresponding learning rate can achieve [Formula: see text] ([Formula: see text] is the number of labeled samples) in a limiting case. In addition, a representer theorem is provided for the proposed regularized scheme, which underlies its applications.

Linux Kernel Co-Scheduling and Bulk Synchronous Parallelism

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jones, Terry R

2012-01-01

This paper describes a kernel scheduling algorithm that is based on coscheduling principles and that is intended for parallel applications running on 1000 cores or more. Experimental results for a Linux implementation on a Cray XT5 machine are presented. The results indicate that Linux is a suitable operating system for this new scheduling scheme, and that this design provides a dramatic improvement in scaling performance for synchronizing collective operations at scale.

Prediction of heterotrimeric protein complexes by two-phase learning using neighboring kernels

PubMed Central

2014-01-01

Background Protein complexes play important roles in biological systems such as gene regulatory networks and metabolic pathways. Most methods for predicting protein complexes try to find protein complexes with size more than three. It, however, is known that protein complexes with smaller sizes occupy a large part of whole complexes for several species. In our previous work, we developed a method with several feature space mappings and the domain composition kernel for prediction of heterodimeric protein complexes, which outperforms existing methods. Results We propose methods for prediction of heterotrimeric protein complexes by extending techniques in the previous work on the basis of the idea that most heterotrimeric protein complexes are not likely to share the same protein with each other. We make use of the discriminant function in support vector machines (SVMs), and design novel feature space mappings for the second phase. As the second classifier, we examine SVMs and relevance vector machines (RVMs). We perform 10-fold cross-validation computational experiments. The results suggest that our proposed two-phase methods and SVM with the extended features outperform the existing method NWE, which was reported to outperform other existing methods such as MCL, MCODE, DPClus, CMC, COACH, RRW, and PPSampler for prediction of heterotrimeric protein complexes. Conclusions We propose two-phase prediction methods with the extended features, the domain composition kernel, SVMs and RVMs. The two-phase method with the extended features and the domain composition kernel using SVM as the second classifier is particularly useful for prediction of heterotrimeric protein complexes. PMID:24564744

Partial Deconvolution with Inaccurate Blur Kernel.

PubMed

Ren, Dongwei; Zuo, Wangmeng; Zhang, David; Xu, Jun; Zhang, Lei

2017-10-17

Most non-blind deconvolution methods are developed under the error-free kernel assumption, and are not robust to inaccurate blur kernel. Unfortunately, despite the great progress in blind deconvolution, estimation error remains inevitable during blur kernel estimation. Consequently, severe artifacts such as ringing effects and distortions are likely to be introduced in the non-blind deconvolution stage. In this paper, we tackle this issue by suggesting: (i) a partial map in the Fourier domain for modeling kernel estimation error, and (ii) a partial deconvolution model for robust deblurring with inaccurate blur kernel. The partial map is constructed by detecting the reliable Fourier entries of estimated blur kernel. And partial deconvolution is applied to wavelet-based and learning-based models to suppress the adverse effect of kernel estimation error. Furthermore, an E-M algorithm is developed for estimating the partial map and recovering the latent sharp image alternatively. Experimental results show that our partial deconvolution model is effective in relieving artifacts caused by inaccurate blur kernel, and can achieve favorable deblurring quality on synthetic and real blurry images.Most non-blind deconvolution methods are developed under the error-free kernel assumption, and are not robust to inaccurate blur kernel. Unfortunately, despite the great progress in blind deconvolution, estimation error remains inevitable during blur kernel estimation. Consequently, severe artifacts such as ringing effects and distortions are likely to be introduced in the non-blind deconvolution stage. In this paper, we tackle this issue by suggesting: (i) a partial map in the Fourier domain for modeling kernel estimation error, and (ii) a partial deconvolution model for robust deblurring with inaccurate blur kernel. The partial map is constructed by detecting the reliable Fourier entries of estimated blur kernel. And partial deconvolution is applied to wavelet-based and learning-based models to suppress the adverse effect of kernel estimation error. Furthermore, an E-M algorithm is developed for estimating the partial map and recovering the latent sharp image alternatively. Experimental results show that our partial deconvolution model is effective in relieving artifacts caused by inaccurate blur kernel, and can achieve favorable deblurring quality on synthetic and real blurry images.

Real-Time Digital Signal Processing Based on FPGAs for Electronic Skin Implementation †

PubMed Central

Ibrahim, Ali; Gastaldo, Paolo; Chible, Hussein; Valle, Maurizio

2017-01-01

Enabling touch-sensing capability would help appliances understand interaction behaviors with their surroundings. Many recent studies are focusing on the development of electronic skin because of its necessity in various application domains, namely autonomous artificial intelligence (e.g., robots), biomedical instrumentation, and replacement prosthetic devices. An essential task of the electronic skin system is to locally process the tactile data and send structured information either to mimic human skin or to respond to the application demands. The electronic skin must be fabricated together with an embedded electronic system which has the role of acquiring the tactile data, processing, and extracting structured information. On the other hand, processing tactile data requires efficient methods to extract meaningful information from raw sensor data. Machine learning represents an effective method for data analysis in many domains: it has recently demonstrated its effectiveness in processing tactile sensor data. In this framework, this paper presents the implementation of digital signal processing based on FPGAs for tactile data processing. It provides the implementation of a tensorial kernel function for a machine learning approach. Implementation results are assessed by highlighting the FPGA resource utilization and power consumption. Results demonstrate the feasibility of the proposed implementation when real-time classification of input touch modalities are targeted. PMID:28287448

Real-Time Digital Signal Processing Based on FPGAs for Electronic Skin Implementation.

PubMed

Ibrahim, Ali; Gastaldo, Paolo; Chible, Hussein; Valle, Maurizio

2017-03-10

Enabling touch-sensing capability would help appliances understand interaction behaviors with their surroundings. Many recent studies are focusing on the development of electronic skin because of its necessity in various application domains, namely autonomous artificial intelligence (e.g., robots), biomedical instrumentation, and replacement prosthetic devices. An essential task of the electronic skin system is to locally process the tactile data and send structured information either to mimic human skin or to respond to the application demands. The electronic skin must be fabricated together with an embedded electronic system which has the role of acquiring the tactile data, processing, and extracting structured information. On the other hand, processing tactile data requires efficient methods to extract meaningful information from raw sensor data. Machine learning represents an effective method for data analysis in many domains: it has recently demonstrated its effectiveness in processing tactile sensor data. In this framework, this paper presents the implementation of digital signal processing based on FPGAs for tactile data processing. It provides the implementation of a tensorial kernel function for a machine learning approach. Implementation results are assessed by highlighting the FPGA resource utilization and power consumption. Results demonstrate the feasibility of the proposed implementation when real-time classification of input touch modalities are targeted.

Kernel PLS-SVC for Linear and Nonlinear Discrimination

NASA Technical Reports Server (NTRS)

Rosipal, Roman; Trejo, Leonard J.; Matthews, Bryan

2003-01-01

A new methodology for discrimination is proposed. This is based on kernel orthonormalized partial least squares (PLS) dimensionality reduction of the original data space followed by support vector machines for classification. Close connection of orthonormalized PLS and Fisher's approach to linear discrimination or equivalently with canonical correlation analysis is described. This gives preference to use orthonormalized PLS over principal component analysis. Good behavior of the proposed method is demonstrated on 13 different benchmark data sets and on the real world problem of the classification finger movement periods versus non-movement periods based on electroencephalogram.

Evaluation of extreme learning machine for classification of individual and combined finger movements using electromyography on amputees and non-amputees.

PubMed

Anam, Khairul; Al-Jumaily, Adel

2017-01-01

The success of myoelectric pattern recognition (M-PR) mostly relies on the features extracted and classifier employed. This paper proposes and evaluates a fast classifier, extreme learning machine (ELM), to classify individual and combined finger movements on amputees and non-amputees. ELM is a single hidden layer feed-forward network (SLFN) that avoids iterative learning by determining input weights randomly and output weights analytically. Therefore, it can accelerate the training time of SLFNs. In addition to the classifier evaluation, this paper evaluates various feature combinations to improve the performance of M-PR and investigate some feature projections to improve the class separability of the features. Different from other studies on the implementation of ELM in the myoelectric controller, this paper presents a complete and thorough investigation of various types of ELMs including the node-based and kernel-based ELM. Furthermore, this paper provides comparisons of ELMs and other well-known classifiers such as linear discriminant analysis (LDA), k-nearest neighbour (kNN), support vector machine (SVM) and least-square SVM (LS-SVM). The experimental results show the most accurate ELM classifier is radial basis function ELM (RBF-ELM). The comparison of RBF-ELM and other well-known classifiers shows that RBF-ELM is as accurate as SVM and LS-SVM but faster than the SVM family; it is superior to LDA and kNN. The experimental results also indicate that the accuracy gap of the M-PR on the amputees and non-amputees is not too much with the accuracy of 98.55% on amputees and 99.5% on the non-amputees using six electromyography (EMG) channels. Copyright © 2016 Elsevier Ltd. All rights reserved.

Emotion Recognition from Single-Trial EEG Based on Kernel Fisher's Emotion Pattern and Imbalanced Quasiconformal Kernel Support Vector Machine

PubMed Central

Liu, Yi-Hung; Wu, Chien-Te; Cheng, Wei-Teng; Hsiao, Yu-Tsung; Chen, Po-Ming; Teng, Jyh-Tong

2014-01-01

Electroencephalogram-based emotion recognition (EEG-ER) has received increasing attention in the fields of health care, affective computing, and brain-computer interface (BCI). However, satisfactory ER performance within a bi-dimensional and non-discrete emotional space using single-trial EEG data remains a challenging task. To address this issue, we propose a three-layer scheme for single-trial EEG-ER. In the first layer, a set of spectral powers of different EEG frequency bands are extracted from multi-channel single-trial EEG signals. In the second layer, the kernel Fisher's discriminant analysis method is applied to further extract features with better discrimination ability from the EEG spectral powers. The feature vector produced by layer 2 is called a kernel Fisher's emotion pattern (KFEP), and is sent into layer 3 for further classification where the proposed imbalanced quasiconformal kernel support vector machine (IQK-SVM) serves as the emotion classifier. The outputs of the three layer EEG-ER system include labels of emotional valence and arousal. Furthermore, to collect effective training and testing datasets for the current EEG-ER system, we also use an emotion-induction paradigm in which a set of pictures selected from the International Affective Picture System (IAPS) are employed as emotion induction stimuli. The performance of the proposed three-layer solution is compared with that of other EEG spectral power-based features and emotion classifiers. Results on 10 healthy participants indicate that the proposed KFEP feature performs better than other spectral power features, and IQK-SVM outperforms traditional SVM in terms of the EEG-ER accuracy. Our findings also show that the proposed EEG-ER scheme achieves the highest classification accuracies of valence (82.68%) and arousal (84.79%) among all testing methods. PMID:25061837

Emotion recognition from single-trial EEG based on kernel Fisher's emotion pattern and imbalanced quasiconformal kernel support vector machine.

PubMed

Liu, Yi-Hung; Wu, Chien-Te; Cheng, Wei-Teng; Hsiao, Yu-Tsung; Chen, Po-Ming; Teng, Jyh-Tong

2014-07-24

Electroencephalogram-based emotion recognition (EEG-ER) has received increasing attention in the fields of health care, affective computing, and brain-computer interface (BCI). However, satisfactory ER performance within a bi-dimensional and non-discrete emotional space using single-trial EEG data remains a challenging task. To address this issue, we propose a three-layer scheme for single-trial EEG-ER. In the first layer, a set of spectral powers of different EEG frequency bands are extracted from multi-channel single-trial EEG signals. In the second layer, the kernel Fisher's discriminant analysis method is applied to further extract features with better discrimination ability from the EEG spectral powers. The feature vector produced by layer 2 is called a kernel Fisher's emotion pattern (KFEP), and is sent into layer 3 for further classification where the proposed imbalanced quasiconformal kernel support vector machine (IQK-SVM) serves as the emotion classifier. The outputs of the three layer EEG-ER system include labels of emotional valence and arousal. Furthermore, to collect effective training and testing datasets for the current EEG-ER system, we also use an emotion-induction paradigm in which a set of pictures selected from the International Affective Picture System (IAPS) are employed as emotion induction stimuli. The performance of the proposed three-layer solution is compared with that of other EEG spectral power-based features and emotion classifiers. Results on 10 healthy participants indicate that the proposed KFEP feature performs better than other spectral power features, and IQK-SVM outperforms traditional SVM in terms of the EEG-ER accuracy. Our findings also show that the proposed EEG-ER scheme achieves the highest classification accuracies of valence (82.68%) and arousal (84.79%) among all testing methods.

A Novel Mittag-Leffler Kernel Based Hybrid Fault Diagnosis Method for Wheeled Robot Driving System.

PubMed

Yuan, Xianfeng; Song, Mumin; Zhou, Fengyu; Chen, Zhumin; Li, Yan

2015-01-01

The wheeled robots have been successfully applied in many aspects, such as industrial handling vehicles, and wheeled service robots. To improve the safety and reliability of wheeled robots, this paper presents a novel hybrid fault diagnosis framework based on Mittag-Leffler kernel (ML-kernel) support vector machine (SVM) and Dempster-Shafer (D-S) fusion. Using sensor data sampled under different running conditions, the proposed approach initially establishes multiple principal component analysis (PCA) models for fault feature extraction. The fault feature vectors are then applied to train the probabilistic SVM (PSVM) classifiers that arrive at a preliminary fault diagnosis. To improve the accuracy of preliminary results, a novel ML-kernel based PSVM classifier is proposed in this paper, and the positive definiteness of the ML-kernel is proved as well. The basic probability assignments (BPAs) are defined based on the preliminary fault diagnosis results and their confidence values. Eventually, the final fault diagnosis result is archived by the fusion of the BPAs. Experimental results show that the proposed framework not only is capable of detecting and identifying the faults in the robot driving system, but also has better performance in stability and diagnosis accuracy compared with the traditional methods.

A Novel Mittag-Leffler Kernel Based Hybrid Fault Diagnosis Method for Wheeled Robot Driving System

PubMed Central

Yuan, Xianfeng; Song, Mumin; Chen, Zhumin; Li, Yan

2015-01-01

The wheeled robots have been successfully applied in many aspects, such as industrial handling vehicles, and wheeled service robots. To improve the safety and reliability of wheeled robots, this paper presents a novel hybrid fault diagnosis framework based on Mittag-Leffler kernel (ML-kernel) support vector machine (SVM) and Dempster-Shafer (D-S) fusion. Using sensor data sampled under different running conditions, the proposed approach initially establishes multiple principal component analysis (PCA) models for fault feature extraction. The fault feature vectors are then applied to train the probabilistic SVM (PSVM) classifiers that arrive at a preliminary fault diagnosis. To improve the accuracy of preliminary results, a novel ML-kernel based PSVM classifier is proposed in this paper, and the positive definiteness of the ML-kernel is proved as well. The basic probability assignments (BPAs) are defined based on the preliminary fault diagnosis results and their confidence values. Eventually, the final fault diagnosis result is archived by the fusion of the BPAs. Experimental results show that the proposed framework not only is capable of detecting and identifying the faults in the robot driving system, but also has better performance in stability and diagnosis accuracy compared with the traditional methods. PMID:26229526

Applying machine-learning techniques to Twitter data for automatic hazard-event classification.

NASA Astrophysics Data System (ADS)

Filgueira, R.; Bee, E. J.; Diaz-Doce, D.; Poole, J., Sr.; Singh, A.

2017-12-01

The constant flow of information offered by tweets provides valuable information about all sorts of events at a high temporal and spatial resolution. Over the past year we have been analyzing in real-time geological hazards/phenomenon, such as earthquakes, volcanic eruptions, landslides, floods or the aurora, as part of the GeoSocial project, by geo-locating tweets filtered by keywords in a web-map. However, not all the filtered tweets are related with hazard/phenomenon events. This work explores two classification techniques for automatic hazard-event categorization based on tweets about the "Aurora". First, tweets were filtered using aurora-related keywords, removing stop words and selecting the ones written in English. For classifying the remaining between "aurora-event" or "no-aurora-event" categories, we compared two state-of-art techniques: Support Vector Machine (SVM) and Deep Convolutional Neural Networks (CNN) algorithms. Both approaches belong to the family of supervised learning algorithms, which make predictions based on labelled training dataset. Therefore, we created a training dataset by tagging 1200 tweets between both categories. The general form of SVM is used to separate two classes by a function (kernel). We compared the performance of four different kernels (Linear Regression, Logistic Regression, Multinomial Naïve Bayesian and Stochastic Gradient Descent) provided by Scikit-Learn library using our training dataset to build the SVM classifier. The results shown that the Logistic Regression (LR) gets the best accuracy (87%). So, we selected the SVM-LR classifier to categorise a large collection of tweets using the "dispel4py" framework.Later, we developed a CNN classifier, where the first layer embeds words into low-dimensional vectors. The next layer performs convolutions over the embedded word vectors. Results from the convolutional layer are max-pooled into a long feature vector, which is classified using a softmax layer. The CNN's accuracy is lower (83%) than the SVM-LR, since the algorithm needs a bigger training dataset to increase its accuracy. We used TensorFlow framework for applying CNN classifier to the same collection of tweets.In future we will modify both classifiers to work with other geo-hazards, use larger training datasets and apply them in real-time.

Ideal regularization for learning kernels from labels.

PubMed

Pan, Binbin; Lai, Jianhuang; Shen, Lixin

2014-08-01

In this paper, we propose a new form of regularization that is able to utilize the label information of a data set for learning kernels. The proposed regularization, referred to as ideal regularization, is a linear function of the kernel matrix to be learned. The ideal regularization allows us to develop efficient algorithms to exploit labels. Three applications of the ideal regularization are considered. Firstly, we use the ideal regularization to incorporate the labels into a standard kernel, making the resulting kernel more appropriate for learning tasks. Next, we employ the ideal regularization to learn a data-dependent kernel matrix from an initial kernel matrix (which contains prior similarity information, geometric structures, and labels of the data). Finally, we incorporate the ideal regularization to some state-of-the-art kernel learning problems. With this regularization, these learning problems can be formulated as simpler ones which permit more efficient solvers. Empirical results show that the ideal regularization exploits the labels effectively and efficiently. Copyright © 2014 Elsevier Ltd. All rights reserved.

Mass Estimation and Its Applications

DTIC Science & Technology

2012-02-23

parameters); e.g., the rect- angular kernel function has fixed width or fixed per unit size. But the rectangular function used in mass has no parameter...MassTER is implemented in JAVA , and we use DBSCAN in WEKA [13] and a version of DENCLUE implemented in R (www.r-project.org) in our empirical evaluation...Proceedings of SIGKDD, 2010, 989-998. [13] I.H. Witten and E. Frank, Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations

A new discriminative kernel from probabilistic models.

PubMed

Tsuda, Koji; Kawanabe, Motoaki; Rätsch, Gunnar; Sonnenburg, Sören; Müller, Klaus-Robert

2002-10-01

Recently, Jaakkola and Haussler (1999) proposed a method for constructing kernel functions from probabilistic models. Their so-called Fisher kernel has been combined with discriminative classifiers such as support vector machines and applied successfully in, for example, DNA and protein analysis. Whereas the Fisher kernel is calculated from the marginal log-likelihood, we propose the TOP kernel derived; from tangent vectors of posterior log-odds. Furthermore, we develop a theoretical framework on feature extractors from probabilistic models and use it for analyzing the TOP kernel. In experiments, our new discriminative TOP kernel compares favorably to the Fisher kernel.

Out-of-Sample Extensions for Non-Parametric Kernel Methods.

PubMed

Pan, Binbin; Chen, Wen-Sheng; Chen, Bo; Xu, Chen; Lai, Jianhuang

2017-02-01

Choosing suitable kernels plays an important role in the performance of kernel methods. Recently, a number of studies were devoted to developing nonparametric kernels. Without assuming any parametric form of the target kernel, nonparametric kernel learning offers a flexible scheme to utilize the information of the data, which may potentially characterize the data similarity better. The kernel methods using nonparametric kernels are referred to as nonparametric kernel methods. However, many nonparametric kernel methods are restricted to transductive learning, where the prediction function is defined only over the data points given beforehand. They have no straightforward extension for the out-of-sample data points, and thus cannot be applied to inductive learning. In this paper, we show how to make the nonparametric kernel methods applicable to inductive learning. The key problem of out-of-sample extension is how to extend the nonparametric kernel matrix to the corresponding kernel function. A regression approach in the hyper reproducing kernel Hilbert space is proposed to solve this problem. Empirical results indicate that the out-of-sample performance is comparable to the in-sample performance in most cases. Experiments on face recognition demonstrate the superiority of our nonparametric kernel method over the state-of-the-art parametric kernel methods.

A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in Lung nodule CAD.

PubMed

Cao, Peng; Liu, Xiaoli; Zhang, Jian; Li, Wei; Zhao, Dazhe; Huang, Min; Zaiane, Osmar

2017-03-01

The aim of this paper is to describe a novel algorithm for False Positive Reduction in lung nodule Computer Aided Detection(CAD). In this paper, we describes a new CT lung CAD method which aims to detect solid nodules. Specially, we proposed a multi-kernel classifier with a ℓ 2, 1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, and designed two efficient strategies to optimize the parameters of kernel weights in non-smooth ℓ 2, 1 regularized multiple kernel learning algorithm. The first optimization algorithm adapts a proximal gradient method for solving the ℓ 2, 1 norm of kernel weights, and use an accelerated method based on FISTA; the second one employs an iterative scheme based on an approximate gradient descent method. The results demonstrates that the FISTA-style accelerated proximal descent method is efficient for the ℓ 2, 1 norm formulation of multiple kernel learning with the theoretical guarantee of the convergence rate. Moreover, the experimental results demonstrate the effectiveness of the proposed methods in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and significantly outperforms the competing methods. The proposed approach exhibits some remarkable advantages both in heterogeneous feature subsets fusion and classification phases. Compared with the fusion strategies of feature-level and decision level, the proposed ℓ 2, 1 norm multi-kernel learning algorithm is able to accurately fuse the complementary and heterogeneous feature sets, and automatically prune the irrelevant and redundant feature subsets to form a more discriminative feature set, leading a promising classification performance. Moreover, the proposed algorithm consistently outperforms the comparable classification approaches in the literature. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

An information theoretic approach of designing sparse kernel adaptive filters.

PubMed

Liu, Weifeng; Park, Il; Principe, José C

2009-12-01

This paper discusses an information theoretic approach of designing sparse kernel adaptive filters. To determine useful data to be learned and remove redundant ones, a subjective information measure called surprise is introduced. Surprise captures the amount of information a datum contains which is transferable to a learning system. Based on this concept, we propose a systematic sparsification scheme, which can drastically reduce the time and space complexity without harming the performance of kernel adaptive filters. Nonlinear regression, short term chaotic time-series prediction, and long term time-series forecasting examples are presented.

Combining heterogeneous features for colonic polyp detection in CTC based on semi-definite programming

NASA Astrophysics Data System (ADS)

Wang, Shijun; Yao, Jianhua; Petrick, Nicholas A.; Summers, Ronald M.

2009-02-01

Colon cancer is the second leading cause of cancer-related deaths in the United States. Computed tomographic colonography (CTC) combined with a computer aided detection system provides a feasible combination for improving colonic polyps detection and increasing the use of CTC for colon cancer screening. To distinguish true polyps from false positives, various features extracted from polyp candidates have been proposed. Most of these features try to capture the shape information of polyp candidates or neighborhood knowledge about the surrounding structures (fold, colon wall, etc.). In this paper, we propose a new set of shape descriptors for polyp candidates based on statistical curvature information. These features, called histogram of curvature features, are rotation, translation and scale invariant and can be treated as complementing our existing feature set. Then in order to make full use of the traditional features (defined as group A) and the new features (group B) which are highly heterogeneous, we employed a multiple kernel learning method based on semi-definite programming to identify an optimized classification kernel based on the combined set of features. We did leave-one-patient-out test on a CTC dataset which contained scans from 50 patients (with 90 6-9mm polyp detections). Experimental results show that a support vector machine (SVM) based on the combined feature set and the semi-definite optimization kernel achieved higher FROC performance compared to SVMs using the two groups of features separately. At a false positive per patient rate of 7, the sensitivity on 6-9mm polyps using the combined features improved from 0.78 (Group A) and 0.73 (Group B) to 0.82 (p<=0.01).

Simulating and Detecting Radiation-Induced Errors for Onboard Machine Learning

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri L.; Bornstein, Benjamin; Granat, Robert; Tang, Benyang; Turmon, Michael

2009-01-01

Spacecraft processors and memory are subjected to high radiation doses and therefore employ radiation-hardened components. However, these components are orders of magnitude more expensive than typical desktop components, and they lag years behind in terms of speed and size. We have integrated algorithm-based fault tolerance (ABFT) methods into onboard data analysis algorithms to detect radiation-induced errors, which ultimately may permit the use of spacecraft memory that need not be fully hardened, reducing cost and increasing capability at the same time. We have also developed a lightweight software radiation simulator, BITFLIPS, that permits evaluation of error detection strategies in a controlled fashion, including the specification of the radiation rate and selective exposure of individual data structures. Using BITFLIPS, we evaluated our error detection methods when using a support vector machine to analyze data collected by the Mars Odyssey spacecraft. We found ABFT error detection for matrix multiplication is very successful, while error detection for Gaussian kernel computation still has room for improvement.

Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data.

PubMed

Koutsoukas, Alexios; Monaghan, Keith J; Li, Xiaoli; Huan, Jun

2017-06-28

In recent years, research in artificial neural networks has resurged, now under the deep-learning umbrella, and grown extremely popular. Recently reported success of DL techniques in crowd-sourced QSAR and predictive toxicology competitions has showcased these methods as powerful tools in drug-discovery and toxicology research. The aim of this work was dual, first large number of hyper-parameter configurations were explored to investigate how they affect the performance of DNNs and could act as starting points when tuning DNNs and second their performance was compared to popular methods widely employed in the field of cheminformatics namely Naïve Bayes, k-nearest neighbor, random forest and support vector machines. Moreover, robustness of machine learning methods to different levels of artificially introduced noise was assessed. The open-source Caffe deep-learning framework and modern NVidia GPU units were utilized to carry out this study, allowing large number of DNN configurations to be explored. We show that feed-forward deep neural networks are capable of achieving strong classification performance and outperform shallow methods across diverse activity classes when optimized. Hyper-parameters that were found to play critical role are the activation function, dropout regularization, number hidden layers and number of neurons. When compared to the rest methods, tuned DNNs were found to statistically outperform, with p value <0.01 based on Wilcoxon statistical test. DNN achieved on average MCC units of 0.149 higher than NB, 0.092 than kNN, 0.052 than SVM with linear kernel, 0.021 than RF and finally 0.009 higher than SVM with radial basis function kernel. When exploring robustness to noise, non-linear methods were found to perform well when dealing with low levels of noise, lower than or equal to 20%, however when dealing with higher levels of noise, higher than 30%, the Naïve Bayes method was found to perform well and even outperform at the highest level of noise 50% more sophisticated methods across several datasets.

Genomic similarity and kernel methods I: advancements by building on mathematical and statistical foundations.

PubMed

Schaid, Daniel J

2010-01-01

Measures of genomic similarity are the basis of many statistical analytic methods. We review the mathematical and statistical basis of similarity methods, particularly based on kernel methods. A kernel function converts information for a pair of subjects to a quantitative value representing either similarity (larger values meaning more similar) or distance (smaller values meaning more similar), with the requirement that it must create a positive semidefinite matrix when applied to all pairs of subjects. This review emphasizes the wide range of statistical methods and software that can be used when similarity is based on kernel methods, such as nonparametric regression, linear mixed models and generalized linear mixed models, hierarchical models, score statistics, and support vector machines. The mathematical rigor for these methods is summarized, as is the mathematical framework for making kernels. This review provides a framework to move from intuitive and heuristic approaches to define genomic similarities to more rigorous methods that can take advantage of powerful statistical modeling and existing software. A companion paper reviews novel approaches to creating kernels that might be useful for genomic analyses, providing insights with examples [1]. Copyright © 2010 S. Karger AG, Basel.

Linux Kernel Co-Scheduling For Bulk Synchronous Parallel Applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jones, Terry R

2011-01-01

This paper describes a kernel scheduling algorithm that is based on co-scheduling principles and that is intended for parallel applications running on 1000 cores or more where inter-node scalability is key. Experimental results for a Linux implementation on a Cray XT5 machine are presented.1 The results indicate that Linux is a suitable operating system for this new scheduling scheme, and that this design provides a dramatic improvement in scaling performance for synchronizing collective operations at scale.

An Approximate Approach to Automatic Kernel Selection.

PubMed

Ding, Lizhong; Liao, Shizhong

2016-02-02

Kernel selection is a fundamental problem of kernel-based learning algorithms. In this paper, we propose an approximate approach to automatic kernel selection for regression from the perspective of kernel matrix approximation. We first introduce multilevel circulant matrices into automatic kernel selection, and develop two approximate kernel selection algorithms by exploiting the computational virtues of multilevel circulant matrices. The complexity of the proposed algorithms is quasi-linear in the number of data points. Then, we prove an approximation error bound to measure the effect of the approximation in kernel matrices by multilevel circulant matrices on the hypothesis and further show that the approximate hypothesis produced with multilevel circulant matrices converges to the accurate hypothesis produced with kernel matrices. Experimental evaluations on benchmark datasets demonstrate the effectiveness of approximate kernel selection.

A Wavelet Support Vector Machine Combination Model for Singapore Tourist Arrival to Malaysia

NASA Astrophysics Data System (ADS)

Rafidah, A.; Shabri, Ani; Nurulhuda, A.; Suhaila, Y.

2017-08-01

In this study, wavelet support vector machine model (WSVM) is proposed and applied for monthly data Singapore tourist time series prediction. The WSVM model is combination between wavelet analysis and support vector machine (SVM). In this study, we have two parts, first part we compare between the kernel function and second part we compare between the developed models with single model, SVM. The result showed that kernel function linear better than RBF while WSVM outperform with single model SVM to forecast monthly Singapore tourist arrival to Malaysia.

Prediction of Human Intestinal Absorption of Compounds Using Artificial Intelligence Techniques.

PubMed

Kumar, Rajnish; Sharma, Anju; Siddiqui, Mohammed Haris; Tiwari, Rajesh Kumar

2017-01-01

Information about Pharmacokinetics of compounds is an essential component of drug design and development. Modeling the pharmacokinetic properties require identification of the factors effecting absorption, distribution, metabolism and excretion of compounds. There have been continuous attempts in the prediction of intestinal absorption of compounds using various Artificial intelligence methods in the effort to reduce the attrition rate of drug candidates entering to preclinical and clinical trials. Currently, there are large numbers of individual predictive models available for absorption using machine learning approaches. Six Artificial intelligence methods namely, Support vector machine, k- nearest neighbor, Probabilistic neural network, Artificial neural network, Partial least square and Linear discriminant analysis were used for prediction of absorption of compounds. Prediction accuracy of Support vector machine, k- nearest neighbor, Probabilistic neural network, Artificial neural network, Partial least square and Linear discriminant analysis for prediction of intestinal absorption of compounds was found to be 91.54%, 88.33%, 84.30%, 86.51%, 79.07% and 80.08% respectively. Comparative analysis of all the six prediction models suggested that Support vector machine with Radial basis function based kernel is comparatively better for binary classification of compounds using human intestinal absorption and may be useful at preliminary stages of drug design and development. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Multi-pose facial correction based on Gaussian process with combined kernel function

NASA Astrophysics Data System (ADS)

Shi, Shuyan; Ji, Ruirui; Zhang, Fan

2018-04-01

In order to improve the recognition rate of various postures, this paper proposes a method of facial correction based on Gaussian Process which build a nonlinear regression model between the front and the side face with combined kernel function. The face images with horizontal angle from -45° to +45° can be properly corrected to front faces. Finally, Support Vector Machine is employed for face recognition. Experiments on CAS PEAL R1 face database show that Gaussian process can weaken the influence of pose changes and improve the accuracy of face recognition to certain extent.

Exploring the color feature power for psoriasis risk stratification and classification: A data mining paradigm.

PubMed

Shrivastava, Vimal K; Londhe, Narendra D; Sonawane, Rajendra S; Suri, Jasjit S

2015-10-01

A large percentage of dermatologist׳s decision in psoriasis disease assessment is based on color. The current computer-aided diagnosis systems for psoriasis risk stratification and classification lack the vigor of color paradigm. The paper presents an automated psoriasis computer-aided diagnosis (pCAD) system for classification of psoriasis skin images into psoriatic lesion and healthy skin, which solves the two major challenges: (i) fulfills the color feature requirements and (ii) selects the powerful dominant color features while retaining high classification accuracy. Fourteen color spaces are discovered for psoriasis disease analysis leading to 86 color features. The pCAD system is implemented in a support vector-based machine learning framework where the offline image data set is used for computing machine learning offline color machine learning parameters. These are then used for transformation of the online color features to predict the class labels for healthy vs. diseased cases. The above paradigm uses principal component analysis for color feature selection of dominant features, keeping the original color feature unaltered. Using the cross-validation protocol, the above machine learning protocol is compared against the standalone grayscale features with 60 features and against the combined grayscale and color feature set of 146. Using a fixed data size of 540 images with equal number of healthy and diseased, 10 fold cross-validation protocol, and SVM of polynomial kernel of type two, pCAD system shows an accuracy of 99.94% with sensitivity and specificity of 99.93% and 99.96%. Using a varying data size protocol, the mean classification accuracies for color, grayscale, and combined scenarios are: 92.85%, 93.83% and 93.99%, respectively. The reliability of the system in these three scenarios are: 94.42%, 97.39% and 96.00%, respectively. We conclude that pCAD system using color space alone is compatible to grayscale space or combined color and grayscale spaces. We validated our pCAD system against facial color databases and the results are consistent in accuracy and reliability. Copyright © 2015 Elsevier Ltd. All rights reserved.

Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

PubMed

McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

2018-04-01

Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

An Operating Environment for the Jellybean Machine

DTIC Science & Technology

1988-05-01

MODEL 48 5.4.4 Restarting a Context The operating system provides one primitive message (RESTART-CONTEXT) and two system calls (XFERID and XFER.ADDR) to...efficient, powerful services is reqired to support this "stem. To provide this supportive operating environment, I developed an operating system kernel that...serves many of the initial needs of our machine. This Jellybean Operating System Software provides an object- based storage model, where typed

Machine Learning Feature Selection for Tuning Memory Page Swapping

DTIC Science & Technology

2013-09-01

environments we set up. 13 Figure 4.1 Updated Feature Vector List. Features we added to the kernel are anno - tated with “(MLVM...Feb. 1966. [2] P. J . Denning, “The working set model for program behavior,” Communications of the ACM, vol. 11, no. 5, pp. 323–333, May 1968. [3] L. A...8] R. W. Cart and J . L. Hennessy, “WSClock — A simple and effective algorithm for virtual memory management,” M.S. thesis, Dept. Computer Science

Putting Priors in Mixture Density Mercer Kernels

NASA Technical Reports Server (NTRS)

Srivastava, Ashok N.; Schumann, Johann; Fischer, Bernd

2004-01-01

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly infinite dimensional feature space. We describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using predefined kernels. These data adaptive kernels can en- code prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS). The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains template for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic- algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code. The results show that the Mixture Density Mercer-Kernel described here outperforms tree-based classification in distinguishing high-redshift galaxies from low- redshift galaxies by approximately 16% on test data, bagged trees by approximately 7%, and bagged trees built on a much larger sample of data by approximately 2%.

The maximum vector-angular margin classifier and its fast training on large datasets using a core vector machine.

PubMed

Hu, Wenjun; Chung, Fu-Lai; Wang, Shitong

2012-03-01

Although pattern classification has been extensively studied in the past decades, how to effectively solve the corresponding training on large datasets is a problem that still requires particular attention. Many kernelized classification methods, such as SVM and SVDD, can be formulated as the corresponding quadratic programming (QP) problems, but computing the associated kernel matrices requires O(n2)(or even up to O(n3)) computational complexity, where n is the size of the training patterns, which heavily limits the applicability of these methods for large datasets. In this paper, a new classification method called the maximum vector-angular margin classifier (MAMC) is first proposed based on the vector-angular margin to find an optimal vector c in the pattern feature space, and all the testing patterns can be classified in terms of the maximum vector-angular margin ρ, between the vector c and all the training data points. Accordingly, it is proved that the kernelized MAMC can be equivalently formulated as the kernelized Minimum Enclosing Ball (MEB), which leads to a distinctive merit of MAMC, i.e., it has the flexibility of controlling the sum of support vectors like v-SVC and may be extended to a maximum vector-angular margin core vector machine (MAMCVM) by connecting the core vector machine (CVM) method with MAMC such that the corresponding fast training on large datasets can be effectively achieved. Experimental results on artificial and real datasets are provided to validate the power of the proposed methods. Copyright © 2011 Elsevier Ltd. All rights reserved.

Support vector machines for prediction and analysis of beta and gamma-turns in proteins.

PubMed

Pham, Tho Hoan; Satou, Kenji; Ho, Tu Bao

2005-04-01

Tight turns have long been recognized as one of the three important features of proteins, together with alpha-helix and beta-sheet. Tight turns play an important role in globular proteins from both the structural and functional points of view. More than 90% tight turns are beta-turns and most of the rest are gamma-turns. Analysis and prediction of beta-turns and gamma-turns is very useful for design of new molecules such as drugs, pesticides, and antigens. In this paper we investigated two aspects of applying support vector machine (SVM), a promising machine learning method for bioinformatics, to prediction and analysis of beta-turns and gamma-turns. First, we developed two SVM-based methods, called BTSVM and GTSVM, which predict beta-turns and gamma-turns in a protein from its sequence. When compared with other methods, BTSVM has a superior performance and GTSVM is competitive. Second, we used SVMs with a linear kernel to estimate the support of amino acids for the formation of beta-turns and gamma-turns depending on their position in a protein. Our analysis results are more comprehensive and easier to use than the previous results in designing turns in proteins.

Statistical downscaling of GCM simulations to streamflow using relevance vector machine

NASA Astrophysics Data System (ADS)

Ghosh, Subimal; Mujumdar, P. P.

2008-01-01

General circulation models (GCMs), the climate models often used in assessing the impact of climate change, operate on a coarse scale and thus the simulation results obtained from GCMs are not particularly useful in a comparatively smaller river basin scale hydrology. The article presents a methodology of statistical downscaling based on sparse Bayesian learning and Relevance Vector Machine (RVM) to model streamflow at river basin scale for monsoon period (June, July, August, September) using GCM simulated climatic variables. NCEP/NCAR reanalysis data have been used for training the model to establish a statistical relationship between streamflow and climatic variables. The relationship thus obtained is used to project the future streamflow from GCM simulations. The statistical methodology involves principal component analysis, fuzzy clustering and RVM. Different kernel functions are used for comparison purpose. The model is applied to Mahanadi river basin in India. The results obtained using RVM are compared with those of state-of-the-art Support Vector Machine (SVM) to present the advantages of RVMs over SVMs. A decreasing trend is observed for monsoon streamflow of Mahanadi due to high surface warming in future, with the CCSR/NIES GCM and B2 scenario.

Automated segmentation of the parotid gland based on atlas registration and machine learning: a longitudinal MRI study in head-and-neck radiation therapy.

PubMed

Yang, Xiaofeng; Wu, Ning; Cheng, Guanghui; Zhou, Zhengyang; Yu, David S; Beitler, Jonathan J; Curran, Walter J; Liu, Tian

2014-12-01

To develop an automated magnetic resonance imaging (MRI) parotid segmentation method to monitor radiation-induced parotid gland changes in patients after head and neck radiation therapy (RT). The proposed method combines the atlas registration method, which captures the global variation of anatomy, with a machine learning technology, which captures the local statistical features, to automatically segment the parotid glands from the MRIs. The segmentation method consists of 3 major steps. First, an atlas (pre-RT MRI and manually contoured parotid gland mask) is built for each patient. A hybrid deformable image registration is used to map the pre-RT MRI to the post-RT MRI, and the transformation is applied to the pre-RT parotid volume. Second, the kernel support vector machine (SVM) is trained with the subject-specific atlas pair consisting of multiple features (intensity, gradient, and others) from the aligned pre-RT MRI and the transformed parotid volume. Third, the well-trained kernel SVM is used to differentiate the parotid from surrounding tissues in the post-RT MRIs by statistically matching multiple texture features. A longitudinal study of 15 patients undergoing head and neck RT was conducted: baseline MRI was acquired prior to RT, and the post-RT MRIs were acquired at 3-, 6-, and 12-month follow-up examinations. The resulting segmentations were compared with the physicians' manual contours. Successful parotid segmentation was achieved for all 15 patients (42 post-RT MRIs). The average percentage of volume differences between the automated segmentations and those of the physicians' manual contours were 7.98% for the left parotid and 8.12% for the right parotid. The average volume overlap was 91.1% ± 1.6% for the left parotid and 90.5% ± 2.4% for the right parotid. The parotid gland volume reduction at follow-up was 25% at 3 months, 27% at 6 months, and 16% at 12 months. We have validated our automated parotid segmentation algorithm in a longitudinal study. This segmentation method may be useful in future studies to address radiation-induced xerostomia in head and neck radiation therapy. Copyright © 2014 Elsevier Inc. All rights reserved.

A Kernel-Based Low-Rank (KLR) Model for Low-Dimensional Manifold Recovery in Highly Accelerated Dynamic MRI.

PubMed

Nakarmi, Ukash; Wang, Yanhua; Lyu, Jingyuan; Liang, Dong; Ying, Leslie

2017-11-01

While many low rank and sparsity-based approaches have been developed for accelerated dynamic magnetic resonance imaging (dMRI), they all use low rankness or sparsity in input space, overlooking the intrinsic nonlinear correlation in most dMRI data. In this paper, we propose a kernel-based framework to allow nonlinear manifold models in reconstruction from sub-Nyquist data. Within this framework, many existing algorithms can be extended to kernel framework with nonlinear models. In particular, we have developed a novel algorithm with a kernel-based low-rank model generalizing the conventional low rank formulation. The algorithm consists of manifold learning using kernel, low rank enforcement in feature space, and preimaging with data consistency. Extensive simulation and experiment results show that the proposed method surpasses the conventional low-rank-modeled approaches for dMRI.

Identifying presence of correlated errors in GRACE monthly harmonic coefficients using machine learning algorithms

NASA Astrophysics Data System (ADS)

Piretzidis, Dimitrios; Sra, Gurveer; Karantaidis, George; Sideris, Michael G.

2017-04-01

A new method for identifying correlated errors in Gravity Recovery and Climate Experiment (GRACE) monthly harmonic coefficients has been developed and tested. Correlated errors are present in the differences between monthly GRACE solutions, and can be suppressed using a de-correlation filter. In principle, the de-correlation filter should be implemented only on coefficient series with correlated errors to avoid losing useful geophysical information. In previous studies, two main methods of implementing the de-correlation filter have been utilized. In the first one, the de-correlation filter is implemented starting from a specific minimum order until the maximum order of the monthly solution examined. In the second one, the de-correlation filter is implemented only on specific coefficient series, the selection of which is based on statistical testing. The method proposed in the present study exploits the capabilities of supervised machine learning algorithms such as neural networks and support vector machines (SVMs). The pattern of correlated errors can be described by several numerical and geometric features of the harmonic coefficient series. The features of extreme cases of both correlated and uncorrelated coefficients are extracted and used for the training of the machine learning algorithms. The trained machine learning algorithms are later used to identify correlated errors and provide the probability of a coefficient series to be correlated. Regarding SVMs algorithms, an extensive study is performed with various kernel functions in order to find the optimal training model for prediction. The selection of the optimal training model is based on the classification accuracy of the trained SVM algorithm on the same samples used for training. Results show excellent performance of all algorithms with a classification accuracy of 97% - 100% on a pre-selected set of training samples, both in the validation stage of the training procedure and in the subsequent use of the trained algorithms to classify independent coefficients. This accuracy is also confirmed by the external validation of the trained algorithms using the hydrology model GLDAS NOAH. The proposed method meet the requirement of identifying and de-correlating only coefficients with correlated errors. Also, there is no need of applying statistical testing or other techniques that require prior de-correlation of the harmonic coefficients.

A comparison of machine learning methods for classification using simulation with multiple real data examples from mental health studies.

PubMed

Khondoker, Mizanur; Dobson, Richard; Skirrow, Caroline; Simmons, Andrew; Stahl, Daniel

2016-10-01

Recent literature on the comparison of machine learning methods has raised questions about the neutrality, unbiasedness and utility of many comparative studies. Reporting of results on favourable datasets and sampling error in the estimated performance measures based on single samples are thought to be the major sources of bias in such comparisons. Better performance in one or a few instances does not necessarily imply so on an average or on a population level and simulation studies may be a better alternative for objectively comparing the performances of machine learning algorithms. We compare the classification performance of a number of important and widely used machine learning algorithms, namely the Random Forests (RF), Support Vector Machines (SVM), Linear Discriminant Analysis (LDA) and k-Nearest Neighbour (kNN). Using massively parallel processing on high-performance supercomputers, we compare the generalisation errors at various combinations of levels of several factors: number of features, training sample size, biological variation, experimental variation, effect size, replication and correlation between features. For smaller number of correlated features, number of features not exceeding approximately half the sample size, LDA was found to be the method of choice in terms of average generalisation errors as well as stability (precision) of error estimates. SVM (with RBF kernel) outperforms LDA as well as RF and kNN by a clear margin as the feature set gets larger provided the sample size is not too small (at least 20). The performance of kNN also improves as the number of features grows and outplays that of LDA and RF unless the data variability is too high and/or effect sizes are too small. RF was found to outperform only kNN in some instances where the data are more variable and have smaller effect sizes, in which cases it also provide more stable error estimates than kNN and LDA. Applications to a number of real datasets supported the findings from the simulation study. © The Author(s) 2013.

Recognition and Quantification of Area Damaged by Oligonychus Perseae in Avocado Leaves

NASA Astrophysics Data System (ADS)

Díaz, Gloria; Romero, Eduardo; Boyero, Juan R.; Malpica, Norberto

The measure of leaf damage is a basic tool in plant epidemiology research. Measuring the area of a great number of leaves is subjective and time consuming. We investigate the use of machine learning approaches for the objective segmentation and quantification of leaf area damaged by mites in avocado leaves. After extraction of the leaf veins, pixels are labeled with a look-up table generated using a Support Vector Machine with a polynomial kernel of degree 3, on the chrominance components of YCrCb color space. Spatial information is included in the segmentation process by rating the degree of membership to a certain class and the homogeneity of the classified region. Results are presented on real images with different degrees of damage.

Providing Observation Context via Kernel Visualization and Informatics for Planning and Data Analysis

NASA Astrophysics Data System (ADS)

Kidd, J. N.; Selznick, S.; Hergenrother, C. W.

2018-04-01

From our lessons learned and SPICE expertise, we lay out the features and capabilities of a new web-based tool to provide an accessible platform to obtain context and informatics from a planetary mission's SPICE kernels.

A Novel Application of Machine Learning Methods to Model Microcontroller Upset Due to Intentional Electromagnetic Interference

NASA Astrophysics Data System (ADS)

Bilalic, Rusmir

A novel application of support vector machines (SVMs), artificial neural networks (ANNs), and Gaussian processes (GPs) for machine learning (GPML) to model microcontroller unit (MCU) upset due to intentional electromagnetic interference (IEMI) is presented. In this approach, an MCU performs a counting operation (0-7) while electromagnetic interference in the form of a radio frequency (RF) pulse is direct-injected into the MCU clock line. Injection times with respect to the clock signal are the clock low, clock rising edge, clock high, and the clock falling edge periods in the clock window during which the MCU is performing initialization and executing the counting procedure. The intent is to cause disruption in the counting operation and model the probability of effect (PoE) using machine learning tools. Five experiments were executed as part of this research, each of which contained a set of 38,300 training points and 38,300 test points, for a total of 383,000 total points with the following experiment variables: injection times with respect to the clock signal, injected RF power, injected RF pulse width, and injected RF frequency. For the 191,500 training points, the average training error was 12.47%, while for the 191,500 test points the average test error was 14.85%, meaning that on average, the machine was able to predict MCU upset with an 85.15% accuracy. Leaving out the results for the worst-performing model (SVM with a linear kernel), the test prediction accuracy for the remaining machines is almost 89%. All three machine learning methods (ANNs, SVMs, and GPML) showed excellent and consistent results in their ability to model and predict the PoE on an MCU due to IEMI. The GP approach performed best during training with a 7.43% average training error, while the ANN technique was most accurate during the test with a 10.80% error.

Machine Learning Based Malware Detection

DTIC Science & Technology

2015-05-18

A TRIDENT SCHOLAR PROJECT REPORT NO. 440 Machine Learning Based Malware Detection by Midshipman 1/C Zane A. Markel, USN...COVERED (From - To) 4. TITLE AND SUBTITLE Machine Learning Based Malware Detection 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM...suitably be projected into realistic performance. This work explores several aspects of machine learning based malware detection . First, we

A multiple-feature and multiple-kernel scene segmentation algorithm for humanoid robot.

PubMed

Liu, Zhi; Xu, Shuqiong; Zhang, Yun; Chen, Chun Lung Philip

2014-11-01

This technical correspondence presents a multiple-feature and multiple-kernel support vector machine (MFMK-SVM) methodology to achieve a more reliable and robust segmentation performance for humanoid robot. The pixel wise intensity, gradient, and C1 SMF features are extracted via the local homogeneity model and Gabor filter, which would be used as inputs of MFMK-SVM model. It may provide multiple features of the samples for easier implementation and efficient computation of MFMK-SVM model. A new clustering method, which is called feature validity-interval type-2 fuzzy C-means (FV-IT2FCM) clustering algorithm, is proposed by integrating a type-2 fuzzy criterion in the clustering optimization process to improve the robustness and reliability of clustering results by the iterative optimization. Furthermore, the clustering validity is employed to select the training samples for the learning of the MFMK-SVM model. The MFMK-SVM scene segmentation method is able to fully take advantage of the multiple features of scene image and the ability of multiple kernels. Experiments on the BSDS dataset and real natural scene images demonstrate the superior performance of our proposed method.

A comparative study of linear and nonlinear anomaly detectors for hyperspectral imagery

NASA Astrophysics Data System (ADS)

Goldberg, Hirsh; Nasrabadi, Nasser M.

2007-04-01

In this paper we implement various linear and nonlinear subspace-based anomaly detectors for hyperspectral imagery. First, a dual window technique is used to separate the local area around each pixel into two regions - an inner-window region (IWR) and an outer-window region (OWR). Pixel spectra from each region are projected onto a subspace which is defined by projection bases that can be generated in several ways. Here we use three common pattern classification techniques (Principal Component Analysis (PCA), Fisher Linear Discriminant (FLD) Analysis, and the Eigenspace Separation Transform (EST)) to generate projection vectors. In addition to these three algorithms, the well-known Reed-Xiaoli (RX) anomaly detector is also implemented. Each of the four linear methods is then implicitly defined in a high- (possibly infinite-) dimensional feature space by using a nonlinear mapping associated with a kernel function. Using a common machine-learning technique known as the kernel trick all dot products in the feature space are replaced with a Mercer kernel function defined in terms of the original input data space. To determine how anomalous a given pixel is, we then project the current test pixel spectra and the spectral mean vector of the OWR onto the linear and nonlinear projection vectors in order to exploit the statistical differences between the IWR and OWR pixels. Anomalies are detected if the separation of the projection of the current test pixel spectra and the OWR mean spectra are greater than a certain threshold. Comparisons are made using receiver operating characteristics (ROC) curves.

Application of kernel principal component analysis and computational machine learning to exploration of metabolites strongly associated with diet.

PubMed

Shiokawa, Yuka; Date, Yasuhiro; Kikuchi, Jun

2018-02-21

Computer-based technological innovation provides advancements in sophisticated and diverse analytical instruments, enabling massive amounts of data collection with relative ease. This is accompanied by a fast-growing demand for technological progress in data mining methods for analysis of big data derived from chemical and biological systems. From this perspective, use of a general "linear" multivariate analysis alone limits interpretations due to "non-linear" variations in metabolic data from living organisms. Here we describe a kernel principal component analysis (KPCA)-incorporated analytical approach for extracting useful information from metabolic profiling data. To overcome the limitation of important variable (metabolite) determinations, we incorporated a random forest conditional variable importance measure into our KPCA-based analytical approach to demonstrate the relative importance of metabolites. Using a market basket analysis, hippurate, the most important variable detected in the importance measure, was associated with high levels of some vitamins and minerals present in foods eaten the previous day, suggesting a relationship between increased hippurate and intake of a wide variety of vegetables and fruits. Therefore, the KPCA-incorporated analytical approach described herein enabled us to capture input-output responses, and should be useful not only for metabolic profiling but also for profiling in other areas of biological and environmental systems.

Kernel machine SNP set analysis provides new insight into the association between obesity and polymorphisms located on the chromosomal 16q.12.2 region: Tehran Lipid and Glucose Study.

PubMed

Javanrouh, Niloufar; Daneshpour, Maryam S; Soltanian, Ali Reza; Tapak, Leili

2018-06-05

Obesity is a serious health problem that leads to low quality of life and early mortality. To the purpose of prevention and gene therapy for such a worldwide disease, genome wide association study is a powerful tool for finding SNPs associated with increased risk of obesity. To conduct an association analysis, kernel machine regression is a generalized regression method, has an advantage of considering the epistasis effects as well as the correlation between individuals due to unknown factors. In this study, information of the people who participated in Tehran cardio-metabolic genetic study was used. They were genotyped for the chromosomal region, evaluation 986 variations located at 16q12.2; build 38hg. Kernel machine regression and single SNP analysis were used to assess the association between obesity and SNPs genotyped data. We found that associated SNP sets with obesity, were almost in the FTO (P = 0.01), AIKTIP (P = 0.02) and MMP2 (P = 0.02) genes. Moreover, two SNPs, i.e., rs10521296 and rs11647470, showed significant association with obesity using kernel regression (P = 0.02). In conclusion, significant sets were randomly distributed throughout the region with more density around the FTO, AIKTIP and MMP2 genes. Furthermore, two intergenic SNPs showed significant association after using kernel machine regression. Therefore, more studies have to be conducted to assess their functionality or precise mechanism. Copyright © 2018 Elsevier B.V. All rights reserved.

Machine learning classifier using abnormal brain network topological metrics in major depressive disorder.

PubMed

Guo, Hao; Cao, Xiaohua; Liu, Zhifen; Li, Haifang; Chen, Junjie; Zhang, Kerang

2012-12-05

Resting state functional brain networks have been widely studied in brain disease research. However, it is currently unclear whether abnormal resting state functional brain network metrics can be used with machine learning for the classification of brain diseases. Resting state functional brain networks were constructed for 28 healthy controls and 38 major depressive disorder patients by thresholding partial correlation matrices of 90 regions. Three nodal metrics were calculated using graph theory-based approaches. Nonparametric permutation tests were then used for group comparisons of topological metrics, which were used as classified features in six different algorithms. We used statistical significance as the threshold for selecting features and measured the accuracies of six classifiers with different number of features. A sensitivity analysis method was used to evaluate the importance of different features. The result indicated that some of the regions exhibited significantly abnormal nodal centralities, including the limbic system, basal ganglia, medial temporal, and prefrontal regions. Support vector machine with radial basis kernel function algorithm and neural network algorithm exhibited the highest average accuracy (79.27 and 78.22%, respectively) with 28 features (P<0.05). Correlation analysis between feature importance and the statistical significance of metrics was investigated, and the results revealed a strong positive correlation between them. Overall, the current study demonstrated that major depressive disorder is associated with abnormal functional brain network topological metrics and statistically significant nodal metrics can be successfully used for feature selection in classification algorithms.

Implementation and performance of parallel Prolog interpreter

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wei, S.; Kale, L.V.; Balkrishna, R.

1988-01-01

In this paper, the authors discuss the implementation of a parallel Prolog interpreter on different parallel machines. The implementation is based on the REDUCE--OR process model which exploits both AND and OR parallelism in logic programs. It is machine independent as it runs on top of the chare-kernel--a machine-independent parallel programming system. The authors also give the performance of the interpreter running a diverse set of benchmark pargrams on parallel machines including shared memory systems: an Alliant FX/8, Sequent and a MultiMax, and a non-shared memory systems: Intel iPSC/32 hypercube, in addition to its performance on a multiprocessor simulation system.

Multi-class Mode of Action Classification of Toxic Compounds Using Logic Based Kernel Methods.

PubMed

Lodhi, Huma; Muggleton, Stephen; Sternberg, Mike J E

2010-09-17

Toxicity prediction is essential for drug design and development of effective therapeutics. In this paper we present an in silico strategy, to identify the mode of action of toxic compounds, that is based on the use of a novel logic based kernel method. The technique uses support vector machines in conjunction with the kernels constructed from first order rules induced by an Inductive Logic Programming system. It constructs multi-class models by using a divide and conquer reduction strategy that splits multi-classes into binary groups and solves each individual problem recursively hence generating an underlying decision list structure. In order to evaluate the effectiveness of the approach for chemoinformatics problems like predictive toxicology, we apply it to toxicity classification in aquatic systems. The method is used to identify and classify 442 compounds with respect to the mode of action. The experimental results show that the technique successfully classifies toxic compounds and can be useful in assessing environmental risks. Experimental comparison of the performance of the proposed multi-class scheme with the standard multi-class Inductive Logic Programming algorithm and multi-class Support Vector Machine yields statistically significant results and demonstrates the potential power and benefits of the approach in identifying compounds of various toxic mechanisms. Copyright © 2010 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Building machine learning force fields for nanoclusters

NASA Astrophysics Data System (ADS)

Zeni, Claudio; Rossi, Kevin; Glielmo, Aldo; Fekete, Ádám; Gaston, Nicola; Baletto, Francesca; De Vita, Alessandro

2018-06-01

We assess Gaussian process (GP) regression as a technique to model interatomic forces in metal nanoclusters by analyzing the performance of 2-body, 3-body, and many-body kernel functions on a set of 19-atom Ni cluster structures. We find that 2-body GP kernels fail to provide faithful force estimates, despite succeeding in bulk Ni systems. However, both 3- and many-body kernels predict forces within an ˜0.1 eV/Å average error even for small training datasets and achieve high accuracy even on out-of-sample, high temperature structures. While training and testing on the same structure always provide satisfactory accuracy, cross-testing on dissimilar structures leads to higher prediction errors, posing an extrapolation problem. This can be cured using heterogeneous training on databases that contain more than one structure, which results in a good trade-off between versatility and overall accuracy. Starting from a 3-body kernel trained this way, we build an efficient non-parametric 3-body force field that allows accurate prediction of structural properties at finite temperatures, following a newly developed scheme [A. Glielmo et al., Phys. Rev. B 95, 214302 (2017)]. We use this to assess the thermal stability of Ni19 nanoclusters at a fractional cost of full ab initio calculations.

Within-brain classification for brain tumor segmentation.

PubMed

Havaei, Mohammad; Larochelle, Hugo; Poulin, Philippe; Jodoin, Pierre-Marc

2016-05-01

In this paper, we investigate a framework for interactive brain tumor segmentation which, at its core, treats the problem of interactive brain tumor segmentation as a machine learning problem. This method has an advantage over typical machine learning methods for this task where generalization is made across brains. The problem with these methods is that they need to deal with intensity bias correction and other MRI-specific noise. In this paper, we avoid these issues by approaching the problem as one of within brain generalization. Specifically, we propose a semi-automatic method that segments a brain tumor by training and generalizing within that brain only, based on some minimum user interaction. We investigate how adding spatial feature coordinates (i.e., i, j, k) to the intensity features can significantly improve the performance of different classification methods such as SVM, kNN and random forests. This would only be possible within an interactive framework. We also investigate the use of a more appropriate kernel and the adaptation of hyper-parameters specifically for each brain. As a result of these experiments, we obtain an interactive method whose results reported on the MICCAI-BRATS 2013 dataset are the second most accurate compared to published methods, while using significantly less memory and processing power than most state-of-the-art methods.

Projected Regression Methods for Inverting Fredholm Integrals: Formalism and Application to Analytical Continuation

NASA Astrophysics Data System (ADS)

Arsenault, Louis-Francois; Neuberg, Richard; Hannah, Lauren A.; Millis, Andrew J.

We present a machine learning-based statistical regression approach to the inversion of Fredholm integrals of the first kind by studying an important example for the quantum materials community, the analytical continuation problem of quantum many-body physics. It involves reconstructing the frequency dependence of physical excitation spectra from data obtained at specific points in the complex frequency plane. The approach provides a natural regularization in cases where the inverse of the Fredholm kernel is ill-conditioned and yields robust error metrics. The stability of the forward problem permits the construction of a large database of input-output pairs. Machine learning methods applied to this database generate approximate solutions which are projected onto the subspace of functions satisfying relevant constraints. We show that for low input noise the method performs as well or better than Maximum Entropy (MaxEnt) under standard error metrics, and is substantially more robust to noise. We expect the methodology to be similarly effective for any problem involving a formally ill-conditioned inversion, provided that the forward problem can be efficiently solved. AJM was supported by the Office of Science of the U.S. Department of Energy under Subcontract No. 3F-3138 and LFA by the Columbia Univeristy IDS-ROADS project, UR009033-05 which also provided part support to RN and LH.

Automated Tissue Classification Framework for Reproducible Chronic Wound Assessment

PubMed Central

Mukherjee, Rashmi; Manohar, Dhiraj Dhane; Das, Dev Kumar; Achar, Arun; Mitra, Analava; Chakraborty, Chandan

2014-01-01

The aim of this paper was to develop a computer assisted tissue classification (granulation, necrotic, and slough) scheme for chronic wound (CW) evaluation using medical image processing and statistical machine learning techniques. The red-green-blue (RGB) wound images grabbed by normal digital camera were first transformed into HSI (hue, saturation, and intensity) color space and subsequently the “S” component of HSI color channels was selected as it provided higher contrast. Wound areas from 6 different types of CW were segmented from whole images using fuzzy divergence based thresholding by minimizing edge ambiguity. A set of color and textural features describing granulation, necrotic, and slough tissues in the segmented wound area were extracted using various mathematical techniques. Finally, statistical learning algorithms, namely, Bayesian classification and support vector machine (SVM), were trained and tested for wound tissue classification in different CW images. The performance of the wound area segmentation protocol was further validated by ground truth images labeled by clinical experts. It was observed that SVM with 3rd order polynomial kernel provided the highest accuracies, that is, 86.94%, 90.47%, and 75.53%, for classifying granulation, slough, and necrotic tissues, respectively. The proposed automated tissue classification technique achieved the highest overall accuracy, that is, 87.61%, with highest kappa statistic value (0.793). PMID:25114925

Bioinformatics algorithm based on a parallel implementation of a machine learning approach using transducers

NASA Astrophysics Data System (ADS)

Roche-Lima, Abiel; Thulasiram, Ruppa K.

2012-02-01

Finite automata, in which each transition is augmented with an output label in addition to the familiar input label, are considered finite-state transducers. Transducers have been used to analyze some fundamental issues in bioinformatics. Weighted finite-state transducers have been proposed to pairwise alignments of DNA and protein sequences; as well as to develop kernels for computational biology. Machine learning algorithms for conditional transducers have been implemented and used for DNA sequence analysis. Transducer learning algorithms are based on conditional probability computation. It is calculated by using techniques, such as pair-database creation, normalization (with Maximum-Likelihood normalization) and parameters optimization (with Expectation-Maximization - EM). These techniques are intrinsically costly for computation, even worse when are applied to bioinformatics, because the databases sizes are large. In this work, we describe a parallel implementation of an algorithm to learn conditional transducers using these techniques. The algorithm is oriented to bioinformatics applications, such as alignments, phylogenetic trees, and other genome evolution studies. Indeed, several experiences were developed using the parallel and sequential algorithm on Westgrid (specifically, on the Breeze cluster). As results, we obtain that our parallel algorithm is scalable, because execution times are reduced considerably when the data size parameter is increased. Another experience is developed by changing precision parameter. In this case, we obtain smaller execution times using the parallel algorithm. Finally, number of threads used to execute the parallel algorithm on the Breezy cluster is changed. In this last experience, we obtain as result that speedup is considerably increased when more threads are used; however there is a convergence for number of threads equal to or greater than 16.

Modeling the milling tool wear by using an evolutionary SVM-based model from milling runs experimental data

NASA Astrophysics Data System (ADS)

Nieto, Paulino José García; García-Gonzalo, Esperanza; Vilán, José Antonio Vilán; Robleda, Abraham Segade

2015-12-01

The main aim of this research work is to build a new practical hybrid regression model to predict the milling tool wear in a regular cut as well as entry cut and exit cut of a milling tool. The model was based on Particle Swarm Optimization (PSO) in combination with support vector machines (SVMs). This optimization mechanism involved kernel parameter setting in the SVM training procedure, which significantly influences the regression accuracy. Bearing this in mind, a PSO-SVM-based model, which is based on the statistical learning theory, was successfully used here to predict the milling tool flank wear (output variable) as a function of the following input variables: the time duration of experiment, depth of cut, feed, type of material, etc. To accomplish the objective of this study, the experimental dataset represents experiments from runs on a milling machine under various operating conditions. In this way, data sampled by three different types of sensors (acoustic emission sensor, vibration sensor and current sensor) were acquired at several positions. A second aim is to determine the factors with the greatest bearing on the milling tool flank wear with a view to proposing milling machine's improvements. Firstly, this hybrid PSO-SVM-based regression model captures the main perception of statistical learning theory in order to obtain a good prediction of the dependence among the flank wear (output variable) and input variables (time, depth of cut, feed, etc.). Indeed, regression with optimal hyperparameters was performed and a determination coefficient of 0.95 was obtained. The agreement of this model with experimental data confirmed its good performance. Secondly, the main advantages of this PSO-SVM-based model are its capacity to produce a simple, easy-to-interpret model, its ability to estimate the contributions of the input variables, and its computational efficiency. Finally, the main conclusions of this study are exposed.

The engine maintenance scheduling by using reliability centered maintenance method and the identification of 5S application in PT. XYZ

NASA Astrophysics Data System (ADS)

Sembiring, N.; Panjaitan, N.; Saragih, A. F.

2018-02-01

PT. XYZ is a manufacturing company that produces fresh fruit bunches (FFB) to Crude Palm Oil (CPO) and Palm Kernel Oil (PKO). PT. XYZ consists of six work stations: receipt station, sterilizing station, thressing station, pressing station, clarification station, and kernelery station. So far, the company is still implementing corrective maintenance maintenance system for production machines where the machine repair is done after damage occurs. Problems at PT. XYZ is the absence of scheduling engine maintenance in a planned manner resulting in the engine often damaged which can disrupt the smooth production. Another factor that is the problem in this research is the kernel station environment that becomes less convenient for operators such as there are machines and equipment not used in the production area, slippery, muddy, scattered fibers, incomplete use of PPE, and lack of employee discipline. The most commonly damaged machine is in the seed processing station (kernel station) which is cake breaker conveyor machine. The solution of this problem is to propose a schedule plan for maintenance of the machine by using the method of reliability centered maintenance and also the application of 5S. The result of the application of Reliability Centered maintenance method is obtained four components that must be treated scheduled (time directed), namely: for bearing component is 37 days, gearbox component is 97 days, CBC pen component is 35 days and conveyor pedal component is 32 days While after identification the application of 5S obtained the proposed corporate environmental improvement measures in accordance with the principles of 5S where unused goods will be moved from the production area, grouping goods based on their use, determining the procedure of cleaning the production area, conducting inspection in the use of PPE, and making 5S slogans.

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm.

PubMed

Mao, Yong; Zhou, Xiao-Bo; Pi, Dao-Ying; Sun, You-Xian; Wong, Stephen T C

2005-10-01

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear statistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two representative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method performs well in selecting genes and achieves high classification accuracies with these genes.

Performance Measurement, Visualization and Modeling of Parallel and Distributed Programs

NASA Technical Reports Server (NTRS)

Yan, Jerry C.; Sarukkai, Sekhar R.; Mehra, Pankaj; Lum, Henry, Jr. (Technical Monitor)

1994-01-01

This paper presents a methodology for debugging the performance of message-passing programs on both tightly coupled and loosely coupled distributed-memory machines. The AIMS (Automated Instrumentation and Monitoring System) toolkit, a suite of software tools for measurement and analysis of performance, is introduced and its application illustrated using several benchmark programs drawn from the field of computational fluid dynamics. AIMS includes (i) Xinstrument, a powerful source-code instrumentor, which supports both Fortran77 and C as well as a number of different message-passing libraries including Intel's NX Thinking Machines' CMMD, and PVM; (ii) Monitor, a library of timestamping and trace -collection routines that run on supercomputers (such as Intel's iPSC/860, Delta, and Paragon and Thinking Machines' CM5) as well as on networks of workstations (including Convex Cluster and SparcStations connected by a LAN); (iii) Visualization Kernel, a trace-animation facility that supports source-code clickback, simultaneous visualization of computation and communication patterns, as well as analysis of data movements; (iv) Statistics Kernel, an advanced profiling facility, that associates a variety of performance data with various syntactic components of a parallel program; (v) Index Kernel, a diagnostic tool that helps pinpoint performance bottlenecks through the use of abstract indices; (vi) Modeling Kernel, a facility for automated modeling of message-passing programs that supports both simulation -based and analytical approaches to performance prediction and scalability analysis; (vii) Intrusion Compensator, a utility for recovering true performance from observed performance by removing the overheads of monitoring and their effects on the communication pattern of the program; and (viii) Compatibility Tools, that convert AIMS-generated traces into formats used by other performance-visualization tools, such as ParaGraph, Pablo, and certain AVS/Explorer modules.

Optimizing Irregular Applications for Energy and Performance on the Tilera Many-core Architecture

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chavarría-Miranda, Daniel; Panyala, Ajay R.; Halappanavar, Mahantesh

Optimizing applications simultaneously for energy and performance is a complex problem. High performance, parallel, irregular applications are notoriously hard to optimize due to their data-dependent memory accesses, lack of structured locality and complex data structures and code patterns. Irregular kernels are growing in importance in applications such as machine learning, graph analytics and combinatorial scientific computing. Performance- and energy-efficient implementation of these kernels on modern, energy efficient, multicore and many-core platforms is therefore an important and challenging problem. We present results from optimizing two irregular applications { the Louvain method for community detection (Grappolo), and high-performance conjugate gradient (HPCCG) {more » on the Tilera many-core system. We have significantly extended MIT's OpenTuner auto-tuning framework to conduct a detailed study of platform-independent and platform-specific optimizations to improve performance as well as reduce total energy consumption. We explore the optimization design space along three dimensions: memory layout schemes, compiler-based code transformations, and optimization of parallel loop schedules. Using auto-tuning, we demonstrate whole node energy savings of up to 41% relative to a baseline instantiation, and up to 31% relative to manually optimized variants.« less

A comparison of different chemometrics approaches for the robust classification of electronic nose data.

PubMed

Gromski, Piotr S; Correa, Elon; Vaughan, Andrew A; Wedge, David C; Turner, Michael L; Goodacre, Royston

2014-11-01

Accurate detection of certain chemical vapours is important, as these may be diagnostic for the presence of weapons, drugs of misuse or disease. In order to achieve this, chemical sensors could be deployed remotely. However, the readout from such sensors is a multivariate pattern, and this needs to be interpreted robustly using powerful supervised learning methods. Therefore, in this study, we compared the classification accuracy of four pattern recognition algorithms which include linear discriminant analysis (LDA), partial least squares-discriminant analysis (PLS-DA), random forests (RF) and support vector machines (SVM) which employed four different kernels. For this purpose, we have used electronic nose (e-nose) sensor data (Wedge et al., Sensors Actuators B Chem 143:365-372, 2009). In order to allow direct comparison between our four different algorithms, we employed two model validation procedures based on either 10-fold cross-validation or bootstrapping. The results show that LDA (91.56% accuracy) and SVM with a polynomial kernel (91.66% accuracy) were very effective at analysing these e-nose data. These two models gave superior prediction accuracy, sensitivity and specificity in comparison to the other techniques employed. With respect to the e-nose sensor data studied here, our findings recommend that SVM with a polynomial kernel should be favoured as a classification method over the other statistical models that we assessed. SVM with non-linear kernels have the advantage that they can be used for classifying non-linear as well as linear mapping from analytical data space to multi-group classifications and would thus be a suitable algorithm for the analysis of most e-nose sensor data.

Critical Assessment of Small Molecule Identification 2016: automated methods.

PubMed

Schymanski, Emma L; Ruttkies, Christoph; Krauss, Martin; Brouard, Céline; Kind, Tobias; Dührkop, Kai; Allen, Felicity; Vaniya, Arpana; Verdegem, Dries; Böcker, Sebastian; Rousu, Juho; Shen, Huibin; Tsugawa, Hiroshi; Sajed, Tanvir; Fiehn, Oliver; Ghesquière, Bart; Neumann, Steffen

2017-03-27

The fourth round of the Critical Assessment of Small Molecule Identification (CASMI) Contest ( www.casmi-contest.org ) was held in 2016, with two new categories for automated methods. This article covers the 208 challenges in Categories 2 and 3, without and with metadata, from organization, participation, results and post-contest evaluation of CASMI 2016 through to perspectives for future contests and small molecule annotation/identification. The Input Output Kernel Regression (CSI:IOKR) machine learning approach performed best in "Category 2: Best Automatic Structural Identification-In Silico Fragmentation Only", won by Team Brouard with 41% challenge wins. The winner of "Category 3: Best Automatic Structural Identification-Full Information" was Team Kind (MS-FINDER), with 76% challenge wins. The best methods were able to achieve over 30% Top 1 ranks in Category 2, with all methods ranking the correct candidate in the Top 10 in around 50% of challenges. This success rate rose to 70% Top 1 ranks in Category 3, with candidates in the Top 10 in over 80% of the challenges. The machine learning and chemistry-based approaches are shown to perform in complementary ways. The improvement in (semi-)automated fragmentation methods for small molecule identification has been substantial. The achieved high rates of correct candidates in the Top 1 and Top 10, despite large candidate numbers, open up great possibilities for high-throughput annotation of untargeted analysis for "known unknowns". As more high quality training data becomes available, the improvements in machine learning methods will likely continue, but the alternative approaches still provide valuable complementary information. Improved integration of experimental context will also improve identification success further for "real life" annotations. The true "unknown unknowns" remain to be evaluated in future CASMI contests. Graphical abstract .

Kernel Principal Component Analysis for dimensionality reduction in fMRI-based diagnosis of ADHD.

PubMed

Sidhu, Gagan S; Asgarian, Nasimeh; Greiner, Russell; Brown, Matthew R G

2012-01-01

This study explored various feature extraction methods for use in automated diagnosis of Attention-Deficit Hyperactivity Disorder (ADHD) from functional Magnetic Resonance Image (fMRI) data. Each participant's data consisted of a resting state fMRI scan as well as phenotypic data (age, gender, handedness, IQ, and site of scanning) from the ADHD-200 dataset. We used machine learning techniques to produce support vector machine (SVM) classifiers that attempted to differentiate between (1) all ADHD patients vs. healthy controls and (2) ADHD combined (ADHD-c) type vs. ADHD inattentive (ADHD-i) type vs. controls. In different tests, we used only the phenotypic data, only the imaging data, or else both the phenotypic and imaging data. For feature extraction on fMRI data, we tested the Fast Fourier Transform (FFT), different variants of Principal Component Analysis (PCA), and combinations of FFT and PCA. PCA variants included PCA over time (PCA-t), PCA over space and time (PCA-st), and kernelized PCA (kPCA-st). Baseline chance accuracy was 64.2% produced by guessing healthy control (the majority class) for all participants. Using only phenotypic data produced 72.9% accuracy on two class diagnosis and 66.8% on three class diagnosis. Diagnosis using only imaging data did not perform as well as phenotypic-only approaches. Using both phenotypic and imaging data with combined FFT and kPCA-st feature extraction yielded accuracies of 76.0% on two class diagnosis and 68.6% on three class diagnosis-better than phenotypic-only approaches. Our results demonstrate the potential of using FFT and kPCA-st with resting-state fMRI data as well as phenotypic data for automated diagnosis of ADHD. These results are encouraging given known challenges of learning ADHD diagnostic classifiers using the ADHD-200 dataset (see Brown et al., 2012).

Scoliosis curve type classification using kernel machine from 3D trunk image

NASA Astrophysics Data System (ADS)

Adankon, Mathias M.; Dansereau, Jean; Parent, Stefan; Labelle, Hubert; Cheriet, Farida

2012-03-01

Adolescent idiopathic scoliosis (AIS) is a deformity of the spine manifested by asymmetry and deformities of the external surface of the trunk. Classification of scoliosis deformities according to curve type is used to plan management of scoliosis patients. Currently, scoliosis curve type is determined based on X-ray exam. However, cumulative exposure to X-rays radiation significantly increases the risk for certain cancer. In this paper, we propose a robust system that can classify the scoliosis curve type from non invasive acquisition of 3D trunk surface of the patients. The 3D image of the trunk is divided into patches and local geometric descriptors characterizing the surface of the back are computed from each patch and forming the features. We perform the reduction of the dimensionality by using Principal Component Analysis and 53 components were retained. In this work a multi-class classifier is built with Least-squares support vector machine (LS-SVM) which is a kernel classifier. For this study, a new kernel was designed in order to achieve a robust classifier in comparison with polynomial and Gaussian kernel. The proposed system was validated using data of 103 patients with different scoliosis curve types diagnosed and classified by an orthopedic surgeon from the X-ray images. The average rate of successful classification was 93.3% with a better rate of prediction for the major thoracic and lumbar/thoracolumbar types.

Operator based integration of information in multimodal radiological search mission with applications to anomaly detection

NASA Astrophysics Data System (ADS)

Benedetto, J.; Cloninger, A.; Czaja, W.; Doster, T.; Kochersberger, K.; Manning, B.; McCullough, T.; McLane, M.

2014-05-01

Successful performance of radiological search mission is dependent on effective utilization of mixture of signals. Examples of modalities include, e.g., EO imagery and gamma radiation data, or radiation data collected during multiple events. In addition, elevation data or spatial proximity can be used to enhance the performance of acquisition systems. State of the art techniques in processing and exploitation of complex information manifolds rely on diffusion operators. Our approach involves machine learning techniques based on analysis of joint data- dependent graphs and their associated diffusion kernels. Then, the significant eigenvectors of the derived fused graph Laplace and Schroedinger operators form the new representation, which provides integrated features from the heterogeneous input data. The families of data-dependent Laplace and Schroedinger operators on joint data graphs, shall be integrated by means of appropriately designed fusion metrics. These fused representations are used for target and anomaly detection.

Optimization of the kernel functions in a probabilistic neural network analyzing the local pattern distribution.

PubMed

Galleske, I; Castellanos, J

2002-05-01

This article proposes a procedure for the automatic determination of the elements of the covariance matrix of the gaussian kernel function of probabilistic neural networks. Two matrices, a rotation matrix and a matrix of variances, can be calculated by analyzing the local environment of each training pattern. The combination of them will form the covariance matrix of each training pattern. This automation has two advantages: First, it will free the neural network designer from indicating the complete covariance matrix, and second, it will result in a network with better generalization ability than the original model. A variation of the famous two-spiral problem and real-world examples from the UCI Machine Learning Repository will show a classification rate not only better than the original probabilistic neural network but also that this model can outperform other well-known classification techniques.

Efficient HIK SVM learning for image classification.

PubMed

Wu, Jianxin

2012-10-01

Histograms are used in almost every aspect of image processing and computer vision, from visual descriptors to image representations. Histogram intersection kernel (HIK) and support vector machine (SVM) classifiers are shown to be very effective in dealing with histograms. This paper presents contributions concerning HIK SVM for image classification. First, we propose intersection coordinate descent (ICD), a deterministic and scalable HIK SVM solver. ICD is much faster than, and has similar accuracies to, general purpose SVM solvers and other fast HIK SVM training methods. We also extend ICD to the efficient training of a broader family of kernels. Second, we show an important empirical observation that ICD is not sensitive to the C parameter in SVM, and we provide some theoretical analyses to explain this observation. ICD achieves high accuracies in many problems, using its default parameters. This is an attractive property for practitioners, because many image processing tasks are too large to choose SVM parameters using cross-validation.

Collaborative filtering on a family of biological targets.

PubMed

Erhan, Dumitru; L'heureux, Pierre-Jean; Yue, Shi Yi; Bengio, Yoshua

2006-01-01

Building a QSAR model of a new biological target for which few screening data are available is a statistical challenge. However, the new target may be part of a bigger family, for which we have more screening data. Collaborative filtering or, more generally, multi-task learning, is a machine learning approach that improves the generalization performance of an algorithm by using information from related tasks as an inductive bias. We use collaborative filtering techniques for building predictive models that link multiple targets to multiple examples. The more commonalities between the targets, the better the multi-target model that can be built. We show an example of a multi-target neural network that can use family information to produce a predictive model of an undersampled target. We evaluate JRank, a kernel-based method designed for collaborative filtering. We show their performance on compound prioritization for an HTS campaign and the underlying shared representation between targets. JRank outperformed the neural network both in the single- and multi-target models.

Total Ambient Dose Equivalent Buildup Factor Determination for Nbs04 Concrete.

PubMed

Duckic, Paulina; Hayes, Robert B

2018-06-01

Buildup factors are dimensionless multiplicative factors required by the point kernel method to account for scattered radiation through a shielding material. The accuracy of the point kernel method is strongly affected by the correspondence of analyzed parameters to experimental configurations, which is attempted to be simplified here. The point kernel method has not been found to have widespread practical use for neutron shielding calculations due to the complex neutron transport behavior through shielding materials (i.e. the variety of interaction mechanisms that neutrons may undergo while traversing the shield) as well as non-linear neutron total cross section energy dependence. In this work, total ambient dose buildup factors for NBS04 concrete are calculated in terms of neutron and secondary gamma ray transmission factors. The neutron and secondary gamma ray transmission factors are calculated using MCNP6™ code with updated cross sections. Both transmission factors and buildup factors are given in a tabulated form. Practical use of neutron transmission and buildup factors warrants rigorously calculated results with all associated uncertainties. In this work, sensitivity analysis of neutron transmission factors and total buildup factors with varying water content has been conducted. The analysis showed significant impact of varying water content in concrete on both neutron transmission factors and total buildup factors. Finally, support vector regression, a machine learning technique, has been engaged to make a model based on the calculated data for calculation of the buildup factors. The developed model can predict most of the data with 20% relative error.

Osteoarthritis Severity Determination using Self Organizing Map Based Gabor Kernel

NASA Astrophysics Data System (ADS)

Anifah, L.; Purnomo, M. H.; Mengko, T. L. R.; Purnama, I. K. E.

2018-02-01

The number of osteoarthritis patients in Indonesia is enormous, so early action is needed in order for this disease to be handled. The aim of this paper to determine osteoarthritis severity based on x-ray image template based on gabor kernel. This research is divided into 3 stages, the first step is image processing that is using gabor kernel. The second stage is the learning stage, and the third stage is the testing phase. The image processing stage is by normalizing the image dimension to be template to 50 □ 200 image. Learning stage is done with parameters initial learning rate of 0.5 and the total number of iterations of 1000. The testing stage is performed using the weights generated at the learning stage. The testing phase has been done and the results were obtained. The result shows KL-Grade 0 has an accuracy of 36.21%, accuracy for KL-Grade 2 is 40,52%, while accuracy for KL-Grade 2 and KL-Grade 3 are 15,52%, and 25,86%. The implication of this research is expected that this research as decision support system for medical practitioners in determining KL-Grade on X-ray images of knee osteoarthritis.

Parallel mutual information estimation for inferring gene regulatory networks on GPUs

PubMed Central

2011-01-01

Background Mutual information is a measure of similarity between two variables. It has been widely used in various application domains including computational biology, machine learning, statistics, image processing, and financial computing. Previously used simple histogram based mutual information estimators lack the precision in quality compared to kernel based methods. The recently introduced B-spline function based mutual information estimation method is competitive to the kernel based methods in terms of quality but at a lower computational complexity. Results We present a new approach to accelerate the B-spline function based mutual information estimation algorithm with commodity graphics hardware. To derive an efficient mapping onto this type of architecture, we have used the Compute Unified Device Architecture (CUDA) programming model to design and implement a new parallel algorithm. Our implementation, called CUDA-MI, can achieve speedups of up to 82 using double precision on a single GPU compared to a multi-threaded implementation on a quad-core CPU for large microarray datasets. We have used the results obtained by CUDA-MI to infer gene regulatory networks (GRNs) from microarray data. The comparisons to existing methods including ARACNE and TINGe show that CUDA-MI produces GRNs of higher quality in less time. Conclusions CUDA-MI is publicly available open-source software, written in CUDA and C++ programming languages. It obtains significant speedup over sequential multi-threaded implementation by fully exploiting the compute capability of commonly used CUDA-enabled low-cost GPUs. PMID:21672264

Develop, Build, and Test a Virtual Lab to Support a Vulnerability Training System

DTIC Science & Technology

2004-09-01

docs.us.dell.com/support/edocs/systems/pe1650/ en /it/index.htm> (20 August 2004) “HOWTO: Installing Web Services with Linux /Tomcat/Apache/Struts...configured as host machines with VMware and VNC running on a Linux RedHat 9 Kernel. An Apache-Tomcat web server was configured as the external interface to...1650, dual processor, blade servers were configured as host machines with VMware and VNC running on a Linux RedHat 9 Kernel. An Apache-Tomcat web

In silico prediction of Tetrahymena pyriformis toxicity for diverse industrial chemicals with substructure pattern recognition and machine learning methods.

PubMed

Cheng, Feixiong; Shen, Jie; Yu, Yue; Li, Weihua; Liu, Guixia; Lee, Philip W; Tang, Yun

2011-03-01

There is an increasing need for the rapid safety assessment of chemicals by both industries and regulatory agencies throughout the world. In silico techniques are practical alternatives in the environmental hazard assessment. It is especially true to address the persistence, bioaccumulative and toxicity potentials of organic chemicals. Tetrahymena pyriformis toxicity is often used as a toxic endpoint. In this study, 1571 diverse unique chemicals were collected from the literature and composed of the largest diverse data set for T. pyriformis toxicity. Classification predictive models of T. pyriformis toxicity were developed by substructure pattern recognition and different machine learning methods, including support vector machine (SVM), C4.5 decision tree, k-nearest neighbors and random forest. The results of a 5-fold cross-validation showed that the SVM method performed better than other algorithms. The overall predictive accuracies of the SVM classification model with radial basis functions kernel was 92.2% for the 5-fold cross-validation and 92.6% for the external validation set, respectively. Furthermore, several representative substructure patterns for characterizing T. pyriformis toxicity were also identified via the information gain analysis methods. Copyright © 2010 Elsevier Ltd. All rights reserved.

Automated detection of heart ailments from 12-lead ECG using complex wavelet sub-band bi-spectrum features.

PubMed

Tripathy, Rajesh Kumar; Dandapat, Samarendra

2017-04-01

The complex wavelet sub-band bi-spectrum (CWSB) features are proposed for detection and classification of myocardial infarction (MI), heart muscle disease (HMD) and bundle branch block (BBB) from 12-lead ECG. The dual tree CW transform of 12-lead ECG produces CW coefficients at different sub-bands. The higher-order CW analysis is used for evaluation of CWSB. The mean of the absolute value of CWSB, and the number of negative phase angle and the number of positive phase angle features from the phase of CWSB of 12-lead ECG are evaluated. Extreme learning machine and support vector machine (SVM) classifiers are used to evaluate the performance of CWSB features. Experimental results show that the proposed CWSB features of 12-lead ECG and the SVM classifier are successful for classification of various heart pathologies. The individual accuracy values for MI, HMD and BBB classes are obtained as 98.37, 97.39 and 96.40%, respectively, using SVM classifier and radial basis function kernel function. A comparison has also been made with existing 12-lead ECG-based cardiac disease detection techniques.

Developing a radiomics framework for classifying non-small cell lung carcinoma subtypes

NASA Astrophysics Data System (ADS)

Yu, Dongdong; Zang, Yali; Dong, Di; Zhou, Mu; Gevaert, Olivier; Fang, Mengjie; Shi, Jingyun; Tian, Jie

2017-03-01

Patient-targeted treatment of non-small cell lung carcinoma (NSCLC) has been well documented according to the histologic subtypes over the past decade. In parallel, recent development of quantitative image biomarkers has recently been highlighted as important diagnostic tools to facilitate histological subtype classification. In this study, we present a radiomics analysis that classifies the adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). We extract 52-dimensional, CT-based features (7 statistical features and 45 image texture features) to represent each nodule. We evaluate our approach on a clinical dataset including 324 ADCs and 110 SqCCs patients with CT image scans. Classification of these features is performed with four different machine-learning classifiers including Support Vector Machines with Radial Basis Function kernel (RBF-SVM), Random forest (RF), K-nearest neighbor (KNN), and RUSBoost algorithms. To improve the classifiers' performance, optimal feature subset is selected from the original feature set by using an iterative forward inclusion and backward eliminating algorithm. Extensive experimental results demonstrate that radiomics features achieve encouraging classification results on both complete feature set (AUC=0.89) and optimal feature subset (AUC=0.91).

MO-F-CAMPUS-J-02: Automatic Recognition of Patient Treatment Site in Portal Images Using Machine Learning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chang, X; Yang, D

Purpose: To investigate the method to automatically recognize the treatment site in the X-Ray portal images. It could be useful to detect potential treatment errors, and to provide guidance to sequential tasks, e.g. automatically verify the patient daily setup. Methods: The portal images were exported from MOSAIQ as DICOM files, and were 1) processed with a threshold based intensity transformation algorithm to enhance contrast, and 2) where then down-sampled (from 1024×768 to 128×96) by using bi-cubic interpolation algorithm. An appearance-based vector space model (VSM) was used to rearrange the images into vectors. A principal component analysis (PCA) method was usedmore » to reduce the vector dimensions. A multi-class support vector machine (SVM), with radial basis function kernel, was used to build the treatment site recognition models. These models were then used to recognize the treatment sites in the portal image. Portal images of 120 patients were included in the study. The images were selected to cover six treatment sites: brain, head and neck, breast, lung, abdomen and pelvis. Each site had images of the twenty patients. Cross-validation experiments were performed to evaluate the performance. Results: MATLAB image processing Toolbox and scikit-learn (a machine learning library in python) were used to implement the proposed method. The average accuracies using the AP and RT images separately were 95% and 94% respectively. The average accuracy using AP and RT images together was 98%. Computation time was ∼0.16 seconds per patient with AP or RT image, ∼0.33 seconds per patient with both of AP and RT images. Conclusion: The proposed method of treatment site recognition is efficient and accurate. It is not sensitive to the differences of image intensity, size and positions of patients in the portal images. It could be useful for the patient safety assurance. The work was partially supported by a research grant from Varian Medical System.« less

Privacy preserving RBF kernel support vector machine.

PubMed

Li, Haoran; Xiong, Li; Ohno-Machado, Lucila; Jiang, Xiaoqian

2014-01-01

Data sharing is challenging but important for healthcare research. Methods for privacy-preserving data dissemination based on the rigorous differential privacy standard have been developed but they did not consider the characteristics of biomedical data and make full use of the available information. This often results in too much noise in the final outputs. We hypothesized that this situation can be alleviated by leveraging a small portion of open-consented data to improve utility without sacrificing privacy. We developed a hybrid privacy-preserving differentially private support vector machine (SVM) model that uses public data and private data together. Our model leverages the RBF kernel and can handle nonlinearly separable cases. Experiments showed that this approach outperforms two baselines: (1) SVMs that only use public data, and (2) differentially private SVMs that are built from private data. Our method demonstrated very close performance metrics compared to nonprivate SVMs trained on the private data.

Privacy Preserving RBF Kernel Support Vector Machine

PubMed Central

Xiong, Li; Ohno-Machado, Lucila

2014-01-01

Data sharing is challenging but important for healthcare research. Methods for privacy-preserving data dissemination based on the rigorous differential privacy standard have been developed but they did not consider the characteristics of biomedical data and make full use of the available information. This often results in too much noise in the final outputs. We hypothesized that this situation can be alleviated by leveraging a small portion of open-consented data to improve utility without sacrificing privacy. We developed a hybrid privacy-preserving differentially private support vector machine (SVM) model that uses public data and private data together. Our model leverages the RBF kernel and can handle nonlinearly separable cases. Experiments showed that this approach outperforms two baselines: (1) SVMs that only use public data, and (2) differentially private SVMs that are built from private data. Our method demonstrated very close performance metrics compared to nonprivate SVMs trained on the private data. PMID:25013805

New KF-PP-SVM classification method for EEG in brain-computer interfaces.

PubMed

Yang, Banghua; Han, Zhijun; Zan, Peng; Wang, Qian

2014-01-01

Classification methods are a crucial direction in the current study of brain-computer interfaces (BCIs). To improve the classification accuracy for electroencephalogram (EEG) signals, a novel KF-PP-SVM (kernel fisher, posterior probability, and support vector machine) classification method is developed. Its detailed process entails the use of common spatial patterns to obtain features, based on which the within-class scatter is calculated. Then the scatter is added into the kernel function of a radial basis function to construct a new kernel function. This new kernel is integrated into the SVM to obtain a new classification model. Finally, the output of SVM is calculated based on posterior probability and the final recognition result is obtained. To evaluate the effectiveness of the proposed KF-PP-SVM method, EEG data collected from laboratory are processed with four different classification schemes (KF-PP-SVM, KF-SVM, PP-SVM, and SVM). The results showed that the overall average improvements arising from the use of the KF-PP-SVM scheme as opposed to KF-SVM, PP-SVM and SVM schemes are 2.49%, 5.83 % and 6.49 % respectively.

Parameter diagnostics of phases and phase transition learning by neural networks

NASA Astrophysics Data System (ADS)

Suchsland, Philippe; Wessel, Stefan

2018-05-01

We present an analysis of neural network-based machine learning schemes for phases and phase transitions in theoretical condensed matter research, focusing on neural networks with a single hidden layer. Such shallow neural networks were previously found to be efficient in classifying phases and locating phase transitions of various basic model systems. In order to rationalize the emergence of the classification process and for identifying any underlying physical quantities, it is feasible to examine the weight matrices and the convolutional filter kernels that result from the learning process of such shallow networks. Furthermore, we demonstrate how the learning-by-confusing scheme can be used, in combination with a simple threshold-value classification method, to diagnose the learning parameters of neural networks. In particular, we study the classification process of both fully-connected and convolutional neural networks for the two-dimensional Ising model with extended domain wall configurations included in the low-temperature regime. Moreover, we consider the two-dimensional XY model and contrast the performance of the learning-by-confusing scheme and convolutional neural networks trained on bare spin configurations to the case of preprocessed samples with respect to vortex configurations. We discuss these findings in relation to similar recent investigations and possible further applications.

Multiple kernel learning using single stage function approximation for binary classification problems

NASA Astrophysics Data System (ADS)

Shiju, S.; Sumitra, S.

2017-12-01

In this paper, the multiple kernel learning (MKL) is formulated as a supervised classification problem. We dealt with binary classification data and hence the data modelling problem involves the computation of two decision boundaries of which one related with that of kernel learning and the other with that of input data. In our approach, they are found with the aid of a single cost function by constructing a global reproducing kernel Hilbert space (RKHS) as the direct sum of the RKHSs corresponding to the decision boundaries of kernel learning and input data and searching that function from the global RKHS, which can be represented as the direct sum of the decision boundaries under consideration. In our experimental analysis, the proposed model had shown superior performance in comparison with that of existing two stage function approximation formulation of MKL, where the decision functions of kernel learning and input data are found separately using two different cost functions. This is due to the fact that single stage representation helps the knowledge transfer between the computation procedures for finding the decision boundaries of kernel learning and input data, which inturn boosts the generalisation capacity of the model.

Multiple kernel learning in protein-protein interaction extraction from biomedical literature.

PubMed

Yang, Zhihao; Tang, Nan; Zhang, Xiao; Lin, Hongfei; Li, Yanpeng; Yang, Zhiwei

2011-03-01

Knowledge about protein-protein interactions (PPIs) unveils the molecular mechanisms of biological processes. The volume and content of published biomedical literature on protein interactions is expanding rapidly, making it increasingly difficult for interaction database administrators, responsible for content input and maintenance to detect and manually update protein interaction information. The objective of this work is to develop an effective approach to automatic extraction of PPI information from biomedical literature. We present a weighted multiple kernel learning-based approach for automatic PPI extraction from biomedical literature. The approach combines the following kernels: feature-based, tree, graph and part-of-speech (POS) path. In particular, we extend the shortest path-enclosed tree (SPT) and dependency path tree to capture richer contextual information. Our experimental results show that the combination of SPT and dependency path tree extensions contributes to the improvement of performance by almost 0.7 percentage units in F-score and 2 percentage units in area under the receiver operating characteristics curve (AUC). Combining two or more appropriately weighed individual will further improve the performance. Both on the individual corpus and cross-corpus evaluation our combined kernel can achieve state-of-the-art performance with respect to comparable evaluations, with 64.41% F-score and 88.46% AUC on the AImed corpus. As different kernels calculate the similarity between two sentences from different aspects. Our combined kernel can reduce the risk of missing important features. More specifically, we use a weighted linear combination of individual kernels instead of assigning the same weight to each individual kernel, thus allowing the introduction of each kernel to incrementally contribute to the performance improvement. In addition, SPT and dependency path tree extensions can improve the performance by including richer context information. Copyright © 2010 Elsevier B.V. All rights reserved.

An SVM-based solution for fault detection in wind turbines.

PubMed

Santos, Pedro; Villa, Luisa F; Reñones, Aníbal; Bustillo, Andres; Maudes, Jesús

2015-03-09

Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets.

Multiple Kernel Learning with Random Effects for Predicting Longitudinal Outcomes and Data Integration

PubMed Central

Chen, Tianle; Zeng, Donglin

2015-01-01

Summary Predicting disease risk and progression is one of the main goals in many clinical research studies. Cohort studies on the natural history and etiology of chronic diseases span years and data are collected at multiple visits. Although kernel-based statistical learning methods are proven to be powerful for a wide range of disease prediction problems, these methods are only well studied for independent data but not for longitudinal data. It is thus important to develop time-sensitive prediction rules that make use of the longitudinal nature of the data. In this paper, we develop a novel statistical learning method for longitudinal data by introducing subject-specific short-term and long-term latent effects through a designed kernel to account for within-subject correlation of longitudinal measurements. Since the presence of multiple sources of data is increasingly common, we embed our method in a multiple kernel learning framework and propose a regularized multiple kernel statistical learning with random effects to construct effective nonparametric prediction rules. Our method allows easy integration of various heterogeneous data sources and takes advantage of correlation among longitudinal measures to increase prediction power. We use different kernels for each data source taking advantage of the distinctive feature of each data modality, and then optimally combine data across modalities. We apply the developed methods to two large epidemiological studies, one on Huntington's disease and the other on Alzheimer's Disease (Alzheimer's Disease Neuroimaging Initiative, ADNI) where we explore a unique opportunity to combine imaging and genetic data to study prediction of mild cognitive impairment, and show a substantial gain in performance while accounting for the longitudinal aspect of the data. PMID:26177419

Lung dynamic MRI deblurring using low-rank decomposition and dictionary learning.

PubMed

Gou, Shuiping; Wang, Yueyue; Wu, Jiaolong; Lee, Percy; Sheng, Ke

2015-04-01

Lung dynamic MRI (dMRI) has emerged to be an appealing tool to quantify lung motion for both planning and treatment guidance purposes. However, this modality can result in blurry images due to intrinsically low signal-to-noise ratio in the lung and spatial/temporal interpolation. The image blurring could adversely affect the image processing that depends on the availability of fine landmarks. The purpose of this study is to reduce dMRI blurring using image postprocessing. To enhance the image quality and exploit the spatiotemporal continuity of dMRI sequences, a low-rank decomposition and dictionary learning (LDDL) method was employed to deblur lung dMRI and enhance the conspicuity of lung blood vessels. Fifty frames of continuous 2D coronal dMRI frames using a steady state free precession sequence were obtained from five subjects including two healthy volunteer and three lung cancer patients. In LDDL, the lung dMRI was decomposed into sparse and low-rank components. Dictionary learning was employed to estimate the blurring kernel based on the whole image, low-rank or sparse component of the first image in the lung MRI sequence. Deblurring was performed on the whole image sequences using deconvolution based on the estimated blur kernel. The deblurring results were quantified using an automated blood vessel extraction method based on the classification of Hessian matrix filtered images. Accuracy of automated extraction was calculated using manual segmentation of the blood vessels as the ground truth. In the pilot study, LDDL based on the blurring kernel estimated from the sparse component led to performance superior to the other ways of kernel estimation. LDDL consistently improved image contrast and fine feature conspicuity of the original MRI without introducing artifacts. The accuracy of automated blood vessel extraction was on average increased by 16% using manual segmentation as the ground truth. Image blurring in dMRI images can be effectively reduced using a low-rank decomposition and dictionary learning method using kernels estimated by the sparse component.

Approximate l-fold cross-validation with Least Squares SVM and Kernel Ridge Regression

DOE Office of Scientific and Technical Information (OSTI.GOV)

Edwards, Richard E; Zhang, Hao; Parker, Lynne Edwards

2013-01-01

Kernel methods have difficulties scaling to large modern data sets. The scalability issues are based on computational and memory requirements for working with a large matrix. These requirements have been addressed over the years by using low-rank kernel approximations or by improving the solvers scalability. However, Least Squares Support VectorMachines (LS-SVM), a popular SVM variant, and Kernel Ridge Regression still have several scalability issues. In particular, the O(n^3) computational complexity for solving a single model, and the overall computational complexity associated with tuning hyperparameters are still major problems. We address these problems by introducing an O(n log n) approximate l-foldmore » cross-validation method that uses a multi-level circulant matrix to approximate the kernel. In addition, we prove our algorithm s computational complexity and present empirical runtimes on data sets with approximately 1 million data points. We also validate our approximate method s effectiveness at selecting hyperparameters on real world and standard benchmark data sets. Lastly, we provide experimental results on using a multi-level circulant kernel approximation to solve LS-SVM problems with hyperparameters selected using our method.« less

SVM-based feature extraction and classification of aflatoxin contaminated corn using fluorescence hyperspectral data

USDA-ARS?s Scientific Manuscript database

Support Vector Machine (SVM) was used in the Genetic Algorithms (GA) process to select and classify a subset of hyperspectral image bands. The method was applied to fluorescence hyperspectral data for the detection of aflatoxin contamination in Aspergillus flavus infected single corn kernels. In the...

Drug related webpages classification using images and text information based on multi-kernel learning

NASA Astrophysics Data System (ADS)

Hu, Ruiguang; Xiao, Liping; Zheng, Wenjuan

2015-12-01

In this paper, multi-kernel learning(MKL) is used for drug-related webpages classification. First, body text and image-label text are extracted through HTML parsing, and valid images are chosen by the FOCARSS algorithm. Second, text based BOW model is used to generate text representation, and image-based BOW model is used to generate images representation. Last, text and images representation are fused with a few methods. Experimental results demonstrate that the classification accuracy of MKL is higher than those of all other fusion methods in decision level and feature level, and much higher than the accuracy of single-modal classification.

Toward open set recognition.

PubMed

Scheirer, Walter J; de Rezende Rocha, Anderson; Sapkota, Archana; Boult, Terrance E

2013-07-01

To date, almost all experimental evaluations of machine learning-based recognition algorithms in computer vision have taken the form of "closed set" recognition, whereby all testing classes are known at training time. A more realistic scenario for vision applications is "open set" recognition, where incomplete knowledge of the world is present at training time, and unknown classes can be submitted to an algorithm during testing. This paper explores the nature of open set recognition and formalizes its definition as a constrained minimization problem. The open set recognition problem is not well addressed by existing algorithms because it requires strong generalization. As a step toward a solution, we introduce a novel "1-vs-set machine," which sculpts a decision space from the marginal distances of a 1-class or binary SVM with a linear kernel. This methodology applies to several different applications in computer vision where open set recognition is a challenging problem, including object recognition and face verification. We consider both in this work, with large scale cross-dataset experiments performed over the Caltech 256 and ImageNet sets, as well as face matching experiments performed over the Labeled Faces in the Wild set. The experiments highlight the effectiveness of machines adapted for open set evaluation compared to existing 1-class and binary SVMs for the same tasks.

Detecting Abnormal Word Utterances in Children With Autism Spectrum Disorders: Machine-Learning-Based Voice Analysis Versus Speech Therapists.

PubMed

Nakai, Yasushi; Takiguchi, Tetsuya; Matsui, Gakuyo; Yamaoka, Noriko; Takada, Satoshi

2017-10-01

Abnormal prosody is often evident in the voice intonations of individuals with autism spectrum disorders. We compared a machine-learning-based voice analysis with human hearing judgments made by 10 speech therapists for classifying children with autism spectrum disorders ( n = 30) and typical development ( n = 51). Using stimuli limited to single-word utterances, machine-learning-based voice analysis was superior to speech therapist judgments. There was a significantly higher true-positive than false-negative rate for machine-learning-based voice analysis but not for speech therapists. Results are discussed in terms of some artificiality of clinician judgments based on single-word utterances, and the objectivity machine-learning-based voice analysis adds to judging abnormal prosody.

A sparse grid based method for generative dimensionality reduction of high-dimensional data

NASA Astrophysics Data System (ADS)

Bohn, Bastian; Garcke, Jochen; Griebel, Michael

2016-03-01

Generative dimensionality reduction methods play an important role in machine learning applications because they construct an explicit mapping from a low-dimensional space to the high-dimensional data space. We discuss a general framework to describe generative dimensionality reduction methods, where the main focus lies on a regularized principal manifold learning variant. Since most generative dimensionality reduction algorithms exploit the representer theorem for reproducing kernel Hilbert spaces, their computational costs grow at least quadratically in the number n of data. Instead, we introduce a grid-based discretization approach which automatically scales just linearly in n. To circumvent the curse of dimensionality of full tensor product grids, we use the concept of sparse grids. Furthermore, in real-world applications, some embedding directions are usually more important than others and it is reasonable to refine the underlying discretization space only in these directions. To this end, we employ a dimension-adaptive algorithm which is based on the ANOVA (analysis of variance) decomposition of a function. In particular, the reconstruction error is used to measure the quality of an embedding. As an application, the study of large simulation data from an engineering application in the automotive industry (car crash simulation) is performed.

CS-AMPPred: An Updated SVM Model for Antimicrobial Activity Prediction in Cysteine-Stabilized Peptides

PubMed Central

Porto, William F.; Pires, Állan S.; Franco, Octavio L.

2012-01-01

The antimicrobial peptides (AMP) have been proposed as an alternative to control resistant pathogens. However, due to multifunctional properties of several AMP classes, until now there has been no way to perform efficient AMP identification, except through in vitro and in vivo tests. Nevertheless, an indication of activity can be provided by prediction methods. In order to contribute to the AMP prediction field, the CS-AMPPred (Cysteine-Stabilized Antimicrobial Peptides Predictor) is presented here, consisting of an updated version of the Support Vector Machine (SVM) model for antimicrobial activity prediction in cysteine-stabilized peptides. The CS-AMPPred is based on five sequence descriptors: indexes of (i) α-helix and (ii) loop formation; and averages of (iii) net charge, (iv) hydrophobicity and (v) flexibility. CS-AMPPred was based on 310 cysteine-stabilized AMPs and 310 sequences extracted from PDB. The polynomial kernel achieves the best accuracy on 5-fold cross validation (85.81%), while the radial and linear kernels achieve 84.19%. Testing in a blind data set, the polynomial and radial kernels achieve an accuracy of 90.00%, while the linear model achieves 89.33%. The three models reach higher accuracies than previously described methods. A standalone version of CS-AMPPred is available for download at and runs on any Linux machine. PMID:23240023

Applications of Machine Learning and Rule Induction,

DTIC Science & Technology

1995-02-15

An important area of application for machine learning is in automating the acquisition of knowledge bases required for expert systems. In this paper...we review the major paradigms for machine learning , including neural networks, instance-based methods, genetic learning, rule induction, and analytic

Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

PubMed

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space

PubMed Central

Li, Kan; Príncipe, José C.

2018-01-01

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime. PMID:29666568

Biologically-Inspired Spike-Based Automatic Speech Recognition of Isolated Digits Over a Reproducing Kernel Hilbert Space.

PubMed

Li, Kan; Príncipe, José C

2018-01-01

This paper presents a novel real-time dynamic framework for quantifying time-series structure in spoken words using spikes. Audio signals are converted into multi-channel spike trains using a biologically-inspired leaky integrate-and-fire (LIF) spike generator. These spike trains are mapped into a function space of infinite dimension, i.e., a Reproducing Kernel Hilbert Space (RKHS) using point-process kernels, where a state-space model learns the dynamics of the multidimensional spike input using gradient descent learning. This kernelized recurrent system is very parsimonious and achieves the necessary memory depth via feedback of its internal states when trained discriminatively, utilizing the full context of the phoneme sequence. A main advantage of modeling nonlinear dynamics using state-space trajectories in the RKHS is that it imposes no restriction on the relationship between the exogenous input and its internal state. We are free to choose the input representation with an appropriate kernel, and changing the kernel does not impact the system nor the learning algorithm. Moreover, we show that this novel framework can outperform both traditional hidden Markov model (HMM) speech processing as well as neuromorphic implementations based on spiking neural network (SNN), yielding accurate and ultra-low power word spotters. As a proof of concept, we demonstrate its capabilities using the benchmark TI-46 digit corpus for isolated-word automatic speech recognition (ASR) or keyword spotting. Compared to HMM using Mel-frequency cepstral coefficient (MFCC) front-end without time-derivatives, our MFCC-KAARMA offered improved performance. For spike-train front-end, spike-KAARMA also outperformed state-of-the-art SNN solutions. Furthermore, compared to MFCCs, spike trains provided enhanced noise robustness in certain low signal-to-noise ratio (SNR) regime.

An Ensemble Approach to Building Mercer Kernels with Prior Information

NASA Technical Reports Server (NTRS)

Srivastava, Ashok N.; Schumann, Johann; Fischer, Bernd

2005-01-01

This paper presents a new methodology for automatic knowledge driven data mining based on the theory of Mercer Kernels, which are highly nonlinear symmetric positive definite mappings from the original image space to a very high, possibly dimensional feature space. we describe a new method called Mixture Density Mercer Kernels to learn kernel function directly from data, rather than using pre-defined kernels. These data adaptive kernels can encode prior knowledge in the kernel using a Bayesian formulation, thus allowing for physical information to be encoded in the model. Specifically, we demonstrate the use of the algorithm in situations with extremely small samples of data. We compare the results with existing algorithms on data from the Sloan Digital Sky Survey (SDSS) and demonstrate the method's superior performance against standard methods. The code for these experiments has been generated with the AUTOBAYES tool, which automatically generates efficient and documented C/C++ code from abstract statistical model specifications. The core of the system is a schema library which contains templates for learning and knowledge discovery algorithms like different versions of EM, or numeric optimization methods like conjugate gradient methods. The template instantiation is supported by symbolic-algebraic computations, which allows AUTOBAYES to find closed-form solutions and, where possible, to integrate them into the code.

Kernel machine methods for integrative analysis of genome-wide methylation and genotyping studies.

PubMed

Zhao, Ni; Zhan, Xiang; Huang, Yen-Tsung; Almli, Lynn M; Smith, Alicia; Epstein, Michael P; Conneely, Karen; Wu, Michael C

2018-03-01

Many large GWAS consortia are expanding to simultaneously examine the joint role of DNA methylation in addition to genotype in the same subjects. However, integrating information from both data types is challenging. In this paper, we propose a composite kernel machine regression model to test the joint epigenetic and genetic effect. Our approach works at the gene level, which allows for a common unit of analysis across different data types. The model compares the pairwise similarities in the phenotype to the pairwise similarities in the genotype and methylation values; and high correspondence is suggestive of association. A composite kernel is constructed to measure the similarities in the genotype and methylation values between pairs of samples. We demonstrate through simulations and real data applications that the proposed approach can correctly control type I error, and is more robust and powerful than using only the genotype or methylation data in detecting trait-associated genes. We applied our method to investigate the genetic and epigenetic regulation of gene expression in response to stressful life events using data that are collected from the Grady Trauma Project. Within the kernel machine testing framework, our methods allow for heterogeneity in effect sizes, nonlinear, and interactive effects, as well as rapid P-value computation. © 2017 WILEY PERIODICALS, INC.

Selecting the most relevant brain regions to discriminate Alzheimer's disease patients from healthy controls using multiple kernel learning: A comparison across functional and structural imaging modalities and atlases.

PubMed

Rondina, Jane Maryam; Ferreira, Luiz Kobuti; de Souza Duran, Fabio Luis; Kubo, Rodrigo; Ono, Carla Rachel; Leite, Claudia Costa; Smid, Jerusa; Nitrini, Ricardo; Buchpiguel, Carlos Alberto; Busatto, Geraldo F

2018-01-01

Machine learning techniques such as support vector machine (SVM) have been applied recently in order to accurately classify individuals with neuropsychiatric disorders such as Alzheimer's disease (AD) based on neuroimaging data. However, the multivariate nature of the SVM approach often precludes the identification of the brain regions that contribute most to classification accuracy. Multiple kernel learning (MKL) is a sparse machine learning method that allows the identification of the most relevant sources for the classification. By parcelating the brain into regions of interest (ROI) it is possible to use each ROI as a source to MKL (ROI-MKL). We applied MKL to multimodal neuroimaging data in order to: 1) compare the diagnostic performance of ROI-MKL and whole-brain SVM in discriminating patients with AD from demographically matched healthy controls and 2) identify the most relevant brain regions to the classification. We used two atlases (AAL and Brodmann's) to parcelate the brain into ROIs and applied ROI-MKL to structural (T1) MRI, 18 F-FDG-PET and regional cerebral blood flow SPECT (rCBF-SPECT) data acquired from the same subjects (20 patients with early AD and 18 controls). In ROI-MKL, each ROI received a weight (ROI-weight) that indicated the region's relevance to the classification. For each ROI, we also calculated whether there was a predominance of voxels indicating decreased or increased regional activity (for 18 F-FDG-PET and rCBF-SPECT) or volume (for T1-MRI) in AD patients. Compared to whole-brain SVM, the ROI-MKL approach resulted in better accuracies (with either atlas) for classification using 18 F-FDG-PET (92.5% accuracy for ROI-MKL versus 84% for whole-brain), but not when using rCBF-SPECT or T1-MRI. Although several cortical and subcortical regions contributed to discrimination, high ROI-weights and predominance of hypometabolism and atrophy were identified specially in medial parietal and temporo-limbic cortical regions. Also, the weight of discrimination due to a pattern of increased voxel-weight values in AD individuals was surprisingly high (ranging from approximately 20% to 40% depending on the imaging modality), located mainly in primary sensorimotor and visual cortices and subcortical nuclei. The MKL-ROI approach highlights the high discriminative weight of a subset of brain regions of known relevance to AD, the selection of which contributes to increased classification accuracy when applied to 18 F-FDG-PET data. Moreover, the MKL-ROI approach demonstrates that brain regions typically spared in mild stages of AD also contribute substantially in the individual discrimination of AD patients from controls.

Impact of deep learning on the normalization of reconstruction kernel effects in imaging biomarker quantification: a pilot study in CT emphysema

NASA Astrophysics Data System (ADS)

Jin, Hyeongmin; Heo, Changyong; Kim, Jong Hyo

2018-02-01

Differing reconstruction kernels are known to strongly affect the variability of imaging biomarkers and thus remain as a barrier in translating the computer aided quantification techniques into clinical practice. This study presents a deep learning application to CT kernel conversion which converts a CT image of sharp kernel to that of standard kernel and evaluates its impact on variability reduction of a pulmonary imaging biomarker, the emphysema index (EI). Forty cases of low-dose chest CT exams obtained with 120kVp, 40mAs, 1mm thickness, of 2 reconstruction kernels (B30f, B50f) were selected from the low dose lung cancer screening database of our institution. A Fully convolutional network was implemented with Keras deep learning library. The model consisted of symmetric layers to capture the context and fine structure characteristics of CT images from the standard and sharp reconstruction kernels. Pairs of the full-resolution CT data set were fed to input and output nodes to train the convolutional network to learn the appropriate filter kernels for converting the CT images of sharp kernel to standard kernel with a criterion of measuring the mean squared error between the input and target images. EIs (RA950 and Perc15) were measured with a software package (ImagePrism Pulmo, Seoul, South Korea) and compared for the data sets of B50f, B30f, and the converted B50f. The effect of kernel conversion was evaluated with the mean and standard deviation of pair-wise differences in EI. The population mean of RA950 was 27.65 +/- 7.28% for B50f data set, 10.82 +/- 6.71% for the B30f data set, and 8.87 +/- 6.20% for the converted B50f data set. The mean of pair-wise absolute differences in RA950 between B30f and B50f is reduced from 16.83% to 1.95% using kernel conversion. Our study demonstrates the feasibility of applying the deep learning technique for CT kernel conversion and reducing the kernel-induced variability of EI quantification. The deep learning model has a potential to improve the reliability of imaging biomarker, especially in evaluating the longitudinal changes of EI even when the patient CT scans were performed with different kernels.

Multilevel image recognition using discriminative patches and kernel covariance descriptor

NASA Astrophysics Data System (ADS)

Lu, Le; Yao, Jianhua; Turkbey, Evrim; Summers, Ronald M.

2014-03-01

Computer-aided diagnosis of medical images has emerged as an important tool to objectively improve the performance, accuracy and consistency for clinical workflow. To computerize the medical image diagnostic recognition problem, there are three fundamental problems: where to look (i.e., where is the region of interest from the whole image/volume), image feature description/encoding, and similarity metrics for classification or matching. In this paper, we exploit the motivation, implementation and performance evaluation of task-driven iterative, discriminative image patch mining; covariance matrix based descriptor via intensity, gradient and spatial layout; and log-Euclidean distance kernel for support vector machine, to address these three aspects respectively. To cope with often visually ambiguous image patterns for the region of interest in medical diagnosis, discovery of multilabel selective discriminative patches is desired. Covariance of several image statistics summarizes their second order interactions within an image patch and is proved as an effective image descriptor, with low dimensionality compared with joint statistics and fast computation regardless of the patch size. We extensively evaluate two extended Gaussian kernels using affine-invariant Riemannian metric or log-Euclidean metric with support vector machines (SVM), on two medical image classification problems of degenerative disc disease (DDD) detection on cortical shell unwrapped CT maps and colitis detection on CT key images. The proposed approach is validated with promising quantitative results on these challenging tasks. Our experimental findings and discussion also unveil some interesting insights on the covariance feature composition with or without spatial layout for classification and retrieval, and different kernel constructions for SVM. This will also shed some light on future work using covariance feature and kernel classification for medical image analysis.

Integration of heterogeneous data for classification in hyperspectral satellite imagery

NASA Astrophysics Data System (ADS)

Benedetto, J.; Czaja, W.; Dobrosotskaya, J.; Doster, T.; Duke, K.; Gillis, D.

2012-06-01

As new remote sensing modalities emerge, it becomes increasingly important to nd more suitable algorithms for fusion and integration of dierent data types for the purposes of target/anomaly detection and classication. Typical techniques that deal with this problem are based on performing detection/classication/segmentation separately in chosen modalities, and then integrating the resulting outcomes into a more complete picture. In this paper we provide a broad analysis of a new approach, based on creating fused representations of the multi- modal data, which then can be subjected to analysis by means of the state-of-the-art classiers or detectors. In this scenario we shall consider the hyperspectral imagery combined with spatial information. Our approach involves machine learning techniques based on analysis of joint data-dependent graphs and their associated diusion kernels. Then, the signicant eigenvectors of the derived fused graph Laplace operator form the new representation, which provides integrated features from the heterogeneous input data. We compare these fused approaches with analysis of integrated outputs of spatial and spectral graph methods.

Automated Segmentation of the Parotid Gland Based on Atlas Registration and Machine Learning: A Longitudinal MRI Study in Head-and-Neck Radiation Therapy

DOE Office of Scientific and Technical Information (OSTI.GOV)

Yang, Xiaofeng; Wu, Ning; Cheng, Guanghui

Purpose: To develop an automated magnetic resonance imaging (MRI) parotid segmentation method to monitor radiation-induced parotid gland changes in patients after head and neck radiation therapy (RT). Methods and Materials: The proposed method combines the atlas registration method, which captures the global variation of anatomy, with a machine learning technology, which captures the local statistical features, to automatically segment the parotid glands from the MRIs. The segmentation method consists of 3 major steps. First, an atlas (pre-RT MRI and manually contoured parotid gland mask) is built for each patient. A hybrid deformable image registration is used to map the pre-RTmore » MRI to the post-RT MRI, and the transformation is applied to the pre-RT parotid volume. Second, the kernel support vector machine (SVM) is trained with the subject-specific atlas pair consisting of multiple features (intensity, gradient, and others) from the aligned pre-RT MRI and the transformed parotid volume. Third, the well-trained kernel SVM is used to differentiate the parotid from surrounding tissues in the post-RT MRIs by statistically matching multiple texture features. A longitudinal study of 15 patients undergoing head and neck RT was conducted: baseline MRI was acquired prior to RT, and the post-RT MRIs were acquired at 3-, 6-, and 12-month follow-up examinations. The resulting segmentations were compared with the physicians' manual contours. Results: Successful parotid segmentation was achieved for all 15 patients (42 post-RT MRIs). The average percentage of volume differences between the automated segmentations and those of the physicians' manual contours were 7.98% for the left parotid and 8.12% for the right parotid. The average volume overlap was 91.1% ± 1.6% for the left parotid and 90.5% ± 2.4% for the right parotid. The parotid gland volume reduction at follow-up was 25% at 3 months, 27% at 6 months, and 16% at 12 months. Conclusions: We have validated our automated parotid segmentation algorithm in a longitudinal study. This segmentation method may be useful in future studies to address radiation-induced xerostomia in head and neck radiation therapy.« less

A land use regression model for ambient ultrafine particles in Montreal, Canada: A comparison of linear regression and a machine learning approach.

PubMed

Weichenthal, Scott; Ryswyk, Keith Van; Goldstein, Alon; Bagg, Scott; Shekkarizfard, Maryam; Hatzopoulou, Marianne

2016-04-01

Existing evidence suggests that ambient ultrafine particles (UFPs) (<0.1µm) may contribute to acute cardiorespiratory morbidity. However, few studies have examined the long-term health effects of these pollutants owing in part to a need for exposure surfaces that can be applied in large population-based studies. To address this need, we developed a land use regression model for UFPs in Montreal, Canada using mobile monitoring data collected from 414 road segments during the summer and winter months between 2011 and 2012. Two different approaches were examined for model development including standard multivariable linear regression and a machine learning approach (kernel-based regularized least squares (KRLS)) that learns the functional form of covariate impacts on ambient UFP concentrations from the data. The final models included parameters for population density, ambient temperature and wind speed, land use parameters (park space and open space), length of local roads and rail, and estimated annual average NOx emissions from traffic. The final multivariable linear regression model explained 62% of the spatial variation in ambient UFP concentrations whereas the KRLS model explained 79% of the variance. The KRLS model performed slightly better than the linear regression model when evaluated using an external dataset (R(2)=0.58 vs. 0.55) or a cross-validation procedure (R(2)=0.67 vs. 0.60). In general, our findings suggest that the KRLS approach may offer modest improvements in predictive performance compared to standard multivariable linear regression models used to estimate spatial variations in ambient UFPs. However, differences in predictive performance were not statistically significant when evaluated using the cross-validation procedure. Crown Copyright © 2015. Published by Elsevier Inc. All rights reserved.

Kernel-aligned multi-view canonical correlation analysis for image recognition

NASA Astrophysics Data System (ADS)

Su, Shuzhi; Ge, Hongwei; Yuan, Yun-Hao

2016-09-01

Existing kernel-based correlation analysis methods mainly adopt a single kernel in each view. However, only a single kernel is usually insufficient to characterize nonlinear distribution information of a view. To solve the problem, we transform each original feature vector into a 2-dimensional feature matrix by means of kernel alignment, and then propose a novel kernel-aligned multi-view canonical correlation analysis (KAMCCA) method on the basis of the feature matrices. Our proposed method can simultaneously employ multiple kernels to better capture the nonlinear distribution information of each view, so that correlation features learned by KAMCCA can have well discriminating power in real-world image recognition. Extensive experiments are designed on five real-world image datasets, including NIR face images, thermal face images, visible face images, handwritten digit images, and object images. Promising experimental results on the datasets have manifested the effectiveness of our proposed method.

Hierarchical kernel mixture models for the prediction of AIDS disease progression using HIV structural gp120 profiles

PubMed Central

2010-01-01

Changes to the glycosylation profile on HIV gp120 can influence viral pathogenesis and alter AIDS disease progression. The characterization of glycosylation differences at the sequence level is inadequate as the placement of carbohydrates is structurally complex. However, no structural framework is available to date for the study of HIV disease progression. In this study, we propose a novel machine-learning based framework for the prediction of AIDS disease progression in three stages (RP, SP, and LTNP) using the HIV structural gp120 profile. This new intelligent framework proves to be accurate and provides an important benchmark for predicting AIDS disease progression computationally. The model is trained using a novel HIV gp120 glycosylation structural profile to detect possible stages of AIDS disease progression for the target sequences of HIV+ individuals. The performance of the proposed model was compared to seven existing different machine-learning models on newly proposed gp120-Benchmark_1 dataset in terms of error-rate (MSE), accuracy (CCI), stability (STD), and complexity (TBM). The novel framework showed better predictive performance with 67.82% CCI, 30.21 MSE, 0.8 STD, and 2.62 TBM on the three stages of AIDS disease progression of 50 HIV+ individuals. This framework is an invaluable bioinformatics tool that will be useful to the clinical assessment of viral pathogenesis. PMID:21143806

Machine Learning Estimation of Atom Condensed Fukui Functions.

PubMed

Zhang, Qingyou; Zheng, Fangfang; Zhao, Tanfeng; Qu, Xiaohui; Aires-de-Sousa, João

2016-02-01

To enable the fast estimation of atom condensed Fukui functions, machine learning algorithms were trained with databases of DFT pre-calculated values for ca. 23,000 atoms in organic molecules. The problem was approached as the ranking of atom types with the Bradley-Terry (BT) model, and as the regression of the Fukui function. Random Forests (RF) were trained to predict the condensed Fukui function, to rank atoms in a molecule, and to classify atoms as high/low Fukui function. Atomic descriptors were based on counts of atom types in spheres around the kernel atom. The BT coefficients assigned to atom types enabled the identification (93-94 % accuracy) of the atom with the highest Fukui function in pairs of atoms in the same molecule with differences ≥0.1. In whole molecules, the atom with the top Fukui function could be recognized in ca. 50 % of the cases and, on the average, about 3 of the top 4 atoms could be recognized in a shortlist of 4. Regression RF yielded predictions for test sets with R(2) =0.68-0.69, improving the ability of BT coefficients to rank atoms in a molecule. Atom classification (as high/low Fukui function) was obtained with RF with sensitivity of 55-61 % and specificity of 94-95 %. © 2016 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

An SVM model with hybrid kernels for hydrological time series

NASA Astrophysics Data System (ADS)

Wang, C.; Wang, H.; Zhao, X.; Xie, Q.

2017-12-01

Support Vector Machine (SVM) models have been widely applied to the forecast of climate/weather and its impact on other environmental variables such as hydrologic response to climate/weather. When using SVM, the choice of the kernel function plays the key role. Conventional SVM models mostly use one single type of kernel function, e.g., radial basis kernel function. Provided that there are several featured kernel functions available, each having its own advantages and drawbacks, a combination of these kernel functions may give more flexibility and robustness to SVM approach, making it suitable for a wide range of application scenarios. This paper presents such a linear combination of radial basis kernel and polynomial kernel for the forecast of monthly flowrate in two gaging stations using SVM approach. The results indicate significant improvement in the accuracy of predicted series compared to the approach with either individual kernel function, thus demonstrating the feasibility and advantages of such hybrid kernel approach for SVM applications.

Entanglement-Based Machine Learning on a Quantum Computer

NASA Astrophysics Data System (ADS)

Cai, X.-D.; Wu, D.; Su, Z.-E.; Chen, M.-C.; Wang, X.-L.; Li, Li; Liu, N.-L.; Lu, C.-Y.; Pan, J.-W.

2015-03-01

Machine learning, a branch of artificial intelligence, learns from previous experience to optimize performance, which is ubiquitous in various fields such as computer sciences, financial analysis, robotics, and bioinformatics. A challenge is that machine learning with the rapidly growing "big data" could become intractable for classical computers. Recently, quantum machine learning algorithms [Lloyd, Mohseni, and Rebentrost, arXiv.1307.0411] were proposed which could offer an exponential speedup over classical algorithms. Here, we report the first experimental entanglement-based classification of two-, four-, and eight-dimensional vectors to different clusters using a small-scale photonic quantum computer, which are then used to implement supervised and unsupervised machine learning. The results demonstrate the working principle of using quantum computers to manipulate and classify high-dimensional vectors, the core mathematical routine in machine learning. The method can, in principle, be scaled to larger numbers of qubits, and may provide a new route to accelerate machine learning.

Construction of phylogenetic trees by kernel-based comparative analysis of metabolic networks.

PubMed

Oh, S June; Joung, Je-Gun; Chang, Jeong-Ho; Zhang, Byoung-Tak

2006-06-06

To infer the tree of life requires knowledge of the common characteristics of each species descended from a common ancestor as the measuring criteria and a method to calculate the distance between the resulting values of each measure. Conventional phylogenetic analysis based on genomic sequences provides information about the genetic relationships between different organisms. In contrast, comparative analysis of metabolic pathways in different organisms can yield insights into their functional relationships under different physiological conditions. However, evaluating the similarities or differences between metabolic networks is a computationally challenging problem, and systematic methods of doing this are desirable. Here we introduce a graph-kernel method for computing the similarity between metabolic networks in polynomial time, and use it to profile metabolic pathways and to construct phylogenetic trees. To compare the structures of metabolic networks in organisms, we adopted the exponential graph kernel, which is a kernel-based approach with a labeled graph that includes a label matrix and an adjacency matrix. To construct the phylogenetic trees, we used an unweighted pair-group method with arithmetic mean, i.e., a hierarchical clustering algorithm. We applied the kernel-based network profiling method in a comparative analysis of nine carbohydrate metabolic networks from 81 biological species encompassing Archaea, Eukaryota, and Eubacteria. The resulting phylogenetic hierarchies generally support the tripartite scheme of three domains rather than the two domains of prokaryotes and eukaryotes. By combining the kernel machines with metabolic information, the method infers the context of biosphere development that covers physiological events required for adaptation by genetic reconstruction. The results show that one may obtain a global view of the tree of life by comparing the metabolic pathway structures using meta-level information rather than sequence information. This method may yield further information about biological evolution, such as the history of horizontal transfer of each gene, by studying the detailed structure of the phylogenetic tree constructed by the kernel-based method.

Performance Assessment of Kernel Density Clustering for Gene Expression Profile Data

PubMed Central

Zeng, Beiyan; Chen, Yiping P.; Smith, Oscar H.

2003-01-01

Kernel density smoothing techniques have been used in classification or supervised learning of gene expression profile (GEP) data, but their applications to clustering or unsupervised learning of those data have not been explored and assessed. Here we report a kernel density clustering method for analysing GEP data and compare its performance with the three most widely-used clustering methods: hierarchical clustering, K-means clustering, and multivariate mixture model-based clustering. Using several methods to measure agreement, between-cluster isolation, and withincluster coherence, such as the Adjusted Rand Index, the Pseudo F test, the r2 test, and the profile plot, we have assessed the effectiveness of kernel density clustering for recovering clusters, and its robustness against noise on clustering both simulated and real GEP data. Our results show that the kernel density clustering method has excellent performance in recovering clusters from simulated data and in grouping large real expression profile data sets into compact and well-isolated clusters, and that it is the most robust clustering method for analysing noisy expression profile data compared to the other three methods assessed. PMID:18629292

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

PubMed Central

Guo, Hao; Zhang, Fan; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

Exploring functional interactions among various brain regions is helpful for understanding the pathological underpinnings of neurological disorders. Brain networks provide an important representation of those functional interactions, and thus are widely applied in the diagnosis and classification of neurodegenerative diseases. Many mental disorders involve a sharp decline in cognitive ability as a major symptom, which can be caused by abnormal connectivity patterns among several brain regions. However, conventional functional connectivity networks are usually constructed based on pairwise correlations among different brain regions. This approach ignores higher-order relationships, and cannot effectively characterize the high-order interactions of many brain regions working together. Recent neuroscience research suggests that higher-order relationships between brain regions are important for brain network analysis. Hyper-networks have been proposed that can effectively represent the interactions among brain regions. However, this method extracts the local properties of brain regions as features, but ignores the global topology information, which affects the evaluation of network topology and reduces the performance of the classifier. This problem can be compensated by a subgraph feature-based method, but it is not sensitive to change in a single brain region. Considering that both of these feature extraction methods result in the loss of information, we propose a novel machine learning classification method that combines multiple features of a hyper-network based on functional magnetic resonance imaging in Alzheimer's disease. The method combines the brain region features and subgraph features, and then uses a multi-kernel SVM for classification. This retains not only the global topological information, but also the sensitivity to change in a single brain region. To certify the proposed method, 28 normal control subjects and 38 Alzheimer's disease patients were selected to participate in an experiment. The proposed method achieved satisfactory classification accuracy, with an average of 91.60%. The abnormal brain regions included the bilateral precuneus, right parahippocampal gyrus\\hippocampus, right posterior cingulate gyrus, and other regions that are known to be important in Alzheimer's disease. Machine learning classification combining multiple features of a hyper-network of functional magnetic resonance imaging data in Alzheimer's disease obtains better classification performance. PMID:29209156

[Discrimination of varieties of borneol using terahertz spectra based on principal component analysis and support vector machine].

PubMed

Li, Wu; Hu, Bing; Wang, Ming-wei

2014-12-01

In the present paper, the terahertz time-domain spectroscopy (THz-TDS) identification model of borneol based on principal component analysis (PCA) and support vector machine (SVM) was established. As one Chinese common agent, borneol needs a rapid, simple and accurate detection and identification method for its different source and being easily confused in the pharmaceutical and trade links. In order to assure the quality of borneol product and guard the consumer's right, quickly, efficiently and correctly identifying borneol has significant meaning to the production and transaction of borneol. Terahertz time-domain spectroscopy is a new spectroscopy approach to characterize material using terahertz pulse. The absorption terahertz spectra of blumea camphor, borneol camphor and synthetic borneol were measured in the range of 0.2 to 2 THz with the transmission THz-TDS. The PCA scores of 2D plots (PC1 X PC2) and 3D plots (PC1 X PC2 X PC3) of three kinds of borneol samples were obtained through PCA analysis, and both of them have good clustering effect on the 3 different kinds of borneol. The value matrix of the first 10 principal components (PCs) was used to replace the original spectrum data, and the 60 samples of the three kinds of borneol were trained and then the unknown 60 samples were identified. Four kinds of support vector machine model of different kernel functions were set up in this way. Results show that the accuracy of identification and classification of SVM RBF kernel function for three kinds of borneol is 100%, and we selected the SVM with the radial basis kernel function to establish the borneol identification model, in addition, in the noisy case, the classification accuracy rates of four SVM kernel function are above 85%, and this indicates that SVM has strong generalization ability. This study shows that PCA with SVM method of borneol terahertz spectroscopy has good classification and identification effects, and provides a new method for species identification of borneol in Chinese medicine.

Complex extreme learning machine applications in terahertz pulsed signals feature sets.

PubMed

Yin, X-X; Hadjiloucas, S; Zhang, Y

2014-11-01

This paper presents a novel approach to the automatic classification of very large data sets composed of terahertz pulse transient signals, highlighting their potential use in biochemical, biomedical, pharmaceutical and security applications. Two different types of THz spectra are considered in the classification process. Firstly a binary classification study of poly-A and poly-C ribonucleic acid samples is performed. This is then contrasted with a difficult multi-class classification problem of spectra from six different powder samples that although have fairly indistinguishable features in the optical spectrum, they also possess a few discernable spectral features in the terahertz part of the spectrum. Classification is performed using a complex-valued extreme learning machine algorithm that takes into account features in both the amplitude as well as the phase of the recorded spectra. Classification speed and accuracy are contrasted with that achieved using a support vector machine classifier. The study systematically compares the classifier performance achieved after adopting different Gaussian kernels when separating amplitude and phase signatures. The two signatures are presented as feature vectors for both training and testing purposes. The study confirms the utility of complex-valued extreme learning machine algorithms for classification of the very large data sets generated with current terahertz imaging spectrometers. The classifier can take into consideration heterogeneous layers within an object as would be required within a tomographic setting and is sufficiently robust to detect patterns hidden inside noisy terahertz data sets. The proposed study opens up the opportunity for the establishment of complex-valued extreme learning machine algorithms as new chemometric tools that will assist the wider proliferation of terahertz sensing technology for chemical sensing, quality control, security screening and clinic diagnosis. Furthermore, the proposed algorithm should also be very useful in other applications requiring the classification of very large datasets. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Kernel approach to molecular similarity based on iterative graph similarity.

PubMed

Rupp, Matthias; Proschak, Ewgenij; Schneider, Gisbert

2007-01-01

Similarity measures for molecules are of basic importance in chemical, biological, and pharmaceutical applications. We introduce a molecular similarity measure defined directly on the annotated molecular graph, based on iterative graph similarity and optimal assignments. We give an iterative algorithm for the computation of the proposed molecular similarity measure, prove its convergence and the uniqueness of the solution, and provide an upper bound on the required number of iterations necessary to achieve a desired precision. Empirical evidence for the positive semidefiniteness of certain parametrizations of our function is presented. We evaluated our molecular similarity measure by using it as a kernel in support vector machine classification and regression applied to several pharmaceutical and toxicological data sets, with encouraging results.

Dropout Prediction in E-Learning Courses through the Combination of Machine Learning Techniques

ERIC Educational Resources Information Center

Lykourentzou, Ioanna; Giannoukos, Ioannis; Nikolopoulos, Vassilis; Mpardis, George; Loumos, Vassili

2009-01-01

In this paper, a dropout prediction method for e-learning courses, based on three popular machine learning techniques and detailed student data, is proposed. The machine learning techniques used are feed-forward neural networks, support vector machines and probabilistic ensemble simplified fuzzy ARTMAP. Since a single technique may fail to…

Comparison of different methods for gender estimation from face image of various poses

NASA Astrophysics Data System (ADS)

Ishii, Yohei; Hongo, Hitoshi; Niwa, Yoshinori; Yamamoto, Kazuhiko

2003-04-01

Recently, gender estimation from face images has been studied for frontal facial images. However, it is difficult to obtain such facial images constantly in the case of application systems for security, surveillance and marketing research. In order to build such systems, a method is required to estimate gender from the image of various facial poses. In this paper, three different classifiers are compared in appearance-based gender estimation, which use four directional features (FDF). The classifiers are linear discriminant analysis (LDA), Support Vector Machines (SVMs) and Sparse Network of Winnows (SNoW). Face images used for experiments were obtained from 35 viewpoints. The direction of viewpoints varied +/-45 degrees horizontally, +/-30 degrees vertically at 15 degree intervals respectively. Although LDA showed the best performance for frontal facial images, SVM with Gaussian kernel was found the best performance (86.0%) for the facial images of 35 viewpoints. It is considered that SVM with Gaussian kernel is robust to changes in viewpoint when estimating gender from these results. Furthermore, the estimation rate was quite close to the average estimation rate at 35 viewpoints respectively. It is supposed that the methods are reasonable to estimate gender within the range of experimented viewpoints by learning face images from multiple directions by one class.

Discrete element method as an approach to model the wheat milling process

USDA-ARS?s Scientific Manuscript database

It is a well-known phenomenon that break-release, particle size, and size distribution of wheat milling are functions of machine operational parameters and grain properties. Due to the non-uniformity of characteristics and properties of wheat kernels, the kernel physical and mechanical properties af...

Evaluation of Multiple Kernel Learning Algorithms for Crop Mapping Using Satellite Image Time-Series Data

NASA Astrophysics Data System (ADS)

Niazmardi, S.; Safari, A.; Homayouni, S.

2017-09-01

Crop mapping through classification of Satellite Image Time-Series (SITS) data can provide very valuable information for several agricultural applications, such as crop monitoring, yield estimation, and crop inventory. However, the SITS data classification is not straightforward. Because different images of a SITS data have different levels of information regarding the classification problems. Moreover, the SITS data is a four-dimensional data that cannot be classified using the conventional classification algorithms. To address these issues in this paper, we presented a classification strategy based on Multiple Kernel Learning (MKL) algorithms for SITS data classification. In this strategy, initially different kernels are constructed from different images of the SITS data and then they are combined into a composite kernel using the MKL algorithms. The composite kernel, once constructed, can be used for the classification of the data using the kernel-based classification algorithms. We compared the computational time and the classification performances of the proposed classification strategy using different MKL algorithms for the purpose of crop mapping. The considered MKL algorithms are: MKL-Sum, SimpleMKL, LPMKL and Group-Lasso MKL algorithms. The experimental tests of the proposed strategy on two SITS data sets, acquired by SPOT satellite sensors, showed that this strategy was able to provide better performances when compared to the standard classification algorithm. The results also showed that the optimization method of the used MKL algorithms affects both the computational time and classification accuracy of this strategy.

Ensemble support vector machine classification of dementia using structural MRI and mini-mental state examination.

PubMed

Sørensen, Lauge; Nielsen, Mads

2018-05-15

The International Challenge for Automated Prediction of MCI from MRI data offered independent, standardized comparison of machine learning algorithms for multi-class classification of normal control (NC), mild cognitive impairment (MCI), converting MCI (cMCI), and Alzheimer's disease (AD) using brain imaging and general cognition. We proposed to use an ensemble of support vector machines (SVMs) that combined bagging without replacement and feature selection. SVM is the most commonly used algorithm in multivariate classification of dementia, and it was therefore valuable to evaluate the potential benefit of ensembling this type of classifier. The ensemble SVM, using either a linear or a radial basis function (RBF) kernel, achieved multi-class classification accuracies of 55.6% and 55.0% in the challenge test set (60 NC, 60 MCI, 60 cMCI, 60 AD), resulting in a third place in the challenge. Similar feature subset sizes were obtained for both kernels, and the most frequently selected MRI features were the volumes of the two hippocampal subregions left presubiculum and right subiculum. Post-challenge analysis revealed that enforcing a minimum number of selected features and increasing the number of ensemble classifiers improved classification accuracy up to 59.1%. The ensemble SVM outperformed single SVM classifications consistently in the challenge test set. Ensemble methods using bagging and feature selection can improve the performance of the commonly applied SVM classifier in dementia classification. This resulted in competitive classification accuracies in the International Challenge for Automated Prediction of MCI from MRI data. Copyright © 2018 Elsevier B.V. All rights reserved.

An SVM-Based Solution for Fault Detection in Wind Turbines

PubMed Central

Santos, Pedro; Villa, Luisa F.; Reñones, Aníbal; Bustillo, Andres; Maudes, Jesús

2015-01-01

Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets. PMID:25760051

An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine

PubMed Central

Pettersson-Yeo, William; Benetti, Stefania; Marquand, Andre F.; Joules, Richard; Catani, Marco; Williams, Steve C. R.; Allen, Paul; McGuire, Philip; Mechelli, Andrea

2014-01-01

In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and (4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional, and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (n = 19), first episode psychosis (n = 19) and healthy control subjects (n = 23). Our results show that (i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, (ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, (iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no “magic bullet” for increasing classification accuracy. However, it remains possible that this conclusion is dependent on the use of neuroimaging modalities that had little, or no, complementary information to offer one another, and that the integration of more diverse types of data would have produced greater classification enhancement. We suggest that future studies ideally examine a greater variety of data types (e.g., genetic, cognitive, and neuroimaging) in order to identify the data types and combinations optimally suited to the classification of early stage psychosis. PMID:25076868

An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine.

PubMed

Pettersson-Yeo, William; Benetti, Stefania; Marquand, Andre F; Joules, Richard; Catani, Marco; Williams, Steve C R; Allen, Paul; McGuire, Philip; Mechelli, Andrea

2014-01-01

In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine, that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realized. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: (1) an un-weighted sum of kernels, (2) multi-kernel learning, (3) prediction averaging, and (4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional, and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (n = 19), first episode psychosis (n = 19) and healthy control subjects (n = 23). Our results show that (i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, (ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, (iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no "magic bullet" for increasing classification accuracy. However, it remains possible that this conclusion is dependent on the use of neuroimaging modalities that had little, or no, complementary information to offer one another, and that the integration of more diverse types of data would have produced greater classification enhancement. We suggest that future studies ideally examine a greater variety of data types (e.g., genetic, cognitive, and neuroimaging) in order to identify the data types and combinations optimally suited to the classification of early stage psychosis.

Sepsis mortality prediction with the Quotient Basis Kernel.

PubMed

Ribas Ripoll, Vicent J; Vellido, Alfredo; Romero, Enrique; Ruiz-Rodríguez, Juan Carlos

2014-05-01

This paper presents an algorithm to assess the risk of death in patients with sepsis. Sepsis is a common clinical syndrome in the intensive care unit (ICU) that can lead to severe sepsis, a severe state of septic shock or multi-organ failure. The proposed algorithm may be implemented as part of a clinical decision support system that can be used in combination with the scores deployed in the ICU to improve the accuracy, sensitivity and specificity of mortality prediction for patients with sepsis. In this paper, we used the Simplified Acute Physiology Score (SAPS) for ICU patients and the Sequential Organ Failure Assessment (SOFA) to build our kernels and algorithms. In the proposed method, we embed the available data in a suitable feature space and use algorithms based on linear algebra, geometry and statistics for inference. We present a simplified version of the Fisher kernel (practical Fisher kernel for multinomial distributions), as well as a novel kernel that we named the Quotient Basis Kernel (QBK). These kernels are used as the basis for mortality prediction using soft-margin support vector machines. The two new kernels presented are compared against other generative kernels based on the Jensen-Shannon metric (centred, exponential and inverse) and other widely used kernels (linear, polynomial and Gaussian). Clinical relevance is also evaluated by comparing these results with logistic regression and the standard clinical prediction method based on the initial SAPS score. As described in this paper, we tested the new methods via cross-validation with a cohort of 400 test patients. The results obtained using our methods compare favourably with those obtained using alternative kernels (80.18% accuracy for the QBK) and the standard clinical prediction method, which are based on the basal SAPS score or logistic regression (71.32% and 71.55%, respectively). The QBK presented a sensitivity and specificity of 79.34% and 83.24%, which outperformed the other kernels analysed, logistic regression and the standard clinical prediction method based on the basal SAPS score. Several scoring systems for patients with sepsis have been introduced and developed over the last 30 years. They allow for the assessment of the severity of disease and provide an estimate of in-hospital mortality. Physiology-based scoring systems are applied to critically ill patients and have a number of advantages over diagnosis-based systems. Severity score systems are often used to stratify critically ill patients for possible inclusion in clinical trials. In this paper, we present an effective algorithm that combines both scoring methodologies for the assessment of death in patients with sepsis that can be used to improve the sensitivity and specificity of the currently available methods. Copyright © 2014 Elsevier B.V. All rights reserved.

Support Vector Feature Selection for Early Detection of Anastomosis Leakage From Bag-of-Words in Electronic Health Records.

PubMed

Soguero-Ruiz, Cristina; Hindberg, Kristian; Rojo-Alvarez, Jose Luis; Skrovseth, Stein Olav; Godtliebsen, Fred; Mortensen, Kim; Revhaug, Arthur; Lindsetmo, Rolv-Ole; Augestad, Knut Magne; Jenssen, Robert

2016-09-01

The free text in electronic health records (EHRs) conveys a huge amount of clinical information about health state and patient history. Despite a rapidly growing literature on the use of machine learning techniques for extracting this information, little effort has been invested toward feature selection and the features' corresponding medical interpretation. In this study, we focus on the task of early detection of anastomosis leakage (AL), a severe complication after elective surgery for colorectal cancer (CRC) surgery, using free text extracted from EHRs. We use a bag-of-words model to investigate the potential for feature selection strategies. The purpose is earlier detection of AL and prediction of AL with data generated in the EHR before the actual complication occur. Due to the high dimensionality of the data, we derive feature selection strategies using the robust support vector machine linear maximum margin classifier, by investigating: 1) a simple statistical criterion (leave-one-out-based test); 2) an intensive-computation statistical criterion (Bootstrap resampling); and 3) an advanced statistical criterion (kernel entropy). Results reveal a discriminatory power for early detection of complications after CRC (sensitivity 100%; specificity 72%). These results can be used to develop prediction models, based on EHR data, that can support surgeons and patients in the preoperative decision making phase.

Comparative analysis of machine learning methods in ligand-based virtual screening of large compound libraries.

PubMed

Ma, Xiao H; Jia, Jia; Zhu, Feng; Xue, Ying; Li, Ze R; Chen, Yu Z

2009-05-01

Machine learning methods have been explored as ligand-based virtual screening tools for facilitating drug lead discovery. These methods predict compounds of specific pharmacodynamic, pharmacokinetic or toxicological properties based on their structure-derived structural and physicochemical properties. Increasing attention has been directed at these methods because of their capability in predicting compounds of diverse structures and complex structure-activity relationships without requiring the knowledge of target 3D structure. This article reviews current progresses in using machine learning methods for virtual screening of pharmacodynamically active compounds from large compound libraries, and analyzes and compares the reported performances of machine learning tools with those of structure-based and other ligand-based (such as pharmacophore and clustering) virtual screening methods. The feasibility to improve the performance of machine learning methods in screening large libraries is discussed.

Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics

NASA Astrophysics Data System (ADS)

Arsenault, Louis-François; Neuberg, Richard; Hannah, Lauren A.; Millis, Andrew J.

2017-11-01

We present a supervised machine learning approach to the inversion of Fredholm integrals of the first kind as they arise, for example, in the analytic continuation problem of quantum many-body physics. The approach provides a natural regularization for the ill-conditioned inverse of the Fredholm kernel, as well as an efficient and stable treatment of constraints. The key observation is that the stability of the forward problem permits the construction of a large database of outputs for physically meaningful inputs. Applying machine learning to this database generates a regression function of controlled complexity, which returns approximate solutions for previously unseen inputs; the approximate solutions are then projected onto the subspace of functions satisfying relevant constraints. Under standard error metrics the method performs as well or better than the Maximum Entropy method for low input noise and is substantially more robust to increased input noise. We suggest that the methodology will be similarly effective for other problems involving a formally ill-conditioned inversion of an integral operator, provided that the forward problem can be efficiently solved.

MO-G-17A-05: PET Image Deblurring Using Adaptive Dictionary Learning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Valiollahzadeh, S; Clark, J; Mawlawi, O

2014-06-15

Purpose: The aim of this work is to deblur PET images while suppressing Poisson noise effects using adaptive dictionary learning (DL) techniques. Methods: The model that relates a blurred and noisy PET image to the desired image is described as a linear transform y=Hm+n where m is the desired image, H is a blur kernel, n is Poisson noise and y is the blurred image. The approach we follow to recover m involves the sparse representation of y over a learned dictionary, since the image has lots of repeated patterns, edges, textures and smooth regions. The recovery is based onmore » an optimization of a cost function having four major terms: adaptive dictionary learning term, sparsity term, regularization term, and MLEM Poisson noise estimation term. The optimization is solved by a variable splitting method that introduces additional variables. We simulated a 128×128 Hoffman brain PET image (baseline) with varying kernel types and sizes (Gaussian 9×9, σ=5.4mm; Uniform 5×5, σ=2.9mm) with additive Poisson noise (Blurred). Image recovery was performed once when the kernel type was included in the model optimization and once with the model blinded to kernel type. The recovered image was compared to the baseline as well as another recovery algorithm PIDSPLIT+ (Setzer et. al.) by calculating PSNR (Peak SNR) and normalized average differences in pixel intensities (NADPI) of line profiles across the images. Results: For known kernel types, the PSNR of the Gaussian (Uniform) was 28.73 (25.1) and 25.18 (23.4) for DL and PIDSPLIT+ respectively. For blinded deblurring the PSNRs were 25.32 and 22.86 for DL and PIDSPLIT+ respectively. NADPI between baseline and DL, and baseline and blurred for the Gaussian kernel was 2.5 and 10.8 respectively. Conclusion: PET image deblurring using dictionary learning seems to be a good approach to restore image resolution in presence of Poisson noise. GE Health Care.« less

Protein Kinase Classification with 2866 Hidden Markov Models and One Support Vector Machine

NASA Technical Reports Server (NTRS)

Weber, Ryan; New, Michael H.; Fonda, Mark (Technical Monitor)

2002-01-01

The main application considered in this paper is predicting true kinases from randomly permuted kinases that share the same length and amino acid distributions as the true kinases. Numerous methods already exist for this classification task, such as HMMs, motif-matchers, and sequence comparison algorithms. We build on some of these efforts by creating a vector from the output of thousands of structurally based HMMs, created offline with Pfam-A seed alignments using SAM-T99, which then must be combined into an overall classification for the protein. Then we use a Support Vector Machine for classifying this large ensemble Pfam-Vector, with a polynomial and chisquared kernel. In particular, the chi-squared kernel SVM performs better than the HMMs and better than the BLAST pairwise comparisons, when predicting true from false kinases in some respects, but no one algorithm is best for all purposes or in all instances so we consider the particular strengths and weaknesses of each.

Predicting complex traits using a diffusion kernel on genetic markers with an application to dairy cattle and wheat data

PubMed Central

2013-01-01

Background Arguably, genotypes and phenotypes may be linked in functional forms that are not well addressed by the linear additive models that are standard in quantitative genetics. Therefore, developing statistical learning models for predicting phenotypic values from all available molecular information that are capable of capturing complex genetic network architectures is of great importance. Bayesian kernel ridge regression is a non-parametric prediction model proposed for this purpose. Its essence is to create a spatial distance-based relationship matrix called a kernel. Although the set of all single nucleotide polymorphism genotype configurations on which a model is built is finite, past research has mainly used a Gaussian kernel. Results We sought to investigate the performance of a diffusion kernel, which was specifically developed to model discrete marker inputs, using Holstein cattle and wheat data. This kernel can be viewed as a discretization of the Gaussian kernel. The predictive ability of the diffusion kernel was similar to that of non-spatial distance-based additive genomic relationship kernels in the Holstein data, but outperformed the latter in the wheat data. However, the difference in performance between the diffusion and Gaussian kernels was negligible. Conclusions It is concluded that the ability of a diffusion kernel to capture the total genetic variance is not better than that of a Gaussian kernel, at least for these data. Although the diffusion kernel as a choice of basis function may have potential for use in whole-genome prediction, our results imply that embedding genetic markers into a non-Euclidean metric space has very small impact on prediction. Our results suggest that use of the black box Gaussian kernel is justified, given its connection to the diffusion kernel and its similar predictive performance. PMID:23763755

Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection.

PubMed

Zeng, Xueqiang; Luo, Gang

2017-12-01

Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.

Local Kernel for Brains Classification in Schizophrenia

NASA Astrophysics Data System (ADS)

Castellani, U.; Rossato, E.; Murino, V.; Bellani, M.; Rambaldelli, G.; Tansella, M.; Brambilla, P.

In this paper a novel framework for brain classification is proposed in the context of mental health research. A learning by example method is introduced by combining local measurements with non linear Support Vector Machine. Instead of considering a voxel-by-voxel comparison between patients and controls, we focus on landmark points which are characterized by local region descriptors, namely Scale Invariance Feature Transform (SIFT). Then, matching is obtained by introducing the local kernel for which the samples are represented by unordered set of features. Moreover, a new weighting approach is proposed to take into account the discriminative relevance of the detected groups of features. Experiments have been performed including a set of 54 patients with schizophrenia and 54 normal controls on which region of interest (ROI) have been manually traced by experts. Preliminary results on Dorso-lateral PreFrontal Cortex (DLPFC) region are promising since up to 75% of successful classification rate has been obtained with this technique and the performance has improved up to 85% when the subjects have been stratified by sex.

Kernel Recursive Least-Squares Temporal Difference Algorithms with Sparsification and Regularization

PubMed Central

Zhu, Qingxin; Niu, Xinzheng

2016-01-01

By combining with sparse kernel methods, least-squares temporal difference (LSTD) algorithms can construct the feature dictionary automatically and obtain a better generalization ability. However, the previous kernel-based LSTD algorithms do not consider regularization and their sparsification processes are batch or offline, which hinder their widespread applications in online learning problems. In this paper, we combine the following five techniques and propose two novel kernel recursive LSTD algorithms: (i) online sparsification, which can cope with unknown state regions and be used for online learning, (ii) L 2 and L 1 regularization, which can avoid overfitting and eliminate the influence of noise, (iii) recursive least squares, which can eliminate matrix-inversion operations and reduce computational complexity, (iv) a sliding-window approach, which can avoid caching all history samples and reduce the computational cost, and (v) the fixed-point subiteration and online pruning, which can make L 1 regularization easy to implement. Finally, simulation results on two 50-state chain problems demonstrate the effectiveness of our algorithms. PMID:27436996

Kernel Recursive Least-Squares Temporal Difference Algorithms with Sparsification and Regularization.

PubMed

Zhang, Chunyuan; Zhu, Qingxin; Niu, Xinzheng

2016-01-01

By combining with sparse kernel methods, least-squares temporal difference (LSTD) algorithms can construct the feature dictionary automatically and obtain a better generalization ability. However, the previous kernel-based LSTD algorithms do not consider regularization and their sparsification processes are batch or offline, which hinder their widespread applications in online learning problems. In this paper, we combine the following five techniques and propose two novel kernel recursive LSTD algorithms: (i) online sparsification, which can cope with unknown state regions and be used for online learning, (ii) L 2 and L 1 regularization, which can avoid overfitting and eliminate the influence of noise, (iii) recursive least squares, which can eliminate matrix-inversion operations and reduce computational complexity, (iv) a sliding-window approach, which can avoid caching all history samples and reduce the computational cost, and (v) the fixed-point subiteration and online pruning, which can make L 1 regularization easy to implement. Finally, simulation results on two 50-state chain problems demonstrate the effectiveness of our algorithms.

Adaptive learning in complex reproducing kernel Hilbert spaces employing Wirtinger's subgradients.

PubMed

Bouboulis, Pantelis; Slavakis, Konstantinos; Theodoridis, Sergios

2012-03-01

This paper presents a wide framework for non-linear online supervised learning tasks in the context of complex valued signal processing. The (complex) input data are mapped into a complex reproducing kernel Hilbert space (RKHS), where the learning phase is taking place. Both pure complex kernels and real kernels (via the complexification trick) can be employed. Moreover, any convex, continuous and not necessarily differentiable function can be used to measure the loss between the output of the specific system and the desired response. The only requirement is the subgradient of the adopted loss function to be available in an analytic form. In order to derive analytically the subgradients, the principles of the (recently developed) Wirtinger's calculus in complex RKHS are exploited. Furthermore, both linear and widely linear (in RKHS) estimation filters are considered. To cope with the problem of increasing memory requirements, which is present in almost all online schemes in RKHS, the sparsification scheme, based on projection onto closed balls, has been adopted. We demonstrate the effectiveness of the proposed framework in a non-linear channel identification task, a non-linear channel equalization problem and a quadrature phase shift keying equalization scheme, using both circular and non circular synthetic signal sources.

A kernel adaptive algorithm for quaternion-valued inputs.

PubMed

Paul, Thomas K; Ogunfunmi, Tokunbo

2015-10-01

The use of quaternion data can provide benefit in applications like robotics and image recognition, and particularly for performing transforms in 3-D space. Here, we describe a kernel adaptive algorithm for quaternions. A least mean square (LMS)-based method was used, resulting in the derivation of the quaternion kernel LMS (Quat-KLMS) algorithm. Deriving this algorithm required describing the idea of a quaternion reproducing kernel Hilbert space (RKHS), as well as kernel functions suitable with quaternions. A modified HR calculus for Hilbert spaces was used to find the gradient of cost functions defined on a quaternion RKHS. In addition, the use of widely linear (or augmented) filtering is proposed to improve performance. The benefit of the Quat-KLMS and widely linear forms in learning nonlinear transformations of quaternion data are illustrated with simulations.

Bio-inspired adaptive feedback error learning architecture for motor control.

PubMed

Tolu, Silvia; Vanegas, Mauricio; Luque, Niceto R; Garrido, Jesús A; Ros, Eduardo

2012-10-01

This study proposes an adaptive control architecture based on an accurate regression method called Locally Weighted Projection Regression (LWPR) and on a bio-inspired module, such as a cerebellar-like engine. This hybrid architecture takes full advantage of the machine learning module (LWPR kernel) to abstract an optimized representation of the sensorimotor space while the cerebellar component integrates this to generate corrective terms in the framework of a control task. Furthermore, we illustrate how the use of a simple adaptive error feedback term allows to use the proposed architecture even in the absence of an accurate analytic reference model. The presented approach achieves an accurate control with low gain corrective terms (for compliant control schemes). We evaluate the contribution of the different components of the proposed scheme comparing the obtained performance with alternative approaches. Then, we show that the presented architecture can be used for accurate manipulation of different objects when their physical properties are not directly known by the controller. We evaluate how the scheme scales for simulated plants of high Degrees of Freedom (7-DOFs).

Graph wavelet alignment kernels for drug virtual screening.

PubMed

Smalter, Aaron; Huan, Jun; Lushington, Gerald

2009-06-01

In this paper, we introduce a novel statistical modeling technique for target property prediction, with applications to virtual screening and drug design. In our method, we use graphs to model chemical structures and apply a wavelet analysis of graphs to summarize features capturing graph local topology. We design a novel graph kernel function to utilize the topology features to build predictive models for chemicals via Support Vector Machine classifier. We call the new graph kernel a graph wavelet-alignment kernel. We have evaluated the efficacy of the wavelet-alignment kernel using a set of chemical structure-activity prediction benchmarks. Our results indicate that the use of the kernel function yields performance profiles comparable to, and sometimes exceeding that of the existing state-of-the-art chemical classification approaches. In addition, our results also show that the use of wavelet functions significantly decreases the computational costs for graph kernel computation with more than ten fold speedup.

An acceleration framework for synthetic aperture radar algorithms

NASA Astrophysics Data System (ADS)

Kim, Youngsoo; Gloster, Clay S.; Alexander, Winser E.

2017-04-01

Algorithms for radar signal processing, such as Synthetic Aperture Radar (SAR) are computationally intensive and require considerable execution time on a general purpose processor. Reconfigurable logic can be used to off-load the primary computational kernel onto a custom computing machine in order to reduce execution time by an order of magnitude as compared to kernel execution on a general purpose processor. Specifically, Field Programmable Gate Arrays (FPGAs) can be used to accelerate these kernels using hardware-based custom logic implementations. In this paper, we demonstrate a framework for algorithm acceleration. We used SAR as a case study to illustrate the potential for algorithm acceleration offered by FPGAs. Initially, we profiled the SAR algorithm and implemented a homomorphic filter using a hardware implementation of the natural logarithm. Experimental results show a linear speedup by adding reasonably small processing elements in Field Programmable Gate Array (FPGA) as opposed to using a software implementation running on a typical general purpose processor.

Prediction of clinical depression scores and detection of changes in whole-brain using resting-state functional MRI data with partial least squares regression

PubMed Central

Shimizu, Yu; Yoshimoto, Junichiro; Takamura, Masahiro; Okada, Go; Okamoto, Yasumasa; Yamawaki, Shigeto; Doya, Kenji

2017-01-01

In diagnostic applications of statistical machine learning methods to brain imaging data, common problems include data high-dimensionality and co-linearity, which often cause over-fitting and instability. To overcome these problems, we applied partial least squares (PLS) regression to resting-state functional magnetic resonance imaging (rs-fMRI) data, creating a low-dimensional representation that relates symptoms to brain activity and that predicts clinical measures. Our experimental results, based upon data from clinically depressed patients and healthy controls, demonstrated that PLS and its kernel variants provided significantly better prediction of clinical measures than ordinary linear regression. Subsequent classification using predicted clinical scores distinguished depressed patients from healthy controls with 80% accuracy. Moreover, loading vectors for latent variables enabled us to identify brain regions relevant to depression, including the default mode network, the right superior frontal gyrus, and the superior motor area. PMID:28700672

Machine Learning and Radiology

PubMed Central

Wang, Shijun; Summers, Ronald M.

2012-01-01

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers. PMID:22465077

Automated detection of heart ailments from 12-lead ECG using complex wavelet sub-band bi-spectrum features

PubMed Central

Dandapat, Samarendra

2017-01-01

The complex wavelet sub-band bi-spectrum (CWSB) features are proposed for detection and classification of myocardial infarction (MI), heart muscle disease (HMD) and bundle branch block (BBB) from 12-lead ECG. The dual tree CW transform of 12-lead ECG produces CW coefficients at different sub-bands. The higher-order CW analysis is used for evaluation of CWSB. The mean of the absolute value of CWSB, and the number of negative phase angle and the number of positive phase angle features from the phase of CWSB of 12-lead ECG are evaluated. Extreme learning machine and support vector machine (SVM) classifiers are used to evaluate the performance of CWSB features. Experimental results show that the proposed CWSB features of 12-lead ECG and the SVM classifier are successful for classification of various heart pathologies. The individual accuracy values for MI, HMD and BBB classes are obtained as 98.37, 97.39 and 96.40%, respectively, using SVM classifier and radial basis function kernel function. A comparison has also been made with existing 12-lead ECG-based cardiac disease detection techniques. PMID:28894589

Efficient and Privacy-Preserving Online Medical Prediagnosis Framework Using Nonlinear SVM.

PubMed

Zhu, Hui; Liu, Xiaoxia; Lu, Rongxing; Li, Hui

2017-05-01

With the advances of machine learning algorithms and the pervasiveness of network terminals, the online medical prediagnosis system, which can provide the diagnosis of healthcare provider anywhere anytime, has attracted considerable interest recently. However, the flourish of online medical prediagnosis system still faces many challenges including information security and privacy preservation. In this paper, we propose an e fficient and privacy-preserving online medical prediagnosis framework, called eDiag, by using nonlinear kernel support vector machine (SVM). With eDiag, the sensitive personal health information can be processed without privacy disclosure during online prediagnosis service. Specifically, based on an improved expression for the nonlinear SVM, an efficient and privacy-preserving classification scheme is introduced with lightweight multiparty random masking and polynomial aggregation techniques. The encrypted user query is directly operated at the service provider without decryption, and the diagnosis result can only be decrypted by user. Through extensive analysis, we show that eDiag can ensure that users' health information and healthcare provider's prediction model are kept confidential, and has significantly less computation and communication overhead than existing schemes. In addition, performance evaluations via implementing eDiag on smartphone and computer demonstrate eDiag's effectiveness in term of real online environment.

A Machine Learning Approach to the Detection of Pilot's Reaction to Unexpected Events Based on EEG Signals

PubMed Central

Cyran, Krzysztof A.

2018-01-01

This work considers the problem of utilizing electroencephalographic signals for use in systems designed for monitoring and enhancing the performance of aircraft pilots. Systems with such capabilities are generally referred to as cognitive cockpits. This article provides a description of the potential that is carried by such systems, especially in terms of increasing flight safety. Additionally, a neuropsychological background of the problem is presented. Conducted research was focused mainly on the problem of discrimination between states of brain activity related to idle but focused anticipation of visual cue and reaction to it. Especially, a problem of selecting a proper classification algorithm for such problems is being examined. For that purpose an experiment involving 10 subjects was planned and conducted. Experimental electroencephalographic data was acquired using an Emotiv EPOC+ headset. Proposed methodology involved use of a popular method in biomedical signal processing, the Common Spatial Pattern, extraction of bandpower features, and an extensive test of different classification algorithms, such as Linear Discriminant Analysis, k-nearest neighbors, and Support Vector Machines with linear and radial basis function kernels, Random Forests, and Artificial Neural Networks. PMID:29849544

The effects of pre-processing strategies in sentiment analysis of online movie reviews

NASA Astrophysics Data System (ADS)

Zin, Harnani Mat; Mustapha, Norwati; Murad, Masrah Azrifah Azmi; Sharef, Nurfadhlina Mohd

2017-10-01

With the ever increasing of internet applications and social networking sites, people nowadays can easily express their feelings towards any products and services. These online reviews act as an important source for further analysis and improved decision making. These reviews are mostly unstructured by nature and thus, need processing like sentiment analysis and classification to provide a meaningful information for future uses. In text analysis tasks, the appropriate selection of words/features will have a huge impact on the effectiveness of the classifier. Thus, this paper explores the effect of the pre-processing strategies in the sentiment analysis of online movie reviews. In this paper, supervised machine learning method was used to classify the reviews. The support vector machine (SVM) with linear and non-linear kernel has been considered as classifier for the classification of the reviews. The performance of the classifier is critically examined based on the results of precision, recall, f-measure, and accuracy. Two different features representations were used which are term frequency and term frequency-inverse document frequency. Results show that the pre-processing strategies give a significant impact on the classification process.

Constant size descriptors for accurate machine learning models of molecular properties

NASA Astrophysics Data System (ADS)

Collins, Christopher R.; Gordon, Geoffrey J.; von Lilienfeld, O. Anatole; Yaron, David J.

2018-06-01

Two different classes of molecular representations for use in machine learning of thermodynamic and electronic properties are studied. The representations are evaluated by monitoring the performance of linear and kernel ridge regression models on well-studied data sets of small organic molecules. One class of representations studied here counts the occurrence of bonding patterns in the molecule. These require only the connectivity of atoms in the molecule as may be obtained from a line diagram or a SMILES string. The second class utilizes the three-dimensional structure of the molecule. These include the Coulomb matrix and Bag of Bonds, which list the inter-atomic distances present in the molecule, and Encoded Bonds, which encode such lists into a feature vector whose length is independent of molecular size. Encoded Bonds' features introduced here have the advantage of leading to models that may be trained on smaller molecules and then used successfully on larger molecules. A wide range of feature sets are constructed by selecting, at each rank, either a graph or geometry-based feature. Here, rank refers to the number of atoms involved in the feature, e.g., atom counts are rank 1, while Encoded Bonds are rank 2. For atomization energies in the QM7 data set, the best graph-based feature set gives a mean absolute error of 3.4 kcal/mol. Inclusion of 3D geometry substantially enhances the performance, with Encoded Bonds giving 2.4 kcal/mol, when used alone, and 1.19 kcal/mol, when combined with graph features.

Large Scale Processes and Extreme Floods in Brazil

NASA Astrophysics Data System (ADS)

Ribeiro Lima, C. H.; AghaKouchak, A.; Lall, U.

2016-12-01

Persistent large scale anomalies in the atmospheric circulation and ocean state have been associated with heavy rainfall and extreme floods in water basins of different sizes across the world. Such studies have emerged in the last years as a new tool to improve the traditional, stationary based approach in flood frequency analysis and flood prediction. Here we seek to advance previous studies by evaluating the dominance of large scale processes (e.g. atmospheric rivers/moisture transport) over local processes (e.g. local convection) in producing floods. We consider flood-prone regions in Brazil as case studies and the role of large scale climate processes in generating extreme floods in such regions is explored by means of observed streamflow, reanalysis data and machine learning methods. The dynamics of the large scale atmospheric circulation in the days prior to the flood events are evaluated based on the vertically integrated moisture flux and its divergence field, which are interpreted in a low-dimensional space as obtained by machine learning techniques, particularly supervised kernel principal component analysis. In such reduced dimensional space, clusters are obtained in order to better understand the role of regional moisture recycling or teleconnected moisture in producing floods of a given magnitude. The convective available potential energy (CAPE) is also used as a measure of local convection activities. We investigate for individual sites the exceedance probability in which large scale atmospheric fluxes dominate the flood process. Finally, we analyze regional patterns of floods and how the scaling law of floods with drainage area responds to changes in the climate forcing mechanisms (e.g. local vs large scale).

A Fast Multiple-Kernel Method With Applications to Detect Gene-Environment Interaction.

PubMed

Marceau, Rachel; Lu, Wenbin; Holloway, Shannon; Sale, Michèle M; Worrall, Bradford B; Williams, Stephen R; Hsu, Fang-Chi; Tzeng, Jung-Ying

2015-09-01

Kernel machine (KM) models are a powerful tool for exploring associations between sets of genetic variants and complex traits. Although most KM methods use a single kernel function to assess the marginal effect of a variable set, KM analyses involving multiple kernels have become increasingly popular. Multikernel analysis allows researchers to study more complex problems, such as assessing gene-gene or gene-environment interactions, incorporating variance-component based methods for population substructure into rare-variant association testing, and assessing the conditional effects of a variable set adjusting for other variable sets. The KM framework is robust, powerful, and provides efficient dimension reduction for multifactor analyses, but requires the estimation of high dimensional nuisance parameters. Traditional estimation techniques, including regularization and the "expectation-maximization (EM)" algorithm, have a large computational cost and are not scalable to large sample sizes needed for rare variant analysis. Therefore, under the context of gene-environment interaction, we propose a computationally efficient and statistically rigorous "fastKM" algorithm for multikernel analysis that is based on a low-rank approximation to the nuisance effect kernel matrices. Our algorithm is applicable to various trait types (e.g., continuous, binary, and survival traits) and can be implemented using any existing single-kernel analysis software. Through extensive simulation studies, we show that our algorithm has similar performance to an EM-based KM approach for quantitative traits while running much faster. We also apply our method to the Vitamin Intervention for Stroke Prevention (VISP) clinical trial, examining gene-by-vitamin effects on recurrent stroke risk and gene-by-age effects on change in homocysteine level. © 2015 WILEY PERIODICALS, INC.

Gaussian processes with optimal kernel construction for neuro-degenerative clinical onset prediction

NASA Astrophysics Data System (ADS)

Canas, Liane S.; Yvernault, Benjamin; Cash, David M.; Molteni, Erika; Veale, Tom; Benzinger, Tammie; Ourselin, Sébastien; Mead, Simon; Modat, Marc

2018-02-01

Gaussian Processes (GP) are a powerful tool to capture the complex time-variations of a dataset. In the context of medical imaging analysis, they allow a robust modelling even in case of highly uncertain or incomplete datasets. Predictions from GP are dependent of the covariance kernel function selected to explain the data variance. To overcome this limitation, we propose a framework to identify the optimal covariance kernel function to model the data.The optimal kernel is defined as a composition of base kernel functions used to identify correlation patterns between data points. Our approach includes a modified version of the Compositional Kernel Learning (CKL) algorithm, in which we score the kernel families using a new energy function that depends both the Bayesian Information Criterion (BIC) and the explained variance score. We applied the proposed framework to model the progression of neurodegenerative diseases over time, in particular the progression of autosomal dominantly-inherited Alzheimer's disease, and use it to predict the time to clinical onset of subjects carrying genetic mutation.

Hybrid approach of selecting hyperparameters of support vector machine for regression.

PubMed

Jeng, Jin-Tsong

2006-06-01

To select the hyperparameters of the support vector machine for regression (SVR), a hybrid approach is proposed to determine the kernel parameter of the Gaussian kernel function and the epsilon value of Vapnik's epsilon-insensitive loss function. The proposed hybrid approach includes a competitive agglomeration (CA) clustering algorithm and a repeated SVR (RSVR) approach. Since the CA clustering algorithm is used to find the nearly "optimal" number of clusters and the centers of clusters in the clustering process, the CA clustering algorithm is applied to select the Gaussian kernel parameter. Additionally, an RSVR approach that relies on the standard deviation of a training error is proposed to obtain an epsilon in the loss function. Finally, two functions, one real data set (i.e., a time series of quarterly unemployment rate for West Germany) and an identification of nonlinear plant are used to verify the usefulness of the hybrid approach.

Customer demand prediction of service-oriented manufacturing using the least square support vector machine optimized by particle swarm optimization algorithm

NASA Astrophysics Data System (ADS)

Cao, Jin; Jiang, Zhibin; Wang, Kangzhou

2017-07-01

Many nonlinear customer satisfaction-related factors significantly influence the future customer demand for service-oriented manufacturing (SOM). To address this issue and enhance the prediction accuracy, this article develops a novel customer demand prediction approach for SOM. The approach combines the phase space reconstruction (PSR) technique with the optimized least square support vector machine (LSSVM). First, the prediction sample space is reconstructed by the PSR to enrich the time-series dynamics of the limited data sample. Then, the generalization and learning ability of the LSSVM are improved by the hybrid polynomial and radial basis function kernel. Finally, the key parameters of the LSSVM are optimized by the particle swarm optimization algorithm. In a real case study, the customer demand prediction of an air conditioner compressor is implemented. Furthermore, the effectiveness and validity of the proposed approach are demonstrated by comparison with other classical predication approaches.

Single image super-resolution based on convolutional neural networks

NASA Astrophysics Data System (ADS)

Zou, Lamei; Luo, Ming; Yang, Weidong; Li, Peng; Jin, Liujia

2018-03-01

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

Logic Learning Machine and standard supervised methods for Hodgkin's lymphoma prognosis using gene expression data and clinical variables.

PubMed

Parodi, Stefano; Manneschi, Chiara; Verda, Damiano; Ferrari, Enrico; Muselli, Marco

2018-03-01

This study evaluates the performance of a set of machine learning techniques in predicting the prognosis of Hodgkin's lymphoma using clinical factors and gene expression data. Analysed samples from 130 Hodgkin's lymphoma patients included a small set of clinical variables and more than 54,000 gene features. Machine learning classifiers included three black-box algorithms ( k-nearest neighbour, Artificial Neural Network, and Support Vector Machine) and two methods based on intelligible rules (Decision Tree and the innovative Logic Learning Machine method). Support Vector Machine clearly outperformed any of the other methods. Among the two rule-based algorithms, Logic Learning Machine performed better and identified a set of simple intelligible rules based on a combination of clinical variables and gene expressions. Decision Tree identified a non-coding gene ( XIST) involved in the early phases of X chromosome inactivation that was overexpressed in females and in non-relapsed patients. XIST expression might be responsible for the better prognosis of female Hodgkin's lymphoma patients.

[Study on application of SVM in prediction of coronary heart disease].

PubMed

Zhu, Yue; Wu, Jianghua; Fang, Ying

2013-12-01

Base on the data of blood pressure, plasma lipid, Glu and UA by physical test, Support Vector Machine (SVM) was applied to identify coronary heart disease (CHD) in patients and non-CHD individuals in south China population for guide of further prevention and treatment of the disease. Firstly, the SVM classifier was built using radial basis kernel function, liner kernel function and polynomial kernel function, respectively. Secondly, the SVM penalty factor C and kernel parameter sigma were optimized by particle swarm optimization (PSO) and then employed to diagnose and predict the CHD. By comparison with those from artificial neural network with the back propagation (BP) model, linear discriminant analysis, logistic regression method and non-optimized SVM, the overall results of our calculation demonstrated that the classification performance of optimized RBF-SVM model could be superior to other classifier algorithm with higher accuracy rate, sensitivity and specificity, which were 94.51%, 92.31% and 96.67%, respectively. So, it is well concluded that SVM could be used as a valid method for assisting diagnosis of CHD.

GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China

NASA Astrophysics Data System (ADS)

Xu, Chong; Dai, Fuchu; Xu, Xiwei; Lee, Yuan Hsi

2012-04-01

Support vector machine (SVM) modeling is based on statistical learning theory. It involves a training phase with associated input and target output values. In recent years, the method has become increasingly popular. The main purpose of this study is to evaluate the mapping power of SVM modeling in earthquake triggered landslide-susceptibility mapping for a section of the Jianjiang River watershed using a Geographic Information System (GIS) software. The river was affected by the Wenchuan earthquake of May 12, 2008. Visual interpretation of colored aerial photographs of 1-m resolution and extensive field surveys provided a detailed landslide inventory map containing 3147 landslides related to the 2008 Wenchuan earthquake. Elevation, slope angle, slope aspect, distance from seismogenic faults, distance from drainages, and lithology were used as the controlling parameters. For modeling, three groups of positive and negative training samples were used in concert with four different kernel functions. Positive training samples include the centroids of 500 large landslides, those of all 3147 landslides, and 5000 randomly selected points in landslide polygons. Negative training samples include 500, 3147, and 5000 randomly selected points on slopes that remained stable during the Wenchuan earthquake. The four kernel functions are linear, polynomial, radial basis, and sigmoid. In total, 12 cases of landslide susceptibility were mapped. Comparative analyses of landslide-susceptibility probability and area relation curves show that both the polynomial and radial basis functions suitably classified the input data as either landslide positive or negative though the radial basis function was more successful. The 12 generated landslide-susceptibility maps were compared with known landslide centroid locations and landslide polygons to verify the success rate and predictive accuracy of each model. The 12 results were further validated using area-under-curve analysis. Group 3 with 5000 randomly selected points on the landslide polygons, and 5000 randomly selected points along stable slopes gave the best results with a success rate of 79.20% and predictive accuracy of 79.13% under the radial basis function. Of all the results, the sigmoid kernel function was the least skillful when used in concert with the centroid data of all 3147 landslides as positive training samples, and the negative training samples of 3147 randomly selected points in regions of stable slope (success rate = 54.95%; predictive accuracy = 61.85%). This paper also provides suggestions and reference data for selecting appropriate training samples and kernel function types for earthquake triggered landslide-susceptibility mapping using SVM modeling. Predictive landslide-susceptibility maps could be useful in hazard mitigation by helping planners understand the probability of landslides in different regions.

Learning Machine, Vietnamese Based Human-Computer Interface.

ERIC Educational Resources Information Center

Northwest Regional Educational Lab., Portland, OR.

The sixth session of IT@EDU98 consisted of seven papers on the topic of the learning machine--Vietnamese based human-computer interface, and was chaired by Phan Viet Hoang (Informatics College, Singapore). "Knowledge Based Approach for English Vietnamese Machine Translation" (Hoang Kiem, Dinh Dien) presents the knowledge base approach,…

Predicting plant protein subcellular multi-localization by Chou's PseAAC formulation based multi-label homolog knowledge transfer learning.

PubMed

Mei, Suyu

2012-10-07

Recent years have witnessed much progress in computational modeling for protein subcellular localization. However, there are far few computational models for predicting plant protein subcellular multi-localization. In this paper, we propose a multi-label multi-kernel transfer learning model for predicting multiple subcellular locations of plant proteins (MLMK-TLM). The method proposes a multi-label confusion matrix and adapts one-against-all multi-class probabilistic outputs to multi-label learning scenario, based on which we further extend our published work MK-TLM (multi-kernel transfer learning based on Chou's PseAAC formulation for protein submitochondria localization) for plant protein subcellular multi-localization. By proper homolog knowledge transfer, MLMK-TLM is applicable to novel plant protein subcellular localization in multi-label learning scenario. The experiments on plant protein benchmark dataset show that MLMK-TLM outperforms the baseline model. Unlike the existing models, MLMK-TLM also reports its misleading tendency, which is important for comprehensive survey of model's multi-labeling performance. Copyright © 2012 Elsevier Ltd. All rights reserved.

Machine Learning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chikkagoudar, Satish; Chatterjee, Samrat; Thomas, Dennis G.

The absence of a robust and unified theory of cyber dynamics presents challenges and opportunities for using machine learning based data-driven approaches to further the understanding of the behavior of such complex systems. Analysts can also use machine learning approaches to gain operational insights. In order to be operationally beneficial, cybersecurity machine learning based models need to have the ability to: (1) represent a real-world system, (2) infer system properties, and (3) learn and adapt based on expert knowledge and observations. Probabilistic models and Probabilistic graphical models provide these necessary properties and are further explored in this chapter. Bayesian Networksmore » and Hidden Markov Models are introduced as an example of a widely used data driven classification/modeling strategy.« less

Characterization of groups using composite kernels and multi-source fMRI analysis data: application to schizophrenia

PubMed Central

Castro, Eduardo; Martínez-Ramón, Manel; Pearlson, Godfrey; Sui, Jing; Calhoun, Vince D.

2011-01-01

Pattern classification of brain imaging data can enable the automatic detection of differences in cognitive processes of specific groups of interest. Furthermore, it can also give neuroanatomical information related to the regions of the brain that are most relevant to detect these differences by means of feature selection procedures, which are also well-suited to deal with the high dimensionality of brain imaging data. This work proposes the application of recursive feature elimination using a machine learning algorithm based on composite kernels to the classification of healthy controls and patients with schizophrenia. This framework, which evaluates nonlinear relationships between voxels, analyzes whole-brain fMRI data from an auditory task experiment that is segmented into anatomical regions and recursively eliminates the uninformative ones based on their relevance estimates, thus yielding the set of most discriminative brain areas for group classification. The collected data was processed using two analysis methods: the general linear model (GLM) and independent component analysis (ICA). GLM spatial maps as well as ICA temporal lobe and default mode component maps were then input to the classifier. A mean classification accuracy of up to 95% estimated with a leave-two-out cross-validation procedure was achieved by doing multi-source data classification. In addition, it is shown that the classification accuracy rate obtained by using multi-source data surpasses that reached by using single-source data, hence showing that this algorithm takes advantage of the complimentary nature of GLM and ICA. PMID:21723948

A machine vision system for high speed sorting of small spots on grains

USDA-ARS?s Scientific Manuscript database

A sorting system was developed to detect and remove individual grain kernels with small localized blemishes or defects. The system uses a color VGA sensor to capture images of the kernels at high speed as the grain drops off an inclined chute. The image data are directly input into a field-programma...

Semi-supervised learning for ordinal Kernel Discriminant Analysis.

PubMed

Pérez-Ortiz, M; Gutiérrez, P A; Carbonero-Ruz, M; Hervás-Martínez, C

2016-12-01

Ordinal classification considers those classification problems where the labels of the variable to predict follow a given order. Naturally, labelled data is scarce or difficult to obtain in this type of problems because, in many cases, ordinal labels are given by a user or expert (e.g. in recommendation systems). Firstly, this paper develops a new strategy for ordinal classification where both labelled and unlabelled data are used in the model construction step (a scheme which is referred to as semi-supervised learning). More specifically, the ordinal version of kernel discriminant learning is extended for this setting considering the neighbourhood information of unlabelled data, which is proposed to be computed in the feature space induced by the kernel function. Secondly, a new method for semi-supervised kernel learning is devised in the context of ordinal classification, which is combined with our developed classification strategy to optimise the kernel parameters. The experiments conducted compare 6 different approaches for semi-supervised learning in the context of ordinal classification in a battery of 30 datasets, showing (1) the good synergy of the ordinal version of discriminant analysis and the use of unlabelled data and (2) the advantage of computing distances in the feature space induced by the kernel function. Copyright © 2016 Elsevier Ltd. All rights reserved.

Machine learning and radiology.

PubMed

Wang, Shijun; Summers, Ronald M

2012-07-01

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers. Copyright © 2012. Published by Elsevier B.V.

Characterizing cartilage microarchitecture on phase-contrast x-ray computed tomography using deep learning with convolutional neural networks

NASA Astrophysics Data System (ADS)

Deng, Botao; Abidin, Anas Z.; D'Souza, Adora M.; Nagarajan, Mahesh B.; Coan, Paola; Wismüller, Axel

2017-03-01

The effectiveness of phase contrast X-ray computed tomography (PCI-CT) in visualizing human patellar cartilage matrix has been demonstrated due to its ability to capture soft tissue contrast on a micrometer resolution scale. Recent studies have shown that off-the-shelf Convolutional Neural Network (CNN) features learned from a nonmedical data set can be used for medical image classification. In this paper, we investigate the ability of features extracted from two different CNNs for characterizing chondrocyte patterns in the cartilage matrix. We obtained features from 842 regions of interest annotated on PCI-CT images of human patellar cartilage using CaffeNet and Inception-v3 Network, which were then used in a machine learning task involving support vector machines with radial basis function kernel to classify the ROIs as healthy or osteoarthritic. Classification performance was evaluated using the area (AUC) under the Receiver Operating Characteristic (ROC) curve. The best classification performance was observed with features from Inception-v3 network (AUC = 0.95), which outperforms features extracted from CaffeNet (AUC = 0.91). These results suggest that such characterization of chondrocyte patterns using features from internal layers of CNNs can be used to distinguish between healthy and osteoarthritic tissue with high accuracy.

Prediction of drug synergy in cancer using ensemble-based machine learning techniques

NASA Astrophysics Data System (ADS)

Singh, Harpreet; Rana, Prashant Singh; Singh, Urvinder

2018-04-01

Drug synergy prediction plays a significant role in the medical field for inhibiting specific cancer agents. It can be developed as a pre-processing tool for therapeutic successes. Examination of different drug-drug interaction can be done by drug synergy score. It needs efficient regression-based machine learning approaches to minimize the prediction errors. Numerous machine learning techniques such as neural networks, support vector machines, random forests, LASSO, Elastic Nets, etc., have been used in the past to realize requirement as mentioned above. However, these techniques individually do not provide significant accuracy in drug synergy score. Therefore, the primary objective of this paper is to design a neuro-fuzzy-based ensembling approach. To achieve this, nine well-known machine learning techniques have been implemented by considering the drug synergy data. Based on the accuracy of each model, four techniques with high accuracy are selected to develop ensemble-based machine learning model. These models are Random forest, Fuzzy Rules Using Genetic Cooperative-Competitive Learning method (GFS.GCCL), Adaptive-Network-Based Fuzzy Inference System (ANFIS) and Dynamic Evolving Neural-Fuzzy Inference System method (DENFIS). Ensembling is achieved by evaluating the biased weighted aggregation (i.e. adding more weights to the model with a higher prediction score) of predicted data by selected models. The proposed and existing machine learning techniques have been evaluated on drug synergy score data. The comparative analysis reveals that the proposed method outperforms others in terms of accuracy, root mean square error and coefficient of correlation.

Combination of mass spectrometry-based targeted lipidomics and supervised machine learning algorithms in detecting adulterated admixtures of white rice.

PubMed

Lim, Dong Kyu; Long, Nguyen Phuoc; Mo, Changyeun; Dong, Ziyuan; Cui, Lingmei; Kim, Giyoung; Kwon, Sung Won

2017-10-01

The mixing of extraneous ingredients with original products is a common adulteration practice in food and herbal medicines. In particular, authenticity of white rice and its corresponding blended products has become a key issue in food industry. Accordingly, our current study aimed to develop and evaluate a novel discrimination method by combining targeted lipidomics with powerful supervised learning methods, and eventually introduce a platform to verify the authenticity of white rice. A total of 30 cultivars were collected, and 330 representative samples of white rice from Korea and China as well as seven mixing ratios were examined. Random forests (RF), support vector machines (SVM) with a radial basis function kernel, C5.0, model averaged neural network, and k-nearest neighbor classifiers were used for the classification. We achieved desired results, and the classifiers effectively differentiated white rice from Korea to blended samples with high prediction accuracy for the contamination ratio as low as five percent. In addition, RF and SVM classifiers were generally superior to and more robust than the other techniques. Our approach demonstrated that the relative differences in lysoGPLs can be successfully utilized to detect the adulterated mixing of white rice originating from different countries. In conclusion, the present study introduces a novel and high-throughput platform that can be applied to authenticate adulterated admixtures from original white rice samples. Copyright © 2017 Elsevier Ltd. All rights reserved.

Optimization of fixture layouts of glass laser optics using multiple kernel regression.

PubMed

Su, Jianhua; Cao, Enhua; Qiao, Hong

2014-05-10

We aim to build an integrated fixturing model to describe the structural properties and thermal properties of the support frame of glass laser optics. Therefore, (a) a near global optimal set of clamps can be computed to minimize the surface shape error of the glass laser optic based on the proposed model, and (b) a desired surface shape error can be obtained by adjusting the clamping forces under various environmental temperatures based on the model. To construct the model, we develop a new multiple kernel learning method and call it multiple kernel support vector functional regression. The proposed method uses two layer regressions to group and order the data sources by the weights of the kernels and the factors of the layers. Because of that, the influences of the clamps and the temperature can be evaluated by grouping them into different layers.

Risk Classification with an Adaptive Naive Bayes Kernel Machine Model.

PubMed

Minnier, Jessica; Yuan, Ming; Liu, Jun S; Cai, Tianxi

2015-04-22

Genetic studies of complex traits have uncovered only a small number of risk markers explaining a small fraction of heritability and adding little improvement to disease risk prediction. Standard single marker methods may lack power in selecting informative markers or estimating effects. Most existing methods also typically do not account for non-linearity. Identifying markers with weak signals and estimating their joint effects among many non-informative markers remains challenging. One potential approach is to group markers based on biological knowledge such as gene structure. If markers in a group tend to have similar effects, proper usage of the group structure could improve power and efficiency in estimation. We propose a two-stage method relating markers to disease risk by taking advantage of known gene-set structures. Imposing a naive bayes kernel machine (KM) model, we estimate gene-set specific risk models that relate each gene-set to the outcome in stage I. The KM framework efficiently models potentially non-linear effects of predictors without requiring explicit specification of functional forms. In stage II, we aggregate information across gene-sets via a regularization procedure. Estimation and computational efficiency is further improved with kernel principle component analysis. Asymptotic results for model estimation and gene set selection are derived and numerical studies suggest that the proposed procedure could outperform existing procedures for constructing genetic risk models.

Confidence Preserving Machine for Facial Action Unit Detection

PubMed Central

Zeng, Jiabei; Chu, Wen-Sheng; De la Torre, Fernando; Cohn, Jeffrey F.; Xiong, Zhang

2016-01-01

Facial action unit (AU) detection from video has been a long-standing problem in automated facial expression analysis. While progress has been made, accurate detection of facial AUs remains challenging due to ubiquitous sources of errors, such as inter-personal variability, pose, and low-intensity AUs. In this paper, we refer to samples causing such errors as hard samples, and the remaining as easy samples. To address learning with the hard samples, we propose the Confidence Preserving Machine (CPM), a novel two-stage learning framework that combines multiple classifiers following an “easy-to-hard” strategy. During the training stage, CPM learns two confident classifiers. Each classifier focuses on separating easy samples of one class from all else, and thus preserves confidence on predicting each class. During the testing stage, the confident classifiers provide “virtual labels” for easy test samples. Given the virtual labels, we propose a quasi-semi-supervised (QSS) learning strategy to learn a person-specific (PS) classifier. The QSS strategy employs a spatio-temporal smoothness that encourages similar predictions for samples within a spatio-temporal neighborhood. In addition, to further improve detection performance, we introduce two CPM extensions: iCPM that iteratively augments training samples to train the confident classifiers, and kCPM that kernelizes the original CPM model to promote nonlinearity. Experiments on four spontaneous datasets GFT [15], BP4D [56], DISFA [42], and RU-FACS [3] illustrate the benefits of the proposed CPM models over baseline methods and state-of-the-art semisupervised learning and transfer learning methods. PMID:27479964

Structured Kernel Dictionary Learning with Correlation Constraint for Object Recognition.

PubMed

Wang, Zhengjue; Wang, Yinghua; Liu, Hongwei; Zhang, Hao

2017-06-21

In this paper, we propose a new discriminative non-linear dictionary learning approach, called correlation constrained structured kernel KSVD, for object recognition. The objective function for dictionary learning contains a reconstructive term and a discriminative term. In the reconstructive term, signals are implicitly non-linearly mapped into a space, where a structured kernel dictionary, each sub-dictionary of which lies in the span of the mapped signals from the corresponding class, is established. In the discriminative term, by analyzing the classification mechanism, the correlation constraint is proposed in kernel form, constraining the correlations between different discriminative codes, and restricting the coefficient vectors to be transformed into a feature space, where the features are highly correlated inner-class and nearly independent between-classes. The objective function is optimized by the proposed structured kernel KSVD. During the classification stage, the specific form of the discriminative feature is needless to be known, while the inner product of the discriminative feature with kernel matrix embedded is available, and is suitable for a linear SVM classifier. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art dictionary learning approaches for face, scene and synthetic aperture radar (SAR) vehicle target recognition.

DRREP: deep ridge regressed epitope predictor.

PubMed

Sher, Gene; Zhi, Degui; Zhang, Shaojie

2017-10-03

The ability to predict epitopes plays an enormous role in vaccine development in terms of our ability to zero in on where to do a more thorough in-vivo analysis of the protein in question. Though for the past decade there have been numerous advancements and improvements in epitope prediction, on average the best benchmark prediction accuracies are still only around 60%. New machine learning algorithms have arisen within the domain of deep learning, text mining, and convolutional networks. This paper presents a novel analytically trained and string kernel using deep neural network, which is tailored for continuous epitope prediction, called: Deep Ridge Regressed Epitope Predictor (DRREP). DRREP was tested on long protein sequences from the following datasets: SARS, Pellequer, HIV, AntiJen, and SEQ194. DRREP was compared to numerous state of the art epitope predictors, including the most recently published predictors called LBtope and DMNLBE. Using area under ROC curve (AUC), DRREP achieved a performance improvement over the best performing predictors on SARS (13.7%), HIV (8.9%), Pellequer (1.5%), and SEQ194 (3.1%), with its performance being matched only on the AntiJen dataset, by the LBtope predictor, where both DRREP and LBtope achieved an AUC of 0.702. DRREP is an analytically trained deep neural network, thus capable of learning in a single step through regression. By combining the features of deep learning, string kernels, and convolutional networks, the system is able to perform residue-by-residue prediction of continues epitopes with higher accuracy than the current state of the art predictors.

A Tensor-Product-Kernel Framework for Multiscale Neural Activity Decoding and Control

PubMed Central

Li, Lin; Brockmeier, Austin J.; Choi, John S.; Francis, Joseph T.; Sanchez, Justin C.; Príncipe, José C.

2014-01-01

Brain machine interfaces (BMIs) have attracted intense attention as a promising technology for directly interfacing computers or prostheses with the brain's motor and sensory areas, thereby bypassing the body. The availability of multiscale neural recordings including spike trains and local field potentials (LFPs) brings potential opportunities to enhance computational modeling by enriching the characterization of the neural system state. However, heterogeneity on data type (spike timing versus continuous amplitude signals) and spatiotemporal scale complicates the model integration of multiscale neural activity. In this paper, we propose a tensor-product-kernel-based framework to integrate the multiscale activity and exploit the complementary information available in multiscale neural activity. This provides a common mathematical framework for incorporating signals from different domains. The approach is applied to the problem of neural decoding and control. For neural decoding, the framework is able to identify the nonlinear functional relationship between the multiscale neural responses and the stimuli using general purpose kernel adaptive filtering. In a sensory stimulation experiment, the tensor-product-kernel decoder outperforms decoders that use only a single neural data type. In addition, an adaptive inverse controller for delivering electrical microstimulation patterns that utilizes the tensor-product kernel achieves promising results in emulating the responses to natural stimulation. PMID:24829569

High-Grade Serous Ovarian Cancer: Use of Machine Learning to Predict Abdominopelvic Recurrence on CT on the Basis of Serial Cancer Antigen 125 Levels.

PubMed

Shinagare, Atul B; Balthazar, Patricia; Ip, Ivan K; Lacson, Ronilda; Liu, Joyce; Ramaiya, Nikhil; Khorasani, Ramin

2018-05-19

The aim of this study was to use machine learning to predict abdominal recurrence on CT on the basis of serial cancer antigen 125 (CA125) levels in patients with advanced high-grade serous ovarian cancer on surveillance. This institutional review board-approved, HIPAA-compliant, retrospective, hypothesis-generating study included all 57 patients (mean age, 61 ± 11.2 years) with advanced high-grade serous ovarian cancer who underwent cytoreductive surgery from January to December 2012, followed by surveillance abdominopelvic CT and corresponding CA125 levels. A blinded radiologist reviewed abdominopelvic CT studies until recurrence was noted. Four measures of CA125 were assessed: actual CA125 levels at the time of CT, absolute change since prior CT, relative change since prior CT, and rate of change since prior CT. Using machine learning, support vector machine models were optimized and evaluated using 10-fold cross-validation to determine the CA125 measure most predictive of abdominal recurrence. The association of the most accurate CA125 measure was further analyzed using Cox proportional-hazards model along with age, tumor size, stage, and degree of cytoreduction. Rate of change in CA125 was most predictive of abdominal recurrence in a linear kernel support vector machine model and was significantly higher preceding CT studies showing abdominal recurrence (median 13.2 versus 0.6 units/month; P = .007). On multivariate analysis, a higher rate of CA125 increase was significantly associated with recurrence (hazard ratio, 1.02 per 10 units change; 95% confidence interval, 1.0006-1.04; P = .04). A higher rate of CA125 increase is associated with abdominal recurrence. The rate of increase of CA125 may help in the selection of patients who are most likely to benefit from abdominopelvic CT in surveillance of ovarian cancer. Copyright © 2018 American College of Radiology. Published by Elsevier Inc. All rights reserved.

Automatic plankton image classification combining multiple view features via multiple kernel learning.

PubMed

Zheng, Haiyong; Wang, Ruchen; Yu, Zhibin; Wang, Nan; Gu, Zhaorui; Zheng, Bing

2017-12-28

Plankton, including phytoplankton and zooplankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, plankton is very sensitive to environment changes, and the study of plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoplankton to zooplankton. The experimental results validated that our system outperforms state-of-the-art plankton image classification systems in terms of accuracy and robustness. This study demonstrated automatic plankton image classification system combining multiple view features using multiple kernel learning. The results indicated that multiple view features combined by NLMKL using three kernel functions (linear, polynomial and Gaussian kernel functions) can describe and use information of features better so that achieve a higher classification accuracy.

Machine Learning Applications to Resting-State Functional MR Imaging Analysis.

PubMed

Billings, John M; Eder, Maxwell; Flood, William C; Dhami, Devendra Singh; Natarajan, Sriraam; Whitlow, Christopher T

2017-11-01

Machine learning is one of the most exciting and rapidly expanding fields within computer science. Academic and commercial research entities are investing in machine learning methods, especially in personalized medicine via patient-level classification. There is great promise that machine learning methods combined with resting state functional MR imaging will aid in diagnosis of disease and guide potential treatment for conditions thought to be impossible to identify based on imaging alone, such as psychiatric disorders. We discuss machine learning methods and explore recent advances. Copyright © 2017 Elsevier Inc. All rights reserved.

Optimal algorithm for automatic detection of microaneurysms based on receiver operating characteristic curve

NASA Astrophysics Data System (ADS)

Xu, Lili; Luo, Shuqian

2010-11-01

Microaneurysms (MAs) are the first manifestations of the diabetic retinopathy (DR) as well as an indicator for its progression. Their automatic detection plays a key role for both mass screening and monitoring and is therefore in the core of any system for computer-assisted diagnosis of DR. The algorithm basically comprises the following stages: candidate detection aiming at extracting the patterns possibly corresponding to MAs based on mathematical morphological black top hat, feature extraction to characterize these candidates, and classification based on support vector machine (SVM), to validate MAs. Feature vector and kernel function of SVM selection is very important to the algorithm. We use the receiver operating characteristic (ROC) curve to evaluate the distinguishing performance of different feature vectors and different kernel functions of SVM. The ROC analysis indicates the quadratic polynomial SVM with a combination of features as the input shows the best discriminating performance.

Optimal algorithm for automatic detection of microaneurysms based on receiver operating characteristic curve.

PubMed

Xu, Lili; Luo, Shuqian

2010-01-01

Microaneurysms (MAs) are the first manifestations of the diabetic retinopathy (DR) as well as an indicator for its progression. Their automatic detection plays a key role for both mass screening and monitoring and is therefore in the core of any system for computer-assisted diagnosis of DR. The algorithm basically comprises the following stages: candidate detection aiming at extracting the patterns possibly corresponding to MAs based on mathematical morphological black top hat, feature extraction to characterize these candidates, and classification based on support vector machine (SVM), to validate MAs. Feature vector and kernel function of SVM selection is very important to the algorithm. We use the receiver operating characteristic (ROC) curve to evaluate the distinguishing performance of different feature vectors and different kernel functions of SVM. The ROC analysis indicates the quadratic polynomial SVM with a combination of features as the input shows the best discriminating performance.

Game-powered machine learning

PubMed Central

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-01-01

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the “wisdom of the crowds.” Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., “funky jazz with saxophone,” “spooky electronica,” etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data. PMID:22460786

Game-powered machine learning.

PubMed

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-04-24

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders.

PubMed

Subasi, Abdulhamit

2013-06-01

Support vector machine (SVM) is an extensively used machine learning method with many biomedical signal classification applications. In this study, a novel PSO-SVM model has been proposed that hybridized the particle swarm optimization (PSO) and SVM to improve the EMG signal classification accuracy. This optimization mechanism involves kernel parameter setting in the SVM training procedure, which significantly influences the classification accuracy. The experiments were conducted on the basis of EMG signal to classify into normal, neurogenic or myopathic. In the proposed method the EMG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT) and a set of statistical features were extracted from these sub-bands to represent the distribution of wavelet coefficients. The obtained results obviously validate the superiority of the SVM method compared to conventional machine learning methods, and suggest that further significant enhancements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. The PSO-SVM yielded an overall accuracy of 97.41% on 1200 EMG signals selected from 27 subject records against 96.75%, 95.17% and 94.08% for the SVM, the k-NN and the RBF classifiers, respectively. PSO-SVM is developed as an efficient tool so that various SVMs can be used conveniently as the core of PSO-SVM for diagnosis of neuromuscular disorders. Copyright © 2013 Elsevier Ltd. All rights reserved.

Machine learning modelling for predicting soil liquefaction susceptibility

NASA Astrophysics Data System (ADS)

Samui, P.; Sitharam, T. G.

2011-01-01

This study describes two machine learning techniques applied to predict liquefaction susceptibility of soil based on the standard penetration test (SPT) data from the 1999 Chi-Chi, Taiwan earthquake. The first machine learning technique which uses Artificial Neural Network (ANN) based on multi-layer perceptions (MLP) that are trained with Levenberg-Marquardt backpropagation algorithm. The second machine learning technique uses the Support Vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses classification technique. ANN and SVM have been developed to predict liquefaction susceptibility using corrected SPT [(N1)60] and cyclic stress ratio (CSR). Further, an attempt has been made to simplify the models, requiring only the two parameters [(N1)60 and peck ground acceleration (amax/g)], for the prediction of liquefaction susceptibility. The developed ANN and SVM models have also been applied to different case histories available globally. The paper also highlights the capability of the SVM over the ANN models.

An efficient scheme for automatic web pages categorization using the support vector machine

NASA Astrophysics Data System (ADS)

Bhalla, Vinod Kumar; Kumar, Neeraj

2016-07-01

In the past few years, with an evolution of the Internet and related technologies, the number of the Internet users grows exponentially. These users demand access to relevant web pages from the Internet within fraction of seconds. To achieve this goal, there is a requirement of an efficient categorization of web page contents. Manual categorization of these billions of web pages to achieve high accuracy is a challenging task. Most of the existing techniques reported in the literature are semi-automatic. Using these techniques, higher level of accuracy cannot be achieved. To achieve these goals, this paper proposes an automatic web pages categorization into the domain category. The proposed scheme is based on the identification of specific and relevant features of the web pages. In the proposed scheme, first extraction and evaluation of features are done followed by filtering the feature set for categorization of domain web pages. A feature extraction tool based on the HTML document object model of the web page is developed in the proposed scheme. Feature extraction and weight assignment are based on the collection of domain-specific keyword list developed by considering various domain pages. Moreover, the keyword list is reduced on the basis of ids of keywords in keyword list. Also, stemming of keywords and tag text is done to achieve a higher accuracy. An extensive feature set is generated to develop a robust classification technique. The proposed scheme was evaluated using a machine learning method in combination with feature extraction and statistical analysis using support vector machine kernel as the classification tool. The results obtained confirm the effectiveness of the proposed scheme in terms of its accuracy in different categories of web pages.

Classification of cardiovascular tissues using LBP based descriptors and a cascade SVM.

PubMed

Mazo, Claudia; Alegre, Enrique; Trujillo, Maria

2017-08-01

Histological images have characteristics, such as texture, shape, colour and spatial structure, that permit the differentiation of each fundamental tissue and organ. Texture is one of the most discriminative features. The automatic classification of tissues and organs based on histology images is an open problem, due to the lack of automatic solutions when treating tissues without pathologies. In this paper, we demonstrate that it is possible to automatically classify cardiovascular tissues using texture information and Support Vector Machines (SVM). Additionally, we realised that it is feasible to recognise several cardiovascular organs following the same process. The texture of histological images was described using Local Binary Patterns (LBP), LBP Rotation Invariant (LBPri), Haralick features and different concatenations between them, representing in this way its content. Using a SVM with linear kernel, we selected the more appropriate descriptor that, for this problem, was a concatenation of LBP and LBPri. Due to the small number of the images available, we could not follow an approach based on deep learning, but we selected the classifier who yielded the higher performance by comparing SVM with Random Forest and Linear Discriminant Analysis. Once SVM was selected as the classifier with a higher area under the curve that represents both higher recall and precision, we tuned it evaluating different kernels, finding that a linear SVM allowed us to accurately separate four classes of tissues: (i) cardiac muscle of the heart, (ii) smooth muscle of the muscular artery, (iii) loose connective tissue, and (iv) smooth muscle of the large vein and the elastic artery. The experimental validation was conducted using 3000 blocks of 100 × 100 sized pixels, with 600 blocks per class and the classification was assessed using a 10-fold cross-validation. using LBP as the descriptor, concatenated with LBPri and a SVM with linear kernel, the main four classes of tissues were recognised with an AUC higher than 0.98. A polynomial kernel was then used to separate the elastic artery and vein, yielding an AUC in both cases superior to 0.98. Following the proposed approach, it is possible to separate with very high precision (AUC greater than 0.98) the fundamental tissues of the cardiovascular system along with some organs, such as the heart, arteries and veins. Copyright © 2017 Elsevier B.V. All rights reserved.

Model-based machine learning.

PubMed

Bishop, Christopher M

2013-02-13

Several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. To tackle a new application, a researcher typically tries to map their problem onto one of these existing methods, often influenced by their familiarity with specific algorithms and by the availability of corresponding software implementations. In this study, we describe an alternative methodology for applying machine learning, in which a bespoke solution is formulated for each new application. The solution is expressed through a compact modelling language, and the corresponding custom machine learning code is then generated automatically. This model-based approach offers several major advantages, including the opportunity to create highly tailored models for specific scenarios, as well as rapid prototyping and comparison of a range of alternative models. Furthermore, newcomers to the field of machine learning do not have to learn about the huge range of traditional methods, but instead can focus their attention on understanding a single modelling environment. In this study, we show how probabilistic graphical models, coupled with efficient inference algorithms, provide a very flexible foundation for model-based machine learning, and we outline a large-scale commercial application of this framework involving tens of millions of users. We also describe the concept of probabilistic programming as a powerful software environment for model-based machine learning, and we discuss a specific probabilistic programming language called Infer.NET, which has been widely used in practical applications.

Model-based machine learning

PubMed Central

Bishop, Christopher M.

2013-01-01

Several decades of research in the field of machine learning have resulted in a multitude of different algorithms for solving a broad range of problems. To tackle a new application, a researcher typically tries to map their problem onto one of these existing methods, often influenced by their familiarity with specific algorithms and by the availability of corresponding software implementations. In this study, we describe an alternative methodology for applying machine learning, in which a bespoke solution is formulated for each new application. The solution is expressed through a compact modelling language, and the corresponding custom machine learning code is then generated automatically. This model-based approach offers several major advantages, including the opportunity to create highly tailored models for specific scenarios, as well as rapid prototyping and comparison of a range of alternative models. Furthermore, newcomers to the field of machine learning do not have to learn about the huge range of traditional methods, but instead can focus their attention on understanding a single modelling environment. In this study, we show how probabilistic graphical models, coupled with efficient inference algorithms, provide a very flexible foundation for model-based machine learning, and we outline a large-scale commercial application of this framework involving tens of millions of users. We also describe the concept of probabilistic programming as a powerful software environment for model-based machine learning, and we discuss a specific probabilistic programming language called Infer.NET, which has been widely used in practical applications. PMID:23277612

Hybrid forecasting of chaotic processes: Using machine learning in conjunction with a knowledge-based model

NASA Astrophysics Data System (ADS)

Pathak, Jaideep; Wikner, Alexander; Fussell, Rebeckah; Chandra, Sarthak; Hunt, Brian R.; Girvan, Michelle; Ott, Edward

2018-04-01

A model-based approach to forecasting chaotic dynamical systems utilizes knowledge of the mechanistic processes governing the dynamics to build an approximate mathematical model of the system. In contrast, machine learning techniques have demonstrated promising results for forecasting chaotic systems purely from past time series measurements of system state variables (training data), without prior knowledge of the system dynamics. The motivation for this paper is the potential of machine learning for filling in the gaps in our underlying mechanistic knowledge that cause widely-used knowledge-based models to be inaccurate. Thus, we here propose a general method that leverages the advantages of these two approaches by combining a knowledge-based model and a machine learning technique to build a hybrid forecasting scheme. Potential applications for such an approach are numerous (e.g., improving weather forecasting). We demonstrate and test the utility of this approach using a particular illustrative version of a machine learning known as reservoir computing, and we apply the resulting hybrid forecaster to a low-dimensional chaotic system, as well as to a high-dimensional spatiotemporal chaotic system. These tests yield extremely promising results in that our hybrid technique is able to accurately predict for a much longer period of time than either its machine-learning component or its model-based component alone.

Machine-Learning Approach for Design of Nanomagnetic-Based Antennas

NASA Astrophysics Data System (ADS)

Gianfagna, Carmine; Yu, Huan; Swaminathan, Madhavan; Pulugurtha, Raj; Tummala, Rao; Antonini, Giulio

2017-08-01

We propose a machine-learning approach for design of planar inverted-F antennas with a magneto-dielectric nanocomposite substrate. It is shown that machine-learning techniques can be efficiently used to characterize nanomagnetic-based antennas by accurately mapping the particle radius and volume fraction of the nanomagnetic material to antenna parameters such as gain, bandwidth, radiation efficiency, and resonant frequency. A modified mixing rule model is also presented. In addition, the inverse problem is addressed through machine learning as well, where given the antenna parameters, the corresponding design space of possible material parameters is identified.

Oil point and mechanical behaviour of oil palm kernels in linear compression

NASA Astrophysics Data System (ADS)

Kabutey, Abraham; Herak, David; Choteborsky, Rostislav; Mizera, Čestmír; Sigalingging, Riswanti; Akangbe, Olaosebikan Layi

2017-07-01

The study described the oil point and mechanical properties of roasted and unroasted bulk oil palm kernels under compression loading. The literature information available is very limited. A universal compression testing machine and vessel diameter of 60 mm with a plunger were used by applying maximum force of 100 kN and speed ranging from 5 to 25 mm min-1. The initial pressing height of the bulk kernels was measured at 40 mm. The oil point was determined by a litmus test for each deformation level of 5, 10, 15, 20, and 25 mm at a minimum speed of 5 mmmin-1. The measured parameters were the deformation, deformation energy, oil yield, oil point strain and oil point pressure. Clearly, the roasted bulk kernels required less deformation energy compared to the unroasted kernels for recovering the kernel oil. However, both kernels were not permanently deformed. The average oil point strain was determined at 0.57. The study is an essential contribution to pursuing innovative methods for processing palm kernel oil in rural areas of developing countries.

Generalized multiple kernel learning with data-dependent priors.

PubMed

Mao, Qi; Tsang, Ivor W; Gao, Shenghua; Wang, Li

2015-06-01

Multiple kernel learning (MKL) and classifier ensemble are two mainstream methods for solving learning problems in which some sets of features/views are more informative than others, or the features/views within a given set are inconsistent. In this paper, we first present a novel probabilistic interpretation of MKL such that maximum entropy discrimination with a noninformative prior over multiple views is equivalent to the formulation of MKL. Instead of using the noninformative prior, we introduce a novel data-dependent prior based on an ensemble of kernel predictors, which enhances the prediction performance of MKL by leveraging the merits of the classifier ensemble. With the proposed probabilistic framework of MKL, we propose a hierarchical Bayesian model to learn the proposed data-dependent prior and classification model simultaneously. The resultant problem is convex and other information (e.g., instances with either missing views or missing labels) can be seamlessly incorporated into the data-dependent priors. Furthermore, a variety of existing MKL models can be recovered under the proposed MKL framework and can be readily extended to incorporate these priors. Extensive experiments demonstrate the benefits of our proposed framework in supervised and semisupervised settings, as well as in tasks with partial correspondence among multiple views.

Noninvasive prostate cancer screening based on serum surface-enhanced Raman spectroscopy and support vector machine

NASA Astrophysics Data System (ADS)

Li, Shaoxin; Zhang, Yanjiao; Xu, Junfa; Li, Linfang; Zeng, Qiuyao; Lin, Lin; Guo, Zhouyi; Liu, Zhiming; Xiong, Honglian; Liu, Songhao

2014-09-01

This study aims to present a noninvasive prostate cancer screening methods using serum surface-enhanced Raman scattering (SERS) and support vector machine (SVM) techniques through peripheral blood sample. SERS measurements are performed using serum samples from 93 prostate cancer patients and 68 healthy volunteers by silver nanoparticles. Three types of kernel functions including linear, polynomial, and Gaussian radial basis function (RBF) are employed to build SVM diagnostic models for classifying measured SERS spectra. For comparably evaluating the performance of SVM classification models, the standard multivariate statistic analysis method of principal component analysis (PCA) is also applied to classify the same datasets. The study results show that for the RBF kernel SVM diagnostic model, the diagnostic accuracy of 98.1% is acquired, which is superior to the results of 91.3% obtained from PCA methods. The receiver operating characteristic curve of diagnostic models further confirm above research results. This study demonstrates that label-free serum SERS analysis technique combined with SVM diagnostic algorithm has great potential for noninvasive prostate cancer screening.

Machine learning in cardiovascular medicine: are we there yet?

PubMed

Shameer, Khader; Johnson, Kipp W; Glicksberg, Benjamin S; Dudley, Joel T; Sengupta, Partho P

2018-01-19

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

Scuba: scalable kernel-based gene prioritization.

PubMed

Zampieri, Guido; Tran, Dinh Van; Donini, Michele; Navarin, Nicolò; Aiolli, Fabio; Sperduti, Alessandro; Valle, Giorgio

2018-01-25

The uncovering of genes linked to human diseases is a pressing challenge in molecular biology and precision medicine. This task is often hindered by the large number of candidate genes and by the heterogeneity of the available information. Computational methods for the prioritization of candidate genes can help to cope with these problems. In particular, kernel-based methods are a powerful resource for the integration of heterogeneous biological knowledge, however, their practical implementation is often precluded by their limited scalability. We propose Scuba, a scalable kernel-based method for gene prioritization. It implements a novel multiple kernel learning approach, based on a semi-supervised perspective and on the optimization of the margin distribution. Scuba is optimized to cope with strongly unbalanced settings where known disease genes are few and large scale predictions are required. Importantly, it is able to efficiently deal both with a large amount of candidate genes and with an arbitrary number of data sources. As a direct consequence of scalability, Scuba integrates also a new efficient strategy to select optimal kernel parameters for each data source. We performed cross-validation experiments and simulated a realistic usage setting, showing that Scuba outperforms a wide range of state-of-the-art methods. Scuba achieves state-of-the-art performance and has enhanced scalability compared to existing kernel-based approaches for genomic data. This method can be useful to prioritize candidate genes, particularly when their number is large or when input data is highly heterogeneous. The code is freely available at https://github.com/gzampieri/Scuba .

Integrating different data types by regularized unsupervised multiple kernel learning with application to cancer subtype discovery.

PubMed

Speicher, Nora K; Pfeifer, Nico

2015-06-15

Despite ongoing cancer research, available therapies are still limited in quantity and effectiveness, and making treatment decisions for individual patients remains a hard problem. Established subtypes, which help guide these decisions, are mainly based on individual data types. However, the analysis of multidimensional patient data involving the measurements of various molecular features could reveal intrinsic characteristics of the tumor. Large-scale projects accumulate this kind of data for various cancer types, but we still lack the computational methods to reliably integrate this information in a meaningful manner. Therefore, we apply and extend current multiple kernel learning for dimensionality reduction approaches. On the one hand, we add a regularization term to avoid overfitting during the optimization procedure, and on the other hand, we show that one can even use several kernels per data type and thereby alleviate the user from having to choose the best kernel functions and kernel parameters for each data type beforehand. We have identified biologically meaningful subgroups for five different cancer types. Survival analysis has revealed significant differences between the survival times of the identified subtypes, with P values comparable or even better than state-of-the-art methods. Moreover, our resulting subtypes reflect combined patterns from the different data sources, and we demonstrate that input kernel matrices with only little information have less impact on the integrated kernel matrix. Our subtypes show different responses to specific therapies, which could eventually assist in treatment decision making. An executable is available upon request. © The Author 2015. Published by Oxford University Press.

A Novel Local Learning based Approach With Application to Breast Cancer Diagnosis

DOE Office of Scientific and Technical Information (OSTI.GOV)

Xu, Songhua; Tourassi, Georgia

2012-01-01

The purpose of this study is to develop and evaluate a novel local learning-based approach for computer-assisted diagnosis of breast cancer. Our new local learning based algorithm using the linear logistic regression method as its base learner is described. Overall, our algorithm will perform its stochastic searching process until the total allowed computing time is used up by our random walk process in identifying the most suitable population subdivision scheme and their corresponding individual base learners. The proposed local learning-based approach was applied for the prediction of breast cancer given 11 mammographic and clinical findings reported by physicians using themore » BI-RADS lexicon. Our database consisted of 850 patients with biopsy confirmed diagnosis (290 malignant and 560 benign). We also compared the performance of our method with a collection of publicly available state-of-the-art machine learning methods. Predictive performance for all classifiers was evaluated using 10-fold cross validation and Receiver Operating Characteristics (ROC) analysis. Figure 1 reports the performance of 54 machine learning methods implemented in the machine learning toolkit Weka (version 3.0). We introduced a novel local learning-based classifier and compared it with an extensive list of other classifiers for the problem of breast cancer diagnosis. Our experiments show that the algorithm superior prediction performance outperforming a wide range of other well established machine learning techniques. Our conclusion complements the existing understanding in the machine learning field that local learning may capture complicated, non-linear relationships exhibited by real-world datasets.« less

A graph kernel approach for alignment-free domain-peptide interaction prediction with an application to human SH3 domains.

PubMed

Kundu, Kousik; Costa, Fabrizio; Backofen, Rolf

2013-07-01

State-of-the-art experimental data for determining binding specificities of peptide recognition modules (PRMs) is obtained by high-throughput approaches like peptide arrays. Most prediction tools applicable to this kind of data are based on an initial multiple alignment of the peptide ligands. Building an initial alignment can be error-prone, especially in the case of the proline-rich peptides bound by the SH3 domains. Here, we present a machine-learning approach based on an efficient graph-kernel technique to predict the specificity of a large set of 70 human SH3 domains, which are an important class of PRMs. The graph-kernel strategy allows us to (i) integrate several types of physico-chemical information for each amino acid, (ii) consider high-order correlations between these features and (iii) eliminate the need for an initial peptide alignment. We build specialized models for each human SH3 domain and achieve competitive predictive performance of 0.73 area under precision-recall curve, compared with 0.27 area under precision-recall curve for state-of-the-art methods based on position weight matrices. We show that better models can be obtained when we use information on the noninteracting peptides (negative examples), which is currently not used by the state-of-the art approaches based on position weight matrices. To this end, we analyze two strategies to identify subsets of high confidence negative data. The techniques introduced here are more general and hence can also be used for any other protein domains, which interact with short peptides (i.e. other PRMs). The program with the predictive models can be found at http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/SH3PepInt.tar.gz. We also provide a genome-wide prediction for all 70 human SH3 domains, which can be found under http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/Genome-Wide-Predictions.tar.gz. Supplementary data are available at Bioinformatics online.

A graph kernel approach for alignment-free domain–peptide interaction prediction with an application to human SH3 domains

PubMed Central

Kundu, Kousik; Costa, Fabrizio; Backofen, Rolf

2013-01-01

Motivation: State-of-the-art experimental data for determining binding specificities of peptide recognition modules (PRMs) is obtained by high-throughput approaches like peptide arrays. Most prediction tools applicable to this kind of data are based on an initial multiple alignment of the peptide ligands. Building an initial alignment can be error-prone, especially in the case of the proline-rich peptides bound by the SH3 domains. Results: Here, we present a machine-learning approach based on an efficient graph-kernel technique to predict the specificity of a large set of 70 human SH3 domains, which are an important class of PRMs. The graph-kernel strategy allows us to (i) integrate several types of physico-chemical information for each amino acid, (ii) consider high-order correlations between these features and (iii) eliminate the need for an initial peptide alignment. We build specialized models for each human SH3 domain and achieve competitive predictive performance of 0.73 area under precision-recall curve, compared with 0.27 area under precision-recall curve for state-of-the-art methods based on position weight matrices. We show that better models can be obtained when we use information on the noninteracting peptides (negative examples), which is currently not used by the state-of-the art approaches based on position weight matrices. To this end, we analyze two strategies to identify subsets of high confidence negative data. The techniques introduced here are more general and hence can also be used for any other protein domains, which interact with short peptides (i.e. other PRMs). Availability: The program with the predictive models can be found at http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/SH3PepInt.tar.gz. We also provide a genome-wide prediction for all 70 human SH3 domains, which can be found under http://www.bioinf.uni-freiburg.de/Software/SH3PepInt/Genome-Wide-Predictions.tar.gz. Contact: backofen@informatik.uni-freiburg.de Supplementary information: Supplementary data are available at Bioinformatics online. PMID:23813002

Investigating the Impact of a LEGO(TM)-Based, Engineering-Oriented Curriculum Compared to an Inquiry-Based Curriculum on Fifth Graders' Content Learning of Simple Machines

ERIC Educational Resources Information Center

Marulcu, Ismail

2010-01-01

This mixed method study examined the impact of a LEGO-based, engineering-oriented curriculum compared to an inquiry-based curriculum on fifth graders' content learning of simple machines. This study takes a social constructivist theoretical stance that science learning involves learning scientific concepts and their relations to each other. From…

Automation of energy demand forecasting

NASA Astrophysics Data System (ADS)

Siddique, Sanzad

Automation of energy demand forecasting saves time and effort by searching automatically for an appropriate model in a candidate model space without manual intervention. This thesis introduces a search-based approach that improves the performance of the model searching process for econometrics models. Further improvements in the accuracy of the energy demand forecasting are achieved by integrating nonlinear transformations within the models. This thesis introduces machine learning techniques that are capable of modeling such nonlinearity. Algorithms for learning domain knowledge from time series data using the machine learning methods are also presented. The novel search based approach and the machine learning models are tested with synthetic data as well as with natural gas and electricity demand signals. Experimental results show that the model searching technique is capable of finding an appropriate forecasting model. Further experimental results demonstrate an improved forecasting accuracy achieved by using the novel machine learning techniques introduced in this thesis. This thesis presents an analysis of how the machine learning techniques learn domain knowledge. The learned domain knowledge is used to improve the forecast accuracy.

Quantum neural network based machine translator for Hindi to English.

PubMed

Narayan, Ravi; Singh, V P; Chakraverty, S

2014-01-01

This paper presents the machine learning based machine translation system for Hindi to English, which learns the semantically correct corpus. The quantum neural based pattern recognizer is used to recognize and learn the pattern of corpus, using the information of part of speech of individual word in the corpus, like a human. The system performs the machine translation using its knowledge gained during the learning by inputting the pair of sentences of Devnagri-Hindi and English. To analyze the effectiveness of the proposed approach, 2600 sentences have been evaluated during simulation and evaluation. The accuracy achieved on BLEU score is 0.7502, on NIST score is 6.5773, on ROUGE-L score is 0.9233, and on METEOR score is 0.5456, which is significantly higher in comparison with Google Translation and Bing Translation for Hindi to English Machine Translation.

Data-Driven Hierarchical Structure Kernel for Multiscale Part-Based Object Recognition

PubMed Central

Wang, Botao; Xiong, Hongkai; Jiang, Xiaoqian; Zheng, Yuan F.

2017-01-01

Detecting generic object categories in images and videos are a fundamental issue in computer vision. However, it faces the challenges from inter and intraclass diversity, as well as distortions caused by viewpoints, poses, deformations, and so on. To solve object variations, this paper constructs a structure kernel and proposes a multiscale part-based model incorporating the discriminative power of kernels. The structure kernel would measure the resemblance of part-based objects in three aspects: 1) the global similarity term to measure the resemblance of the global visual appearance of relevant objects; 2) the part similarity term to measure the resemblance of the visual appearance of distinctive parts; and 3) the spatial similarity term to measure the resemblance of the spatial layout of parts. In essence, the deformation of parts in the structure kernel is penalized in a multiscale space with respect to horizontal displacement, vertical displacement, and scale difference. Part similarities are combined with different weights, which are optimized efficiently to maximize the intraclass similarities and minimize the interclass similarities by the normalized stochastic gradient ascent algorithm. In addition, the parameters of the structure kernel are learned during the training process with regard to the distribution of the data in a more discriminative way. With flexible part sizes on scale and displacement, it can be more robust to the intraclass variations, poses, and viewpoints. Theoretical analysis and experimental evaluations demonstrate that the proposed multiscale part-based representation model with structure kernel exhibits accurate and robust performance, and outperforms state-of-the-art object classification approaches. PMID:24808345

Thutmose - Investigation of Machine Learning-Based Intrusion Detection Systems

DTIC Science & Technology

2016-06-01

research is being done to incorporate the field of machine learning into intrusion detection. Machine learning is a branch of artificial intelligence (AI...adversarial drift." Proceedings of the 2013 ACM workshop on Artificial intelligence and security. ACM. (2013) Kantarcioglu, M., Xi, B., and Clifton, C. "A...34 Proceedings of the 4th ACM workshop on Security and artificial intelligence . ACM. (2011) Dua, S., and Du, X. Data Mining and Machine Learning in

Regularized Embedded Multiple Kernel Dimensionality Reduction for Mine Signal Processing.

PubMed

Li, Shuang; Liu, Bing; Zhang, Chen

2016-01-01

Traditional multiple kernel dimensionality reduction models are generally based on graph embedding and manifold assumption. But such assumption might be invalid for some high-dimensional or sparse data due to the curse of dimensionality, which has a negative influence on the performance of multiple kernel learning. In addition, some models might be ill-posed if the rank of matrices in their objective functions was not high enough. To address these issues, we extend the traditional graph embedding framework and propose a novel regularized embedded multiple kernel dimensionality reduction method. Different from the conventional convex relaxation technique, the proposed algorithm directly takes advantage of a binary search and an alternative optimization scheme to obtain optimal solutions efficiently. The experimental results demonstrate the effectiveness of the proposed method for supervised, unsupervised, and semisupervised scenarios.

Testing in Microbiome-Profiling Studies with MiRKAT, the Microbiome Regression-Based Kernel Association Test

PubMed Central

Zhao, Ni; Chen, Jun; Carroll, Ian M.; Ringel-Kulka, Tamar; Epstein, Michael P.; Zhou, Hua; Zhou, Jin J.; Ringel, Yehuda; Li, Hongzhe; Wu, Michael C.

2015-01-01

High-throughput sequencing technology has enabled population-based studies of the role of the human microbiome in disease etiology and exposure response. Distance-based analysis is a popular strategy for evaluating the overall association between microbiome diversity and outcome, wherein the phylogenetic distance between individuals’ microbiome profiles is computed and tested for association via permutation. Despite their practical popularity, distance-based approaches suffer from important challenges, especially in selecting the best distance and extending the methods to alternative outcomes, such as survival outcomes. We propose the microbiome regression-based kernel association test (MiRKAT), which directly regresses the outcome on the microbiome profiles via the semi-parametric kernel machine regression framework. MiRKAT allows for easy covariate adjustment and extension to alternative outcomes while non-parametrically modeling the microbiome through a kernel that incorporates phylogenetic distance. It uses a variance-component score statistic to test for the association with analytical p value calculation. The model also allows simultaneous examination of multiple distances, alleviating the problem of choosing the best distance. Our simulations demonstrated that MiRKAT provides correctly controlled type I error and adequate power in detecting overall association. “Optimal” MiRKAT, which considers multiple candidate distances, is robust in that it suffers from little power loss in comparison to when the best distance is used and can achieve tremendous power gain in comparison to when a poor distance is chosen. Finally, we applied MiRKAT to real microbiome datasets to show that microbial communities are associated with smoking and with fecal protease levels after confounders are controlled for. PMID:25957468

Real Time Linux - The RTOS for Astronomy?

NASA Astrophysics Data System (ADS)

Daly, P. N.

The BoF was attended by about 30 participants and a free CD of real time Linux-based upon RedHat 5.2-was available. There was a detailed presentation on the nature of real time Linux and the variants for hard real time: New Mexico Tech's RTL and DIAPM's RTAI. Comparison tables between standard Linux and real time Linux responses to time interval generation and interrupt response latency were presented (see elsewhere in these proceedings). The present recommendations are to use RTL for UP machines running the 2.0.x kernels and RTAI for SMP machines running the 2.2.x kernel. Support, both academically and commercially, is available. Some known limitations were presented and the solutions reported e.g., debugging and hardware support. The features of RTAI (scheduler, fifos, shared memory, semaphores, message queues and RPCs) were described. Typical performance statistics were presented: Pentium-based oneshot tasks running > 30kHz, 486-based oneshot tasks running at ~ 10 kHz, periodic timer tasks running in excess of 90 kHz with average zero jitter peaking to ~ 13 mus (UP) and ~ 30 mus (SMP). Some detail on kernel module programming, including coding examples, were presented showing a typical data acquisition system generating simulated (random) data writing to a shared memory buffer and a fifo buffer to communicate between real time Linux and user space. All coding examples were complete and tested under RTAI v0.6 and the 2.2.12 kernel. Finally, arguments were raised in support of real time Linux: it's open source, free under GPL, enables rapid prototyping, has good support and the ability to have a fully functioning workstation capable of co-existing hard real time performance. The counter weight-the negatives-of lack of platforms (x86 and PowerPC only at present), lack of board support, promiscuous root access and the danger of ignorance of real time programming issues were also discussed. See ftp://orion.tuc.noao.edu/pub/pnd/rtlbof.tgz for the StarOffice overheads for this presentation.

Direct Patlak Reconstruction From Dynamic PET Data Using the Kernel Method With MRI Information Based on Structural Similarity.

PubMed

Gong, Kuang; Cheng-Liao, Jinxiu; Wang, Guobao; Chen, Kevin T; Catana, Ciprian; Qi, Jinyi

2018-04-01

Positron emission tomography (PET) is a functional imaging modality widely used in oncology, cardiology, and neuroscience. It is highly sensitive, but suffers from relatively poor spatial resolution, as compared with anatomical imaging modalities, such as magnetic resonance imaging (MRI). With the recent development of combined PET/MR systems, we can improve the PET image quality by incorporating MR information into image reconstruction. Previously, kernel learning has been successfully embedded into static and dynamic PET image reconstruction using either PET temporal or MRI information. Here, we combine both PET temporal and MRI information adaptively to improve the quality of direct Patlak reconstruction. We examined different approaches to combine the PET and MRI information in kernel learning to address the issue of potential mismatches between MRI and PET signals. Computer simulations and hybrid real-patient data acquired on a simultaneous PET/MR scanner were used to evaluate the proposed methods. Results show that the method that combines PET temporal information and MRI spatial information adaptively based on the structure similarity index has the best performance in terms of noise reduction and resolution improvement.

Multiple kernels learning-based biological entity relationship extraction method.

PubMed

Dongliang, Xu; Jingchang, Pan; Bailing, Wang

2017-09-20

Automatic extracting protein entity interaction information from biomedical literature can help to build protein relation network and design new drugs. There are more than 20 million literature abstracts included in MEDLINE, which is the most authoritative textual database in the field of biomedicine, and follow an exponential growth over time. This frantic expansion of the biomedical literature can often be difficult to absorb or manually analyze. Thus efficient and automated search engines are necessary to efficiently explore the biomedical literature using text mining techniques. The P, R, and F value of tag graph method in Aimed corpus are 50.82, 69.76, and 58.61%, respectively. The P, R, and F value of tag graph kernel method in other four evaluation corpuses are 2-5% higher than that of all-paths graph kernel. And The P, R and F value of feature kernel and tag graph kernel fuse methods is 53.43, 71.62 and 61.30%, respectively. The P, R and F value of feature kernel and tag graph kernel fuse methods is 55.47, 70.29 and 60.37%, respectively. It indicated that the performance of the two kinds of kernel fusion methods is better than that of simple kernel. In comparison with the all-paths graph kernel method, the tag graph kernel method is superior in terms of overall performance. Experiments show that the performance of the multi-kernels method is better than that of the three separate single-kernel method and the dual-mutually fused kernel method used hereof in five corpus sets.

Fifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning.

PubMed

van Ginneken, Bram

2017-03-01

Half a century ago, the term "computer-aided diagnosis" (CAD) was introduced in the scientific literature. Pulmonary imaging, with chest radiography and computed tomography, has always been one of the focus areas in this field. In this study, I describe how machine learning became the dominant technology for tackling CAD in the lungs, generally producing better results than do classical rule-based approaches, and how the field is now rapidly changing: in the last few years, we have seen how even better results can be obtained with deep learning. The key differences among rule-based processing, machine learning, and deep learning are summarized and illustrated for various applications of CAD in the chest.

Automated image segmentation using support vector machines

NASA Astrophysics Data System (ADS)

Powell, Stephanie; Magnotta, Vincent A.; Andreasen, Nancy C.

2007-03-01

Neurodegenerative and neurodevelopmental diseases demonstrate problems associated with brain maturation and aging. Automated methods to delineate brain structures of interest are required to analyze large amounts of imaging data like that being collected in several on going multi-center studies. We have previously reported on using artificial neural networks (ANN) to define subcortical brain structures including the thalamus (0.88), caudate (0.85) and the putamen (0.81). In this work, apriori probability information was generated using Thirion's demons registration algorithm. The input vector consisted of apriori probability, spherical coordinates, and an iris of surrounding signal intensity values. We have applied the support vector machine (SVM) machine learning algorithm to automatically segment subcortical and cerebellar regions using the same input vector information. SVM architecture was derived from the ANN framework. Training was completed using a radial-basis function kernel with gamma equal to 5.5. Training was performed using 15,000 vectors collected from 15 training images in approximately 10 minutes. The resulting support vectors were applied to delineate 10 images not part of the training set. Relative overlap calculated for the subcortical structures was 0.87 for the thalamus, 0.84 for the caudate, 0.84 for the putamen, and 0.72 for the hippocampus. Relative overlap for the cerebellar lobes ranged from 0.76 to 0.86. The reliability of the SVM based algorithm was similar to the inter-rater reliability between manual raters and can be achieved without rater intervention.

Machine learning: novel bioinformatics approaches for combating antimicrobial resistance.

PubMed

Macesic, Nenad; Polubriaginof, Fernanda; Tatonetti, Nicholas P

2017-12-01

Antimicrobial resistance (AMR) is a threat to global health and new approaches to combating AMR are needed. Use of machine learning in addressing AMR is in its infancy but has made promising steps. We reviewed the current literature on the use of machine learning for studying bacterial AMR. The advent of large-scale data sets provided by next-generation sequencing and electronic health records make applying machine learning to the study and treatment of AMR possible. To date, it has been used for antimicrobial susceptibility genotype/phenotype prediction, development of AMR clinical decision rules, novel antimicrobial agent discovery and antimicrobial therapy optimization. Application of machine learning to studying AMR is feasible but remains limited. Implementation of machine learning in clinical settings faces barriers to uptake with concerns regarding model interpretability and data quality.Future applications of machine learning to AMR are likely to be laboratory-based, such as antimicrobial susceptibility phenotype prediction.

A Hybrid Method for Opinion Finding Task (KUNLP at TREC 2008 Blog Track)

DTIC Science & Technology

2008-11-01

retrieve relevant documents. For the Opinion Retrieval subtask, we propose a hybrid model of lexicon-based approach and machine learning approach for...estimating and ranking the opinionated documents. For the Polarized Opinion Retrieval subtask, we employ machine learning for predicting the polarity...and linear combination technique for ranking polar documents. The hybrid model which utilize both lexicon-based approach and machine learning approach

Osteoporosis risk prediction using machine learning and conventional methods.

PubMed

Kim, Sung Kean; Yoo, Tae Keun; Oh, Ein; Kim, Deok Won

2013-01-01

A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women, and compared with the ability of a conventional clinical decision tool, osteoporosis self-assessment tool (OST). We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Surveys (KNHANES V-1). The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests (RF), artificial neural networks (ANN), and logistic regression (LR) based on various predictors associated with low bone density. The learning models were compared with OST. SVM had significantly better area under the curve (AUC) of the receiver operating characteristic (ROC) than ANN, LR, and OST. Validation on the test set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0%. We were the first to perform comparisons of the performance of osteoporosis prediction between the machine learning and conventional methods using population-based epidemiological data. The machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.

Automatic Defect Detection for TFT-LCD Array Process Using Quasiconformal Kernel Support Vector Data Description

PubMed Central

Liu, Yi-Hung; Chen, Yan-Jen

2011-01-01

Defect detection has been considered an efficient way to increase the yield rate of panels in thin film transistor liquid crystal display (TFT-LCD) manufacturing. In this study we focus on the array process since it is the first and key process in TFT-LCD manufacturing. Various defects occur in the array process, and some of them could cause great damage to the LCD panels. Thus, how to design a method that can robustly detect defects from the images captured from the surface of LCD panels has become crucial. Previously, support vector data description (SVDD) has been successfully applied to LCD defect detection. However, its generalization performance is limited. In this paper, we propose a novel one-class machine learning method, called quasiconformal kernel SVDD (QK-SVDD) to address this issue. The QK-SVDD can significantly improve generalization performance of the traditional SVDD by introducing the quasiconformal transformation into a predefined kernel. Experimental results, carried out on real LCD images provided by an LCD manufacturer in Taiwan, indicate that the proposed QK-SVDD not only obtains a high defect detection rate of 96%, but also greatly improves generalization performance of SVDD. The improvement has shown to be over 30%. In addition, results also show that the QK-SVDD defect detector is able to accomplish the task of defect detection on an LCD image within 60 ms. PMID:22016625

Automatic defect detection for TFT-LCD array process using quasiconformal kernel support vector data description.

PubMed

Liu, Yi-Hung; Chen, Yan-Jen

2011-01-01

Defect detection has been considered an efficient way to increase the yield rate of panels in thin film transistor liquid crystal display (TFT-LCD) manufacturing. In this study we focus on the array process since it is the first and key process in TFT-LCD manufacturing. Various defects occur in the array process, and some of them could cause great damage to the LCD panels. Thus, how to design a method that can robustly detect defects from the images captured from the surface of LCD panels has become crucial. Previously, support vector data description (SVDD) has been successfully applied to LCD defect detection. However, its generalization performance is limited. In this paper, we propose a novel one-class machine learning method, called quasiconformal kernel SVDD (QK-SVDD) to address this issue. The QK-SVDD can significantly improve generalization performance of the traditional SVDD by introducing the quasiconformal transformation into a predefined kernel. Experimental results, carried out on real LCD images provided by an LCD manufacturer in Taiwan, indicate that the proposed QK-SVDD not only obtains a high defect detection rate of 96%, but also greatly improves generalization performance of SVDD. The improvement has shown to be over 30%. In addition, results also show that the QK-SVDD defect detector is able to accomplish the task of defect detection on an LCD image within 60 ms.

A novel method for landslide displacement prediction by integrating advanced computational intelligence algorithms.

PubMed

Zhou, Chao; Yin, Kunlong; Cao, Ying; Ahmed, Bayes; Fu, Xiaolin

2018-05-08

Landslide displacement prediction is considered as an essential component for developing early warning systems. The modelling of conventional forecast methods requires enormous monitoring data that limit its application. To conduct accurate displacement prediction with limited data, a novel method is proposed and applied by integrating three computational intelligence algorithms namely: the wavelet transform (WT), the artificial bees colony (ABC), and the kernel-based extreme learning machine (KELM). At first, the total displacement was decomposed into several sub-sequences with different frequencies using the WT. Next each sub-sequence was predicted separately by the KELM whose parameters were optimized by the ABC. Finally the predicted total displacement was obtained by adding all the predicted sub-sequences. The Shuping landslide in the Three Gorges Reservoir area in China was taken as a case study. The performance of the new method was compared with the WT-ELM, ABC-KELM, ELM, and the support vector machine (SVM) methods. Results show that the prediction accuracy can be improved by decomposing the total displacement into sub-sequences with various frequencies and by predicting them separately. The ABC-KELM algorithm shows the highest prediction capacity followed by the ELM and SVM. Overall, the proposed method achieved excellent performance both in terms of accuracy and stability.

High-throughput method for ear phenotyping and kernel weight estimation in maize using ear digital imaging.

PubMed

Makanza, R; Zaman-Allah, M; Cairns, J E; Eyre, J; Burgueño, J; Pacheco, Ángela; Diepenbrock, C; Magorokosho, C; Tarekegne, A; Olsen, M; Prasanna, B M

2018-01-01

Grain yield, ear and kernel attributes can assist to understand the performance of maize plant under different environmental conditions and can be used in the variety development process to address farmer's preferences. These parameters are however still laborious and expensive to measure. A low-cost ear digital imaging method was developed that provides estimates of ear and kernel attributes i.e., ear number and size, kernel number and size as well as kernel weight from photos of ears harvested from field trial plots. The image processing method uses a script that runs in a batch mode on ImageJ; an open source software. Kernel weight was estimated using the total kernel number derived from the number of kernels visible on the image and the average kernel size. Data showed a good agreement in terms of accuracy and precision between ground truth measurements and data generated through image processing. Broad-sense heritability of the estimated parameters was in the range or higher than that for measured grain weight. Limitation of the method for kernel weight estimation is discussed. The method developed in this work provides an opportunity to significantly reduce the cost of selection in the breeding process, especially for resource constrained crop improvement programs and can be used to learn more about the genetic bases of grain yield determinants.

Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction

PubMed Central

Lancaster, Jenessa; Lorenz, Romy; Leech, Rob; Cole, James H.

2018-01-01

Neuroimaging-based age prediction using machine learning is proposed as a biomarker of brain aging, relating to cognitive performance, health outcomes and progression of neurodegenerative disease. However, even leading age-prediction algorithms contain measurement error, motivating efforts to improve experimental pipelines. T1-weighted MRI is commonly used for age prediction, and the pre-processing of these scans involves normalization to a common template and resampling to a common voxel size, followed by spatial smoothing. Resampling parameters are often selected arbitrarily. Here, we sought to improve brain-age prediction accuracy by optimizing resampling parameters using Bayesian optimization. Using data on N = 2003 healthy individuals (aged 16–90 years) we trained support vector machines to (i) distinguish between young (<22 years) and old (>50 years) brains (classification) and (ii) predict chronological age (regression). We also evaluated generalisability of the age-regression model to an independent dataset (CamCAN, N = 648, aged 18–88 years). Bayesian optimization was used to identify optimal voxel size and smoothing kernel size for each task. This procedure adaptively samples the parameter space to evaluate accuracy across a range of possible parameters, using independent sub-samples to iteratively assess different parameter combinations to arrive at optimal values. When distinguishing between young and old brains a classification accuracy of 88.1% was achieved, (optimal voxel size = 11.5 mm3, smoothing kernel = 2.3 mm). For predicting chronological age, a mean absolute error (MAE) of 5.08 years was achieved, (optimal voxel size = 3.73 mm3, smoothing kernel = 3.68 mm). This was compared to performance using default values of 1.5 mm3 and 4mm respectively, resulting in MAE = 5.48 years, though this 7.3% improvement was not statistically significant. When assessing generalisability, best performance was achieved when applying the entire Bayesian optimization framework to the new dataset, out-performing the parameters optimized for the initial training dataset. Our study outlines the proof-of-principle that neuroimaging models for brain-age prediction can use Bayesian optimization to derive case-specific pre-processing parameters. Our results suggest that different pre-processing parameters are selected when optimization is conducted in specific contexts. This potentially motivates use of optimization techniques at many different points during the experimental process, which may improve statistical sensitivity and reduce opportunities for experimenter-led bias. PMID:29483870

Supervised machine learning algorithms to diagnose stress for vehicle drivers based on physiological sensor signals.

PubMed

Barua, Shaibal; Begum, Shahina; Ahmed, Mobyen Uddin

2015-01-01

Machine learning algorithms play an important role in computer science research. Recent advancement in sensor data collection in clinical sciences lead to a complex, heterogeneous data processing, and analysis for patient diagnosis and prognosis. Diagnosis and treatment of patients based on manual analysis of these sensor data are difficult and time consuming. Therefore, development of Knowledge-based systems to support clinicians in decision-making is important. However, it is necessary to perform experimental work to compare performances of different machine learning methods to help to select appropriate method for a specific characteristic of data sets. This paper compares classification performance of three popular machine learning methods i.e., case-based reasoning, neutral networks and support vector machine to diagnose stress of vehicle drivers using finger temperature and heart rate variability. The experimental results show that case-based reasoning outperforms other two methods in terms of classification accuracy. Case-based reasoning has achieved 80% and 86% accuracy to classify stress using finger temperature and heart rate variability. On contrary, both neural network and support vector machine have achieved less than 80% accuracy by using both physiological signals.