Wavelet analysis of MR functional data from the cerebellum

NASA Astrophysics Data System (ADS)

Romero Sánchez, Karen; Vásquez Reyes, Marcos A.; González Gómez, Dulce I.; Hidalgo Tobón, Silvia; Hernández López, Javier M.; Dies Suarez, Pilar; Barragán Pérez, Eduardo; De Celis Alonso, Benito

2014-11-01

The main goal of this project was to create a computer algorithm based on wavelet analysis of BOLD signals, which automatically diagnosed ADHD using information from resting state MR experiments. Male right handed volunteers (infants with ages between 7 and 11 years old) were studied and compared with age matched controls. Wavelet analysis, which is a mathematical tool used to decompose time series into elementary constituents and detect hidden information, was applied here to the BOLD signal obtained from the cerebellum 8 region of all our volunteers. Statistical differences between the values of the a parameters of wavelet analysis was found and showed significant differences (p<0.02) between groups. This difference might help in the future to distinguish healthy from ADHD patients and therefore diagnose ADHD.

Hidden corrosion detection in aircraft aluminum structures using laser ultrasonics and wavelet transform signal analysis.

PubMed

Silva, M Z; Gouyon, R; Lepoutre, F

2003-06-01

Preliminary results of hidden corrosion detection in aircraft aluminum structures using a noncontact laser based ultrasonic technique are presented. A short laser pulse focused to a line spot is used as a broadband source of ultrasonic guided waves in an aluminum 2024 sample cut from an aircraft structure and prepared with artificially corroded circular areas on its back surface. The out of plane surface displacements produced by the propagating ultrasonic waves were detected with a heterodyne Mach-Zehnder interferometer. Time-frequency analysis of the signals using a continuous wavelet transform allowed the identification of the generated Lamb modes by comparison with the calculated dispersion curves. The presence of back surface corrosion was detected by noting the loss of the S(1) mode near its cutoff frequency. This method is applicable to fast scanning inspection techniques and it is particularly suited for early corrosion detection.

Fast Bayesian Inference of Copy Number Variants using Hidden Markov Models with Wavelet Compression

PubMed Central

Wiedenhoeft, John; Brugel, Eric; Schliep, Alexander

2016-01-01

By integrating Haar wavelets with Hidden Markov Models, we achieve drastically reduced running times for Bayesian inference using Forward-Backward Gibbs sampling. We show that this improves detection of genomic copy number variants (CNV) in array CGH experiments compared to the state-of-the-art, including standard Gibbs sampling. The method concentrates computational effort on chromosomal segments which are difficult to call, by dynamically and adaptively recomputing consecutive blocks of observations likely to share a copy number. This makes routine diagnostic use and re-analysis of legacy data collections feasible; to this end, we also propose an effective automatic prior. An open source software implementation of our method is available at http://schlieplab.org/Software/HaMMLET/ (DOI: 10.5281/zenodo.46262). This paper was selected for oral presentation at RECOMB 2016, and an abstract is published in the conference proceedings. PMID:27177143

Development of a classification method for a crack on a pavement surface images using machine learning

NASA Astrophysics Data System (ADS)

Hizukuri, Akiyoshi; Nagata, Takeshi

2017-03-01

The purpose of this study is to develop a classification method for a crack on a pavement surface image using machine learning to reduce a maintenance fee. Our database consists of 3500 pavement surface images. This includes 800 crack and 2700 normal pavement surface images. The pavement surface images first are decomposed into several sub-images using a discrete wavelet transform (DWT) decomposition. We then calculate the wavelet sub-band histogram from each several sub-images at each level. The support vector machine (SVM) with computed wavelet sub-band histogram is employed for distinguishing between a crack and normal pavement surface images. The accuracies of the proposed classification method are 85.3% for crack and 84.4% for normal pavement images. The proposed classification method achieved high performance. Therefore, the proposed method would be useful in maintenance inspection.

Detection of Dendritic Spines Using Wavelet Packet Entropy and Fuzzy Support Vector Machine.

PubMed

Wang, Shuihua; Li, Yang; Shao, Ying; Cattani, Carlo; Zhang, Yudong; Du, Sidan

2017-01-01

The morphology of dendritic spines is highly correlated with the neuron function. Therefore, it is of positive influence for the research of the dendritic spines. However, it is tried to manually label the spine types for statistical analysis. In this work, we proposed an approach based on the combination of wavelet contour analysis for the backbone detection, wavelet packet entropy, and fuzzy support vector machine for the spine classification. The experiments show that this approach is promising. The average detection accuracy of "MushRoom" achieves 97.3%, "Stubby" achieves 94.6%, and "Thin" achieves 97.2%. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

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

Karen, Romero Sánchez, E-mail: alphacentauri-hp@hotmail.com, E-mail: marcos-vaquezr@hotmail.com, E-mail: isabeldgg@hotmail.com; Vásquez Reyes Marcos, A., E-mail: alphacentauri-hp@hotmail.com, E-mail: marcos-vaquezr@hotmail.com, E-mail: isabeldgg@hotmail.com; González Gómez Dulce, I., E-mail: alphacentauri-hp@hotmail.com, E-mail: marcos-vaquezr@hotmail.com, E-mail: isabeldgg@hotmail.com

The main goal of this project was to create a computer algorithm based on wavelet analysis of BOLD signals, which automatically diagnosed ADHD using information from resting state MR experiments. Male right handed volunteers (infants with ages between 7 and 11 years old) were studied and compared with age matched controls. Wavelet analysis, which is a mathematical tool used to decompose time series into elementary constituents and detect hidden information, was applied here to the BOLD signal obtained from the cerebellum 8 region of all our volunteers. Statistical differences between the values of the a parameters of wavelet analysis wasmore » found and showed significant differences (p<0.02) between groups. This difference might help in the future to distinguish healthy from ADHD patients and therefore diagnose ADHD.« less

Image-adaptive and robust digital wavelet-domain watermarking for images

NASA Astrophysics Data System (ADS)

Zhao, Yi; Zhang, Liping

2018-03-01

We propose a new frequency domain wavelet based watermarking technique. The key idea of our scheme is twofold: multi-tier solution representation of image and odd-even quantization embedding/extracting watermark. Because many complementary watermarks need to be hidden, the watermark image designed is image-adaptive. The meaningful and complementary watermark images was embedded into the original image (host image) by odd-even quantization modifying coefficients, which was selected from the detail wavelet coefficients of the original image, if their magnitudes are larger than their corresponding Just Noticeable Difference thresholds. The tests show good robustness against best-known attacks such as noise addition, image compression, median filtering, clipping as well as geometric transforms. Further research may improve the performance by refining JND thresholds.

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.

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.

Decision support system for diabetic retinopathy using discrete wavelet transform.

PubMed

Noronha, K; Acharya, U R; Nayak, K P; Kamath, S; Bhandary, S V

2013-03-01

Prolonged duration of the diabetes may affect the tiny blood vessels of the retina causing diabetic retinopathy. Routine eye screening of patients with diabetes helps to detect diabetic retinopathy at the early stage. It is very laborious and time-consuming for the doctors to go through many fundus images continuously. Therefore, decision support system for diabetic retinopathy detection can reduce the burden of the ophthalmologists. In this work, we have used discrete wavelet transform and support vector machine classifier for automated detection of normal and diabetic retinopathy classes. The wavelet-based decomposition was performed up to the second level, and eight energy features were extracted. Two energy features from the approximation coefficients of two levels and six energy values from the details in three orientations (horizontal, vertical and diagonal) were evaluated. These features were fed to the support vector machine classifier with various kernel functions (linear, radial basis function, polynomial of orders 2 and 3) to evaluate the highest classification accuracy. We obtained the highest average classification accuracy, sensitivity and specificity of more than 99% with support vector machine classifier (polynomial kernel of order 3) using three discrete wavelet transform features. We have also proposed an integrated index called Diabetic Retinopathy Risk Index using clinically significant wavelet energy features to identify normal and diabetic retinopathy classes using just one number. We believe that this (Diabetic Retinopathy Risk Index) can be used as an adjunct tool by the doctors during the eye screening to cross-check their diagnosis.

Swarm-wavelet based extreme learning machine for finger movement classification on transradial amputees.

PubMed

Anam, Khairul; Al-Jumaily, Adel

2014-01-01

The use of a small number of surface electromyography (EMG) channels on the transradial amputee in a myoelectric controller is a big challenge. This paper proposes a pattern recognition system using an extreme learning machine (ELM) optimized by particle swarm optimization (PSO). PSO is mutated by wavelet function to avoid trapped in a local minima. The proposed system is used to classify eleven imagined finger motions on five amputees by using only two EMG channels. The optimal performance of wavelet-PSO was compared to a grid-search method and standard PSO. The experimental results show that the proposed system is the most accurate classifier among other tested classifiers. It could classify 11 finger motions with the average accuracy of about 94 % across five amputees.

Research on the fault diagnosis of bearing based on wavelet and demodulation

NASA Astrophysics Data System (ADS)

Li, Jiapeng; Yuan, Yu

2017-05-01

As a most commonly-used machine part, antifriction bearing is extensively used in mechanical equipment. Vibration signal analysis is one of the methods to monitor and diagnose the running status of antifriction bearings. Therefore, using wavelet analysis for demising is of great importance in the engineering practice. This paper firstly presented the basic theory of wavelet analysis to study the transformation, decomposition and reconstruction of wavelet. In addition, edition software LabVIEW was adopted to conduct wavelet and demodulation upon the vibration signal of antifriction bearing collected. With the combination of Hilbert envelop demodulation analysis, the fault character frequencies of the demised signal were extracted to conduct fault diagnosis analysis, which serves as a reference for the wavelet and demodulation of the vibration signal in engineering practice.

Measuring the usefulness of hidden units in Boltzmann machines with mutual information.

PubMed

Berglund, Mathias; Raiko, Tapani; Cho, Kyunghyun

2015-04-01

Restricted Boltzmann machines (RBMs) and deep Boltzmann machines (DBMs) are important models in deep learning, but it is often difficult to measure their performance in general, or measure the importance of individual hidden units in specific. We propose to use mutual information to measure the usefulness of individual hidden units in Boltzmann machines. The measure is fast to compute, and serves as an upper bound for the information the neuron can pass on, enabling detection of a particular kind of poor training results. We confirm experimentally that the proposed measure indicates how much the performance of the model drops when some of the units of an RBM are pruned away. We demonstrate the usefulness of the measure for early detection of poor training in DBMs. Copyright © 2014 Elsevier Ltd. All rights reserved.

Detection of Unilateral Hearing Loss by Stationary Wavelet Entropy.

PubMed

Zhang, Yudong; Nayak, Deepak Ranjan; Yang, Ming; Yuan, Ti-Fei; Liu, Bin; Lu, Huimin; Wang, Shuihua

2017-01-01

Sensorineural hearing loss is correlated to massive neurological or psychiatric disease. T1-weighted volumetric images were acquired from fourteen subjects with right-sided hearing loss (RHL), fifteen subjects with left-sided hearing loss (LHL), and twenty healthy controls (HC). We treated a three-class classification problem: HC, LHL, and RHL. Stationary wavelet entropy was employed to extract global features from magnetic resonance images of each subject. Those stationary wavelet entropy features were used as input to a single-hidden layer feedforward neuralnetwork classifier. The 10 repetition results of 10-fold cross validation show that the accuracies of HC, LHL, and RHL are 96.94%, 97.14%, and 97.35%, respectively. Our developed system is promising and effective in detecting hearing loss. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Adjusting Wavelet-based Multiresolution Analysis Boundary Conditions for Robust Long-term Streamflow Forecasting Model

NASA Astrophysics Data System (ADS)

Maslova, I.; Ticlavilca, A. M.; McKee, M.

2012-12-01

There has been an increased interest in wavelet-based streamflow forecasting models in recent years. Often overlooked in this approach are the circularity assumptions of the wavelet transform. We propose a novel technique for minimizing the wavelet decomposition boundary condition effect to produce long-term, up to 12 months ahead, forecasts of streamflow. A simulation study is performed to evaluate the effects of different wavelet boundary rules using synthetic and real streamflow data. A hybrid wavelet-multivariate relevance vector machine model is developed for forecasting the streamflow in real-time for Yellowstone River, Uinta Basin, Utah, USA. The inputs of the model utilize only the past monthly streamflow records. They are decomposed into components formulated in terms of wavelet multiresolution analysis. It is shown that the model model accuracy can be increased by using the wavelet boundary rule introduced in this study. This long-term streamflow modeling and forecasting methodology would enable better decision-making and managing water availability risk.

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.

A support vector machine approach for classification of welding defects from ultrasonic signals

NASA Astrophysics Data System (ADS)

Chen, Yuan; Ma, Hong-Wei; Zhang, Guang-Ming

2014-07-01

Defect classification is an important issue in ultrasonic non-destructive evaluation. A layered multi-class support vector machine (LMSVM) classification system, which combines multiple SVM classifiers through a layered architecture, is proposed in this paper. The proposed LMSVM classification system is applied to the classification of welding defects from ultrasonic test signals. The measured ultrasonic defect echo signals are first decomposed into wavelet coefficients by the wavelet packet transform. The energy of the wavelet coefficients at different frequency channels are used to construct the feature vectors. The bees algorithm (BA) is then used for feature selection and SVM parameter optimisation for the LMSVM classification system. The BA-based feature selection optimises the energy feature vectors. The optimised feature vectors are input to the LMSVM classification system for training and testing. Experimental results of classifying welding defects demonstrate that the proposed technique is highly robust, precise and reliable for ultrasonic defect classification.

A wavelet domain adaptive image watermarking method based on chaotic encryption

NASA Astrophysics Data System (ADS)

Wei, Fang; Liu, Jian; Cao, Hanqiang; Yang, Jun

2009-10-01

A digital watermarking technique is a specific branch of steganography, which can be used in various applications, provides a novel way to solve security problems for multimedia information. In this paper, we proposed a kind of wavelet domain adaptive image digital watermarking method using chaotic stream encrypt and human eye visual property. The secret information that can be seen as a watermarking is hidden into a host image, which can be publicly accessed, so the transportation of the secret information will not attract the attention of illegal receiver. The experimental results show that the method is invisible and robust against some image processing.

Reversible integer wavelet transform for blind image hiding method

PubMed Central

Bibi, Nargis; Mahmood, Zahid; Akram, Tallha; Naqvi, Syed Rameez

2017-01-01

In this article, a blind data hiding reversible methodology to embed the secret data for hiding purpose into cover image is proposed. The key advantage of this research work is to resolve the privacy and secrecy issues raised during the data transmission over the internet. Firstly, data is decomposed into sub-bands using the integer wavelets. For decomposition, the Fresnelet transform is utilized which encrypts the secret data by choosing a unique key parameter to construct a dummy pattern. The dummy pattern is then embedded into an approximated sub-band of the cover image. Our proposed method reveals high-capacity and great imperceptibility of the secret embedded data. With the utilization of family of integer wavelets, the proposed novel approach becomes more efficient for hiding and retrieving process. It retrieved the secret hidden data from the embedded data blindly, without the requirement of original cover image. PMID:28498855

Efficacy Evaluation of Different Wavelet Feature Extraction Methods on Brain MRI Tumor Detection

NASA Astrophysics Data System (ADS)

Nabizadeh, Nooshin; John, Nigel; Kubat, Miroslav

2014-03-01

Automated Magnetic Resonance Imaging brain tumor detection and segmentation is a challenging task. Among different available methods, feature-based methods are very dominant. While many feature extraction techniques have been employed, it is still not quite clear which of feature extraction methods should be preferred. To help improve the situation, we present the results of a study in which we evaluate the efficiency of using different wavelet transform features extraction methods in brain MRI abnormality detection. Applying T1-weighted brain image, Discrete Wavelet Transform (DWT), Discrete Wavelet Packet Transform (DWPT), Dual Tree Complex Wavelet Transform (DTCWT), and Complex Morlet Wavelet Transform (CMWT) methods are applied to construct the feature pool. Three various classifiers as Support Vector Machine, K Nearest Neighborhood, and Sparse Representation-Based Classifier are applied and compared for classifying the selected features. The results show that DTCWT and CMWT features classified with SVM, result in the highest classification accuracy, proving of capability of wavelet transform features to be informative in this application.

Detecting features in the dark energy equation of state: a wavelet approach

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

Hojjati, Alireza; Pogosian, Levon; Zhao, Gong-Bo, E-mail: alireza_hojjati@sfu.ca, E-mail: levon@sfu.ca, E-mail: gong-bo.zhao@port.ac.uk

2010-04-01

We study the utility of wavelets for detecting the redshift evolution of the dark energy equation of state w(z) from the combination of supernovae (SNe), CMB and BAO data. We show that local features in w, such as bumps, can be detected efficiently using wavelets. To demonstrate, we first generate a mock supernovae data sample for a SNAP-like survey with a bump feature in w(z) hidden in, then successfully discover it by performing a blind wavelet analysis. We also apply our method to analyze the recently released ''Constitution'' SNe data, combined with WMAP and BAO from SDSS, and find weakmore » hints of dark energy dynamics. Namely, we find that models with w(z) < −1 for 0.2 < z < 0.5, and w(z) > −1 for 0.5 < z < 1, are mildly favored at 95% confidence level. This is in good agreement with several recent studies using other methods, such as redshift binning with principal component analysis (PCA) (e.g. Zhao and Zhang, arXiv: 0908.1568)« less

Improved Extreme Learning Machine based on the Sensitivity Analysis

NASA Astrophysics Data System (ADS)

Cui, Licheng; Zhai, Huawei; Wang, Benchao; Qu, Zengtang

2018-03-01

Extreme learning machine and its improved ones is weak in some points, such as computing complex, learning error and so on. After deeply analyzing, referencing the importance of hidden nodes in SVM, an novel analyzing method of the sensitivity is proposed which meets people’s cognitive habits. Based on these, an improved ELM is proposed, it could remove hidden nodes before meeting the learning error, and it can efficiently manage the number of hidden nodes, so as to improve the its performance. After comparing tests, it is better in learning time, accuracy and so on.

A novel approach for detection and classification of mammographic microcalcifications using wavelet analysis and extreme learning machine.

PubMed

Malar, E; Kandaswamy, A; Chakravarthy, D; Giri Dharan, A

2012-09-01

The objective of this paper is to reveal the effectiveness of wavelet based tissue texture analysis for microcalcification detection in digitized mammograms using Extreme Learning Machine (ELM). Microcalcifications are tiny deposits of calcium in the breast tissue which are potential indicators for early detection of breast cancer. The dense nature of the breast tissue and the poor contrast of the mammogram image prohibit the effectiveness in identifying microcalcifications. Hence, a new approach to discriminate the microcalcifications from the normal tissue is done using wavelet features and is compared with different feature vectors extracted using Gray Level Spatial Dependence Matrix (GLSDM) and Gabor filter based techniques. A total of 120 Region of Interests (ROIs) extracted from 55 mammogram images of mini-Mias database, including normal and microcalcification images are used in the current research. The network is trained with the above mentioned features and the results denote that ELM produces relatively better classification accuracy (94%) with a significant reduction in training time than the other artificial neural networks like Bayesnet classifier, Naivebayes classifier, and Support Vector Machine. ELM also avoids problems like local minima, improper learning rate, and over fitting. Copyright © 2012 Elsevier Ltd. All rights reserved.

Hybrid wavelet-support vector machine approach for modelling rainfall-runoff process.

PubMed

Komasi, Mehdi; Sharghi, Soroush

2016-01-01

Because of the importance of water resources management, the need for accurate modeling of the rainfall-runoff process has rapidly grown in the past decades. Recently, the support vector machine (SVM) approach has been used by hydrologists for rainfall-runoff modeling and the other fields of hydrology. Similar to the other artificial intelligence models, such as artificial neural network (ANN) and adaptive neural fuzzy inference system, the SVM model is based on the autoregressive properties. In this paper, the wavelet analysis was linked to the SVM model concept for modeling the rainfall-runoff process of Aghchai and Eel River watersheds. In this way, the main time series of two variables, rainfall and runoff, were decomposed to multiple frequent time series by wavelet theory; then, these time series were imposed as input data on the SVM model in order to predict the runoff discharge one day ahead. The obtained results show that the wavelet SVM model can predict both short- and long-term runoff discharges by considering the seasonality effects. Also, the proposed hybrid model is relatively more appropriate than classical autoregressive ones such as ANN and SVM because it uses the multi-scale time series of rainfall and runoff data in the modeling process.

A Fast SVD-Hidden-nodes based Extreme Learning Machine for Large-Scale Data Analytics.

PubMed

Deng, Wan-Yu; Bai, Zuo; Huang, Guang-Bin; Zheng, Qing-Hua

2016-05-01

Big dimensional data is a growing trend that is emerging in many real world contexts, extending from web mining, gene expression analysis, protein-protein interaction to high-frequency financial data. Nowadays, there is a growing consensus that the increasing dimensionality poses impeding effects on the performances of classifiers, which is termed as the "peaking phenomenon" in the field of machine intelligence. To address the issue, dimensionality reduction is commonly employed as a preprocessing step on the Big dimensional data before building the classifiers. In this paper, we propose an Extreme Learning Machine (ELM) approach for large-scale data analytic. In contrast to existing approaches, we embed hidden nodes that are designed using singular value decomposition (SVD) into the classical ELM. These SVD nodes in the hidden layer are shown to capture the underlying characteristics of the Big dimensional data well, exhibiting excellent generalization performances. The drawback of using SVD on the entire dataset, however, is the high computational complexity involved. To address this, a fast divide and conquer approximation scheme is introduced to maintain computational tractability on high volume data. The resultant algorithm proposed is labeled here as Fast Singular Value Decomposition-Hidden-nodes based Extreme Learning Machine or FSVD-H-ELM in short. In FSVD-H-ELM, instead of identifying the SVD hidden nodes directly from the entire dataset, SVD hidden nodes are derived from multiple random subsets of data sampled from the original dataset. Comprehensive experiments and comparisons are conducted to assess the FSVD-H-ELM against other state-of-the-art algorithms. The results obtained demonstrated the superior generalization performance and efficiency of the FSVD-H-ELM. Copyright © 2016 Elsevier Ltd. All rights reserved.

Wavelet-based energy features for glaucomatous image classification.

PubMed

Dua, Sumeet; Acharya, U Rajendra; Chowriappa, Pradeep; Sree, S Vinitha

2012-01-01

Texture features within images are actively pursued for accurate and efficient glaucoma classification. Energy distribution over wavelet subbands is applied to find these important texture features. In this paper, we investigate the discriminatory potential of wavelet features obtained from the daubechies (db3), symlets (sym3), and biorthogonal (bio3.3, bio3.5, and bio3.7) wavelet filters. We propose a novel technique to extract energy signatures obtained using 2-D discrete wavelet transform, and subject these signatures to different feature ranking and feature selection strategies. We have gauged the effectiveness of the resultant ranked and selected subsets of features using a support vector machine, sequential minimal optimization, random forest, and naïve Bayes classification strategies. We observed an accuracy of around 93% using tenfold cross validations to demonstrate the effectiveness of these methods.

The wavelet analysis for the assessment of microvascular function with the laser Doppler fluxmetry over the last 20 years. Looking for hidden informations.

PubMed

Martini, Romeo; Bagno, Andrea

2018-04-14

The wavelet analysis has been applied to the Laser Doppler Fluxmetry for assessing the frequency spectrum of the flowmotion to study the microvascular function waves.Although the application of wavelet analysis has allowed a detailed evaluation of the microvascular function, its use does not seem to be yet widespread over the last two decades.Aiming to improve the diffusion of this methodology, we herein present a systematic review of the literature about the application of the wavelet analysis to the laser Doppler fluxmetry signal. A computer research has been performed on PubMed and Scopus databases from January 1990 to December 2017. The used terms for the investigation have been "wavelet analysis", "wavelet transform analysis", "Morlet wavelet transform" along with the terms "laser Doppler", "laserdoppler" and/or "flowmetry" or "fluxmetry". One hundred and eighteen studies have been found. After the scrutiny, 97 studies reporting data on humans have been selected. Fifty-three studies, 54.0% (95% CI 44.2-63.6) pooled rate, have been performed on 892 healthy subjects and 44, 45,9 % (95% CI 36.3-55.7%) pooled rate have been performed on 1679 patients. No significant difference has been found between the two groups (p 0,81). On average, the number of studies published each year was 4.8 (95% CI 3.4-6.2). The trend of studies production has increased significantly from 1998 to 2017, (p 0.0006). But only the studies on patients have shown a significant increase trend along the years (p 0.0003), than the studies on healthy subjects (p 0.09).In conclusion, this review highlights that despite being a promising and interesting methodology for the study of the microcirculatory function, the wavelet analysis has remained still neglected.

Hyperspectral imaging with wavelet transform for classification of colon tissue biopsy samples

NASA Astrophysics Data System (ADS)

Masood, Khalid

2008-08-01

Automatic classification of medical images is a part of our computerised medical imaging programme to support the pathologists in their diagnosis. Hyperspectral data has found its applications in medical imagery. Its usage is increasing significantly in biopsy analysis of medical images. In this paper, we present a histopathological analysis for the classification of colon biopsy samples into benign and malignant classes. The proposed study is based on comparison between 3D spectral/spatial analysis and 2D spatial analysis. Wavelet textural features in the wavelet domain are used in both these approaches for classification of colon biopsy samples. Experimental results indicate that the incorporation of wavelet textural features using a support vector machine, in 2D spatial analysis, achieve best classification accuracy.

Taking the fifth amendment in Turing's imitation game

NASA Astrophysics Data System (ADS)

Warwick, Kevin; Shah, Huma

2017-03-01

In this paper, we look at a specific issue with practical Turing tests, namely the right of the machine to remain silent during interrogation. In particular, we consider the possibility of a machine passing the Turing test simply by not saying anything. We include a number of transcripts from practical Turing tests in which silence has actually occurred on the part of a hidden entity. Each of the transcripts considered here resulted in a judge being unable to make the 'right identification', i.e., they could not say for certain which hidden entity was the machine.

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.

A hybrid wavelet transform based short-term wind speed forecasting approach.

PubMed

Wang, Jujie

2014-01-01

It is important to improve the accuracy of wind speed forecasting for wind parks management and wind power utilization. In this paper, a novel hybrid approach known as WTT-TNN is proposed for wind speed forecasting. In the first step of the approach, a wavelet transform technique (WTT) is used to decompose wind speed into an approximate scale and several detailed scales. In the second step, a two-hidden-layer neural network (TNN) is used to predict both approximated scale and detailed scales, respectively. In order to find the optimal network architecture, the partial autocorrelation function is adopted to determine the number of neurons in the input layer, and an experimental simulation is made to determine the number of neurons within each hidden layer in the modeling process of TNN. Afterwards, the final prediction value can be obtained by the sum of these prediction results. In this study, a WTT is employed to extract these different patterns of the wind speed and make it easier for forecasting. To evaluate the performance of the proposed approach, it is applied to forecast Hexi Corridor of China's wind speed. Simulation results in four different cases show that the proposed method increases wind speed forecasting accuracy.

A Hybrid Wavelet Transform Based Short-Term Wind Speed Forecasting Approach

PubMed Central

Wang, Jujie

2014-01-01

It is important to improve the accuracy of wind speed forecasting for wind parks management and wind power utilization. In this paper, a novel hybrid approach known as WTT-TNN is proposed for wind speed forecasting. In the first step of the approach, a wavelet transform technique (WTT) is used to decompose wind speed into an approximate scale and several detailed scales. In the second step, a two-hidden-layer neural network (TNN) is used to predict both approximated scale and detailed scales, respectively. In order to find the optimal network architecture, the partial autocorrelation function is adopted to determine the number of neurons in the input layer, and an experimental simulation is made to determine the number of neurons within each hidden layer in the modeling process of TNN. Afterwards, the final prediction value can be obtained by the sum of these prediction results. In this study, a WTT is employed to extract these different patterns of the wind speed and make it easier for forecasting. To evaluate the performance of the proposed approach, it is applied to forecast Hexi Corridor of China's wind speed. Simulation results in four different cases show that the proposed method increases wind speed forecasting accuracy. PMID:25136699

A Signal Processing Approach with a Smooth Empirical Mode Decomposition to Reveal Hidden Trace of Corrosion in Highly Contaminated Guided Wave Signals for Concrete-Covered Pipes

PubMed Central

Rostami, Javad; Chen, Jingming; Tse, Peter W.

2017-01-01

Ultrasonic guided waves have been extensively applied for non-destructive testing of plate-like structures particularly pipes in past two decades. In this regard, if a structure has a simple geometry, obtained guided waves’ signals are easy to explain. However, any small degree of complexity in the geometry such as contacting with other materials may cause an extra amount of complication in the interpretation of guided wave signals. The problem deepens if defects have irregular shapes such as natural corrosion. Signal processing techniques that have been proposed for guided wave signals’ analysis are generally good for simple signals obtained in a highly controlled experimental environment. In fact, guided wave signals in a real situation such as the existence of natural corrosion in wall-covered pipes are much more complicated. Considering pipes in residential buildings that pass through concrete walls, in this paper we introduced Smooth Empirical Mode Decomposition (SEMD) to efficiently separate overlapped guided waves. As empirical mode decomposition (EMD) which is a good candidate for analyzing non-stationary signals, suffers from some shortcomings, wavelet transform was adopted in the sifting stage of EMD to improve its outcome in SEMD. However, selection of mother wavelet that suits best for our purpose plays an important role. Since in guided wave inspection, the incident waves are well known and are usually tone-burst signals, we tailored a complex tone-burst signal to be used as our mother wavelet. In the sifting stage of EMD, wavelet de-noising was applied to eliminate unwanted frequency components from each IMF. SEMD greatly enhances the performance of EMD in guided wave analysis for highly contaminated signals. In our experiment on concrete covered pipes with natural corrosion, this method not only separates the concrete wall indication clearly in time domain signal, a natural corrosion with complex geometry that was hidden and located inside the concrete section was successfully exposed. PMID:28178220

A Signal Processing Approach with a Smooth Empirical Mode Decomposition to Reveal Hidden Trace of Corrosion in Highly Contaminated Guided Wave Signals for Concrete-Covered Pipes.

PubMed

Rostami, Javad; Chen, Jingming; Tse, Peter W

2017-02-07

Ultrasonic guided waves have been extensively applied for non-destructive testing of plate-like structures particularly pipes in past two decades. In this regard, if a structure has a simple geometry, obtained guided waves' signals are easy to explain. However, any small degree of complexity in the geometry such as contacting with other materials may cause an extra amount of complication in the interpretation of guided wave signals. The problem deepens if defects have irregular shapes such as natural corrosion. Signal processing techniques that have been proposed for guided wave signals' analysis are generally good for simple signals obtained in a highly controlled experimental environment. In fact, guided wave signals in a real situation such as the existence of natural corrosion in wall-covered pipes are much more complicated. Considering pipes in residential buildings that pass through concrete walls, in this paper we introduced Smooth Empirical Mode Decomposition (SEMD) to efficiently separate overlapped guided waves. As empirical mode decomposition (EMD) which is a good candidate for analyzing non-stationary signals, suffers from some shortcomings, wavelet transform was adopted in the sifting stage of EMD to improve its outcome in SEMD. However, selection of mother wavelet that suits best for our purpose plays an important role. Since in guided wave inspection, the incident waves are well known and are usually tone-burst signals, we tailored a complex tone-burst signal to be used as our mother wavelet. In the sifting stage of EMD, wavelet de-noising was applied to eliminate unwanted frequency components from each IMF. SEMD greatly enhances the performance of EMD in guided wave analysis for highly contaminated signals. In our experiment on concrete covered pipes with natural corrosion, this method not only separates the concrete wall indication clearly in time domain signal, a natural corrosion with complex geometry that was hidden and located inside the concrete section was successfully exposed.

Photometric Supernova Classification with Machine Learning

NASA Astrophysics Data System (ADS)

Lochner, Michelle; McEwen, Jason D.; Peiris, Hiranya V.; Lahav, Ofer; Winter, Max K.

2016-08-01

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models to curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k-nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.

Wab-InSAR: a new wavelet based InSAR time series technique applied to volcanic and tectonic areas

NASA Astrophysics Data System (ADS)

Walter, T. R.; Shirzaei, M.; Nankali, H.; Roustaei, M.

2009-12-01

Modern geodetic techniques such as InSAR and GPS provide valuable observations of the deformation field. Because of the variety of environmental interferences (e.g., atmosphere, topography distortion) and incompleteness of the models (assumption of the linear model for deformation), those observations are usually tainted by various systematic and random errors. Therefore we develop and test new methods to identify and filter unwanted periodic or episodic artifacts to obtain accurate and precise deformation measurements. Here we present and implement a new wavelet based InSAR (Wab-InSAR) time series approach. Because wavelets are excellent tools for identifying hidden patterns and capturing transient signals, we utilize wavelet functions for reducing the effect of atmospheric delay and digital elevation model inaccuracies. Wab-InSAR is a model free technique, reducing digital elevation model errors in individual interferograms using a 2D spatial Legendre polynomial wavelet filter. Atmospheric delays are reduced using a 3D spatio-temporal wavelet transform algorithm and a novel technique for pixel selection. We apply Wab-InSAR to several targets, including volcano deformation processes at Hawaii Island, and mountain building processes in Iran. Both targets are chosen to investigate large and small amplitude signals, variable and complex topography and atmospheric effects. In this presentation we explain different steps of the technique, validate the results by comparison to other high resolution processing methods (GPS, PS-InSAR, SBAS) and discuss the geophysical results.

A Wavelet Bicoherence-Based Quadratic Nonlinearity Feature for Translational Axis Condition Monitoring

PubMed Central

Li, Yong; Wang, Xiufeng; Lin, Jing; Shi, Shengyu

2014-01-01

The translational axis is one of the most important subsystems in modern machine tools, as its degradation may result in the loss of the product qualification and lower the control precision. Condition-based maintenance (CBM) has been considered as one of the advanced maintenance schemes to achieve effective, reliable and cost-effective operation of machine systems, however, current vibration-based maintenance schemes cannot be employed directly in the translational axis system, due to its complex structure and the inefficiency of commonly used condition monitoring features. In this paper, a wavelet bicoherence-based quadratic nonlinearity feature is proposed for translational axis condition monitoring by using the torque signature of the drive servomotor. Firstly, the quadratic nonlinearity of the servomotor torque signature is discussed, and then, a biphase randomization wavelet bicoherence is introduced for its quadratic nonlinear detection. On this basis, a quadratic nonlinearity feature is proposed for condition monitoring of the translational axis. The properties of the proposed quadratic nonlinearity feature are investigated by simulations. Subsequently, this feature is applied to the real-world servomotor torque data collected from the X-axis on a high precision vertical machining centre. All the results show that the performance of the proposed feature is much better than that of original condition monitoring features. PMID:24473281

Regime Behavior in Paleo-Reconstructed Streamflow: Attributions to Atmospheric Dynamics, Synoptic Circulation and Large-Scale Climate Teleconnection Patterns

NASA Astrophysics Data System (ADS)

Ravindranath, A.; Devineni, N.

2017-12-01

Studies have shown that streamflow behavior and dynamics have a significant link with climate and climate variability. Patterns of persistent regime behavior from extended streamflow records in many watersheds justify investigating large-scale climate mechanisms as potential drivers of hydrologic regime behavior and streamflow variability. Understanding such streamflow-climate relationships is crucial to forecasting/simulation systems and the planning and management of water resources. In this study, hidden Markov models are used with reconstructed streamflow to detect regime-like behaviors - the hidden states - and state transition phenomena. Individual extreme events and their spatial variability across the basin are then verified with the identified states. Wavelet analysis is performed to examine the signals over time in the streamflow records. Joint analyses of the climatic data in the 20th century and the identified states are undertaken to better understand the hydroclimatic connections within the basin as well as important teleconnections that influence water supply. Compositing techniques are used to identify atmospheric circulation patterns associated with identified states of streamflow. The grouping of such synoptic patterns and their frequency are then examined. Sliding time-window correlation analysis and cross-wavelet spectral analysis are performed to establish the synchronicity of basin flows to the identified synoptic and teleconnection patterns. The Missouri River Basin (MRB) is examined in this study, both as a means of better understanding the synoptic climate controls in this important watershed and as a case study for the techniques developed here. Initial wavelet analyses of reconstructed streamflow at major gauges in the MRB show multidecadal cycles in regime behavior.

The efficacy of support vector machines (SVM) in robust determination of earthquake early warning magnitudes in central Japan

NASA Astrophysics Data System (ADS)

Reddy, Ramakrushna; Nair, Rajesh R.

2013-10-01

This work deals with a methodology applied to seismic early warning systems which are designed to provide real-time estimation of the magnitude of an event. We will reappraise the work of Simons et al. (2006), who on the basis of wavelet approach predicted a magnitude error of ±1. We will verify and improve upon the methodology of Simons et al. (2006) by applying an SVM statistical learning machine on the time-scale wavelet decomposition methods. We used the data of 108 events in central Japan with magnitude ranging from 3 to 7.4 recorded at KiK-net network stations, for a source-receiver distance of up to 150 km during the period 1998-2011. We applied a wavelet transform on the seismogram data and calculating scale-dependent threshold wavelet coefficients. These coefficients were then classified into low magnitude and high magnitude events by constructing a maximum margin hyperplane between the two classes, which forms the essence of SVMs. Further, the classified events from both the classes were picked up and linear regressions were plotted to determine the relationship between wavelet coefficient magnitude and earthquake magnitude, which in turn helped us to estimate the earthquake magnitude of an event given its threshold wavelet coefficient. At wavelet scale number 7, we predicted the earthquake magnitude of an event within 2.7 seconds. This means that a magnitude determination is available within 2.7 s after the initial onset of the P-wave. These results shed light on the application of SVM as a way to choose the optimal regression function to estimate the magnitude from a few seconds of an incoming seismogram. This would improve the approaches from Simons et al. (2006) which use an average of the two regression functions to estimate the magnitude.

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.

PHOTOMETRIC SUPERNOVA CLASSIFICATION WITH MACHINE LEARNING

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

Lochner, Michelle; Peiris, Hiranya V.; Lahav, Ofer

Automated photometric supernova classification has become an active area of research in recent years in light of current and upcoming imaging surveys such as the Dark Energy Survey (DES) and the Large Synoptic Survey Telescope, given that spectroscopic confirmation of type for all supernovae discovered will be impossible. Here, we develop a multi-faceted classification pipeline, combining existing and new approaches. Our pipeline consists of two stages: extracting descriptive features from the light curves and classification using a machine learning algorithm. Our feature extraction methods vary from model-dependent techniques, namely SALT2 fits, to more independent techniques that fit parametric models tomore » curves, to a completely model-independent wavelet approach. We cover a range of representative machine learning algorithms, including naive Bayes, k -nearest neighbors, support vector machines, artificial neural networks, and boosted decision trees (BDTs). We test the pipeline on simulated multi-band DES light curves from the Supernova Photometric Classification Challenge. Using the commonly used area under the curve (AUC) of the Receiver Operating Characteristic as a metric, we find that the SALT2 fits and the wavelet approach, with the BDTs algorithm, each achieve an AUC of 0.98, where 1 represents perfect classification. We find that a representative training set is essential for good classification, whatever the feature set or algorithm, with implications for spectroscopic follow-up. Importantly, we find that by using either the SALT2 or the wavelet feature sets with a BDT algorithm, accurate classification is possible purely from light curve data, without the need for any redshift information.« less

Machine learning algorithms for mode-of-action classification in toxicity assessment.

PubMed

Zhang, Yile; Wong, Yau Shu; Deng, Jian; Anton, Cristina; Gabos, Stephan; Zhang, Weiping; Huang, Dorothy Yu; Jin, Can

2016-01-01

Real Time Cell Analysis (RTCA) technology is used to monitor cellular changes continuously over the entire exposure period. Combining with different testing concentrations, the profiles have potential in probing the mode of action (MOA) of the testing substances. In this paper, we present machine learning approaches for MOA assessment. Computational tools based on artificial neural network (ANN) and support vector machine (SVM) are developed to analyze the time-concentration response curves (TCRCs) of human cell lines responding to tested chemicals. The techniques are capable of learning data from given TCRCs with known MOA information and then making MOA classification for the unknown toxicity. A novel data processing step based on wavelet transform is introduced to extract important features from the original TCRC data. From the dose response curves, time interval leading to higher classification success rate can be selected as input to enhance the performance of the machine learning algorithm. This is particularly helpful when handling cases with limited and imbalanced data. The validation of the proposed method is demonstrated by the supervised learning algorithm applied to the exposure data of HepG2 cell line to 63 chemicals with 11 concentrations in each test case. Classification success rate in the range of 85 to 95 % are obtained using SVM for MOA classification with two clusters to cases up to four clusters. Wavelet transform is capable of capturing important features of TCRCs for MOA classification. The proposed SVM scheme incorporated with wavelet transform has a great potential for large scale MOA classification and high-through output chemical screening.

Classification of different kinds of pesticide residues on lettuce based on fluorescence spectra and WT-BCC-SVM algorithm

NASA Astrophysics Data System (ADS)

Zhou, Xin; Jun, Sun; Zhang, Bing; Jun, Wu

2017-07-01

In order to improve the reliability of the spectrum feature extracted by wavelet transform, a method combining wavelet transform (WT) with bacterial colony chemotaxis algorithm and support vector machine (BCC-SVM) algorithm (WT-BCC-SVM) was proposed in this paper. Besides, we aimed to identify different kinds of pesticide residues on lettuce leaves in a novel and rapid non-destructive way by using fluorescence spectra technology. The fluorescence spectral data of 150 lettuce leaf samples of five different kinds of pesticide residues on the surface of lettuce were obtained using Cary Eclipse fluorescence spectrometer. Standard normalized variable detrending (SNV detrending), Savitzky-Golay coupled with Standard normalized variable detrending (SG-SNV detrending) were used to preprocess the raw spectra, respectively. Bacterial colony chemotaxis combined with support vector machine (BCC-SVM) and support vector machine (SVM) classification models were established based on full spectra (FS) and wavelet transform characteristics (WTC), respectively. Moreover, WTC were selected by WT. The results showed that the accuracy of training set, calibration set and the prediction set of the best optimal classification model (SG-SNV detrending-WT-BCC-SVM) were 100%, 98% and 93.33%, respectively. In addition, the results indicated that it was feasible to use WT-BCC-SVM to establish diagnostic model of different kinds of pesticide residues on lettuce leaves.

Wavelet images and Chou's pseudo amino acid composition for protein classification.

PubMed

Nanni, Loris; Brahnam, Sheryl; Lumini, Alessandra

2012-08-01

The last decade has seen an explosion in the collection of protein data. To actualize the potential offered by this wealth of data, it is important to develop machine systems capable of classifying and extracting features from proteins. Reliable machine systems for protein classification offer many benefits, including the promise of finding novel drugs and vaccines. In developing our system, we analyze and compare several feature extraction methods used in protein classification that are based on the calculation of texture descriptors starting from a wavelet representation of the protein. We then feed these texture-based representations of the protein into an Adaboost ensemble of neural network or a support vector machine classifier. In addition, we perform experiments that combine our feature extraction methods with a standard method that is based on the Chou's pseudo amino acid composition. Using several datasets, we show that our best approach outperforms standard methods. The Matlab code of the proposed protein descriptors is available at http://bias.csr.unibo.it/nanni/wave.rar .

Accelerating the discovery of hidden two-dimensional magnets using machine learning and first principle calculations

NASA Astrophysics Data System (ADS)

Miyazato, Itsuki; Tanaka, Yuzuru; Takahashi, Keisuke

2018-02-01

Two-dimensional (2D) magnets are explored in terms of data science and first principle calculations. Machine learning determines four descriptors for predicting the magnetic moments of 2D materials within reported 216 2D materials data. With the trained machine, 254 2D materials are predicted to have high magnetic moments. First principle calculations are performed to evaluate the predicted 254 2D materials where eight undiscovered stable 2D materials with high magnetic moments are revealed. The approach taken in this work indicates that undiscovered materials can be surfaced by utilizing data science and materials data, leading to an innovative way of discovering hidden materials.

Fault diagnosis of helical gearbox using acoustic signal and wavelets

NASA Astrophysics Data System (ADS)

Pranesh, SK; Abraham, Siju; Sugumaran, V.; Amarnath, M.

2017-05-01

The efficient transmission of power in machines is needed and gears are an appropriate choice. Faults in gears result in loss of energy and money. The monitoring and fault diagnosis are done by analysis of the acoustic and vibrational signals which are generally considered to be unwanted by products. This study proposes the usage of machine learning algorithm for condition monitoring of a helical gearbox by using the sound signals produced by the gearbox. Artificial faults were created and subsequently signals were captured by a microphone. An extensive study using different wavelet transformations for feature extraction from the acoustic signals was done, followed by waveletselection and feature selection using J48 decision tree and feature classification was performed using K star algorithm. Classification accuracy of 100% was obtained in the study

Impact-acoustics inspection of tile-wall bonding integrity via wavelet transform and hidden Markov models

NASA Astrophysics Data System (ADS)

Luk, B. L.; Liu, K. P.; Tong, F.; Man, K. F.

2010-05-01

The impact-acoustics method utilizes different information contained in the acoustic signals generated by tapping a structure with a small metal object. It offers a convenient and cost-efficient way to inspect the tile-wall bonding integrity. However, the existence of the surface irregularities will cause abnormal multiple bounces in the practical inspection implementations. The spectral characteristics from those bounces can easily be confused with the signals obtained from different bonding qualities. As a result, it will deteriorate the classic feature-based classification methods based on frequency domain. Another crucial difficulty posed by the implementation is the additive noise existing in the practical environments that may also cause feature mismatch and false judgment. In order to solve this problem, the work described in this paper aims to develop a robust inspection method that applies model-based strategy, and utilizes the wavelet domain features with hidden Markov modeling. It derives a bonding integrity recognition approach with enhanced immunity to surface roughness as well as the environmental noise. With the help of the specially designed artificial sample slabs, experiments have been carried out with impact acoustic signals contaminated by real environmental noises acquired under practical inspection background. The results are compared with those using classic method to demonstrate the effectiveness of the proposed method.

Simulation of groundwater level variations using wavelet combined with neural network, linear regression and support vector machine

NASA Astrophysics Data System (ADS)

Ebrahimi, Hadi; Rajaee, Taher

2017-01-01

Simulation of groundwater level (GWL) fluctuations is an important task in management of groundwater resources. In this study, the effect of wavelet analysis on the training of the artificial neural network (ANN), multi linear regression (MLR) and support vector regression (SVR) approaches was investigated, and the ANN, MLR and SVR along with the wavelet-ANN (WNN), wavelet-MLR (WLR) and wavelet-SVR (WSVR) models were compared in simulating one-month-ahead of GWL. The only variable used to develop the models was the monthly GWL data recorded over a period of 11 years from two wells in the Qom plain, Iran. The results showed that decomposing GWL time series into several sub-time series, extremely improved the training of the models. For both wells 1 and 2, the Meyer and Db5 wavelets produced better results compared to the other wavelets; which indicated wavelet types had similar behavior in similar case studies. The optimal number of delays was 6 months, which seems to be due to natural phenomena. The best WNN model, using Meyer mother wavelet with two decomposition levels, simulated one-month-ahead with RMSE values being equal to 0.069 m and 0.154 m for wells 1 and 2, respectively. The RMSE values for the WLR model were 0.058 m and 0.111 m, and for WSVR model were 0.136 m and 0.060 m for wells 1 and 2, respectively.

Time-Frequency Analyses of Tide-Gauge Sensor Data

PubMed Central

Erol, Serdar

2011-01-01

The real world phenomena being observed by sensors are generally non-stationary in nature. The classical linear techniques for analysis and modeling natural time-series observations are inefficient and should be replaced by non-linear techniques of whose theoretical aspects and performances are varied. In this manner adopting the most appropriate technique and strategy is essential in evaluating sensors’ data. In this study, two different time-series analysis approaches, namely least squares spectral analysis (LSSA) and wavelet analysis (continuous wavelet transform, cross wavelet transform and wavelet coherence algorithms as extensions of wavelet analysis), are applied to sea-level observations recorded by tide-gauge sensors, and the advantages and drawbacks of these methods are reviewed. The analyses were carried out using sea-level observations recorded at the Antalya-II and Erdek tide-gauge stations of the Turkish National Sea-Level Monitoring System. In the analyses, the useful information hidden in the noisy signals was detected, and the common features between the two sea-level time series were clarified. The tide-gauge records have data gaps in time because of issues such as instrumental shortcomings and power outages. Concerning the difficulties of the time-frequency analysis of data with voids, the sea-level observations were preprocessed, and the missing parts were predicted using the neural network method prior to the analysis. In conclusion the merits and limitations of the techniques in evaluating non-stationary observations by means of tide-gauge sensors records were documented and an analysis strategy for the sequential sensors observations was presented. PMID:22163829

Time-frequency analyses of tide-gauge sensor data.

PubMed

Erol, Serdar

2011-01-01

The real world phenomena being observed by sensors are generally non-stationary in nature. The classical linear techniques for analysis and modeling natural time-series observations are inefficient and should be replaced by non-linear techniques of whose theoretical aspects and performances are varied. In this manner adopting the most appropriate technique and strategy is essential in evaluating sensors' data. In this study, two different time-series analysis approaches, namely least squares spectral analysis (LSSA) and wavelet analysis (continuous wavelet transform, cross wavelet transform and wavelet coherence algorithms as extensions of wavelet analysis), are applied to sea-level observations recorded by tide-gauge sensors, and the advantages and drawbacks of these methods are reviewed. The analyses were carried out using sea-level observations recorded at the Antalya-II and Erdek tide-gauge stations of the Turkish National Sea-Level Monitoring System. In the analyses, the useful information hidden in the noisy signals was detected, and the common features between the two sea-level time series were clarified. The tide-gauge records have data gaps in time because of issues such as instrumental shortcomings and power outages. Concerning the difficulties of the time-frequency analysis of data with voids, the sea-level observations were preprocessed, and the missing parts were predicted using the neural network method prior to the analysis. In conclusion the merits and limitations of the techniques in evaluating non-stationary observations by means of tide-gauge sensors records were documented and an analysis strategy for the sequential sensors observations was presented.

Texture feature extraction based on wavelet transform and gray-level co-occurrence matrices applied to osteosarcoma diagnosis.

PubMed

Hu, Shan; Xu, Chao; Guan, Weiqiao; Tang, Yong; Liu, Yana

2014-01-01

Osteosarcoma is the most common malignant bone tumor among children and adolescents. In this study, image texture analysis was made to extract texture features from bone CR images to evaluate the recognition rate of osteosarcoma. To obtain the optimal set of features, Sym4 and Db4 wavelet transforms and gray-level co-occurrence matrices were applied to the image, with statistical methods being used to maximize the feature selection. To evaluate the performance of these methods, a support vector machine algorithm was used. The experimental results demonstrated that the Sym4 wavelet had a higher classification accuracy (93.44%) than the Db4 wavelet with respect to osteosarcoma occurrence in the epiphysis, whereas the Db4 wavelet had a higher classification accuracy (96.25%) for osteosarcoma occurrence in the diaphysis. Results including accuracy, sensitivity, specificity and ROC curves obtained using the wavelets were all higher than those obtained using the features derived from the GLCM method. It is concluded that, a set of texture features can be extracted from the wavelets and used in computer-aided osteosarcoma diagnosis systems. In addition, this study also confirms that multi-resolution analysis is a useful tool for texture feature extraction during bone CR image processing.

A New Method for Computed Tomography Angiography (CTA) Imaging via Wavelet Decomposition-Dependented Edge Matching Interpolation.

PubMed

Li, Zeyu; Chen, Yimin; Zhao, Yan; Zhu, Lifeng; Lv, Shengqing; Lu, Jiahui

2016-08-01

The interpolation technique of computed tomography angiography (CTA) image provides the ability for 3D reconstruction, as well as reduces the detect cost and the amount of radiation. However, most of the image interpolation algorithms cannot take the automation and accuracy into account. This study provides a new edge matching interpolation algorithm based on wavelet decomposition of CTA. It includes mark, scale and calculation (MSC). Combining the real clinical image data, this study mainly introduces how to search for proportional factor and use the root mean square operator to find a mean value. Furthermore, we re- synthesize the high frequency and low frequency parts of the processed image by wavelet inverse operation, and get the final interpolation image. MSC can make up for the shortage of the conventional Computed Tomography (CT) and Magnetic Resonance Imaging(MRI) examination. The radiation absorption and the time to check through the proposed synthesized image were significantly reduced. In clinical application, it can help doctor to find hidden lesions in time. Simultaneously, the patients get less economic burden as well as less radiation exposure absorbed.

Bilogy Machine Initiative: Developing Innovative Novel Methods to Improve Neuro-rehabilitation for Amputees and Treatment for Patients at Remote Sites with Acute Brain Injury

DTIC Science & Technology

2010-09-01

service to support the creation of both normative and pathological neuroinformatics databases. Project 3 Deliverable: The aim of this project is to...Gainesville, FL, 2010. D. Hammond, P. Vandergheynst, R. Gribonval, “ Wavelets on Graphs via Spectral Graph Theory,” Applied Computational and...the Phantom Experiments,” International Conference on Electrical Bioimpedance, April 4-8-, Gainesville, FL, 2010. 21 D. Hammond, “ Wavelets on

Wavelet-based Gaussian-mixture hidden Markov model for the detection of multistage seizure dynamics: A proof-of-concept study

PubMed Central

2011-01-01

Background Epilepsy is a common neurological disorder characterized by recurrent electrophysiological activities, known as seizures. Without the appropriate detection strategies, these seizure episodes can dramatically affect the quality of life for those afflicted. The rationale of this study is to develop an unsupervised algorithm for the detection of seizure states so that it may be implemented along with potential intervention strategies. Methods Hidden Markov model (HMM) was developed to interpret the state transitions of the in vitro rat hippocampal slice local field potentials (LFPs) during seizure episodes. It can be used to estimate the probability of state transitions and the corresponding characteristics of each state. Wavelet features were clustered and used to differentiate the electrophysiological characteristics at each corresponding HMM states. Using unsupervised training method, the HMM and the clustering parameters were obtained simultaneously. The HMM states were then assigned to the electrophysiological data using expert guided technique. Minimum redundancy maximum relevance (mRMR) analysis and Akaike Information Criterion (AICc) were applied to reduce the effect of over-fitting. The sensitivity, specificity and optimality index of chronic seizure detection were compared for various HMM topologies. The ability of distinguishing early and late tonic firing patterns prior to chronic seizures were also evaluated. Results Significant improvement in state detection performance was achieved when additional wavelet coefficient rates of change information were used as features. The final HMM topology obtained using mRMR and AICc was able to detect non-ictal (interictal), early and late tonic firing, chronic seizures and postictal activities. A mean sensitivity of 95.7%, mean specificity of 98.9% and optimality index of 0.995 in the detection of chronic seizures was achieved. The detection of early and late tonic firing was validated with experimental intracellular electrical recordings of seizures. Conclusions The HMM implementation of a seizure dynamics detector is an improvement over existing approaches using visual detection and complexity measures. The subjectivity involved in partitioning the observed data prior to training can be eliminated. It can also decipher the probabilities of seizure state transitions using the magnitude and rate of change wavelet information of the LFPs. PMID:21504608

BOOK REVIEW: The Illustrated Wavelet Transform Handbook: Introductory Theory and Applications in Science, Engineering, Medicine and Finance

NASA Astrophysics Data System (ADS)

Ng, J.; Kingsbury, N. G.

2004-02-01

This book provides an overview of the theory and practice of continuous and discrete wavelet transforms. Divided into seven chapters, the first three chapters of the book are introductory, describing the various forms of the wavelet transform and their computation, while the remaining chapters are devoted to applications in fluids, engineering, medicine and miscellaneous areas. Each chapter is well introduced, with suitable examples to demonstrate key concepts. Illustrations are included where appropriate, thus adding a visual dimension to the text. A noteworthy feature is the inclusion, at the end of each chapter, of a list of further resources from the academic literature which the interested reader can consult. The first chapter is purely an introduction to the text. The treatment of wavelet transforms begins in the second chapter, with the definition of what a wavelet is. The chapter continues by defining the continuous wavelet transform and its inverse and a description of how it may be used to interrogate signals. The continuous wavelet transform is then compared to the short-time Fourier transform. Energy and power spectra with respect to scale are also discussed and linked to their frequency counterparts. Towards the end of the chapter, the two-dimensional continuous wavelet transform is introduced. Examples of how the continuous wavelet transform is computed using the Mexican hat and Morlet wavelets are provided throughout. The third chapter introduces the discrete wavelet transform, with its distinction from the discretized continuous wavelet transform having been made clear at the end of the second chapter. In the first half of the chapter, the logarithmic discretization of the wavelet function is described, leading to a discussion of dyadic grid scaling, frames, orthogonal and orthonormal bases, scaling functions and multiresolution representation. The fast wavelet transform is introduced and its computation is illustrated with an example using the Haar wavelet. The second half of the chapter groups together miscellaneous points about the discrete wavelet transform, including coefficient manipulation for signal denoising and smoothing, a description of Daubechies’ wavelets, the properties of translation invariance and biorthogonality, the two-dimensional discrete wavelet transforms and wavelet packets. The fourth chapter is dedicated to wavelet transform methods in the author’s own specialty, fluid mechanics. Beginning with a definition of wavelet-based statistical measures for turbulence, the text proceeds to describe wavelet thresholding in the analysis of fluid flows. The remainder of the chapter describes wavelet analysis of engineering flows, in particular jets, wakes, turbulence and coherent structures, and geophysical flows, including atmospheric and oceanic processes. The fifth chapter describes the application of wavelet methods in various branches of engineering, including machining, materials, dynamics and information engineering. Unlike previous chapters, this (and subsequent) chapters are styled more as literature reviews that describe the findings of other authors. The areas addressed in this chapter include: the monitoring of machining processes, the monitoring of rotating machinery, dynamical systems, chaotic systems, non-destructive testing, surface characterization and data compression. The sixth chapter continues in this vein with the attention now turned to wavelets in the analysis of medical signals. Most of the chapter is devoted to the analysis of one-dimensional signals (electrocardiogram, neural waveforms, acoustic signals etc.), although there is a small section on the analysis of two-dimensional medical images. The seventh and final chapter of the book focuses on the application of wavelets in three seemingly unrelated application areas: fractals, finance and geophysics. The treatment on wavelet methods in fractals focuses on stochastic fractals with a short section on multifractals. The treatment on finance touches on the use of wavelets by other authors in studying stock prices, commodity behaviour, market dynamics and foreign exchange rates. The treatment on geophysics covers what was omitted from the fourth chapter, namely, seismology, well logging, topographic feature analysis and the analysis of climatic data. The text concludes with an assortment of other application areas which could only be mentioned in passing. Unlike most other publications in the subject, this book does not treat wavelet transforms in a mathematically rigorous manner but rather aims to explain the mechanics of the wavelet transform in a way that is easy to understand. Consequently, it serves as an excellent overview of the subject rather than as a reference text. Keeping the mathematics to a minimum and omitting cumbersome and detailed proofs from the text, the book is best-suited to those who are new to wavelets or who want an intuitive understanding of the subject. Such an audience may include graduate students in engineering and professionals and researchers in engineering and the applied sciences.

The application of continuous wavelet transform and least squares support vector machine for the simultaneous quantitative spectrophotometric determination of Myricetin, Kaempferol and Quercetin as flavonoids in pharmaceutical plants

NASA Astrophysics Data System (ADS)

Sohrabi, Mahmoud Reza; Darabi, Golnaz

2016-01-01

Flavonoids are γ-benzopyrone derivatives, which are highly regarded in these researchers for their antioxidant property. In this study, two new signals processing methods been coupled with UV spectroscopy for spectral resolution and simultaneous quantitative determination of Myricetin, Kaempferol and Quercetin as flavonoids in Laurel, St. John's Wort and Green Tea without the need for any previous separation procedure. The developed methods are continuous wavelet transform (CWT) and least squares support vector machine (LS-SVM) methods integrated with UV spectroscopy individually. Different wavelet families were tested by CWT method and finally the Daubechies wavelet family (Db4) for Myricetin and the Gaussian wavelet families for Kaempferol (Gaus3) and Quercetin (Gaus7) were selected and applied for simultaneous analysis under the optimal conditions. The LS-SVM was applied to build the flavonoids prediction model based on absorption spectra. The root mean square errors for prediction (RMSEP) of Myricetin, Kaempferol and Quercetin were 0.0552, 0.0275 and 0.0374, respectively. The developed methods were validated by the analysis of the various synthetic mixtures associated with a well- known flavonoid contents. Mean recovery values of Myricetin, Kaempferol and Quercetin, in CWT method were 100.123, 100.253, 100.439 and in LS-SVM method were 99.94, 99.81 and 99.682, respectively. The results achieved by analyzing the real samples from the CWT and LS-SVM methods were compared to the HPLC reference method and the results were very close to the reference method. Meanwhile, the obtained results of the one-way ANOVA (analysis of variance) test revealed that there was no significant difference between the suggested methods.

The application of continuous wavelet transform and least squares support vector machine for the simultaneous quantitative spectrophotometric determination of Myricetin, Kaempferol and Quercetin as flavonoids in pharmaceutical plants.

PubMed

Sohrabi, Mahmoud Reza; Darabi, Golnaz

2016-01-05

Flavonoids are γ-benzopyrone derivatives, which are highly regarded in these researchers for their antioxidant property. In this study, two new signals processing methods been coupled with UV spectroscopy for spectral resolution and simultaneous quantitative determination of Myricetin, Kaempferol and Quercetin as flavonoids in Laurel, St. John's Wort and Green Tea without the need for any previous separation procedure. The developed methods are continuous wavelet transform (CWT) and least squares support vector machine (LS-SVM) methods integrated with UV spectroscopy individually. Different wavelet families were tested by CWT method and finally the Daubechies wavelet family (Db4) for Myricetin and the Gaussian wavelet families for Kaempferol (Gaus3) and Quercetin (Gaus7) were selected and applied for simultaneous analysis under the optimal conditions. The LS-SVM was applied to build the flavonoids prediction model based on absorption spectra. The root mean square errors for prediction (RMSEP) of Myricetin, Kaempferol and Quercetin were 0.0552, 0.0275 and 0.0374, respectively. The developed methods were validated by the analysis of the various synthetic mixtures associated with a well- known flavonoid contents. Mean recovery values of Myricetin, Kaempferol and Quercetin, in CWT method were 100.123, 100.253, 100.439 and in LS-SVM method were 99.94, 99.81 and 99.682, respectively. The results achieved by analyzing the real samples from the CWT and LS-SVM methods were compared to the HPLC reference method and the results were very close to the reference method. Meanwhile, the obtained results of the one-way ANOVA (analysis of variance) test revealed that there was no significant difference between the suggested methods. Copyright © 2015 Elsevier B.V. All rights reserved.

Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses

NASA Astrophysics Data System (ADS)

Huang, Haiping

2017-05-01

Revealing hidden features in unlabeled data is called unsupervised feature learning, which plays an important role in pretraining a deep neural network. Here we provide a statistical mechanics analysis of the unsupervised learning in a restricted Boltzmann machine with binary synapses. A message passing equation to infer the hidden feature is derived, and furthermore, variants of this equation are analyzed. A statistical analysis by replica theory describes the thermodynamic properties of the model. Our analysis confirms an entropy crisis preceding the non-convergence of the message passing equation, suggesting a discontinuous phase transition as a key characteristic of the restricted Boltzmann machine. Continuous phase transition is also confirmed depending on the embedded feature strength in the data. The mean-field result under the replica symmetric assumption agrees with that obtained by running message passing algorithms on single instances of finite sizes. Interestingly, in an approximate Hopfield model, the entropy crisis is absent, and a continuous phase transition is observed instead. We also develop an iterative equation to infer the hyper-parameter (temperature) hidden in the data, which in physics corresponds to iteratively imposing Nishimori condition. Our study provides insights towards understanding the thermodynamic properties of the restricted Boltzmann machine learning, and moreover important theoretical basis to build simplified deep networks.

Gait recognition based on Gabor wavelets and modified gait energy image for human identification

NASA Astrophysics Data System (ADS)

Huang, Deng-Yuan; Lin, Ta-Wei; Hu, Wu-Chih; Cheng, Chih-Hsiang

2013-10-01

This paper proposes a method for recognizing human identity using gait features based on Gabor wavelets and modified gait energy images (GEIs). Identity recognition by gait generally involves gait representation, extraction, and classification. In this work, a modified GEI convolved with an ensemble of Gabor wavelets is proposed as a gait feature. Principal component analysis is then used to project the Gabor-wavelet-based gait features into a lower-dimension feature space for subsequent classification. Finally, support vector machine classifiers based on a radial basis function kernel are trained and utilized to recognize human identity. The major contributions of this paper are as follows: (1) the consideration of the shadow effect to yield a more complete segmentation of gait silhouettes; (2) the utilization of motion estimation to track people when walkers overlap; and (3) the derivation of modified GEIs to extract more useful gait information. Extensive performance evaluation shows a great improvement of recognition accuracy due to the use of shadow removal, motion estimation, and gait representation using the modified GEIs and Gabor wavelets.

Exploring the impact of wavelet-based denoising in the classification of remote sensing hyperspectral images

NASA Astrophysics Data System (ADS)

Quesada-Barriuso, Pablo; Heras, Dora B.; Argüello, Francisco

2016-10-01

The classification of remote sensing hyperspectral images for land cover applications is a very intensive topic. In the case of supervised classification, Support Vector Machines (SVMs) play a dominant role. Recently, the Extreme Learning Machine algorithm (ELM) has been extensively used. The classification scheme previously published by the authors, and called WT-EMP, introduces spatial information in the classification process by means of an Extended Morphological Profile (EMP) that is created from features extracted by wavelets. In addition, the hyperspectral image is denoised in the 2-D spatial domain, also using wavelets and it is joined to the EMP via a stacked vector. In this paper, the scheme is improved achieving two goals. The first one is to reduce the classification time while preserving the accuracy of the classification by using ELM instead of SVM. The second one is to improve the accuracy results by performing not only a 2-D denoising for every spectral band, but also a previous additional 1-D spectral signature denoising applied to each pixel vector of the image. For each denoising the image is transformed by applying a 1-D or 2-D wavelet transform, and then a NeighShrink thresholding is applied. Improvements in terms of classification accuracy are obtained, especially for images with close regions in the classification reference map, because in these cases the accuracy of the classification in the edges between classes is more relevant.

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

NASA Astrophysics Data System (ADS)

Cornejo-Bueno, L.; Casanova-Mateo, C.; Sanz-Justo, J.; Cerro-Prada, E.; Salcedo-Sanz, S.

2017-11-01

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is {>}1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ({<}500 m). However, we show improved results of all the methods when data from a neighbouring meteorological tower are included, and also with a pre-processing scheme using a wavelet transform. Also presented are results of the algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.

Hidden Markov models and other machine learning approaches in computational molecular biology

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

Baldi, P.

1995-12-31

This tutorial was one of eight tutorials selected to be presented at the Third International Conference on Intelligent Systems for Molecular Biology which was held in the United Kingdom from July 16 to 19, 1995. Computational tools are increasingly needed to process the massive amounts of data, to organize and classify sequences, to detect weak similarities, to separate coding from non-coding regions, and reconstruct the underlying evolutionary history. The fundamental problem in machine learning is the same as in scientific reasoning in general, as well as statistical modeling: to come up with a good model for the data. In thismore » tutorial four classes of models are reviewed. They are: Hidden Markov models; artificial Neural Networks; Belief Networks; and Stochastic Grammars. When dealing with DNA and protein primary sequences, Hidden Markov models are one of the most flexible and powerful alignments and data base searches. In this tutorial, attention is focused on the theory of Hidden Markov Models, and how to apply them to problems in molecular biology.« less

An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects.

PubMed

Kim, Jinkwon; Min, Se Dong; Lee, Myoungho

2011-06-27

Numerous studies have been conducted regarding a heartbeat classification algorithm over the past several decades. However, many algorithms have also been studied to acquire robust performance, as biosignals have a large amount of variation among individuals. Various methods have been proposed to reduce the differences coming from personal characteristics, but these expand the differences caused by arrhythmia. In this paper, an arrhythmia classification algorithm using a dedicated wavelet adapted to individual subjects is proposed. We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects. The proposed algorithm utilizes morphological filtering and a continuous wavelet transform with a dedicated wavelet. A principal component analysis and linear discriminant analysis were utilized to compress the morphological data transformed by the dedicated wavelets. An extreme learning machine was used as a classifier in the proposed algorithm. A performance evaluation was conducted with the MIT-BIH arrhythmia database. The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%. The proposed algorithm achieves better accuracy than other state-of-the-art algorithms with no intrasubject between the training and evaluation datasets. And it significantly reduces the amount of intervention needed by physicians.

An arrhythmia classification algorithm using a dedicated wavelet adapted to different subjects

PubMed Central

2011-01-01

Background Numerous studies have been conducted regarding a heartbeat classification algorithm over the past several decades. However, many algorithms have also been studied to acquire robust performance, as biosignals have a large amount of variation among individuals. Various methods have been proposed to reduce the differences coming from personal characteristics, but these expand the differences caused by arrhythmia. Methods In this paper, an arrhythmia classification algorithm using a dedicated wavelet adapted to individual subjects is proposed. We reduced the performance variation using dedicated wavelets, as in the ECG morphologies of the subjects. The proposed algorithm utilizes morphological filtering and a continuous wavelet transform with a dedicated wavelet. A principal component analysis and linear discriminant analysis were utilized to compress the morphological data transformed by the dedicated wavelets. An extreme learning machine was used as a classifier in the proposed algorithm. Results A performance evaluation was conducted with the MIT-BIH arrhythmia database. The results showed a high sensitivity of 97.51%, specificity of 85.07%, accuracy of 97.94%, and a positive predictive value of 97.26%. Conclusions The proposed algorithm achieves better accuracy than other state-of-the-art algorithms with no intrasubject between the training and evaluation datasets. And it significantly reduces the amount of intervention needed by physicians. PMID:21707989

Exploring an optimal wavelet-based filter for cryo-ET imaging.

PubMed

Huang, Xinrui; Li, Sha; Gao, Song

2018-02-07

Cryo-electron tomography (cryo-ET) is one of the most advanced technologies for the in situ visualization of molecular machines by producing three-dimensional (3D) biological structures. However, cryo-ET imaging has two serious disadvantages-low dose and low image contrast-which result in high-resolution information being obscured by noise and image quality being degraded, and this causes errors in biological interpretation. The purpose of this research is to explore an optimal wavelet denoising technique to reduce noise in cryo-ET images. We perform tests using simulation data and design a filter using the optimum selected wavelet parameters (three-level decomposition, level-1 zeroed out, subband-dependent threshold, a soft-thresholding and spline-based discrete dyadic wavelet transform (DDWT)), which we call a modified wavelet shrinkage filter; this filter is suitable for noisy cryo-ET data. When testing using real cryo-ET experiment data, higher quality images and more accurate measures of a biological structure can be obtained with the modified wavelet shrinkage filter processing compared with conventional processing. Because the proposed method provides an inherent advantage when dealing with cryo-ET images, it can therefore extend the current state-of-the-art technology in assisting all aspects of cryo-ET studies: visualization, reconstruction, structural analysis, and interpretation.

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.

Fuzzy wavelet plus a quantum neural network as a design base for power system stability enhancement.

PubMed

Ganjefar, Soheil; Tofighi, Morteza; Karami, Hamidreza

2015-11-01

In this study, we introduce an indirect adaptive fuzzy wavelet neural controller (IAFWNC) as a power system stabilizer to damp inter-area modes of oscillations in a multi-machine power system. Quantum computing is an efficient method for improving the computational efficiency of neural networks, so we developed an identifier based on a quantum neural network (QNN) to train the IAFWNC in the proposed scheme. All of the controller parameters are tuned online based on the Lyapunov stability theory to guarantee the closed-loop stability. A two-machine, two-area power system equipped with a static synchronous series compensator as a series flexible ac transmission system was used to demonstrate the effectiveness of the proposed controller. The simulation and experimental results demonstrated that the proposed IAFWNC scheme can achieve favorable control performance. Copyright © 2015 Elsevier Ltd. All rights reserved.

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.

Dynamic extreme learning machine and its approximation capability.

PubMed

Zhang, Rui; Lan, Yuan; Huang, Guang-Bin; Xu, Zong-Ben; Soh, Yeng Chai

2013-12-01

Extreme learning machines (ELMs) have been proposed for generalized single-hidden-layer feedforward networks which need not be neuron alike and perform well in both regression and classification applications. The problem of determining the suitable network architectures is recognized to be crucial in the successful application of ELMs. This paper first proposes a dynamic ELM (D-ELM) where the hidden nodes can be recruited or deleted dynamically according to their significance to network performance, so that not only the parameters can be adjusted but also the architecture can be self-adapted simultaneously. Then, this paper proves in theory that such D-ELM using Lebesgue p-integrable hidden activation functions can approximate any Lebesgue p-integrable function on a compact input set. Simulation results obtained over various test problems demonstrate and verify that the proposed D-ELM does a good job reducing the network size while preserving good generalization performance.

Shedding Light on Synergistic Chemical Genetic Connections with Machine Learning.

PubMed

Ekins, Sean; Siqueira-Neto, Jair Lage

2015-12-23

Machine learning can be used to predict compounds acting synergistically, and this could greatly expand the universe of available potential treatments for diseases that are currently hidden in the dark chemical matter. Copyright © 2015 Elsevier Inc. All rights reserved.

Online Sequential Projection Vector Machine with Adaptive Data Mean Update

PubMed Central

Chen, Lin; Jia, Ji-Ting; Zhang, Qiong; Deng, Wan-Yu; Wei, Wei

2016-01-01

We propose a simple online learning algorithm especial for high-dimensional data. The algorithm is referred to as online sequential projection vector machine (OSPVM) which derives from projection vector machine and can learn from data in one-by-one or chunk-by-chunk mode. In OSPVM, data centering, dimension reduction, and neural network training are integrated seamlessly. In particular, the model parameters including (1) the projection vectors for dimension reduction, (2) the input weights, biases, and output weights, and (3) the number of hidden nodes can be updated simultaneously. Moreover, only one parameter, the number of hidden nodes, needs to be determined manually, and this makes it easy for use in real applications. Performance comparison was made on various high-dimensional classification problems for OSPVM against other fast online algorithms including budgeted stochastic gradient descent (BSGD) approach, adaptive multihyperplane machine (AMM), primal estimated subgradient solver (Pegasos), online sequential extreme learning machine (OSELM), and SVD + OSELM (feature selection based on SVD is performed before OSELM). The results obtained demonstrated the superior generalization performance and efficiency of the OSPVM. PMID:27143958

Online Sequential Projection Vector Machine with Adaptive Data Mean Update.

PubMed

Chen, Lin; Jia, Ji-Ting; Zhang, Qiong; Deng, Wan-Yu; Wei, Wei

2016-01-01

We propose a simple online learning algorithm especial for high-dimensional data. The algorithm is referred to as online sequential projection vector machine (OSPVM) which derives from projection vector machine and can learn from data in one-by-one or chunk-by-chunk mode. In OSPVM, data centering, dimension reduction, and neural network training are integrated seamlessly. In particular, the model parameters including (1) the projection vectors for dimension reduction, (2) the input weights, biases, and output weights, and (3) the number of hidden nodes can be updated simultaneously. Moreover, only one parameter, the number of hidden nodes, needs to be determined manually, and this makes it easy for use in real applications. Performance comparison was made on various high-dimensional classification problems for OSPVM against other fast online algorithms including budgeted stochastic gradient descent (BSGD) approach, adaptive multihyperplane machine (AMM), primal estimated subgradient solver (Pegasos), online sequential extreme learning machine (OSELM), and SVD + OSELM (feature selection based on SVD is performed before OSELM). The results obtained demonstrated the superior generalization performance and efficiency of the OSPVM.

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning

PubMed Central

Wang, Shuihua; Yang, Ming; Du, Sidan; Yang, Jiquan; Liu, Bin; Gorriz, Juan M.; Ramírez, Javier; Yuan, Ti-Fei; Zhang, Yudong

2016-01-01

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way. Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC). Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM). Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier. Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss. PMID:27807415

Wavelet Entropy and Directed Acyclic Graph Support Vector Machine for Detection of Patients with Unilateral Hearing Loss in MRI Scanning.

PubMed

Wang, Shuihua; Yang, Ming; Du, Sidan; Yang, Jiquan; Liu, Bin; Gorriz, Juan M; Ramírez, Javier; Yuan, Ti-Fei; Zhang, Yudong

2016-01-01

Highlights We develop computer-aided diagnosis system for unilateral hearing loss detection in structural magnetic resonance imaging.Wavelet entropy is introduced to extract image global features from brain images. Directed acyclic graph is employed to endow support vector machine an ability to handle multi-class problems.The developed computer-aided diagnosis system achieves an overall accuracy of 95.1% for this three-class problem of differentiating left-sided and right-sided hearing loss from healthy controls. Aim: Sensorineural hearing loss (SNHL) is correlated to many neurodegenerative disease. Now more and more computer vision based methods are using to detect it in an automatic way. Materials: We have in total 49 subjects, scanned by 3.0T MRI (Siemens Medical Solutions, Erlangen, Germany). The subjects contain 14 patients with right-sided hearing loss (RHL), 15 patients with left-sided hearing loss (LHL), and 20 healthy controls (HC). Method: We treat this as a three-class classification problem: RHL, LHL, and HC. Wavelet entropy (WE) was selected from the magnetic resonance images of each subjects, and then submitted to a directed acyclic graph support vector machine (DAG-SVM). Results: The 10 repetition results of 10-fold cross validation shows 3-level decomposition will yield an overall accuracy of 95.10% for this three-class classification problem, higher than feedforward neural network, decision tree, and naive Bayesian classifier. Conclusions: This computer-aided diagnosis system is promising. We hope this study can attract more computer vision method for detecting hearing loss.

Diverse Effects, Complex Causes: Children Use Information about Machines' Functional Diversity to Infer Internal Complexity

ERIC Educational Resources Information Center

Ahl, Richard E.; Keil, Frank C.

2017-01-01

Four studies explored the abilities of 80 adults and 180 children (4-9 years), from predominantly middle-class families in the Northeastern United States, to use information about machines' observable functional capacities to infer their internal, "hidden" mechanistic complexity. Children as young as 4 and 5 years old used machines'…

Sparsity guided empirical wavelet transform for fault diagnosis of rolling element bearings

NASA Astrophysics Data System (ADS)

Wang, Dong; Zhao, Yang; Yi, Cai; Tsui, Kwok-Leung; Lin, Jianhui

2018-02-01

Rolling element bearings are widely used in various industrial machines, such as electric motors, generators, pumps, gearboxes, railway axles, turbines, and helicopter transmissions. Fault diagnosis of rolling element bearings is beneficial to preventing any unexpected accident and reducing economic loss. In the past years, many bearing fault detection methods have been developed. Recently, a new adaptive signal processing method called empirical wavelet transform attracts much attention from readers and engineers and its applications to bearing fault diagnosis have been reported. The main problem of empirical wavelet transform is that Fourier segments required in empirical wavelet transform are strongly dependent on the local maxima of the amplitudes of the Fourier spectrum of a signal, which connotes that Fourier segments are not always reliable and effective if the Fourier spectrum of the signal is complicated and overwhelmed by heavy noises and other strong vibration components. In this paper, sparsity guided empirical wavelet transform is proposed to automatically establish Fourier segments required in empirical wavelet transform for fault diagnosis of rolling element bearings. Industrial bearing fault signals caused by single and multiple railway axle bearing defects are used to verify the effectiveness of the proposed sparsity guided empirical wavelet transform. Results show that the proposed method can automatically discover Fourier segments required in empirical wavelet transform and reveal single and multiple railway axle bearing defects. Besides, some comparisons with three popular signal processing methods including ensemble empirical mode decomposition, the fast kurtogram and the fast spectral correlation are conducted to highlight the superiority of the proposed method.

Bayesian structural inference for hidden processes.

PubMed

Strelioff, Christopher C; Crutchfield, James P

2014-04-01

We introduce a Bayesian approach to discovering patterns in structurally complex processes. The proposed method of Bayesian structural inference (BSI) relies on a set of candidate unifilar hidden Markov model (uHMM) topologies for inference of process structure from a data series. We employ a recently developed exact enumeration of topological ε-machines. (A sequel then removes the topological restriction.) This subset of the uHMM topologies has the added benefit that inferred models are guaranteed to be ε-machines, irrespective of estimated transition probabilities. Properties of ε-machines and uHMMs allow for the derivation of analytic expressions for estimating transition probabilities, inferring start states, and comparing the posterior probability of candidate model topologies, despite process internal structure being only indirectly present in data. We demonstrate BSI's effectiveness in estimating a process's randomness, as reflected by the Shannon entropy rate, and its structure, as quantified by the statistical complexity. We also compare using the posterior distribution over candidate models and the single, maximum a posteriori model for point estimation and show that the former more accurately reflects uncertainty in estimated values. We apply BSI to in-class examples of finite- and infinite-order Markov processes, as well to an out-of-class, infinite-state hidden process.

Bayesian structural inference for hidden processes

NASA Astrophysics Data System (ADS)

Strelioff, Christopher C.; Crutchfield, James P.

2014-04-01

We introduce a Bayesian approach to discovering patterns in structurally complex processes. The proposed method of Bayesian structural inference (BSI) relies on a set of candidate unifilar hidden Markov model (uHMM) topologies for inference of process structure from a data series. We employ a recently developed exact enumeration of topological ɛ-machines. (A sequel then removes the topological restriction.) This subset of the uHMM topologies has the added benefit that inferred models are guaranteed to be ɛ-machines, irrespective of estimated transition probabilities. Properties of ɛ-machines and uHMMs allow for the derivation of analytic expressions for estimating transition probabilities, inferring start states, and comparing the posterior probability of candidate model topologies, despite process internal structure being only indirectly present in data. We demonstrate BSI's effectiveness in estimating a process's randomness, as reflected by the Shannon entropy rate, and its structure, as quantified by the statistical complexity. We also compare using the posterior distribution over candidate models and the single, maximum a posteriori model for point estimation and show that the former more accurately reflects uncertainty in estimated values. We apply BSI to in-class examples of finite- and infinite-order Markov processes, as well to an out-of-class, infinite-state hidden process.

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.

Rendering of 3D-wavelet-compressed concentric mosaic scenery with progressive inverse wavelet synthesis (PIWS)

NASA Astrophysics Data System (ADS)

Wu, Yunnan; Luo, Lin; Li, Jin; Zhang, Ya-Qin

2000-05-01

The concentric mosaics offer a quick solution to the construction and navigation of a virtual environment. To reduce the vast data amount of the concentric mosaics, a compression scheme based on 3D wavelet transform has been proposed in a previous paper. In this work, we investigate the efficient implementation of the renderer. It is preferable not to expand the compressed bitstream as a whole, so that the memory consumption of the renderer can be reduced. Instead, only the data necessary to render the current view are accessed and decoded. The progressive inverse wavelet synthesis (PIWS) algorithm is proposed to provide the random data access and to reduce the calculation for the data access requests to a minimum. A mixed cache is used in PIWS, where the entropy decoded wavelet coefficient, intermediate result of lifting and fully synthesized pixel are all stored at the same memory unit because of the in- place calculation property of the lifting implementation. PIWS operates with a finite state machine, where each memory unit is attached with a state to indicate what type of content is currently stored. The computational saving achieved by PIWS is demonstrated with extensive experiment results.

Morphological and wavelet features towards sonographic thyroid nodules evaluation.

PubMed

Tsantis, Stavros; Dimitropoulos, Nikos; Cavouras, Dionisis; Nikiforidis, George

2009-03-01

This paper presents a computer-based classification scheme that utilized various morphological and novel wavelet-based features towards malignancy risk evaluation of thyroid nodules in ultrasonography. The study comprised 85 ultrasound images-patients that were cytological confirmed (54 low-risk and 31 high-risk). A set of 20 features (12 based on nodules boundary shape and 8 based on wavelet local maxima located within each nodule) has been generated. Two powerful pattern recognition algorithms (support vector machines and probabilistic neural networks) have been designed and developed in order to quantify the power of differentiation of the introduced features. A comparative study has also been held, in order to estimate the impact speckle had onto the classification procedure. The diagnostic sensitivity and specificity of both classifiers was made by means of receiver operating characteristics (ROC) analysis. In the speckle-free feature set, the area under the ROC curve was 0.96 for the support vector machines classifier whereas for the probabilistic neural networks was 0.91. In the feature set with speckle, the corresponding areas under the ROC curves were 0.88 and 0.86 respectively for the two classifiers. The proposed features can increase the classification accuracy and decrease the rate of missing and misdiagnosis in thyroid cancer control.

Machine Learning for Biological Trajectory Classification Applications

NASA Technical Reports Server (NTRS)

Sbalzarini, Ivo F.; Theriot, Julie; Koumoutsakos, Petros

2002-01-01

Machine-learning techniques, including clustering algorithms, support vector machines and hidden Markov models, are applied to the task of classifying trajectories of moving keratocyte cells. The different algorithms axe compared to each other as well as to expert and non-expert test persons, using concepts from signal-detection theory. The algorithms performed very well as compared to humans, suggesting a robust tool for trajectory classification in biological applications.

Scalable learning method for feedforward neural networks using minimal-enclosing-ball approximation.

PubMed

Wang, Jun; Deng, Zhaohong; Luo, Xiaoqing; Jiang, Yizhang; Wang, Shitong

2016-06-01

Training feedforward neural networks (FNNs) is one of the most critical issues in FNNs studies. However, most FNNs training methods cannot be directly applied for very large datasets because they have high computational and space complexity. In order to tackle this problem, the CCMEB (Center-Constrained Minimum Enclosing Ball) problem in hidden feature space of FNN is discussed and a novel learning algorithm called HFSR-GCVM (hidden-feature-space regression using generalized core vector machine) is developed accordingly. In HFSR-GCVM, a novel learning criterion using L2-norm penalty-based ε-insensitive function is formulated and the parameters in the hidden nodes are generated randomly independent of the training sets. Moreover, the learning of parameters in its output layer is proved equivalent to a special CCMEB problem in FNN hidden feature space. As most CCMEB approximation based machine learning algorithms, the proposed HFSR-GCVM training algorithm has the following merits: The maximal training time of the HFSR-GCVM training is linear with the size of training datasets and the maximal space consumption is independent of the size of training datasets. The experiments on regression tasks confirm the above conclusions. Copyright © 2016 Elsevier Ltd. All rights reserved.

Predictability and Market Efficiency in Agricultural Futures Markets: a Perspective from Price-Volume Correlation Based on Wavelet Coherency Analysis

NASA Astrophysics Data System (ADS)

He, Ling-Yun; Wen, Xing-Chun

2015-12-01

In this paper, we use a time-frequency domain technique, namely, wavelet squared coherency, to examine the associations between the trading volumes of three agricultural futures and three different forms of these futures' daily closing prices, i.e. prices, returns and volatilities, over the past several years. These agricultural futures markets are selected from China as a typical case of the emerging countries, and from the US as a representative of the developed economies. We investigate correlations and lead-lag relationships between the trading volumes and the prices to detect the predictability and efficiency of these futures markets. The results suggest that the information contained in the trading volumes of the three agricultural futures markets in China can be applied to predict the prices or returns, while that in US has extremely weak predictive power for prices or returns. We also conduct the wavelet analysis on the relationships between the volumes and returns or volatilities to examine the existence of the two "stylized facts" proposed by Karpoff [J. M. Karpoff, The relation between price changes and trading volume: A survey, J. Financ. Quant. Anal.22(1) (1987) 109-126]. Different markets in the two countries perform differently in reproducing the two stylized facts. As the wavelet tools can decode nonlinear regularities and hidden patterns behind price-volume relationship in time-frequency space, different from the conventional econometric framework, this paper offers a new perspective into the market predictability and efficiency.

Wavelet analysis in ecology and epidemiology: impact of statistical tests

PubMed Central

Cazelles, Bernard; Cazelles, Kévin; Chavez, Mario

2014-01-01

Wavelet analysis is now frequently used to extract information from ecological and epidemiological time series. Statistical hypothesis tests are conducted on associated wavelet quantities to assess the likelihood that they are due to a random process. Such random processes represent null models and are generally based on synthetic data that share some statistical characteristics with the original time series. This allows the comparison of null statistics with those obtained from original time series. When creating synthetic datasets, different techniques of resampling result in different characteristics shared by the synthetic time series. Therefore, it becomes crucial to consider the impact of the resampling method on the results. We have addressed this point by comparing seven different statistical testing methods applied with different real and simulated data. Our results show that statistical assessment of periodic patterns is strongly affected by the choice of the resampling method, so two different resampling techniques could lead to two different conclusions about the same time series. Moreover, our results clearly show the inadequacy of resampling series generated by white noise and red noise that are nevertheless the methods currently used in the wide majority of wavelets applications. Our results highlight that the characteristics of a time series, namely its Fourier spectrum and autocorrelation, are important to consider when choosing the resampling technique. Results suggest that data-driven resampling methods should be used such as the hidden Markov model algorithm and the ‘beta-surrogate’ method. PMID:24284892

Wavelet analysis in ecology and epidemiology: impact of statistical tests.

PubMed

Cazelles, Bernard; Cazelles, Kévin; Chavez, Mario

2014-02-06

Wavelet analysis is now frequently used to extract information from ecological and epidemiological time series. Statistical hypothesis tests are conducted on associated wavelet quantities to assess the likelihood that they are due to a random process. Such random processes represent null models and are generally based on synthetic data that share some statistical characteristics with the original time series. This allows the comparison of null statistics with those obtained from original time series. When creating synthetic datasets, different techniques of resampling result in different characteristics shared by the synthetic time series. Therefore, it becomes crucial to consider the impact of the resampling method on the results. We have addressed this point by comparing seven different statistical testing methods applied with different real and simulated data. Our results show that statistical assessment of periodic patterns is strongly affected by the choice of the resampling method, so two different resampling techniques could lead to two different conclusions about the same time series. Moreover, our results clearly show the inadequacy of resampling series generated by white noise and red noise that are nevertheless the methods currently used in the wide majority of wavelets applications. Our results highlight that the characteristics of a time series, namely its Fourier spectrum and autocorrelation, are important to consider when choosing the resampling technique. Results suggest that data-driven resampling methods should be used such as the hidden Markov model algorithm and the 'beta-surrogate' method.

Highly Productive Tools For Turning And Milling

NASA Astrophysics Data System (ADS)

Vasilko, Karol

2015-12-01

Beside cutting speed, shift is another important parameter of machining. Its considerable influence is shown mainly in the workpiece machined surface microgeometry. In practice, mainly its combination with the radius of cutting tool tip rounding is used. Options to further increase machining productivity and machined surface quality are hidden in this approach. The paper presents variations of the design of productive cutting tools for lathe work and milling on the base of the use of the laws of the relationship among the highest reached uneveness of machined surface, tool tip radius and shift.

Multi-category micro-milling tool wear monitoring with continuous hidden Markov models

NASA Astrophysics Data System (ADS)

Zhu, Kunpeng; Wong, Yoke San; Hong, Geok Soon

2009-02-01

In-process monitoring of tool conditions is important in micro-machining due to the high precision requirement and high tool wear rate. Tool condition monitoring in micro-machining poses new challenges compared to conventional machining. In this paper, a multi-category classification approach is proposed for tool flank wear state identification in micro-milling. Continuous Hidden Markov models (HMMs) are adapted for modeling of the tool wear process in micro-milling, and estimation of the tool wear state given the cutting force features. For a noise-robust approach, the HMM outputs are connected via a medium filter to minimize the tool state before entry into the next state due to high noise level. A detailed study on the selection of HMM structures for tool condition monitoring (TCM) is presented. Case studies on the tool state estimation in the micro-milling of pure copper and steel demonstrate the effectiveness and potential of these methods.

Virtual screening by a new Clustering-based Weighted Similarity Extreme Learning Machine approach

PubMed Central

Kudisthalert, Wasu

2018-01-01

Machine learning techniques are becoming popular in virtual screening tasks. One of the powerful machine learning algorithms is Extreme Learning Machine (ELM) which has been applied to many applications and has recently been applied to virtual screening. We propose the Weighted Similarity ELM (WS-ELM) which is based on a single layer feed-forward neural network in a conjunction of 16 different similarity coefficients as activation function in the hidden layer. It is known that the performance of conventional ELM is not robust due to random weight selection in the hidden layer. Thus, we propose a Clustering-based WS-ELM (CWS-ELM) that deterministically assigns weights by utilising clustering algorithms i.e. k-means clustering and support vector clustering. The experiments were conducted on one of the most challenging datasets–Maximum Unbiased Validation Dataset–which contains 17 activity classes carefully selected from PubChem. The proposed algorithms were then compared with other machine learning techniques such as support vector machine, random forest, and similarity searching. The results show that CWS-ELM in conjunction with support vector clustering yields the best performance when utilised together with Sokal/Sneath(1) coefficient. Furthermore, ECFP_6 fingerprint presents the best results in our framework compared to the other types of fingerprints, namely ECFP_4, FCFP_4, and FCFP_6. PMID:29652912

Automated Diagnosis of Glaucoma Using Empirical Wavelet Transform and Correntropy Features Extracted From Fundus Images.

PubMed

Maheshwari, Shishir; Pachori, Ram Bilas; Acharya, U Rajendra

2017-05-01

Glaucoma is an ocular disorder caused due to increased fluid pressure in the optic nerve. It damages the optic nerve and subsequently causes loss of vision. The available scanning methods are Heidelberg retinal tomography, scanning laser polarimetry, and optical coherence tomography. These methods are expensive and require experienced clinicians to use them. So, there is a need to diagnose glaucoma accurately with low cost. Hence, in this paper, we have presented a new methodology for an automated diagnosis of glaucoma using digital fundus images based on empirical wavelet transform (EWT). The EWT is used to decompose the image, and correntropy features are obtained from decomposed EWT components. These extracted features are ranked based on t value feature selection algorithm. Then, these features are used for the classification of normal and glaucoma images using least-squares support vector machine (LS-SVM) classifier. The LS-SVM is employed for classification with radial basis function, Morlet wavelet, and Mexican-hat wavelet kernels. The classification accuracy of the proposed method is 98.33% and 96.67% using threefold and tenfold cross validation, respectively.

Wavelet multiresolution complex network for decoding brain fatigued behavior from P300 signals

NASA Astrophysics Data System (ADS)

Gao, Zhong-Ke; Wang, Zi-Bo; Yang, Yu-Xuan; Li, Shan; Dang, Wei-Dong; Mao, Xiao-Qian

2018-09-01

Brain-computer interface (BCI) enables users to interact with the environment without relying on neural pathways and muscles. P300 based BCI systems have been extensively used to achieve human-machine interaction. However, the appearance of fatigue symptoms during operation process leads to the decline in classification accuracy of P300. Characterizing brain cognitive process underlying normal and fatigue conditions constitutes a problem of vital importance in the field of brain science. We in this paper propose a novel wavelet decomposition based complex network method to efficiently analyze the P300 signals recorded in the image stimulus test based on classical 'Oddball' paradigm. Initially, multichannel EEG signals are decomposed into wavelet coefficient series. Then we construct complex network by treating electrodes as nodes and determining the connections according to the 2-norm distances between wavelet coefficient series. The analysis of topological structure and statistical index indicates that the properties of brain network demonstrate significant distinctions between normal status and fatigue status. More specifically, the brain network reconfiguration in response to the cognitive task in fatigue status is reflected as the enhancement of the small-worldness.

New micro waveforms firstly recorded on electrocardiogram in human.

PubMed

Liu, Renguang; Chang, Qinghua; Chen, Juan

2015-10-01

In our study, not only the P-QRS-T waves but also the micro-wavelets before QRS complex (in P wave and PR segment) and after QRS complex (ST segment and upstroke of T wave) were first to be identified on surface electrocardiogram in human by the "new electrocardiogram" machine (model PHS-A10) according to conventional 12-lead electrocardiogram connection methods. By comparison to the conventional electrocardiogram in 100 cases of healthy individuals and several patients with arrhythmias, we have found that the wavelets before P wave theoretically reflected electrical activity of sinus node and the micro-wavelets before QRS complex may be related to atrioventricular conduction system (atrioventricular node, His bundle and bundle branch) potentials. Noninvasive atrioventricular node and His bundle potential tracing will contribute to differentiation of the origin of wide QRS and the location of the atrioventricular block. We also have found that the wavelets after QRS complex may be associated with phase 2 and 3 repolarization of ventricular action potential, which will further reveal ventricular repolarization changes. Copyright © 2015 Elsevier Ltd. All rights reserved.

Wavelet transform processing applied to partial discharge evaluation

NASA Astrophysics Data System (ADS)

Macedo, E. C. T.; Araújo, D. B.; da Costa, E. G.; Freire, R. C. S.; Lopes, W. T. A.; Torres, I. S. M.; de Souza Neto, J. M. R.; Bhatti, S. A.; Glover, I. A.

2012-05-01

Partial Discharge (PD) is characterized by high frequency current pulses that occur in high voltage (HV) electrical equipments originated from gas ionization process when damaged insulation is submitted to high values of electric field [1]. PD monitoring is a useful method of assessing the aging degree of the insulation, manufacturing defects or chemical/mechanical damage. Many sources of noise (e.g. radio transmissions, commutator noise from rotating machines, power electronics switching circuits, corona discharge, etc.) can directly affect the PD estimation. Among the many mathematical techniques that can be applied to de-noise PD signals, the wavelet transform is one of the most powerful. It can simultaneously supply information about the pulse occurrence, time and pulse spectrum, and also de-noise in-field measured PD signals. In this paper is described the application of wavelet transform in the suppression of the main types of noise that can affect the observation and analysis of PD signals in high voltage apparatus. In addition, is presented a study that indicates the appropriated mother-wavelet for this application based on the cross-correlation factor.

Variable complexity online sequential extreme learning machine, with applications to streamflow prediction

NASA Astrophysics Data System (ADS)

Lima, Aranildo R.; Hsieh, William W.; Cannon, Alex J.

2017-12-01

In situations where new data arrive continually, online learning algorithms are computationally much less costly than batch learning ones in maintaining the model up-to-date. The extreme learning machine (ELM), a single hidden layer artificial neural network with random weights in the hidden layer, is solved by linear least squares, and has an online learning version, the online sequential ELM (OSELM). As more data become available during online learning, information on the longer time scale becomes available, so ideally the model complexity should be allowed to change, but the number of hidden nodes (HN) remains fixed in OSELM. A variable complexity VC-OSELM algorithm is proposed to dynamically add or remove HN in the OSELM, allowing the model complexity to vary automatically as online learning proceeds. The performance of VC-OSELM was compared with OSELM in daily streamflow predictions at two hydrological stations in British Columbia, Canada, with VC-OSELM significantly outperforming OSELM in mean absolute error, root mean squared error and Nash-Sutcliffe efficiency at both stations.

A Hybrid Generalized Hidden Markov Model-Based Condition Monitoring Approach for Rolling Bearings

PubMed Central

Liu, Jie; Hu, Youmin; Wu, Bo; Wang, Yan; Xie, Fengyun

2017-01-01

The operating condition of rolling bearings affects productivity and quality in the rotating machine process. Developing an effective rolling bearing condition monitoring approach is critical to accurately identify the operating condition. In this paper, a hybrid generalized hidden Markov model-based condition monitoring approach for rolling bearings is proposed, where interval valued features are used to efficiently recognize and classify machine states in the machine process. In the proposed method, vibration signals are decomposed into multiple modes with variational mode decomposition (VMD). Parameters of the VMD, in the form of generalized intervals, provide a concise representation for aleatory and epistemic uncertainty and improve the robustness of identification. The multi-scale permutation entropy method is applied to extract state features from the decomposed signals in different operating conditions. Traditional principal component analysis is adopted to reduce feature size and computational cost. With the extracted features’ information, the generalized hidden Markov model, based on generalized interval probability, is used to recognize and classify the fault types and fault severity levels. Finally, the experiment results show that the proposed method is effective at recognizing and classifying the fault types and fault severity levels of rolling bearings. This monitoring method is also efficient enough to quantify the two uncertainty components. PMID:28524088

Objective Auscultation of TCM Based on Wavelet Packet Fractal Dimension and Support Vector Machine.

PubMed

Yan, Jian-Jun; Guo, Rui; Wang, Yi-Qin; Liu, Guo-Ping; Yan, Hai-Xia; Xia, Chun-Ming; Shen, Xiaojing

2014-01-01

This study was conducted to illustrate that auscultation features based on the fractal dimension combined with wavelet packet transform (WPT) were conducive to the identification the pattern of syndromes of Traditional Chinese Medicine (TCM). The WPT and the fractal dimension were employed to extract features of auscultation signals of 137 patients with lung Qi-deficient pattern, 49 patients with lung Yin-deficient pattern, and 43 healthy subjects. With these features, the classification model was constructed based on multiclass support vector machine (SVM). When all auscultation signals were trained by SVM to decide the patterns of TCM syndromes, the overall recognition rate of model was 79.49%; when male and female auscultation signals were trained, respectively, to decide the patterns, the overall recognition rate of model reached 86.05%. The results showed that the methods proposed in this paper were effective to analyze auscultation signals, and the performance of model can be greatly improved when the distinction of gender was considered.

Objective Auscultation of TCM Based on Wavelet Packet Fractal Dimension and Support Vector Machine

PubMed Central

Yan, Jian-Jun; Wang, Yi-Qin; Liu, Guo-Ping; Yan, Hai-Xia; Xia, Chun-Ming; Shen, Xiaojing

2014-01-01

This study was conducted to illustrate that auscultation features based on the fractal dimension combined with wavelet packet transform (WPT) were conducive to the identification the pattern of syndromes of Traditional Chinese Medicine (TCM). The WPT and the fractal dimension were employed to extract features of auscultation signals of 137 patients with lung Qi-deficient pattern, 49 patients with lung Yin-deficient pattern, and 43 healthy subjects. With these features, the classification model was constructed based on multiclass support vector machine (SVM). When all auscultation signals were trained by SVM to decide the patterns of TCM syndromes, the overall recognition rate of model was 79.49%; when male and female auscultation signals were trained, respectively, to decide the patterns, the overall recognition rate of model reached 86.05%. The results showed that the methods proposed in this paper were effective to analyze auscultation signals, and the performance of model can be greatly improved when the distinction of gender was considered. PMID:24883068

Performance evaluation for epileptic electroencephalogram (EEG) detection by using Neyman-Pearson criteria and a support vector machine

NASA Astrophysics Data System (ADS)

Wang, Chun-mei; Zhang, Chong-ming; Zou, Jun-zhong; Zhang, Jian

2012-02-01

The diagnosis of several neurological disorders is based on the detection of typical pathological patterns in electroencephalograms (EEGs). This is a time-consuming task requiring significant training and experience. A lot of effort has been devoted to developing automatic detection techniques which might help not only in accelerating this process but also in avoiding the disagreement among readers of the same record. In this work, Neyman-Pearson criteria and a support vector machine (SVM) are applied for detecting an epileptic EEG. Decision making is performed in two stages: feature extraction by computing the wavelet coefficients and the approximate entropy (ApEn) and detection by using Neyman-Pearson criteria and an SVM. Then the detection performance of the proposed method is evaluated. Simulation results demonstrate that the wavelet coefficients and the ApEn are features that represent the EEG signals well. By comparison with Neyman-Pearson criteria, an SVM applied on these features achieved higher detection accuracies.

Directional Multi-scale Modeling of High-Resolution Computed Tomography (HRCT) Lung Images for Diffuse Lung Disease Classification

NASA Astrophysics Data System (ADS)

Vo, Kiet T.; Sowmya, Arcot

A directional multi-scale modeling scheme based on wavelet and contourlet transforms is employed to describe HRCT lung image textures for classifying four diffuse lung disease patterns: normal, emphysema, ground glass opacity (GGO) and honey-combing. Generalized Gaussian density parameters are used to represent the detail sub-band features obtained by wavelet and contourlet transforms. In addition, support vector machines (SVMs) with excellent performance in a variety of pattern classification problems are used as classifier. The method is tested on a collection of 89 slices from 38 patients, each slice of size 512x512, 16 bits/pixel in DICOM format. The dataset contains 70,000 ROIs of those slices marked by experienced radiologists. We employ this technique at different wavelet and contourlet transform scales for diffuse lung disease classification. The technique presented here has best overall sensitivity 93.40% and specificity 98.40%.

Fast Fourier and discrete wavelet transforms applied to sensorless vector control induction motor for rotor bar faults diagnosis.

PubMed

Talhaoui, Hicham; Menacer, Arezki; Kessal, Abdelhalim; Kechida, Ridha

2014-09-01

This paper presents new techniques to evaluate faults in case of broken rotor bars of induction motors. Procedures are applied with closed-loop control. Electrical and mechanical variables are treated using fast Fourier transform (FFT), and discrete wavelet transform (DWT) at start-up and steady state. The wavelet transform has proven to be an excellent mathematical tool for the detection of the faults particularly broken rotor bars type. As a performance, DWT can provide a local representation of the non-stationary current signals for the healthy machine and with fault. For sensorless control, a Luenberger observer is applied; the estimation rotor speed is analyzed; the effect of the faults in the speed pulsation is compensated; a quadratic current appears and used for fault detection. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

An expert support system for breast cancer diagnosis using color wavelet features.

PubMed

Issac Niwas, S; Palanisamy, P; Chibbar, Rajni; Zhang, W J

2012-10-01

Breast cancer diagnosis can be done through the pathologic assessments of breast tissue samples such as core needle biopsy technique. The result of analysis on this sample by pathologist is crucial for breast cancer patient. In this paper, nucleus of tissue samples are investigated after decomposition by means of the Log-Gabor wavelet on HSV color domain and an algorithm is developed to compute the color wavelet features. These features are used for breast cancer diagnosis using Support Vector Machine (SVM) classifier algorithm. The ability of properly trained SVM is to correctly classify patterns and make them particularly suitable for use in an expert system that aids in the diagnosis of cancer tissue samples. The results are compared with other multivariate classifiers such as Naïves Bayes classifier and Artificial Neural Network. The overall accuracy of the proposed method using SVM classifier will be further useful for automation in cancer diagnosis.

Hierarchical Diagnosis of Vocal Fold Disorders

NASA Astrophysics Data System (ADS)

Nikkhah-Bahrami, Mansour; Ahmadi-Noubari, Hossein; Seyed Aghazadeh, Babak; Khadivi Heris, Hossein

This paper explores the use of hierarchical structure for diagnosis of vocal fold disorders. The hierarchical structure is initially used to train different second-level classifiers. At the first level normal and pathological signals have been distinguished. Next, pathological signals have been classified into neurogenic and organic vocal fold disorders. At the final level, vocal fold nodules have been distinguished from polyps in organic disorders category. For feature selection at each level of hierarchy, the reconstructed signal at each wavelet packet decomposition sub-band in 5 levels of decomposition with mother wavelet of (db10) is used to extract the nonlinear features of self-similarity and approximate entropy. Also, wavelet packet coefficients are used to measure energy and Shannon entropy features at different spectral sub-bands. Davies-Bouldin criterion has been employed to find the most discriminant features. Finally, support vector machines have been adopted as classifiers at each level of hierarchy resulting in the diagnosis accuracy of 92%.

A Novel Approach for Lie Detection Based on F-Score and Extreme Learning Machine

PubMed Central

Gao, Junfeng; Wang, Zhao; Yang, Yong; Zhang, Wenjia; Tao, Chunyi; Guan, Jinan; Rao, Nini

2013-01-01

A new machine learning method referred to as F-score_ELM was proposed to classify the lying and truth-telling using the electroencephalogram (EEG) signals from 28 guilty and innocent subjects. Thirty-one features were extracted from the probe responses from these subjects. Then, a recently-developed classifier called extreme learning machine (ELM) was combined with F-score, a simple but effective feature selection method, to jointly optimize the number of the hidden nodes of ELM and the feature subset by a grid-searching training procedure. The method was compared to two classification models combining principal component analysis with back-propagation network and support vector machine classifiers. We thoroughly assessed the performance of these classification models including the training and testing time, sensitivity and specificity from the training and testing sets, as well as network size. The experimental results showed that the number of the hidden nodes can be effectively optimized by the proposed method. Also, F-score_ELM obtained the best classification accuracy and required the shortest training and testing time. PMID:23755136

Multifractal analysis of macro- and microcerebral circulation in rats

NASA Astrophysics Data System (ADS)

Pavlov, Alexey N.; Sindeeva, Olga S.; Sindeev, Sergey S.; Pavlova, Olga N.; Abdurashitov, Arkady S.; Rybalova, Elena V.; Semyachkina-Glushkovskaya, Oxana V.

2016-04-01

Application of noninvasive optical coherent-domain methods and advanced data processing tools such as the wavelet-based multifractal formalism allows revealing effective markers of early stages of functional distortions in the dynamics of cerebral vessels. Based on experiments performed in rats we discuss a possibility to diagnose a hidden stage of the development of intracranial hemorrhage (ICH). We also consider responses of the cerebrovascular dynamics to a pharmacologically induced increase in the peripheral blood pressure. We report distinctions occurring at the levels of macro- and microcerebral circulation.

Machine learning in sentiment reconstruction of the simulated stock market

NASA Astrophysics Data System (ADS)

Goykhman, Mikhail; Teimouri, Ali

2018-02-01

In this paper we continue the study of the simulated stock market framework defined by the driving sentiment processes. We focus on the market environment driven by the buy/sell trading sentiment process of the Markov chain type. We apply the methodology of the Hidden Markov Models and the Recurrent Neural Networks to reconstruct the transition probabilities matrix of the Markov sentiment process and recover the underlying sentiment states from the observed stock price behavior. We demonstrate that the Hidden Markov Model can successfully recover the transition probabilities matrix for the hidden sentiment process of the Markov Chain type. We also demonstrate that the Recurrent Neural Network can successfully recover the hidden sentiment states from the observed simulated stock price time series.

An approach based on wavelet analysis for feature extraction in the a-wave of the electroretinogram.

PubMed

Barraco, R; Persano Adorno, D; Brai, M

2011-12-01

Most biomedical signals are non-stationary. The knowledge of their frequency content and temporal distribution is then useful in a clinical context. The wavelet analysis is appropriate to achieve this task. The present paper uses this method to reveal hidden characteristics and anomalies of the human a-wave, an important component of the electroretinogram since it is a measure of the functional integrity of the photoreceptors. We here analyse the time-frequency features of the a-wave both in normal subjects and in patients affected by Achromatopsia, a pathology disturbing the functionality of the cones. The results indicate the presence of two or three stable frequencies that, in the pathological case, shift toward lower values and change their times of occurrence. The present findings are a first step toward a deeper understanding of the features of the a-wave and possible applications to diagnostic procedures in order to recognise incipient photoreceptoral pathologies. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Characterizing the SEMG patterns with myofascial pain using a multi-scale wavelet model through machine learning approaches.

PubMed

Lin, Yu-Ching; Yu, Nan-Ying; Jiang, Ching-Fen; Chang, Shao-Hsia

2018-06-02

In this paper, we introduce a newly developed multi-scale wavelet model for the interpretation of surface electromyography (SEMG) signals and validate the model's capability to characterize changes in neuromuscular activation in cases with myofascial pain syndrome (MPS) via machine learning methods. The SEMG data collected from normal (N = 30; 27 women, 3 men) and MPS subjects (N = 26; 22 women, 4 men) were adopted for this retrospective analysis. SMEGs were measured from the taut-band loci on both sides of the trapezius muscle on the upper back while he/she conducted a cyclic bilateral backward shoulder extension movement within 1 min. Classification accuracy of the SEMG model to differentiate MPS patients from normal subjects was 77% using template matching and 60% using K-means clustering. Classification consistency between the two machine learning methods was 87% in the normal group and 93% in the MPS group. The 2D feature graphs derived from the proposed multi-scale model revealed distinct patterns between normal subjects and MPS patients. The classification consistency using template matching and K-means clustering suggests the potential of using the proposed model to characterize interference pattern changes induced by MPS. Copyright © 2018. Published by Elsevier Ltd.

Classification of arterial and venous cerebral vasculature based on wavelet postprocessing of CT perfusion data.

PubMed

Havla, Lukas; Schneider, Moritz J; Thierfelder, Kolja M; Beyer, Sebastian E; Ertl-Wagner, Birgit; Reiser, Maximilian F; Sommer, Wieland H; Dietrich, Olaf

2016-02-01

The purpose of this study was to propose and evaluate a new wavelet-based technique for classification of arterial and venous vessels using time-resolved cerebral CT perfusion data sets. Fourteen consecutive patients (mean age 73 yr, range 17-97) with suspected stroke but no pathology in follow-up MRI were included. A CT perfusion scan with 32 dynamic phases was performed during intravenous bolus contrast-agent application. After rigid-body motion correction, a Paul wavelet (order 1) was used to calculate voxelwise the wavelet power spectrum (WPS) of each attenuation-time course. The angiographic intensity A was defined as the maximum of the WPS, located at the coordinates T (time axis) and W (scale/width axis) within the WPS. Using these three parameters (A, T, W) separately as well as combined by (1) Fisher's linear discriminant analysis (FLDA), (2) logistic regression (LogR) analysis, or (3) support vector machine (SVM) analysis, their potential to classify 18 different arterial and venous vessel segments per subject was evaluated. The best vessel classification was obtained using all three parameters A and T and W [area under the curve (AUC): 0.953 with FLDA and 0.957 with LogR or SVM]. In direct comparison, the wavelet-derived parameters provided performance at least equal to conventional attenuation-time-course parameters. The maximum AUC obtained from the proposed wavelet parameters was slightly (although not statistically significantly) higher than the maximum AUC (0.945) obtained from the conventional parameters. A new method to classify arterial and venous cerebral vessels with high statistical accuracy was introduced based on the time-domain wavelet transform of dynamic CT perfusion data in combination with linear or nonlinear multidimensional classification techniques.

Textural characterization of histopathological images for oral sub-mucous fibrosis detection.

PubMed

Krishnan, M Muthu Rama; Shah, Pratik; Choudhary, Anirudh; Chakraborty, Chandan; Paul, Ranjan Rashmi; Ray, Ajoy K

2011-10-01

In the field of quantitative microscopy, textural information plays a significant role very often in tissue characterization and diagnosis, in addition to morphology and intensity. The aim of this work is to improve the classification accuracy based on textural features for the development of a computer assisted screening of oral sub-mucous fibrosis (OSF). In fact, a systematic approach is introduced in order to grade the histopathological tissue sections into normal, OSF without dysplasia and OSF with dysplasia, which would help the oral onco-pathologists to screen the subjects rapidly. In totality, 71 textural features are extracted from epithelial region of the tissue sections using various wavelet families, Gabor-wavelet, local binary pattern, fractal dimension and Brownian motion curve, followed by preprocessing and segmentation. Wavelet families contribute a common set of 9 features, out of which 8 are significant and other 61 out of 62 obtained from the rest of the extractors are also statistically significant (p<0.05) in discriminating the three stages. Based on mean distance criteria, the best wavelet family (i.e., biorthogonal3.1 (bior3.1)) is selected for classifier design. support vector machine (SVM) is trained by 146 samples based on 69 textural features and its classification accuracy is computed for each of the combinations of wavelet family and rest of the extractors. Finally, it has been investigated that bior3.1 wavelet coefficients leads to higher accuracy (88.38%) in combination with LBP and Gabor wavelet features through three-fold cross validation. Results are shown and discussed in detail. It is shown that combining more than one texture measure instead of using just one might improve the overall accuracy. Copyright © 2011 Elsevier Ltd. All rights reserved.

A comparative analysis of support vector machines and extreme learning machines.

PubMed

Liu, Xueyi; Gao, Chuanhou; Li, Ping

2012-09-01

The theory of extreme learning machines (ELMs) has recently become increasingly popular. As a new learning algorithm for single-hidden-layer feed-forward neural networks, an ELM offers the advantages of low computational cost, good generalization ability, and ease of implementation. Hence the comparison and model selection between ELMs and other kinds of state-of-the-art machine learning approaches has become significant and has attracted many research efforts. This paper performs a comparative analysis of the basic ELMs and support vector machines (SVMs) from two viewpoints that are different from previous works: one is the Vapnik-Chervonenkis (VC) dimension, and the other is their performance under different training sample sizes. It is shown that the VC dimension of an ELM is equal to the number of hidden nodes of the ELM with probability one. Additionally, their generalization ability and computational complexity are exhibited with changing training sample size. ELMs have weaker generalization ability than SVMs for small sample but can generalize as well as SVMs for large sample. Remarkably, great superiority in computational speed especially for large-scale sample problems is found in ELMs. The results obtained can provide insight into the essential relationship between them, and can also serve as complementary knowledge for their past experimental and theoretical comparisons. Copyright © 2012 Elsevier Ltd. All rights reserved.

Identification of large geomorphological anomalies based on 2D discrete wavelet transform

NASA Astrophysics Data System (ADS)

Doglioni, A.; Simeone, V.

2012-04-01

The identification and analysis based on quantitative evidences of large geomorphological anomalies is an important stage for the study of large landslides. Numerical geomorphic analyses represent an interesting approach to this kind of studies, allowing for a detailed and pretty accurate identification of hidden topographic anomalies that may be related to large landslides. Here a geomorphic numerical analyses of the Digital Terrain Model (DTM) is presented. The introduced approach is based on 2D discrete wavelet transform (Antoine et al., 2003; Bruun and Nilsen, 2003, Booth et al., 2009). The 2D wavelet decomposition of the DTM, and in particular the analysis of the detail coefficients of the wavelet transform can provide evidences of anomalies or singularities, i.e. discontinuities of the land surface. These discontinuities are not very evident from the DTM as it is, while 2D wavelet transform allows for grid-based analysis of DTM and for mapping the decomposition. In fact, the grid-based DTM can be assumed as a matrix, where a discrete wavelet transform (Daubechies, 1992) is performed columnwise and linewise, which basically represent horizontal and vertical directions. The outcomes of this analysis are low-frequency approximation coefficients and high-frequency detail coefficients. Detail coefficients are analyzed, since their variations are associated to discontinuities of the DTM. Detailed coefficients are estimated assuming to perform 2D wavelet transform both for the horizontal direction (east-west) and for the vertical direction (north-south). Detail coefficients are then mapped for both the cases, thus allowing to visualize and quantify potential anomalies of the land surface. Moreover, wavelet decomposition can be pushed to further levels, assuming a higher scale number of the transform. This may potentially return further interesting results, in terms of identification of the anomalies of land surface. In this kind of approach, the choice of a proper mother wavelet function is a tricky point, since it conditions the analysis and then their outcomes. Therefore multiple levels as well as multiple wavelet analyses are guessed. Here the introduced approach is applied to some interesting cases study of south Italy, in particular for the identification of large anomalies associated to large landslides at the transition between Apennine chain domain and the foredeep domain. In particular low Biferno valley and Fortore valley are here analyzed. Finally, the wavelet transforms are performed on multiple levels, thus trying to address the problem of which is the level extent for an accurate analysis fit to a specific problem. Antoine J.P., Carrette P., Murenzi R., and Piette B., (2003), Image analysis with two-dimensional continuous wavelet transform, Signal Processing, 31(3), pp. 241-272, doi:10.1016/0165-1684(93)90085-O. Booth A.M., Roering J.J., and Taylor Perron J., (2009), Automated landslide mapping using spectral analysis and high-resolution topographic data: Puget Sound lowlands, Washington, and Portland Hills, Oregon, Geomorphology, 109(3-4), pp. 132-147, doi:10.1016/j.geomorph.2009.02.027. Bruun B.T., and Nilsen S., (2003), Wavelet representation of large digital terrain models, Computers and Geoscience, 29(6), pp. 695-703, doi:10.1016/S0098-3004(03)00015-3. Daubechies, I. (1992), Ten lectures on wavelets, SIAM.

Automated Classification and Removal of EEG Artifacts With SVM and Wavelet-ICA.

PubMed

Sai, Chong Yeh; Mokhtar, Norrima; Arof, Hamzah; Cumming, Paul; Iwahashi, Masahiro

2018-05-01

Brain electrical activity recordings by electroencephalography (EEG) are often contaminated with signal artifacts. Procedures for automated removal of EEG artifacts are frequently sought for clinical diagnostics and brain-computer interface applications. In recent years, a combination of independent component analysis (ICA) and discrete wavelet transform has been introduced as standard technique for EEG artifact removal. However, in performing the wavelet-ICA procedure, visual inspection or arbitrary thresholding may be required for identifying artifactual components in the EEG signal. We now propose a novel approach for identifying artifactual components separated by wavelet-ICA using a pretrained support vector machine (SVM). Our method presents a robust and extendable system that enables fully automated identification and removal of artifacts from EEG signals, without applying any arbitrary thresholding. Using test data contaminated by eye blink artifacts, we show that our method performed better in identifying artifactual components than did existing thresholding methods. Furthermore, wavelet-ICA in conjunction with SVM successfully removed target artifacts, while largely retaining the EEG source signals of interest. We propose a set of features including kurtosis, variance, Shannon's entropy, and range of amplitude as training and test data of SVM to identify eye blink artifacts in EEG signals. This combinatorial method is also extendable to accommodate multiple types of artifacts present in multichannel EEG. We envision future research to explore other descriptive features corresponding to other types of artifactual components.

Correlation analysis of motor current and chatter vibration in grinding using complex continuous wavelet coherence

NASA Astrophysics Data System (ADS)

Liu, Yao; Wang, Xiufeng; Lin, Jing; Zhao, Wei

2016-11-01

Motor current is an emerging and popular signal which can be used to detect machining chatter with its multiple advantages. To achieve accurate and reliable chatter detection using motor current, it is important to make clear the quantitative relationship between motor current and chatter vibration, which has not yet been studied clearly. In this study, complex continuous wavelet coherence, including cross wavelet transform and wavelet coherence, is applied to the correlation analysis of motor current and chatter vibration in grinding. Experimental results show that complex continuous wavelet coherence performs very well in demonstrating and quantifying the intense correlation between these two signals in frequency, amplitude and phase. When chatter occurs, clear correlations in frequency and amplitude in the chatter frequency band appear and the phase difference of current signal to vibration signal turns from random to stable. The phase lead of the most correlated chatter frequency is the largest. With the further development of chatter, the correlation grows up in intensity and expands to higher order chatter frequency band. The analyzing results confirm that there is a consistent correlation between motor current and vibration signals in the grinding chatter process. However, to achieve accurate and reliable chatter detection using motor current, the frequency response bandwidth of current loop of the feed drive system must be wide enough to response chatter effectively.

Acoustic⁻Seismic Mixed Feature Extraction Based on Wavelet Transform for Vehicle Classification in Wireless Sensor Networks.

PubMed

Zhang, Heng; Pan, Zhongming; Zhang, Wenna

2018-06-07

An acoustic⁻seismic mixed feature extraction method based on the wavelet coefficient energy ratio (WCER) of the target signal is proposed in this study for classifying vehicle targets in wireless sensor networks. The signal was decomposed into a set of wavelet coefficients using the à trous algorithm, which is a concise method used to implement the wavelet transform of a discrete signal sequence. After the wavelet coefficients of the target acoustic and seismic signals were obtained, the energy ratio of each layer coefficient was calculated as the feature vector of the target signals. Subsequently, the acoustic and seismic features were merged into an acoustic⁻seismic mixed feature to improve the target classification accuracy after the acoustic and seismic WCER features of the target signal were simplified using the hierarchical clustering method. We selected the support vector machine method for classification and utilized the data acquired from a real-world experiment to validate the proposed method. The calculated results show that the WCER feature extraction method can effectively extract the target features from target signals. Feature simplification can reduce the time consumption of feature extraction and classification, with no effect on the target classification accuracy. The use of acoustic⁻seismic mixed features effectively improved target classification accuracy by approximately 12% compared with either acoustic signal or seismic signal alone.

Quantification of localized vertebral deformities using a sparse wavelet-based shape model.

PubMed

Zewail, R; Elsafi, A; Durdle, N

2008-01-01

Medical experts often examine hundreds of spine x-ray images to determine existence of various pathologies. Common pathologies of interest are anterior osteophites, disc space narrowing, and wedging. By careful inspection of the outline shapes of the vertebral bodies, experts are able to identify and assess vertebral abnormalities with respect to the pathology under investigation. In this paper, we present a novel method for quantification of vertebral deformation using a sparse shape model. Using wavelets and Independent component analysis (ICA), we construct a sparse shape model that benefits from the approximation power of wavelets and the capability of ICA to capture higher order statistics in wavelet space. The new model is able to capture localized pathology-related shape deformations, hence it allows for quantification of vertebral shape variations. We investigate the capability of the model to predict localized pathology related deformations. Next, using support-vector machines, we demonstrate the diagnostic capabilities of the method through the discrimination of anterior osteophites in lumbar vertebrae. Experiments were conducted using a set of 150 contours from digital x-ray images of lumbar spine. Each vertebra is labeled as normal or abnormal. Results reported in this work focus on anterior osteophites as the pathology of interest.

[The Identification of the Origin of Chinese Wolfberry Based on Infrared Spectral Technology and the Artificial Neural Network].

PubMed

Li, Zhong; Liu, Ming-de; Ji, Shou-xiang

2016-03-01

The Fourier Transform Infrared Spectroscopy (FTIR) is established to find the geographic origins of Chinese wolfberry quickly. In the paper, the 45 samples of Chinese wolfberry from different places of Qinghai Province are to be surveyed by FTIR. The original data matrix of FTIR is pretreated with common preprocessing and wavelet transform. Compared with common windows shifting smoothing preprocessing, standard normal variation correction and multiplicative scatter correction, wavelet transform is an effective spectrum data preprocessing method. Before establishing model through the artificial neural networks, the spectra variables are compressed by means of the wavelet transformation so as to enhance the training speed of the artificial neural networks, and at the same time the related parameters of the artificial neural networks model are also discussed in detail. The survey shows even if the infrared spectroscopy data is compressed to 1/8 of its original data, the spectral information and analytical accuracy are not deteriorated. The compressed spectra variables are used for modeling parameters of the backpropagation artificial neural network (BP-ANN) model and the geographic origins of Chinese wolfberry are used for parameters of export. Three layers of neural network model are built to predict the 10 unknown samples by using the MATLAB neural network toolbox design error back propagation network. The number of hidden layer neurons is 5, and the number of output layer neuron is 1. The transfer function of hidden layer is tansig, while the transfer function of output layer is purelin. Network training function is trainl and the learning function of weights and thresholds is learngdm. net. trainParam. epochs=1 000, while net. trainParam. goal = 0.001. The recognition rate of 100% is to be achieved. It can be concluded that the method is quite suitable for the quick discrimination of producing areas of Chinese wolfberry. The infrared spectral analysis technology combined with the artificial neural networks is proved to be a reliable and new method for the identification of the original place of Traditional Chinese Medicine.

Employing wavelet-based texture features in ammunition classification

NASA Astrophysics Data System (ADS)

Borzino, Ángelo M. C. R.; Maher, Robert C.; Apolinário, José A.; de Campos, Marcello L. R.

2017-05-01

Pattern recognition, a branch of machine learning, involves classification of information in images, sounds, and other digital representations. This paper uses pattern recognition to identify which kind of ammunition was used when a bullet was fired based on a carefully constructed set of gunshot sound recordings. To do this task, we show that texture features obtained from the wavelet transform of a component of the gunshot signal, treated as an image, and quantized in gray levels, are good ammunition discriminators. We test the technique with eight different calibers and achieve a classification rate better than 95%. We also compare the performance of the proposed method with results obtained by standard temporal and spectrographic techniques

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.

Predicting subcellular location of apoptosis proteins based on wavelet transform and support vector machine.

PubMed

Qiu, Jian-Ding; Luo, San-Hua; Huang, Jian-Hua; Sun, Xing-Yu; Liang, Ru-Ping

2010-04-01

Apoptosis proteins have a central role in the development and homeostasis of an organism. These proteins are very important for understanding the mechanism of programmed cell death. As a result of genome and other sequencing projects, the gap between the number of known apoptosis protein sequences and the number of known apoptosis protein structures is widening rapidly. Because of this extremely unbalanced state, it would be worthwhile to develop a fast and reliable method to identify their subcellular locations so as to gain better insight into their biological functions. In view of this, a new method, in which the support vector machine combines with discrete wavelet transform, has been developed to predict the subcellular location of apoptosis proteins. The results obtained by the jackknife test were quite promising, and indicated that the proposed method can remarkably improve the prediction accuracy of subcellular locations, and might also become a useful high-throughput tool in characterizing other attributes of proteins, such as enzyme class, membrane protein type, and nuclear receptor subfamily according to their sequences.

Classification of pulmonary pathology from breath sounds using the wavelet packet transform and an extreme learning machine.

PubMed

Palaniappan, Rajkumar; Sundaraj, Kenneth; Sundaraj, Sebastian; Huliraj, N; Revadi, S S

2017-06-08

Auscultation is a medical procedure used for the initial diagnosis and assessment of lung and heart diseases. From this perspective, we propose assessing the performance of the extreme learning machine (ELM) classifiers for the diagnosis of pulmonary pathology using breath sounds. Energy and entropy features were extracted from the breath sound using the wavelet packet transform. The statistical significance of the extracted features was evaluated by one-way analysis of variance (ANOVA). The extracted features were inputted into the ELM classifier. The maximum classification accuracies obtained for the conventional validation (CV) of the energy and entropy features were 97.36% and 98.37%, respectively, whereas the accuracies obtained for the cross validation (CRV) of the energy and entropy features were 96.80% and 97.91%, respectively. In addition, maximum classification accuracies of 98.25% and 99.25% were obtained for the CV and CRV of the ensemble features, respectively. The results indicate that the classification accuracy obtained with the ensemble features was higher than those obtained with the energy and entropy features.

A new method for the prediction of chatter stability lobes based on dynamic cutting force simulation model and support vector machine

NASA Astrophysics Data System (ADS)

Peng, Chong; Wang, Lun; Liao, T. Warren

2015-10-01

Currently, chatter has become the critical factor in hindering machining quality and productivity in machining processes. To avoid cutting chatter, a new method based on dynamic cutting force simulation model and support vector machine (SVM) is presented for the prediction of chatter stability lobes. The cutting force is selected as the monitoring signal, and the wavelet energy entropy theory is used to extract the feature vectors. A support vector machine is constructed using the MATLAB LIBSVM toolbox for pattern classification based on the feature vectors derived from the experimental cutting data. Then combining with the dynamic cutting force simulation model, the stability lobes diagram (SLD) can be estimated. Finally, the predicted results are compared with existing methods such as zero-order analytical (ZOA) and semi-discretization (SD) method as well as actual cutting experimental results to confirm the validity of this new method.

Vibration Sensor Monitoring of Nickel-Titanium Alloy Turning for Machinability Evaluation.

PubMed

Segreto, Tiziana; Caggiano, Alessandra; Karam, Sara; Teti, Roberto

2017-12-12

Nickel-Titanium (Ni-Ti) alloys are very difficult-to-machine materials causing notable manufacturing problems due to their unique mechanical properties, including superelasticity, high ductility, and severe strain-hardening. In this framework, the aim of this paper is to assess the machinability of Ni-Ti alloys with reference to turning processes in order to realize a reliable and robust in-process identification of machinability conditions. An on-line sensor monitoring procedure based on the acquisition of vibration signals was implemented during the experimental turning tests. The detected vibration sensorial data were processed through an advanced signal processing method in time-frequency domain based on wavelet packet transform (WPT). The extracted sensorial features were used to construct WPT pattern feature vectors to send as input to suitably configured neural networks (NNs) for cognitive pattern recognition in order to evaluate the correlation between input sensorial information and output machinability conditions.

Vibration Sensor Monitoring of Nickel-Titanium Alloy Turning for Machinability Evaluation

PubMed Central

Segreto, Tiziana; Karam, Sara; Teti, Roberto

2017-01-01

Nickel-Titanium (Ni-Ti) alloys are very difficult-to-machine materials causing notable manufacturing problems due to their unique mechanical properties, including superelasticity, high ductility, and severe strain-hardening. In this framework, the aim of this paper is to assess the machinability of Ni-Ti alloys with reference to turning processes in order to realize a reliable and robust in-process identification of machinability conditions. An on-line sensor monitoring procedure based on the acquisition of vibration signals was implemented during the experimental turning tests. The detected vibration sensorial data were processed through an advanced signal processing method in time-frequency domain based on wavelet packet transform (WPT). The extracted sensorial features were used to construct WPT pattern feature vectors to send as input to suitably configured neural networks (NNs) for cognitive pattern recognition in order to evaluate the correlation between input sensorial information and output machinability conditions. PMID:29231864

Structure and Randomness of Continuous-Time, Discrete-Event Processes

NASA Astrophysics Data System (ADS)

Marzen, Sarah E.; Crutchfield, James P.

2017-10-01

Loosely speaking, the Shannon entropy rate is used to gauge a stochastic process' intrinsic randomness; the statistical complexity gives the cost of predicting the process. We calculate, for the first time, the entropy rate and statistical complexity of stochastic processes generated by finite unifilar hidden semi-Markov models—memoryful, state-dependent versions of renewal processes. Calculating these quantities requires introducing novel mathematical objects (ɛ -machines of hidden semi-Markov processes) and new information-theoretic methods to stochastic processes.

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 in heart failure: ready for prime time.

PubMed

Awan, Saqib Ejaz; Sohel, Ferdous; Sanfilippo, Frank Mario; Bennamoun, Mohammed; Dwivedi, Girish

2018-03-01

The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

PubMed

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

PubMed Central

Belo, David; Gamboa, Hugo

2017-01-01

The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components. PMID:28831239

Bidirectional extreme learning machine for regression problem and its learning effectiveness.

PubMed

Yang, Yimin; Wang, Yaonan; Yuan, Xiaofang

2012-09-01

It is clear that the learning effectiveness and learning speed of neural networks are in general far slower than required, which has been a major bottleneck for many applications. Recently, a simple and efficient learning method, referred to as extreme learning machine (ELM), was proposed by Huang , which has shown that, compared to some conventional methods, the training time of neural networks can be reduced by a thousand times. However, one of the open problems in ELM research is whether the number of hidden nodes can be further reduced without affecting learning effectiveness. This brief proposes a new learning algorithm, called bidirectional extreme learning machine (B-ELM), in which some hidden nodes are not randomly selected. In theory, this algorithm tends to reduce network output error to 0 at an extremely early learning stage. Furthermore, we find a relationship between the network output error and the network output weights in the proposed B-ELM. Simulation results demonstrate that the proposed method can be tens to hundreds of times faster than other incremental ELM algorithms.

Forecasting daily streamflow using online sequential extreme learning machines

NASA Astrophysics Data System (ADS)

Lima, Aranildo R.; Cannon, Alex J.; Hsieh, William W.

2016-06-01

While nonlinear machine methods have been widely used in environmental forecasting, in situations where new data arrive continually, the need to make frequent model updates can become cumbersome and computationally costly. To alleviate this problem, an online sequential learning algorithm for single hidden layer feedforward neural networks - the online sequential extreme learning machine (OSELM) - is automatically updated inexpensively as new data arrive (and the new data can then be discarded). OSELM was applied to forecast daily streamflow at two small watersheds in British Columbia, Canada, at lead times of 1-3 days. Predictors used were weather forecast data generated by the NOAA Global Ensemble Forecasting System (GEFS), and local hydro-meteorological observations. OSELM forecasts were tested with daily, monthly or yearly model updates. More frequent updating gave smaller forecast errors, including errors for data above the 90th percentile. Larger datasets used in the initial training of OSELM helped to find better parameters (number of hidden nodes) for the model, yielding better predictions. With the online sequential multiple linear regression (OSMLR) as benchmark, we concluded that OSELM is an attractive approach as it easily outperformed OSMLR in forecast accuracy.

Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals.

PubMed

Elhaj, Fatin A; Salim, Naomie; Harris, Arief R; Swee, Tan Tian; Ahmed, Taqwa

2016-04-01

Arrhythmia is a cardiac condition caused by abnormal electrical activity of the heart, and an electrocardiogram (ECG) is the non-invasive method used to detect arrhythmias or heart abnormalities. Due to the presence of noise, the non-stationary nature of the ECG signal (i.e. the changing morphology of the ECG signal with respect to time) and the irregularity of the heartbeat, physicians face difficulties in the diagnosis of arrhythmias. The computer-aided analysis of ECG results assists physicians to detect cardiovascular diseases. The development of many existing arrhythmia systems has depended on the findings from linear experiments on ECG data which achieve high performance on noise-free data. However, nonlinear experiments characterize the ECG signal more effectively sense, extract hidden information in the ECG signal, and achieve good performance under noisy conditions. This paper investigates the representation ability of linear and nonlinear features and proposes a combination of such features in order to improve the classification of ECG data. In this study, five types of beat classes of arrhythmia as recommended by the Association for Advancement of Medical Instrumentation are analyzed: non-ectopic beats (N), supra-ventricular ectopic beats (S), ventricular ectopic beats (V), fusion beats (F) and unclassifiable and paced beats (U). The characterization ability of nonlinear features such as high order statistics and cumulants and nonlinear feature reduction methods such as independent component analysis are combined with linear features, namely, the principal component analysis of discrete wavelet transform coefficients. The features are tested for their ability to differentiate different classes of data using different classifiers, namely, the support vector machine and neural network methods with tenfold cross-validation. Our proposed method is able to classify the N, S, V, F and U arrhythmia classes with high accuracy (98.91%) using a combined support vector machine and radial basis function method. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

SU-E-J-191: Motion Prediction Using Extreme Learning Machine in Image Guided Radiotherapy

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

Jia, J; Cao, R; Pei, X

Purpose: Real-time motion tracking is a critical issue in image guided radiotherapy due to the time latency caused by image processing and system response. It is of great necessity to fast and accurately predict the future position of the respiratory motion and the tumor location. Methods: The prediction of respiratory position was done based on the positioning and tracking module in ARTS-IGRT system which was developed by FDS Team (www.fds.org.cn). An approach involving with the extreme learning machine (ELM) was adopted to predict the future respiratory position as well as the tumor’s location by training the past trajectories. For themore » training process, a feed-forward neural network with one single hidden layer was used for the learning. First, the number of hidden nodes was figured out for the single layered feed forward network (SLFN). Then the input weights and hidden layer biases of the SLFN were randomly assigned to calculate the hidden neuron output matrix. Finally, the predicted movement were obtained by applying the output weights and compared with the actual movement. Breathing movement acquired from the external infrared markers was used to test the prediction accuracy. And the implanted marker movement for the prostate cancer was used to test the implementation of the tumor motion prediction. Results: The accuracy of the predicted motion and the actual motion was tested. Five volunteers with different breathing patterns were tested. The average prediction time was 0.281s. And the standard deviation of prediction accuracy was 0.002 for the respiratory motion and 0.001 for the tumor motion. Conclusion: The extreme learning machine method can provide an accurate and fast prediction of the respiratory motion and the tumor location and therefore can meet the requirements of real-time tumor-tracking in image guided radiotherapy.« less

Learning a single-hidden layer feedforward neural network using a rank correlation-based strategy with application to high dimensional gene expression and proteomic spectra datasets in cancer detection.

PubMed

Belciug, Smaranda; Gorunescu, Florin

2018-06-08

Methods based on microarrays (MA), mass spectrometry (MS), and machine learning (ML) algorithms have evolved rapidly in recent years, allowing for early detection of several types of cancer. A pitfall of these approaches, however, is the overfitting of data due to large number of attributes and small number of instances -- a phenomenon known as the 'curse of dimensionality'. A potentially fruitful idea to avoid this drawback is to develop algorithms that combine fast computation with a filtering module for the attributes. The goal of this paper is to propose a statistical strategy to initiate the hidden nodes of a single-hidden layer feedforward neural network (SLFN) by using both the knowledge embedded in data and a filtering mechanism for attribute relevance. In order to attest its feasibility, the proposed model has been tested on five publicly available high-dimensional datasets: breast, lung, colon, and ovarian cancer regarding gene expression and proteomic spectra provided by cDNA arrays, DNA microarray, and MS. The novel algorithm, called adaptive SLFN (aSLFN), has been compared with four major classification algorithms: traditional ELM, radial basis function network (RBF), single-hidden layer feedforward neural network trained by backpropagation algorithm (BP-SLFN), and support vector-machine (SVM). Experimental results showed that the classification performance of aSLFN is competitive with the comparison models. Copyright © 2018. Published by Elsevier Inc.

Active semi-supervised learning method with hybrid deep belief networks.

PubMed

Zhou, Shusen; Chen, Qingcai; Wang, Xiaolong

2014-01-01

In this paper, we develop a novel semi-supervised learning algorithm called active hybrid deep belief networks (AHD), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltzmann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. Finally, active learning method is combined based on the proposed deep architecture. We did several experiments on five sentiment classification datasets, and show that AHD is competitive with previous semi-supervised learning algorithm. Experiments are also conducted to verify the effectiveness of our proposed method with different number of labeled reviews and unlabeled reviews respectively.

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

A discrete wavelet based feature extraction and hybrid classification technique for microarray data analysis.

PubMed

Bennet, Jaison; Ganaprakasam, Chilambuchelvan Arul; Arputharaj, Kannan

2014-01-01

Cancer classification by doctors and radiologists was based on morphological and clinical features and had limited diagnostic ability in olden days. The recent arrival of DNA microarray technology has led to the concurrent monitoring of thousands of gene expressions in a single chip which stimulates the progress in cancer classification. In this paper, we have proposed a hybrid approach for microarray data classification based on nearest neighbor (KNN), naive Bayes, and support vector machine (SVM). Feature selection prior to classification plays a vital role and a feature selection technique which combines discrete wavelet transform (DWT) and moving window technique (MWT) is used. The performance of the proposed method is compared with the conventional classifiers like support vector machine, nearest neighbor, and naive Bayes. Experiments have been conducted on both real and benchmark datasets and the results indicate that the ensemble approach produces higher classification accuracy than conventional classifiers. This paper serves as an automated system for the classification of cancer and can be applied by doctors in real cases which serve as a boon to the medical community. This work further reduces the misclassification of cancers which is highly not allowed in cancer detection.

Carbon Nanotube Growth Rate Regression using Support Vector Machines and Artificial Neural Networks

DTIC Science & Technology

2014-03-27

intensity D peak. Reprinted with permission from [38]. The SVM classifier is trained using custom written Java code leveraging the Sequential Minimal...Society Encog is a machine learning framework for Java , C++ and .Net applications that supports Bayesian Networks, Hidden Markov Models, SVMs and ANNs [13...SVM classifiers are trained using Weka libraries and leveraging custom written Java code. The data set is created as an Attribute Relationship File

Induction motors airgap-eccentricity detection through the discrete wavelet transform of the apparent power signal under non-stationary operating conditions.

PubMed

Yahia, K; Cardoso, A J M; Ghoggal, A; Zouzou, S E

2014-03-01

Fast Fourier transform (FFT) analysis has been successfully used for fault diagnosis in induction machines. However, this method does not always provide good results for the cases of load torque, speed and voltages variation, leading to a variation of the motor-slip and the consequent FFT problems that appear due to the non-stationary nature of the involved signals. In this paper, the discrete wavelet transform (DWT) of the apparent-power signal for the airgap-eccentricity fault detection in three-phase induction motors is presented in order to overcome the above FFT problems. The proposed method is based on the decomposition of the apparent-power signal from which wavelet approximation and detail coefficients are extracted. The energy evaluation of a known bandwidth permits to define a fault severity factor (FSF). Simulation as well as experimental results are provided to illustrate the effectiveness and accuracy of the proposed method presented even for the case of load torque variations. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Identification and classification of similar looking food grains

NASA Astrophysics Data System (ADS)

Anami, B. S.; Biradar, Sunanda D.; Savakar, D. G.; Kulkarni, P. V.

2013-01-01

This paper describes the comparative study of Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers by taking a case study of identification and classification of four pairs of similar looking food grains namely, Finger Millet, Mustard, Soyabean, Pigeon Pea, Aniseed, Cumin-seeds, Split Greengram and Split Blackgram. Algorithms are developed to acquire and process color images of these grains samples. The developed algorithms are used to extract 18 colors-Hue Saturation Value (HSV), and 42 wavelet based texture features. Back Propagation Neural Network (BPNN)-based classifier is designed using three feature sets namely color - HSV, wavelet-texture and their combined model. SVM model for color- HSV model is designed for the same set of samples. The classification accuracies ranging from 93% to 96% for color-HSV, ranging from 78% to 94% for wavelet texture model and from 92% to 97% for combined model are obtained for ANN based models. The classification accuracy ranging from 80% to 90% is obtained for color-HSV based SVM model. Training time required for the SVM based model is substantially lesser than ANN for the same set of images.

Intelligent approach to prognostic enhancements of diagnostic systems

NASA Astrophysics Data System (ADS)

Vachtsevanos, George; Wang, Peng; Khiripet, Noppadon; Thakker, Ash; Galie, Thomas R.

2001-07-01

This paper introduces a novel methodology to prognostics based on a dynamic wavelet neural network construct and notions from the virtual sensor area. This research has been motivated and supported by the U.S. Navy's active interest in integrating advanced diagnostic and prognostic algorithms in existing Naval digital control and monitoring systems. A rudimentary diagnostic platform is assumed to be available providing timely information about incipient or impending failure conditions. We focus on the development of a prognostic algorithm capable of predicting accurately and reliably the remaining useful lifetime of a failing machine or component. The prognostic module consists of a virtual sensor and a dynamic wavelet neural network as the predictor. The virtual sensor employs process data to map real measurements into difficult to monitor fault quantities. The prognosticator uses a dynamic wavelet neural network as a nonlinear predictor. Means to manage uncertainty and performance metrics are suggested for comparison purposes. An interface to an available shipboard Integrated Condition Assessment System is described and applications to shipboard equipment are discussed. Typical results from pump failures are presented to illustrate the effectiveness of the methodology.

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

A Fast and On-Machine Measuring System Using the Laser Displacement Sensor for the Contour Parameters of the Drill Pipe Thread.

PubMed

Dong, Zhixu; Sun, Xingwei; Chen, Changzheng; Sun, Mengnan

2018-04-13

The inconvenient loading and unloading of a long and heavy drill pipe gives rise to the difficulty in measuring the contour parameters of its threads at both ends. To solve this problem, in this paper we take the SCK230 drill pipe thread-repairing machine tool as a carrier to design and achieve a fast and on-machine measuring system based on a laser probe. This system drives a laser displacement sensor to acquire the contour data of a certain axial section of the thread by using the servo function of a CNC machine tool. To correct the sensor's measurement errors caused by the measuring point inclination angle, an inclination error model is built to compensate data in real time. To better suppress random error interference and ensure real contour information, a new wavelet threshold function is proposed to process data through the wavelet threshold denoising. Discrete data after denoising is segmented according to the geometrical characteristics of the drill pipe thread, and the regression model of the contour data in each section is fitted by using the method of weighted total least squares (WTLS). Then, the thread parameters are calculated in real time to judge the processing quality. Inclination error experiments show that the proposed compensation model is accurate and effective, and it can improve the data acquisition accuracy of a sensor. Simulation results indicate that the improved threshold function is of better continuity and self-adaptability, which makes sure that denoising effects are guaranteed, and, meanwhile, the complete elimination of real data distorted in random errors is avoided. Additionally, NC50 thread-testing experiments show that the proposed on-machine measuring system can complete the measurement of a 25 mm thread in 7.8 s, with a measurement accuracy of ±8 μm and repeatability limit ≤ 4 μm (high repeatability), and hence the accuracy and efficiency of measurement are both improved.

A Fast and On-Machine Measuring System Using the Laser Displacement Sensor for the Contour Parameters of the Drill Pipe Thread

PubMed Central

Sun, Xingwei; Chen, Changzheng; Sun, Mengnan

2018-01-01

The inconvenient loading and unloading of a long and heavy drill pipe gives rise to the difficulty in measuring the contour parameters of its threads at both ends. To solve this problem, in this paper we take the SCK230 drill pipe thread-repairing machine tool as a carrier to design and achieve a fast and on-machine measuring system based on a laser probe. This system drives a laser displacement sensor to acquire the contour data of a certain axial section of the thread by using the servo function of a CNC machine tool. To correct the sensor’s measurement errors caused by the measuring point inclination angle, an inclination error model is built to compensate data in real time. To better suppress random error interference and ensure real contour information, a new wavelet threshold function is proposed to process data through the wavelet threshold denoising. Discrete data after denoising is segmented according to the geometrical characteristics of the drill pipe thread, and the regression model of the contour data in each section is fitted by using the method of weighted total least squares (WTLS). Then, the thread parameters are calculated in real time to judge the processing quality. Inclination error experiments show that the proposed compensation model is accurate and effective, and it can improve the data acquisition accuracy of a sensor. Simulation results indicate that the improved threshold function is of better continuity and self-adaptability, which makes sure that denoising effects are guaranteed, and, meanwhile, the complete elimination of real data distorted in random errors is avoided. Additionally, NC50 thread-testing experiments show that the proposed on-machine measuring system can complete the measurement of a 25 mm thread in 7.8 s, with a measurement accuracy of ±8 μm and repeatability limit ≤ 4 μm (high repeatability), and hence the accuracy and efficiency of measurement are both improved. PMID:29652836

Machine Learning Technique to Find Quantum Many-Body Ground States of Bosons on a Lattice

NASA Astrophysics Data System (ADS)

Saito, Hiroki; Kato, Masaya

2018-01-01

We have developed a variational method to obtain many-body ground states of the Bose-Hubbard model using feedforward artificial neural networks. A fully connected network with a single hidden layer works better than a fully connected network with multiple hidden layers, and a multilayer convolutional network is more efficient than a fully connected network. AdaGrad and Adam are optimization methods that work well. Moreover, we show that many-body ground states with different numbers of particles can be generated by a single network.

Automated pathologies detection in retina digital images based on complex continuous wavelet transform phase angles.

PubMed

Lahmiri, Salim; Gargour, Christian S; Gabrea, Marcel

2014-10-01

An automated diagnosis system that uses complex continuous wavelet transform (CWT) to process retina digital images and support vector machines (SVMs) for classification purposes is presented. In particular, each retina image is transformed into two one-dimensional signals by concatenating image rows and columns separately. The mathematical norm of phase angles found in each one-dimensional signal at each level of CWT decomposition are relied on to characterise the texture of normal images against abnormal images affected by exudates, drusen and microaneurysms. The leave-one-out cross-validation method was adopted to conduct experiments and the results from the SVM show that the proposed approach gives better results than those obtained by other methods based on the correct classification rate, sensitivity and specificity.

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.

Recognizing emotions from EEG subbands using wavelet analysis.

PubMed

Candra, Henry; Yuwono, Mitchell; Handojoseno, Ardi; Chai, Rifai; Su, Steven; Nguyen, Hung T

2015-01-01

Objectively recognizing emotions is a particularly important task to ensure that patients with emotional symptoms are given the appropriate treatments. The aim of this study was to develop an emotion recognition system using Electroencephalogram (EEG) signals to identify four emotions including happy, sad, angry, and relaxed. We approached this objective by firstly investigating the relevant EEG frequency band followed by deciding the appropriate feature extraction method. Two features were considered namely: 1. Wavelet Energy, and 2. Wavelet Entropy. EEG Channels reduction was then implemented to reduce the complexity of the features. The ground truth emotional states of each subject were inferred using Russel's circumplex model of emotion, that is, by mapping the subjectively reported degrees of valence (pleasure) and arousal to the appropriate emotions - for example, an emotion with high valence and high arousal is equivalent to a `happy' emotional state, while low valence and low arousal is equivalent to a `sad' emotional state. The Support Vector Machine (SVM) classifier was then used for mapping each feature vector into corresponding discrete emotions. The results presented in this study indicated thatWavelet features extracted from alpha, beta and gamma bands seem to provide the necessary information for describing the aforementioned emotions. Using the DEAP (Dataset for Emotion Analysis using electroencephalogram, Physiological and Video Signals), our proposed method achieved an average sensitivity and specificity of 77.4% ± 14.1% and 69.1% ± 12.8%, respectively.

Efficient feature selection using a hybrid algorithm for the task of epileptic seizure detection

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2014-07-01

Feature selection is a very important aspect in the field of machine learning. It entails the search of an optimal subset from a very large data set with high dimensional feature space. Apart from eliminating redundant features and reducing computational cost, a good selection of feature also leads to higher prediction and classification accuracy. In this paper, an efficient feature selection technique is introduced in the task of epileptic seizure detection. The raw data are electroencephalography (EEG) signals. Using discrete wavelet transform, the biomedical signals were decomposed into several sets of wavelet coefficients. To reduce the dimension of these wavelet coefficients, a feature selection method that combines the strength of both filter and wrapper methods is proposed. Principal component analysis (PCA) is used as part of the filter method. As for wrapper method, the evolutionary harmony search (HS) algorithm is employed. This metaheuristic method aims at finding the best discriminating set of features from the original data. The obtained features were then used as input for an automated classifier, namely wavelet neural networks (WNNs). The WNNs model was trained to perform a binary classification task, that is, to determine whether a given EEG signal was normal or epileptic. For comparison purposes, different sets of features were also used as input. Simulation results showed that the WNNs that used the features chosen by the hybrid algorithm achieved the highest overall classification accuracy.

Pedestrian detection based on redundant wavelet transform

NASA Astrophysics Data System (ADS)

Huang, Lin; Ji, Liping; Hu, Ping; Yang, Tiejun

2016-10-01

Intelligent video surveillance is to analysis video or image sequences captured by a fixed or mobile surveillance camera, including moving object detection, segmentation and recognition. By using it, we can be notified immediately in an abnormal situation. Pedestrian detection plays an important role in an intelligent video surveillance system, and it is also a key technology in the field of intelligent vehicle. So pedestrian detection has very vital significance in traffic management optimization, security early warn and abnormal behavior detection. Generally, pedestrian detection can be summarized as: first to estimate moving areas; then to extract features of region of interest; finally to classify using a classifier. Redundant wavelet transform (RWT) overcomes the deficiency of shift variant of discrete wavelet transform, and it has better performance in motion estimation when compared to discrete wavelet transform. Addressing the problem of the detection of multi-pedestrian with different speed, we present an algorithm of pedestrian detection based on motion estimation using RWT, combining histogram of oriented gradients (HOG) and support vector machine (SVM). Firstly, three intensities of movement (IoM) are estimated using RWT and the corresponding areas are segmented. According to the different IoM, a region proposal (RP) is generated. Then, the features of a RP is extracted using HOG. Finally, the features are fed into a SVM trained by pedestrian databases and the final detection results are gained. Experiments show that the proposed algorithm can detect pedestrians accurately and efficiently.

Neural network face recognition using wavelets

NASA Astrophysics Data System (ADS)

Karunaratne, Passant V.; Jouny, Ismail I.

1997-04-01

The recognition of human faces is a phenomenon that has been mastered by the human visual system and that has been researched extensively in the domain of computer neural networks and image processing. This research is involved in the study of neural networks and wavelet image processing techniques in the application of human face recognition. The objective of the system is to acquire a digitized still image of a human face, carry out pre-processing on the image as required, an then, given a prior database of images of possible individuals, be able to recognize the individual in the image. The pre-processing segment of the system includes several procedures, namely image compression, denoising, and feature extraction. The image processing is carried out using Daubechies wavelets. Once the images have been passed through the wavelet-based image processor they can be efficiently analyzed by means of a neural network. A back- propagation neural network is used for the recognition segment of the system. The main constraints of the system is with regard to the characteristics of the images being processed. The system should be able to carry out effective recognition of the human faces irrespective of the individual's facial-expression, presence of extraneous objects such as head-gear or spectacles, and face/head orientation. A potential application of this face recognition system would be as a secondary verification method in an automated teller machine.

Hidden physics models: Machine learning of nonlinear partial differential equations

NASA Astrophysics Data System (ADS)

Raissi, Maziar; Karniadakis, George Em

2018-03-01

While there is currently a lot of enthusiasm about "big data", useful data is usually "small" and expensive to acquire. In this paper, we present a new paradigm of learning partial differential equations from small data. In particular, we introduce hidden physics models, which are essentially data-efficient learning machines capable of leveraging the underlying laws of physics, expressed by time dependent and nonlinear partial differential equations, to extract patterns from high-dimensional data generated from experiments. The proposed methodology may be applied to the problem of learning, system identification, or data-driven discovery of partial differential equations. Our framework relies on Gaussian processes, a powerful tool for probabilistic inference over functions, that enables us to strike a balance between model complexity and data fitting. The effectiveness of the proposed approach is demonstrated through a variety of canonical problems, spanning a number of scientific domains, including the Navier-Stokes, Schrödinger, Kuramoto-Sivashinsky, and time dependent linear fractional equations. The methodology provides a promising new direction for harnessing the long-standing developments of classical methods in applied mathematics and mathematical physics to design learning machines with the ability to operate in complex domains without requiring large quantities of data.

SU-E-I-30: Image Analysis in Ultrasonography for Diagnosis of Sjoegren's Syndrome Using Dual-Tree Complex Wavelet Transform

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

Matsui, T; Ohki, M; Nakamura, T

Purpose: Sjoegren's syndrome (SS) is an autoimmune disease invading mainly salivary and lacrimal glands. Ultrasonography is used for an initial and non-invasive examination of this disease. However, the ultrasonography diagnosis tends to lack in objectivity and depends on the operator's skills. The purpose of this study is to propose a computer-aided diagnosis (CAD) system for SS based on a dual-tree complex wavelet transform (DT-CWT) and machine learning. Methods: The subjects of this study were 174 patients suspected of having SS at Nagasaki University Hospital and examined with ultrasonography of the parotid glands. Out of these patients, 77 patients were diagnosedmore » with SS by sialography. A region of interest (ROI) of 128 × 128 pixels was set within the parotid gland that was indicated by a dental radiologist. The DT-CWT was applied to the images in the ROI and every image was decomposed into 72 sub-images of the real and imaginary components in six different resolution levels and six orientations. The statistical features of the sub-image were calculated and used as data input for the support vector machine (SVM) classifier for the detection of SS. A ten-fold cross-validation was employed to verify the Resultof SVM. The accuracy of diagnosis was compared by a CAD system with a human observer performance. Results: The sensitivity, specificity, and accuracy in the detection of SS were 95%, 86%, and 91% through our CAD system respectively, while those by a human observer were 84%, 81%, and 83% respectively. Conclusion: The proposed computer-aided diagnosis system for Sjoegren's syndrome in ultrasonography based on dual-tree complex wavelet transform had a better performance than a human observer.« less

Classification of EEG Signals Based on Pattern Recognition Approach.

PubMed

Amin, Hafeez Ullah; Mumtaz, Wajid; Subhani, Ahmad Rauf; Saad, Mohamad Naufal Mohamad; Malik, Aamir Saeed

2017-01-01

Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a "pattern recognition" approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90-7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11-89.63% and 91.60-81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy.

Classification of EEG Signals Based on Pattern Recognition Approach

PubMed Central

Amin, Hafeez Ullah; Mumtaz, Wajid; Subhani, Ahmad Rauf; Saad, Mohamad Naufal Mohamad; Malik, Aamir Saeed

2017-01-01

Feature extraction is an important step in the process of electroencephalogram (EEG) signal classification. The authors propose a “pattern recognition” approach that discriminates EEG signals recorded during different cognitive conditions. Wavelet based feature extraction such as, multi-resolution decompositions into detailed and approximate coefficients as well as relative wavelet energy were computed. Extracted relative wavelet energy features were normalized to zero mean and unit variance and then optimized using Fisher's discriminant ratio (FDR) and principal component analysis (PCA). A high density EEG dataset validated the proposed method (128-channels) by identifying two classifications: (1) EEG signals recorded during complex cognitive tasks using Raven's Advance Progressive Metric (RAPM) test; (2) EEG signals recorded during a baseline task (eyes open). Classifiers such as, K-nearest neighbors (KNN), Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and Naïve Bayes (NB) were then employed. Outcomes yielded 99.11% accuracy via SVM classifier for coefficient approximations (A5) of low frequencies ranging from 0 to 3.90 Hz. Accuracy rates for detailed coefficients were 98.57 and 98.39% for SVM and KNN, respectively; and for detailed coefficients (D5) deriving from the sub-band range (3.90–7.81 Hz). Accuracy rates for MLP and NB classifiers were comparable at 97.11–89.63% and 91.60–81.07% for A5 and D5 coefficients, respectively. In addition, the proposed approach was also applied on public dataset for classification of two cognitive tasks and achieved comparable classification results, i.e., 93.33% accuracy with KNN. The proposed scheme yielded significantly higher classification performances using machine learning classifiers compared to extant quantitative feature extraction. These results suggest the proposed feature extraction method reliably classifies EEG signals recorded during cognitive tasks with a higher degree of accuracy. PMID:29209190

Adaptive hidden Markov model with anomaly States for price manipulation detection.

PubMed

Cao, Yi; Li, Yuhua; Coleman, Sonya; Belatreche, Ammar; McGinnity, Thomas Martin

2015-02-01

Price manipulation refers to the activities of those traders who use carefully designed trading behaviors to manually push up or down the underlying equity prices for making profits. With increasing volumes and frequency of trading, price manipulation can be extremely damaging to the proper functioning and integrity of capital markets. The existing literature focuses on either empirical studies of market abuse cases or analysis of particular manipulation types based on certain assumptions. Effective approaches for analyzing and detecting price manipulation in real time are yet to be developed. This paper proposes a novel approach, called adaptive hidden Markov model with anomaly states (AHMMAS) for modeling and detecting price manipulation activities. Together with wavelet transformations and gradients as the feature extraction methods, the AHMMAS model caters to price manipulation detection and basic manipulation type recognition. The evaluation experiments conducted on seven stock tick data from NASDAQ and the London Stock Exchange and 10 simulated stock prices by stochastic differential equation show that the proposed AHMMAS model can effectively detect price manipulation patterns and outperforms the selected benchmark models.

An Efficient Method for Image and Audio Steganography using Least Significant Bit (LSB) Substitution

NASA Astrophysics Data System (ADS)

Chadha, Ankit; Satam, Neha; Sood, Rakshak; Bade, Dattatray

2013-09-01

In order to improve the data hiding in all types of multimedia data formats such as image and audio and to make hidden message imperceptible, a novel method for steganography is introduced in this paper. It is based on Least Significant Bit (LSB) manipulation and inclusion of redundant noise as secret key in the message. This method is applied to data hiding in images. For data hiding in audio, Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) both are used. All the results displayed prove to be time-efficient and effective. Also the algorithm is tested for various numbers of bits. For those values of bits, Mean Square Error (MSE) and Peak-Signal-to-Noise-Ratio (PSNR) are calculated and plotted. Experimental results show that the stego-image is visually indistinguishable from the original cover-image when n<=4, because of better PSNR which is achieved by this technique. The final results obtained after steganography process does not reveal presence of any hidden message, thus qualifying the criteria of imperceptible message.

Mean-field message-passing equations in the Hopfield model and its generalizations

NASA Astrophysics Data System (ADS)

Mézard, Marc

2017-02-01

Motivated by recent progress in using restricted Boltzmann machines as preprocessing algorithms for deep neural network, we revisit the mean-field equations [belief-propagation and Thouless-Anderson Palmer (TAP) equations] in the best understood of such machines, namely the Hopfield model of neural networks, and we explicit how they can be used as iterative message-passing algorithms, providing a fast method to compute the local polarizations of neurons. In the "retrieval phase", where neurons polarize in the direction of one memorized pattern, we point out a major difference between the belief propagation and TAP equations: The set of belief propagation equations depends on the pattern which is retrieved, while one can use a unique set of TAP equations. This makes the latter method much better suited for applications in the learning process of restricted Boltzmann machines. In the case where the patterns memorized in the Hopfield model are not independent, but are correlated through a combinatorial structure, we show that the TAP equations have to be modified. This modification can be seen either as an alteration of the reaction term in TAP equations or, more interestingly, as the consequence of message passing on a graphical model with several hidden layers, where the number of hidden layers depends on the depth of the correlations in the memorized patterns. This layered structure is actually necessary when one deals with more general restricted Boltzmann machines.

Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine.

PubMed

Madero Orozco, Hiram; Vergara Villegas, Osslan Osiris; Cruz Sánchez, Vianey Guadalupe; Ochoa Domínguez, Humberto de Jesús; Nandayapa Alfaro, Manuel de Jesús

2015-02-12

Lung cancer is a leading cause of death worldwide; it refers to the uncontrolled growth of abnormal cells in the lung. A computed tomography (CT) scan of the thorax is the most sensitive method for detecting cancerous lung nodules. A lung nodule is a round lesion which can be either non-cancerous or cancerous. In the CT, the lung cancer is observed as round white shadow nodules. The possibility to obtain a manually accurate interpretation from CT scans demands a big effort by the radiologist and might be a fatiguing process. Therefore, the design of a computer-aided diagnosis (CADx) system would be helpful as a second opinion tool. The stages of the proposed CADx are: a supervised extraction of the region of interest to eliminate the shape differences among CT images. The Daubechies db1, db2, and db4 wavelet transforms are computed with one and two levels of decomposition. After that, 19 features are computed from each wavelet sub-band. Then, the sub-band and attribute selection is performed. As a result, 11 features are selected and combined in pairs as inputs to the support vector machine (SVM), which is used to distinguish CT images containing cancerous nodules from those not containing nodules. The clinical data set used for experiments consists of 45 CT scans from ELCAP and LIDC. For the training stage 61 CT images were used (36 with cancerous lung nodules and 25 without lung nodules). The system performance was tested with 45 CT scans (23 CT scans with lung nodules and 22 without nodules), different from that used for training. The results obtained show that the methodology successfully classifies cancerous nodules with a diameter from 2 mm to 30 mm. The total preciseness obtained was 82%; the sensitivity was 90.90%, whereas the specificity was 73.91%. The CADx system presented is competitive with other literature systems in terms of sensitivity. The system reduces the complexity of classification by not performing the typical segmentation stage of most CADx systems. Additionally, the novelty of the algorithm is the use of a wavelet feature descriptor.

Appearance and characterization of fruit image textures for quality sorting using wavelet transform and genetic algorithms.

PubMed

Khoje, Suchitra

2018-02-01

Images of four qualities of mangoes and guavas are evaluated for color and textural features to characterize and classify them, and to model the fruit appearance grading. The paper discusses three approaches to identify most discriminating texture features of both the fruits. In the first approach, fruit's color and texture features are selected using Mahalanobis distance. A total of 20 color features and 40 textural features are extracted for analysis. Using Mahalanobis distance and feature intercorrelation analyses, one best color feature (mean of a* [L*a*b* color space]) and two textural features (energy a*, contrast of H*) are selected as features for Guava while two best color features (R std, H std) and one textural features (energy b*) are selected as features for mangoes with the highest discriminate power. The second approach studies some common wavelet families for searching the best classification model for fruit quality grading. The wavelet features extracted from five basic mother wavelets (db, bior, rbior, Coif, Sym) are explored to characterize fruits texture appearance. In third approach, genetic algorithm is used to select only those color and wavelet texture features that are relevant to the separation of the class, from a large universe of features. The study shows that image color and texture features which were identified using a genetic algorithm can distinguish between various qualities classes of fruits. The experimental results showed that support vector machine classifier is elected for Guava grading with an accuracy of 97.61% and artificial neural network is elected from Mango grading with an accuracy of 95.65%. The proposed method is nondestructive fruit quality assessment method. The experimental results has proven that Genetic algorithm along with wavelet textures feature has potential to discriminate fruit quality. Finally, it can be concluded that discussed method is an accurate, reliable, and objective tool to determine fruit quality namely Mango and Guava, and might be applicable to in-line sorting systems. © 2017 Wiley Periodicals, Inc.

Application of the wavelet packet transform to vibration signals for surface roughness monitoring in CNC turning operations

NASA Astrophysics Data System (ADS)

García Plaza, E.; Núñez López, P. J.

2018-01-01

The wavelet packet transform method decomposes a time signal into several independent time-frequency signals called packets. This enables the temporary location of transient events occurring during the monitoring of the cutting processes, which is advantageous in monitoring condition and fault diagnosis. This paper proposes the monitoring of surface roughness using a single low cost sensor that is easily implemented in numerical control machine tools in order to make on-line decisions on workpiece surface finish quality. Packet feature extraction in vibration signals was applied to correlate the sensor signals to measured surface roughness. For the successful application of the WPT method, mother wavelets, packet decomposition level, and appropriate packet selection methods should be considered, but are poorly understood aspects in the literature. In this novel contribution, forty mother wavelets, optimal decomposition level, and packet reduction methods were analysed, as well as identifying the effective frequency range providing the best packet feature extraction for monitoring surface finish. The results show that mother wavelet biorthogonal 4.4 in decomposition level L3 with the fusion of the orthogonal vibration components (ax + ay + az) were the best option in the vibration signal and surface roughness correlation. The best packets were found in the medium-high frequency DDA (6250-9375 Hz) and high frequency ADA (9375-12500 Hz) ranges, and the feed acceleration component ay was the primary source of information. The packet reduction methods forfeited packets with relevant features to the signal, leading to poor results for the prediction of surface roughness. WPT is a robust vibration signal processing method for the monitoring of surface roughness using a single sensor without other information sources, satisfactory results were obtained in comparison to other processing methods with a low computational cost.

Computer-aided diagnosis of breast microcalcifications based on dual-tree complex wavelet transform.

PubMed

Jian, Wushuai; Sun, Xueyan; Luo, Shuqian

2012-12-19

Digital mammography is the most reliable imaging modality for breast carcinoma diagnosis and breast micro-calcifications is regarded as one of the most important signs on imaging diagnosis. In this paper, a computer-aided diagnosis (CAD) system is presented for breast micro-calcifications based on dual-tree complex wavelet transform (DT-CWT) to facilitate radiologists like double reading. Firstly, 25 abnormal ROIs were extracted according to the center and diameter of the lesions manually and 25 normal ROIs were selected randomly. Then micro-calcifications were segmented by combining space and frequency domain techniques. We extracted three texture features based on wavelet (Haar, DB4, DT-CWT) transform. Totally 14 descriptors were introduced to define the characteristics of the suspicious micro-calcifications. Principal Component Analysis (PCA) was used to transform these descriptors to a compact and efficient vector expression. Support Vector Machine (SVM) classifier was used to classify potential micro-calcifications. Finally, we used the receiver operating characteristic (ROC) curve and free-response operating characteristic (FROC) curve to evaluate the performance of the CAD system. The results of SVM classifications based on different wavelets shows DT-CWT has a better performance. Compared with other results, DT-CWT method achieved an accuracy of 96% and 100% for the classification of normal and abnormal ROIs, and the classification of benign and malignant micro-calcifications respectively. In FROC analysis, our CAD system for clinical dataset detection achieved a sensitivity of 83.5% at a false positive per image of 1.85. Compared with general wavelets, DT-CWT could describe the features more effectively, and our CAD system had a competitive performance.

Computer-aided diagnosis of breast microcalcifications based on dual-tree complex wavelet transform

PubMed Central

2012-01-01

Background Digital mammography is the most reliable imaging modality for breast carcinoma diagnosis and breast micro-calcifications is regarded as one of the most important signs on imaging diagnosis. In this paper, a computer-aided diagnosis (CAD) system is presented for breast micro-calcifications based on dual-tree complex wavelet transform (DT-CWT) to facilitate radiologists like double reading. Methods Firstly, 25 abnormal ROIs were extracted according to the center and diameter of the lesions manually and 25 normal ROIs were selected randomly. Then micro-calcifications were segmented by combining space and frequency domain techniques. We extracted three texture features based on wavelet (Haar, DB4, DT-CWT) transform. Totally 14 descriptors were introduced to define the characteristics of the suspicious micro-calcifications. Principal Component Analysis (PCA) was used to transform these descriptors to a compact and efficient vector expression. Support Vector Machine (SVM) classifier was used to classify potential micro-calcifications. Finally, we used the receiver operating characteristic (ROC) curve and free-response operating characteristic (FROC) curve to evaluate the performance of the CAD system. Results The results of SVM classifications based on different wavelets shows DT-CWT has a better performance. Compared with other results, DT-CWT method achieved an accuracy of 96% and 100% for the classification of normal and abnormal ROIs, and the classification of benign and malignant micro-calcifications respectively. In FROC analysis, our CAD system for clinical dataset detection achieved a sensitivity of 83.5% at a false positive per image of 1.85. Conclusions Compared with general wavelets, DT-CWT could describe the features more effectively, and our CAD system had a competitive performance. PMID:23253202

Hybrid Discrete Wavelet Transform and Gabor Filter Banks Processing for Features Extraction from Biomedical Images

PubMed Central

Lahmiri, Salim; Boukadoum, Mounir

2013-01-01

A new methodology for automatic feature extraction from biomedical images and subsequent classification is presented. The approach exploits the spatial orientation of high-frequency textural features of the processed image as determined by a two-step process. First, the two-dimensional discrete wavelet transform (DWT) is applied to obtain the HH high-frequency subband image. Then, a Gabor filter bank is applied to the latter at different frequencies and spatial orientations to obtain new Gabor-filtered image whose entropy and uniformity are computed. Finally, the obtained statistics are fed to a support vector machine (SVM) binary classifier. The approach was validated on mammograms, retina, and brain magnetic resonance (MR) images. The obtained classification accuracies show better performance in comparison to common approaches that use only the DWT or Gabor filter banks for feature extraction. PMID:27006906

Histogram of gradient and binarized statistical image features of wavelet subband-based palmprint features extraction

NASA Astrophysics Data System (ADS)

Attallah, Bilal; Serir, Amina; Chahir, Youssef; Boudjelal, Abdelwahhab

2017-11-01

Palmprint recognition systems are dependent on feature extraction. A method of feature extraction using higher discrimination information was developed to characterize palmprint images. In this method, two individual feature extraction techniques are applied to a discrete wavelet transform of a palmprint image, and their outputs are fused. The two techniques used in the fusion are the histogram of gradient and the binarized statistical image features. They are then evaluated using an extreme learning machine classifier before selecting a feature based on principal component analysis. Three palmprint databases, the Hong Kong Polytechnic University (PolyU) Multispectral Palmprint Database, Hong Kong PolyU Palmprint Database II, and the Delhi Touchless (IIDT) Palmprint Database, are used in this study. The study shows that our method effectively identifies and verifies palmprints and outperforms other methods based on feature extraction.

A new set of wavelet- and fractals-based features for Gleason grading of prostate cancer histopathology images

NASA Astrophysics Data System (ADS)

Mosquera Lopez, Clara; Agaian, Sos

2013-02-01

Prostate cancer detection and staging is an important step towards patient treatment selection. Advancements in digital pathology allow the application of new quantitative image analysis algorithms for computer-assisted diagnosis (CAD) on digitized histopathology images. In this paper, we introduce a new set of features to automatically grade pathological images using the well-known Gleason grading system. The goal of this study is to classify biopsy images belonging to Gleason patterns 3, 4, and 5 by using a combination of wavelet and fractal features. For image classification we use pairwise coupling Support Vector Machine (SVM) classifiers. The accuracy of the system, which is close to 97%, is estimated through three different cross-validation schemes. The proposed system offers the potential for automating classification of histological images and supporting prostate cancer diagnosis.

Object's optical geometry measurements based on Extended Depth of Field (EDoF) approach

NASA Astrophysics Data System (ADS)

Szydłowski, Michał; Powałka, Bartosz; Chady, Tomasz; Waszczuk, Paweł

2017-02-01

The authors propose a method of using EDoF in macro inspections using bi-telecentric lenses and a specially designed experimental machine setup, allowing accurate focal distance changing. Also a software method is presented allowing EDoF image reconstruction using the continuous wavelet transform (CWT). Exploited method results are additionally compared with measurements performed with Keyence's LJ-V Series in-line Profilometer for reference matters.

Coupling hydrological modeling and support vector regression to model hydropeaking in alpine catchments.

PubMed

Chiogna, Gabriele; Marcolini, Giorgia; Liu, Wanying; Pérez Ciria, Teresa; Tuo, Ye

2018-08-15

Water management in the alpine region has an important impact on streamflow. In particular, hydropower production is known to cause hydropeaking i.e., sudden fluctuations in river stage caused by the release or storage of water in artificial reservoirs. Modeling hydropeaking with hydrological models, such as the Soil Water Assessment Tool (SWAT), requires knowledge of reservoir management rules. These data are often not available since they are sensitive information belonging to hydropower production companies. In this short communication, we propose to couple the results of a calibrated hydrological model with a machine learning method to reproduce hydropeaking without requiring the knowledge of the actual reservoir management operation. We trained a support vector machine (SVM) with SWAT model outputs, the day of the week and the energy price. We tested the model for the Upper Adige river basin in North-East Italy. A wavelet analysis showed that energy price has a significant influence on river discharge, and a wavelet coherence analysis demonstrated the improved performance of the SVM model in comparison to the SWAT model alone. The SVM model was also able to capture the fluctuations in streamflow caused by hydropeaking when both energy price and river discharge displayed a complex temporal dynamic. Copyright © 2018 Elsevier B.V. All rights reserved.

Stop Sleazeware

ERIC Educational Resources Information Center

Reynolds, Ben

2005-01-01

"Sleazeware" is the authors' term for spyware, adware, malware, trackware, foistware, trojans, and other programs that sleaze into computers, either as a hidden component or by tricking someone into downloading them. Once in the machine, the program phones home for purposes ranging from simply reporting where people browse to downloading…

Improving the Accuracy and Training Speed of Motor Imagery Brain-Computer Interfaces Using Wavelet-Based Combined Feature Vectors and Gaussian Mixture Model-Supervectors.

PubMed

Lee, David; Park, Sang-Hoon; Lee, Sang-Goog

2017-10-07

In this paper, we propose a set of wavelet-based combined feature vectors and a Gaussian mixture model (GMM)-supervector to enhance training speed and classification accuracy in motor imagery brain-computer interfaces. The proposed method is configured as follows: first, wavelet transforms are applied to extract the feature vectors for identification of motor imagery electroencephalography (EEG) and principal component analyses are used to reduce the dimensionality of the feature vectors and linearly combine them. Subsequently, the GMM universal background model is trained by the expectation-maximization (EM) algorithm to purify the training data and reduce its size. Finally, a purified and reduced GMM-supervector is used to train the support vector machine classifier. The performance of the proposed method was evaluated for three different motor imagery datasets in terms of accuracy, kappa, mutual information, and computation time, and compared with the state-of-the-art algorithms. The results from the study indicate that the proposed method achieves high accuracy with a small amount of training data compared with the state-of-the-art algorithms in motor imagery EEG classification.

Applications of wavelet-based compression to multidimensional Earth science data

NASA Technical Reports Server (NTRS)

Bradley, Jonathan N.; Brislawn, Christopher M.

1993-01-01

A data compression algorithm involving vector quantization (VQ) and the discrete wavelet transform (DWT) is applied to two different types of multidimensional digital earth-science data. The algorithms (WVQ) is optimized for each particular application through an optimization procedure that assigns VQ parameters to the wavelet transform subbands subject to constraints on compression ratio and encoding complexity. Preliminary results of compressing global ocean model data generated on a Thinking Machines CM-200 supercomputer are presented. The WVQ scheme is used in both a predictive and nonpredictive mode. Parameters generated by the optimization algorithm are reported, as are signal-to-noise (SNR) measurements of actual quantized data. The problem of extrapolating hydrodynamic variables across the continental landmasses in order to compute the DWT on a rectangular grid is discussed. Results are also presented for compressing Landsat TM 7-band data using the WVQ scheme. The formulation of the optimization problem is presented along with SNR measurements of actual quantized data. Postprocessing applications are considered in which the seven spectral bands are clustered into 256 clusters using a k-means algorithm and analyzed using the Los Alamos multispectral data analysis program, SPECTRUM, both before and after being compressed using the WVQ program.

Bone marrow cavity segmentation using graph-cuts with wavelet-based texture feature.

PubMed

Shigeta, Hironori; Mashita, Tomohiro; Kikuta, Junichi; Seno, Shigeto; Takemura, Haruo; Ishii, Masaru; Matsuda, Hideo

2017-10-01

Emerging bioimaging technologies enable us to capture various dynamic cellular activities [Formula: see text]. As large amounts of data are obtained these days and it is becoming unrealistic to manually process massive number of images, automatic analysis methods are required. One of the issues for automatic image segmentation is that image-taking conditions are variable. Thus, commonly, many manual inputs are required according to each image. In this paper, we propose a bone marrow cavity (BMC) segmentation method for bone images as BMC is considered to be related to the mechanism of bone remodeling, osteoporosis, and so on. To reduce manual inputs to segment BMC, we classified the texture pattern using wavelet transformation and support vector machine. We also integrated the result of texture pattern classification into the graph-cuts-based image segmentation method because texture analysis does not consider spatial continuity. Our method is applicable to a particular frame in an image sequence in which the condition of fluorescent material is variable. In the experiment, we evaluated our method with nine types of mother wavelets and several sets of scale parameters. The proposed method with graph-cuts and texture pattern classification performs well without manual inputs by a user.

Evaluation of effectiveness of wavelet based denoising schemes using ANN and SVM for bearing condition classification.

PubMed

Vijay, G S; Kumar, H S; Srinivasa Pai, P; Sriram, N S; Rao, Raj B K N

2012-01-01

The wavelet based denoising has proven its ability to denoise the bearing vibration signals by improving the signal-to-noise ratio (SNR) and reducing the root-mean-square error (RMSE). In this paper seven wavelet based denoising schemes have been evaluated based on the performance of the Artificial Neural Network (ANN) and the Support Vector Machine (SVM), for the bearing condition classification. The work consists of two parts, the first part in which a synthetic signal simulating the defective bearing vibration signal with Gaussian noise was subjected to these denoising schemes. The best scheme based on the SNR and the RMSE was identified. In the second part, the vibration signals collected from a customized Rolling Element Bearing (REB) test rig for four bearing conditions were subjected to these denoising schemes. Several time and frequency domain features were extracted from the denoised signals, out of which a few sensitive features were selected using the Fisher's Criterion (FC). Extracted features were used to train and test the ANN and the SVM. The best denoising scheme identified, based on the classification performances of the ANN and the SVM, was found to be the same as the one obtained using the synthetic signal.

Speech sound classification and detection of articulation disorders with support vector machines and wavelets.

PubMed

Georgoulas, George; Georgopoulos, Voula C; Stylios, Chrysostomos D

2006-01-01

This paper proposes a novel integrated methodology to extract features and classify speech sounds with intent to detect the possible existence of a speech articulation disorder in a speaker. Articulation, in effect, is the specific and characteristic way that an individual produces the speech sounds. A methodology to process the speech signal, extract features and finally classify the signal and detect articulation problems in a speaker is presented. The use of support vector machines (SVMs), for the classification of speech sounds and detection of articulation disorders is introduced. The proposed method is implemented on a data set where different sets of features and different schemes of SVMs are tested leading to satisfactory performance.

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

PubMed

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

2015-01-01

An extreme learning machine (ELM) is a feedforward neural network (FNN) like learning system whose connections with output neurons are adjustable, while the connections with and within hidden neurons are randomly fixed. Numerous applications have demonstrated the feasibility and high efficiency of ELM-like systems. It has, however, been open if this is true for any general applications. In this two-part paper, we conduct a comprehensive feasibility analysis of ELM. In Part I, we provide an answer to the question by theoretically justifying the following: 1) for some suitable activation functions, such as polynomials, Nadaraya-Watson and sigmoid functions, the ELM-like systems can attain the theoretical generalization bound of the FNNs with all connections adjusted, i.e., they do not degrade the generalization capability of the FNNs even when the connections with and within hidden neurons are randomly fixed; 2) the number of hidden neurons needed for an ELM-like system to achieve the theoretical bound can be estimated; and 3) whenever the activation function is taken as polynomial, the deduced hidden layer output matrix is of full column-rank, therefore the generalized inverse technique can be efficiently applied to yield the solution of an ELM-like system, and, furthermore, for the nonpolynomial case, the Tikhonov regularization can be applied to guarantee the weak regularity while not sacrificing the generalization capability. In Part II, however, we reveal a different aspect of the feasibility of ELM: there also exists some activation functions, which makes the corresponding ELM degrade the generalization capability. The obtained results underlie the feasibility and efficiency of ELM-like systems, and yield various generalizations and improvements of the systems as well.

Modeling Spanish Mood Choice in Belief Statements

ERIC Educational Resources Information Center

Robinson, Jason R.

2013-01-01

This work develops a computational methodology new to linguistics that empirically evaluates competing linguistic theories on Spanish verbal mood choice through the use of computational techniques to learn mood and other hidden linguistic features from Spanish belief statements found in corpora. The machine learned probabilistic linguistic models…

Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine

PubMed Central

Liu, Yongxiang; Huo, Kai; Zhang, Zhongshuai

2018-01-01

A novel radar high-resolution range profile (HRRP) target recognition method based on a stacked autoencoder (SAE) and extreme learning machine (ELM) is presented in this paper. As a key component of deep structure, the SAE does not only learn features by making use of data, it also obtains feature expressions at different levels of data. However, with the deep structure, it is hard to achieve good generalization performance with a fast learning speed. ELM, as a new learning algorithm for single hidden layer feedforward neural networks (SLFNs), has attracted great interest from various fields for its fast learning speed and good generalization performance. However, ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. In addition, the existing ELM methods cannot utilize the class information of targets well. To solve this problem, a regularized ELM method based on the class information of the target is proposed. In this paper, SAE and the regularized ELM are combined to make full use of their advantages and make up for each of their shortcomings. The effectiveness of the proposed method is demonstrated by experiments with measured radar HRRP data. The experimental results show that the proposed method can achieve good performance in the two aspects of real-time and accuracy, especially when only a few training samples are available. PMID:29320453

Radar HRRP Target Recognition Based on Stacked Autoencoder and Extreme Learning Machine.

PubMed

Zhao, Feixiang; Liu, Yongxiang; Huo, Kai; Zhang, Shuanghui; Zhang, Zhongshuai

2018-01-10

A novel radar high-resolution range profile (HRRP) target recognition method based on a stacked autoencoder (SAE) and extreme learning machine (ELM) is presented in this paper. As a key component of deep structure, the SAE does not only learn features by making use of data, it also obtains feature expressions at different levels of data. However, with the deep structure, it is hard to achieve good generalization performance with a fast learning speed. ELM, as a new learning algorithm for single hidden layer feedforward neural networks (SLFNs), has attracted great interest from various fields for its fast learning speed and good generalization performance. However, ELM needs more hidden nodes than conventional tuning-based learning algorithms due to the random set of input weights and hidden biases. In addition, the existing ELM methods cannot utilize the class information of targets well. To solve this problem, a regularized ELM method based on the class information of the target is proposed. In this paper, SAE and the regularized ELM are combined to make full use of their advantages and make up for each of their shortcomings. The effectiveness of the proposed method is demonstrated by experiments with measured radar HRRP data. The experimental results show that the proposed method can achieve good performance in the two aspects of real-time and accuracy, especially when only a few training samples are available.

Veiled EGM Jackpots: The Effects of Hidden and Mystery Jackpots on Gambling Intensity.

PubMed

Donaldson, Phillip; Langham, Erika; Rockloff, Matthew J; Browne, Matthew

2016-06-01

Understanding the impact of EGM Jackpots on gambling intensity may allow targeted strategies to be implemented that facilitate harm minimisation by acting to reduce losses of gamblers who play frequently, while maintaining the enjoyment and excitement of potential jackpots. The current study investigated the influences of Hidden and Mystery Jackpots on EGM gambling intensity. In a Hidden Jackpot, the prize value is not shown to the player, although the existence of a jackpot prize is advertised. In a Mystery Jackpot, the jackpot triggering state of the machine is unknown to players. One hundred and seven volunteers (males = 49, females = 58) played a laptop-simulated EGM with a starting $20 real-money stake and a chance to win a Jackpot ($500). Participants played for either a Hidden or Known Jackpot Value, with either a Mystery or Known winning symbol combination in a crossed design. Lastly, a control condition with no jackpot was included. Gambling intensity (speed of bets, persistence) was greater when the Jackpot value was unknown, especially when a winning-symbol combination suggested that a win was possible. While there is no evidence in the present investigation to suggest that Hidden or Mystery jackpots contribute to greater player enjoyment, there is some evidence to suggest a marginal positive contribution of hidden jackpots to risky playing behaviour.

Geographical traceability of Marsdenia tenacissima by Fourier transform infrared spectroscopy and chemometrics

NASA Astrophysics Data System (ADS)

Li, Chao; Yang, Sheng-Chao; Guo, Qiao-Sheng; Zheng, Kai-Yan; Wang, Ping-Li; Meng, Zhen-Gui

2016-01-01

A combination of Fourier transform infrared spectroscopy with chemometrics tools provided an approach for studying Marsdenia tenacissima according to its geographical origin. A total of 128 M. tenacissima samples from four provinces in China were analyzed with FTIR spectroscopy. Six pattern recognition methods were used to construct the discrimination models: support vector machine-genetic algorithms, support vector machine-particle swarm optimization, K-nearest neighbors, radial basis function neural network, random forest and support vector machine-grid search. Experimental results showed that K-nearest neighbors was superior to other mathematical algorithms after data were preprocessed with wavelet de-noising, with a discrimination rate of 100% in both the training and prediction sets. This study demonstrated that FTIR spectroscopy coupled with K-nearest neighbors could be successfully applied to determine the geographical origins of M. tenacissima samples, thereby providing reliable authentication in a rapid, cheap and noninvasive way.

Can machines think? A report on Turing test experiments at the Royal Society

NASA Astrophysics Data System (ADS)

Warwick, Kevin; Shah, Huma

2016-11-01

In this article we consider transcripts that originated from a practical series of Turing's Imitation Game that was held on 6 and 7 June 2014 at the Royal Society London. In all cases the tests involved a three-participant simultaneous comparison by an interrogator of two hidden entities, one being a human and the other a machine. Each of the transcripts considered here resulted in a human interrogator being fooled such that they could not make the 'right identification', that is, they could not say for certain which was the machine and which was the human. The transcripts presented all involve one machine only, namely 'Eugene Goostman', the result being that the machine became the first to pass the Turing test, as set out by Alan Turing, on unrestricted conversation. This is the first time that results from the Royal Society tests have been disclosed and discussed in a paper.

Correct machine learning on protein sequences: a peer-reviewing perspective.

PubMed

Walsh, Ian; Pollastri, Gianluca; Tosatto, Silvio C E

2016-09-01

Machine learning methods are becoming increasingly popular to predict protein features from sequences. Machine learning in bioinformatics can be powerful but carries also the risk of introducing unexpected biases, which may lead to an overestimation of the performance. This article espouses a set of guidelines to allow both peer reviewers and authors to avoid common machine learning pitfalls. Understanding biology is necessary to produce useful data sets, which have to be large and diverse. Separating the training and test process is imperative to avoid over-selling method performance, which is also dependent on several hidden parameters. A novel predictor has always to be compared with several existing methods, including simple baseline strategies. Using the presented guidelines will help nonspecialists to appreciate the critical issues in machine learning. © The Author 2015. Published by Oxford University Press. For Permissions, please email: journals.permissions@oup.com.

The incorrect usage of singular spectral analysis and discrete wavelet transform in hybrid models to predict hydrological time series

NASA Astrophysics Data System (ADS)

Du, Kongchang; Zhao, Ying; Lei, Jiaqiang

2017-09-01

In hydrological time series prediction, singular spectrum analysis (SSA) and discrete wavelet transform (DWT) are widely used as preprocessing techniques for artificial neural network (ANN) and support vector machine (SVM) predictors. These hybrid or ensemble models seem to largely reduce the prediction error. In current literature researchers apply these techniques to the whole observed time series and then obtain a set of reconstructed or decomposed time series as inputs to ANN or SVM. However, through two comparative experiments and mathematical deduction we found the usage of SSA and DWT in building hybrid models is incorrect. Since SSA and DWT adopt 'future' values to perform the calculation, the series generated by SSA reconstruction or DWT decomposition contain information of 'future' values. These hybrid models caused incorrect 'high' prediction performance and may cause large errors in practice.

Transient classification in LIGO data using difference boosting neural network

NASA Astrophysics Data System (ADS)

Mukund, N.; Abraham, S.; Kandhasamy, S.; Mitra, S.; Philip, N. S.

2017-05-01

Detection and classification of transients in data from gravitational wave detectors are crucial for efficient searches for true astrophysical events and identification of noise sources. We present a hybrid method for classification of short duration transients seen in gravitational wave data using both supervised and unsupervised machine learning techniques. To train the classifiers, we use the relative wavelet energy and the corresponding entropy obtained by applying one-dimensional wavelet decomposition on the data. The prediction accuracy of the trained classifier on nine simulated classes of gravitational wave transients and also LIGO's sixth science run hardware injections are reported. Targeted searches for a couple of known classes of nonastrophysical signals in the first observational run of Advanced LIGO data are also presented. The ability to accurately identify transient classes using minimal training samples makes the proposed method a useful tool for LIGO detector characterization as well as searches for short duration gravitational wave signals.

Prognostics of Lithium-Ion Batteries Based on Wavelet Denoising and DE-RVM

PubMed Central

Zhang, Chaolong; He, Yigang; Yuan, Lifeng; Xiang, Sheng; Wang, Jinping

2015-01-01

Lithium-ion batteries are widely used in many electronic systems. Therefore, it is significantly important to estimate the lithium-ion battery's remaining useful life (RUL), yet very difficult. One important reason is that the measured battery capacity data are often subject to the different levels of noise pollution. In this paper, a novel battery capacity prognostics approach is presented to estimate the RUL of lithium-ion batteries. Wavelet denoising is performed with different thresholds in order to weaken the strong noise and remove the weak noise. Relevance vector machine (RVM) improved by differential evolution (DE) algorithm is utilized to estimate the battery RUL based on the denoised data. An experiment including battery 5 capacity prognostics case and battery 18 capacity prognostics case is conducted and validated that the proposed approach can predict the trend of battery capacity trajectory closely and estimate the battery RUL accurately. PMID:26413090

E-Nose Vapor Identification Based on Dempster-Shafer Fusion of Multiple Classifiers

NASA Technical Reports Server (NTRS)

Li, Winston; Leung, Henry; Kwan, Chiman; Linnell, Bruce R.

2005-01-01

Electronic nose (e-nose) vapor identification is an efficient approach to monitor air contaminants in space stations and shuttles in order to ensure the health and safety of astronauts. Data preprocessing (measurement denoising and feature extraction) and pattern classification are important components of an e-nose system. In this paper, a wavelet-based denoising method is applied to filter the noisy sensor measurements. Transient-state features are then extracted from the denoised sensor measurements, and are used to train multiple classifiers such as multi-layer perceptions (MLP), support vector machines (SVM), k nearest neighbor (KNN), and Parzen classifier. The Dempster-Shafer (DS) technique is used at the end to fuse the results of the multiple classifiers to get the final classification. Experimental analysis based on real vapor data shows that the wavelet denoising method can remove both random noise and outliers successfully, and the classification rate can be improved by using classifier fusion.

23 CFR Appendix A to Part 1313 - Tamper Resistant Driver's License

Code of Federal Regulations, 2010 CFR

2010-04-01

...) Block graphics. (15) Security fonts and graphics with known hidden flaws. (16) Card stock, layer with colors. (17) Micro-graphics. (18) Retroflective security logos. (19) Machine readable technologies such... permit that has one or more of the following security features: (1) Ghost image. (2) Ghost graphic. (3...

Efficacy of hidden markov model over support vector machine on multiclass classification of healthy and cancerous cervical tissues

NASA Astrophysics Data System (ADS)

Mukhopadhyay, Sabyasachi; Kurmi, Indrajit; Pratiher, Sawon; Mukherjee, Sukanya; Barman, Ritwik; Ghosh, Nirmalya; Panigrahi, Prasanta K.

2018-02-01

In this paper, a comparative study between SVM and HMM has been carried out for multiclass classification of cervical healthy and cancerous tissues. In our study, the HMM methodology is more promising to produce higher accuracy in classification.

Machine learning for the automatic detection of anomalous events

NASA Astrophysics Data System (ADS)

Fisher, Wendy D.

In this dissertation, we describe our research contributions for a novel approach to the application of machine learning for the automatic detection of anomalous events. We work in two different domains to ensure a robust data-driven workflow that could be generalized for monitoring other systems. Specifically, in our first domain, we begin with the identification of internal erosion events in earth dams and levees (EDLs) using geophysical data collected from sensors located on the surface of the levee. As EDLs across the globe reach the end of their design lives, effectively monitoring their structural integrity is of critical importance. The second domain of interest is related to mobile telecommunications, where we investigate a system for automatically detecting non-commercial base station routers (BSRs) operating in protected frequency space. The presence of non-commercial BSRs can disrupt the connectivity of end users, cause service issues for the commercial providers, and introduce significant security concerns. We provide our motivation, experimentation, and results from investigating a generalized novel data-driven workflow using several machine learning techniques. In Chapter 2, we present results from our performance study that uses popular unsupervised clustering algorithms to gain insights to our real-world problems, and evaluate our results using internal and external validation techniques. Using EDL passive seismic data from an experimental laboratory earth embankment, results consistently show a clear separation of events from non-events in four of the five clustering algorithms applied. Chapter 3 uses a multivariate Gaussian machine learning model to identify anomalies in our experimental data sets. For the EDL work, we used experimental data from two different laboratory earth embankments. Additionally, we explore five wavelet transform methods for signal denoising. The best performance is achieved with the Haar wavelets. We achieve up to 97.3% overall accuracy and less than 1.4% false negatives in anomaly detection. In Chapter 4, we research using two-class and one-class support vector machines (SVMs) for an effective anomaly detection system. We again use the two different EDL data sets from experimental laboratory earth embankments (each having approximately 80% normal and 20% anomalies) to ensure our workflow is robust enough to work with multiple data sets and different types of anomalous events (e.g., cracks and piping). We apply Haar wavelet-denoising techniques and extract nine spectral features from decomposed segments of the time series data. The two-class SVM with 10-fold cross validation achieved over 94% overall accuracy and 96% F1-score. Our approach provides a means for automatically identifying anomalous events using various machine learning techniques. Detecting internal erosion events in aging EDLs, earlier than is currently possible, can allow more time to prevent or mitigate catastrophic failures. Results show that we can successfully separate normal from anomalous data observations in passive seismic data, and provide a step towards techniques for continuous real-time monitoring of EDL health. Our lightweight non-commercial BSR detection system also has promise in separating commercial from non-commercial BSR scans without the need for prior geographic location information, extensive time-lapse surveys, or a database of known commercial carriers. (Abstract shortened by ProQuest.).

A Multiscale Vision Model applied to analyze EIT images of the solar corona

NASA Astrophysics Data System (ADS)

Portier-Fozzani, F.; Vandame, B.; Bijaoui, A.; Maucherat, A. J.; EIT Team

2001-07-01

The large dynamic range provided by the SOHO/EIT CCD (1 : 5000) is needed to observe the large EUV zoom of coronal structures from coronal homes up to flares. Histograms show that often a wide dynamic range is present in each image. Extracting hidden structures in the background level requires specific techniques such as the use of the Multiscale Vision Model (MVM, Bijaoui et al., 1998). This method, based on wavelet transformations optimizes detection of various size objects, however complex they may be. Bijaoui et al. built the Multiscale Vision Model to extract small dynamical structures from noise, mainly for studying galaxies. In this paper, we describe requirements for the use of this method with SOHO/EIT images (calibration, size of the image, dynamics of the subimage, etc.). Two different areas were studied revealing hidden structures: (1) classical coronal mass ejection (CME) formation and (2) a complex group of active regions with its evolution. The aim of this paper is to define carefully the constraints for this new method of imaging the solar corona with SOHO/EIT. Physical analysis derived from multi-wavelength observations will later complete these first results.

Kurtosis based weighted sparse model with convex optimization technique for bearing fault diagnosis

NASA Astrophysics Data System (ADS)

Zhang, Han; Chen, Xuefeng; Du, Zhaohui; Yan, Ruqiang

2016-12-01

The bearing failure, generating harmful vibrations, is one of the most frequent reasons for machine breakdowns. Thus, performing bearing fault diagnosis is an essential procedure to improve the reliability of the mechanical system and reduce its operating expenses. Most of the previous studies focused on rolling bearing fault diagnosis could be categorized into two main families, kurtosis-based filter method and wavelet-based shrinkage method. Although tremendous progresses have been made, their effectiveness suffers from three potential drawbacks: firstly, fault information is often decomposed into proximal frequency bands and results in impulsive feature frequency band splitting (IFFBS) phenomenon, which significantly degrades the performance of capturing the optimal information band; secondly, noise energy spreads throughout all frequency bins and contaminates fault information in the information band, especially under the heavy noisy circumstance; thirdly, wavelet coefficients are shrunk equally to satisfy the sparsity constraints and most of the feature information energy are thus eliminated unreasonably. Therefore, exploiting two pieces of prior information (i.e., one is that the coefficient sequences of fault information in the wavelet basis is sparse, and the other is that the kurtosis of the envelope spectrum could evaluate accurately the information capacity of rolling bearing faults), a novel weighted sparse model and its corresponding framework for bearing fault diagnosis is proposed in this paper, coined KurWSD. KurWSD formulates the prior information into weighted sparse regularization terms and then obtains a nonsmooth convex optimization problem. The alternating direction method of multipliers (ADMM) is sequentially employed to solve this problem and the fault information is extracted through the estimated wavelet coefficients. Compared with state-of-the-art methods, KurWSD overcomes the three drawbacks and utilizes the advantages of both family tools. KurWSD has three main advantages: firstly, all the characteristic information scattered in proximal sub-bands is gathered through synthesizing those impulsive dominant sub-band signals and thus eliminates the dilemma of the IFFBS phenomenon. Secondly, the noises in the focused sub-bands could be alleviated efficiently through shrinking or removing the dense wavelet coefficients of Gaussian noise. Lastly, wavelet coefficients with faulty information are reliably detected and preserved through manipulating wavelet coefficients discriminatively based on the contribution to the impulsive components. Moreover, the reliability and effectiveness of the KurWSD are demonstrated through simulated and experimental signals.

ONRASIA Scientific Information Bulletin, Volume 17, Number 2, April/June 1992

DTIC Science & Technology

1992-06-01

studying the role of overcomplete- Tel: +81-422-59-4201 seminar on wavelets was chosen to be ness properties and their applications Fax: +81-422-59-3393...technologies, explore interactive environment for man- to emulate various types of cache proto- applications, and study how theycan be machine interface...cols. The Keio professors specifically integrated. Flexible integration is seen want to study the kind of logic simula- as an important goal in order for

A joint resonance frequency estimation and in-band noise reduction method for enhancing the detectability of bearing fault signals

NASA Astrophysics Data System (ADS)

Bozchalooi, I. Soltani; Liang, Ming

2008-05-01

The vibration signal measured from a bearing contains vital information for the prognostic and health assessment purposes. However, when bearings are installed as part of a complex mechanical system, the measured signal is often heavily clouded by various noises due to the compounded effect of interferences of other machine elements and background noises present in the measuring device. As such, reliable condition monitoring would not be possible without proper de-noising. This is particularly true for incipient bearing faults with very weak signature signals. A new de-noising scheme is proposed in this paper to enhance the vibration signals acquired from faulty bearings. This de-noising scheme features a spectral subtraction to trim down the in-band noise prior to wavelet filtering. The Gabor wavelet is used in the wavelet transform and its parameters, i.e., scale and shape factor are selected in separate steps. The proper scale is found based on a novel resonance estimation algorithm. This algorithm makes use of the information derived from the variable shaft rotational speed though such variation is highly undesirable in fault detection since it complicates the process substantially. The shape factor value is then selected by minimizing a smoothness index. This index is defined as the ratio of the geometric mean to the arithmetic mean of the wavelet coefficient moduli. De-noising results are presented for simulated signals and experimental data acquired from both normal and faulty bearings with defective outer race, inner race, and rolling element.

A wavelet-based technique to predict treatment outcome for Major Depressive Disorder.

PubMed

Mumtaz, Wajid; Xia, Likun; Mohd Yasin, Mohd Azhar; Azhar Ali, Syed Saad; Malik, Aamir Saeed

2017-01-01

Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant's treatment outcome may help during antidepressant's selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant's treatment outcome for the MDD patients.

Intelligent complementary sliding-mode control for LUSMS-based X-Y-theta motion control stage.

PubMed

Lin, Faa-Jeng; Chen, Syuan-Yi; Shyu, Kuo-Kai; Liu, Yen-Hung

2010-07-01

An intelligent complementary sliding-mode control (ICSMC) system using a recurrent wavelet-based Elman neural network (RWENN) estimator is proposed in this study to control the mover position of a linear ultrasonic motors (LUSMs)-based X-Y-theta motion control stage for the tracking of various contours. By the addition of a complementary generalized error transformation, the complementary sliding-mode control (CSMC) can efficiently reduce the guaranteed ultimate bound of the tracking error by half compared with the slidingmode control (SMC) while using the saturation function. To estimate a lumped uncertainty on-line and replace the hitting control of the CSMC directly, the RWENN estimator is adopted in the proposed ICSMC system. In the RWENN, each hidden neuron employs a different wavelet function as an activation function to improve both the convergent precision and the convergent time compared with the conventional Elman neural network (ENN). The estimation laws of the RWENN are derived using the Lyapunov stability theorem to train the network parameters on-line. A robust compensator is also proposed to confront the uncertainties including approximation error, optimal parameter vectors, and higher-order terms in Taylor series. Finally, some experimental results of various contours tracking show that the tracking performance of the ICSMC system is significantly improved compared with the SMC and CSMC systems.

Time-frequency featured co-movement between the stock and prices of crude oil and gold

NASA Astrophysics Data System (ADS)

Huang, Shupei; An, Haizhong; Gao, Xiangyun; Huang, Xuan

2016-02-01

The nonlinear relationships among variables caused by the hidden frequency information complicate the time series analysis. To shed more light on this nonlinear issue, we examine their relationships in joint time-frequency domain with multivariate framework, and the analyses in the time domain and frequency domain serve as comparisons. The daily Brent oil prices, London gold fixing price and Shanghai Composite index from January 1991 to September 2014 are adopted as example. First, they have long-term cointegration relationship in time domain from holistic perspective. Second, the Granger causality tests in different frequency bands are heterogeneous. Finally, the comparison between results from wavelet coherence and multiple wavelet coherence in the joint time-frequency domain indicates that in the high (1-14 days) and medium frequency (14-128 days) bands, the combination of Brent and gold prices has stronger correlation with the stock. In the low frequency band (256-512 days), year 2003 is the structure broken point before which Brent and oil are ideal choice for hedging the risk of the stock market. Thus, this paper offers more details between the Chinese stock market and the commodities markets of crude oil and gold, which suggests that the decisions for different time and frequencies should consider the corresponding benchmark information.

Detection of inter-turn short-circuit at start-up of induction machine based on torque analysis

NASA Astrophysics Data System (ADS)

Pietrowski, Wojciech; Górny, Konrad

2017-12-01

Recently, interest in new diagnostics methods in a field of induction machines was observed. Research presented in the paper shows the diagnostics of induction machine based on torque pulsation, under inter-turn short-circuit, during start-up of a machine. In the paper three numerical techniques were used: finite element analysis, signal analysis and artificial neural networks (ANN). The elaborated numerical model of faulty machine consists of field, circuit and motion equations. Voltage excited supply allowed to determine the torque waveform during start-up. The inter-turn short-circuit was treated as a galvanic connection between two points of the stator winding. The waveforms were calculated for different amounts of shorted-turns from 0 to 55. Due to the non-stationary waveforms a wavelet packet decomposition was used to perform an analysis of the torque. The obtained results of analysis were used as input vector for ANN. The response of the neural network was the number of shorted-turns in the stator winding. Special attention was paid to compare response of general regression neural network (GRNN) and multi-layer perceptron neural network (MLP). Based on the results of the research, the efficiency of the developed algorithm can be inferred.

Investigating the Relationship between Dialogue Structure and Tutoring Effectiveness: A Hidden Markov Modeling Approach

ERIC Educational Resources Information Center

Boyer, Kristy Elizabeth; Phillips, Robert; Ingram, Amy; Ha, Eun Young; Wallis, Michael; Vouk, Mladen; Lester, James

2011-01-01

Identifying effective tutorial dialogue strategies is a key issue for intelligent tutoring systems research. Human-human tutoring offers a valuable model for identifying effective tutorial strategies, but extracting them is a challenge because of the richness of human dialogue. This article addresses that challenge through a machine learning…

Learning to represent spatial transformations with factored higher-order Boltzmann machines.

PubMed

Memisevic, Roland; Hinton, Geoffrey E

2010-06-01

To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicative interactions that use the intensity of a pixel in the first image as a multiplicative gain on a learned, symmetric weight between a pixel in the second image and a hidden unit. This creates cubically many parameters, which form a three-dimensional interaction tensor. We describe a low-rank approximation to this interaction tensor that uses a sum of factors, each of which is a three-way outer product. This approximation allows efficient learning of transformations between larger image patches. Since each factor can be viewed as an image filter, the model as a whole learns optimal filter pairs for efficiently representing transformations. We demonstrate the learning of optimal filter pairs from various synthetic and real image sequences. We also show how learning about image transformations allows the model to perform a simple visual analogy task, and we show how a completely unsupervised network trained on transformations perceives multiple motions of transparent dot patterns in the same way as humans.

An Incremental Type-2 Meta-Cognitive Extreme Learning Machine.

PubMed

Pratama, Mahardhika; Zhang, Guangquan; Er, Meng Joo; Anavatti, Sreenatha

2017-02-01

Existing extreme learning algorithm have not taken into account four issues: 1) complexity; 2) uncertainty; 3) concept drift; and 4) high dimensionality. A novel incremental type-2 meta-cognitive extreme learning machine (ELM) called evolving type-2 ELM (eT2ELM) is proposed to cope with the four issues in this paper. The eT2ELM presents three main pillars of human meta-cognition: 1) what-to-learn; 2) how-to-learn; and 3) when-to-learn. The what-to-learn component selects important training samples for model updates by virtue of the online certainty-based active learning method, which renders eT2ELM as a semi-supervised classifier. The how-to-learn element develops a synergy between extreme learning theory and the evolving concept, whereby the hidden nodes can be generated and pruned automatically from data streams with no tuning of hidden nodes. The when-to-learn constituent makes use of the standard sample reserved strategy. A generalized interval type-2 fuzzy neural network is also put forward as a cognitive component, in which a hidden node is built upon the interval type-2 multivariate Gaussian function while exploiting a subset of Chebyshev series in the output node. The efficacy of the proposed eT2ELM is numerically validated in 12 data streams containing various concept drifts. The numerical results are confirmed by thorough statistical tests, where the eT2ELM demonstrates the most encouraging numerical results in delivering reliable prediction, while sustaining low complexity.

Effective Data-Driven Calibration for a Galvanometric Laser Scanning System Using Binocular Stereo Vision.

PubMed

Tu, Junchao; Zhang, Liyan

2018-01-12

A new solution to the problem of galvanometric laser scanning (GLS) system calibration is presented. Under the machine learning framework, we build a single-hidden layer feedforward neural network (SLFN）to represent the GLS system, which takes the digital control signal at the drives of the GLS system as input and the space vector of the corresponding outgoing laser beam as output. The training data set is obtained with the aid of a moving mechanism and a binocular stereo system. The parameters of the SLFN are efficiently solved in a closed form by using extreme learning machine (ELM). By quantitatively analyzing the regression precision with respective to the number of hidden neurons in the SLFN, we demonstrate that the proper number of hidden neurons can be safely chosen from a broad interval to guarantee good generalization performance. Compared to the traditional model-driven calibration, the proposed calibration method does not need a complex modeling process and is more accurate and stable. As the output of the network is the space vectors of the outgoing laser beams, it costs much less training time and can provide a uniform solution to both laser projection and 3D-reconstruction, in contrast with the existing data-driven calibration method which only works for the laser triangulation problem. Calibration experiment, projection experiment and 3D reconstruction experiment are respectively conducted to test the proposed method, and good results are obtained.

Efficient implementation of a real-time estimation system for thalamocortical hidden Parkinsonian properties

NASA Astrophysics Data System (ADS)

Yang, Shuangming; Deng, Bin; Wang, Jiang; Li, Huiyan; Liu, Chen; Fietkiewicz, Chris; Loparo, Kenneth A.

2017-01-01

Real-time estimation of dynamical characteristics of thalamocortical cells, such as dynamics of ion channels and membrane potentials, is useful and essential in the study of the thalamus in Parkinsonian state. However, measuring the dynamical properties of ion channels is extremely challenging experimentally and even impossible in clinical applications. This paper presents and evaluates a real-time estimation system for thalamocortical hidden properties. For the sake of efficiency, we use a field programmable gate array for strictly hardware-based computation and algorithm optimization. In the proposed system, the FPGA-based unscented Kalman filter is implemented into a conductance-based TC neuron model. Since the complexity of TC neuron model restrains its hardware implementation in parallel structure, a cost efficient model is proposed to reduce the resource cost while retaining the relevant ionic dynamics. Experimental results demonstrate the real-time capability to estimate thalamocortical hidden properties with high precision under both normal and Parkinsonian states. While it is applied to estimate the hidden properties of the thalamus and explore the mechanism of the Parkinsonian state, the proposed method can be useful in the dynamic clamp technique of the electrophysiological experiments, the neural control engineering and brain-machine interface studies.

Experimental Machine Learning of Quantum States

NASA Astrophysics Data System (ADS)

Gao, Jun; Qiao, Lu-Feng; Jiao, Zhi-Qiang; Ma, Yue-Chi; Hu, Cheng-Qiu; Ren, Ruo-Jing; Yang, Ai-Lin; Tang, Hao; Yung, Man-Hong; Jin, Xian-Min

2018-06-01

Quantum information technologies provide promising applications in communication and computation, while machine learning has become a powerful technique for extracting meaningful structures in "big data." A crossover between quantum information and machine learning represents a new interdisciplinary area stimulating progress in both fields. Traditionally, a quantum state is characterized by quantum-state tomography, which is a resource-consuming process when scaled up. Here we experimentally demonstrate a machine-learning approach to construct a quantum-state classifier for identifying the separability of quantum states. We show that it is possible to experimentally train an artificial neural network to efficiently learn and classify quantum states, without the need of obtaining the full information of the states. We also show how adding a hidden layer of neurons to the neural network can significantly boost the performance of the state classifier. These results shed new light on how classification of quantum states can be achieved with limited resources, and represent a step towards machine-learning-based applications in quantum information processing.

Summer Faculty Research Program (SFRP) (1992). Volume 1. Program Management Report.

DTIC Science & Technology

1992-12-01

the side of the 1.5 meter telescope. The receiver has two optical channels and the lidar can be configured either as a two- color system or as long...using a coordinate measuring machine (CMM) was employed. The part and mold thickness data were computed and plotted in the form of color contours for ease...using wavelets is developed based on the principle of scattering centers. The adopted target representation is based on the colored bright spots approach

Military Operating Room of the Future

DTIC Science & Technology

2014-12-01

aortic aneurysms, stroke and acute myocardial infarction . 0 1 2 3 4 5 6 7 8 9 Sim 1 (App) Sim 2 (No App/Fire) W81XWH-11-1-0813 Page 41 of 77...ED fire was simulated with an indoor smoke machine which was hidden from view and triggered after approximately 10 minutes. The simulation sessions

Integrating image quality in 2nu-SVM biometric match score fusion.

PubMed

Vatsa, Mayank; Singh, Richa; Noore, Afzel

2007-10-01

This paper proposes an intelligent 2nu-support vector machine based match score fusion algorithm to improve the performance of face and iris recognition by integrating the quality of images. The proposed algorithm applies redundant discrete wavelet transform to evaluate the underlying linear and non-linear features present in the image. A composite quality score is computed to determine the extent of smoothness, sharpness, noise, and other pertinent features present in each subband of the image. The match score and the corresponding quality score of an image are fused using 2nu-support vector machine to improve the verification performance. The proposed algorithm is experimentally validated using the FERET face database and the CASIA iris database. The verification performance and statistical evaluation show that the proposed algorithm outperforms existing fusion algorithms.

Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles

NASA Astrophysics Data System (ADS)

Hannel, Mark D.; Abdulali, Aidan; O'Brien, Michael; Grier, David G.

2018-06-01

Holograms of colloidal particles can be analyzed with the Lorenz-Mie theory of light scattering to measure individual particles' three-dimensional positions with nanometer precision while simultaneously estimating their sizes and refractive indexes. Extracting this wealth of information begins by detecting and localizing features of interest within individual holograms. Conventionally approached with heuristic algorithms, this image analysis problem can be solved faster and more generally with machine-learning techniques. We demonstrate that two popular machine-learning algorithms, cascade classifiers and deep convolutional neural networks (CNN), can solve the feature-localization problem orders of magnitude faster than current state-of-the-art techniques. Our CNN implementation localizes holographic features precisely enough to bootstrap more detailed analyses based on the Lorenz-Mie theory of light scattering. The wavelet-based Haar cascade proves to be less precise, but is so computationally efficient that it creates new opportunities for applications that emphasize speed and low cost. We demonstrate its use as a real-time targeting system for holographic optical trapping.

A video, text, and speech-driven realistic 3-d virtual head for human-machine interface.

PubMed

Yu, Jun; Wang, Zeng-Fu

2015-05-01

A multiple inputs-driven realistic facial animation system based on 3-D virtual head for human-machine interface is proposed. The system can be driven independently by video, text, and speech, thus can interact with humans through diverse interfaces. The combination of parameterized model and muscular model is used to obtain a tradeoff between computational efficiency and high realism of 3-D facial animation. The online appearance model is used to track 3-D facial motion from video in the framework of particle filtering, and multiple measurements, i.e., pixel color value of input image and Gabor wavelet coefficient of illumination ratio image, are infused to reduce the influence of lighting and person dependence for the construction of online appearance model. The tri-phone model is used to reduce the computational consumption of visual co-articulation in speech synchronized viseme synthesis without sacrificing any performance. The objective and subjective experiments show that the system is suitable for human-machine interaction.

A wavelet-based technique to predict treatment outcome for Major Depressive Disorder

PubMed Central

Xia, Likun; Mohd Yasin, Mohd Azhar; Azhar Ali, Syed Saad

2017-01-01

Treatment management for Major Depressive Disorder (MDD) has been challenging. However, electroencephalogram (EEG)-based predictions of antidepressant’s treatment outcome may help during antidepressant’s selection and ultimately improve the quality of life for MDD patients. In this study, a machine learning (ML) method involving pretreatment EEG data was proposed to perform such predictions for Selective Serotonin Reuptake Inhibitor (SSRIs). For this purpose, the acquisition of experimental data involved 34 MDD patients and 30 healthy controls. Consequently, a feature matrix was constructed involving time-frequency decomposition of EEG data based on wavelet transform (WT) analysis, termed as EEG data matrix. However, the resultant EEG data matrix had high dimensionality. Therefore, dimension reduction was performed based on a rank-based feature selection method according to a criterion, i.e., receiver operating characteristic (ROC). As a result, the most significant features were identified and further be utilized during the training and testing of a classification model, i.e., the logistic regression (LR) classifier. Finally, the LR model was validated with 100 iterations of 10-fold cross-validation (10-CV). The classification results were compared with short-time Fourier transform (STFT) analysis, and empirical mode decompositions (EMD). The wavelet features extracted from frontal and temporal EEG data were found statistically significant. In comparison with other time-frequency approaches such as the STFT and EMD, the WT analysis has shown highest classification accuracy, i.e., accuracy = 87.5%, sensitivity = 95%, and specificity = 80%. In conclusion, significant wavelet coefficients extracted from frontal and temporal pre-treatment EEG data involving delta and theta frequency bands may predict antidepressant’s treatment outcome for the MDD patients. PMID:28152063

Single Trial EEG Patterns for the Prediction of Individual Differences in Fluid Intelligence.

PubMed

Qazi, Emad-Ul-Haq; Hussain, Muhammad; Aboalsamh, Hatim; Malik, Aamir Saeed; Amin, Hafeez Ullah; Bamatraf, Saeed

2016-01-01

Assessing a person's intelligence level is required in many situations, such as career counseling and clinical applications. EEG evoked potentials in oddball task and fluid intelligence score are correlated because both reflect the cognitive processing and attention. A system for prediction of an individual's fluid intelligence level using single trial Electroencephalography (EEG) signals has been proposed. For this purpose, we employed 2D and 3D contents and 34 subjects each for 2D and 3D, which were divided into low-ability (LA) and high-ability (HA) groups using Raven's Advanced Progressive Matrices (RAPM) test. Using visual oddball cognitive task, neural activity of each group was measured and analyzed over three midline electrodes (Fz, Cz, and Pz). To predict whether an individual belongs to LA or HA group, features were extracted using wavelet decomposition of EEG signals recorded in visual oddball task and support vector machine (SVM) was used as a classifier. Two different types of Haar wavelet transform based features have been extracted from the band (0.3 to 30 Hz) of EEG signals. Statistical wavelet features and wavelet coefficient features from the frequency bands 0.0-1.875 Hz (delta low) and 1.875-3.75 Hz (delta high), resulted in the 100 and 98% prediction accuracies, respectively, both for 2D and 3D contents. The analysis of these frequency bands showed clear difference between LA and HA groups. Further, discriminative values of the features have been validated using statistical significance tests and inter-class and intra-class variation analysis. Also, statistical test showed that there was no effect of 2D and 3D content on the assessment of fluid intelligence level. Comparisons with state-of-the-art techniques showed the superiority of the proposed system.

Nonlinear Analysis of Auscultation Signals in TCM Using the Combination of Wavelet Packet Transform and Sample Entropy.

PubMed

Yan, Jian-Jun; Wang, Yi-Qin; Guo, Rui; Zhou, Jin-Zhuan; Yan, Hai-Xia; Xia, Chun-Ming; Shen, Yong

2012-01-01

Auscultation signals are nonstationary in nature. Wavelet packet transform (WPT) has currently become a very useful tool in analyzing nonstationary signals. Sample entropy (SampEn) has recently been proposed to act as a measurement for quantifying regularity and complexity of time series data. WPT and SampEn were combined in this paper to analyze auscultation signals in traditional Chinese medicine (TCM). SampEns for WPT coefficients were computed to quantify the signals from qi- and yin-deficient, as well as healthy, subjects. The complexity of the signal can be evaluated with this scheme in different time-frequency resolutions. First, the voice signals were decomposed into approximated and detailed WPT coefficients. Then, SampEn values for approximated and detailed coefficients were calculated. Finally, SampEn values with significant differences in the three kinds of samples were chosen as the feature parameters for the support vector machine to identify the three types of auscultation signals. The recognition accuracy rates were higher than 90%.

Automatic classification of sleep stages based on the time-frequency image of EEG signals.

PubMed

Bajaj, Varun; Pachori, Ram Bilas

2013-12-01

In this paper, a new method for automatic sleep stage classification based on time-frequency image (TFI) of electroencephalogram (EEG) signals is proposed. Automatic classification of sleep stages is an important part for diagnosis and treatment of sleep disorders. The smoothed pseudo Wigner-Ville distribution (SPWVD) based time-frequency representation (TFR) of EEG signal has been used to obtain the time-frequency image (TFI). The segmentation of TFI has been performed based on the frequency-bands of the rhythms of EEG signals. The features derived from the histogram of segmented TFI have been used as an input feature set to multiclass least squares support vector machines (MC-LS-SVM) together with the radial basis function (RBF), Mexican hat wavelet, and Morlet wavelet kernel functions for automatic classification of sleep stages from EEG signals. The experimental results are presented to show the effectiveness of the proposed method for classification of sleep stages from EEG signals. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Nonlinear Analysis of Auscultation Signals in TCM Using the Combination of Wavelet Packet Transform and Sample Entropy

PubMed Central

Yan, Jian-Jun; Wang, Yi-Qin; Guo, Rui; Zhou, Jin-Zhuan; Yan, Hai-Xia; Xia, Chun-Ming; Shen, Yong

2012-01-01

Auscultation signals are nonstationary in nature. Wavelet packet transform (WPT) has currently become a very useful tool in analyzing nonstationary signals. Sample entropy (SampEn) has recently been proposed to act as a measurement for quantifying regularity and complexity of time series data. WPT and SampEn were combined in this paper to analyze auscultation signals in traditional Chinese medicine (TCM). SampEns for WPT coefficients were computed to quantify the signals from qi- and yin-deficient, as well as healthy, subjects. The complexity of the signal can be evaluated with this scheme in different time-frequency resolutions. First, the voice signals were decomposed into approximated and detailed WPT coefficients. Then, SampEn values for approximated and detailed coefficients were calculated. Finally, SampEn values with significant differences in the three kinds of samples were chosen as the feature parameters for the support vector machine to identify the three types of auscultation signals. The recognition accuracy rates were higher than 90%. PMID:22690242

Study of wavelet packet energy entropy for emotion classification in speech and glottal signals

NASA Astrophysics Data System (ADS)

He, Ling; Lech, Margaret; Zhang, Jing; Ren, Xiaomei; Deng, Lihua

2013-07-01

The automatic speech emotion recognition has important applications in human-machine communication. Majority of current research in this area is focused on finding optimal feature parameters. In recent studies, several glottal features were examined as potential cues for emotion differentiation. In this study, a new type of feature parameter is proposed, which calculates energy entropy on values within selected Wavelet Packet frequency bands. The modeling and classification tasks are conducted using the classical GMM algorithm. The experiments use two data sets: the Speech Under Simulated Emotion (SUSE) data set annotated with three different emotions (angry, neutral and soft) and Berlin Emotional Speech (BES) database annotated with seven different emotions (angry, bored, disgust, fear, happy, sad and neutral). The average classification accuracy achieved for the SUSE data (74%-76%) is significantly higher than the accuracy achieved for the BES data (51%-54%). In both cases, the accuracy was significantly higher than the respective random guessing levels (33% for SUSE and 14.3% for BES).

Pathological brain detection based on wavelet entropy and Hu moment invariants.

PubMed

Zhang, Yudong; Wang, Shuihua; Sun, Ping; Phillips, Preetha

2015-01-01

With the aim of developing an accurate pathological brain detection system, we proposed a novel automatic computer-aided diagnosis (CAD) to detect pathological brains from normal brains obtained by magnetic resonance imaging (MRI) scanning. The problem still remained a challenge for technicians and clinicians, since MR imaging generated an exceptionally large information dataset. A new two-step approach was proposed in this study. We used wavelet entropy (WE) and Hu moment invariants (HMI) for feature extraction, and the generalized eigenvalue proximal support vector machine (GEPSVM) for classification. To further enhance classification accuracy, the popular radial basis function (RBF) kernel was employed. The 10 runs of k-fold stratified cross validation result showed that the proposed "WE + HMI + GEPSVM + RBF" method was superior to existing methods w.r.t. classification accuracy. It obtained the average classification accuracies of 100%, 100%, and 99.45% over Dataset-66, Dataset-160, and Dataset-255, respectively. The proposed method is effective and can be applied to realistic use.

Machine learning for neuroimaging with scikit-learn.

PubMed

Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

2014-01-01

Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain.

Machine learning for neuroimaging with scikit-learn

PubMed Central

Abraham, Alexandre; Pedregosa, Fabian; Eickenberg, Michael; Gervais, Philippe; Mueller, Andreas; Kossaifi, Jean; Gramfort, Alexandre; Thirion, Bertrand; Varoquaux, Gaël

2014-01-01

Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g., multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g., resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain. PMID:24600388

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach.

PubMed

Albadr, Musatafa Abbas Abbood; Tiun, Sabrina; Al-Dhief, Fahad Taha; Sammour, Mahmoud A M

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%.

Spoken language identification based on the enhanced self-adjusting extreme learning machine approach

PubMed Central

Tiun, Sabrina; AL-Dhief, Fahad Taha; Sammour, Mahmoud A. M.

2018-01-01

Spoken Language Identification (LID) is the process of determining and classifying natural language from a given content and dataset. Typically, data must be processed to extract useful features to perform LID. The extracting features for LID, based on literature, is a mature process where the standard features for LID have already been developed using Mel-Frequency Cepstral Coefficients (MFCC), Shifted Delta Cepstral (SDC), the Gaussian Mixture Model (GMM) and ending with the i-vector based framework. However, the process of learning based on extract features remains to be improved (i.e. optimised) to capture all embedded knowledge on the extracted features. The Extreme Learning Machine (ELM) is an effective learning model used to perform classification and regression analysis and is extremely useful to train a single hidden layer neural network. Nevertheless, the learning process of this model is not entirely effective (i.e. optimised) due to the random selection of weights within the input hidden layer. In this study, the ELM is selected as a learning model for LID based on standard feature extraction. One of the optimisation approaches of ELM, the Self-Adjusting Extreme Learning Machine (SA-ELM) is selected as the benchmark and improved by altering the selection phase of the optimisation process. The selection process is performed incorporating both the Split-Ratio and K-Tournament methods, the improved SA-ELM is named Enhanced Self-Adjusting Extreme Learning Machine (ESA-ELM). The results are generated based on LID with the datasets created from eight different languages. The results of the study showed excellent superiority relating to the performance of the Enhanced Self-Adjusting Extreme Learning Machine LID (ESA-ELM LID) compared with the SA-ELM LID, with ESA-ELM LID achieving an accuracy of 96.25%, as compared to the accuracy of SA-ELM LID of only 95.00%. PMID:29672546

Rolling element bearing defect diagnosis under variable speed operation through angle synchronous averaging of wavelet de-noised estimate

NASA Astrophysics Data System (ADS)

Mishra, C.; Samantaray, A. K.; Chakraborty, G.

2016-05-01

Rolling element bearings are widely used in rotating machines and their faults can lead to excessive vibration levels and/or complete seizure of the machine. Under special operating conditions such as non-uniform or low speed shaft rotation, the available fault diagnosis methods cannot be applied for bearing fault diagnosis with full confidence. Fault symptoms in such operating conditions cannot be easily extracted through usual measurement and signal processing techniques. A typical example is a bearing in heavy rolling mill with variable load and disturbance from other sources. In extremely slow speed operation, variation in speed due to speed controller transients or external disturbances (e.g., varying load) can be relatively high. To account for speed variation, instantaneous angular position instead of time is used as the base variable of signals for signal processing purposes. Even with time synchronous averaging (TSA) and well-established methods like envelope order analysis, rolling element faults in rolling element bearings cannot be easily identified during such operating conditions. In this article we propose to use order tracking on the envelope of the wavelet de-noised estimate of the short-duration angle synchronous averaged signal to diagnose faults in rolling element bearing operating under the stated special conditions. The proposed four-stage sequential signal processing method eliminates uncorrelated content, avoids signal smearing and exposes only the fault frequencies and its harmonics in the spectrum. We use experimental data1

The role of the continuous wavelet transform in mineral identification using hyperspectral imaging in the long-wave infrared by using SVM classifier

NASA Astrophysics Data System (ADS)

Sojasi, Saeed; Yousefi, Bardia; Liaigre, Kévin; Ibarra-Castanedo, Clemente; Beaudoin, Georges; Maldague, Xavier P. V.; Huot, François; Chamberland, Martin

2017-05-01

Hyperspectral imaging (HSI) in the long-wave infrared spectrum (LWIR) provides spectral and spatial information concerning the emissivity of the surface of materials, which can be used for mineral identification. For this, an endmember, which is the purest form of a mineral, is used as reference. All pure minerals have specific spectral profiles in the electromagnetic wavelength, which can be thought of as the mineral's fingerprint. The main goal of this paper is the identification of minerals by LWIR hyperspectral imaging using a machine learning scheme. The information of hyperspectral imaging has been recorded from the energy emitted from the mineral's surface. Solar energy is the source of energy in remote sensing, while a heating element is the energy source employed in laboratory experiments. Our work contains three main steps where the first step involves obtaining the spectral signatures of pure (single) minerals with a hyperspectral camera, in the long-wave infrared (7.7 to 11.8 μm), which measures the emitted radiance from the minerals' surface. The second step concerns feature extraction by applying the continuous wavelet transform (CWT) and finally we use support vector machine classifier with radial basis functions (SVM-RBF) for classification/identification of minerals. The overall accuracy of classification in our work is 90.23+/- 2.66%. In conclusion, based on CWT's ability to capture the information of signals can be used as a good marker for classification and identification the minerals substance.

Coarse-to-fine wavelet-based airport detection

NASA Astrophysics Data System (ADS)

Li, Cheng; Wang, Shuigen; Pang, Zhaofeng; Zhao, Baojun

2015-10-01

Airport detection on optical remote sensing images has attracted great interest in the applications of military optics scout and traffic control. However, most of the popular techniques for airport detection from optical remote sensing images have three weaknesses: 1) Due to the characteristics of optical images, the detection results are often affected by imaging conditions, like weather situation and imaging distortion; and 2) optical images contain comprehensive information of targets, so that it is difficult for extracting robust features (e.g., intensity and textural information) to represent airport area; 3) the high resolution results in large data volume, which makes real-time processing limited. Most of the previous works mainly focus on solving one of those problems, and thus, the previous methods cannot achieve the balance of performance and complexity. In this paper, we propose a novel coarse-to-fine airport detection framework to solve aforementioned three issues using wavelet coefficients. The framework includes two stages: 1) an efficient wavelet-based feature extraction is adopted for multi-scale textural feature representation, and support vector machine(SVM) is exploited for classifying and coarsely deciding airport candidate region; and then 2) refined line segment detection is used to obtain runway and landing field of airport. Finally, airport recognition is achieved by applying the fine runway positioning to the candidate regions. Experimental results show that the proposed approach outperforms the existing algorithms in terms of detection accuracy and processing efficiency.

Performance of wavelet analysis and neural networks for pathological voices identification

NASA Astrophysics Data System (ADS)

Salhi, Lotfi; Talbi, Mourad; Abid, Sabeur; Cherif, Adnane

2011-09-01

Within the medical environment, diverse techniques exist to assess the state of the voice of the patient. The inspection technique is inconvenient for a number of reasons, such as its high cost, the duration of the inspection, and above all, the fact that it is an invasive technique. This study focuses on a robust, rapid and accurate system for automatic identification of pathological voices. This system employs non-invasive, non-expensive and fully automated method based on hybrid approach: wavelet transform analysis and neural network classifier. First, we present the results obtained in our previous study while using classic feature parameters. These results allow visual identification of pathological voices. Second, quantified parameters drifting from the wavelet analysis are proposed to characterise the speech sample. On the other hand, a system of multilayer neural networks (MNNs) has been developed which carries out the automatic detection of pathological voices. The developed method was evaluated using voice database composed of recorded voice samples (continuous speech) from normophonic or dysphonic speakers. The dysphonic speakers were patients of a National Hospital 'RABTA' of Tunis Tunisia and a University Hospital in Brussels, Belgium. Experimental results indicate a success rate ranging between 75% and 98.61% for discrimination of normal and pathological voices using the proposed parameters and neural network classifier. We also compared the average classification rate based on the MNN, Gaussian mixture model and support vector machines.

Concrete Condition Assessment Using Impact-Echo Method and Extreme Learning Machines

PubMed Central

Zhang, Jing-Kui; Yan, Weizhong; Cui, De-Mi

2016-01-01

The impact-echo (IE) method is a popular non-destructive testing (NDT) technique widely used for measuring the thickness of plate-like structures and for detecting certain defects inside concrete elements or structures. However, the IE method is not effective for full condition assessment (i.e., defect detection, defect diagnosis, defect sizing and location), because the simple frequency spectrum analysis involved in the existing IE method is not sufficient to capture the IE signal patterns associated with different conditions. In this paper, we attempt to enhance the IE technique and enable it for full condition assessment of concrete elements by introducing advanced machine learning techniques for performing comprehensive analysis and pattern recognition of IE signals. Specifically, we use wavelet decomposition for extracting signatures or features out of the raw IE signals and apply extreme learning machine, one of the recently developed machine learning techniques, as classification models for full condition assessment. To validate the capabilities of the proposed method, we build a number of specimens with various types, sizes, and locations of defects and perform IE testing on these specimens in a lab environment. Based on analysis of the collected IE signals using the proposed machine learning based IE method, we demonstrate that the proposed method is effective in performing full condition assessment of concrete elements or structures. PMID:27023563

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.

Tissue multifractality and hidden Markov model based integrated framework for optimum precancer detection

NASA Astrophysics Data System (ADS)

Mukhopadhyay, Sabyasachi; Das, Nandan K.; Kurmi, Indrajit; Pradhan, Asima; Ghosh, Nirmalya; Panigrahi, Prasanta K.

2017-10-01

We report the application of a hidden Markov model (HMM) on multifractal tissue optical properties derived via the Born approximation-based inverse light scattering method for effective discrimination of precancerous human cervical tissue sites from the normal ones. Two global fractal parameters, generalized Hurst exponent and the corresponding singularity spectrum width, computed by multifractal detrended fluctuation analysis (MFDFA), are used here as potential biomarkers. We develop a methodology that makes use of these multifractal parameters by integrating with different statistical classifiers like the HMM and support vector machine (SVM). It is shown that the MFDFA-HMM integrated model achieves significantly better discrimination between normal and different grades of cancer as compared to the MFDFA-SVM integrated model.

Measures and Metrics of Information Processing in Complex Systems: A Rope of Sand

ERIC Educational Resources Information Center

James, Ryan Gregory

2013-01-01

How much information do natural systems store and process? In this work we attempt to answer this question in multiple ways. We first establish a mathematical framework where natural systems are represented by a canonical form of edge-labeled hidden fc models called e-machines. Then, utilizing this framework, a variety of measures are defined and…

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

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

Structural classification of proteins using texture descriptors extracted from the cellular automata image.

PubMed

Kavianpour, Hamidreza; Vasighi, Mahdi

2017-02-01

Nowadays, having knowledge about cellular attributes of proteins has an important role in pharmacy, medical science and molecular biology. These attributes are closely correlated with the function and three-dimensional structure of proteins. Knowledge of protein structural class is used by various methods for better understanding the protein functionality and folding patterns. Computational methods and intelligence systems can have an important role in performing structural classification of proteins. Most of protein sequences are saved in databanks as characters and strings and a numerical representation is essential for applying machine learning methods. In this work, a binary representation of protein sequences is introduced based on reduced amino acids alphabets according to surrounding hydrophobicity index. Many important features which are hidden in these long binary sequences can be clearly displayed through their cellular automata images. The extracted features from these images are used to build a classification model by support vector machine. Comparing to previous studies on the several benchmark datasets, the promising classification rates obtained by tenfold cross-validation imply that the current approach can help in revealing some inherent features deeply hidden in protein sequences and improve the quality of predicting protein structural class.

Detection and diagnosis of bearing and cutting tool faults using hidden Markov models

NASA Astrophysics Data System (ADS)

Boutros, Tony; Liang, Ming

2011-08-01

Over the last few decades, the research for new fault detection and diagnosis techniques in machining processes and rotating machinery has attracted increasing interest worldwide. This development was mainly stimulated by the rapid advance in industrial technologies and the increase in complexity of machining and machinery systems. In this study, the discrete hidden Markov model (HMM) is applied to detect and diagnose mechanical faults. The technique is tested and validated successfully using two scenarios: tool wear/fracture and bearing faults. In the first case the model correctly detected the state of the tool (i.e., sharp, worn, or broken) whereas in the second application, the model classified the severity of the fault seeded in two different engine bearings. The success rate obtained in our tests for fault severity classification was above 95%. In addition to the fault severity, a location index was developed to determine the fault location. This index has been applied to determine the location (inner race, ball, or outer race) of a bearing fault with an average success rate of 96%. The training time required to develop the HMMs was less than 5 s in both the monitoring cases.

Discrimination between landmine and mine-like targets using wavelets and spectral analysis

NASA Astrophysics Data System (ADS)

Mohana, Mahmoud A.; Abbas, Abbas M.; Gomaa, Mohamed L.; Ebrahim, Shereen M.

2013-06-01

Landmine is an explosive apparatus hidden in or on the ground, which blows up when a person or vehicle passes over it. Egypt is one of the countries suffering due to the unexploded ordnance (UXO). Around 2 million UXO are present in the Egyptian soil especially at Al-Alameen province, north of the western desert. Detection of buried landmines is a problem of military and humanitarian importance. Ground penetrating radar (GPR) is a powerful and non-destructive geophysical approach with a wide range of advantages in the field of landmine inspection. In the present paper, we apply different simulation models with Vivaldi antenna and mine-like targets by using the CST Microwave studio program. The field work is carried out by using a GPR device of model SIR 2000 from GSSI (Geophysical Survey Systems Incorporation) connected to 900 MHz antenna where the targets were buried in sand soil. Depending on the fact that the receiving powers (reflected, refracted and scattered) from the different materials are different, we study the spectral power densities for the received power from the different targets. The techniques used in this study are: direct fast Fourier transform, short time Fourier transform (spectrogram), wavelets transform and denoising techniques. Our results ought to be considered as finger prints for different scanned targets during this work. So we can discriminate between landmines and mine-like targets.

[Application of wavelet transform-radial basis function neural network in NIRS for determination of rifampicin and isoniazide tablets].

PubMed

Lu, Jia-hui; Zhang, Yi-bo; Zhang, Zhuo-yong; Meng, Qing-fan; Guo, Wei-liang; Teng, Li-rong

2008-06-01

A calibration model (WT-RBFNN) combination of wavelet transform (WT) and radial basis function neural network (RBFNN) was proposed for synchronous and rapid determination of rifampicin and isoniazide in Rifampicin and Isoniazide tablets by near infrared reflectance spectroscopy (NIRS). The approximation coefficients were used for input data in RBFNN. The network parameters including the number of hidden layer neurons and spread constant (SC) were investigated. WT-RBFNN model which compressed the original spectra data, removed the noise and the interference of background, and reduced the randomness, the capabilities of prediction were well optimized. The root mean square errors of prediction (RMSEP) for the determination of rifampicin and isoniazide obtained from the optimum WT-RBFNN model are 0.00639 and 0.00587, and the root mean square errors of cross-calibration (RMSECV) for them are 0.00604 and 0.00457, respectively which are superior to those obtained by the optimum RBFNN and PLS models. Regression coefficient (R) between NIRS predicted values and RP-HPLC values for rifampicin and isoniazide are 0.99522 and 0.99392, respectively and the relative error is lower than 2.300%. It was verified that WT-RBFNN model is a suitable approach to dealing with NIRS. The proposed WT-RBFNN model is convenient, and rapid and with no pollution for the determination of rifampicin and isoniazide tablets.

Reliability Centred Maintenance (RCM) Analysis of Laser Machine in Filling Lithos at PT X

NASA Astrophysics Data System (ADS)

Suryono, M. A. E.; Rosyidi, C. N.

2018-03-01

PT. X used automated machines which work for sixteen hours per day. Therefore, the machines should be maintained to keep the availability of the machines. The aim of this research is to determine maintenance tasks according to the cause of component’s failure using Reliability Centred Maintenance (RCM) and determine the amount of optimal inspection frequency which must be performed to the machine at filling lithos process. In this research, RCM is used as an analysis tool to determine the critical component and find optimal inspection frequencies to maximize machine’s reliability. From the analysis, we found that the critical machine in filling lithos process is laser machine in Line 2. Then we proceed to determine the cause of machine’s failure. Lastube component has the highest Risk Priority Number (RPN) among other components such as power supply, lens, chiller, laser siren, encoder, conveyor, and mirror galvo. Most of the components have operational consequences and the others have hidden failure consequences and safety consequences. Time-directed life-renewal task, failure finding task, and servicing task can be used to overcome these consequences. The results of data analysis show that the inspection must be performed once a month for laser machine in the form of preventive maintenance to lowering the downtime.

Hidden imperfect synchronization of wall turbulence.

PubMed

Tardu, Sedat F

2010-03-01

Instantaneous amplitude and phase concept emerging from analytical signal formulation is applied to the wavelet coefficients of streamwise velocity fluctuations in the buffer layer of a near wall turbulent flow. Experiments and direct numerical simulations show both the existence of long periods of inert zones wherein the local phase is constant. These regions are separated by random phase jumps. The local amplitude is globally highly intermittent, but not in the phase locked regions wherein it varies smoothly. These behaviors are reminiscent of phase synchronization phenomena observed in stochastic chaotic systems. The lengths of the constant phase inert (laminar) zones reveal a type I intermittency behavior, in concordance with saddle-node bifurcation, and the periodic orbits of saddle nature recently identified in Couette turbulence. The imperfect synchronization is related to the footprint of coherent Reynolds shear stress producing eddies convecting in the low buffer.

Ischemia episode detection in ECG using kernel density estimation, support vector machine and feature selection

PubMed Central

2012-01-01

Background Myocardial ischemia can be developed into more serious diseases. Early Detection of the ischemic syndrome in electrocardiogram (ECG) more accurately and automatically can prevent it from developing into a catastrophic disease. To this end, we propose a new method, which employs wavelets and simple feature selection. Methods For training and testing, the European ST-T database is used, which is comprised of 367 ischemic ST episodes in 90 records. We first remove baseline wandering, and detect time positions of QRS complexes by a method based on the discrete wavelet transform. Next, for each heart beat, we extract three features which can be used for differentiating ST episodes from normal: 1) the area between QRS offset and T-peak points, 2) the normalized and signed sum from QRS offset to effective zero voltage point, and 3) the slope from QRS onset to offset point. We average the feature values for successive five beats to reduce effects of outliers. Finally we apply classifiers to those features. Results We evaluated the algorithm by kernel density estimation (KDE) and support vector machine (SVM) methods. Sensitivity and specificity for KDE were 0.939 and 0.912, respectively. The KDE classifier detects 349 ischemic ST episodes out of total 367 ST episodes. Sensitivity and specificity of SVM were 0.941 and 0.923, respectively. The SVM classifier detects 355 ischemic ST episodes. Conclusions We proposed a new method for detecting ischemia in ECG. It contains signal processing techniques of removing baseline wandering and detecting time positions of QRS complexes by discrete wavelet transform, and feature extraction from morphology of ECG waveforms explicitly. It was shown that the number of selected features were sufficient to discriminate ischemic ST episodes from the normal ones. We also showed how the proposed KDE classifier can automatically select kernel bandwidths, meaning that the algorithm does not require any numerical values of the parameters to be supplied in advance. In the case of the SVM classifier, one has to select a single parameter. PMID:22703641

Space coding for sensorimotor transformations can emerge through unsupervised learning.

PubMed

De Filippo De Grazia, Michele; Cutini, Simone; Lisi, Matteo; Zorzi, Marco

2012-08-01

The posterior parietal cortex (PPC) is fundamental for sensorimotor transformations because it combines multiple sensory inputs and posture signals into different spatial reference frames that drive motor programming. Here, we present a computational model mimicking the sensorimotor transformations occurring in the PPC. A recurrent neural network with one layer of hidden neurons (restricted Boltzmann machine) learned a stochastic generative model of the sensory data without supervision. After the unsupervised learning phase, the activity of the hidden neurons was used to compute a motor program (a population code on a bidimensional map) through a simple linear projection and delta rule learning. The average motor error, calculated as the difference between the expected and the computed output, was less than 3°. Importantly, analyses of the hidden neurons revealed gain-modulated visual receptive fields, thereby showing that space coding for sensorimotor transformations similar to that observed in the PPC can emerge through unsupervised learning. These results suggest that gain modulation is an efficient coding strategy to integrate visual and postural information toward the generation of motor commands.

Learning to classify in large committee machines

NASA Astrophysics Data System (ADS)

O'kane, Dominic; Winther, Ole

1994-10-01

The ability of a two-layer neural network to learn a specific non-linearly-separable classification task, the proximity problem, is investigated using a statistical mechanics approach. Both the tree and fully connected architectures are investigated in the limit where the number K of hidden units is large, but still much smaller than the number N of inputs. Both have continuous weights. Within the replica symmetric ansatz, we find that for zero temperature training, the tree architecture exhibits a strong overtraining effect. For nonzero temperature the asymptotic error is lowered, but it is still higher than the corresponding value for the simple perceptron. The fully connected architecture is considered for two regimes. First, for a finite number of examples we find a symmetry among the hidden units as each performs equally well. The asymptotic generalization error is finite, and minimal for T-->∞ where it goes to the same value as for the simple perceptron. For a large number of examples we find a continuous transition to a phase with broken hidden-unit symmetry, which has an asymptotic generalization error equal to zero.

Quantitative thickness prediction of tectonically deformed coal using Extreme Learning Machine and Principal Component Analysis: a case study

NASA Astrophysics Data System (ADS)

Wang, Xin; Li, Yan; Chen, Tongjun; Yan, Qiuyan; Ma, Li

2017-04-01

The thickness of tectonically deformed coal (TDC) has positive correlation associations with gas outbursts. In order to predict the TDC thickness of coal beds, we propose a new quantitative predicting method using an extreme learning machine (ELM) algorithm, a principal component analysis (PCA) algorithm, and seismic attributes. At first, we build an ELM prediction model using the PCA attributes of a synthetic seismic section. The results suggest that the ELM model can produce a reliable and accurate prediction of the TDC thickness for synthetic data, preferring Sigmoid activation function and 20 hidden nodes. Then, we analyze the applicability of the ELM model on the thickness prediction of the TDC with real application data. Through the cross validation of near-well traces, the results suggest that the ELM model can produce a reliable and accurate prediction of the TDC. After that, we use 250 near-well traces from 10 wells to build an ELM predicting model and use the model to forecast the TDC thickness of the No. 15 coal in the study area using the PCA attributes as the inputs. Comparing the predicted results, it is noted that the trained ELM model with two selected PCA attributes yields better predication results than those from the other combinations of the attributes. Finally, the trained ELM model with real seismic data have a different number of hidden nodes (10) than the trained ELM model with synthetic seismic data. In summary, it is feasible to use an ELM model to predict the TDC thickness using the calculated PCA attributes as the inputs. However, the input attributes, the activation function and the number of hidden nodes in the ELM model should be selected and tested carefully based on individual application.

New machine-learning algorithms for prediction of Parkinson's disease

NASA Astrophysics Data System (ADS)

Mandal, Indrajit; Sairam, N.

2014-03-01

This article presents an enhanced prediction accuracy of diagnosis of Parkinson's disease (PD) to prevent the delay and misdiagnosis of patients using the proposed robust inference system. New machine-learning methods are proposed and performance comparisons are based on specificity, sensitivity, accuracy and other measurable parameters. The robust methods of treating Parkinson's disease (PD) includes sparse multinomial logistic regression, rotation forest ensemble with support vector machines and principal components analysis, artificial neural networks, boosting methods. A new ensemble method comprising of the Bayesian network optimised by Tabu search algorithm as classifier and Haar wavelets as projection filter is used for relevant feature selection and ranking. The highest accuracy obtained by linear logistic regression and sparse multinomial logistic regression is 100% and sensitivity, specificity of 0.983 and 0.996, respectively. All the experiments are conducted over 95% and 99% confidence levels and establish the results with corrected t-tests. This work shows a high degree of advancement in software reliability and quality of the computer-aided diagnosis system and experimentally shows best results with supportive statistical inference.

A Framework for Final Drive Simultaneous Failure Diagnosis Based on Fuzzy Entropy and Sparse Bayesian Extreme Learning Machine

PubMed Central

Ye, Qing; Pan, Hao; Liu, Changhua

2015-01-01

This research proposes a novel framework of final drive simultaneous failure diagnosis containing feature extraction, training paired diagnostic models, generating decision threshold, and recognizing simultaneous failure modes. In feature extraction module, adopt wavelet package transform and fuzzy entropy to reduce noise interference and extract representative features of failure mode. Use single failure sample to construct probability classifiers based on paired sparse Bayesian extreme learning machine which is trained only by single failure modes and have high generalization and sparsity of sparse Bayesian learning approach. To generate optimal decision threshold which can convert probability output obtained from classifiers into final simultaneous failure modes, this research proposes using samples containing both single and simultaneous failure modes and Grid search method which is superior to traditional techniques in global optimization. Compared with other frequently used diagnostic approaches based on support vector machine and probability neural networks, experiment results based on F 1-measure value verify that the diagnostic accuracy and efficiency of the proposed framework which are crucial for simultaneous failure diagnosis are superior to the existing approach. PMID:25722717

Unsupervised deep learning reveals prognostically relevant subtypes of glioblastoma.

PubMed

Young, Jonathan D; Cai, Chunhui; Lu, Xinghua

2017-10-03

One approach to improving the personalized treatment of cancer is to understand the cellular signaling transduction pathways that cause cancer at the level of the individual patient. In this study, we used unsupervised deep learning to learn the hierarchical structure within cancer gene expression data. Deep learning is a group of machine learning algorithms that use multiple layers of hidden units to capture hierarchically related, alternative representations of the input data. We hypothesize that this hierarchical structure learned by deep learning will be related to the cellular signaling system. Robust deep learning model selection identified a network architecture that is biologically plausible. Our model selection results indicated that the 1st hidden layer of our deep learning model should contain about 1300 hidden units to most effectively capture the covariance structure of the input data. This agrees with the estimated number of human transcription factors, which is approximately 1400. This result lends support to our hypothesis that the 1st hidden layer of a deep learning model trained on gene expression data may represent signals related to transcription factor activation. Using the 3rd hidden layer representation of each tumor as learned by our unsupervised deep learning model, we performed consensus clustering on all tumor samples-leading to the discovery of clusters of glioblastoma multiforme with differential survival. One of these clusters contained all of the glioblastoma samples with G-CIMP, a known methylation phenotype driven by the IDH1 mutation and associated with favorable prognosis, suggesting that the hidden units in the 3rd hidden layer representations captured a methylation signal without explicitly using methylation data as input. We also found differentially expressed genes and well-known mutations (NF1, IDH1, EGFR) that were uniquely correlated with each of these clusters. Exploring these unique genes and mutations will allow us to further investigate the disease mechanisms underlying each of these clusters. In summary, we show that a deep learning model can be trained to represent biologically and clinically meaningful abstractions of cancer gene expression data. Understanding what additional relationships these hidden layer abstractions have with the cancer cellular signaling system could have a significant impact on the understanding and treatment of cancer.

Identification of breathing cracks in a beam structure with entropy

NASA Astrophysics Data System (ADS)

Wimarshana, Buddhi; Wu, Nan; Wu, Christine

2016-04-01

A cantilever beam with a breathing crack is studied to detect and evaluate the crack using entropy measures. Closed cracks in engineering structures lead to proportional complexities to their vibration responses due to weak bi-linearity imposed by the crack breathing phenomenon. Entropy is a measure of system complexity and has the potential in quantifying the complexity. The weak bi-linearity in vibration signals can be amplified using wavelet transformation to increase the sensitivity of the measurements. A mathematical model of harmonically excited unit length steel cantilever beam with a breathing crack located near the fixed end is established, and an iterative numerical method is applied to generate accurate time domain dynamic responses. The bi-linearity in time domain signals due to the crack breathing are amplified by wavelet transformation first, and then the complexities due to bi-linearity is quantified using sample entropy to detect the possible crack and estimate the crack depth. It is observed that the method is capable of identifying crack depths even at very early stages of 3% with the increase in the entropy values more than 10% compared with the healthy beam. The current study extends the entropy based damage detection of rotary machines to structural analysis and takes a step further in high-sensitivity structural health monitoring by combining wavelet transformation with entropy calculations. The proposed technique can also be applied to other types of structures, such as plates and shells.

Analysis of dual tree M-band wavelet transform based features for brain image classification.

PubMed

Ayalapogu, Ratna Raju; Pabboju, Suresh; Ramisetty, Rajeswara Rao

2018-04-29

The most complex organ in the human body is the brain. The unrestrained growth of cells in the brain is called a brain tumor. The cause of a brain tumor is still unknown and the survival rate is lower than other types of cancers. Hence, early detection is very important for proper treatment. In this study, an efficient computer-aided diagnosis (CAD) system is presented for brain image classification by analyzing MRI of the brain. At first, the MRI brain images of normal and abnormal categories are modeled by using the statistical features of dual tree m-band wavelet transform (DTMBWT). A maximum margin classifier, support vector machine (SVM) is then used for the classification and validated with k-fold approach. Results show that the system provides promising results on a repository of molecular brain neoplasia data (REMBRANDT) with 97.5% accuracy using 4 th level statistical features of DTMBWT. Viewing the experimental results, we conclude that the system gives a satisfactory performance for the brain image classification. © 2018 International Society for Magnetic Resonance in Medicine.

Implementation and performance evaluation of acoustic denoising algorithms for UAV

NASA Astrophysics Data System (ADS)

Chowdhury, Ahmed Sony Kamal

Unmanned Aerial Vehicles (UAVs) have become popular alternative for wildlife monitoring and border surveillance applications. Elimination of the UAV's background noise and classifying the target audio signal effectively are still a major challenge. The main goal of this thesis is to remove UAV's background noise by means of acoustic denoising techniques. Existing denoising algorithms, such as Adaptive Least Mean Square (LMS), Wavelet Denoising, Time-Frequency Block Thresholding, and Wiener Filter, were implemented and their performance evaluated. The denoising algorithms were evaluated for average Signal to Noise Ratio (SNR), Segmental SNR (SSNR), Log Likelihood Ratio (LLR), and Log Spectral Distance (LSD) metrics. To evaluate the effectiveness of the denoising algorithms on classification of target audio, we implemented Support Vector Machine (SVM) and Naive Bayes classification algorithms. Simulation results demonstrate that LMS and Discrete Wavelet Transform (DWT) denoising algorithm offered superior performance than other algorithms. Finally, we implemented the LMS and DWT algorithms on a DSP board for hardware evaluation. Experimental results showed that LMS algorithm's performance is robust compared to DWT for various noise types to classify target audio signals.

Continuous EEG signal analysis for asynchronous BCI application.

PubMed

Hsu, Wei-Yen

2011-08-01

In this study, we propose a two-stage recognition system for continuous analysis of electroencephalogram (EEG) signals. An independent component analysis (ICA) and correlation coefficient are used to automatically eliminate the electrooculography (EOG) artifacts. Based on the continuous wavelet transform (CWT) and Student's two-sample t-statistics, active segment selection then detects the location of active segment in the time-frequency domain. Next, multiresolution fractal feature vectors (MFFVs) are extracted with the proposed modified fractal dimension from wavelet data. Finally, the support vector machine (SVM) is adopted for the robust classification of MFFVs. The EEG signals are continuously analyzed in 1-s segments, and every 0.5 second moves forward to simulate asynchronous BCI works in the two-stage recognition architecture. The segment is first recognized as lifted or not in the first stage, and then is classified as left or right finger lifting at stage two if the segment is recognized as lifting in the first stage. Several statistical analyses are used to evaluate the performance of the proposed system. The results indicate that it is a promising system in the applications of asynchronous BCI work.

High-accuracy peak picking of proteomics data using wavelet techniques.

PubMed

Lange, Eva; Gröpl, Clemens; Reinert, Knut; Kohlbacher, Oliver; Hildebrandt, Andreas

2006-01-01

A new peak picking algorithm for the analysis of mass spectrometric (MS) data is presented. It is independent of the underlying machine or ionization method, and is able to resolve highly convoluted and asymmetric signals. The method uses the multiscale nature of spectrometric data by first detecting the mass peaks in the wavelet-transformed signal before a given asymmetric peak function is fitted to the raw data. In an optional third stage, the resulting fit can be further improved using techniques from nonlinear optimization. In contrast to currently established techniques (e.g. SNAP, Apex) our algorithm is able to separate overlapping peaks of multiply charged peptides in ESI-MS data of low resolution. Its improved accuracy with respect to peak positions makes it a valuable preprocessing method for MS-based identification and quantification experiments. The method has been validated on a number of different annotated test cases, where it compares favorably in both runtime and accuracy with currently established techniques. An implementation of the algorithm is freely available in our open source framework OpenMS.

Development of a method for comprehensive water quality forecasting and its application in Miyun reservoir of Beijing, China.

PubMed

Zhang, Lei; Zou, Zhihong; Shan, Wei

2017-06-01

Water quality forecasting is an essential part of water resource management. Spatiotemporal variations of water quality and their inherent constraints make it very complex. This study explored a data-based method for short-term water quality forecasting. Prediction of water quality indicators including dissolved oxygen, chemical oxygen demand by KMnO 4 and ammonia nitrogen using support vector machine was taken as inputs of the particle swarm algorithm based optimal wavelet neural network to forecast the whole status index of water quality. Gubeikou monitoring section of Miyun reservoir in Beijing, China was taken as the study case to examine effectiveness of this approach. The experiment results also revealed that the proposed model has advantages of stability and time reduction in comparison with other data-driven models including traditional BP neural network model, wavelet neural network model and Gradient Boosting Decision Tree model. It can be used as an effective approach to perform short-term comprehensive water quality prediction. Copyright © 2016. Published by Elsevier B.V.

Electroencephalogram Signal Classification for Automated Epileptic Seizure Detection Using Genetic Algorithm

PubMed Central

Nanthini, B. Suguna; Santhi, B.

2017-01-01

Background: Epilepsy causes when the repeated seizure occurs in the brain. Electroencephalogram (EEG) test provides valuable information about the brain functions and can be useful to detect brain disorder, especially for epilepsy. In this study, application for an automated seizure detection model has been introduced successfully. Materials and Methods: The EEG signals are decomposed into sub-bands by discrete wavelet transform using db2 (daubechies) wavelet. The eight statistical features, the four gray level co-occurrence matrix and Renyi entropy estimation with four different degrees of order, are extracted from the raw EEG and its sub-bands. Genetic algorithm (GA) is used to select eight relevant features from the 16 dimension features. The model has been trained and tested using support vector machine (SVM) classifier successfully for EEG signals. The performance of the SVM classifier is evaluated for two different databases. Results: The study has been experimented through two different analyses and achieved satisfactory performance for automated seizure detection using relevant features as the input to the SVM classifier. Conclusion: Relevant features using GA give better accuracy performance for seizure detection. PMID:28781480

Discrete wavelet transform and energy eigen value for rotor bars fault detection in variable speed field-oriented control of induction motor drive.

PubMed

Ameid, Tarek; Menacer, Arezki; Talhaoui, Hicham; Azzoug, Youness

2018-05-03

This paper presents a methodology for the broken rotor bars fault detection is considered when the rotor speed varies continuously and the induction machine is controlled by Field-Oriented Control (FOC). The rotor fault detection is obtained by analyzing a several mechanical and electrical quantities (i.e., rotor speed, stator phase current and output signal of the speed regulator) by the Discrete Wavelet Transform (DWT) in variable speed drives. The severity of the fault is obtained by stored energy calculation for active power signal. Hence, it can be a useful solution as fault indicator. The FOC is implemented in order to preserve a good performance speed control; to compensate the broken rotor bars effect in the mechanical speed and to ensure the operation continuity and to investigate the fault effect in the variable speed. The effectiveness of the technique is evaluated in simulation and in a real-time implementation by using Matlab/Simulink with the real-time interface (RTI) based on dSpace 1104 board. Copyright © 2018. Published by Elsevier Ltd.

Heart murmur detection based on wavelet transformation and a synergy between artificial neural network and modified neighbor annealing methods.

PubMed

Eslamizadeh, Gholamhossein; Barati, Ramin

2017-05-01

Early recognition of heart disease plays a vital role in saving lives. Heart murmurs are one of the common heart problems. In this study, Artificial Neural Network (ANN) is trained with Modified Neighbor Annealing (MNA) to classify heart cycles into normal and murmur classes. Heart cycles are separated from heart sounds using wavelet transformer. The network inputs are features extracted from individual heart cycles, and two classification outputs. Classification accuracy of the proposed model is compared with five multilayer perceptron trained with Levenberg-Marquardt, Extreme-learning-machine, back-propagation, simulated-annealing, and neighbor-annealing algorithms. It is also compared with a Self-Organizing Map (SOM) ANN. The proposed model is trained and tested using real heart sounds available in the Pascal database to show the applicability of the proposed scheme. Also, a device to record real heart sounds has been developed and used for comparison purposes too. Based on the results of this study, MNA can be used to produce considerable results as a heart cycle classifier. Copyright © 2017 Elsevier B.V. All rights reserved.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System.

PubMed

Li, Hongqiang; Yuan, Danyang; Wang, Youxi; Cui, Dianyin; Cao, Lu

2016-10-20

Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias.

Arrhythmia Classification Based on Multi-Domain Feature Extraction for an ECG Recognition System

PubMed Central

Li, Hongqiang; Yuan, Danyang; Wang, Youxi; Cui, Dianyin; Cao, Lu

2016-01-01

Automatic recognition of arrhythmias is particularly important in the diagnosis of heart diseases. This study presents an electrocardiogram (ECG) recognition system based on multi-domain feature extraction to classify ECG beats. An improved wavelet threshold method for ECG signal pre-processing is applied to remove noise interference. A novel multi-domain feature extraction method is proposed; this method employs kernel-independent component analysis in nonlinear feature extraction and uses discrete wavelet transform to extract frequency domain features. The proposed system utilises a support vector machine classifier optimized with a genetic algorithm to recognize different types of heartbeats. An ECG acquisition experimental platform, in which ECG beats are collected as ECG data for classification, is constructed to demonstrate the effectiveness of the system in ECG beat classification. The presented system, when applied to the MIT-BIH arrhythmia database, achieves a high classification accuracy of 98.8%. Experimental results based on the ECG acquisition experimental platform show that the system obtains a satisfactory classification accuracy of 97.3% and is able to classify ECG beats efficiently for the automatic identification of cardiac arrhythmias. PMID:27775596

Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals

PubMed Central

Muthusamy, Hariharan; Polat, Kemal; Yaacob, Sazali

2015-01-01

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature. PMID:25799141

Nondestructive Detection of the Internalquality of Apple Using X-Ray and Machine Vision

NASA Astrophysics Data System (ADS)

Yang, Fuzeng; Yang, Liangliang; Yang, Qing; Kang, Likui

The internal quality of apple is impossible to be detected by eyes in the procedure of sorting, which could reduce the apple’s quality reaching market. This paper illustrates an instrument using X-ray and machine vision. The following steps were introduced to process the X-ray image in order to determine the mould core apple. Firstly, lifting wavelet transform was used to get a low frequency image and three high frequency images. Secondly, we enhanced the low frequency image through image’s histogram equalization. Then, the edge of each apple's image was detected using canny operator. Finally, a threshold was set to clarify mould core and normal apple according to the different length of the apple core’s diameter. The experimental results show that this method could on-line detect the mould core apple with less time consuming, less than 0.03 seconds per apple, and the accuracy could reach 92%.

Tool Condition Monitoring and Remaining Useful Life Prognostic Based on a Wireless Sensor in Dry Milling Operations.

PubMed

Zhang, Cunji; Yao, Xifan; Zhang, Jianming; Jin, Hong

2016-05-31

Tool breakage causes losses of surface polishing and dimensional accuracy for machined part, or possible damage to a workpiece or machine. Tool Condition Monitoring (TCM) is considerably vital in the manufacturing industry. In this paper, an indirect TCM approach is introduced with a wireless triaxial accelerometer. The vibrations in the three vertical directions (x, y and z) are acquired during milling operations, and the raw signals are de-noised by wavelet analysis. These features of de-noised signals are extracted in the time, frequency and time-frequency domains. The key features are selected based on Pearson's Correlation Coefficient (PCC). The Neuro-Fuzzy Network (NFN) is adopted to predict the tool wear and Remaining Useful Life (RUL). In comparison with Back Propagation Neural Network (BPNN) and Radial Basis Function Network (RBFN), the results show that the NFN has the best performance in the prediction of tool wear and RUL.

Improved biliary detection and diagnosis through intelligent machine analysis.

PubMed

Logeswaran, Rajasvaran

2012-09-01

This paper reports on work undertaken to improve automated detection of bile ducts in magnetic resonance cholangiopancreatography (MRCP) images, with the objective of conducting preliminary classification of the images for diagnosis. The proposed I-BDeDIMA (Improved Biliary Detection and Diagnosis through Intelligent Machine Analysis) scheme is a multi-stage framework consisting of successive phases of image normalization, denoising, structure identification, object labeling, feature selection and disease classification. A combination of multiresolution wavelet, dynamic intensity thresholding, segment-based region growing, region elimination, statistical analysis and neural networks, is used in this framework to achieve good structure detection and preliminary diagnosis. Tests conducted on over 200 clinical images with known diagnosis have shown promising results of over 90% accuracy. The scheme outperforms related work in the literature, making it a viable framework for computer-aided diagnosis of biliary diseases. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

Pursuing optimal electric machines transient diagnosis: The adaptive slope transform

NASA Astrophysics Data System (ADS)

Pons-Llinares, Joan; Riera-Guasp, Martín; Antonino-Daviu, Jose A.; Habetler, Thomas G.

2016-12-01

The aim of this paper is to introduce a new linear time-frequency transform to improve the detection of fault components in electric machines transient currents. Linear transforms are analysed from the perspective of the atoms used. A criterion to select the atoms at every point of the time-frequency plane is proposed, taking into account the characteristics of the searched component at each point. This criterion leads to the definition of the Adaptive Slope Transform, which enables a complete and optimal capture of the different components evolutions in a transient current. A comparison with conventional linear transforms (Short-Time Fourier Transform and Wavelet Transform) is carried out, showing their inherent limitations. The approach is tested with laboratory and field motors, and the Lower Sideband Harmonic is captured for the first time during an induction motor startup and subsequent load oscillations, accurately tracking its evolution.

Evaluation and recognition of skin images with aging by support vector machine

NASA Astrophysics Data System (ADS)

Hu, Liangjun; Wu, Shulian; Li, Hui

2016-10-01

Aging is a very important issue not only in dermatology, but also cosmetic science. Cutaneous aging involves both chronological and photoaging aging process. The evaluation and classification of aging is an important issue with the medical cosmetology workers nowadays. The purpose of this study is to assess chronological-age-related and photo-age-related of human skin. The texture features of skin surface skin, such as coarseness, contrast were analyzed by Fourier transform and Tamura. And the aim of it is to detect the object hidden in the skin texture in difference aging skin. Then, Support vector machine was applied to train the texture feature. The different age's states were distinguished by the support vector machine (SVM) classifier. The results help us to further understand the mechanism of different aging skin from texture feature and help us to distinguish the different aging states.

Temperature based Restricted Boltzmann Machines

NASA Astrophysics Data System (ADS)

Li, Guoqi; Deng, Lei; Xu, Yi; Wen, Changyun; Wang, Wei; Pei, Jing; Shi, Luping

2016-01-01

Restricted Boltzmann machines (RBMs), which apply graphical models to learning probability distribution over a set of inputs, have attracted much attention recently since being proposed as building blocks of multi-layer learning systems called deep belief networks (DBNs). Note that temperature is a key factor of the Boltzmann distribution that RBMs originate from. However, none of existing schemes have considered the impact of temperature in the graphical model of DBNs. In this work, we propose temperature based restricted Boltzmann machines (TRBMs) which reveals that temperature is an essential parameter controlling the selectivity of the firing neurons in the hidden layers. We theoretically prove that the effect of temperature can be adjusted by setting the parameter of the sharpness of the logistic function in the proposed TRBMs. The performance of RBMs can be improved by adjusting the temperature parameter of TRBMs. This work provides a comprehensive insights into the deep belief networks and deep learning architectures from a physical point of view.

Regenerative Medicine for Battlefield Injuries

DTIC Science & Technology

2014-10-01

used immunohistochemical staining of BMP-4 and HGF after treatment with BMP-4/HGF or unamputated limb tissue extract. Sample slides were de- waxed in...Cambridge, MA) primary antibodies were applied on samples separately and incubated overnight at 40 C. After washing the slides in 1x PBS, HRP conjugate...and other dictionaries such as LocusLink and (3) Hidden Markov Models and N-gram, machine - learning methods, to identify biological entities not

Fingerprinting Reverse Proxies Using Timing Analysis of TCP Flows

DTIC Science & Technology

2013-09-01

bayes classifier,” in Cloud Computing Security , ser. CCSW ’09. New York City, NY: ACM, 2009, pp. 31–42. [30] J. Zhang, R. Perdisci, W. Lee, U. Sarfraz...FSM Finite State Machine HTML Hypertext Markup Language HTTP Hypertext Transfer Protocol HTTPS Hypertext Transfer Protocol Secure ICMP Internet Control...This hidden traffic concept supports network access control, security protection through obfuscation, and performance boosts at the Internet facing

Data Stream Mining

NASA Astrophysics Data System (ADS)

Gaber, Mohamed Medhat; Zaslavsky, Arkady; Krishnaswamy, Shonali

Data mining is concerned with the process of computationally extracting hidden knowledge structures represented in models and patterns from large data repositories. It is an interdisciplinary field of study that has its roots in databases, statistics, machine learning, and data visualization. Data mining has emerged as a direct outcome of the data explosion that resulted from the success in database and data warehousing technologies over the past two decades (Fayyad, 1997,Fayyad, 1998,Kantardzic, 2003).

Exploring the potential relationship between indoor air quality and the concentration of airborne culturable fungi: a combined experimental and neural network modeling study.

PubMed

Liu, Zhijian; Cheng, Kewei; Li, Hao; Cao, Guoqing; Wu, Di; Shi, Yunjie

2018-02-01

Indoor airborne culturable fungi exposure has been closely linked to occupants' health. However, conventional measurement of indoor airborne fungal concentration is complicated and usually requires around one week for fungi incubation in laboratory. To provide an ultra-fast solution, here, for the first time, a knowledge-based machine learning model is developed with the inputs of indoor air quality data for estimating the concentration of indoor airborne culturable fungi. To construct a database for statistical analysis and model training, 249 data groups of air quality indicators (concentration of indoor airborne culturable fungi, indoor/outdoor PM 2.5 and PM 10 concentrations, indoor temperature, indoor relative humidity, and indoor CO 2 concentration) were measured from 85 residential buildings of Baoding (China) during the period of 2016.11.15-2017.03.15. Our results show that artificial neural network (ANN) with one hidden layer has good prediction performances, compared to a support vector machine (SVM). With the tolerance of ± 30%, the prediction accuracy of the ANN model with ten hidden nodes can at highest reach 83.33% in the testing set. Most importantly, we here provide a quick method for estimating the concentration of indoor airborne fungi that can be applied to real-time evaluation.

Adaptive Online Sequential ELM for Concept Drift Tackling

PubMed Central

Basaruddin, Chan

2016-01-01

A machine learning method needs to adapt to over time changes in the environment. Such changes are known as concept drift. In this paper, we propose concept drift tackling method as an enhancement of Online Sequential Extreme Learning Machine (OS-ELM) and Constructive Enhancement OS-ELM (CEOS-ELM) by adding adaptive capability for classification and regression problem. The scheme is named as adaptive OS-ELM (AOS-ELM). It is a single classifier scheme that works well to handle real drift, virtual drift, and hybrid drift. The AOS-ELM also works well for sudden drift and recurrent context change type. The scheme is a simple unified method implemented in simple lines of code. We evaluated AOS-ELM on regression and classification problem by using concept drift public data set (SEA and STAGGER) and other public data sets such as MNIST, USPS, and IDS. Experiments show that our method gives higher kappa value compared to the multiclassifier ELM ensemble. Even though AOS-ELM in practice does not need hidden nodes increase, we address some issues related to the increasing of the hidden nodes such as error condition and rank values. We propose taking the rank of the pseudoinverse matrix as an indicator parameter to detect “underfitting” condition. PMID:27594879

Hidden Markov Model and Support Vector Machine based decoding of finger movements using Electrocorticography

PubMed Central

Wissel, Tobias; Pfeiffer, Tim; Frysch, Robert; Knight, Robert T.; Chang, Edward F.; Hinrichs, Hermann; Rieger, Jochem W.; Rose, Georg

2013-01-01

Objective Support Vector Machines (SVM) have developed into a gold standard for accurate classification in Brain-Computer-Interfaces (BCI). The choice of the most appropriate classifier for a particular application depends on several characteristics in addition to decoding accuracy. Here we investigate the implementation of Hidden Markov Models (HMM)for online BCIs and discuss strategies to improve their performance. Approach We compare the SVM, serving as a reference, and HMMs for classifying discrete finger movements obtained from the Electrocorticograms of four subjects doing a finger tapping experiment. The classifier decisions are based on a subset of low-frequency time domain and high gamma oscillation features. Main results We show that decoding optimization between the two approaches is due to the way features are extracted and selected and less dependent on the classifier. An additional gain in HMM performance of up to 6% was obtained by introducing model constraints. Comparable accuracies of up to 90% were achieved with both SVM and HMM with the high gamma cortical response providing the most important decoding information for both techniques. Significance We discuss technical HMM characteristics and adaptations in the context of the presented data as well as for general BCI applications. Our findings suggest that HMMs and their characteristics are promising for efficient online brain-computer interfaces. PMID:24045504

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia

PubMed Central

Kim, Junghoe; Calhoun, Vince D.; Shim, Eunsoo; Lee, Jong-Hwan

2015-01-01

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantified by using kurtosis/modularity measures and features from the higher hidden layer showed holistic/global FC patterns differentiating SZ from HC. Our proposed schemes and reported findings attained by using the DNN classifier and whole-brain FC data suggest that such approaches show improved ability to learn hidden patterns in brain imaging data, which may be useful for developing diagnostic tools for SZ and other neuropsychiatric disorders and identifying associated aberrant FC patterns. PMID:25987366

A fast and accurate online sequential learning algorithm for feedforward networks.

PubMed

Liang, Nan-Ying; Huang, Guang-Bin; Saratchandran, P; Sundararajan, N

2006-11-01

In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.

An accurate sleep stages classification system using a new class of optimally time-frequency localized three-band wavelet filter bank.

PubMed

Sharma, Manish; Goyal, Deepanshu; Achuth, P V; Acharya, U Rajendra

2018-07-01

Sleep related disorder causes diminished quality of lives in human beings. Sleep scoring or sleep staging is the process of classifying various sleep stages which helps to detect the quality of sleep. The identification of sleep-stages using electroencephalogram (EEG) signals is an arduous task. Just by looking at an EEG signal, one cannot determine the sleep stages precisely. Sleep specialists may make errors in identifying sleep stages by visual inspection. To mitigate the erroneous identification and to reduce the burden on doctors, a computer-aided EEG based system can be deployed in the hospitals, which can help identify the sleep stages, correctly. Several automated systems based on the analysis of polysomnographic (PSG) signals have been proposed. A few sleep stage scoring systems using EEG signals have also been proposed. But, still there is a need for a robust and accurate portable system developed using huge dataset. In this study, we have developed a new single-channel EEG based sleep-stages identification system using a novel set of wavelet-based features extracted from a large EEG dataset. We employed a novel three-band time-frequency localized (TBTFL) wavelet filter bank (FB). The EEG signals are decomposed using three-level wavelet decomposition, yielding seven sub-bands (SBs). This is followed by the computation of discriminating features namely, log-energy (LE), signal-fractal-dimensions (SFD), and signal-sample-entropy (SSE) from all seven SBs. The extracted features are ranked and fed to the support vector machine (SVM) and other supervised learning classifiers. In this study, we have considered five different classification problems (CPs), (two-class (CP-1), three-class (CP-2), four-class (CP-3), five-class (CP-4) and six-class (CP-5)). The proposed system yielded accuracies of 98.3%, 93.9%, 92.1%, 91.7%, and 91.5% for CP-1 to CP-5, respectively, using 10-fold cross validation (CV) technique. Copyright © 2018 Elsevier Ltd. All rights reserved.

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.

Quantitative analysis of bayberry juice acidity based on visible and near-infrared spectroscopy

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

Shao Yongni; He Yong; Mao Jingyuan

Visible and near-infrared (Vis/NIR) reflectance spectroscopy has been investigated for its ability to nondestructively detect acidity in bayberry juice. What we believe to be a new, better mathematic model is put forward, which we have named principal component analysis-stepwise regression analysis-backpropagation neural network (PCA-SRA-BPNN), to build a correlation between the spectral reflectivity data and the acidity of bayberry juice. In this model, the optimum network parameters,such as the number of input nodes, hidden nodes, learning rate, and momentum, are chosen by the value of root-mean-square (rms) error. The results show that its prediction statistical parameters are correlation coefficient (r) ofmore » 0.9451 and root-mean-square error of prediction(RMSEP) of 0.1168. Partial least-squares (PLS) regression is also established to compare with this model. Before doing this, the influences of various spectral pretreatments (standard normal variate, multiplicative scatter correction, S. Golay first derivative, and wavelet package transform) are compared. The PLS approach with wavelet package transform preprocessing spectra is found to provide the best results, and its prediction statistical parameters are correlation coefficient (r) of 0.9061 and RMSEP of 0.1564. Hence, these two models are both desirable to analyze the data from Vis/NIR spectroscopy and to solve the problem of the acidity prediction of bayberry juice. This supplies basal research to ultimately realize the online measurements of the juice's internal quality through this Vis/NIR spectroscopy technique.« less

Stego on FPGA: An IWT Approach

PubMed Central

Ramalingam, Balakrishnan

2014-01-01

A reconfigurable hardware architecture for the implementation of integer wavelet transform (IWT) based adaptive random image steganography algorithm is proposed. The Haar-IWT was used to separate the subbands namely, LL, LH, HL, and HH, from 8 × 8 pixel blocks and the encrypted secret data is hidden in the LH, HL, and HH blocks using Moore and Hilbert space filling curve (SFC) scan patterns. Either Moore or Hilbert SFC was chosen for hiding the encrypted data in LH, HL, and HH coefficients, whichever produces the lowest mean square error (MSE) and the highest peak signal-to-noise ratio (PSNR). The fixated random walk's verdict of all blocks is registered which is nothing but the furtive key. Our system took 1.6 µs for embedding the data in coefficient blocks and consumed 34% of the logic elements, 22% of the dedicated logic register, and 2% of the embedded multiplier on Cyclone II field programmable gate array (FPGA). PMID:24723794

Crack orientation and depth estimation in a low-pressure turbine disc using a phased array ultrasonic transducer and an artificial neural network.

PubMed

Yang, Xiaoxia; Chen, Shili; Jin, Shijiu; Chang, Wenshuang

2013-09-13

Stress corrosion cracks (SCC) in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN), is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF) neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks.

Crack Orientation and Depth Estimation in a Low-Pressure Turbine Disc Using a Phased Array Ultrasonic Transducer and an Artificial Neural Network

PubMed Central

Yang, Xiaoxia; Chen, Shili; Jin, Shijiu; Chang, Wenshuang

2013-01-01

Stress corrosion cracks (SCC) in low-pressure steam turbine discs are serious hidden dangers to production safety in the power plants, and knowing the orientation and depth of the initial cracks is essential for the evaluation of the crack growth rate, propagation direction and working life of the turbine disc. In this paper, a method based on phased array ultrasonic transducer and artificial neural network (ANN), is proposed to estimate both the depth and orientation of initial cracks in the turbine discs. Echo signals from cracks with different depths and orientations were collected by a phased array ultrasonic transducer, and the feature vectors were extracted by wavelet packet, fractal technology and peak amplitude methods. The radial basis function (RBF) neural network was investigated and used in this application. The final results demonstrated that the method presented was efficient in crack estimation tasks. PMID:24064602

Semantic Context Detection Using Audio Event Fusion

NASA Astrophysics Data System (ADS)

Chu, Wei-Ta; Cheng, Wen-Huang; Wu, Ja-Ling

2006-12-01

Semantic-level content analysis is a crucial issue in achieving efficient content retrieval and management. We propose a hierarchical approach that models audio events over a time series in order to accomplish semantic context detection. Two levels of modeling, audio event and semantic context modeling, are devised to bridge the gap between physical audio features and semantic concepts. In this work, hidden Markov models (HMMs) are used to model four representative audio events, that is, gunshot, explosion, engine, and car braking, in action movies. At the semantic context level, generative (ergodic hidden Markov model) and discriminative (support vector machine (SVM)) approaches are investigated to fuse the characteristics and correlations among audio events, which provide cues for detecting gunplay and car-chasing scenes. The experimental results demonstrate the effectiveness of the proposed approaches and provide a preliminary framework for information mining by using audio characteristics.

Solid harmonic wavelet scattering for predictions of molecule properties

NASA Astrophysics Data System (ADS)

Eickenberg, Michael; Exarchakis, Georgios; Hirn, Matthew; Mallat, Stéphane; Thiry, Louis

2018-06-01

We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory (DFT). Using Gaussian-type orbital functions, we create surrogate electronic densities of the molecule from which we compute invariant "solid harmonic scattering coefficients" that account for different types of interactions at different scales. Multilinear regressions of various physical properties of molecules are computed from these invariant coefficients. Numerical experiments show that these regressions have near state-of-the-art performance, even with relatively few training examples. Predictions over small sets of scattering coefficients can reach a DFT precision while being interpretable.

Refining Markov state models for conformational dynamics using ensemble-averaged data and time-series trajectories

NASA Astrophysics Data System (ADS)

Matsunaga, Y.; Sugita, Y.

2018-06-01

A data-driven modeling scheme is proposed for conformational dynamics of biomolecules based on molecular dynamics (MD) simulations and experimental measurements. In this scheme, an initial Markov State Model (MSM) is constructed from MD simulation trajectories, and then, the MSM parameters are refined using experimental measurements through machine learning techniques. The second step can reduce the bias of MD simulation results due to inaccurate force-field parameters. Either time-series trajectories or ensemble-averaged data are available as a training data set in the scheme. Using a coarse-grained model of a dye-labeled polyproline-20, we compare the performance of machine learning estimations from the two types of training data sets. Machine learning from time-series data could provide the equilibrium populations of conformational states as well as their transition probabilities. It estimates hidden conformational states in more robust ways compared to that from ensemble-averaged data although there are limitations in estimating the transition probabilities between minor states. We discuss how to use the machine learning scheme for various experimental measurements including single-molecule time-series trajectories.

River flow prediction using hybrid models of support vector regression with the wavelet transform, singular spectrum analysis and chaotic approach

NASA Astrophysics Data System (ADS)

Baydaroğlu, Özlem; Koçak, Kasım; Duran, Kemal

2018-06-01

Prediction of water amount that will enter the reservoirs in the following month is of vital importance especially for semi-arid countries like Turkey. Climate projections emphasize that water scarcity will be one of the serious problems in the future. This study presents a methodology for predicting river flow for the subsequent month based on the time series of observed monthly river flow with hybrid models of support vector regression (SVR). Monthly river flow over the period 1940-2012 observed for the Kızılırmak River in Turkey has been used for training the method, which then has been applied for predictions over a period of 3 years. SVR is a specific implementation of support vector machines (SVMs), which transforms the observed input data time series into a high-dimensional feature space (input matrix) by way of a kernel function and performs a linear regression in this space. SVR requires a special input matrix. The input matrix was produced by wavelet transforms (WT), singular spectrum analysis (SSA), and a chaotic approach (CA) applied to the input time series. WT convolutes the original time series into a series of wavelets, and SSA decomposes the time series into a trend, an oscillatory and a noise component by singular value decomposition. CA uses a phase space formed by trajectories, which represent the dynamics producing the time series. These three methods for producing the input matrix for the SVR proved successful, while the SVR-WT combination resulted in the highest coefficient of determination and the lowest mean absolute error.

Detection algorithm for glass bottle mouth defect by continuous wavelet transform based on machine vision

NASA Astrophysics Data System (ADS)

Qian, Jinfang; Zhang, Changjiang

2014-11-01

An efficient algorithm based on continuous wavelet transform combining with pre-knowledge, which can be used to detect the defect of glass bottle mouth, is proposed. Firstly, under the condition of ball integral light source, a perfect glass bottle mouth image is obtained by Japanese Computar camera through the interface of IEEE-1394b. A single threshold method based on gray level histogram is used to obtain the binary image of the glass bottle mouth. In order to efficiently suppress noise, moving average filter is employed to smooth the histogram of original glass bottle mouth image. And then continuous wavelet transform is done to accurately determine the segmentation threshold. Mathematical morphology operations are used to get normal binary bottle mouth mask. A glass bottle to be detected is moving to the detection zone by conveyor belt. Both bottle mouth image and binary image are obtained by above method. The binary image is multiplied with normal bottle mask and a region of interest is got. Four parameters (number of connected regions, coordinate of centroid position, diameter of inner cycle, and area of annular region) can be computed based on the region of interest. Glass bottle mouth detection rules are designed by above four parameters so as to accurately detect and identify the defect conditions of glass bottle. Finally, the glass bottles of Coca-Cola Company are used to verify the proposed algorithm. The experimental results show that the proposed algorithm can accurately detect the defect conditions of the glass bottles and have 98% detecting accuracy.

Analysis of cutting force signals by wavelet packet transform for surface roughness monitoring in CNC turning

NASA Astrophysics Data System (ADS)

García Plaza, E.; Núñez López, P. J.

2018-01-01

On-line monitoring of surface finish in machining processes has proven to be a substantial advancement over traditional post-process quality control techniques by reducing inspection times and costs and by avoiding the manufacture of defective products. This study applied techniques for processing cutting force signals based on the wavelet packet transform (WPT) method for the monitoring of surface finish in computer numerical control (CNC) turning operations. The behaviour of 40 mother wavelets was analysed using three techniques: global packet analysis (G-WPT), and the application of two packet reduction criteria: maximum energy (E-WPT) and maximum entropy (SE-WPT). The optimum signal decomposition level (Lj) was determined to eliminate noise and to obtain information correlated to surface finish. The results obtained with the G-WPT method provided an in-depth analysis of cutting force signals, and frequency ranges and signal characteristics were correlated to surface finish with excellent results in the accuracy and reliability of the predictive models. The radial and tangential cutting force components at low frequency provided most of the information for the monitoring of surface finish. The E-WPT and SE-WPT packet reduction criteria substantially reduced signal processing time, but at the expense of discarding packets with relevant information, which impoverished the results. The G-WPT method was observed to be an ideal procedure for processing cutting force signals applied to the real-time monitoring of surface finish, and was estimated to be highly accurate and reliable at a low analytical-computational cost.

Empirical Wavelet Transform Based Features for Classification of Parkinson's Disease Severity.

PubMed

Oung, Qi Wei; Muthusamy, Hariharan; Basah, Shafriza Nisha; Lee, Hoileong; Vijean, Vikneswaran

2017-12-29

Parkinson's disease (PD) is a type of progressive neurodegenerative disorder that has affected a large part of the population till now. Several symptoms of PD include tremor, rigidity, slowness of movements and vocal impairments. In order to develop an effective diagnostic system, a number of algorithms were proposed mainly to distinguish healthy individuals from the ones with PD. However, most of the previous works were conducted based on a binary classification, with the early PD stage and the advanced ones being treated equally. Therefore, in this work, we propose a multiclass classification with three classes of PD severity level (mild, moderate, severe) and healthy control. The focus is to detect and classify PD using signals from wearable motion and audio sensors based on both empirical wavelet transform (EWT) and empirical wavelet packet transform (EWPT) respectively. The EWT/EWPT was applied to decompose both speech and motion data signals up to five levels. Next, several features are extracted after obtaining the instantaneous amplitudes and frequencies from the coefficients of the decomposed signals by applying the Hilbert transform. The performance of the algorithm was analysed using three classifiers - K-nearest neighbour (KNN), probabilistic neural network (PNN) and extreme learning machine (ELM). Experimental results demonstrated that our proposed approach had the ability to differentiate PD from non-PD subjects, including their severity level - with classification accuracies of more than 90% using EWT/EWPT-ELM based on signals from motion and audio sensors respectively. Additionally, classification accuracy of more than 95% was achieved when EWT/EWPT-ELM is applied to signals from integration of both signal's information.

Classification of radiological errors in chest radiographs, using support vector machine on the spatial frequency features of false- negative and false-positive regions

NASA Astrophysics Data System (ADS)

Pietrzyk, Mariusz W.; Donovan, Tim; Brennan, Patrick C.; Dix, Alan; Manning, David J.

2011-03-01

Aim: To optimize automated classification of radiological errors during lung nodule detection from chest radiographs (CxR) using a support vector machine (SVM) run on the spatial frequency features extracted from the local background of selected regions. Background: The majority of the unreported pulmonary nodules are visually detected but not recognized; shown by the prolonged dwell time values at false-negative regions. Similarly, overestimated nodule locations are capturing substantial amounts of foveal attention. Spatial frequency properties of selected local backgrounds are correlated with human observer responses either in terms of accuracy in indicating abnormality position or in the precision of visual sampling the medical images. Methods: Seven radiologists participated in the eye tracking experiments conducted under conditions of pulmonary nodule detection from a set of 20 postero-anterior CxR. The most dwelled locations have been identified and subjected to spatial frequency (SF) analysis. The image-based features of selected ROI were extracted with un-decimated Wavelet Packet Transform. An analysis of variance was run to select SF features and a SVM schema was implemented to classify False-Negative and False-Positive from all ROI. Results: A relative high overall accuracy was obtained for each individually developed Wavelet-SVM algorithm, with over 90% average correct ratio for errors recognition from all prolonged dwell locations. Conclusion: The preliminary results show that combined eye-tracking and image-based features can be used for automated detection of radiological error with SVM. The work is still in progress and not all analytical procedures have been completed, which might have an effect on the specificity of the algorithm.

Scalable Performance Measurement and Analysis

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

Gamblin, Todd

2009-01-01

Concurrency levels in large-scale, distributed-memory supercomputers are rising exponentially. Modern machines may contain 100,000 or more microprocessor cores, and the largest of these, IBM's Blue Gene/L, contains over 200,000 cores. Future systems are expected to support millions of concurrent tasks. In this dissertation, we focus on efficient techniques for measuring and analyzing the performance of applications running on very large parallel machines. Tuning the performance of large-scale applications can be a subtle and time-consuming task because application developers must measure and interpret data from many independent processes. While the volume of the raw data scales linearly with the number ofmore » tasks in the running system, the number of tasks is growing exponentially, and data for even small systems quickly becomes unmanageable. Transporting performance data from so many processes over a network can perturb application performance and make measurements inaccurate, and storing such data would require a prohibitive amount of space. Moreover, even if it were stored, analyzing the data would be extremely time-consuming. In this dissertation, we present novel methods for reducing performance data volume. The first draws on multi-scale wavelet techniques from signal processing to compress systemwide, time-varying load-balance data. The second uses statistical sampling to select a small subset of running processes to generate low-volume traces. A third approach combines sampling and wavelet compression to stratify performance data adaptively at run-time and to reduce further the cost of sampled tracing. We have integrated these approaches into Libra, a toolset for scalable load-balance analysis. We present Libra and show how it can be used to analyze data from large scientific applications scalably.« less

Automated Cough Assessment on a Mobile Platform

PubMed Central

2014-01-01

The development of an Automated System for Asthma Monitoring (ADAM) is described. This consists of a consumer electronics mobile platform running a custom application. The application acquires an audio signal from an external user-worn microphone connected to the device analog-to-digital converter (microphone input). This signal is processed to determine the presence or absence of cough sounds. Symptom tallies and raw audio waveforms are recorded and made easily accessible for later review by a healthcare provider. The symptom detection algorithm is based upon standard speech recognition and machine learning paradigms and consists of an audio feature extraction step followed by a Hidden Markov Model based Viterbi decoder that has been trained on a large database of audio examples from a variety of subjects. Multiple Hidden Markov Model topologies and orders are studied. Performance of the recognizer is presented in terms of the sensitivity and the rate of false alarm as determined in a cross-validation test. PMID:25506590

A Novel Extreme Learning Control Framework of Unmanned Surface Vehicles.

PubMed

Wang, Ning; Sun, Jing-Chao; Er, Meng Joo; Liu, Yan-Cheng

2016-05-01

In this paper, an extreme learning control (ELC) framework using the single-hidden-layer feedforward network (SLFN) with random hidden nodes for tracking an unmanned surface vehicle suffering from unknown dynamics and external disturbances is proposed. By combining tracking errors with derivatives, an error surface and transformed states are defined to encapsulate unknown dynamics and disturbances into a lumped vector field of transformed states. The lumped nonlinearity is further identified accurately by an extreme-learning-machine-based SLFN approximator which does not require a priori system knowledge nor tuning input weights. Only output weights of the SLFN need to be updated by adaptive projection-based laws derived from the Lyapunov approach. Moreover, an error compensator is incorporated to suppress approximation residuals, and thereby contributing to the robustness and global asymptotic stability of the closed-loop ELC system. Simulation studies and comprehensive comparisons demonstrate that the ELC framework achieves high accuracy in both tracking and approximation.

Global-constrained hidden Markov model applied on wireless capsule endoscopy video segmentation

NASA Astrophysics Data System (ADS)

Wan, Yiwen; Duraisamy, Prakash; Alam, Mohammad S.; Buckles, Bill

2012-06-01

Accurate analysis of wireless capsule endoscopy (WCE) videos is vital but tedious. Automatic image analysis can expedite this task. Video segmentation of WCE into the four parts of the gastrointestinal tract is one way to assist a physician. The segmentation approach described in this paper integrates pattern recognition with statiscal analysis. Iniatially, a support vector machine is applied to classify video frames into four classes using a combination of multiple color and texture features as the feature vector. A Poisson cumulative distribution, for which the parameter depends on the length of segments, models a prior knowledge. A priori knowledge together with inter-frame difference serves as the global constraints driven by the underlying observation of each WCE video, which is fitted by Gaussian distribution to constrain the transition probability of hidden Markov model.Experimental results demonstrated effectiveness of the approach.

The norms and variances of the Gabor, Morlet and general harmonic wavelet functions

NASA Astrophysics Data System (ADS)

Simonovski, I.; Boltežar, M.

2003-07-01

This paper deals with certain properties of the continuous wavelet transform and wavelet functions. The norms and the spreads in time and frequency of the common Gabor and Morlet wavelet functions are presented. It is shown that the norm of the Morlet wavelet function does not satisfy the normalization condition and that the normalized Morlet wavelet function is identical to the Gabor wavelet function with the parameter σ=1. The general harmonic wavelet function is developed using frequency modulation of the Hanning and Hamming window functions. Several properties of the general harmonic wavelet function are also presented and compared to the Gabor wavelet function. The time and frequency spreads of the general harmonic wavelet function are only slightly higher than the time and frequency spreads of the Gabor wavelet function. However, the general harmonic wavelet function is simpler to use than the Gabor wavelet function. In addition, the general harmonic wavelet function can be constructed in such a way that the zero average condition is truly satisfied. The average value of the Gabor wavelet function can approach a value of zero but it cannot reach it. When calculating the continuous wavelet transform, errors occur at the start- and the end-time indexes. This is called the edge effect and is caused by the fact that the wavelet transform is calculated from a signal of finite length. In this paper, we propose a method that uses signal mirroring to reduce the errors caused by the edge effect. The success of the proposed method is demonstrated by using a simulated signal.

Optimal wavelets for biomedical signal compression.

PubMed

Nielsen, Mogens; Kamavuako, Ernest Nlandu; Andersen, Michael Midtgaard; Lucas, Marie-Françoise; Farina, Dario

2006-07-01

Signal compression is gaining importance in biomedical engineering due to the potential applications in telemedicine. In this work, we propose a novel scheme of signal compression based on signal-dependent wavelets. To adapt the mother wavelet to the signal for the purpose of compression, it is necessary to define (1) a family of wavelets that depend on a set of parameters and (2) a quality criterion for wavelet selection (i.e., wavelet parameter optimization). We propose the use of an unconstrained parameterization of the wavelet for wavelet optimization. A natural performance criterion for compression is the minimization of the signal distortion rate given the desired compression rate. For coding the wavelet coefficients, we adopted the embedded zerotree wavelet coding algorithm, although any coding scheme may be used with the proposed wavelet optimization. As a representative example of application, the coding/encoding scheme was applied to surface electromyographic signals recorded from ten subjects. The distortion rate strongly depended on the mother wavelet (for example, for 50% compression rate, optimal wavelet, mean+/-SD, 5.46+/-1.01%; worst wavelet 12.76+/-2.73%). Thus, optimization significantly improved performance with respect to previous approaches based on classic wavelets. The algorithm can be applied to any signal type since the optimal wavelet is selected on a signal-by-signal basis. Examples of application to ECG and EEG signals are also reported.

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia.

PubMed

Kim, Junghoe; Calhoun, Vince D; Shim, Eunsoo; Lee, Jong-Hwan

2016-01-01

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantified by using kurtosis/modularity measures and features from the higher hidden layer showed holistic/global FC patterns differentiating SZ from HC. Our proposed schemes and reported findings attained by using the DNN classifier and whole-brain FC data suggest that such approaches show improved ability to learn hidden patterns in brain imaging data, which may be useful for developing diagnostic tools for SZ and other neuropsychiatric disorders and identifying associated aberrant FC patterns. Copyright © 2015 Elsevier Inc. All rights reserved.

Quantum Computing since Democritus

NASA Astrophysics Data System (ADS)

Aaronson, Scott

2013-03-01

1. Atoms and the void; 2. Sets; 3. Gödel, Turing, and friends; 4. Minds and machines; 5. Paleocomplexity; 6. P, NP, and friends; 7. Randomness; 8. Crypto; 9. Quantum; 10. Quantum computing; 11. Penrose; 12. Decoherence and hidden variables; 13. Proofs; 14. How big are quantum states?; 15. Skepticism of quantum computing; 16. Learning; 17. Interactive proofs and more; 18. Fun with the Anthropic Principle; 19. Free will; 20. Time travel; 21. Cosmology and complexity; 22. Ask me anything.

Detection and Classification of Network Intrusions Using Hidden Markov Models

DTIC Science & Technology

2002-01-01

31 2.2.3 High-level state machines for misuse detection . . . . . . . 32 2.2.4 EMERALD ...Solaris host audit data to detect Solaris R2L (Remote-to-Local) and U2R (User-to-Root) attacks. 7 login as a legitimate user on a local system and use a...as suspicious rather than the entire login session and it can detect some anomalies that are difficult to detect with traditional approaches. It’s

Artificial intelligence (AI) systems for interpreting complex medical datasets.

PubMed

Altman, R B

2017-05-01

Advances in machine intelligence have created powerful capabilities in algorithms that find hidden patterns in data, classify objects based on their measured characteristics, and associate similar patients/diseases/drugs based on common features. However, artificial intelligence (AI) applications in medical data have several technical challenges: complex and heterogeneous datasets, noisy medical datasets, and explaining their output to users. There are also social challenges related to intellectual property, data provenance, regulatory issues, economics, and liability. © 2017 ASCPT.

A novel artificial neural network method for biomedical prediction based on matrix pseudo-inversion.

PubMed

Cai, Binghuang; Jiang, Xia

2014-04-01

Biomedical prediction based on clinical and genome-wide data has become increasingly important in disease diagnosis and classification. To solve the prediction problem in an effective manner for the improvement of clinical care, we develop a novel Artificial Neural Network (ANN) method based on Matrix Pseudo-Inversion (MPI) for use in biomedical applications. The MPI-ANN is constructed as a three-layer (i.e., input, hidden, and output layers) feed-forward neural network, and the weights connecting the hidden and output layers are directly determined based on MPI without a lengthy learning iteration. The LASSO (Least Absolute Shrinkage and Selection Operator) method is also presented for comparative purposes. Single Nucleotide Polymorphism (SNP) simulated data and real breast cancer data are employed to validate the performance of the MPI-ANN method via 5-fold cross validation. Experimental results demonstrate the efficacy of the developed MPI-ANN for disease classification and prediction, in view of the significantly superior accuracy (i.e., the rate of correct predictions), as compared with LASSO. The results based on the real breast cancer data also show that the MPI-ANN has better performance than other machine learning methods (including support vector machine (SVM), logistic regression (LR), and an iterative ANN). In addition, experiments demonstrate that our MPI-ANN could be used for bio-marker selection as well. Copyright © 2013 Elsevier Inc. All rights reserved.

Parsimonious extreme learning machine using recursive orthogonal least squares.

PubMed

Wang, Ning; Er, Meng Joo; Han, Min

2014-10-01

Novel constructive and destructive parsimonious extreme learning machines (CP- and DP-ELM) are proposed in this paper. By virtue of the proposed ELMs, parsimonious structure and excellent generalization of multiinput-multioutput single hidden-layer feedforward networks (SLFNs) are obtained. The proposed ELMs are developed by innovative decomposition of the recursive orthogonal least squares procedure into sequential partial orthogonalization (SPO). The salient features of the proposed approaches are as follows: 1) Initial hidden nodes are randomly generated by the ELM methodology and recursively orthogonalized into an upper triangular matrix with dramatic reduction in matrix size; 2) the constructive SPO in the CP-ELM focuses on the partial matrix with the subcolumn of the selected regressor including nonzeros as the first column while the destructive SPO in the DP-ELM operates on the partial matrix including elements determined by the removed regressor; 3) termination criteria for CP- and DP-ELM are simplified by the additional residual error reduction method; and 4) the output weights of the SLFN need not be solved in the model selection procedure and is derived from the final upper triangular equation by backward substitution. Both single- and multi-output real-world regression data sets are used to verify the effectiveness and superiority of the CP- and DP-ELM in terms of parsimonious architecture and generalization accuracy. Innovative applications to nonlinear time-series modeling demonstrate superior identification results.

Dynamical analysis of contrastive divergence learning: Restricted Boltzmann machines with Gaussian visible units.

PubMed

Karakida, Ryo; Okada, Masato; Amari, Shun-Ichi

2016-07-01

The restricted Boltzmann machine (RBM) is an essential constituent of deep learning, but it is hard to train by using maximum likelihood (ML) learning, which minimizes the Kullback-Leibler (KL) divergence. Instead, contrastive divergence (CD) learning has been developed as an approximation of ML learning and widely used in practice. To clarify the performance of CD learning, in this paper, we analytically derive the fixed points where ML and CDn learning rules converge in two types of RBMs: one with Gaussian visible and Gaussian hidden units and the other with Gaussian visible and Bernoulli hidden units. In addition, we analyze the stability of the fixed points. As a result, we find that the stable points of CDn learning rule coincide with those of ML learning rule in a Gaussian-Gaussian RBM. We also reveal that larger principal components of the input data are extracted at the stable points. Moreover, in a Gaussian-Bernoulli RBM, we find that both ML and CDn learning can extract independent components at one of stable points. Our analysis demonstrates that the same feature components as those extracted by ML learning are extracted simply by performing CD1 learning. Expanding this study should elucidate the specific solutions obtained by CD learning in other types of RBMs or in deep networks. Copyright © 2016 Elsevier Ltd. All rights reserved.

Biomarker selection and classification of "-omics" data using a two-step bayes classification framework.

PubMed

Assawamakin, Anunchai; Prueksaaroon, Supakit; Kulawonganunchai, Supasak; Shaw, Philip James; Varavithya, Vara; Ruangrajitpakorn, Taneth; Tongsima, Sissades

2013-01-01

Identification of suitable biomarkers for accurate prediction of phenotypic outcomes is a goal for personalized medicine. However, current machine learning approaches are either too complex or perform poorly. Here, a novel two-step machine-learning framework is presented to address this need. First, a Naïve Bayes estimator is used to rank features from which the top-ranked will most likely contain the most informative features for prediction of the underlying biological classes. The top-ranked features are then used in a Hidden Naïve Bayes classifier to construct a classification prediction model from these filtered attributes. In order to obtain the minimum set of the most informative biomarkers, the bottom-ranked features are successively removed from the Naïve Bayes-filtered feature list one at a time, and the classification accuracy of the Hidden Naïve Bayes classifier is checked for each pruned feature set. The performance of the proposed two-step Bayes classification framework was tested on different types of -omics datasets including gene expression microarray, single nucleotide polymorphism microarray (SNParray), and surface-enhanced laser desorption/ionization time-of-flight (SELDI-TOF) proteomic data. The proposed two-step Bayes classification framework was equal to and, in some cases, outperformed other classification methods in terms of prediction accuracy, minimum number of classification markers, and computational time.

A Tensor-Based Structural Damage Identification and Severity Assessment

PubMed Central

Anaissi, Ali; Makki Alamdari, Mehrisadat; Rakotoarivelo, Thierry; Khoa, Nguyen Lu Dang

2018-01-01

Early damage detection is critical for a large set of global ageing infrastructure. Structural Health Monitoring systems provide a sensor-based quantitative and objective approach to continuously monitor these structures, as opposed to traditional engineering visual inspection. Analysing these sensed data is one of the major Structural Health Monitoring (SHM) challenges. This paper presents a novel algorithm to detect and assess damage in structures such as bridges. This method applies tensor analysis for data fusion and feature extraction, and further uses one-class support vector machine on this feature to detect anomalies, i.e., structural damage. To evaluate this approach, we collected acceleration data from a sensor-based SHM system, which we deployed on a real bridge and on a laboratory specimen. The results show that our tensor method outperforms a state-of-the-art approach using the wavelet energy spectrum of the measured data. In the specimen case, our approach succeeded in detecting 92.5% of induced damage cases, as opposed to 61.1% for the wavelet-based approach. While our method was applied to bridges, its algorithm and computation can be used on other structures or sensor-data analysis problems, which involve large series of correlated data from multiple sensors. PMID:29301314

Stationary Wavelet Transform and AdaBoost with SVM Based Pathological Brain Detection in MRI Scanning.

PubMed

Nayak, Deepak Ranjan; Dash, Ratnakar; Majhi, Banshidhar

2017-01-01

This paper presents an automatic classification system for segregating pathological brain from normal brains in magnetic resonance imaging scanning. The proposed system employs contrast limited adaptive histogram equalization scheme to enhance the diseased region in brain MR images. Two-dimensional stationary wavelet transform is harnessed to extract features from the preprocessed images. The feature vector is constructed using the energy and entropy values, computed from the level- 2 SWT coefficients. Then, the relevant and uncorrelated features are selected using symmetric uncertainty ranking filter. Subsequently, the selected features are given input to the proposed AdaBoost with support vector machine classifier, where SVM is used as the base classifier of AdaBoost algorithm. To validate the proposed system, three standard MR image datasets, Dataset-66, Dataset-160, and Dataset- 255 have been utilized. The 5 runs of k-fold stratified cross validation results indicate the suggested scheme offers better performance than other existing schemes in terms of accuracy and number of features. The proposed system earns ideal classification over Dataset-66 and Dataset-160; whereas, for Dataset- 255, an accuracy of 99.45% is achieved. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

A novel Pareto-based Bayesian approach on extension of the infogram for extracting repetitive transients

NASA Astrophysics Data System (ADS)

Gu, Xiaohui; Yang, Shaopu; Liu, Yongqiang; Hao, Rujiang

2018-06-01

Two most important signatures of repetitive transients in the vibration signals of a faulty rotating machine are impulsiveness and cyclostationarity. In the newly proposed infogram, the time-domain and frequency-domain spectral negentropy were put forward to characterize these two aspects, respectively. However, in extension of the infogram to Bayesian inference based optimal wavelet filtering, only one spectral negentropy was employed in identifying the informative frequency band. To overcome its drawback, a novel Pareto-based Bayesian approach was proposed in this paper. The Pareto optimal solutions which can simultaneously maximize the time-domain and frequency-domain spectral negentropy were utilized in estimating the posterior wavelet parameters distributions. Moreover, the relationship between the impulsive and cyclostationary signatures was established by the domination. It can help balance the contributions due to these two aspects other than simply synthesize by the average weight in the infogram. Three instance studies including simulated and experimental signals were investigated to illustrate the effectiveness of the proposed method by challenging different noises and interferences. In addition, some comparisons with the aforementioned peer methods were also conducted to show its superiority and robustness in extracting the repetitive transients.

Exploring time- and frequency- dependent functional connectivity and brain networks during deception with single-trial event-related potentials

NASA Astrophysics Data System (ADS)

Gao, Jun-Feng; Yang, Yong; Huang, Wen-Tao; Lin, Pan; Ge, Sheng; Zheng, Hong-Mei; Gu, Ling-Yun; Zhou, Hui; Li, Chen-Hong; Rao, Ni-Ni

2016-11-01

To better characterize the cognitive processes and mechanisms that are associated with deception, wavelet coherence was employed to evaluate functional connectivity between different brain regions. Two groups of subjects were evaluated for this purpose: 32 participants were required to either tell the truth or to lie when facing certain stimuli, and their electroencephalogram signals on 12 electrodes were recorded. The experimental results revealed that deceptive responses elicited greater connectivity strength than truthful responses, particularly in the θ band on specific electrode pairs primarily involving connections between the prefrontal/frontal and central regions and between the prefrontal/frontal and left parietal regions. These results indicate that these brain regions play an important role in executing lying responses. Additionally, three time- and frequency-dependent functional connectivity networks were proposed to thoroughly reflect the functional coupling of brain regions that occurs during lying. Furthermore, the wavelet coherence values for the connections shown in the networks were extracted as features for support vector machine training. High classification accuracy suggested that the proposed network effectively characterized differences in functional connectivity between the two groups of subjects over a specific time-frequency area and hence could be a sensitive measurement for identifying deception.

BELM: Bayesian extreme learning machine.

PubMed

Soria-Olivas, Emilio; Gómez-Sanchis, Juan; Martín, José D; Vila-Francés, Joan; Martínez, Marcelino; Magdalena, José R; Serrano, Antonio J

2011-03-01

The theory of extreme learning machine (ELM) has become very popular on the last few years. ELM is a new approach for learning the parameters of the hidden layers of a multilayer neural network (as the multilayer perceptron or the radial basis function neural network). Its main advantage is the lower computational cost, which is especially relevant when dealing with many patterns defined in a high-dimensional space. This brief proposes a bayesian approach to ELM, which presents some advantages over other approaches: it allows the introduction of a priori knowledge; obtains the confidence intervals (CIs) without the need of applying methods that are computationally intensive, e.g., bootstrap; and presents high generalization capabilities. Bayesian ELM is benchmarked against classical ELM in several artificial and real datasets that are widely used for the evaluation of machine learning algorithms. Achieved results show that the proposed approach produces a competitive accuracy with some additional advantages, namely, automatic production of CIs, reduction of probability of model overfitting, and use of a priori knowledge.

Developing Novel Machine Learning Algorithms to Improve Sedentary Assessment for Youth Health Enhancement.

PubMed

Golla, Gowtham Kumar; Carlson, Jordan A; Huan, Jun; Kerr, Jacqueline; Mitchell, Tarrah; Borner, Kelsey

2016-10-01

Sedentary behavior of youth is an important determinant of health. However, better measures are needed to improve understanding of this relationship and the mechanisms at play, as well as to evaluate health promotion interventions. Wearable accelerometers are considered as the standard for assessing physical activity in research, but do not perform well for assessing posture (i.e., sitting vs. standing), a critical component of sedentary behavior. The machine learning algorithms that we propose for assessing sedentary behavior will allow us to re-examine existing accelerometer data to better understand the association between sedentary time and health in various populations. We collected two datasets, a laboratory-controlled dataset and a free-living dataset. We trained machine learning classifiers separately on each dataset and compared performance across datasets. The classifiers predict five postures: sit, stand, sit-stand, stand-sit, and stand\\walk. We compared a manually constructed Hidden Markov model (HMM) with an automated HMM from existing software. The manually constructed HMM gave more F1-Macro score on both datasets.

Wavelets in Physics

NASA Astrophysics Data System (ADS)

van den Berg, J. C.

2004-03-01

A guided tour J. C. van den Berg; 1. Wavelet analysis, a new tool in physics J.-P. Antoine; 2. The 2-D wavelet transform, physical applications J.-P. Antoine; 3. Wavelets and astrophysical applications A. Bijaoui; 4. Turbulence analysis, modelling and computing using wavelets M. Farge, N. K.-R. Kevlahan, V. Perrier and K. Schneider; 5. Wavelets and detection of coherent structures in fluid turbulence L. Hudgins and J. H. Kaspersen; 6. Wavelets, non-linearity and turbulence in fusion plasmas B. Ph. van Milligen; 7. Transfers and fluxes of wind kinetic energy between orthogonal wavelet components during atmospheric blocking A. Fournier; 8. Wavelets in atomic physics and in solid state physics J.-P. Antoine, Ph. Antoine and B. Piraux; 9. The thermodynamics of fractals revisited with wavelets A. Arneodo, E. Bacry and J. F. Muzy; 10. Wavelets in medicine and physiology P. Ch. Ivanov, A. L. Goldberger, S. Havlin, C.-K. Peng, M. G. Rosenblum and H. E. Stanley; 11. Wavelet dimension and time evolution Ch.-A. Guérin and M. Holschneider.

Wavelets in Physics

NASA Astrophysics Data System (ADS)

van den Berg, J. C.

1999-08-01

A guided tour J. C. van den Berg; 1. Wavelet analysis, a new tool in physics J.-P. Antoine; 2. The 2-D wavelet transform, physical applications J.-P. Antoine; 3. Wavelets and astrophysical applications A. Bijaoui; 4. Turbulence analysis, modelling and computing using wavelets M. Farge, N. K.-R. Kevlahan, V. Perrier and K. Schneider; 5. Wavelets and detection of coherent structures in fluid turbulence L. Hudgins and J. H. Kaspersen; 6. Wavelets, non-linearity and turbulence in fusion plasmas B. Ph. van Milligen; 7. Transfers and fluxes of wind kinetic energy between orthogonal wavelet components during atmospheric blocking A. Fournier; 8. Wavelets in atomic physics and in solid state physics J.-P. Antoine, Ph. Antoine and B. Piraux; 9. The thermodynamics of fractals revisited with wavelets A. Arneodo, E. Bacry and J. F. Muzy; 10. Wavelets in medicine and physiology P. Ch. Ivanov, A. L. Goldberger, S. Havlin, C.-K. Peng, M. G. Rosenblum and H. E. Stanley; 11. Wavelet dimension and time evolution Ch.-A. Guérin and M. Holschneider.

The Next Era: Deep Learning in Pharmaceutical Research.

PubMed

Ekins, Sean

2016-11-01

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule's properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique.

Prediction of mortality after radical cystectomy for bladder cancer by machine learning techniques.

PubMed

Wang, Guanjin; Lam, Kin-Man; Deng, Zhaohong; Choi, Kup-Sze

2015-08-01

Bladder cancer is a common cancer in genitourinary malignancy. For muscle invasive bladder cancer, surgical removal of the bladder, i.e. radical cystectomy, is in general the definitive treatment which, unfortunately, carries significant morbidities and mortalities. Accurate prediction of the mortality of radical cystectomy is therefore needed. Statistical methods have conventionally been used for this purpose, despite the complex interactions of high-dimensional medical data. Machine learning has emerged as a promising technique for handling high-dimensional data, with increasing application in clinical decision support, e.g. cancer prediction and prognosis. Its ability to reveal the hidden nonlinear interactions and interpretable rules between dependent and independent variables is favorable for constructing models of effective generalization performance. In this paper, seven machine learning methods are utilized to predict the 5-year mortality of radical cystectomy, including back-propagation neural network (BPN), radial basis function (RBFN), extreme learning machine (ELM), regularized ELM (RELM), support vector machine (SVM), naive Bayes (NB) classifier and k-nearest neighbour (KNN), on a clinicopathological dataset of 117 patients of the urology unit of a hospital in Hong Kong. The experimental results indicate that RELM achieved the highest average prediction accuracy of 0.8 at a fast learning speed. The research findings demonstrate the potential of applying machine learning techniques to support clinical decision making. Copyright © 2015 Elsevier Ltd. All rights reserved.

The application of machine vision in fire protection system

NASA Astrophysics Data System (ADS)

Rong, Jiang

2018-04-01

Based on the previous research, this paper introduces the theory of wavelet, collects the situation through the video system, and calculates the key information needed in the fire protection system. That is, through the algorithm to collect the information, according to the flame color characteristics and smoke characteristics were extracted, and as the characteristic information corresponding processing. Alarm system set the corresponding alarm threshold, when more than this alarm threshold, the system will alarm. This combination of flame color characteristics and smoke characteristics of the fire method not only improve the accuracy of judgment, but also improve the efficiency of judgments. Experiments show that the scheme is feasible.

MARTI: man-machine animation real-time interface

NASA Astrophysics Data System (ADS)

Jones, Christian M.; Dlay, Satnam S.

1997-05-01

The research introduces MARTI (man-machine animation real-time interface) for the realization of natural human-machine interfacing. The system uses simple vocal sound-tracks of human speakers to provide lip synchronization of computer graphical facial models. We present novel research in a number of engineering disciplines, which include speech recognition, facial modeling, and computer animation. This interdisciplinary research utilizes the latest, hybrid connectionist/hidden Markov model, speech recognition system to provide very accurate phone recognition and timing for speaker independent continuous speech, and expands on knowledge from the animation industry in the development of accurate facial models and automated animation. The research has many real-world applications which include the provision of a highly accurate and 'natural' man-machine interface to assist user interactions with computer systems and communication with one other using human idiosyncrasies; a complete special effects and animation toolbox providing automatic lip synchronization without the normal constraints of head-sets, joysticks, and skilled animators; compression of video data to well below standard telecommunication channel bandwidth for video communications and multi-media systems; assisting speech training and aids for the handicapped; and facilitating player interaction for 'video gaming' and 'virtual worlds.' MARTI has introduced a new level of realism to man-machine interfacing and special effect animation which has been previously unseen.

Hum-mPLoc 3.0: prediction enhancement of human protein subcellular localization through modeling the hidden correlations of gene ontology and functional domain features.

PubMed

Zhou, Hang; Yang, Yang; Shen, Hong-Bin

2017-03-15

Protein subcellular localization prediction has been an important research topic in computational biology over the last decade. Various automatic methods have been proposed to predict locations for large scale protein datasets, where statistical machine learning algorithms are widely used for model construction. A key step in these predictors is encoding the amino acid sequences into feature vectors. Many studies have shown that features extracted from biological domains, such as gene ontology and functional domains, can be very useful for improving the prediction accuracy. However, domain knowledge usually results in redundant features and high-dimensional feature spaces, which may degenerate the performance of machine learning models. In this paper, we propose a new amino acid sequence-based human protein subcellular location prediction approach Hum-mPLoc 3.0, which covers 12 human subcellular localizations. The sequences are represented by multi-view complementary features, i.e. context vocabulary annotation-based gene ontology (GO) terms, peptide-based functional domains, and residue-based statistical features. To systematically reflect the structural hierarchy of the domain knowledge bases, we propose a novel feature representation protocol denoted as HCM (Hidden Correlation Modeling), which will create more compact and discriminative feature vectors by modeling the hidden correlations between annotation terms. Experimental results on four benchmark datasets show that HCM improves prediction accuracy by 5-11% and F 1 by 8-19% compared with conventional GO-based methods. A large-scale application of Hum-mPLoc 3.0 on the whole human proteome reveals proteins co-localization preferences in the cell. www.csbio.sjtu.edu.cn/bioinf/Hum-mPLoc3/. hbshen@sjtu.edu.cn. Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Application of Deep Learning and Supervised Learning Methods to Recognize Nonlinear Hidden Pattern in Water Stress Levels from Spatiotemporal Datasets across Rural and Urban US Counties

NASA Astrophysics Data System (ADS)

Eisenhart, T.; Josset, L.; Rising, J. A.; Devineni, N.; Lall, U.

2017-12-01

In the wake of recent water crises, the need to understand and predict the risk of water stress in urban and rural areas has grown. This understanding has the potential to improve decision making in public resource management, policy making, risk management and investment decisions. Assuming an underlying relationship between urban and rural water stress and observable features, we apply Deep Learning and Supervised Learning models to uncover hidden nonlinear patterns from spatiotemporal datasets. Results of interest includes prediction accuracy on extreme categories (i.e. urban areas highly prone to water stress) and not solely the average risk for urban or rural area, which adds complexity to the tuning of model parameters. We first label urban water stressed counties using annual water quality violations and compile a comprehensive spatiotemporal dataset that captures the yearly evolution of climatic, demographic and economic factors of more than 3,000 US counties over the 1980-2010 period. As county-level data reporting is not done on a yearly basis, we test multiple imputation methods to get around the issue of missing data. Using Python libraries, TensorFlow and scikit-learn, we apply and compare the ability of, amongst other methods, Recurrent Neural Networks (testing both LSTM and GRU cells), Convolutional Neural Networks and Support Vector Machines to predict urban water stress. We evaluate the performance of those models over multiple time spans and combine methods to diminish the risk of overfitting and increase prediction power on test sets. This methodology seeks to identify hidden nonlinear patterns to assess the predominant data features that influence urban and rural water stress. Results from this application at the national scale will assess the performance of deep learning models to predict water stress risk areas across all US counties and will highlight a predominant Machine Learning method for modeling water stress risk using spatiotemporal data.

Understanding overlay signatures using machine learning on non-lithography context information

NASA Astrophysics Data System (ADS)

Overcast, Marshall; Mellegaard, Corey; Daniel, David; Habets, Boris; Erley, Georg; Guhlemann, Steffen; Thrun, Xaver; Buhl, Stefan; Tottewitz, Steven

2018-03-01

Overlay errors between two layers can be caused by non-lithography processes. While these errors can be compensated by the run-to-run system, such process and tool signatures are not always stable. In order to monitor the impact of non-lithography context on overlay at regular intervals, a systematic approach is needed. Using various machine learning techniques, significant context parameters that relate to deviating overlay signatures are automatically identified. Once the most influential context parameters are found, a run-to-run simulation is performed to see how much improvement can be obtained. The resulting analysis shows good potential for reducing the influence of hidden context parameters on overlay performance. Non-lithographic contexts are significant contributors, and their automatic detection and classification will enable the overlay roadmap, given the corresponding control capabilities.

Learning algorithm in restricted Boltzmann machines using Kullback-Leibler importance estimation procedure

NASA Astrophysics Data System (ADS)

Yasuda, Muneki; Sakurai, Tetsuharu; Tanaka, Kazuyuki

Restricted Boltzmann machines (RBMs) are bipartite structured statistical neural networks and consist of two layers. One of them is a layer of visible units and the other one is a layer of hidden units. In each layer, any units do not connect to each other. RBMs have high flexibility and rich structure and have been expected to applied to various applications, for example, image and pattern recognitions, face detections and so on. However, most of computational models in RBMs are intractable and often belong to the class of NP-hard problem. In this paper, in order to construct a practical learning algorithm for them, we employ the Kullback-Leibler Importance Estimation Procedure (KLIEP) to RBMs, and give a new scheme of practical approximate learning algorithm for RBMs based on the KLIEP.

Neural architecture design based on extreme learning machine.

PubMed

Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

2013-12-01

Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

Enhancing seismic P phase arrival picking based on wavelet denoising and kurtosis picker

NASA Astrophysics Data System (ADS)

Shang, Xueyi; Li, Xibing; Weng, Lei

2018-01-01

P phase arrival picking of weak signals is still challenging in seismology. A wavelet denoising is proposed to enhance seismic P phase arrival picking, and the kurtosis picker is applied on the wavelet-denoised signal to identify P phase arrival. It has been called the WD-K picker. The WD-K picker, which is different from those traditional wavelet-based pickers on the basis of a single wavelet component or certain main wavelet components, takes full advantage of the reconstruction of main detail wavelet components and the approximate wavelet component. The proposed WD-K picker considers more wavelet components and presents a better P phase arrival feature. The WD-K picker has been evaluated on 500 micro-seismic signals recorded in the Chinese Yongshaba mine. The comparison between the WD-K pickings and manual pickings shows the good picking accuracy of the WD-K picker. Furthermore, the WD-K picking performance has been compared with the main detail wavelet component combining-based kurtosis (WDC-K) picker, the single wavelet component-based kurtosis (SW-K) picker, and certain main wavelet component-based maximum kurtosis (MMW-K) picker. The comparison has demonstrated that the WD-K picker has better picking accuracy than the other three-wavelet and kurtosis-based pickers, thus showing the enhanced ability of wavelet denoising.

Accurate modeling of switched reluctance machine based on hybrid trained WNN

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

Song, Shoujun, E-mail: sunnyway@nwpu.edu.cn; Ge, Lefei; Ma, Shaojie

2014-04-15

According to the strong nonlinear electromagnetic characteristics of switched reluctance machine (SRM), a novel accurate modeling method is proposed based on hybrid trained wavelet neural network (WNN) which combines improved genetic algorithm (GA) with gradient descent (GD) method to train the network. In the novel method, WNN is trained by GD method based on the initial weights obtained per improved GA optimization, and the global parallel searching capability of stochastic algorithm and local convergence speed of deterministic algorithm are combined to enhance the training accuracy, stability and speed. Based on the measured electromagnetic characteristics of a 3-phase 12/8-pole SRM, themore » nonlinear simulation model is built by hybrid trained WNN in Matlab. The phase current and mechanical characteristics from simulation under different working conditions meet well with those from experiments, which indicates the accuracy of the model for dynamic and static performance evaluation of SRM and verifies the effectiveness of the proposed modeling method.« less

Tool Condition Monitoring and Remaining Useful Life Prognostic Based on a Wireless Sensor in Dry Milling Operations

PubMed Central

Zhang, Cunji; Yao, Xifan; Zhang, Jianming; Jin, Hong

2016-01-01

Tool breakage causes losses of surface polishing and dimensional accuracy for machined part, or possible damage to a workpiece or machine. Tool Condition Monitoring (TCM) is considerably vital in the manufacturing industry. In this paper, an indirect TCM approach is introduced with a wireless triaxial accelerometer. The vibrations in the three vertical directions (x, y and z) are acquired during milling operations, and the raw signals are de-noised by wavelet analysis. These features of de-noised signals are extracted in the time, frequency and time–frequency domains. The key features are selected based on Pearson’s Correlation Coefficient (PCC). The Neuro-Fuzzy Network (NFN) is adopted to predict the tool wear and Remaining Useful Life (RUL). In comparison with Back Propagation Neural Network (BPNN) and Radial Basis Function Network (RBFN), the results show that the NFN has the best performance in the prediction of tool wear and RUL. PMID:27258277

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

Hudgins, L.H.

After a brief review of the elementary properties of Fourier Transforms, the Wavelet Transform is defined in Part I. Basic results are given for admissable wavelets. The Multiresolution Analysis, or MRA (a mathematical structure which unifies a large class of wavelets with Quadrature Mirror Filters) is then introduced. Some fundamental aspects of wavelet design are then explored. The Discrete Wavelet Transform is discussed and, in the context of an MRA, is seen to supply a Fast Wavelet Transform which competes with the Fast Fourier Transform for efficiency. In Part II, the Wavelet Transform is developed in terms of the scalemore » number variable s instead of the scale length variable a where a = 1/s. Basic results such as the admissibility condition, conservation of energy, and the reconstruction theorem are proven in this context. After reviewing some motivation for the usual Fourier power spectrum, a definition is given for the wavelet power spectrum. This `spectral density` is then intepreted in the context of spectral estimation theory. Parseval`s theorem for Wavelets then leads naturally to the Wavelet Cross Spectrum, Wavelet Cospectrum, and Wavelet Quadrature Spectrum. Wavelet Transforms are then applied in Part III to the analysis of atmospheric turbulence. Data collected over the ocean is examined in the wavelet transform domain for underlying structure. A brief overview of atmospheric turbulence is provided. Then the overall method of applying Wavelet Transform techniques to time series data is described. A trace study is included, showing some of the aspects of choosing the computational algorithm, and selection of a specific analyzing wavelet. A model for generating synthetic turbulence data is developed, and seen to yield useful results in comparing with real data for structural transitions. Results from the theory of Wavelet Spectral Estimation and Wavelength Cross-Transforms are applied to studying the momentum transport and the heat flux.« less

Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach.

PubMed

Hussain, Lal

2018-06-01

Epilepsy is a neurological disorder produced due to abnormal excitability of neurons in the brain. The research reveals that brain activity is monitored through electroencephalogram (EEG) of patients suffered from seizure to detect the epileptic seizure. The performance of EEG detection based epilepsy require feature extracting strategies. In this research, we have extracted varying features extracting strategies based on time and frequency domain characteristics, nonlinear, wavelet based entropy and few statistical features. A deeper study was undertaken using novel machine learning classifiers by considering multiple factors. The support vector machine kernels are evaluated based on multiclass kernel and box constraint level. Likewise, for K-nearest neighbors (KNN), we computed the different distance metrics, Neighbor weights and Neighbors. Similarly, the decision trees we tuned the paramours based on maximum splits and split criteria and ensemble classifiers are evaluated based on different ensemble methods and learning rate. For training/testing tenfold Cross validation was employed and performance was evaluated in form of TPR, NPR, PPV, accuracy and AUC. In this research, a deeper analysis approach was performed using diverse features extracting strategies using robust machine learning classifiers with more advanced optimal options. Support Vector Machine linear kernel and KNN with City block distance metric give the overall highest accuracy of 99.5% which was higher than using the default parameters for these classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at different kernel scales using SVM. Additionally, the K-nearest neighbors with inverse squared distance weight give higher performance at different Neighbors. Moreover, to distinguish the postictal heart rate oscillations from epileptic ictal subjects, and highest performance of 100% was obtained using different machine learning classifiers.

Wavelet transforms with discrete-time continuous-dilation wavelets

NASA Astrophysics Data System (ADS)

Zhao, Wei; Rao, Raghuveer M.

1999-03-01

Wavelet constructions and transforms have been confined principally to the continuous-time domain. Even the discrete wavelet transform implemented through multirate filter banks is based on continuous-time wavelet functions that provide orthogonal or biorthogonal decompositions. This paper provides a novel wavelet transform construction based on the definition of discrete-time wavelets that can undergo continuous parameter dilations. The result is a transformation that has the advantage of discrete-time or digital implementation while circumventing the problem of inadequate scaling resolution seen with conventional dyadic or M-channel constructions. Examples of constructing such wavelets are presented.

Overview of existing algorithms for emotion classification. Uncertainties in evaluations of accuracies.

NASA Astrophysics Data System (ADS)

Avetisyan, H.; Bruna, O.; Holub, J.

2016-11-01

A numerous techniques and algorithms are dedicated to extract emotions from input data. In our investigation it was stated that emotion-detection approaches can be classified into 3 following types: Keyword based / lexical-based, learning based, and hybrid. The most commonly used techniques, such as keyword-spotting method, Support Vector Machines, Naïve Bayes Classifier, Hidden Markov Model and hybrid algorithms, have impressive results in this sphere and can reach more than 90% determining accuracy.

Prognosis of Electrical Faults in Permanent Magnet AC Machines using the Hidden Markov Model

DTIC Science & Technology

2010-11-10

time resolution and high frequency resolution Tiling is variable Wigner Ville Distribution Defined as W (t, ω) = ∫ s(t + τ 2 )s∗(t − τ 2 )e−jωτdτ...smoothed version of the Wigner distribution Amount of smoothing is controlled by σ Smoothing comes with a tradeoff of reduced resolution UNCLAS: Dist A...the Wigner or Choi-Williams distributions Although for Wigner and Choi-Williams distributions the probabilities are close for the early fault

Unmanned Aerial Vehicle Flight Test Approval Process and Its Implications: A Methodological Approach to Capture and Evaluate Hidden Costs and Value in the Overall Process

DTIC Science & Technology

2012-03-22

world’s first powered and controlled flying machine. Numerous flight designs and tests were done by scientists, engineers, and flight enthusiasts...conceptual flight and preliminary designs before they could control the craft with three-axis control and the correct airfoil design . These pioneers...analysis support. Although wind tunnel testing can provide data to predict and develop control surface designs , few SUAV operators opt to utilize wind

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

A novel strategy for classifying the output from an in silico vaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms.

PubMed

Goodswen, Stephen J; Kennedy, Paul J; Ellis, John T

2013-11-02

An in silico vaccine discovery pipeline for eukaryotic pathogens typically consists of several computational tools to predict protein characteristics. The aim of the in silico approach to discovering subunit vaccines is to use predicted characteristics to identify proteins which are worthy of laboratory investigation. A major challenge is that these predictions are inherent with hidden inaccuracies and contradictions. This study focuses on how to reduce the number of false candidates using machine learning algorithms rather than relying on expensive laboratory validation. Proteins from Toxoplasma gondii, Plasmodium sp., and Caenorhabditis elegans were used as training and test datasets. The results show that machine learning algorithms can effectively distinguish expected true from expected false vaccine candidates (with an average sensitivity and specificity of 0.97 and 0.98 respectively), for proteins observed to induce immune responses experimentally. Vaccine candidates from an in silico approach can only be truly validated in a laboratory. Given any in silico output and appropriate training data, the number of false candidates allocated for validation can be dramatically reduced using a pool of machine learning algorithms. This will ultimately save time and money in the laboratory.

A novel strategy for classifying the output from an in silico vaccine discovery pipeline for eukaryotic pathogens using machine learning algorithms

PubMed Central

2013-01-01

Background An in silico vaccine discovery pipeline for eukaryotic pathogens typically consists of several computational tools to predict protein characteristics. The aim of the in silico approach to discovering subunit vaccines is to use predicted characteristics to identify proteins which are worthy of laboratory investigation. A major challenge is that these predictions are inherent with hidden inaccuracies and contradictions. This study focuses on how to reduce the number of false candidates using machine learning algorithms rather than relying on expensive laboratory validation. Proteins from Toxoplasma gondii, Plasmodium sp., and Caenorhabditis elegans were used as training and test datasets. Results The results show that machine learning algorithms can effectively distinguish expected true from expected false vaccine candidates (with an average sensitivity and specificity of 0.97 and 0.98 respectively), for proteins observed to induce immune responses experimentally. Conclusions Vaccine candidates from an in silico approach can only be truly validated in a laboratory. Given any in silico output and appropriate training data, the number of false candidates allocated for validation can be dramatically reduced using a pool of machine learning algorithms. This will ultimately save time and money in the laboratory. PMID:24180526

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.

Time-frequency analysis of phonocardiogram signals using wavelet transform: a comparative study.

PubMed

Ergen, Burhan; Tatar, Yetkin; Gulcur, Halil Ozcan

2012-01-01

Analysis of phonocardiogram (PCG) signals provides a non-invasive means to determine the abnormalities caused by cardiovascular system pathology. In general, time-frequency representation (TFR) methods are used to study the PCG signal because it is one of the non-stationary bio-signals. The continuous wavelet transform (CWT) is especially suitable for the analysis of non-stationary signals and to obtain the TFR, due to its high resolution, both in time and in frequency and has recently become a favourite tool. It decomposes a signal in terms of elementary contributions called wavelets, which are shifted and dilated copies of a fixed mother wavelet function, and yields a joint TFR. Although the basic characteristics of the wavelets are similar, each type of the wavelets produces a different TFR. In this study, eight real types of the most known wavelets are examined on typical PCG signals indicating heart abnormalities in order to determine the best wavelet to obtain a reliable TFR. For this purpose, the wavelet energy and frequency spectrum estimations based on the CWT and the spectra of the chosen wavelets were compared with the energy distribution and the autoregressive frequency spectra in order to determine the most suitable wavelet. The results show that Morlet wavelet is the most reliable wavelet for the time-frequency analysis of PCG signals.

Wavelets and distributed approximating functionals

NASA Astrophysics Data System (ADS)

Wei, G. W.; Kouri, D. J.; Hoffman, D. K.

1998-07-01

A general procedure is proposed for constructing father and mother wavelets that have excellent time-frequency localization and can be used to generate entire wavelet families for use as wavelet transforms. One interesting feature of our father wavelets (scaling functions) is that they belong to a class of generalized delta sequences, which we refer to as distributed approximating functionals (DAFs). We indicate this by the notation wavelet-DAFs. Correspondingly, the mother wavelets generated from these wavelet-DAFs are appropriately called DAF-wavelets. Wavelet-DAFs can be regarded as providing a pointwise (localized) spectral method, which furnishes a bridge between the traditional global methods and local methods for solving partial differential equations. They are shown to provide extremely accurate numerical solutions for a number of nonlinear partial differential equations, including the Korteweg-de Vries (KdV) equation, for which a previous method has encountered difficulties (J. Comput. Phys. 132 (1997) 233).

Estimating mental fatigue based on electroencephalogram and heart rate variability

NASA Astrophysics Data System (ADS)

Zhang, Chong; Yu, Xiaolin

2010-01-01

The effects of long term mental arithmetic task on psychology are investigated by subjective self-reporting measures and action performance test. Based on electroencephalogram (EEG) and heart rate variability (HRV), the impacts of prolonged cognitive activity on central nervous system and autonomic nervous system are observed and analyzed. Wavelet packet parameters of EEG and power spectral indices of HRV are combined to estimate the change of mental fatigue. Then wavelet packet parameters of EEG which change significantly are extracted as the features of brain activity in different mental fatigue state, support vector machine (SVM) algorithm is applied to differentiate two mental fatigue states. The experimental results show that long term mental arithmetic task induces the mental fatigue. The wavelet packet parameters of EEG and power spectral indices of HRV are strongly correlated with mental fatigue. The predominant activity of autonomic nervous system of subjects turns to the sympathetic activity from parasympathetic activity after the task. Moreover, the slow waves of EEG increase, the fast waves of EEG and the degree of disorder of brain decrease compared with the pre-task. The SVM algorithm can effectively differentiate two mental fatigue states, which achieves the maximum classification accuracy (91%). The SVM algorithm could be a promising tool for the evaluation of mental fatigue. Fatigue, especially mental fatigue, is a common phenomenon in modern life, is a persistent occupational hazard for professional. Mental fatigue is usually accompanied with a sense of weariness, reduced alertness, and reduced mental performance, which would lead the accidents in life, decrease productivity in workplace and harm the health. Therefore, the evaluation of mental fatigue is important for the occupational risk protection, productivity, and occupational health.

Automatic T1 bladder tumor detection by using wavelet analysis in cystoscopy images

NASA Astrophysics Data System (ADS)

Freitas, Nuno R.; Vieira, Pedro M.; Lima, Estevão; Lima, Carlos S.

2018-02-01

Correct classification of cystoscopy images depends on the interpreter’s experience. Bladder cancer is a common lesion that can only be confirmed by biopsying the tissue, therefore, the automatic identification of tumors plays a significant role in early stage diagnosis and its accuracy. To our best knowledge, the use of white light cystoscopy images for bladder tumor diagnosis has not been reported so far. In this paper, a texture analysis based approach is proposed for bladder tumor diagnosis presuming that tumors change in tissue texture. As is well accepted by the scientific community, texture information is more present in the medium to high frequency range which can be selected by using a discrete wavelet transform (DWT). Tumor enhancement can be improved by using automatic segmentation, since a mixing with normal tissue is avoided under ideal conditions. The segmentation module proposed in this paper takes advantage of the wavelet decomposition tree to discard poor texture information in such a way that both steps of the proposed algorithm segmentation and classification share the same focus on texture. Multilayer perceptron and a support vector machine with a stratified ten-fold cross-validation procedure were used for classification purposes by using the hue-saturation-value (HSV), red-green-blue, and CIELab color spaces. Performances of 91% in sensitivity and 92.9% in specificity were obtained regarding HSV color by using both preprocessing and classification steps based on the DWT. The proposed method can achieve good performance on identifying bladder tumor frames. These promising results open the path towards a deeper study regarding the applicability of this algorithm in computer aided diagnosis.

Detecting Pilot's Engagement Using fNIRS Connectivity Features in an Automated vs. Manual Landing Scenario

PubMed Central

Verdière, Kevin J.; Roy, Raphaëlle N.; Dehais, Frédéric

2018-01-01

Monitoring pilot's mental states is a relevant approach to mitigate human error and enhance human machine interaction. A promising brain imaging technique to perform such a continuous measure of human mental state under ecological settings is Functional Near-InfraRed Spectroscopy (fNIRS). However, to our knowledge no study has yet assessed the potential of fNIRS connectivity metrics as long as passive Brain Computer Interfaces (BCI) are concerned. Therefore, we designed an experimental scenario in a realistic simulator in which 12 pilots had to perform landings under two contrasted levels of engagement (manual vs. automated). The collected data were used to benchmark the performance of classical oxygenation features (i.e., Average, Peak, Variance, Skewness, Kurtosis, Area Under the Curve, and Slope) and connectivity features (i.e., Covariance, Pearson's, and Spearman's Correlation, Spectral Coherence, and Wavelet Coherence) to discriminate these two landing conditions. Classification performance was obtained by using a shrinkage Linear Discriminant Analysis (sLDA) and a stratified cross validation using each feature alone or by combining them. Our findings disclosed that the connectivity features performed significantly better than the classical concentration metrics with a higher accuracy for the wavelet coherence (average: 65.3/59.9 %, min: 45.3/45.0, max: 80.5/74.7 computed for HbO/HbR signals respectively). A maximum classification performance was obtained by combining the area under the curve with the wavelet coherence (average: 66.9/61.6 %, min: 57.3/44.8, max: 80.0/81.3 computed for HbO/HbR signals respectively). In a general manner all connectivity measures allowed an efficient classification when computed over HbO signals. Those promising results provide methodological cues for further implementation of fNIRS-based passive BCIs. PMID:29422841

Influence of pansharpening techniques in obtaining accurate vegetation thematic maps

NASA Astrophysics Data System (ADS)

Ibarrola-Ulzurrun, Edurne; Gonzalo-Martin, Consuelo; Marcello-Ruiz, Javier

2016-10-01

In last decades, there have been a decline in natural resources, becoming important to develop reliable methodologies for their management. The appearance of very high resolution sensors has offered a practical and cost-effective means for a good environmental management. In this context, improvements are needed for obtaining higher quality of the information available in order to get reliable classified images. Thus, pansharpening enhances the spatial resolution of the multispectral band by incorporating information from the panchromatic image. The main goal in the study is to implement pixel and object-based classification techniques applied to the fused imagery using different pansharpening algorithms and the evaluation of thematic maps generated that serve to obtain accurate information for the conservation of natural resources. A vulnerable heterogenic ecosystem from Canary Islands (Spain) was chosen, Teide National Park, and Worldview-2 high resolution imagery was employed. The classes considered of interest were set by the National Park conservation managers. 7 pansharpening techniques (GS, FIHS, HCS, MTF based, Wavelet `à trous' and Weighted Wavelet `à trous' through Fractal Dimension Maps) were chosen in order to improve the data quality with the goal to analyze the vegetation classes. Next, different classification algorithms were applied at pixel-based and object-based approach, moreover, an accuracy assessment of the different thematic maps obtained were performed. The highest classification accuracy was obtained applying Support Vector Machine classifier at object-based approach in the Weighted Wavelet `à trous' through Fractal Dimension Maps fused image. Finally, highlight the difficulty of the classification in Teide ecosystem due to the heterogeneity and the small size of the species. Thus, it is important to obtain accurate thematic maps for further studies in the management and conservation of natural resources.

Classifying vulnerability to sleep deprivation using baseline measures of psychomotor vigilance.

PubMed

Patanaik, Amiya; Kwoh, Chee Keong; Chua, Eric C P; Gooley, Joshua J; Chee, Michael W L

2015-05-01

To identify measures derived from baseline psychomotor vigilance task (PVT) performance that can reliably predict vulnerability to sleep deprivation. Subjects underwent total sleep deprivation and completed a 10-min PVT every 1-2 h in a controlled laboratory setting. Participants were categorized as vulnerable or resistant to sleep deprivation, based on a median split of lapses that occurred following sleep deprivation. Standard reaction time, drift diffusion model (DDM), and wavelet metrics were derived from PVT response times collected at baseline. A support vector machine model that incorporated maximum relevance and minimum redundancy feature selection and wrapper-based heuristics was used to classify subjects as vulnerable or resistant using rested data. Two academic sleep laboratories. Independent samples of 135 (69 women, age 18 to 25 y), and 45 (3 women, age 22 to 32 y) healthy adults. In both datasets, DDM measures, number of consecutive reaction times that differ by more than 250 ms, and two wavelet features were selected by the model as features predictive of vulnerability to sleep deprivation. Using the best set of features selected in each dataset, classification accuracy was 77% and 82% using fivefold stratified cross-validation, respectively. In both datasets, DDM measures, number of consecutive reaction times that differ by more than 250 ms, and two wavelet features were selected by the model as features predictive of vulnerability to sleep deprivation. Using the best set of features selected in each dataset, classification accuracy was 77% and 82% using fivefold stratified cross-validation, respectively. Despite differences in experimental conditions across studies, drift diffusion model parameters associated reliably with individual differences in performance during total sleep deprivation. These results demonstrate the utility of drift diffusion modeling of baseline performance in estimating vulnerability to psychomotor vigilance decline following sleep deprivation. © 2015 Associated Professional Sleep Societies, LLC.

Asymmetric author-topic model for knowledge discovering of big data in toxicogenomics.

PubMed

Chung, Ming-Hua; Wang, Yuping; Tang, Hailin; Zou, Wen; Basinger, John; Xu, Xiaowei; Tong, Weida

2015-01-01

The advancement of high-throughput screening technologies facilitates the generation of massive amount of biological data, a big data phenomena in biomedical science. Yet, researchers still heavily rely on keyword search and/or literature review to navigate the databases and analyses are often done in rather small-scale. As a result, the rich information of a database has not been fully utilized, particularly for the information embedded in the interactive nature between data points that are largely ignored and buried. For the past 10 years, probabilistic topic modeling has been recognized as an effective machine learning algorithm to annotate the hidden thematic structure of massive collection of documents. The analogy between text corpus and large-scale genomic data enables the application of text mining tools, like probabilistic topic models, to explore hidden patterns of genomic data and to the extension of altered biological functions. In this paper, we developed a generalized probabilistic topic model to analyze a toxicogenomics dataset that consists of a large number of gene expression data from the rat livers treated with drugs in multiple dose and time-points. We discovered the hidden patterns in gene expression associated with the effect of doses and time-points of treatment. Finally, we illustrated the ability of our model to identify the evidence of potential reduction of animal use.

Applying wavelet transforms to analyse aircraft-measured turbulence and turbulent fluxes in the atmospheric boundary layer over eastern Siberia

NASA Astrophysics Data System (ADS)

Strunin, M. A.; Hiyama, T.

2004-11-01

The wavelet spectral method was applied to aircraft-based measurements of atmospheric turbulence obtained during joint Russian-Japanese research on the atmospheric boundary layer near Yakutsk (eastern Siberia) in April-June 2000. Practical ways to apply Fourier and wavelet methods for aircraft-based turbulence data are described. Comparisons between Fourier and wavelet transform results are shown and they demonstrate, in conjunction with theoretical and experimental restrictions, that the Fourier transform method is not useful for studying non-homogeneous turbulence. The wavelet method is free from many disadvantages of Fourier analysis and can yield more informative results. Comparison of Fourier and Morlet wavelet spectra showed good agreement at high frequencies (small scales). The quality of the wavelet transform and corresponding software was estimated by comparing the original data with restored data constructed with an inverse wavelet transform. A Haar wavelet basis was inappropriate for the turbulence data; the mother wavelet function recommended in this study is the Morlet wavelet. Good agreement was also shown between variances and covariances estimated with different mathematical techniques, i.e. through non-orthogonal wavelet spectra and through eddy correlation methods.

High-performance wavelet engine

NASA Astrophysics Data System (ADS)

Taylor, Fred J.; Mellot, Jonathon D.; Strom, Erik; Koren, Iztok; Lewis, Michael P.

1993-11-01

Wavelet processing has shown great promise for a variety of image and signal processing applications. Wavelets are also among the most computationally expensive techniques in signal processing. It is demonstrated that a wavelet engine constructed with residue number system arithmetic elements offers significant advantages over commercially available wavelet accelerators based upon conventional arithmetic elements. Analysis is presented predicting the dynamic range requirements of the reported residue number system based wavelet accelerator.

Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks

PubMed Central

Jang, Hojin; Plis, Sergey M.; Calhoun, Vince D.; Lee, Jong-Hwan

2016-01-01

Feedforward deep neural networks (DNN), artificial neural networks with multiple hidden layers, have recently demonstrated a record-breaking performance in multiple areas of applications in computer vision and speech processing. Following the success, DNNs have been applied to neuroimaging modalities including functional/structural magnetic resonance imaging (MRI) and positron-emission tomography data. However, no study has explicitly applied DNNs to 3D whole-brain fMRI volumes and thereby extracted hidden volumetric representations of fMRI that are discriminative for a task performed as the fMRI volume was acquired. Our study applied fully connected feedforward DNN to fMRI volumes collected in four sensorimotor tasks (i.e., left-hand clenching, right-hand clenching, auditory attention, and visual stimulus) undertaken by 12 healthy participants. Using a leave-one-subject-out cross-validation scheme, a restricted Boltzmann machine-based deep belief network was pretrained and used to initialize weights of the DNN. The pretrained DNN was fine-tuned while systematically controlling weight-sparsity levels across hidden layers. Optimal weight-sparsity levels were determined from a minimum validation error rate of fMRI volume classification. Minimum error rates (mean ± standard deviation; %) of 6.9 (± 3.8) were obtained from the three-layer DNN with the sparsest condition of weights across the three hidden layers. These error rates were even lower than the error rates from the single-layer network (9.4 ± 4.6) and the two-layer network (7.4 ± 4.1). The estimated DNN weights showed spatial patterns that are remarkably task-specific, particularly in the higher layers. The output values of the third hidden layer represented distinct patterns/codes of the 3D whole-brain fMRI volume and encoded the information of the tasks as evaluated from representational similarity analysis. Our reported findings show the ability of the DNN to classify a single fMRI volume based on the extraction of hidden representations of fMRI volumes associated with tasks across multiple hidden layers. Our study may be beneficial to the automatic classification/diagnosis of neuropsychiatric and neurological diseases and prediction of disease severity and recovery in (pre-) clinical settings using fMRI volumes without requiring an estimation of activation patterns or ad hoc statistical evaluation. PMID:27079534

Task-specific feature extraction and classification of fMRI volumes using a deep neural network initialized with a deep belief network: Evaluation using sensorimotor tasks.

PubMed

Jang, Hojin; Plis, Sergey M; Calhoun, Vince D; Lee, Jong-Hwan

2017-01-15

Feedforward deep neural networks (DNNs), artificial neural networks with multiple hidden layers, have recently demonstrated a record-breaking performance in multiple areas of applications in computer vision and speech processing. Following the success, DNNs have been applied to neuroimaging modalities including functional/structural magnetic resonance imaging (MRI) and positron-emission tomography data. However, no study has explicitly applied DNNs to 3D whole-brain fMRI volumes and thereby extracted hidden volumetric representations of fMRI that are discriminative for a task performed as the fMRI volume was acquired. Our study applied fully connected feedforward DNN to fMRI volumes collected in four sensorimotor tasks (i.e., left-hand clenching, right-hand clenching, auditory attention, and visual stimulus) undertaken by 12 healthy participants. Using a leave-one-subject-out cross-validation scheme, a restricted Boltzmann machine-based deep belief network was pretrained and used to initialize weights of the DNN. The pretrained DNN was fine-tuned while systematically controlling weight-sparsity levels across hidden layers. Optimal weight-sparsity levels were determined from a minimum validation error rate of fMRI volume classification. Minimum error rates (mean±standard deviation; %) of 6.9 (±3.8) were obtained from the three-layer DNN with the sparsest condition of weights across the three hidden layers. These error rates were even lower than the error rates from the single-layer network (9.4±4.6) and the two-layer network (7.4±4.1). The estimated DNN weights showed spatial patterns that are remarkably task-specific, particularly in the higher layers. The output values of the third hidden layer represented distinct patterns/codes of the 3D whole-brain fMRI volume and encoded the information of the tasks as evaluated from representational similarity analysis. Our reported findings show the ability of the DNN to classify a single fMRI volume based on the extraction of hidden representations of fMRI volumes associated with tasks across multiple hidden layers. Our study may be beneficial to the automatic classification/diagnosis of neuropsychiatric and neurological diseases and prediction of disease severity and recovery in (pre-) clinical settings using fMRI volumes without requiring an estimation of activation patterns or ad hoc statistical evaluation. Copyright © 2016 Elsevier Inc. All rights reserved.

Fast DCNN based on FWT, intelligent dropout and layer skipping for image retrieval.

PubMed

ElAdel, Asma; Zaied, Mourad; Amar, Chokri Ben

2017-11-01

Deep Convolutional Neural Network (DCNN) can be marked as a powerful tool for object and image classification and retrieval. However, the training stage of such networks is highly consuming in terms of storage space and time. Also, the optimization is still a challenging subject. In this paper, we propose a fast DCNN based on Fast Wavelet Transform (FWT), intelligent dropout and layer skipping. The proposed approach led to improve the image retrieval accuracy as well as the searching time. This was possible thanks to three key advantages: First, the rapid way to compute the features using FWT. Second, the proposed intelligent dropout method is based on whether or not a unit is efficiently and not randomly selected. Third, it is possible to classify the image using efficient units of earlier layer(s) and skipping all the subsequent hidden layers directly to the output layer. Our experiments were performed on CIFAR-10 and MNIST datasets and the obtained results are very promising. Copyright © 2017 Elsevier Ltd. All rights reserved.

Wavelet tree structure based speckle noise removal for optical coherence tomography

NASA Astrophysics Data System (ADS)

Yuan, Xin; Liu, Xuan; Liu, Yang

2018-02-01

We report a new speckle noise removal algorithm in optical coherence tomography (OCT). Though wavelet domain thresholding algorithms have demonstrated superior advantages in suppressing noise magnitude and preserving image sharpness in OCT, the wavelet tree structure has not been investigated in previous applications. In this work, we propose an adaptive wavelet thresholding algorithm via exploiting the tree structure in wavelet coefficients to remove the speckle noise in OCT images. The threshold for each wavelet band is adaptively selected following a special rule to retain the structure of the image across different wavelet layers. Our results demonstrate that the proposed algorithm outperforms conventional wavelet thresholding, with significant advantages in preserving image features.

A Review of Intelligent Driving Style Analysis Systems and Related Artificial Intelligence Algorithms

PubMed Central

Meiring, Gys Albertus Marthinus; Myburgh, Hermanus Carel

2015-01-01

In this paper the various driving style analysis solutions are investigated. An in-depth investigation is performed to identify the relevant machine learning and artificial intelligence algorithms utilised in current driver behaviour and driving style analysis systems. This review therefore serves as a trove of information, and will inform the specialist and the student regarding the current state of the art in driver style analysis systems, the application of these systems and the underlying artificial intelligence algorithms applied to these applications. The aim of the investigation is to evaluate the possibilities for unique driver identification utilizing the approaches identified in other driver behaviour studies. It was found that Fuzzy Logic inference systems, Hidden Markov Models and Support Vector Machines consist of promising capabilities to address unique driver identification algorithms if model complexity can be reduced. PMID:26690164

A Review of Intelligent Driving Style Analysis Systems and Related Artificial Intelligence Algorithms.

PubMed

Meiring, Gys Albertus Marthinus; Myburgh, Hermanus Carel

2015-12-04

In this paper the various driving style analysis solutions are investigated. An in-depth investigation is performed to identify the relevant machine learning and artificial intelligence algorithms utilised in current driver behaviour and driving style analysis systems. This review therefore serves as a trove of information, and will inform the specialist and the student regarding the current state of the art in driver style analysis systems, the application of these systems and the underlying artificial intelligence algorithms applied to these applications. The aim of the investigation is to evaluate the possibilities for unique driver identification utilizing the approaches identified in other driver behaviour studies. It was found that Fuzzy Logic inference systems, Hidden Markov Models and Support Vector Machines consist of promising capabilities to address unique driver identification algorithms if model complexity can be reduced.

Study of Environmental Data Complexity using Extreme Learning Machine

NASA Astrophysics Data System (ADS)

Leuenberger, Michael; Kanevski, Mikhail

2017-04-01

The main goals of environmental data science using machine learning algorithm deal, in a broad sense, around the calibration, the prediction and the visualization of hidden relationship between input and output variables. In order to optimize the models and to understand the phenomenon under study, the characterization of the complexity (at different levels) should be taken into account. Therefore, the identification of the linear or non-linear behavior between input and output variables adds valuable information for the knowledge of the phenomenon complexity. The present research highlights and investigates the different issues that can occur when identifying the complexity (linear/non-linear) of environmental data using machine learning algorithm. In particular, the main attention is paid to the description of a self-consistent methodology for the use of Extreme Learning Machines (ELM, Huang et al., 2006), which recently gained a great popularity. By applying two ELM models (with linear and non-linear activation functions) and by comparing their efficiency, quantification of the linearity can be evaluated. The considered approach is accompanied by simulated and real high dimensional and multivariate data case studies. In conclusion, the current challenges and future development in complexity quantification using environmental data mining are discussed. References - Huang, G.-B., Zhu, Q.-Y., Siew, C.-K., 2006. Extreme learning machine: theory and applications. Neurocomputing 70 (1-3), 489-501. - Kanevski, M., Pozdnoukhov, A., Timonin, V., 2009. Machine Learning for Spatial Environmental Data. EPFL Press; Lausanne, Switzerland, p.392. - Leuenberger, M., Kanevski, M., 2015. Extreme Learning Machines for spatial environmental data. Computers and Geosciences 85, 64-73.

The Next Era: Deep Learning in Pharmaceutical Research

PubMed Central

Ekins, Sean

2016-01-01

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule’s properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique. PMID:27599991

A New Multivariate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering.

PubMed

Javed, Kamran; Gouriveau, Rafael; Zerhouni, Noureddine

2015-12-01

Prognostics is a core process of prognostics and health management (PHM) discipline, that estimates the remaining useful life (RUL) of a degrading machinery to optimize its service delivery potential. However, machinery operates in a dynamic environment and the acquired condition monitoring data are usually noisy and subject to a high level of uncertainty/unpredictability, which complicates prognostics. The complexity further increases, when there is absence of prior knowledge about ground truth (or failure definition). For such issues, data-driven prognostics can be a valuable solution without deep understanding of system physics. This paper contributes a new data-driven prognostics approach namely, an "enhanced multivariate degradation modeling," which enables modeling degrading states of machinery without assuming a homogeneous pattern. In brief, a predictability scheme is introduced to reduce the dimensionality of the data. Following that, the proposed prognostics model is achieved by integrating two new algorithms namely, the summation wavelet-extreme learning machine and subtractive-maximum entropy fuzzy clustering to show evolution of machine degradation by simultaneous predictions and discrete state estimation. The prognostics model is equipped with a dynamic failure threshold assignment procedure to estimate RUL in a realistic manner. To validate the proposition, a case study is performed on turbofan engines data from PHM challenge 2008 (NASA), and results are compared with recent publications.

Detection of segments with fetal QRS complex from abdominal maternal ECG recordings using support vector machine

NASA Astrophysics Data System (ADS)

Delgado, Juan A.; Altuve, Miguel; Nabhan Homsi, Masun

2015-12-01

This paper introduces a robust method based on the Support Vector Machine (SVM) algorithm to detect the presence of Fetal QRS (fQRS) complexes in electrocardiogram (ECG) recordings provided by the PhysioNet/CinC challenge 2013. ECG signals are first segmented into contiguous frames of 250 ms duration and then labeled in six classes. Fetal segments are tagged according to the position of fQRS complex within each one. Next, segment features extraction and dimensionality reduction are obtained by applying principal component analysis on Haar-wavelet transform. After that, two sub-datasets are generated to separate representative segments from atypical ones. Imbalanced class problem is dealt by applying sampling without replacement on each sub-dataset. Finally, two SVMs are trained and cross-validated using the two balanced sub-datasets separately. Experimental results show that the proposed approach achieves high performance rates in fetal heartbeats detection that reach up to 90.95% of accuracy, 92.16% of sensitivity, 88.51% of specificity, 94.13% of positive predictive value and 84.96% of negative predictive value. A comparative study is also carried out to show the performance of other two machine learning algorithms for fQRS complex estimation, which are K-nearest neighborhood and Bayesian network.

Critical object recognition in millimeter-wave images with robustness to rotation and scale.

PubMed

Mohammadzade, Hoda; Ghojogh, Benyamin; Faezi, Sina; Shabany, Mahdi

2017-06-01

Locating critical objects is crucial in various security applications and industries. For example, in security applications, such as in airports, these objects might be hidden or covered under shields or secret sheaths. Millimeter-wave images can be utilized to discover and recognize the critical objects out of the hidden cases without any health risk due to their non-ionizing features. However, millimeter-wave images usually have waves in and around the detected objects, making object recognition difficult. Thus, regular image processing and classification methods cannot be used for these images and additional pre-processings and classification methods should be introduced. This paper proposes a novel pre-processing method for canceling rotation and scale using principal component analysis. In addition, a two-layer classification method is introduced and utilized for recognition. Moreover, a large dataset of millimeter-wave images is collected and created for experiments. Experimental results show that a typical classification method such as support vector machines can recognize 45.5% of a type of critical objects at 34.2% false alarm rate (FAR), which is a drastically poor recognition. The same method within the proposed recognition framework achieves 92.9% recognition rate at 0.43% FAR, which indicates a highly significant improvement. The significant contribution of this work is to introduce a new method for analyzing millimeter-wave images based on machine vision and learning approaches, which is not yet widely noted in the field of millimeter-wave image analysis.

Wavelet-domain de-noising of OCT images of human brain malignant glioma

NASA Astrophysics Data System (ADS)

Dolganova, I. N.; Aleksandrova, P. V.; Beshplav, S.-I. T.; Chernomyrdin, N. V.; Dubyanskaya, E. N.; Goryaynov, S. A.; Kurlov, V. N.; Reshetov, I. V.; Potapov, A. A.; Tuchin, V. V.; Zaytsev, K. I.

2018-04-01

We have proposed a wavelet-domain de-noising technique for imaging of human brain malignant glioma by optical coherence tomography (OCT). It implies OCT image decomposition using the direct fast wavelet transform, thresholding of the obtained wavelet spectrum and further inverse fast wavelet transform for image reconstruction. By selecting both wavelet basis and thresholding procedure, we have found an optimal wavelet filter, which application improves differentiation of the considered brain tissue classes - i.e. malignant glioma and normal/intact tissue. Namely, it allows reducing the scattering noise in the OCT images and retaining signal decrement for each tissue class. Therefore, the observed results reveals the wavelet-domain de-noising as a prospective tool for improved characterization of biological tissue using the OCT.

Wavelet transforms as solutions of partial differential equations

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

Zweig, G.

This is the final report of a three-year, Laboratory Directed Research and Development (LDRD) project at Los Alamos National Laboratory (LANL). Wavelet transforms are useful in representing transients whose time and frequency structure reflect the dynamics of an underlying physical system. Speech sound, pressure in turbulent fluid flow, or engine sound in automobiles are excellent candidates for wavelet analysis. This project focused on (1) methods for choosing the parent wavelet for a continuous wavelet transform in pattern recognition applications and (2) the more efficient computation of continuous wavelet transforms by understanding the relationship between discrete wavelet transforms and discretized continuousmore » wavelet transforms. The most interesting result of this research is the finding that the generalized wave equation, on which the continuous wavelet transform is based, can be used to understand phenomena that relate to the process of hearing.« less

Wavelet Transforms using VTK-m

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

Li, Shaomeng; Sewell, Christopher Meyer

2016-09-27

These are a set of slides that deal with the topics of wavelet transforms using VTK-m. First, wavelets are discussed and detailed, then VTK-m is discussed and detailed, then wavelets and VTK-m are looked at from a performance comparison, then from an accuracy comparison, and finally lessons learned, conclusion, and what is next. Lessons learned are the following: Launching worklets is expensive; Natural logic of performing 2D wavelet transform: Repeat the same 1D wavelet transform on every row, repeat the same 1D wavelet transform on every column, invoke the 1D wavelet worklet every time: num_rows x num_columns; VTK-m approach ofmore » performing 2D wavelet transform: Create a worklet for 2D that handles both rows and columns, invoke this new worklet only one time; Fast calculation, but cannot reuse 1D implementations.« less

Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming.

PubMed

Wu, Stephen Gang; Wang, Yuxuan; Jiang, Wu; Oyetunde, Tolutola; Yao, Ruilian; Zhang, Xuehong; Shimizu, Kazuyuki; Tang, Yinjie J; Bao, Forrest Sheng

2016-04-01

13C metabolic flux analysis (13C-MFA) has been widely used to measure in vivo enzyme reaction rates (i.e., metabolic flux) in microorganisms. Mining the relationship between environmental and genetic factors and metabolic fluxes hidden in existing fluxomic data will lead to predictive models that can significantly accelerate flux quantification. In this paper, we present a web-based platform MFlux (http://mflux.org) that predicts the bacterial central metabolism via machine learning, leveraging data from approximately 100 13C-MFA papers on heterotrophic bacterial metabolisms. Three machine learning methods, namely Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree, were employed to study the sophisticated relationship between influential factors and metabolic fluxes. We performed a grid search of the best parameter set for each algorithm and verified their performance through 10-fold cross validations. SVM yields the highest accuracy among all three algorithms. Further, we employed quadratic programming to adjust flux profiles to satisfy stoichiometric constraints. Multiple case studies have shown that MFlux can reasonably predict fluxomes as a function of bacterial species, substrate types, growth rate, oxygen conditions, and cultivation methods. Due to the interest of studying model organism under particular carbon sources, bias of fluxome in the dataset may limit the applicability of machine learning models. This problem can be resolved after more papers on 13C-MFA are published for non-model species.

Rapid Prediction of Bacterial Heterotrophic Fluxomics Using Machine Learning and Constraint Programming

PubMed Central

Wu, Stephen Gang; Wang, Yuxuan; Jiang, Wu; Oyetunde, Tolutola; Yao, Ruilian; Zhang, Xuehong; Shimizu, Kazuyuki; Tang, Yinjie J.; Bao, Forrest Sheng

2016-01-01

13C metabolic flux analysis (13C-MFA) has been widely used to measure in vivo enzyme reaction rates (i.e., metabolic flux) in microorganisms. Mining the relationship between environmental and genetic factors and metabolic fluxes hidden in existing fluxomic data will lead to predictive models that can significantly accelerate flux quantification. In this paper, we present a web-based platform MFlux (http://mflux.org) that predicts the bacterial central metabolism via machine learning, leveraging data from approximately 100 13C-MFA papers on heterotrophic bacterial metabolisms. Three machine learning methods, namely Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), and Decision Tree, were employed to study the sophisticated relationship between influential factors and metabolic fluxes. We performed a grid search of the best parameter set for each algorithm and verified their performance through 10-fold cross validations. SVM yields the highest accuracy among all three algorithms. Further, we employed quadratic programming to adjust flux profiles to satisfy stoichiometric constraints. Multiple case studies have shown that MFlux can reasonably predict fluxomes as a function of bacterial species, substrate types, growth rate, oxygen conditions, and cultivation methods. Due to the interest of studying model organism under particular carbon sources, bias of fluxome in the dataset may limit the applicability of machine learning models. This problem can be resolved after more papers on 13C-MFA are published for non-model species. PMID:27092947

Naive scoring of human sleep based on a hidden Markov model of the electroencephalogram.

PubMed

Yaghouby, Farid; Modur, Pradeep; Sunderam, Sridhar

2014-01-01

Clinical sleep scoring involves tedious visual review of overnight polysomnograms by a human expert. Many attempts have been made to automate the process by training computer algorithms such as support vector machines and hidden Markov models (HMMs) to replicate human scoring. Such supervised classifiers are typically trained on scored data and then validated on scored out-of-sample data. Here we describe a methodology based on HMMs for scoring an overnight sleep recording without the benefit of a trained initial model. The number of states in the data is not known a priori and is optimized using a Bayes information criterion. When tested on a 22-subject database, this unsupervised classifier agreed well with human scores (mean of Cohen's kappa > 0.7). The HMM also outperformed other unsupervised classifiers (Gaussian mixture models, k-means, and linkage trees), that are capable of naive classification but do not model dynamics, by a significant margin (p < 0.05).

Strong convective storm nowcasting using a hybrid approach of convolutional neural network and hidden Markov model

NASA Astrophysics Data System (ADS)

Zhang, Wei; Jiang, Ling; Han, Lei

2018-04-01

Convective storm nowcasting refers to the prediction of the convective weather initiation, development, and decay in a very short term (typically 0 2 h) .Despite marked progress over the past years, severe convective storm nowcasting still remains a challenge. With the boom of machine learning, it has been well applied in various fields, especially convolutional neural network (CNN). In this paper, we build a servere convective weather nowcasting system based on CNN and hidden Markov model (HMM) using reanalysis meteorological data. The goal of convective storm nowcasting is to predict if there is a convective storm in 30min. In this paper, we compress the VDRAS reanalysis data to low-dimensional data by CNN as the observation vector of HMM, then obtain the development trend of strong convective weather in the form of time series. It shows that, our method can extract robust features without any artificial selection of features, and can capture the development trend of strong convective storm.

Wavelet denoising during optical coherence tomography of the prostate nerves using the complex wavelet transform.

PubMed

Chitchian, Shahab; Fiddy, Michael; Fried, Nathaniel M

2008-01-01

Preservation of the cavernous nerves during prostate cancer surgery is critical in preserving sexual function after surgery. Optical coherence tomography (OCT) of the prostate nerves has recently been studied for potential use in nerve-sparing prostate surgery. In this study, the discrete wavelet transform and complex dual-tree wavelet transform are implemented for wavelet shrinkage denoising in OCT images of the rat prostate. Applying the complex dual-tree wavelet transform provides improved results for speckle noise reduction in the OCT prostate image. Image quality metrics of the cavernous nerves and signal-to-noise ratio (SNR) were improved significantly using this complex wavelet denoising technique.

Optical phase distribution evaluation by using zero order Generalized Morse Wavelet

NASA Astrophysics Data System (ADS)

Kocahan, Özlem; Elmas, Merve Naz; Durmuş, ćaǧla; Coşkun, Emre; Tiryaki, Erhan; Özder, Serhat

2017-02-01

When determining the phase from the projected fringes by using continuous wavelet transform (CWT), selection of wavelet is an important step. A new wavelet for phase retrieval from the fringe pattern with the spatial carrier frequency in the x direction is presented. As a mother wavelet, zero order generalized Morse wavelet (GMW) is chosen because of the flexible spatial and frequency localization property, and it is exactly analytic. In this study, GMW method is explained and numerical simulations are carried out to show the validity of this technique for finding the phase distributions. Results for the Morlet and Paul wavelets are compared with the results of GMW analysis.

Comparisons between real and complex Gauss wavelet transform methods of three-dimensional shape reconstruction

NASA Astrophysics Data System (ADS)

Xu, Luopeng; Dan, Youquan; Wang, Qingyuan

2015-10-01

The continuous wavelet transform (CWT) introduces an expandable spatial and frequency window which can overcome the inferiority of localization characteristic in Fourier transform and windowed Fourier transform. The CWT method is widely applied in the non-stationary signal analysis field including optical 3D shape reconstruction with remarkable performance. In optical 3D surface measurement, the performance of CWT for optical fringe pattern phase reconstruction usually depends on the choice of wavelet function. A large kind of wavelet functions of CWT, such as Mexican Hat wavelet, Morlet wavelet, DOG wavelet, Gabor wavelet and so on, can be generated from Gauss wavelet function. However, so far, application of the Gauss wavelet transform (GWT) method (i.e. CWT with Gauss wavelet function) in optical profilometry is few reported. In this paper, the method using GWT for optical fringe pattern phase reconstruction is presented first and the comparisons between real and complex GWT methods are discussed in detail. The examples of numerical simulations are also given and analyzed. The results show that both the real GWT method along with a Hilbert transform and the complex GWT method can realize three-dimensional surface reconstruction; and the performance of reconstruction generally depends on the frequency domain appearance of Gauss wavelet functions. For the case of optical fringe pattern of large phase variation with position, the performance of real GWT is better than that of complex one due to complex Gauss series wavelets existing frequency sidelobes. Finally, the experiments are carried out and the experimental results agree well with our theoretical analysis.

Modern Approaches to the Computation of the Probability of Target Detection in Cluttered Environments

NASA Astrophysics Data System (ADS)

Meitzler, Thomas J.

The field of computer vision interacts with fields such as psychology, vision research, machine vision, psychophysics, mathematics, physics, and computer science. The focus of this thesis is new algorithms and methods for the computation of the probability of detection (Pd) of a target in a cluttered scene. The scene can be either a natural visual scene such as one sees with the naked eye (visual), or, a scene displayed on a monitor with the help of infrared sensors. The relative clutter and the temperature difference between the target and background (DeltaT) are defined and then used to calculate a relative signal -to-clutter ratio (SCR) from which the Pd is calculated for a target in a cluttered scene. It is shown how this definition can include many previous definitions of clutter and (DeltaT). Next, fuzzy and neural -fuzzy techniques are used to calculate the Pd and it is shown how these methods can give results that have a good correlation with experiment. The experimental design for actually measuring the Pd of a target by observers is described. Finally, wavelets are applied to the calculation of clutter and it is shown how this new definition of clutter based on wavelets can be used to compute the Pd of a target.

Application of texture analysis method for mammogram density classification

NASA Astrophysics Data System (ADS)

Nithya, R.; Santhi, B.

2017-07-01

Mammographic density is considered a major risk factor for developing breast cancer. This paper proposes an automated approach to classify breast tissue types in digital mammogram. The main objective of the proposed Computer-Aided Diagnosis (CAD) system is to investigate various feature extraction methods and classifiers to improve the diagnostic accuracy in mammogram density classification. Texture analysis methods are used to extract the features from the mammogram. Texture features are extracted by using histogram, Gray Level Co-Occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Difference Matrix (GLDM), Local Binary Pattern (LBP), Entropy, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), Gabor transform and trace transform. These extracted features are selected using Analysis of Variance (ANOVA). The features selected by ANOVA are fed into the classifiers to characterize the mammogram into two-class (fatty/dense) and three-class (fatty/glandular/dense) breast density classification. This work has been carried out by using the mini-Mammographic Image Analysis Society (MIAS) database. Five classifiers are employed namely, Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Experimental results show that ANN provides better performance than LDA, NB, KNN and SVM classifiers. The proposed methodology has achieved 97.5% accuracy for three-class and 99.37% for two-class density classification.

On the use of harmony search algorithm in the training of wavelet neural networks

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2015-10-01

Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.

Automatic quantification framework to detect cracks in teeth

PubMed Central

Shah, Hina; Hernandez, Pablo; Budin, Francois; Chittajallu, Deepak; Vimort, Jean-Baptiste; Walters, Rick; Mol, André; Khan, Asma; Paniagua, Beatriz

2018-01-01

Studies show that cracked teeth are the third most common cause for tooth loss in industrialized countries. If detected early and accurately, patients can retain their teeth for a longer time. Most cracks are not detected early because of the discontinuous symptoms and lack of good diagnostic tools. Currently used imaging modalities like Cone Beam Computed Tomography (CBCT) and intraoral radiography often have low sensitivity and do not show cracks clearly. This paper introduces a novel method that can detect, quantify, and localize cracks automatically in high resolution CBCT (hr-CBCT) scans of teeth using steerable wavelets and learning methods. These initial results were created using hr-CBCT scans of a set of healthy teeth and of teeth with simulated longitudinal cracks. The cracks were simulated using multiple orientations. The crack detection was trained on the most significant wavelet coefficients at each scale using a bagged classifier of Support Vector Machines. Our results show high discriminative specificity and sensitivity of this method. The framework aims to be automatic, reproducible, and open-source. Future work will focus on the clinical validation of the proposed techniques on different types of cracks ex-vivo. We believe that this work will ultimately lead to improved tracking and detection of cracks allowing for longer lasting healthy teeth. PMID:29769755

Fault Analysis of Space Station DC Power Systems-Using Neural Network Adaptive Wavelets to Detect Faults

NASA Technical Reports Server (NTRS)

Momoh, James A.; Wang, Yanchun; Dolce, James L.

1997-01-01

This paper describes the application of neural network adaptive wavelets for fault diagnosis of space station power system. The method combines wavelet transform with neural network by incorporating daughter wavelets into weights. Therefore, the wavelet transform and neural network training procedure become one stage, which avoids the complex computation of wavelet parameters and makes the procedure more straightforward. The simulation results show that the proposed method is very efficient for the identification of fault locations.

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.

Triangular Quantum Loop Topography for Machine Learning

NASA Astrophysics Data System (ADS)

Zhang, Yi; Kim, Eun-Ah

Despite rapidly growing interest in harnessing machine learning in the study of quantum many-body systems there has been little success in training neural networks to identify topological phases. The key challenge is in efficiently extracting essential information from the many-body Hamiltonian or wave function and turning the information into an image that can be fed into a neural network. When targeting topological phases, this task becomes particularly challenging as topological phases are defined in terms of non-local properties. Here we introduce triangular quantum loop (TQL) topography: a procedure of constructing a multi-dimensional image from the ''sample'' Hamiltonian or wave function using two-point functions that form triangles. Feeding the TQL topography to a fully-connected neural network with a single hidden layer, we demonstrate that the architecture can be effectively trained to distinguish Chern insulator and fractional Chern insulator from trivial insulators with high fidelity. Given the versatility of the TQL topography procedure that can handle different lattice geometries, disorder, interaction and even degeneracy our work paves the route towards powerful applications of machine learning in the study of topological quantum matters.

The impact of jackpots on EGM gambling behavior: a review.

PubMed

Rockloff, Matthew J; Hing, Nerilee

2013-12-01

This paper reviews literature on how jackpots influence Electronic Gaming Machine (EGM) gambling behaviour. Most of the available evidence addresses the motivational effect of the mere presence of EGM jackpots on play, as actual wins are relatively rare for individual gamblers. The review identifies a distinction between rational, biased and irrational motivations that attract people to EGM jackpots. The evidence suggests that EGM jackpots should generate additional consumption on EGMs above machines that do not have such lottery-like features. Rational motivations are likely to lead to consumer surplus, whereas biased and irrational motivations are likely to contribute to excessive consumption. Moreover, there is evidence that excessive gambling consumption is strongly associated with gambling-related harm. Future research should identify how the structural features of different types of jackpots; such as progressive, deterministic, hidden, mystery, linked and wide-area jackpots; may differentially appeal to rational, biased and irrational gambling motivations. Jackpots are common feature of EGM games, and therefore it is important to have a better understanding of how jackpot features influence play on the machines.

Comparison between deterministic and statistical wavelet estimation methods through predictive deconvolution: Seismic to well tie example from the North Sea

NASA Astrophysics Data System (ADS)

de Macedo, Isadora A. S.; da Silva, Carolina B.; de Figueiredo, J. J. S.; Omoboya, Bode

2017-01-01

Wavelet estimation as well as seismic-to-well tie procedures are at the core of every seismic interpretation workflow. In this paper we perform a comparative study of wavelet estimation methods for seismic-to-well tie. Two approaches to wavelet estimation are discussed: a deterministic estimation, based on both seismic and well log data, and a statistical estimation, based on predictive deconvolution and the classical assumptions of the convolutional model, which provides a minimum-phase wavelet. Our algorithms, for both wavelet estimation methods introduce a semi-automatic approach to determine the optimum parameters of deterministic wavelet estimation and statistical wavelet estimation and, further, to estimate the optimum seismic wavelets by searching for the highest correlation coefficient between the recorded trace and the synthetic trace, when the time-depth relationship is accurate. Tests with numerical data show some qualitative conclusions, which are probably useful for seismic inversion and interpretation of field data, by comparing deterministic wavelet estimation and statistical wavelet estimation in detail, especially for field data example. The feasibility of this approach is verified on real seismic and well data from Viking Graben field, North Sea, Norway. Our results also show the influence of the washout zones on well log data on the quality of the well to seismic tie.

Denoising embolic Doppler ultrasound signals using Dual Tree Complex Discrete Wavelet Transform.

PubMed

Serbes, Gorkem; Aydin, Nizamettin

2010-01-01

Early and accurate detection of asymptomatic emboli is important for monitoring of preventive therapy in stroke-prone patients. One of the problems in detection of emboli is the identification of an embolic signal caused by very small emboli. The amplitude of the embolic signal may be so small that advanced processing methods are required to distinguish these signals from Doppler signals arising from red blood cells. In this study instead of conventional discrete wavelet transform, the Dual Tree Complex Discrete Wavelet Transform was used for denoising embolic signals. Performances of both approaches were compared. Unlike the conventional discrete wavelet transform discrete complex wavelet transform is a shift invariant transform with limited redundancy. Results demonstrate that the Dual Tree Complex Discrete Wavelet Transform based denoising outperforms conventional discrete wavelet denoising. Approximately 8 dB improvement is obtained by using the Dual Tree Complex Discrete Wavelet Transform compared to the improvement provided by the conventional Discrete Wavelet Transform (less than 5 dB).

Dependence and risk assessment for oil prices and exchange rate portfolios: A wavelet based approach

NASA Astrophysics Data System (ADS)

Aloui, Chaker; Jammazi, Rania

2015-10-01

In this article, we propose a wavelet-based approach to accommodate the stylized facts and complex structure of financial data, caused by frequent and abrupt changes of markets and noises. Specifically, we show how the combination of both continuous and discrete wavelet transforms with traditional financial models helps improve portfolio's market risk assessment. In the empirical stage, three wavelet-based models (wavelet-EGARCH with dynamic conditional correlations, wavelet-copula, and wavelet-extreme value) are considered and applied to crude oil price and US dollar exchange rate data. Our findings show that the wavelet-based approach provides an effective and powerful tool for detecting extreme moments and improving the accuracy of VaR and Expected Shortfall estimates of oil-exchange rate portfolios after noise is removed from the original data.

PULSAR SIGNAL DENOISING METHOD BASED ON LAPLACE DISTRIBUTION IN NO-SUBSAMPLING WAVELET PACKET DOMAIN

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

Wenbo, Wang; Yanchao, Zhao; Xiangli, Wang

2016-11-01

In order to improve the denoising effect of the pulsar signal, a new denoising method is proposed in the no-subsampling wavelet packet domain based on the local Laplace prior model. First, we count the true noise-free pulsar signal’s wavelet packet coefficient distribution characteristics and construct the true signal wavelet packet coefficients’ Laplace probability density function model. Then, we estimate the denosied wavelet packet coefficients by using the noisy pulsar wavelet coefficients based on maximum a posteriori criteria. Finally, we obtain the denoisied pulsar signal through no-subsampling wavelet packet reconstruction of the estimated coefficients. The experimental results show that the proposed method performs better when calculating the pulsar time of arrival than the translation-invariant wavelet denoising method.

Wavelet entropy characterization of elevated intracranial pressure.

PubMed

Xu, Peng; Scalzo, Fabien; Bergsneider, Marvin; Vespa, Paul; Chad, Miller; Hu, Xiao

2008-01-01

Intracranial Hypertension (ICH) often occurs for those patients with traumatic brain injury (TBI), stroke, tumor, etc. Pathology of ICH is still controversial. In this work, we used wavelet entropy and relative wavelet entropy to study the difference existed between normal and hypertension states of ICP for the first time. The wavelet entropy revealed the similar findings as the approximation entropy that entropy during ICH state is smaller than that in normal state. Moreover, with wavelet entropy, we can see that ICH state has the more focused energy in the low wavelet frequency band (0-3.1 Hz) than the normal state. The relative wavelet entropy shows that the energy distribution in the wavelet bands between these two states is actually different. Based on these results, we suggest that ICH may be formed by the re-allocation of oscillation energy within brain.

Iterated oversampled filter banks and wavelet frames

NASA Astrophysics Data System (ADS)

Selesnick, Ivan W.; Sendur, Levent

2000-12-01

This paper takes up the design of wavelet tight frames that are analogous to Daubechies orthonormal wavelets - that is, the design of minimal length wavelet filters satisfying certain polynomial properties, but now in the oversampled case. The oversampled dyadic DWT considered in this paper is based on a single scaling function and tow distinct wavelets. Having more wavelets than necessary gives a closer spacing between adjacent wavelets within the same scale. As a result, the transform is nearly shift-invariant, and can be used to improve denoising. Because the associated time- frequency lattice preserves the dyadic structure of the critically sampled DWT it can be used with tree-based denoising algorithms that exploit parent-child correlation.

Automatic speech recognition using a predictive echo state network classifier.

PubMed

Skowronski, Mark D; Harris, John G

2007-04-01

We have combined an echo state network (ESN) with a competitive state machine framework to create a classification engine called the predictive ESN classifier. We derive the expressions for training the predictive ESN classifier and show that the model was significantly more noise robust compared to a hidden Markov model in noisy speech classification experiments by 8+/-1 dB signal-to-noise ratio. The simple training algorithm and noise robustness of the predictive ESN classifier make it an attractive classification engine for automatic speech recognition.

Semi-automated surface mapping via unsupervised classification

NASA Astrophysics Data System (ADS)

D'Amore, M.; Le Scaon, R.; Helbert, J.; Maturilli, A.

2017-09-01

Due to the increasing volume of the returned data from space mission, the human search for correlation and identification of interesting features becomes more and more unfeasible. Statistical extraction of features via machine learning methods will increase the scientific output of remote sensing missions and aid the discovery of yet unknown feature hidden in dataset. Those methods exploit algorithm trained on features from multiple instrument, returning classification maps that explore intra-dataset correlation, allowing for the discovery of unknown features. We present two applications, one for Mercury and one for Vesta.

Use of Machine Learning Techniques for Identification of Robust Teleconnections to East African Rainfall Variability

NASA Technical Reports Server (NTRS)

Roberts, J. Brent; Robertson, F. R.; Funk, C.

2014-01-01

Hidden Markov models can be used to investigate structure of subseasonal variability. East African short rain variability has connections to large-scale tropical variability. MJO - Intraseasonal variations connected with appearance of "wet" and "dry" states. ENSO/IOZM SST and circulation anomalies are apparent during years of anomalous residence time in the subseasonal "wet" state. Similar results found in previous studies, but we can interpret this with respect to variations of subseasonal wet and dry modes. Reveal underlying connections between MJO/IOZM/ENSO with respect to East African rainfall.

Acoustical Emission Source Location in Thin Rods Through Wavelet Detail Crosscorrelation

DTIC Science & Technology

1998-03-01

NAVAL POSTGRADUATE SCHOOL Monterey, California THESIS ACOUSTICAL EMISSION SOURCE LOCATION IN THIN RODS THROUGH WAVELET DETAIL CROSSCORRELATION...ACOUSTICAL EMISSION SOURCE LOCATION IN THIN RODS THROUGH WAVELET DETAIL CROSSCORRELATION 6. AUTHOR(S) Jerauld, Joseph G. 5. FUNDING NUMBERS Grant...frequency characteristics of Wavelet Analysis. Software implementation now enables the exploration of the Wavelet Transform to identify the time of

Comparative Analysis of Haar and Daubechies Wavelet for Hyper Spectral Image Classification

NASA Astrophysics Data System (ADS)

Sharif, I.; Khare, S.

2014-11-01

With the number of channels in the hundreds instead of in the tens Hyper spectral imagery possesses much richer spectral information than multispectral imagery. The increased dimensionality of such Hyper spectral data provides a challenge to the current technique for analyzing data. Conventional classification methods may not be useful without dimension reduction pre-processing. So dimension reduction has become a significant part of Hyper spectral image processing. This paper presents a comparative analysis of the efficacy of Haar and Daubechies wavelets for dimensionality reduction in achieving image classification. Spectral data reduction using Wavelet Decomposition could be useful because it preserves the distinction among spectral signatures. Daubechies wavelets optimally capture the polynomial trends while Haar wavelet is discontinuous and resembles a step function. The performance of these wavelets are compared in terms of classification accuracy and time complexity. This paper shows that wavelet reduction has more separate classes and yields better or comparable classification accuracy. In the context of the dimensionality reduction algorithm, it is found that the performance of classification of Daubechies wavelets is better as compared to Haar wavelet while Daubechies takes more time compare to Haar wavelet. The experimental results demonstrate the classification system consistently provides over 84% classification accuracy.

Wavelet median denoising of ultrasound images

NASA Astrophysics Data System (ADS)

Macey, Katherine E.; Page, Wyatt H.

2002-05-01

Ultrasound images are contaminated with both additive and multiplicative noise, which is modeled by Gaussian and speckle noise respectively. Distinguishing small features such as fallopian tubes in the female genital tract in the noisy environment is problematic. A new method for noise reduction, Wavelet Median Denoising, is presented. Wavelet Median Denoising consists of performing a standard noise reduction technique, median filtering, in the wavelet domain. The new method is tested on 126 images, comprised of 9 original images each with 14 levels of Gaussian or speckle noise. Results for both separable and non-separable wavelets are evaluated, relative to soft-thresholding in the wavelet domain, using the signal-to-noise ratio and subjective assessment. The performance of Wavelet Median Denoising is comparable to that of soft-thresholding. Both methods are more successful in removing Gaussian noise than speckle noise. Wavelet Median Denoising outperforms soft-thresholding for a larger number of cases of speckle noise reduction than of Gaussian noise reduction. Noise reduction is more successful using non-separable wavelets than separable wavelets. When both methods are applied to ultrasound images obtained from a phantom of the female genital tract a small improvement is seen; however, a substantial improvement is required prior to clinical use.

Wavelet detection of singularities in the presence of fractal noise

NASA Astrophysics Data System (ADS)

Noel, Steven E.; Gohel, Yogesh J.; Szu, Harold H.

1997-04-01

Here we detect singularities with generalized quadrature processing using the recently developed Hermitian Hat wavelet. Our intended application is radar target detection for the optimal fuzzing of ship self-defense munitions. We first develop a wavelet-based fractal noise model to represent sea clutter. We then investigate wavelet shrinkage as a way to reduce and smooth the noise before attempting wavelet detection. Finally, we use the complex phase of the Hermitian Hat wavelet to detect a simulated target singularity in the presence of our fractal noise.

Double Density Dual Tree Discrete Wavelet Transform implementation for Degraded Image Enhancement

NASA Astrophysics Data System (ADS)

Vimala, C.; Aruna Priya, P.

2018-04-01

Wavelet transform is a main tool for image processing applications in modern existence. A Double Density Dual Tree Discrete Wavelet Transform is used and investigated for image denoising. Images are considered for the analysis and the performance is compared with discrete wavelet transform and the Double Density DWT. Peak Signal to Noise Ratio values and Root Means Square error are calculated in all the three wavelet techniques for denoised images and the performance has evaluated. The proposed techniques give the better performance when comparing other two wavelet techniques.

Improved protein-protein interactions prediction via weighted sparse representation model combining continuous wavelet descriptor and PseAA composition.

PubMed

Huang, Yu-An; You, Zhu-Hong; Chen, Xing; Yan, Gui-Ying

2016-12-23

Protein-protein interactions (PPIs) are essential to most biological processes. Since bioscience has entered into the era of genome and proteome, there is a growing demand for the knowledge about PPI network. High-throughput biological technologies can be used to identify new PPIs, but they are expensive, time-consuming, and tedious. Therefore, computational methods for predicting PPIs have an important role. For the past years, an increasing number of computational methods such as protein structure-based approaches have been proposed for predicting PPIs. The major limitation in principle of these methods lies in the prior information of the protein to infer PPIs. Therefore, it is of much significance to develop computational methods which only use the information of protein amino acids sequence. Here, we report a highly efficient approach for predicting PPIs. The main improvements come from the use of a novel protein sequence representation by combining continuous wavelet descriptor and Chou's pseudo amino acid composition (PseAAC), and from adopting weighted sparse representation based classifier (WSRC). This method, cross-validated on the PPIs datasets of Saccharomyces cerevisiae, Human and H. pylori, achieves an excellent results with accuracies as high as 92.50%, 95.54% and 84.28% respectively, significantly better than previously proposed methods. Extensive experiments are performed to compare the proposed method with state-of-the-art Support Vector Machine (SVM) classifier. The outstanding results yield by our model that the proposed feature extraction method combing two kinds of descriptors have strong expression ability and are expected to provide comprehensive and effective information for machine learning-based classification models. In addition, the prediction performance in the comparison experiments shows the well cooperation between the combined feature and WSRC. Thus, the proposed method is a very efficient method to predict PPIs and may be a useful supplementary tool for future proteomics studies.

Daily water level forecasting using wavelet decomposition and artificial intelligence techniques

NASA Astrophysics Data System (ADS)

Seo, Youngmin; Kim, Sungwon; Kisi, Ozgur; Singh, Vijay P.

2015-01-01

Reliable water level forecasting for reservoir inflow is essential for reservoir operation. The objective of this paper is to develop and apply two hybrid models for daily water level forecasting and investigate their accuracy. These two hybrid models are wavelet-based artificial neural network (WANN) and wavelet-based adaptive neuro-fuzzy inference system (WANFIS). Wavelet decomposition is employed to decompose an input time series into approximation and detail components. The decomposed time series are used as inputs to artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS) for WANN and WANFIS models, respectively. Based on statistical performance indexes, the WANN and WANFIS models are found to produce better efficiency than the ANN and ANFIS models. WANFIS7-sym10 yields the best performance among all other models. It is found that wavelet decomposition improves the accuracy of ANN and ANFIS. This study evaluates the accuracy of the WANN and WANFIS models for different mother wavelets, including Daubechies, Symmlet and Coiflet wavelets. It is found that the model performance is dependent on input sets and mother wavelets, and the wavelet decomposition using mother wavelet, db10, can further improve the efficiency of ANN and ANFIS models. Results obtained from this study indicate that the conjunction of wavelet decomposition and artificial intelligence models can be a useful tool for accurate forecasting daily water level and can yield better efficiency than the conventional forecasting models.

Wavelet transform: fundamentals, applications, and implementation using acousto-optic correlators

NASA Astrophysics Data System (ADS)

DeCusatis, Casimer M.; Koay, J.; Litynski, Daniel M.; Das, Pankaj K.

1995-10-01

In recent years there has been a great deal of interest in the use of wavelets to supplement or replace conventional Fourier transform signal processing. This paper provides a review of wavelet transforms for signal processing applications, and discusses several emerging applications which benefit from the advantages of wavelets. The wavelet transform can be implemented as an acousto-optic correlator; perfect reconstruction of digital signals may also be achieved using acousto-optic finite impulse response filter banks. Acousto-optic image correlators are discussed as a potential implementation of the wavelet transform, since a 1D wavelet filter bank may be encoded as a 2D image. We discuss applications of the wavelet transform including nondestructive testing of materials, biomedical applications in the analysis of EEG signals, and interference excision in spread spectrum communication systems. Computer simulations and experimental results for these applications are also provided.

The application of super wavelet finite element on temperature-pressure coupled field simulation of LPG tank under jet fire

NASA Astrophysics Data System (ADS)

Zhao, Bin

2015-02-01

Temperature-pressure coupled field analysis of liquefied petroleum gas (LPG) tank under jet fire can offer theoretical guidance for preventing the fire accidents of LPG tank, the application of super wavelet finite element on it is studied in depth. First, review of related researches on heat transfer analysis of LPG tank under fire and super wavelet are carried out. Second, basic theory of super wavelet transform is studied. Third, the temperature-pressure coupled model of gas phase and liquid LPG under jet fire is established based on the equation of state, the VOF model and the RNG k-ɛ model. Then the super wavelet finite element formulation is constructed using the super wavelet scale function as interpolating function. Finally, the simulation is carried out, and results show that the super wavelet finite element method has higher computing precision than wavelet finite element method.

Study on vibration characteristics and fault diagnosis method of oil-immersed flat wave reactor in Arctic area converter station

NASA Astrophysics Data System (ADS)

Lai, Wenqing; Wang, Yuandong; Li, Wenpeng; Sun, Guang; Qu, Guomin; Cui, Shigang; Li, Mengke; Wang, Yongqiang

2017-10-01

Based on long term vibration monitoring of the No.2 oil-immersed fat wave reactor in the ±500kV converter station in East Mongolia, the vibration signals in normal state and in core loose fault state were saved. Through the time-frequency analysis of the signals, the vibration characteristics of the core loose fault were obtained, and a fault diagnosis method based on the dual tree complex wavelet (DT-CWT) and support vector machine (SVM) was proposed. The vibration signals were analyzed by DT-CWT, and the energy entropy of the vibration signals were taken as the feature vector; the support vector machine was used to train and test the feature vector, and the accurate identification of the core loose fault of the flat wave reactor was realized. Through the identification of many groups of normal and core loose fault state vibration signals, the diagnostic accuracy of the result reached 97.36%. The effectiveness and accuracy of the method in the fault diagnosis of the flat wave reactor core is verified.

Wavelets

NASA Astrophysics Data System (ADS)

Strang, Gilbert

1994-06-01

Several methods are compared that are used to analyze and synthesize a signal. Three ways are mentioned to transform a symphony: into cosine waves (Fourier transform), into pieces of cosines (short-time Fourier transform), and into wavelets (little waves that start and stop). Choosing the best basis, higher dimensions, fast wavelet transform, and Daubechies wavelets are discussed. High-definition television is described. The use of wavelets in identifying fingerprints in the future is related.

Wavelet based free-form deformations for nonrigid registration

NASA Astrophysics Data System (ADS)

Sun, Wei; Niessen, Wiro J.; Klein, Stefan

2014-03-01

In nonrigid registration, deformations may take place on the coarse and fine scales. For the conventional B-splines based free-form deformation (FFD) registration, these coarse- and fine-scale deformations are all represented by basis functions of a single scale. Meanwhile, wavelets have been proposed as a signal representation suitable for multi-scale problems. Wavelet analysis leads to a unique decomposition of a signal into its coarse- and fine-scale components. Potentially, this could therefore be useful for image registration. In this work, we investigate whether a wavelet-based FFD model has advantages for nonrigid image registration. We use a B-splines based wavelet, as defined by Cai and Wang.1 This wavelet is expressed as a linear combination of B-spline basis functions. Derived from the original B-spline function, this wavelet is smooth, differentiable, and compactly supported. The basis functions of this wavelet are orthogonal across scales in Sobolev space. This wavelet was previously used for registration in computer vision, in 2D optical flow problems,2 but it was not compared with the conventional B-spline FFD in medical image registration problems. An advantage of choosing this B-splines based wavelet model is that the space of allowable deformation is exactly equivalent to that of the traditional B-spline. The wavelet transformation is essentially a (linear) reparameterization of the B-spline transformation model. Experiments on 10 CT lung and 18 T1-weighted MRI brain datasets show that wavelet based registration leads to smoother deformation fields than traditional B-splines based registration, while achieving better accuracy.

Photoacoustic signals denoising of the glucose aqueous solutions using an improved wavelet threshold method

NASA Astrophysics Data System (ADS)

Ren, Zhong; Liu, Guodong; Xiong, Zhihua

2016-10-01

The photoacoustic signals denoising of glucose is one of most important steps in the quality identification of the fruit because the real-time photoacoustic singals of glucose are easily interfered by all kinds of noises. To remove the noises and some useless information, an improved wavelet threshld function were proposed. Compared with the traditional wavelet hard and soft threshold functions, the improved wavelet threshold function can overcome the pseudo-oscillation effect of the denoised photoacoustic signals due to the continuity of the improved wavelet threshold function, and the error between the denoised signals and the original signals can be decreased. To validate the feasibility of the improved wavelet threshold function denoising, the denoising simulation experiments based on MATLAB programmimg were performed. In the simulation experiments, the standard test signal was used, and three different denoising methods were used and compared with the improved wavelet threshold function. The signal-to-noise ratio (SNR) and the root-mean-square error (RMSE) values were used to evaluate the performance of the improved wavelet threshold function denoising. The experimental results demonstrate that the SNR value of the improved wavelet threshold function is largest and the RMSE value is lest, which fully verifies that the improved wavelet threshold function denoising is feasible. Finally, the improved wavelet threshold function denoising was used to remove the noises of the photoacoustic signals of the glucose solutions. The denoising effect is also very good. Therefore, the improved wavelet threshold function denoising proposed by this paper, has a potential value in the field of denoising for the photoacoustic singals.

A novelty detection diagnostic methodology for gearboxes operating under fluctuating operating conditions using probabilistic techniques

NASA Astrophysics Data System (ADS)

Schmidt, S.; Heyns, P. S.; de Villiers, J. P.

2018-02-01

In this paper, a fault diagnostic methodology is developed which is able to detect, locate and trend gear faults under fluctuating operating conditions when only vibration data from a single transducer, measured on a healthy gearbox are available. A two-phase feature extraction and modelling process is proposed to infer the operating condition and based on the operating condition, to detect changes in the machine condition. Information from optimised machine and operating condition hidden Markov models are statistically combined to generate a discrepancy signal which is post-processed to infer the condition of the gearbox. The discrepancy signal is processed and combined with statistical methods for automatic fault detection and localisation and to perform fault trending over time. The proposed methodology is validated on experimental data and a tacholess order tracking methodology is used to enhance the cost-effectiveness of the diagnostic methodology.

Lithofacies classification of the Barnett Shale gas reservoir using neural network

NASA Astrophysics Data System (ADS)

Aliouane, Leila; Ouadfeul, Sid-Ali

2017-04-01

Here, we show the contribution of the artificial intelligence such as neural network to predict the lithofacies in the lower Barnett shale gas reservoir. The Multilayer Perceptron (MLP) neural network with Hidden Weight Optimization Algorithm is used. The input is raw well-logs data recorded in a horizontal well drilled in the Lower Barnett shale formation, however the output is the concentration of the Clay and the Quartz calculated using the ELAN model and confirmed with the core rock measurement. After training of the MLP machine weights of connection are calculated, the raw well-logs data of two other horizontal wells drilled in the same reservoir are propagated though the neural machine and an output is calculated. Comparison between the predicted and measured clay and Quartz concentrations in these two horizontal wells shows the ability of neural network to improve shale gas reservoirs characterization.

Accelerometry-based classification of human activities using Markov modeling.

PubMed

Mannini, Andrea; Sabatini, Angelo Maria

2011-01-01

Accelerometers are a popular choice as body-motion sensors: the reason is partly in their capability of extracting information that is useful for automatically inferring the physical activity in which the human subject is involved, beside their role in feeding biomechanical parameters estimators. Automatic classification of human physical activities is highly attractive for pervasive computing systems, whereas contextual awareness may ease the human-machine interaction, and in biomedicine, whereas wearable sensor systems are proposed for long-term monitoring. This paper is concerned with the machine learning algorithms needed to perform the classification task. Hidden Markov Model (HMM) classifiers are studied by contrasting them with Gaussian Mixture Model (GMM) classifiers. HMMs incorporate the statistical information available on movement dynamics into the classification process, without discarding the time history of previous outcomes as GMMs do. An example of the benefits of the obtained statistical leverage is illustrated and discussed by analyzing two datasets of accelerometer time series.

Support-vector-machine tree-based domain knowledge learning toward automated sports video classification

NASA Astrophysics Data System (ADS)

Xiao, Guoqiang; Jiang, Yang; Song, Gang; Jiang, Jianmin

2010-12-01

We propose a support-vector-machine (SVM) tree to hierarchically learn from domain knowledge represented by low-level features toward automatic classification of sports videos. The proposed SVM tree adopts a binary tree structure to exploit the nature of SVM's binary classification, where each internal node is a single SVM learning unit, and each external node represents the classified output type. Such a SVM tree presents a number of advantages, which include: 1. low computing cost; 2. integrated learning and classification while preserving individual SVM's learning strength; and 3. flexibility in both structure and learning modules, where different numbers of nodes and features can be added to address specific learning requirements, and various learning models can be added as individual nodes, such as neural networks, AdaBoost, hidden Markov models, dynamic Bayesian networks, etc. Experiments support that the proposed SVM tree achieves good performances in sports video classifications.

Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning.

PubMed

Yang, Yimin; Wu, Q M Jonathan

2016-11-01

The extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.

Evaluation of the Use of Second Generation Wavelets in the Coherent Vortex Simulation Approach

NASA Technical Reports Server (NTRS)

Goldstein, D. E.; Vasilyev, O. V.; Wray, A. A.; Rogallo, R. S.

2000-01-01

The objective of this study is to investigate the use of the second generation bi-orthogonal wavelet transform for the field decomposition in the Coherent Vortex Simulation of turbulent flows. The performances of the bi-orthogonal second generation wavelet transform and the orthogonal wavelet transform using Daubechies wavelets with the same number of vanishing moments are compared in a priori tests using a spectral direct numerical simulation (DNS) database of isotropic turbulence fields: 256(exp 3) and 512(exp 3) DNS of forced homogeneous turbulence (Re(sub lambda) = 168) and 256(exp 3) and 512(exp 3) DNS of decaying homogeneous turbulence (Re(sub lambda) = 55). It is found that bi-orthogonal second generation wavelets can be used for coherent vortex extraction. The results of a priori tests indicate that second generation wavelets have better compression and the residual field is closer to Gaussian. However, it was found that the use of second generation wavelets results in an integral length scale for the incoherent part that is larger than that derived from orthogonal wavelets. A way of dealing with this difficulty is suggested.

Enhancement of Signal-to-noise Ratio in Natural-source Transient Magnetotelluric Data with Wavelet Transform

NASA Astrophysics Data System (ADS)

Zhang, Y.; Paulson, K. V.

For audio-frequency magnetotelluric surveys where the signals are lightning-stroke transients, the conventional Fourier transform method often fails to produce a high quality impedance tensor. An alternative approach is to use the wavelet transform method which is capable of localizing target information simultaneously in both the temporal and frequency domains. Unlike Fourier analysis that yields an average amplitude and phase, the wavelet transform produces an instantaneous estimate of the amplitude and phase of a signal. In this paper a complex well-localized wavelet, the Morlet wavelet, has been used to transform and analyze audio-frequency magnetotelluric data. With the Morlet wavelet, the magnetotelluric impedance tensor can be computed directly in the wavelet transform domain. The lightning-stroke transients are easily identified on the dilation-translation plane. Choosing those wavelet transform values where the signals are located, a higher signal-to-noise ratio estimation of the impedance tensor can be obtained. In a test using real data, the wavelet transform showed a significant improvement in the signal-to-noise ratio over the conventional Fourier transform.

Extracting laboratory test information from biomedical text

PubMed Central

Kang, Yanna Shen; Kayaalp, Mehmet

2013-01-01

Background: No previous study reported the efficacy of current natural language processing (NLP) methods for extracting laboratory test information from narrative documents. This study investigates the pathology informatics question of how accurately such information can be extracted from text with the current tools and techniques, especially machine learning and symbolic NLP methods. The study data came from a text corpus maintained by the U.S. Food and Drug Administration, containing a rich set of information on laboratory tests and test devices. Methods: The authors developed a symbolic information extraction (SIE) system to extract device and test specific information about four types of laboratory test entities: Specimens, analytes, units of measures and detection limits. They compared the performance of SIE and three prominent machine learning based NLP systems, LingPipe, GATE and BANNER, each implementing a distinct supervised machine learning method, hidden Markov models, support vector machines and conditional random fields, respectively. Results: Machine learning systems recognized laboratory test entities with moderately high recall, but low precision rates. Their recall rates were relatively higher when the number of distinct entity values (e.g., the spectrum of specimens) was very limited or when lexical morphology of the entity was distinctive (as in units of measures), yet SIE outperformed them with statistically significant margins on extracting specimen, analyte and detection limit information in both precision and F-measure. Its high recall performance was statistically significant on analyte information extraction. Conclusions: Despite its shortcomings against machine learning methods, a well-tailored symbolic system may better discern relevancy among a pile of information of the same type and may outperform a machine learning system by tapping into lexically non-local contextual information such as the document structure. PMID:24083058

Representation and design of wavelets using unitary circuits

NASA Astrophysics Data System (ADS)

Evenbly, Glen; White, Steven R.

2018-05-01

The representation of discrete, compact wavelet transformations (WTs) as circuits of local unitary gates is discussed. We employ a similar formalism as used in the multiscale representation of quantum many-body wave functions using unitary circuits, further cementing the relation established in the literature between classical and quantum multiscale methods. An algorithm for constructing the circuit representation of known orthogonal, dyadic, discrete WTs is presented, and the explicit representation for Daubechies wavelets, coiflets, and symlets is provided. Furthermore, we demonstrate the usefulness of the circuit formalism in designing WTs, including various classes of symmetric wavelets and multiwavelets, boundary wavelets, and biorthogonal wavelets.

Parallel object-oriented, denoising system using wavelet multiresolution analysis

DOEpatents

Kamath, Chandrika; Baldwin, Chuck H.; Fodor, Imola K.; Tang, Nu A.

2005-04-12

The present invention provides a data de-noising system utilizing processors and wavelet denoising techniques. Data is read and displayed in different formats. The data is partitioned into regions and the regions are distributed onto the processors. Communication requirements are determined among the processors according to the wavelet denoising technique and the partitioning of the data. The data is transforming onto different multiresolution levels with the wavelet transform according to the wavelet denoising technique, the communication requirements, and the transformed data containing wavelet coefficients. The denoised data is then transformed into its original reading and displaying data format.

F-wave decomposition for time of arrival profile estimation.

PubMed

Han, Zhixiu; Kong, Xuan

2007-01-01

F-waves are distally recorded muscle responses that result from "backfiring" of motor neurons following stimulation of peripheral nerves. Each F-wave response is a superposition of several motor unit responses (F-wavelets). Initial deflection of the earliest F-wavelet defines the traditional F-wave latency (FWL) and earlier F-wavelet may mask F-wavelets traveling along slower (and possibly diseased) fibers. Unmasking the time of arrival (TOA) of late F-wavelets could improve the diagnostic value of the F-waves. An algorithm for F-wavelet decomposition is presented, followed by results of experimental data analysis.

EEG analysis using wavelet-based information tools.

PubMed

Rosso, O A; Martin, M T; Figliola, A; Keller, K; Plastino, A

2006-06-15

Wavelet-based informational tools for quantitative electroencephalogram (EEG) record analysis are reviewed. Relative wavelet energies, wavelet entropies and wavelet statistical complexities are used in the characterization of scalp EEG records corresponding to secondary generalized tonic-clonic epileptic seizures. In particular, we show that the epileptic recruitment rhythm observed during seizure development is well described in terms of the relative wavelet energies. In addition, during the concomitant time-period the entropy diminishes while complexity grows. This is construed as evidence supporting the conjecture that an epileptic focus, for this kind of seizures, triggers a self-organized brain state characterized by both order and maximal complexity.

Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

PubMed

Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

2018-01-05

Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value <0.05) that cannot be discovered by other machine learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

Use of the wavelet transform to investigate differences in brain PET images between patient groups

NASA Astrophysics Data System (ADS)

Ruttimann, Urs E.; Unser, Michael A.; Rio, Daniel E.; Rawlings, Robert R.

1993-06-01

Suitability of the wavelet transform was studied for the analysis of glucose utilization differences between subject groups as displayed in PET images. To strengthen statistical inference, it was of particular interest investigating the tradeoff between signal localization and image decomposition into uncorrelated components. This tradeoff is shown to be controlled by wavelet regularity, with the optimal compromise attained by third-order orthogonal spline wavelets. Testing of the ensuing wavelet coefficients identified only about 1.5% as statistically different (p < .05) from noise, which then served to resynthesize the difference images by the inverse wavelet transform. The resulting images displayed relatively uniform, noise-free regions of significant differences with, due to the good localization maintained by the wavelets, very little reconstruction artifacts.

Analysis of autostereoscopic three-dimensional images using multiview wavelets.

PubMed

Saveljev, Vladimir; Palchikova, Irina

2016-08-10

We propose that multiview wavelets can be used in processing multiview images. The reference functions for the synthesis/analysis of multiview images are described. The synthesized binary images were observed experimentally as three-dimensional visual images. The symmetric multiview B-spline wavelets are proposed. The locations recognized in the continuous wavelet transform correspond to the layout of the test objects. The proposed wavelets can be applied to the multiview, integral, and plenoptic images.

Steganography anomaly detection using simple one-class classification

NASA Astrophysics Data System (ADS)

Rodriguez, Benjamin M.; Peterson, Gilbert L.; Agaian, Sos S.

2007-04-01

There are several security issues tied to multimedia when implementing the various applications in the cellular phone and wireless industry. One primary concern is the potential ease of implementing a steganography system. Traditionally, the only mechanism to embed information into a media file has been with a desktop computer. However, as the cellular phone and wireless industry matures, it becomes much simpler for the same techniques to be performed using a cell phone. In this paper, two methods are compared that classify cell phone images as either an anomaly or clean, where a clean image is one in which no alterations have been made and an anomalous image is one in which information has been hidden within the image. An image in which information has been hidden is known as a stego image. The main concern in detecting steganographic content with machine learning using cell phone images is in training specific embedding procedures to determine if the method has been used to generate a stego image. This leads to a possible flaw in the system when the learned model of stego is faced with a new stego method which doesn't match the existing model. The proposed solution to this problem is to develop systems that detect steganography as anomalies, making the embedding method irrelevant in detection. Two applicable classification methods for solving the anomaly detection of steganographic content problem are single class support vector machines (SVM) and Parzen-window. Empirical comparison of the two approaches shows that Parzen-window outperforms the single class SVM most likely due to the fact that Parzen-window generalizes less.

An Improved Pathological Brain Detection System Based on Two-Dimensional PCA and Evolutionary Extreme Learning Machine.

PubMed

Nayak, Deepak Ranjan; Dash, Ratnakar; Majhi, Banshidhar

2017-12-07

Pathological brain detection has made notable stride in the past years, as a consequence many pathological brain detection systems (PBDSs) have been proposed. But, the accuracy of these systems still needs significant improvement in order to meet the necessity of real world diagnostic situations. In this paper, an efficient PBDS based on MR images is proposed that markedly improves the recent results. The proposed system makes use of contrast limited adaptive histogram equalization (CLAHE) to enhance the quality of the input MR images. Thereafter, two-dimensional PCA (2DPCA) strategy is employed to extract the features and subsequently, a PCA+LDA approach is used to generate a compact and discriminative feature set. Finally, a new learning algorithm called MDE-ELM is suggested that combines modified differential evolution (MDE) and extreme learning machine (ELM) for segregation of MR images as pathological or healthy. The MDE is utilized to optimize the input weights and hidden biases of single-hidden-layer feed-forward neural networks (SLFN), whereas an analytical method is used for determining the output weights. The proposed algorithm performs optimization based on both the root mean squared error (RMSE) and norm of the output weights of SLFNs. The suggested scheme is benchmarked on three standard datasets and the results are compared against other competent schemes. The experimental outcomes show that the proposed scheme offers superior results compared to its counterparts. Further, it has been noticed that the proposed MDE-ELM classifier obtains better accuracy with compact network architecture than conventional algorithms.

Value-at-risk estimation with wavelet-based extreme value theory: Evidence from emerging markets

NASA Astrophysics Data System (ADS)

Cifter, Atilla

2011-06-01

This paper introduces wavelet-based extreme value theory (EVT) for univariate value-at-risk estimation. Wavelets and EVT are combined for volatility forecasting to estimate a hybrid model. In the first stage, wavelets are used as a threshold in generalized Pareto distribution, and in the second stage, EVT is applied with a wavelet-based threshold. This new model is applied to two major emerging stock markets: the Istanbul Stock Exchange (ISE) and the Budapest Stock Exchange (BUX). The relative performance of wavelet-based EVT is benchmarked against the Riskmetrics-EWMA, ARMA-GARCH, generalized Pareto distribution, and conditional generalized Pareto distribution models. The empirical results show that the wavelet-based extreme value theory increases predictive performance of financial forecasting according to number of violations and tail-loss tests. The superior forecasting performance of the wavelet-based EVT model is also consistent with Basel II requirements, and this new model can be used by financial institutions as well.

iSAP: Interactive Sparse Astronomical Data Analysis Packages

NASA Astrophysics Data System (ADS)

Fourt, O.; Starck, J.-L.; Sureau, F.; Bobin, J.; Moudden, Y.; Abrial, P.; Schmitt, J.

2013-03-01

iSAP consists of three programs, written in IDL, which together are useful for spherical data analysis. MR/S (MultiResolution on the Sphere) contains routines for wavelet, ridgelet and curvelet transform on the sphere, and applications such denoising on the sphere using wavelets and/or curvelets, Gaussianity tests and Independent Component Analysis on the Sphere. MR/S has been designed for the PLANCK project, but can be used for many other applications. SparsePol (Polarized Spherical Wavelets and Curvelets) has routines for polarized wavelet, polarized ridgelet and polarized curvelet transform on the sphere, and applications such denoising on the sphere using wavelets and/or curvelets, Gaussianity tests and blind source separation on the Sphere. SparsePol has been designed for the PLANCK project. MS-VSTS (Multi-Scale Variance Stabilizing Transform on the Sphere), designed initially for the FERMI project, is useful for spherical mono-channel and multi-channel data analysis when the data are contaminated by a Poisson noise. It contains routines for wavelet/curvelet denoising, wavelet deconvolution, multichannel wavelet denoising and deconvolution.

Analysis on Behaviour of Wavelet Coefficient during Fault Occurrence in Transformer

NASA Astrophysics Data System (ADS)

Sreewirote, Bancha; Ngaopitakkul, Atthapol

2018-03-01

The protection system for transformer has play significant role in avoiding severe damage to equipment when disturbance occur and ensure overall system reliability. One of the methodology that widely used in protection scheme and algorithm is discrete wavelet transform. However, characteristic of coefficient under fault condition must be analyzed to ensure its effectiveness. So, this paper proposed study and analysis on wavelet coefficient characteristic when fault occur in transformer in both high- and low-frequency component from discrete wavelet transform. The effect of internal and external fault on wavelet coefficient of both fault and normal phase has been taken into consideration. The fault signal has been simulate using transmission connected to transformer experimental setup on laboratory level that modelled after actual system. The result in term of wavelet coefficient shown a clearly differentiate between wavelet characteristic in both high and low frequency component that can be used to further design and improve detection and classification algorithm that based on discrete wavelet transform methodology in the future.

The 4D hyperspherical diffusion wavelet: A new method for the detection of localized anatomical variation.

PubMed

Hosseinbor, Ameer Pasha; Kim, Won Hwa; Adluru, Nagesh; Acharya, Amit; Vorperian, Houri K; Chung, Moo K

2014-01-01

Recently, the HyperSPHARM algorithm was proposed to parameterize multiple disjoint objects in a holistic manner using the 4D hyperspherical harmonics. The HyperSPHARM coefficients are global; they cannot be used to directly infer localized variations in signal. In this paper, we present a unified wavelet framework that links Hyper-SPHARM to the diffusion wavelet transform. Specifically, we will show that the HyperSPHARM basis forms a subset of a wavelet-based multiscale representation of surface-based signals. This wavelet, termed the hyperspherical diffusion wavelet, is a consequence of the equivalence of isotropic heat diffusion smoothing and the diffusion wavelet transform on the hypersphere. Our framework allows for the statistical inference of highly localized anatomical changes, which we demonstrate in the first-ever developmental study on the hyoid bone investigating gender and age effects. We also show that the hyperspherical wavelet successfully picks up group-wise differences that are barely detectable using SPHARM.

The 4D Hyperspherical Diffusion Wavelet: A New Method for the Detection of Localized Anatomical Variation

PubMed Central

Hosseinbor, A. Pasha; Kim, Won Hwa; Adluru, Nagesh; Acharya, Amit; Vorperian, Houri K.; Chung, Moo K.

2014-01-01

Recently, the HyperSPHARM algorithm was proposed to parameterize multiple disjoint objects in a holistic manner using the 4D hyperspherical harmonics. The HyperSPHARM coefficients are global; they cannot be used to directly infer localized variations in signal. In this paper, we present a unified wavelet framework that links HyperSPHARM to the diffusion wavelet transform. Specifically, we will show that the HyperSPHARM basis forms a subset of a wavelet-based multiscale representation of surface-based signals. This wavelet, termed the hyperspherical diffusion wavelet, is a consequence of the equivalence of isotropic heat diffusion smoothing and the diffusion wavelet transform on the hypersphere. Our framework allows for the statistical inference of highly localized anatomical changes, which we demonstrate in the firstever developmental study on the hyoid bone investigating gender and age effects. We also show that the hyperspherical wavelet successfully picks up group-wise differences that are barely detectable using SPHARM. PMID:25320783

Use of parallel computing for analyzing big data in EEG studies of ambiguous perception

NASA Astrophysics Data System (ADS)

Maksimenko, Vladimir A.; Grubov, Vadim V.; Kirsanov, Daniil V.

2018-02-01

Problem of interaction between human and machine systems through the neuro-interfaces (or brain-computer interfaces) is an urgent task which requires analysis of large amount of neurophysiological EEG data. In present paper we consider the methods of parallel computing as one of the most powerful tools for processing experimental data in real-time with respect to multichannel structure of EEG. In this context we demonstrate the application of parallel computing for the estimation of the spectral properties of multichannel EEG signals, associated with the visual perception. Using CUDA C library we run wavelet-based algorithm on GPUs and show possibility for detection of specific patterns in multichannel set of EEG data in real-time.

Wavelet transform analysis of transient signals: the seismogram and the electrocardiogram

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

Anant, K.S.

1997-06-01

In this dissertation I quantitatively demonstrate how the wavelet transform can be an effective mathematical tool for the analysis of transient signals. The two key signal processing applications of the wavelet transform, namely feature identification and representation (i.e., compression), are shown by solving important problems involving the seismogram and the electrocardiogram. The seismic feature identification problem involved locating in time the P and S phase arrivals. Locating these arrivals accurately (particularly the S phase) has been a constant issue in seismic signal processing. In Chapter 3, I show that the wavelet transform can be used to locate both the Pmore » as well as the S phase using only information from single station three-component seismograms. This is accomplished by using the basis function (wave-let) of the wavelet transform as a matching filter and by processing information across scales of the wavelet domain decomposition. The `pick` time results are quite promising as compared to analyst picks. The representation application involved the compression of the electrocardiogram which is a recording of the electrical activity of the heart. Compression of the electrocardiogram is an important problem in biomedical signal processing due to transmission and storage limitations. In Chapter 4, I develop an electrocardiogram compression method that applies vector quantization to the wavelet transform coefficients. The best compression results were obtained by using orthogonal wavelets, due to their ability to represent a signal efficiently. Throughout this thesis the importance of choosing wavelets based on the problem at hand is stressed. In Chapter 5, I introduce a wavelet design method that uses linear prediction in order to design wavelets that are geared to the signal or feature being analyzed. The use of these designed wavelets in a test feature identification application led to positive results. The methods developed in this thesis; the feature identification methods of Chapter 3, the compression methods of Chapter 4, as well as the wavelet design methods of Chapter 5, are general enough to be easily applied to other transient signals.« less

Islanding detection technique using wavelet energy in grid-connected PV system

NASA Astrophysics Data System (ADS)

Kim, Il Song

2016-08-01

This paper proposes a new islanding detection method using wavelet energy in a grid-connected photovoltaic system. The method detects spectral changes in the higher-frequency components of the point of common coupling voltage and obtains wavelet coefficients by multilevel wavelet analysis. The autocorrelation of the wavelet coefficients can clearly identify islanding detection, even in the variations of the grid voltage harmonics during normal operating conditions. The advantage of the proposed method is that it can detect islanding condition the conventional under voltage/over voltage/under frequency/over frequency methods fail to detect. The theoretical method to obtain wavelet energies is evolved and verified by the experimental result.

Design of almost symmetric orthogonal wavelet filter bank via direct optimization.

PubMed

Murugesan, Selvaraaju; Tay, David B H

2012-05-01

It is a well-known fact that (compact-support) dyadic wavelets [based on the two channel filter banks (FBs)] cannot be simultaneously orthogonal and symmetric. Although orthogonal wavelets have the energy preservation property, biorthogonal wavelets are preferred in image processing applications because of their symmetric property. In this paper, a novel method is presented for the design of almost symmetric orthogonal wavelet FB. Orthogonality is structurally imposed by using the unnormalized lattice structure, and this leads to an objective function, which is relatively simple to optimize. The designed filters have good frequency response, flat group delay, almost symmetric filter coefficients, and symmetric wavelet function.

Wavelets and molecular structure

NASA Astrophysics Data System (ADS)

Carson, Mike

1996-08-01

The wavelet method offers possibilities for display, editing, and topological comparison of proteins at a user-specified level of detail. Wavelets are a mathematical tool that first found application in signal processing. The multiresolution analysis of a signal via wavelets provides a hierarchical series of `best' lower-resolution approximations. B-spline ribbons model the protein fold, with one control point per residue. Wavelet analysis sets limits on the information required to define the winding of the backbone through space, suggesting a recognizable fold is generated from a number of points equal to 1/4 or less the number of residues. Wavelets applied to surfaces and volumes show promise in structure-based drug design.

Polar Wavelet Transform and the Associated Uncertainty Principles

NASA Astrophysics Data System (ADS)

Shah, Firdous A.; Tantary, Azhar Y.

2018-06-01

The polar wavelet transform- a generalized form of the classical wavelet transform has been extensively used in science and engineering for finding directional representations of signals in higher dimensions. The aim of this paper is to establish new uncertainty principles associated with the polar wavelet transforms in L2(R2). Firstly, we study some basic properties of the polar wavelet transform and then derive the associated generalized version of Heisenberg-Pauli-Weyl inequality. Finally, following the idea of Beckner (Proc. Amer. Math. Soc. 123, 1897-1905 1995), we drive the logarithmic version of uncertainty principle for the polar wavelet transforms in L2(R2).

Wavelet-based 3-D inversion for frequency-domain airborne EM data

NASA Astrophysics Data System (ADS)

Liu, Yunhe; Farquharson, Colin G.; Yin, Changchun; Baranwal, Vikas C.

2018-04-01

In this paper, we propose a new wavelet-based 3-D inversion method for frequency-domain airborne electromagnetic (FDAEM) data. Instead of inverting the model in the space domain using a smoothing constraint, this new method recovers the model in the wavelet domain based on a sparsity constraint. In the wavelet domain, the model is represented by two types of coefficients, which contain both large- and fine-scale informations of the model, meaning the wavelet-domain inversion has inherent multiresolution. In order to accomplish a sparsity constraint, we minimize an L1-norm measure in the wavelet domain that mostly gives a sparse solution. The final inversion system is solved by an iteratively reweighted least-squares method. We investigate different orders of Daubechies wavelets to accomplish our inversion algorithm, and test them on synthetic frequency-domain AEM data set. The results show that higher order wavelets having larger vanishing moments and regularity can deliver a more stable inversion process and give better local resolution, while the lower order wavelets are simpler and less smooth, and thus capable of recovering sharp discontinuities if the model is simple. At last, we test this new inversion algorithm on a frequency-domain helicopter EM (HEM) field data set acquired in Byneset, Norway. Wavelet-based 3-D inversion of HEM data is compared to L2-norm-based 3-D inversion's result to further investigate the features of the new method.

On the wavelet optimized finite difference method

NASA Technical Reports Server (NTRS)

Jameson, Leland

1994-01-01

When one considers the effect in the physical space, Daubechies-based wavelet methods are equivalent to finite difference methods with grid refinement in regions of the domain where small scale structure exists. Adding a wavelet basis function at a given scale and location where one has a correspondingly large wavelet coefficient is, essentially, equivalent to adding a grid point, or two, at the same location and at a grid density which corresponds to the wavelet scale. This paper introduces a wavelet optimized finite difference method which is equivalent to a wavelet method in its multiresolution approach but which does not suffer from difficulties with nonlinear terms and boundary conditions, since all calculations are done in the physical space. With this method one can obtain an arbitrarily good approximation to a conservative difference method for solving nonlinear conservation laws.

Analysis of the tennis racket vibrations during forehand drives: Selection of the mother wavelet.

PubMed

Blache, Y; Hautier, C; Lefebvre, F; Djordjevic, A; Creveaux, T; Rogowski, I

2017-08-16

The time-frequency analysis of the tennis racket and hand vibrations is of great interest for discomfort and pathology prevention. This study aimed to (i) to assess the stationarity of the vibratory signal of the racket and hand and (ii) to identify the best mother wavelet to perform future time-frequency analysis, (iii) to determine if the stroke spin, racket characteristics and impact zone can influence the selection of the best mother wavelet. A total of 2364 topspin and flat forehand drives were performed by fourteen male competitive tennis players with six different rackets. One tri-axial and one mono-axial accelerometer were taped on the racket throat and dominant hand respectively. The signal stationarity was tested through the wavelet spectrum test. Eighty-nine mother wavelet were tested to select the best mother wavelet based on continuous and discrete transforms. On average only 25±17%, 2±5%, 5±7% and 27±27% of the signal tested respected the hypothesis of stationarity for the three axes of the racket and the hand respectively. Regarding the two methods for the detection of the best mother wavelet, the Daubechy 45 wavelet presented the highest average ranking. No effect of the stroke spin, racket characteristics and impact zone was observed for the selection of the best mother wavelet. It was concluded that alternative approach to Fast Fourier Transform should be used to interpret tennis vibration signals. In the case where wavelet transform is chosen, the Daubechy 45 mother wavelet appeared to be the most suitable. Copyright © 2017 Elsevier Ltd. All rights reserved.

Wavelets, non-linearity and turbulence in fusion plasmas

NASA Astrophysics Data System (ADS)

van Milligen, B. Ph.

Introduction Linear spectral analysis tools Wavelet analysis Wavelet spectra and coherence Joint wavelet phase-frequency spectra Non-linear spectral analysis tools Wavelet bispectra and bicoherence Interpretation of the bicoherence Analysis of computer-generated data Coupled van der Pol oscillators A large eddy simulation model for two-fluid plasma turbulence A long wavelength plasma drift wave model Analysis of plasma edge turbulence from Langmuir probe data Radial coherence observed on the TJ-IU torsatron Bicoherence profile at the L/H transition on CCT Conclusions

Bayesian reconstruction of gravitational wave bursts using chirplets

NASA Astrophysics Data System (ADS)

Millhouse, Margaret; Cornish, Neil; Littenberg, Tyson

2017-01-01

The BayesWave algorithm has been shown to accurately reconstruct unmodeled short duration gravitational wave bursts and to distinguish between astrophysical signals and transient noise events. BayesWave does this by using a variable number of sine-Gaussian (Morlet) wavelets to reconstruct data in multiple interferometers. While the Morlet wavelets can be summed together to produce any possible waveform, there could be other wavelet functions that improve the performance. Because we expect most astrophysical gravitational wave signals to evolve in frequency, modified Morlet wavelets with linear frequency evolution - called chirplets - may better reconstruct signals with fewer wavelets. We compare the performance of BayesWave using Morlet wavelets and chirplets on a variety of simulated signals.

Research on artificial neural network intrusion detection photochemistry based on the improved wavelet analysis and transformation

NASA Astrophysics Data System (ADS)

Li, Hong; Ding, Xue

2017-03-01

This paper combines wavelet analysis and wavelet transform theory with artificial neural network, through the pretreatment on point feature attributes before in intrusion detection, to make them suitable for improvement of wavelet neural network. The whole intrusion classification model gets the better adaptability, self-learning ability, greatly enhances the wavelet neural network for solving the problem of field detection invasion, reduces storage space, contributes to improve the performance of the constructed neural network, and reduces the training time. Finally the results of the KDDCup99 data set simulation experiment shows that, this method reduces the complexity of constructing wavelet neural network, but also ensures the accuracy of the intrusion classification.

Using wavelet denoising and mathematical morphology in the segmentation technique applied to blood cells images.

PubMed

Boix, Macarena; Cantó, Begoña

2013-04-01

Accurate image segmentation is used in medical diagnosis since this technique is a noninvasive pre-processing step for biomedical treatment. In this work we present an efficient segmentation method for medical image analysis. In particular, with this method blood cells can be segmented. For that, we combine the wavelet transform with morphological operations. Moreover, the wavelet thresholding technique is used to eliminate the noise and prepare the image for suitable segmentation. In wavelet denoising we determine the best wavelet that shows a segmentation with the largest area in the cell. We study different wavelet families and we conclude that the wavelet db1 is the best and it can serve for posterior works on blood pathologies. The proposed method generates goods results when it is applied on several images. Finally, the proposed algorithm made in MatLab environment is verified for a selected blood cells.

Method and system for progressive mesh storage and reconstruction using wavelet-encoded height fields

NASA Technical Reports Server (NTRS)

Baxes, Gregory A. (Inventor); Linger, Timothy C. (Inventor)

2011-01-01

Systems and methods are provided for progressive mesh storage and reconstruction using wavelet-encoded height fields. A method for progressive mesh storage includes reading raster height field data, and processing the raster height field data with a discrete wavelet transform to generate wavelet-encoded height fields. In another embodiment, a method for progressive mesh storage includes reading texture map data, and processing the texture map data with a discrete wavelet transform to generate wavelet-encoded texture map fields. A method for reconstructing a progressive mesh from wavelet-encoded height field data includes determining terrain blocks, and a level of detail required for each terrain block, based upon a viewpoint. Triangle strip constructs are generated from vertices of the terrain blocks, and an image is rendered utilizing the triangle strip constructs. Software products that implement these methods are provided.

Method and system for progressive mesh storage and reconstruction using wavelet-encoded height fields

NASA Technical Reports Server (NTRS)

Baxes, Gregory A. (Inventor)

2010-01-01

Systems and methods are provided for progressive mesh storage and reconstruction using wavelet-encoded height fields. A method for progressive mesh storage includes reading raster height field data, and processing the raster height field data with a discrete wavelet transform to generate wavelet-encoded height fields. In another embodiment, a method for progressive mesh storage includes reading texture map data, and processing the texture map data with a discrete wavelet transform to generate wavelet-encoded texture map fields. A method for reconstructing a progressive mesh from wavelet-encoded height field data includes determining terrain blocks, and a level of detail required for each terrain block, based upon a viewpoint. Triangle strip constructs are generated from vertices of the terrain blocks, and an image is rendered utilizing the triangle strip constructs. Software products that implement these methods are provided.

The Wavelet Element Method. Part 2; Realization and Additional Features in 2D and 3D

NASA Technical Reports Server (NTRS)

Canuto, Claudio; Tabacco, Anita; Urban, Karsten

1998-01-01

The Wavelet Element Method (WEM) provides a construction of multiresolution systems and biorthogonal wavelets on fairly general domains. These are split into subdomains that are mapped to a single reference hypercube. Tensor products of scaling functions and wavelets defined on the unit interval are used on the reference domain. By introducing appropriate matching conditions across the interelement boundaries, a globally continuous biorthogonal wavelet basis on the general domain is obtained. This construction does not uniquely define the basis functions but rather leaves some freedom for fulfilling additional features. In this paper we detail the general construction principle of the WEM to the 1D, 2D and 3D cases. We address additional features such as symmetry, vanishing moments and minimal support of the wavelet functions in each particular dimension. The construction is illustrated by using biorthogonal spline wavelets on the interval.

Wavelet analysis techniques applied to removing varying spectroscopic background in calibration model for pear sugar content

NASA Astrophysics Data System (ADS)

Liu, Yande; Ying, Yibin; Lu, Huishan; Fu, Xiaping

2005-11-01

A new method is proposed to eliminate the varying background and noise simultaneously for multivariate calibration of Fourier transform near infrared (FT-NIR) spectral signals. An ideal spectrum signal prototype was constructed based on the FT-NIR spectrum of fruit sugar content measurement. The performances of wavelet based threshold de-noising approaches via different combinations of wavelet base functions were compared. Three families of wavelet base function (Daubechies, Symlets and Coiflets) were applied to estimate the performance of those wavelet bases and threshold selection rules by a series of experiments. The experimental results show that the best de-noising performance is reached via the combinations of Daubechies 4 or Symlet 4 wavelet base function. Based on the optimization parameter, wavelet regression models for sugar content of pear were also developed and result in a smaller prediction error than a traditional Partial Least Squares Regression (PLSR) mode.

Speckle noise reduction in quantitative optical metrology techniques by application of the discrete wavelet transformation

NASA Astrophysics Data System (ADS)

Furlong, Cosme; Pryputniewicz, Ryszard J.

2002-06-01

Effective suppression of speckle noise content in interferometric data images can help in improving accuracy and resolution of the results obtained with interferometric optical metrology techniques. In this paper, novel speckle noise reduction algorithms based on the discrete wavelet transformation are presented. The algorithms proceed by: (a) estimating the noise level contained in the interferograms of interest, (b) selecting wavelet families, (c) applying the wavelet transformation using the selected families, (d) wavelet thresholding, and (e) applying the inverse wavelet transformation, producing denoised interferograms. The algorithms are applied to the different stages of the processing procedures utilized for generation of quantitative speckle correlation interferometry data of fiber-optic based opto-electronic holography (FOBOEH) techniques, allowing identification of optimal processing conditions. It is shown that wavelet algorithms are effective for speckle noise reduction while preserving image features otherwise faded with other algorithms.

Two-dimensional wavelet transform for reliability-guided phase unwrapping in optical fringe pattern analysis.

PubMed

Li, Sikun; Wang, Xiangzhao; Su, Xianyu; Tang, Feng

2012-04-20

This paper theoretically discusses modulus of two-dimensional (2D) wavelet transform (WT) coefficients, calculated by using two frequently used 2D daughter wavelet definitions, in an optical fringe pattern analysis. The discussion shows that neither is good enough to represent the reliability of the phase data. The differences between the two frequently used 2D daughter wavelet definitions in the performance of 2D WT also are discussed. We propose a new 2D daughter wavelet definition for reliability-guided phase unwrapping of optical fringe pattern. The modulus of the advanced 2D WT coefficients, obtained by using a daughter wavelet under this new daughter wavelet definition, includes not only modulation information but also local frequency information of the deformed fringe pattern. Therefore, it can be treated as a good parameter that represents the reliability of the retrieved phase data. Computer simulation and experimentation show the validity of the proposed method.

Discrete wavelet approach to multifractality

NASA Astrophysics Data System (ADS)

Isaacson, Susana I.; Gabbanelli, Susana C.; Busch, Jorge R.

2000-12-01

The use of wavelet techniques for the multifractal analysis generalizes the box counting approach, and in addition provides information on eventual deviations of multifractal behavior. By the introduction of a wavelet partition function Wq and its corresponding free energy (beta) (q), the discrepancies between (beta) (q) and the multifractal free energy r(q) are shown to be indicative of these deviations. We study with Daubechies wavelets (D4) some 1D examples previously treated with Haar wavelets, and we apply the same ideas to some 2D Monte Carlo configurations, that simulate a solution under the action of an attractive potential. In this last case, we study the influence in the multifractal spectra and partition functions of four physical parameters: the intensity of the pairwise potential, the temperature, the range of the model potential, and the concentration of the solution. The wavelet partition function Wq carries more information about the cluster statistics than the multifractal partition function Zq, and the location of its peaks contributes to the determination of characteristic sales of the measure. In our experiences, the information provided by Daubechies wavelet sis slightly more accurate than the one obtained by Haar wavelets.

Extracting time-frequency feature of single-channel vastus medialis EMG signals for knee exercise pattern recognition.

PubMed

Zhang, Yi; Li, Peiyang; Zhu, Xuyang; Su, Steven W; Guo, Qing; Xu, Peng; Yao, Dezhong

2017-01-01

The EMG signal indicates the electrophysiological response to daily living of activities, particularly to lower-limb knee exercises. Literature reports have shown numerous benefits of the Wavelet analysis in EMG feature extraction for pattern recognition. However, its application to typical knee exercises when using only a single EMG channel is limited. In this study, three types of knee exercises, i.e., flexion of the leg up (standing), hip extension from a sitting position (sitting) and gait (walking) are investigated from 14 healthy untrained subjects, while EMG signals from the muscle group of vastus medialis and the goniometer on the knee joint of the detected leg are synchronously monitored and recorded. Four types of lower-limb motions including standing, sitting, stance phase of walking, and swing phase of walking, are segmented. The Wavelet Transform (WT) based Singular Value Decomposition (SVD) approach is proposed for the classification of four lower-limb motions using a single-channel EMG signal from the muscle group of vastus medialis. Based on lower-limb motions from all subjects, the combination of five-level wavelet decomposition and SVD is used to comprise the feature vector. The Support Vector Machine (SVM) is then configured to build a multiple-subject classifier for which the subject independent accuracy will be given across all subjects for the classification of four types of lower-limb motions. In order to effectively indicate the classification performance, EMG features from time-domain (e.g., Mean Absolute Value (MAV), Root-Mean-Square (RMS), integrated EMG (iEMG), Zero Crossing (ZC)) and frequency-domain (e.g., Mean Frequency (MNF) and Median Frequency (MDF)) are also used to classify lower-limb motions. The five-fold cross validation is performed and it repeats fifty times in order to acquire the robust subject independent accuracy. Results show that the proposed WT-based SVD approach has the classification accuracy of 91.85%±0.88% which outperforms other feature models.

Weld quality inspection using laser-EMAT ultrasonic system and C-scan method

NASA Astrophysics Data System (ADS)

Yang, Lei; Ume, I. Charles

2014-02-01

Laser/EMAT ultrasonic technique has attracted more and more interests in weld quality inspection because of its non-destructive and non-contact characteristics. When ultrasonic techniques are used to detect welds joining relative thin plates, the dominant ultrasonic waves present in the plates are Lamb waves, which propagate all through the thickness. Traditional Time of Flight(ToF) method loses its power. The broadband nature of laser excited ultrasound plus dispersive and multi-modal characteristic of Lamb waves make the EMAT acquired signals very complicated in this situation. Challenge rises in interpreting the received signals and establishing relationship between signal feature and weld quality. In this paper, the laser/EMAT ultrasonic technique was applied in a C-scan manner to record full wave propagation field over an area close to the weld. Then the effect of weld defect on the propagation field of Lamb waves was studied visually by watching an movie resulted from the recorded signals. This method was proved to be effective to detect the presence of hidden defect in the weld. Discrete wavelet transform(DWT) was applied to characterize the acquired ultrasonic signals and ideal band-pass filter was used to isolate wave components most sensitive to the weld defect. Different interactions with the weld defect were observed for different wave components. Thus this C-Scan method, combined with DWT and ideal band-pass filter, proved to be an effective methodology to experimentally study interactions of various laser excited Lamb Wave components with weld defect. In this work, the method was demonstrated by inspecting a hidden local incomplete penetration in weld. In fact, this method can be applied to study Lamb Wave interactions with any type of structural inconsistency. This work also proposed a ideal filtered based method to effectively reduce the total experimental time.

Analysis of swallowing sounds using hidden Markov models.

PubMed

Aboofazeli, Mohammad; Moussavi, Zahra

2008-04-01

In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This paper presents a hidden Markov model (HMM) based method for the swallowing sound segmentation and classification. Swallowing sound signals of 15 healthy and 11 dysphagic subjects were studied. The signals were divided into sequences of 25 ms segments each of which were represented by seven features. The sequences of features were modeled by HMMs. Trained HMMs were used for segmentation of the swallowing sounds into three distinct phases, i.e., initial quiet period, initial discrete sounds (IDS) and bolus transit sounds (BTS). Among the seven features, accuracy of segmentation by the HMM based on multi-scale product of wavelet coefficients was higher than that of the other HMMs and the linear prediction coefficient (LPC)-based HMM showed the weakest performance. In addition, HMMs were used for classification of the swallowing sounds of healthy subjects and dysphagic patients. Classification accuracy of different HMM configurations was investigated. When we increased the number of states of the HMMs from 4 to 8, the classification error gradually decreased. In most cases, classification error for N=9 was higher than that of N=8. Among the seven features used, root mean square (RMS) and waveform fractal dimension (WFD) showed the best performance in the HMM-based classification of swallowing sounds. When the sequences of the features of IDS segment were modeled separately, the accuracy reached up to 85.5%. As a second stage classification, a screening algorithm was used which correctly classified all the subjects but one healthy subject when RMS was used as characteristic feature of the swallowing sounds and the number of states was set to N=8.

A Comparative Analysis for Selection of Appropriate Mother Wavelet for Detection of Stationary Disturbances

NASA Astrophysics Data System (ADS)

Kamble, Saurabh Prakash; Thawkar, Shashank; Gaikwad, Vinayak G.; Kothari, D. P.

2017-12-01

Detection of disturbances is the first step of mitigation. Power electronics plays a crucial role in modern power system which makes system operation efficient but it also bring stationary disturbances in the power system and added impurities to the supply. It happens because of the non-linear loads used in modern day power system which inject disturbances like harmonic disturbances, flickers, sag etc. in power grid. These impurities can damage equipments so it is necessary to mitigate these impurities present in the supply very quickly. So, digital signal processing techniques are incorporated for detection purpose. Signal processing techniques like fast Fourier transform, short-time Fourier transform, Wavelet transform etc. are widely used for the detection of disturbances. Among all, wavelet transform is widely used because of its better detection capabilities. But, which mother wavelet has to use for detection is still a mystery. Depending upon the periodicity, the disturbances are classified as stationary and non-stationary disturbances. This paper presents the importance of selection of mother wavelet for analyzing stationary disturbances using discrete wavelet transform. Signals with stationary disturbances of various frequencies are generated using MATLAB. The analysis of these signals is done using various mother wavelets like Daubechies and bi-orthogonal wavelets and the measured root mean square value of stationary disturbance is obtained. The measured value obtained by discrete wavelet transform is compared with the exact RMS value of the frequency component and the percentage differences are presented which helps to select optimum mother wavelet.

Wavelet extractor: A Bayesian well-tie and wavelet extraction program

NASA Astrophysics Data System (ADS)

Gunning, James; Glinsky, Michael E.

2006-06-01

We introduce a new open-source toolkit for the well-tie or wavelet extraction problem of estimating seismic wavelets from seismic data, time-to-depth information, and well-log suites. The wavelet extraction model is formulated as a Bayesian inverse problem, and the software will simultaneously estimate wavelet coefficients, other parameters associated with uncertainty in the time-to-depth mapping, positioning errors in the seismic imaging, and useful amplitude-variation-with-offset (AVO) related parameters in multi-stack extractions. It is capable of multi-well, multi-stack extractions, and uses continuous seismic data-cube interpolation to cope with the problem of arbitrary well paths. Velocity constraints in the form of checkshot data, interpreted markers, and sonic logs are integrated in a natural way. The Bayesian formulation allows computation of full posterior uncertainties of the model parameters, and the important problem of the uncertain wavelet span is addressed uses a multi-model posterior developed from Bayesian model selection theory. The wavelet extraction tool is distributed as part of the Delivery seismic inversion toolkit. A simple log and seismic viewing tool is included in the distribution. The code is written in Java, and thus platform independent, but the Seismic Unix (SU) data model makes the inversion particularly suited to Unix/Linux environments. It is a natural companion piece of software to Delivery, having the capacity to produce maximum likelihood wavelet and noise estimates, but will also be of significant utility to practitioners wanting to produce wavelet estimates for other inversion codes or purposes. The generation of full parameter uncertainties is a crucial function for workers wishing to investigate questions of wavelet stability before proceeding to more advanced inversion studies.

A novel neural-wavelet approach for process diagnostics and complex system modeling

NASA Astrophysics Data System (ADS)

Gao, Rong

Neural networks have been effective in several engineering applications because of their learning abilities and robustness. However certain shortcomings, such as slow convergence and local minima, are always associated with neural networks, especially neural networks applied to highly nonlinear and non-stationary problems. These problems can be effectively alleviated by integrating a new powerful tool, wavelets, into conventional neural networks. The multi-resolution analysis and feature localization capabilities of the wavelet transform offer neural networks new possibilities for learning. A neural wavelet network approach developed in this thesis enjoys fast convergence rate with little possibility to be caught at a local minimum. It combines the localization properties of wavelets with the learning abilities of neural networks. Two different testbeds are used for testing the efficiency of the new approach. The first is magnetic flowmeter-based process diagnostics: here we extend previous work, which has demonstrated that wavelet groups contain process information, to more general process diagnostics. A loop at Applied Intelligent Systems Lab (AISL) is used for collecting and analyzing data through the neural-wavelet approach. The research is important for thermal-hydraulic processes in nuclear and other engineering fields. The neural-wavelet approach developed is also tested with data from the electric power grid. More specifically, the neural-wavelet approach is used for performing short-term and mid-term prediction of power load demand. In addition, the feasibility of determining the type of load using the proposed neural wavelet approach is also examined. The notion of cross scale product has been developed as an expedient yet reliable discriminator of loads. Theoretical issues involved in the integration of wavelets and neural networks are discussed and future work outlined.

Short-Circuit Fault Detection and Classification Using Empirical Wavelet Transform and Local Energy for Electric Transmission Line.

PubMed

Huang, Nantian; Qi, Jiajin; Li, Fuqing; Yang, Dongfeng; Cai, Guowei; Huang, Guilin; Zheng, Jian; Li, Zhenxin

2017-09-16

In order to improve the classification accuracy of recognizing short-circuit faults in electric transmission lines, a novel detection and diagnosis method based on empirical wavelet transform (EWT) and local energy (LE) is proposed. First, EWT is used to deal with the original short-circuit fault signals from photoelectric voltage transformers, before the amplitude modulated-frequency modulated (AM-FM) mode with a compactly supported Fourier spectrum is extracted. Subsequently, the fault occurrence time is detected according to the modulus maxima of intrinsic mode function (IMF₂) from three-phase voltage signals processed by EWT. After this process, the feature vectors are constructed by calculating the LE of the fundamental frequency based on the three-phase voltage signals of one period after the fault occurred. Finally, the classifier based on support vector machine (SVM) which was constructed with the LE feature vectors is used to classify 10 types of short-circuit fault signals. Compared with complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and improved CEEMDAN methods, the new method using EWT has a better ability to present the frequency in time. The difference in the characteristics of the energy distribution in the time domain between different types of short-circuit faults can be presented by the feature vectors of LE. Together, simulation and real signals experiment demonstrate the validity and effectiveness of the new approach.

Three-Class Mammogram Classification Based on Descriptive CNN Features

PubMed Central

Zhang, Qianni; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. PMID:28191461

Three-Class Mammogram Classification Based on Descriptive CNN Features.

PubMed

Jadoon, M Mohsin; Zhang, Qianni; Haq, Ihsan Ul; Butt, Sharjeel; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

Short-Circuit Fault Detection and Classification Using Empirical Wavelet Transform and Local Energy for Electric Transmission Line

PubMed Central

Huang, Nantian; Qi, Jiajin; Li, Fuqing; Yang, Dongfeng; Cai, Guowei; Huang, Guilin; Zheng, Jian; Li, Zhenxin

2017-01-01

In order to improve the classification accuracy of recognizing short-circuit faults in electric transmission lines, a novel detection and diagnosis method based on empirical wavelet transform (EWT) and local energy (LE) is proposed. First, EWT is used to deal with the original short-circuit fault signals from photoelectric voltage transformers, before the amplitude modulated-frequency modulated (AM-FM) mode with a compactly supported Fourier spectrum is extracted. Subsequently, the fault occurrence time is detected according to the modulus maxima of intrinsic mode function (IMF2) from three-phase voltage signals processed by EWT. After this process, the feature vectors are constructed by calculating the LE of the fundamental frequency based on the three-phase voltage signals of one period after the fault occurred. Finally, the classifier based on support vector machine (SVM) which was constructed with the LE feature vectors is used to classify 10 types of short-circuit fault signals. Compared with complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and improved CEEMDAN methods, the new method using EWT has a better ability to present the frequency in time. The difference in the characteristics of the energy distribution in the time domain between different types of short-circuit faults can be presented by the feature vectors of LE. Together, simulation and real signals experiment demonstrate the validity and effectiveness of the new approach. PMID:28926953

Wavelet-based information filtering for fault diagnosis of electric drive systems in electric ships.

PubMed

Silva, Andre A; Gupta, Shalabh; Bazzi, Ali M; Ulatowski, Arthur

2017-09-22

Electric machines and drives have enjoyed extensive applications in the field of electric vehicles (e.g., electric ships, boats, cars, and underwater vessels) due to their ease of scalability and wide range of operating conditions. This stems from their ability to generate the desired torque and power levels for propulsion under various external load conditions. However, as with the most electrical systems, the electric drives are prone to component failures that can degrade their performance, reduce the efficiency, and require expensive maintenance. Therefore, for safe and reliable operation of electric vehicles, there is a need for automated early diagnostics of critical failures such as broken rotor bars and electrical phase failures. In this regard, this paper presents a fault diagnosis methodology for electric drives in electric ships. This methodology utilizes the two-dimensional, i.e. scale-shift, wavelet transform of the sensor data to filter optimal information-rich regions which can enhance the diagnosis accuracy as well as reduce the computational complexity of the classifier. The methodology was tested on sensor data generated from an experimentally validated simulation model of electric drives under various cruising speed conditions. The results in comparison with other existing techniques show a high correct classification rate with low false alarm and miss detection rates. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Mobile Healthcare for Automatic Driving Sleep-Onset Detection Using Wavelet-Based EEG and Respiration Signals

PubMed Central

Lee, Boon-Giin; Lee, Boon-Leng; Chung, Wan-Young

2014-01-01

Driving drowsiness is a major cause of traffic accidents worldwide and has drawn the attention of researchers in recent decades. This paper presents an application for in-vehicle non-intrusive mobile-device-based automatic detection of driver sleep-onset in real time. The proposed application classifies the driving mental fatigue condition by analyzing the electroencephalogram (EEG) and respiration signals of a driver in the time and frequency domains. Our concept is heavily reliant on mobile technology, particularly remote physiological monitoring using Bluetooth. Respiratory events are gathered, and eight-channel EEG readings are captured from the frontal, central, and parietal (Fpz-Cz, Pz-Oz) regions. EEGs are preprocessed with a Butterworth bandpass filter, and features are subsequently extracted from the filtered EEG signals by employing the wavelet-packet-transform (WPT) method to categorize the signals into four frequency bands: α, β, θ, and δ. A mutual information (MI) technique selects the most descriptive features for further classification. The reduction in the number of prominent features improves the sleep-onset classification speed in the support vector machine (SVM) and results in a high sleep-onset recognition rate. Test results reveal that the combined use of the EEG and respiration signals results in 98.6% recognition accuracy. Our proposed application explores the possibility of processing long-term multi-channel signals. PMID:25264954

Design of a hybrid model for cardiac arrhythmia classification based on Daubechies wavelet transform.

PubMed

Rajagopal, Rekha; Ranganathan, Vidhyapriya

2018-06-05

Automation in cardiac arrhythmia classification helps medical professionals make accurate decisions about the patient's health. The aim of this work was to design a hybrid classification model to classify cardiac arrhythmias. The design phase of the classification model comprises the following stages: preprocessing of the cardiac signal by eliminating detail coefficients that contain noise, feature extraction through Daubechies wavelet transform, and arrhythmia classification using a collaborative decision from the K nearest neighbor classifier (KNN) and a support vector machine (SVM). The proposed model is able to classify 5 arrhythmia classes as per the ANSI/AAMI EC57: 1998 classification standard. Level 1 of the proposed model involves classification using the KNN and the classifier is trained with examples from all classes. Level 2 involves classification using an SVM and is trained specifically to classify overlapped classes. The final classification of a test heartbeat pertaining to a particular class is done using the proposed KNN/SVM hybrid model. The experimental results demonstrated that the average sensitivity of the proposed model was 92.56%, the average specificity 99.35%, the average positive predictive value 98.13%, the average F-score 94.5%, and the average accuracy 99.78%. The results obtained using the proposed model were compared with the results of discriminant, tree, and KNN classifiers. The proposed model is able to achieve a high classification accuracy.

3D Riesz-wavelet based Covariance descriptors for texture classification of lung nodule tissue in CT.

PubMed

Cirujeda, Pol; Muller, Henning; Rubin, Daniel; Aguilera, Todd A; Loo, Billy W; Diehn, Maximilian; Binefa, Xavier; Depeursinge, Adrien

2015-01-01

In this paper we present a novel technique for characterizing and classifying 3D textured volumes belonging to different lung tissue types in 3D CT images. We build a volume-based 3D descriptor, robust to changes of size, rigid spatial transformations and texture variability, thanks to the integration of Riesz-wavelet features within a Covariance-based descriptor formulation. 3D Riesz features characterize the morphology of tissue density due to their response to changes in intensity in CT images. These features are encoded in a Covariance-based descriptor formulation: this provides a compact and flexible representation thanks to the use of feature variations rather than dense features themselves and adds robustness to spatial changes. Furthermore, the particular symmetric definite positive matrix form of these descriptors causes them to lay in a Riemannian manifold. Thus, descriptors can be compared with analytical measures, and accurate techniques from machine learning and clustering can be adapted to their spatial domain. Additionally we present a classification model following a "Bag of Covariance Descriptors" paradigm in order to distinguish three different nodule tissue types in CT: solid, ground-glass opacity, and healthy lung. The method is evaluated on top of an acquired dataset of 95 patients with manually delineated ground truth by radiation oncology specialists in 3D, and quantitative sensitivity and specificity values are presented.

Prediction of Air Pollutants Concentration Based on an Extreme Learning Machine: The Case of Hong Kong

PubMed Central

Zhang, Jiangshe; Ding, Weifu

2017-01-01

With the development of the economy and society all over the world, most metropolitan cities are experiencing elevated concentrations of ground-level air pollutants. It is urgent to predict and evaluate the concentration of air pollutants for some local environmental or health agencies. Feed-forward artificial neural networks have been widely used in the prediction of air pollutants concentration. However, there are some drawbacks, such as the low convergence rate and the local minimum. The extreme learning machine for single hidden layer feed-forward neural networks tends to provide good generalization performance at an extremely fast learning speed. The major sources of air pollutants in Hong Kong are mobile, stationary, and from trans-boundary sources. We propose predicting the concentration of air pollutants by the use of trained extreme learning machines based on the data obtained from eight air quality parameters in two monitoring stations, including Sham Shui Po and Tap Mun in Hong Kong for six years. The experimental results show that our proposed algorithm performs better on the Hong Kong data both quantitatively and qualitatively. Particularly, our algorithm shows better predictive ability, with R2 increased and root mean square error values decreased respectively. PMID:28125034

Sequential Nonlinear Learning for Distributed Multiagent Systems via Extreme Learning Machines.

PubMed

Vanli, Nuri Denizcan; Sayin, Muhammed O; Delibalta, Ibrahim; Kozat, Suleyman Serdar

2017-03-01

We study online nonlinear learning over distributed multiagent systems, where each agent employs a single hidden layer feedforward neural network (SLFN) structure to sequentially minimize arbitrary loss functions. In particular, each agent trains its own SLFN using only the data that is revealed to itself. On the other hand, the aim of the multiagent system is to train the SLFN at each agent as well as the optimal centralized batch SLFN that has access to all the data, by exchanging information between neighboring agents. We address this problem by introducing a distributed subgradient-based extreme learning machine algorithm. The proposed algorithm provides guaranteed upper bounds on the performance of the SLFN at each agent and shows that each of these individual SLFNs asymptotically achieves the performance of the optimal centralized batch SLFN. Our performance guarantees explicitly distinguish the effects of data- and network-dependent parameters on the convergence rate of the proposed algorithm. The experimental results illustrate that the proposed algorithm achieves the oracle performance significantly faster than the state-of-the-art methods in the machine learning and signal processing literature. Hence, the proposed method is highly appealing for the applications involving big data.

An implementation of Elman neural network for polycystic ovary classification based on ultrasound images

NASA Astrophysics Data System (ADS)

Thufailah, I. F.; Adiwijaya; Wisesty, U. N.; Jondri

2018-03-01

Polycystic Ovary Syndrome (PCOS) is a reproduction problem that causes irregular menstruation period. Insulin and androgen hormone have big roles for this problem. This syndrome should be detected shortly, since it is able to cause a more serious disease, such as cardiovascular, diabetes, and obesity. The detection of this syndrome is done by analyzing ovary morphology and hormone test. However, the more economical way of test is by identifying the ovary morphology using ultrasonography. To classify whether one ovary is normal or it has polycystic ovary (PCO) follicle, the analysis will be done manually by a gynecologist. This paper will design a system to detect PCO using Gabor Wavelet method for feature extraction and Elman Neural Network is used to classify PCO and non-PCO. Elman Neural Network is chosen because it contains context layer to recall the previous condition. This paper compared the accuracy and process time of each dataset, then also did testing on elman’s parameters, such as layer delay, hidden layer, and training function. Based on tests done in this paper, the most accurate number is 78.1% with 32 features.

Foliage penetration by using 4-D point cloud data

NASA Astrophysics Data System (ADS)

Méndez Rodríguez, Javier; Sánchez-Reyes, Pedro J.; Cruz-Rivera, Sol M.

2012-06-01

Real-time awareness and rapid target detection are critical for the success of military missions. New technologies capable of detecting targets concealed in forest areas are needed in order to track and identify possible threats. Currently, LAser Detection And Ranging (LADAR) systems are capable of detecting obscured targets; however, tracking capabilities are severely limited. Now, a new LADAR-derived technology is under development to generate 4-D datasets (3-D video in a point cloud format). As such, there is a new need for algorithms that are able to process data in real time. We propose an algorithm capable of removing vegetation and other objects that may obfuscate concealed targets in a real 3-D environment. The algorithm is based on wavelets and can be used as a pre-processing step in a target recognition algorithm. Applications of the algorithm in a real-time 3-D system could help make pilots aware of high risk hidden targets such as tanks and weapons, among others. We will be using a 4-D simulated point cloud data to demonstrate the capabilities of our algorithm.

Semantic Annotations and Querying of Web Data Sources

NASA Astrophysics Data System (ADS)

Hornung, Thomas; May, Wolfgang

A large part of the Web, actually holding a significant portion of the useful information throughout the Web, consists of views on hidden databases, provided by numerous heterogeneous interfaces that are partly human-oriented via Web forms ("Deep Web"), and partly based on Web Services (only machine accessible). In this paper we present an approach for annotating these sources in a way that makes them citizens of the Semantic Web. We illustrate how queries can be stated in terms of the ontology, and how the annotations are used to selected and access appropriate sources and to answer the queries.

Applications Using High Flux LCS gamma-ray Beams: Nuclear Security and Contributions to Fukushima

NASA Astrophysics Data System (ADS)

Fujiwara, Mamoru

2014-09-01

Nuclear nonproliferation and security are an important issue for the peaceful use of nuclear energy. Many countries now collaborate together for preventing serious accidents from nuclear terrorism. Detection of hidden long-lived radioisotopes and fissionable nuclides in a non-destructive manner is useful for nuclear safeguards and management of nuclear wastes as well as nuclear security. After introducing the present situation concerning the nuclear nonproliferation and security in Japan, we plan to show the present activities of JAEA to detect the hidden nuclear materials by means of the nuclear resonance fluorescence with energy-tunable, monochromatic gamma-rays generated by Laser Compton Scattering (LCS) with an electron beam. The energy recovery linac (ERL) machine is now under development with the KEK-JAEA collaboration for realizing the new generation of gamma-ray sources. The detection technologies of nuclear materials are currently developed using the existing electron beam facilities at Duke University and at NewSubaru. These developments in Japan will contribute to the nuclear security program in Japan and to the assay of melted nuclear fuels in the Fukushima Daiichi nuclear power plants.

Shift-, rotation-, and scale-invariant shape recognition system using an optical Hough transform

NASA Astrophysics Data System (ADS)

Schmid, Volker R.; Bader, Gerhard; Lueder, Ernst H.

1998-02-01

We present a hybrid shape recognition system with an optical Hough transform processor. The features of the Hough space offer a separate cancellation of distortions caused by translations and rotations. Scale invariance is also provided by suitable normalization. The proposed system extends the capabilities of Hough transform based detection from only straight lines to areas bounded by edges. A very compact optical design is achieved by a microlens array processor accepting incoherent light as direct optical input and realizing the computationally expensive connections massively parallel. Our newly developed algorithm extracts rotation and translation invariant normalized patterns of bright spots on a 2D grid. A neural network classifier maps the 2D features via a nonlinear hidden layer onto the classification output vector. We propose initialization of the connection weights according to regions of activity specifically assigned to each neuron in the hidden layer using a competitive network. The presented system is designed for industry inspection applications. Presently we have demonstrated detection of six different machined parts in real-time. Our method yields very promising detection results of more than 96% correctly classified parts.

Autoregressive-moving-average hidden Markov model for vision-based fall prediction-An application for walker robot.

PubMed

Taghvaei, Sajjad; Jahanandish, Mohammad Hasan; Kosuge, Kazuhiro

2017-01-01

Population aging of the societies requires providing the elderly with safe and dependable assistive technologies in daily life activities. Improving the fall detection algorithms can play a major role in achieving this goal. This article proposes a real-time fall prediction algorithm based on the acquired visual data of a user with walking assistive system from a depth sensor. In the lack of a coupled dynamic model of the human and the assistive walker a hybrid "system identification-machine learning" approach is used. An autoregressive-moving-average (ARMA) model is fitted on the time-series walking data to forecast the upcoming states, and a hidden Markov model (HMM) based classifier is built on the top of the ARMA model to predict falling in the upcoming time frames. The performance of the algorithm is evaluated through experiments with four subjects including an experienced physiotherapist while using a walker robot in five different falling scenarios; namely, fall forward, fall down, fall back, fall left, and fall right. The algorithm successfully predicts the fall with a rate of 84.72%.

A new learning paradigm: learning using privileged information.

PubMed

Vapnik, Vladimir; Vashist, Akshay

2009-01-01

In the Afterword to the second edition of the book "Estimation of Dependences Based on Empirical Data" by V. Vapnik, an advanced learning paradigm called Learning Using Hidden Information (LUHI) was introduced. This Afterword also suggested an extension of the SVM method (the so called SVM(gamma)+ method) to implement algorithms which address the LUHI paradigm (Vapnik, 1982-2006, Sections 2.4.2 and 2.5.3 of the Afterword). See also (Vapnik, Vashist, & Pavlovitch, 2008, 2009) for further development of the algorithms. In contrast to the existing machine learning paradigm where a teacher does not play an important role, the advanced learning paradigm considers some elements of human teaching. In the new paradigm along with examples, a teacher can provide students with hidden information that exists in explanations, comments, comparisons, and so on. This paper discusses details of the new paradigm and corresponding algorithms, introduces some new algorithms, considers several specific forms of privileged information, demonstrates superiority of the new learning paradigm over the classical learning paradigm when solving practical problems, and discusses general questions related to the new ideas.

Reverse engineering a social agent-based hidden markov model--visage.

PubMed

Chen, Hung-Ching Justin; Goldberg, Mark; Magdon-Ismail, Malik; Wallace, William A

2008-12-01

We present a machine learning approach to discover the agent dynamics that drives the evolution of the social groups in a community. We set up the problem by introducing an agent-based hidden Markov model for the agent dynamics: an agent's actions are determined by micro-laws. Nonetheless, We learn the agent dynamics from the observed communications without knowing state transitions. Our approach is to identify the appropriate micro-laws corresponding to an identification of the appropriate parameters in the model. The model identification problem is then formulated as a mixed optimization problem. To solve the problem, we develop a multistage learning process for determining the group structure, the group evolution, and the micro-laws of a community based on the observed set of communications among actors, without knowing the semantic contents. Finally, to test the quality of our approximations and the feasibility of the approach, we present the results of extensive experiments on synthetic data as well as the results on real communities, such as Enron email and Movie newsgroups. Insight into agent dynamics helps us understand the driving forces behind social evolution.

A user's guide to the ssWavelets package

Treesearch

J.H. ​Gove

2017-01-01

ssWavelets is an R package that is meant to be used in conjunction with the sampSurf package (Gove, 2012) to perform wavelet decomposition on the results of a sampling surface simulation. In general, the wavelet filter decomposes the sampSurf simulation results by scale (distance), with each scale corresponding to a different level of the...

Noise adaptive wavelet thresholding for speckle noise removal in optical coherence tomography.

PubMed

Zaki, Farzana; Wang, Yahui; Su, Hao; Yuan, Xin; Liu, Xuan

2017-05-01

Optical coherence tomography (OCT) is based on coherence detection of interferometric signals and hence inevitably suffers from speckle noise. To remove speckle noise in OCT images, wavelet domain thresholding has demonstrated significant advantages in suppressing noise magnitude while preserving image sharpness. However, speckle noise in OCT images has different characteristics in different spatial scales, which has not been considered in previous applications of wavelet domain thresholding. In this study, we demonstrate a noise adaptive wavelet thresholding (NAWT) algorithm that exploits the difference of noise characteristics in different wavelet sub-bands. The algorithm is simple, fast, effective and is closely related to the physical origin of speckle noise in OCT image. Our results demonstrate that NAWT outperforms conventional wavelet thresholding.

A novel method of identifying motor primitives using wavelet decomposition*

PubMed Central

Popov, Anton; Olesh, Erienne V.; Yakovenko, Sergiy; Gritsenko, Valeriya

2018-01-01

This study reports a new technique for extracting muscle synergies using continuous wavelet transform. The method allows to quantify coincident activation of muscle groups caused by the physiological processes of fixed duration, thus enabling the extraction of wavelet modules of arbitrary groups of muscles. Hierarchical clustering and identification of the repeating wavelet modules across subjects and across movements, was used to identify consistent muscle synergies. Results indicate that the most frequently repeated wavelet modules comprised combinations of two muscles that are not traditional agonists and span different joints. We have also found that these wavelet modules were flexibly combined across different movement directions in a pattern resembling directional tuning. This method is extendable to multiple frequency domains and signal modalities.

EnvironmentalWaveletTool: Continuous and discrete wavelet analysis and filtering for environmental time series

NASA Astrophysics Data System (ADS)

Galiana-Merino, J. J.; Pla, C.; Fernandez-Cortes, A.; Cuezva, S.; Ortiz, J.; Benavente, D.

2014-10-01

A MATLAB-based computer code has been developed for the simultaneous wavelet analysis and filtering of several environmental time series, particularly focused on the analyses of cave monitoring data. The continuous wavelet transform, the discrete wavelet transform and the discrete wavelet packet transform have been implemented to provide a fast and precise time-period examination of the time series at different period bands. Moreover, statistic methods to examine the relation between two signals have been included. Finally, the entropy of curves and splines based methods have also been developed for segmenting and modeling the analyzed time series. All these methods together provide a user-friendly and fast program for the environmental signal analysis, with useful, practical and understandable results.

Spherical 3D isotropic wavelets

NASA Astrophysics Data System (ADS)

Lanusse, F.; Rassat, A.; Starck, J.-L.

2012-04-01

Context. Future cosmological surveys will provide 3D large scale structure maps with large sky coverage, for which a 3D spherical Fourier-Bessel (SFB) analysis in spherical coordinates is natural. Wavelets are particularly well-suited to the analysis and denoising of cosmological data, but a spherical 3D isotropic wavelet transform does not currently exist to analyse spherical 3D data. Aims: The aim of this paper is to present a new formalism for a spherical 3D isotropic wavelet, i.e. one based on the SFB decomposition of a 3D field and accompany the formalism with a public code to perform wavelet transforms. Methods: We describe a new 3D isotropic spherical wavelet decomposition based on the undecimated wavelet transform (UWT) described in Starck et al. (2006). We also present a new fast discrete spherical Fourier-Bessel transform (DSFBT) based on both a discrete Bessel transform and the HEALPIX angular pixelisation scheme. We test the 3D wavelet transform and as a toy-application, apply a denoising algorithm in wavelet space to the Virgo large box cosmological simulations and find we can successfully remove noise without much loss to the large scale structure. Results: We have described a new spherical 3D isotropic wavelet transform, ideally suited to analyse and denoise future 3D spherical cosmological surveys, which uses a novel DSFBT. We illustrate its potential use for denoising using a toy model. All the algorithms presented in this paper are available for download as a public code called MRS3D at http://jstarck.free.fr/mrs3d.html

Remote sensing of soil organic matter of farmland with hyperspectral image

NASA Astrophysics Data System (ADS)

Gu, Xiaohe; Wang, Lei; Yang, Guijun; Zhang, Liyan

2017-10-01

Monitoring soil organic matter (SOM) of cultivated land quantitively and mastering its spatial change are helpful for fertility adjustment and sustainable development of agriculture. The study aimed to analyze the response between SOM and reflectivity of hyperspectral image with different pixel size and develop the optimal model of estimating SOM with imaging spectral technology. The wavelet transform method was used to analyze the correlation between the hyperspectral reflectivity and SOM. Then the optimal pixel size and sensitive wavelet feature scale were screened to develop the inversion model of SOM. Result showed that wavelet transform of soil hyperspectrum was help to improve the correlation between the wavelet features and SOM. In the visible wavelength range, the susceptible wavelet features of SOM mainly concentrated 460 603 nm. As the wavelength increased, the wavelet scale corresponding correlation coefficient increased maximum and then gradually decreased. In the near infrared wavelength range, the susceptible wavelet features of SOM mainly concentrated 762 882 nm. As the wavelength increased, the wavelet scale gradually decreased. The study developed multivariate model of continuous wavelet transforms by the method of stepwise linear regression (SLR). The CWT-SLR models reached higher accuracies than those of univariate models. With the resampling scale increasing, the accuracies of CWT-SLR models gradually increased, while the determination coefficients (R2) fluctuated from 0.52 to 0.59. The R2 of 5*5 scale reached highest (0.5954), while the RMSE reached lowest (2.41 g/kg). It indicated that multivariate model based on continuous wavelet transform had better ability for estimating SOM than univariate model.

Fast generation of computer-generated holograms using wavelet shrinkage.

PubMed

Shimobaba, Tomoyoshi; Ito, Tomoyoshi

2017-01-09

Computer-generated holograms (CGHs) are generated by superimposing complex amplitudes emitted from a number of object points. However, this superposition process remains very time-consuming even when using the latest computers. We propose a fast calculation algorithm for CGHs that uses a wavelet shrinkage method, eliminating small wavelet coefficient values to express approximated complex amplitudes using only a few representative wavelet coefficients.

Determination of phase from the ridge of CWT using generalized Morse wavelet

NASA Astrophysics Data System (ADS)

Kocahan, Ozlem; Tiryaki, Erhan; Coskun, Emre; Ozder, Serhat

2018-03-01

The selection of wavelet is an important step in order to determine the phase from the fringe patterns. In the present work, a new wavelet for phase retrieval from the ridge of continuous wavelet transform (CWT) is presented. The phase distributions have been extracted from the optical fringe pattern by choosing the zero order generalized morse wavelet (GMW) as a mother wavelet. The aim of the study is to reveal the ways in which the two varying parameters of GMW affect the phase calculation. To show the validity of this method, an experimental study has been conducted by using the diffraction phase microscopy (DPM) setup; consequently, the profiles of red blood cells have been retrieved. The results for the CWT ridge technique with GMW have been compared with the results for the Morlet wavelet and the Paul wavelet; the results are almost identical for Paul and zero order GMW because of their degree of freedom. Also, for further discussion, the Fourier transform and the Stockwell transform have been applied comparatively. The outcome of the comparison reveals that GMWs are highly applicable to the research in various areas, predominantly biomedicine.

On-Line Loss of Control Detection Using Wavelets

NASA Technical Reports Server (NTRS)

Brenner, Martin J. (Technical Monitor); Thompson, Peter M.; Klyde, David H.; Bachelder, Edward N.; Rosenthal, Theodore J.

2005-01-01

Wavelet transforms are used for on-line detection of aircraft loss of control. Wavelet transforms are compared with Fourier transform methods and shown to more rapidly detect changes in the vehicle dynamics. This faster response is due to a time window that decreases in length as the frequency increases. New wavelets are defined that further decrease the detection time by skewing the shape of the envelope. The wavelets are used for power spectrum and transfer function estimation. Smoothing is used to tradeoff the variance of the estimate with detection time. Wavelets are also used as front-end to the eigensystem reconstruction algorithm. Stability metrics are estimated from the frequency response and models, and it is these metrics that are used for loss of control detection. A Matlab toolbox was developed for post-processing simulation and flight data using the wavelet analysis methods. A subset of these methods was implemented in real time and named the Loss of Control Analysis Tool Set or LOCATS. A manual control experiment was conducted using a hardware-in-the-loop simulator for a large transport aircraft, in which the real time performance of LOCATS was demonstrated. The next step is to use these wavelet analysis tools for flight test support.

Quality of reconstruction of compressed off-axis digital holograms by frequency filtering and wavelets.

PubMed

Cheremkhin, Pavel A; Kurbatova, Ekaterina A

2018-01-01

Compression of digital holograms can significantly help with the storage of objects and data in 2D and 3D form, its transmission, and its reconstruction. Compression of standard images by methods based on wavelets allows high compression ratios (up to 20-50 times) with minimum losses of quality. In the case of digital holograms, application of wavelets directly does not allow high values of compression to be obtained. However, additional preprocessing and postprocessing can afford significant compression of holograms and the acceptable quality of reconstructed images. In this paper application of wavelet transforms for compression of off-axis digital holograms are considered. The combined technique based on zero- and twin-order elimination, wavelet compression of the amplitude and phase components of the obtained Fourier spectrum, and further additional compression of wavelet coefficients by thresholding and quantization is considered. Numerical experiments on reconstruction of images from the compressed holograms are performed. The comparative analysis of applicability of various wavelets and methods of additional compression of wavelet coefficients is performed. Optimum parameters of compression of holograms by the methods can be estimated. Sizes of holographic information were decreased up to 190 times.

Time Domain Propagation of Quantum and Classical Systems using a Wavelet Basis Set Method

NASA Astrophysics Data System (ADS)

Lombardini, Richard; Nowara, Ewa; Johnson, Bruce

2015-03-01

The use of an orthogonal wavelet basis set (Optimized Maximum-N Generalized Coiflets) to effectively model physical systems in the time domain, in particular the electromagnetic (EM) pulse and quantum mechanical (QM) wavefunction, is examined in this work. Although past research has demonstrated the benefits of wavelet basis sets to handle computationally expensive problems due to their multiresolution properties, the overlapping supports of neighboring wavelet basis functions poses problems when dealing with boundary conditions, especially with material interfaces in the EM case. Specifically, this talk addresses this issue using the idea of derivative matching creating fictitious grid points (T.A. Driscoll and B. Fornberg), but replaces the latter element with fictitious wavelet projections in conjunction with wavelet reconstruction filters. Two-dimensional (2D) systems are analyzed, EM pulse incident on silver cylinders and the QM electron wave packet circling the proton in a hydrogen atom system (reduced to 2D), and the new wavelet method is compared to the popular finite-difference time-domain technique.

Fault Diagnosis for Micro-Gas Turbine Engine Sensors via Wavelet Entropy

PubMed Central

Yu, Bing; Liu, Dongdong; Zhang, Tianhong

2011-01-01

Sensor fault diagnosis is necessary to ensure the normal operation of a gas turbine system. However, the existing methods require too many resources and this need can’t be satisfied in some occasions. Since the sensor readings are directly affected by sensor state, sensor fault diagnosis can be performed by extracting features of the measured signals. This paper proposes a novel fault diagnosis method for sensors based on wavelet entropy. Based on the wavelet theory, wavelet decomposition is utilized to decompose the signal in different scales. Then the instantaneous wavelet energy entropy (IWEE) and instantaneous wavelet singular entropy (IWSE) are defined based on the previous wavelet entropy theory. Subsequently, a fault diagnosis method for gas turbine sensors is proposed based on the results of a numerically simulated example. Then, experiments on this method are carried out on a real micro gas turbine engine. In the experiment, four types of faults with different magnitudes are presented. The experimental results show that the proposed method for sensor fault diagnosis is efficient. PMID:22163734

Fault diagnosis for micro-gas turbine engine sensors via wavelet entropy.

PubMed

Yu, Bing; Liu, Dongdong; Zhang, Tianhong

2011-01-01

Sensor fault diagnosis is necessary to ensure the normal operation of a gas turbine system. However, the existing methods require too many resources and this need can't be satisfied in some occasions. Since the sensor readings are directly affected by sensor state, sensor fault diagnosis can be performed by extracting features of the measured signals. This paper proposes a novel fault diagnosis method for sensors based on wavelet entropy. Based on the wavelet theory, wavelet decomposition is utilized to decompose the signal in different scales. Then the instantaneous wavelet energy entropy (IWEE) and instantaneous wavelet singular entropy (IWSE) are defined based on the previous wavelet entropy theory. Subsequently, a fault diagnosis method for gas turbine sensors is proposed based on the results of a numerically simulated example. Then, experiments on this method are carried out on a real micro gas turbine engine. In the experiment, four types of faults with different magnitudes are presented. The experimental results show that the proposed method for sensor fault diagnosis is efficient.

Scope and applications of translation invariant wavelets to image registration

NASA Technical Reports Server (NTRS)

Chettri, Samir; LeMoigne, Jacqueline; Campbell, William

1997-01-01

The first part of this article introduces the notion of translation invariance in wavelets and discusses several wavelets that have this property. The second part discusses the possible applications of such wavelets to image registration. In the case of registration of affinely transformed images, we would conclude that the notion of translation invariance is not really necessary. What is needed is affine invariance and one way to do this is via the method of moment invariants. Wavelets or, in general, pyramid processing can then be combined with the method of moment invariants to reduce the computational load.

Correlation Filtering of Modal Dynamics using the Laplace Wavelet

NASA Technical Reports Server (NTRS)

Freudinger, Lawrence C.; Lind, Rick; Brenner, Martin J.

1997-01-01

Wavelet analysis allows processing of transient response data commonly encountered in vibration health monitoring tasks such as aircraft flutter testing. The Laplace wavelet is formulated as an impulse response of a single mode system to be similar to data features commonly encountered in these health monitoring tasks. A correlation filtering approach is introduced using the Laplace wavelet to decompose a signal into impulse responses of single mode subsystems. Applications using responses from flutter testing of aeroelastic systems demonstrate modal parameters and stability estimates can be estimated by correlation filtering free decay data with a set of Laplace wavelets.

Alcoholism detection in magnetic resonance imaging by Haar wavelet transform and back propagation neural network

NASA Astrophysics Data System (ADS)

Yu, Yali; Wang, Mengxia; Lima, Dimas

2018-04-01

In order to develop a novel alcoholism detection method, we proposed a magnetic resonance imaging (MRI)-based computer vision approach. We first use contrast equalization to increase the contrast of brain slices. Then, we perform Haar wavelet transform and principal component analysis. Finally, we use back propagation neural network (BPNN) as the classification tool. Our method yields a sensitivity of 81.71±4.51%, a specificity of 81.43±4.52%, and an accuracy of 81.57±2.18%. The Haar wavelet gives better performance than db4 wavelet and sym3 wavelet.

Quantum learning of classical stochastic processes: The completely positive realization problem

NASA Astrophysics Data System (ADS)

Monràs, Alex; Winter, Andreas

2016-01-01

Among several tasks in Machine Learning, a specially important one is the problem of inferring the latent variables of a system and their causal relations with the observed behavior. A paradigmatic instance of this is the task of inferring the hidden Markov model underlying a given stochastic process. This is known as the positive realization problem (PRP), [L. Benvenuti and L. Farina, IEEE Trans. Autom. Control 49(5), 651-664 (2004)] and constitutes a central problem in machine learning. The PRP and its solutions have far-reaching consequences in many areas of systems and control theory, and is nowadays an important piece in the broad field of positive systems theory. We consider the scenario where the latent variables are quantum (i.e., quantum states of a finite-dimensional system) and the system dynamics is constrained only by physical transformations on the quantum system. The observable dynamics is then described by a quantum instrument, and the task is to determine which quantum instrument — if any — yields the process at hand by iterative application. We take as a starting point the theory of quasi-realizations, whence a description of the dynamics of the process is given in terms of linear maps on state vectors and probabilities are given by linear functionals on the state vectors. This description, despite its remarkable resemblance with the hidden Markov model, or the iterated quantum instrument, is however devoid of any stochastic or quantum mechanical interpretation, as said maps fail to satisfy any positivity conditions. The completely positive realization problem then consists in determining whether an equivalent quantum mechanical description of the same process exists. We generalize some key results of stochastic realization theory, and show that the problem has deep connections with operator systems theory, giving possible insight to the lifting problem in quotient operator systems. Our results have potential applications in quantum machine learning, device-independent characterization and reverse-engineering of stochastic processes and quantum processors, and more generally, of dynamical processes with quantum memory [M. Guţă, Phys. Rev. A 83(6), 062324 (2011); M. Guţă and N. Yamamoto, e-print arXiv:1303.3771(2013)].

Computer-Aided Diagnosis System for Alzheimer's Disease Using Different Discrete Transform Techniques.

PubMed

Dessouky, Mohamed M; Elrashidy, Mohamed A; Taha, Taha E; Abdelkader, Hatem M

2016-05-01

The different discrete transform techniques such as discrete cosine transform (DCT), discrete sine transform (DST), discrete wavelet transform (DWT), and mel-scale frequency cepstral coefficients (MFCCs) are powerful feature extraction techniques. This article presents a proposed computer-aided diagnosis (CAD) system for extracting the most effective and significant features of Alzheimer's disease (AD) using these different discrete transform techniques and MFCC techniques. Linear support vector machine has been used as a classifier in this article. Experimental results conclude that the proposed CAD system using MFCC technique for AD recognition has a great improvement for the system performance with small number of significant extracted features, as compared with the CAD system based on DCT, DST, DWT, and the hybrid combination methods of the different transform techniques. © The Author(s) 2015.

Epilepsy analytic system with cloud computing.

PubMed

Shen, Chia-Ping; Zhou, Weizhi; Lin, Feng-Seng; Sung, Hsiao-Ya; Lam, Yan-Yu; Chen, Wei; Lin, Jeng-Wei; Pan, Ming-Kai; Chiu, Ming-Jang; Lai, Feipei

2013-01-01

Biomedical data analytic system has played an important role in doing the clinical diagnosis for several decades. Today, it is an emerging research area of analyzing these big data to make decision support for physicians. This paper presents a parallelized web-based tool with cloud computing service architecture to analyze the epilepsy. There are many modern analytic functions which are wavelet transform, genetic algorithm (GA), and support vector machine (SVM) cascaded in the system. To demonstrate the effectiveness of the system, it has been verified by two kinds of electroencephalography (EEG) data, which are short term EEG and long term EEG. The results reveal that our approach achieves the total classification accuracy higher than 90%. In addition, the entire training time accelerate about 4.66 times and prediction time is also meet requirements in real time.

Wavelet analysis in two-dimensional tomography

NASA Astrophysics Data System (ADS)

Burkovets, Dimitry N.

2002-02-01

The diagnostic possibilities of wavelet-analysis of coherent images of connective tissue in its pathological changes diagnostics. The effectiveness of polarization selection in obtaining wavelet-coefficients' images is also shown. The wavelet structures, characterizing the process of skin psoriasis, bone-tissue osteoporosis have been analyzed. The histological sections of physiological normal and pathologically changed samples of connective tissue of human skin and spongy bone tissue have been analyzed.

Adaptive Filtering in the Wavelet Transform Domain via Genetic Algorithms

DTIC Science & Technology

2004-08-06

wavelet transforms. Whereas the term “evolved” pertains only to the altered wavelet coefficients used during the inverse transform process. 2...words, the inverse transform produces the original signal x(t) from the wavelet and scaling coefficients. )()( ,, tdtx nk n nk k ψ...reconstruct the original signal as accurately as possible. The inverse transform reconstructs an approximation of the original signal (Burrus

Sediment Dynamics in a Vegetated Tidally Influenced Interdistributary Island: Wax Lake, Louisiana

DTIC Science & Technology

2017-07-01

60 Appendix A: Time Series of Wax Lake Hydrological Measurements...north-south wind stress (right). In each plot, the global wavelet spectrum is shown to the right of the wavelet plot, and and the original time series ...for Hs. The global wavelet spectrum is shown to the right of the wavelet plot, and and the original time series is shown below

Stop! border ahead: Automatic detection of subthalamic exit during deep brain stimulation surgery.

PubMed

Valsky, Dan; Marmor-Levin, Odeya; Deffains, Marc; Eitan, Renana; Blackwell, Kim T; Bergman, Hagai; Israel, Zvi

2017-01-01

Microelectrode recordings along preplanned trajectories are often used for accurate definition of the subthalamic nucleus (STN) borders during deep brain stimulation (DBS) surgery for Parkinson's disease. Usually, the demarcation of the STN borders is performed manually by a neurophysiologist. The exact detection of the borders is difficult, especially detecting the transition between the STN and the substantia nigra pars reticulata. Consequently, demarcation may be inaccurate, leading to suboptimal location of the DBS lead and inadequate clinical outcomes. We present machine-learning classification procedures that use microelectrode recording power spectra and allow for real-time, high-accuracy discrimination between the STN and substantia nigra pars reticulata. A support vector machine procedure was tested on microelectrode recordings from 58 trajectories that included both STN and substantia nigra pars reticulata that achieved a 97.6% consistency with human expert classification (evaluated by 10-fold cross-validation). We used the same data set as a training set to find the optimal parameters for a hidden Markov model using both microelectrode recording features and trajectory history to enable real-time classification of the ventral STN border (STN exit). Seventy-three additional trajectories were used to test the reliability of the learned statistical model in identifying the exit from the STN. The hidden Markov model procedure identified the STN exit with an error of 0.04 ± 0.18 mm and detection reliability (error < 1 mm) of 94%. The results indicate that robust, accurate, and automatic real-time electrophysiological detection of the ventral STN border is feasible. © 2016 International Parkinson and Movement Disorder Society. © 2016 International Parkinson and Movement Disorder Society.

Implementing wavelet inverse-transform processor with surface acoustic wave device.

PubMed

Lu, Wenke; Zhu, Changchun; Liu, Qinghong; Zhang, Jingduan

2013-02-01

The objective of this research was to investigate the implementation schemes of the wavelet inverse-transform processor using surface acoustic wave (SAW) device, the length function of defining the electrodes, and the possibility of solving the load resistance and the internal resistance for the wavelet inverse-transform processor using SAW device. In this paper, we investigate the implementation schemes of the wavelet inverse-transform processor using SAW device. In the implementation scheme that the input interdigital transducer (IDT) and output IDT stand in a line, because the electrode-overlap envelope of the input IDT is identical with the one of the output IDT (i.e. the two transducers are identical), the product of the input IDT's frequency response and the output IDT's frequency response can be implemented, so that the wavelet inverse-transform processor can be fabricated. X-112(0)Y LiTaO(3) is used as a substrate material to fabricate the wavelet inverse-transform processor. The size of the wavelet inverse-transform processor using this implementation scheme is small, so its cost is low. First, according to the envelope function of the wavelet function, the length function of the electrodes is defined, then, the lengths of the electrodes can be calculated from the length function of the electrodes, finally, the input IDT and output IDT can be designed according to the lengths and widths for the electrodes. In this paper, we also present the load resistance and the internal resistance as the two problems of the wavelet inverse-transform processor using SAW devices. The solutions to these problems are achieved in this study. When the amplifiers are subjected to the input end and output end for the wavelet inverse-transform processor, they can eliminate the influence of the load resistance and the internal resistance on the output voltage of the wavelet inverse-transform processor using SAW device. Copyright © 2012 Elsevier B.V. All rights reserved.

Emotion Discrimination Using Spatially Compact Regions of Interest Extracted from Imaging EEG Activity

PubMed Central

Padilla-Buritica, Jorge I.; Martinez-Vargas, Juan D.; Castellanos-Dominguez, German

2016-01-01

Lately, research on computational models of emotion had been getting much attention due to their potential for understanding the mechanisms of emotions and their promising broad range of applications that potentially bridge the gap between human and machine interactions. We propose a new method for emotion classification that relies on features extracted from those active brain areas that are most likely related to emotions. To this end, we carry out the selection of spatially compact regions of interest that are computed using the brain neural activity reconstructed from Electroencephalography data. Throughout this study, we consider three representative feature extraction methods widely applied to emotion detection tasks, including Power spectral density, Wavelet, and Hjorth parameters. Further feature selection is carried out using principal component analysis. For validation purpose, these features are used to feed a support vector machine classifier that is trained under the leave-one-out cross-validation strategy. Obtained results on real affective data show that incorporation of the proposed training method in combination with the enhanced spatial resolution provided by the source estimation allows improving the performed accuracy of discrimination in most of the considered emotions, namely: dominance, valence, and liking. PMID:27489541

A Pathological Brain Detection System based on Extreme Learning Machine Optimized by Bat Algorithm.

PubMed

Lu, Siyuan; Qiu, Xin; Shi, Jianping; Li, Na; Lu, Zhi-Hai; Chen, Peng; Yang, Meng-Meng; Liu, Fang-Yuan; Jia, Wen-Juan; Zhang, Yudong

2017-01-01

It is beneficial to classify brain images as healthy or pathological automatically, because 3D brain images can generate so much information which is time consuming and tedious for manual analysis. Among various 3D brain imaging techniques, magnetic resonance (MR) imaging is the most suitable for brain, and it is now widely applied in hospitals, because it is helpful in the four ways of diagnosis, prognosis, pre-surgical, and postsurgical procedures. There are automatic detection methods; however they suffer from low accuracy. Therefore, we proposed a novel approach which employed 2D discrete wavelet transform (DWT), and calculated the entropies of the subbands as features. Then, a bat algorithm optimized extreme learning machine (BA-ELM) was trained to identify pathological brains from healthy controls. A 10x10-fold cross validation was performed to evaluate the out-of-sample performance. The method achieved a sensitivity of 99.04%, a specificity of 93.89%, and an overall accuracy of 98.33% over 132 MR brain images. The experimental results suggest that the proposed approach is accurate and robust in pathological brain detection. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

ANN based Performance Evaluation of BDI for Condition Monitoring of Induction Motor Bearings

NASA Astrophysics Data System (ADS)

Patel, Raj Kumar; Giri, V. K.

2017-06-01

One of the critical parts in rotating machines is bearings and most of the failure arises from the defective bearings. Bearing failure leads to failure of a machine and the unpredicted productivity loss in the performance. Therefore, bearing fault detection and prognosis is an integral part of the preventive maintenance procedures. In this paper vibration signal for four conditions of a deep groove ball bearing; normal (N), inner race defect (IRD), ball defect (BD) and outer race defect (ORD) were acquired from a customized bearing test rig, under four different conditions and three different fault sizes. Two approaches have been opted for statistical feature extraction from the vibration signal. In the first approach, raw signal is used for statistical feature extraction and in the second approach statistical features extracted are based on bearing damage index (BDI). The proposed BDI technique uses wavelet packet node energy coefficients analysis method. Both the features are used as inputs to an ANN classifier to evaluate its performance. A comparison of ANN performance is made based on raw vibration data and data chosen by using BDI. The ANN performance has been found to be fairly higher when BDI based signals were used as inputs to the classifier.