A link prediction method for heterogeneous networks based on BP neural network

NASA Astrophysics Data System (ADS)

Li, Ji-chao; Zhao, Dan-ling; Ge, Bing-Feng; Yang, Ke-Wei; Chen, Ying-Wu

2018-04-01

Most real-world systems, composed of different types of objects connected via many interconnections, can be abstracted as various complex heterogeneous networks. Link prediction for heterogeneous networks is of great significance for mining missing links and reconfiguring networks according to observed information, with considerable applications in, for example, friend and location recommendations and disease-gene candidate detection. In this paper, we put forward a novel integrated framework, called MPBP (Meta-Path feature-based BP neural network model), to predict multiple types of links for heterogeneous networks. More specifically, the concept of meta-path is introduced, followed by the extraction of meta-path features for heterogeneous networks. Next, based on the extracted meta-path features, a supervised link prediction model is built with a three-layer BP neural network. Then, the solution algorithm of the proposed link prediction model is put forward to obtain predicted results by iteratively training the network. Last, numerical experiments on the dataset of examples of a gene-disease network and a combat network are conducted to verify the effectiveness and feasibility of the proposed MPBP. It shows that the MPBP with very good performance is superior to the baseline methods.

A local structure model for network analysis

DOE PAGES

Casleton, Emily; Nordman, Daniel; Kaiser, Mark

2017-04-01

The statistical analysis of networks is a popular research topic with ever widening applications. Exponential random graph models (ERGMs), which specify a model through interpretable, global network features, are common for this purpose. In this study we introduce a new class of models for network analysis, called local structure graph models (LSGMs). In contrast to an ERGM, a LSGM specifies a network model through local features and allows for an interpretable and controllable local dependence structure. In particular, LSGMs are formulated by a set of full conditional distributions for each network edge, e.g., the probability of edge presence/absence, depending onmore » neighborhoods of other edges. Additional model features are introduced to aid in specification and to help alleviate a common issue (occurring also with ERGMs) of model degeneracy. Finally, the proposed models are demonstrated on a network of tornadoes in Arkansas where a LSGM is shown to perform significantly better than a model without local dependence.« less

A local structure model for network analysis

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

Casleton, Emily; Nordman, Daniel; Kaiser, Mark

The statistical analysis of networks is a popular research topic with ever widening applications. Exponential random graph models (ERGMs), which specify a model through interpretable, global network features, are common for this purpose. In this study we introduce a new class of models for network analysis, called local structure graph models (LSGMs). In contrast to an ERGM, a LSGM specifies a network model through local features and allows for an interpretable and controllable local dependence structure. In particular, LSGMs are formulated by a set of full conditional distributions for each network edge, e.g., the probability of edge presence/absence, depending onmore » neighborhoods of other edges. Additional model features are introduced to aid in specification and to help alleviate a common issue (occurring also with ERGMs) of model degeneracy. Finally, the proposed models are demonstrated on a network of tornadoes in Arkansas where a LSGM is shown to perform significantly better than a model without local dependence.« less

Brain functional network connectivity based on a visual task: visual information processing-related brain regions are significantly activated in the task state.

PubMed

Yang, Yan-Li; Deng, Hong-Xia; Xing, Gui-Yang; Xia, Xiao-Luan; Li, Hai-Fang

2015-02-01

It is not clear whether the method used in functional brain-network related research can be applied to explore the feature binding mechanism of visual perception. In this study, we investigated feature binding of color and shape in visual perception. Functional magnetic resonance imaging data were collected from 38 healthy volunteers at rest and while performing a visual perception task to construct brain networks active during resting and task states. Results showed that brain regions involved in visual information processing were obviously activated during the task. The components were partitioned using a greedy algorithm, indicating the visual network existed during the resting state. Z-values in the vision-related brain regions were calculated, confirming the dynamic balance of the brain network. Connectivity between brain regions was determined, and the result showed that occipital and lingual gyri were stable brain regions in the visual system network, the parietal lobe played a very important role in the binding process of color features and shape features, and the fusiform and inferior temporal gyri were crucial for processing color and shape information. Experimental findings indicate that understanding visual feature binding and cognitive processes will help establish computational models of vision, improve image recognition technology, and provide a new theoretical mechanism for feature binding in visual perception.

Disrupted reward and cognitive control networks contribute to anhedonia in depression.

PubMed

Gong, Liang; He, Cancan; Zhang, Haisan; Zhang, Hongxing; Zhang, Zhijun; Xie, Chunming

2018-08-01

Neuroimaging studies have identified that anhedonia, a core feature of major depressive disorder (MDD), is associated with dysfunction in reward and cognitive control processing. However, it is still not clear how the reward network (β-network) and the cognitive control network (δ-network) are linked to biased anhedonia in MDD patients. Sixty-eight MDD patients and 64 cognitively normal (CN) subjects underwent a resting-state functional magnetic resonance imaging scan. A 2*2 ANCOVA analysis was used to explore the differences in the nucleus accumbens-based, voxelwise functional connectivity (FC) between the groups. Then, the β- and δ-networks were constructed, and the FC intensities were compared within and between theβ- and δ-networks across all subjects. Multiple linear regression analyses were also employed to investigate the relationships between the neural features of the β- and δ-networks and anhedonia in MDD patients. Compared to the CN subjects, the MDD patients showed synergistic functional decoupling in both the β- and δ-networks, as well as decreased FC intensities in the intra- and inter- β- and δ-networks. In addition, the FC in both the β- and δ-networks was significantly correlated with anhedonia severity in the MDD patients. Importantly, the integrated neural features of the β- and δ-networks could more precisely predict anhedonic symptoms. These findings initially demonstrated that the imbalance between β- and δ-network activity successfully predicted anhedonia severity and suggested that the neural features of both the β- and δ-networks could represent a fundamental mechanism that underlies anhedonia in MDD patients. Copyright © 2018 Elsevier Ltd. All rights reserved.

MiRNA-miRNA synergistic network: construction via co-regulating functional modules and disease miRNA topological features.

PubMed

Xu, Juan; Li, Chuan-Xing; Li, Yong-Sheng; Lv, Jun-Ying; Ma, Ye; Shao, Ting-Ting; Xu, Liang-De; Wang, Ying-Ying; Du, Lei; Zhang, Yun-Peng; Jiang, Wei; Li, Chun-Quan; Xiao, Yun; Li, Xia

2011-02-01

Synergistic regulations among multiple microRNAs (miRNAs) are important to understand the mechanisms of complex post-transcriptional regulations in humans. Complex diseases are affected by several miRNAs rather than a single miRNA. So, it is a challenge to identify miRNA synergism and thereby further determine miRNA functions at a system-wide level and investigate disease miRNA features in the miRNA-miRNA synergistic network from a new view. Here, we constructed a miRNA-miRNA functional synergistic network (MFSN) via co-regulating functional modules that have three features: common targets of corresponding miRNA pairs, enriched in the same gene ontology category and close proximity in the protein interaction network. Predicted miRNA synergism is validated by significantly high co-expression of functional modules and significantly negative regulation to functional modules. We found that the MFSN exhibits a scale free, small world and modular architecture. Furthermore, the topological features of disease miRNAs in the MFSN are distinct from non-disease miRNAs. They have more synergism, indicating their higher complexity of functions and are the global central cores of the MFSN. In addition, miRNAs associated with the same disease are close to each other. The structure of the MFSN and the features of disease miRNAs are validated to be robust using different miRNA target data sets.

Chinese Writing of Deaf or Hard-of-Hearing Students and Normal-Hearing Peers from Complex Network Approach.

PubMed

Jin, Huiyuan; Liu, Haitao

2016-01-01

Deaf or hard-of-hearing individuals usually face a greater challenge to learn to write than their normal-hearing counterparts. Due to the limitations of traditional research methods focusing on microscopic linguistic features, a holistic characterization of the writing linguistic features of these language users is lacking. This study attempts to fill this gap by adopting the methodology of linguistic complex networks. Two syntactic dependency networks are built in order to compare the macroscopic linguistic features of deaf or hard-of-hearing students and those of their normal-hearing peers. One is transformed from a treebank of writing produced by Chinese deaf or hard-of-hearing students, and the other from a treebank of writing produced by their Chinese normal-hearing counterparts. Two major findings are obtained through comparison of the statistical features of the two networks. On the one hand, both linguistic networks display small-world and scale-free network structures, but the network of the normal-hearing students' exhibits a more power-law-like degree distribution. Relevant network measures show significant differences between the two linguistic networks. On the other hand, deaf or hard-of-hearing students tend to have a lower language proficiency level in both syntactic and lexical aspects. The rigid use of function words and a lower vocabulary richness of the deaf or hard-of-hearing students may partially account for the observed differences.

Network motif frequency vectors reveal evolving metabolic network organisation.

PubMed

Pearcy, Nicole; Crofts, Jonathan J; Chuzhanova, Nadia

2015-01-01

At the systems level many organisms of interest may be described by their patterns of interaction, and as such, are perhaps best characterised via network or graph models. Metabolic networks, in particular, are fundamental to the proper functioning of many important biological processes, and thus, have been widely studied over the past decade or so. Such investigations have revealed a number of shared topological features, such as a short characteristic path-length, large clustering coefficient and hierarchical modular structure. However, the extent to which evolutionary and functional properties of metabolism manifest via this underlying network architecture remains unclear. In this paper, we employ a novel graph embedding technique, based upon low-order network motifs, to compare metabolic network structure for 383 bacterial species categorised according to a number of biological features. In particular, we introduce a new global significance score which enables us to quantify important evolutionary relationships that exist between organisms and their physical environments. Using this new approach, we demonstrate a number of significant correlations between environmental factors, such as growth conditions and habitat variability, and network motif structure, providing evidence that organism adaptability leads to increased complexities in the resultant metabolic networks.

A Novel Characterization of Amalgamated Networks in Natural Systems

PubMed Central

Barranca, Victor J.; Zhou, Douglas; Cai, David

2015-01-01

Densely-connected networks are prominent among natural systems, exhibiting structural characteristics often optimized for biological function. To reveal such features in highly-connected networks, we introduce a new network characterization determined by a decomposition of network-connectivity into low-rank and sparse components. Based on these components, we discover a new class of networks we define as amalgamated networks, which exhibit large functional groups and dense connectivity. Analyzing recent experimental findings on cerebral cortex, food-web, and gene regulatory networks, we establish the unique importance of amalgamated networks in fostering biologically advantageous properties, including rapid communication among nodes, structural stability under attacks, and separation of network activity into distinct functional modules. We further observe that our network characterization is scalable with network size and connectivity, thereby identifying robust features significant to diverse physical systems, which are typically undetectable by conventional characterizations of connectivity. We expect that studying the amalgamation properties of biological networks may offer new insights into understanding their structure-function relationships. PMID:26035066

A Spiking Neural Network in sEMG Feature Extraction.

PubMed

Lobov, Sergey; Mironov, Vasiliy; Kastalskiy, Innokentiy; Kazantsev, Victor

2015-11-03

We have developed a novel algorithm for sEMG feature extraction and classification. It is based on a hybrid network composed of spiking and artificial neurons. The spiking neuron layer with mutual inhibition was assigned as feature extractor. We demonstrate that the classification accuracy of the proposed model could reach high values comparable with existing sEMG interface systems. Moreover, the algorithm sensibility for different sEMG collecting systems characteristics was estimated. Results showed rather equal accuracy, despite a significant sampling rate difference. The proposed algorithm was successfully tested for mobile robot control.

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network.

PubMed

Guo, Hao; Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network

PubMed Central

Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%. PMID:29387141

Chinese Writing of Deaf or Hard-of-Hearing Students and Normal-Hearing Peers from Complex Network Approach

PubMed Central

Jin, Huiyuan; Liu, Haitao

2016-01-01

Deaf or hard-of-hearing individuals usually face a greater challenge to learn to write than their normal-hearing counterparts. Due to the limitations of traditional research methods focusing on microscopic linguistic features, a holistic characterization of the writing linguistic features of these language users is lacking. This study attempts to fill this gap by adopting the methodology of linguistic complex networks. Two syntactic dependency networks are built in order to compare the macroscopic linguistic features of deaf or hard-of-hearing students and those of their normal-hearing peers. One is transformed from a treebank of writing produced by Chinese deaf or hard-of-hearing students, and the other from a treebank of writing produced by their Chinese normal-hearing counterparts. Two major findings are obtained through comparison of the statistical features of the two networks. On the one hand, both linguistic networks display small-world and scale-free network structures, but the network of the normal-hearing students' exhibits a more power-law-like degree distribution. Relevant network measures show significant differences between the two linguistic networks. On the other hand, deaf or hard-of-hearing students tend to have a lower language proficiency level in both syntactic and lexical aspects. The rigid use of function words and a lower vocabulary richness of the deaf or hard-of-hearing students may partially account for the observed differences. PMID:27920733

Enlightening discriminative network functional modules behind Principal Component Analysis separation in differential-omic science studies

PubMed Central

Ciucci, Sara; Ge, Yan; Durán, Claudio; Palladini, Alessandra; Jiménez-Jiménez, Víctor; Martínez-Sánchez, Luisa María; Wang, Yuting; Sales, Susanne; Shevchenko, Andrej; Poser, Steven W.; Herbig, Maik; Otto, Oliver; Androutsellis-Theotokis, Andreas; Guck, Jochen; Gerl, Mathias J.; Cannistraci, Carlo Vittorio

2017-01-01

Omic science is rapidly growing and one of the most employed techniques to explore differential patterns in omic datasets is principal component analysis (PCA). However, a method to enlighten the network of omic features that mostly contribute to the sample separation obtained by PCA is missing. An alternative is to build correlation networks between univariately-selected significant omic features, but this neglects the multivariate unsupervised feature compression responsible for the PCA sample segregation. Biologists and medical researchers often prefer effective methods that offer an immediate interpretation to complicated algorithms that in principle promise an improvement but in practice are difficult to be applied and interpreted. Here we present PC-corr: a simple algorithm that associates to any PCA segregation a discriminative network of features. Such network can be inspected in search of functional modules useful in the definition of combinatorial and multiscale biomarkers from multifaceted omic data in systems and precision biomedicine. We offer proofs of PC-corr efficacy on lipidomic, metagenomic, developmental genomic, population genetic, cancer promoteromic and cancer stem-cell mechanomic data. Finally, PC-corr is a general functional network inference approach that can be easily adopted for big data exploration in computer science and analysis of complex systems in physics. PMID:28287094

Understanding regulatory networks requires more than computing a multitude of graph statistics. Comment on "Drivers of structural features in gene regulatory networks: From biophysical constraints to biological function" by O.C. Martin et al.

NASA Astrophysics Data System (ADS)

Tkačik, Gašper

2016-07-01

The article by O. Martin and colleagues provides a much needed systematic review of a body of work that relates the topological structure of genetic regulatory networks to evolutionary selection for function. This connection is very important. Using the current wealth of genomic data, statistical features of regulatory networks (e.g., degree distributions, motif composition, etc.) can be quantified rather easily; it is, however, often unclear how to interpret the results. On a graph theoretic level the statistical significance of the results can be evaluated by comparing observed graphs to ;randomized; ones (bravely ignoring the issue of how precisely to randomize!) and comparing the frequency of appearance of a particular network structure relative to a randomized null expectation. While this is a convenient operational test for statistical significance, its biological meaning is questionable. In contrast, an in-silico genotype-to-phenotype model makes explicit the assumptions about the network function, and thus clearly defines the expected network structures that can be compared to the case of no selection for function and, ultimately, to data.

Machine learning vortices at the Kosterlitz-Thouless transition

NASA Astrophysics Data System (ADS)

Beach, Matthew J. S.; Golubeva, Anna; Melko, Roger G.

2018-01-01

Efficient and automated classification of phases from minimally processed data is one goal of machine learning in condensed-matter and statistical physics. Supervised algorithms trained on raw samples of microstates can successfully detect conventional phase transitions via learning a bulk feature such as an order parameter. In this paper, we investigate whether neural networks can learn to classify phases based on topological defects. We address this question on the two-dimensional classical XY model which exhibits a Kosterlitz-Thouless transition. We find significant feature engineering of the raw spin states is required to convincingly claim that features of the vortex configurations are responsible for learning the transition temperature. We further show a single-layer network does not correctly classify the phases of the XY model, while a convolutional network easily performs classification by learning the global magnetization. Finally, we design a deep network capable of learning vortices without feature engineering. We demonstrate the detection of vortices does not necessarily result in the best classification accuracy, especially for lattices of less than approximately 1000 spins. For larger systems, it remains a difficult task to learn vortices.

Fusion of shallow and deep features for classification of high-resolution remote sensing images

NASA Astrophysics Data System (ADS)

Gao, Lang; Tian, Tian; Sun, Xiao; Li, Hang

2018-02-01

Effective spectral and spatial pixel description plays a significant role for the classification of high resolution remote sensing images. Current approaches of pixel-based feature extraction are of two main kinds: one includes the widelyused principal component analysis (PCA) and gray level co-occurrence matrix (GLCM) as the representative of the shallow spectral and shape features, and the other refers to the deep learning-based methods which employ deep neural networks and have made great promotion on classification accuracy. However, the former traditional features are insufficient to depict complex distribution of high resolution images, while the deep features demand plenty of samples to train the network otherwise over fitting easily occurs if only limited samples are involved in the training. In view of the above, we propose a GLCM-based convolution neural network (CNN) approach to extract features and implement classification for high resolution remote sensing images. The employment of GLCM is able to represent the original images and eliminate redundant information and undesired noises. Meanwhile, taking shallow features as the input of deep network will contribute to a better guidance and interpretability. In consideration of the amount of samples, some strategies such as L2 regularization and dropout methods are used to prevent over-fitting. The fine-tuning strategy is also used in our study to reduce training time and further enhance the generalization performance of the network. Experiments with popular data sets such as PaviaU data validate that our proposed method leads to a performance improvement compared to individual involved approaches.

Network Ecology and Adolescent Social Structure

PubMed Central

McFarland, Daniel A.; Moody, James; Diehl, David; Smith, Jeffrey A.; Thomas, Reuben J.

2014-01-01

Adolescent societies—whether arising from weak, short-term classroom friendships or from close, long-term friendships—exhibit various levels of network clustering, segregation, and hierarchy. Some are rank-ordered caste systems and others are flat, cliquish worlds. Explaining the source of such structural variation remains a challenge, however, because global network features are generally treated as the agglomeration of micro-level tie-formation mechanisms, namely balance, homophily, and dominance. How do the same micro-mechanisms generate significant variation in global network structures? To answer this question we propose and test a network ecological theory that specifies the ways features of organizational environments moderate the expression of tie-formation processes, thereby generating variability in global network structures across settings. We develop this argument using longitudinal friendship data on schools (Add Health study) and classrooms (Classroom Engagement study), and by extending exponential random graph models to the study of multiple societies over time. PMID:25535409

Network Ecology and Adolescent Social Structure.

PubMed

McFarland, Daniel A; Moody, James; Diehl, David; Smith, Jeffrey A; Thomas, Reuben J

2014-12-01

Adolescent societies-whether arising from weak, short-term classroom friendships or from close, long-term friendships-exhibit various levels of network clustering, segregation, and hierarchy. Some are rank-ordered caste systems and others are flat, cliquish worlds. Explaining the source of such structural variation remains a challenge, however, because global network features are generally treated as the agglomeration of micro-level tie-formation mechanisms, namely balance, homophily, and dominance. How do the same micro-mechanisms generate significant variation in global network structures? To answer this question we propose and test a network ecological theory that specifies the ways features of organizational environments moderate the expression of tie-formation processes, thereby generating variability in global network structures across settings. We develop this argument using longitudinal friendship data on schools (Add Health study) and classrooms (Classroom Engagement study), and by extending exponential random graph models to the study of multiple societies over time.

Altered resting-state whole-brain functional networks of neonates with intrauterine growth restriction.

PubMed

Batalle, Dafnis; Muñoz-Moreno, Emma; Tornador, Cristian; Bargallo, Nuria; Deco, Gustavo; Eixarch, Elisenda; Gratacos, Eduard

2016-04-01

The feasibility to use functional MRI (fMRI) during natural sleep to assess low-frequency basal brain activity fluctuations in human neonates has been demonstrated, although its potential to characterise pathologies of prenatal origin has not yet been exploited. In the present study, we used intrauterine growth restriction (IUGR) as a model of altered neurodevelopment due to prenatal condition to show the suitability of brain networks to characterise functional brain organisation at neonatal age. Particularly, we analysed resting-state fMRI signal of 20 neonates with IUGR and 13 controls, obtaining whole-brain functional networks based on correlations of blood oxygen level-dependent (BOLD) signal in 90 grey matter regions of an anatomical atlas (AAL). Characterisation of the networks obtained with graph theoretical features showed increased network infrastructure and raw efficiencies but reduced efficiency after normalisation, demonstrating hyper-connected but sub-optimally organised IUGR functional brain networks. Significant association of network features with neurobehavioral scores was also found. Further assessment of spatiotemporal dynamics displayed alterations into features associated to frontal, cingulate and lingual cortices. These findings show the capacity of functional brain networks to characterise brain reorganisation from an early age, and their potential to develop biomarkers of altered neurodevelopment. Copyright © 2016 Elsevier Ltd. All rights reserved.

Natural Flood Management Plus: Scaling Up Nature Based Solutions to Larger Catchments

NASA Astrophysics Data System (ADS)

Quinn, Paul; Nicholson, Alex; Adams, Russ

2017-04-01

It has been established that networks NFM features, such as ponds and wetlands, can have a significant effect on flood flow and pollution at local scales (less than 10km2). However, it is much less certain that NFM and NBS can impact at larger scales and protect larger cities. This is especially true for recent storms in the UK such as storm Desmond that caused devastation across the north of England. It is possible using observed rainfall and runoff data to estimate the amounts of storage that would be required to impact on extreme flood events. Here we will how a toolkit that will estimate the amount of storage that can be accrued through a dense networks of NFM features. The analysis suggest that the use of many hundreds of small NFM features can have a significant impact on peak flow, however we still require more storage in order to address extreme events and to satisfy flood engineers who may propose more traditional flood defences. We will also show case studies of larger NFM feature positioned on flood plains that can store significantly more flood flow. Examples designs of NFM plus feature will be shown. The storage aggregation tool will then show the degree to which storing large amounts of flood flow in NFM plus features can contribute to flood management and estimate the likely costs. Together smaller and larger NFM features if used together can produce significant flood storage and at a much lower cost than traditional schemes.

Facial expression recognition based on improved local ternary pattern and stacked auto-encoder

NASA Astrophysics Data System (ADS)

Wu, Yao; Qiu, Weigen

2017-08-01

In order to enhance the robustness of facial expression recognition, we propose a method of facial expression recognition based on improved Local Ternary Pattern (LTP) combined with Stacked Auto-Encoder (SAE). This method uses the improved LTP extraction feature, and then uses the improved depth belief network as the detector and classifier to extract the LTP feature. The combination of LTP and improved deep belief network is realized in facial expression recognition. The recognition rate on CK+ databases has improved significantly.

Dynamic security contingency screening and ranking using neural networks.

PubMed

Mansour, Y; Vaahedi, E; El-Sharkawi, M A

1997-01-01

This paper summarizes BC Hydro's experience in applying neural networks to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of BC Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for BC Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (second kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included: 1) the effectiveness of output; 2) the number of outputs; 3) the type of features (static versus dynamic); 4) the number of features; 5) system partitioning; and 6) the ratio of training samples to features. The final results obtained using the large scale systems of BC Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking.

End-to-End Multimodal Emotion Recognition Using Deep Neural Networks

NASA Astrophysics Data System (ADS)

Tzirakis, Panagiotis; Trigeorgis, George; Nicolaou, Mihalis A.; Schuller, Bjorn W.; Zafeiriou, Stefanos

2017-12-01

Automatic affect recognition is a challenging task due to the various modalities emotions can be expressed with. Applications can be found in many domains including multimedia retrieval and human computer interaction. In recent years, deep neural networks have been used with great success in determining emotional states. Inspired by this success, we propose an emotion recognition system using auditory and visual modalities. To capture the emotional content for various styles of speaking, robust features need to be extracted. To this purpose, we utilize a Convolutional Neural Network (CNN) to extract features from the speech, while for the visual modality a deep residual network (ResNet) of 50 layers. In addition to the importance of feature extraction, a machine learning algorithm needs also to be insensitive to outliers while being able to model the context. To tackle this problem, Long Short-Term Memory (LSTM) networks are utilized. The system is then trained in an end-to-end fashion where - by also taking advantage of the correlations of the each of the streams - we manage to significantly outperform the traditional approaches based on auditory and visual handcrafted features for the prediction of spontaneous and natural emotions on the RECOLA database of the AVEC 2016 research challenge on emotion recognition.

Building thiol and metal-thiolate functions into coordination nets: Clues from a simple molecule

NASA Astrophysics Data System (ADS)

He, Jun; Yang, Chen; Xu, Zhengtao; Zeller, Matthias; Hunter, Allen D.; Lin, Jianhua

2009-07-01

The simple and easy-to-prepare bifunctional molecule 2,5-dimercapto-1,4-benzenedicarboxylic acid (H 4DMBD) interacts with the increasingly harder metal ions of Cu +, Pb 2+ and Eu 3+ to form the coordination networks of Cu 6(DMBD) 3(en) 4(Hen) 6 ( 1), Pb 2(DMBD)(en) 2 ( 2) and Eu 2(H 2DMBD) 3(DEF) 4 ( 3), where the carboxyl and thiol groups bind with distinct preference to the hard and soft metal ions, respectively. Notably, 1 features uncoordinated carboxylate groups and Cu 3 cluster units integrated via the thiolate groups into an extended network with significant interaction between the metal centers and the organic molecules; 2 features a 2D coordination net based on the mercapto and carboxylic groups all bonded to the Pb 2+ ions; 3 features free-standing thiol groups inside the channels of a metal-carboxylate-based network. This study illustrates the rich solid state structural features and potential functions offered by the carboxyl-thiol combination.

Network Sampling and Classification:An Investigation of Network Model Representations

PubMed Central

Airoldi, Edoardo M.; Bai, Xue; Carley, Kathleen M.

2011-01-01

Methods for generating a random sample of networks with desired properties are important tools for the analysis of social, biological, and information networks. Algorithm-based approaches to sampling networks have received a great deal of attention in recent literature. Most of these algorithms are based on simple intuitions that associate the full features of connectivity patterns with specific values of only one or two network metrics. Substantive conclusions are crucially dependent on this association holding true. However, the extent to which this simple intuition holds true is not yet known. In this paper, we examine the association between the connectivity patterns that a network sampling algorithm aims to generate and the connectivity patterns of the generated networks, measured by an existing set of popular network metrics. We find that different network sampling algorithms can yield networks with similar connectivity patterns. We also find that the alternative algorithms for the same connectivity pattern can yield networks with different connectivity patterns. We argue that conclusions based on simulated network studies must focus on the full features of the connectivity patterns of a network instead of on the limited set of network metrics for a specific network type. This fact has important implications for network data analysis: for instance, implications related to the way significance is currently assessed. PMID:21666773

Secure Service Proxy: A CoAP(s) Intermediary for a Securer and Smarter Web of Things

PubMed Central

Van den Abeele, Floris; Moerman, Ingrid; Demeester, Piet

2017-01-01

As the IoT continues to grow over the coming years, resource-constrained devices and networks will see an increase in traffic as everything is connected in an open Web of Things. The performance- and function-enhancing features are difficult to provide in resource-constrained environments, but will gain importance if the WoT is to be scaled up successfully. For example, scalable open standards-based authentication and authorization will be important to manage access to the limited resources of constrained devices and networks. Additionally, features such as caching and virtualization may help further reduce the load on these constrained systems. This work presents the Secure Service Proxy (SSP): a constrained-network edge proxy with the goal of improving the performance and functionality of constrained RESTful environments. Our evaluations show that the proposed design reaches its goal by reducing the load on constrained devices while implementing a wide range of features as different adapters. Specifically, the results show that the SSP leads to significant savings in processing, network traffic, network delay and packet loss rates for constrained devices. As a result, the SSP helps to guarantee the proper operation of constrained networks as these networks form an ever-expanding Web of Things. PMID:28696393

Secure Service Proxy: A CoAP(s) Intermediary for a Securer and Smarter Web of Things.

PubMed

Van den Abeele, Floris; Moerman, Ingrid; Demeester, Piet; Hoebeke, Jeroen

2017-07-11

As the IoT continues to grow over the coming years, resource-constrained devices and networks will see an increase in traffic as everything is connected in an open Web of Things. The performance- and function-enhancing features are difficult to provide in resource-constrained environments, but will gain importance if the WoT is to be scaled up successfully. For example, scalable open standards-based authentication and authorization will be important to manage access to the limited resources of constrained devices and networks. Additionally, features such as caching and virtualization may help further reduce the load on these constrained systems. This work presents the Secure Service Proxy (SSP): a constrained-network edge proxy with the goal of improving the performance and functionality of constrained RESTful environments. Our evaluations show that the proposed design reaches its goal by reducing the load on constrained devices while implementing a wide range of features as different adapters. Specifically, the results show that the SSP leads to significant savings in processing, network traffic, network delay and packet loss rates for constrained devices. As a result, the SSP helps to guarantee the proper operation of constrained networks as these networks form an ever-expanding Web of Things.

Evaluating the Small-World-Ness of a Sampled Network: Functional Connectivity of Entorhinal-Hippocampal Circuitry

NASA Astrophysics Data System (ADS)

She, Qi; Chen, Guanrong; Chan, Rosa H. M.

2016-02-01

The amount of publicly accessible experimental data has gradually increased in recent years, which makes it possible to reconsider many longstanding questions in neuroscience. In this paper, an efficient framework is presented for reconstructing functional connectivity using experimental spike-train data. A modified generalized linear model (GLM) with L1-norm penalty was used to investigate 10 datasets. These datasets contain spike-train data collected from the entorhinal-hippocampal region in the brains of rats performing different tasks. The analysis shows that entorhinal-hippocampal network of well-trained rats demonstrated significant small-world features. It is found that the connectivity structure generated by distance-dependent models is responsible for the observed small-world features of the reconstructed networks. The models are utilized to simulate a subset of units recorded from a large biological neural network using multiple electrodes. Two metrics for quantifying the small-world-ness both suggest that the reconstructed network from the sampled nodes estimates a more prominent small-world-ness feature than that of the original unknown network when the number of recorded neurons is small. Finally, this study shows that it is feasible to adjust the estimated small-world-ness results based on the number of neurons recorded to provide a more accurate reference of the network property.

Automatic Ship Detection in Remote Sensing Images from Google Earth of Complex Scenes Based on Multiscale Rotation Dense Feature Pyramid Networks

NASA Astrophysics Data System (ADS)

Yang, Xue; Sun, Hao; Fu, Kun; Yang, Jirui; Sun, Xian; Yan, Menglong; Guo, Zhi

2018-01-01

Ship detection has been playing a significant role in the field of remote sensing for a long time but it is still full of challenges. The main limitations of traditional ship detection methods usually lie in the complexity of application scenarios, the difficulty of intensive object detection and the redundancy of detection region. In order to solve such problems above, we propose a framework called Rotation Dense Feature Pyramid Networks (R-DFPN) which can effectively detect ship in different scenes including ocean and port. Specifically, we put forward the Dense Feature Pyramid Network (DFPN), which is aimed at solving the problem resulted from the narrow width of the ship. Compared with previous multi-scale detectors such as Feature Pyramid Network (FPN), DFPN builds the high-level semantic feature-maps for all scales by means of dense connections, through which enhances the feature propagation and encourages the feature reuse. Additionally, in the case of ship rotation and dense arrangement, we design a rotation anchor strategy to predict the minimum circumscribed rectangle of the object so as to reduce the redundant detection region and improve the recall. Furthermore, we also propose multi-scale ROI Align for the purpose of maintaining the completeness of semantic and spatial information. Experiments based on remote sensing images from Google Earth for ship detection show that our detection method based on R-DFPN representation has a state-of-the-art performance.

Extracting intrinsic functional networks with feature-based group independent component analysis.

PubMed

Calhoun, Vince D; Allen, Elena

2013-04-01

There is increasing use of functional imaging data to understand the macro-connectome of the human brain. Of particular interest is the structure and function of intrinsic networks (regions exhibiting temporally coherent activity both at rest and while a task is being performed), which account for a significant portion of the variance in functional MRI data. While networks are typically estimated based on the temporal similarity between regions (based on temporal correlation, clustering methods, or independent component analysis [ICA]), some recent work has suggested that these intrinsic networks can be extracted from the inter-subject covariation among highly distilled features, such as amplitude maps reflecting regions modulated by a task or even coordinates extracted from large meta analytic studies. In this paper our goal was to explicitly compare the networks obtained from a first-level ICA (ICA on the spatio-temporal functional magnetic resonance imaging (fMRI) data) to those from a second-level ICA (i.e., ICA on computed features rather than on the first-level fMRI data). Convergent results from simulations, task-fMRI data, and rest-fMRI data show that the second-level analysis is slightly noisier than the first-level analysis but yields strikingly similar patterns of intrinsic networks (spatial correlations as high as 0.85 for task data and 0.65 for rest data, well above the empirical null) and also preserves the relationship of these networks with other variables such as age (for example, default mode network regions tended to show decreased low frequency power for first-level analyses and decreased loading parameters for second-level analyses). In addition, the best-estimated second-level results are those which are the most strongly reflected in the input feature. In summary, the use of feature-based ICA appears to be a valid tool for extracting intrinsic networks. We believe it will become a useful and important approach in the study of the macro-connectome, particularly in the context of data fusion.

Improving link prediction in complex networks by adaptively exploiting multiple structural features of networks

NASA Astrophysics Data System (ADS)

Ma, Chuang; Bao, Zhong-Kui; Zhang, Hai-Feng

2017-10-01

So far, many network-structure-based link prediction methods have been proposed. However, these methods only highlight one or two structural features of networks, and then use the methods to predict missing links in different networks. The performances of these existing methods are not always satisfied in all cases since each network has its unique underlying structural features. In this paper, by analyzing different real networks, we find that the structural features of different networks are remarkably different. In particular, even in the same network, their inner structural features are utterly different. Therefore, more structural features should be considered. However, owing to the remarkably different structural features, the contributions of different features are hard to be given in advance. Inspired by these facts, an adaptive fusion model regarding link prediction is proposed to incorporate multiple structural features. In the model, a logistic function combing multiple structural features is defined, then the weight of each feature in the logistic function is adaptively determined by exploiting the known structure information. Last, we use the "learnt" logistic function to predict the connection probabilities of missing links. According to our experimental results, we find that the performance of our adaptive fusion model is better than many similarity indices.

Nonlinear features for classification and pose estimation of machined parts from single views

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-10-01

A new nonlinear feature extraction method is presented for classification and pose estimation of objects from single views. The feature extraction method is called the maximum representation and discrimination feature (MRDF) method. The nonlinear MRDF transformations to use are obtained in closed form, and offer significant advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We consider MRDFs on image data, provide a new 2-stage nonlinear MRDF solution, and show it specializes to well-known linear and nonlinear image processing transforms under certain conditions. We show the use of MRDF in estimating the class and pose of images of rendered solid CAD models of machine parts from single views using a feature-space trajectory neural network classifier. We show new results with better classification and pose estimation accuracy than are achieved by standard principal component analysis and Fukunaga-Koontz feature extraction methods.

Dynamic hydro-climatic networks in pristine and regulated rivers

NASA Astrophysics Data System (ADS)

Botter, G.; Basso, S.; Lazzaro, G.; Doulatyari, B.; Biswal, B.; Schirmer, M.; Rinaldo, A.

2014-12-01

Flow patterns observed at-a-station are the dynamical byproduct of a cascade of processes involving different compartments of the hydro-climatic network (e.g., climate, rainfall, soil, vegetation) that regulates the transformation of rainfall into streamflows. In complex branching rivers, flow regimes result from the heterogeneous arrangement around the stream network of multiple hydrologic cascades that simultaneously occur within distinct contributing areas. As such, flow regimes are seen as the integrated output of a complex "network of networks", which can be properly characterized by its degree of temporal variability and spatial heterogeneity. Hydrologic networks that generate river flow regimes are dynamic in nature. In pristine rivers, the time-variance naturally emerges at multiple timescales from climate variability (namely, seasonality and inter-annual fluctuations), implying that the magnitude (and the features) of the water flow between two nodes may be highly variable across different seasons and years. Conversely, the spatial distribution of river flow regimes within pristine rivers involves scale-dependent transport features, as well as regional climatic and soil use gradients, which in small and meso-scale catchments (A < 103 km2) are usually mild enough to guarantee quite uniform flow regimes and high spatial correlations. Human-impacted rivers, instead, constitute hybrid networks where observed spatio-temporal patterns are dominated by anthropogenic shifts, such as landscape alterations and river regulation. In regulated rivers, the magnitude and the features of water flows from node to node may change significantly through time due to damming and withdrawals. However, regulation may impact river regimes in a spatially heterogeneous manner (e.g. in localized river reaches), with a significant decrease of spatial correlations and network connectivity. Provided that the spatial and temporal dynamics of flow regimes in complex rivers may strongly impact important biotic processes involved in the river food web (e.g. biofilm and riparian vegetation dynamics), the study of rivers as dynamic networks provides important clues to water management strategies and freshwater ecosystem studies.

A multi-layer MRI description of Parkinson's disease

NASA Astrophysics Data System (ADS)

La Rocca, M.; Amoroso, N.; Lella, E.; Bellotti, R.; Tangaro, S.

2017-09-01

Magnetic resonance imaging (MRI) along with complex network is currently one of the most widely adopted techniques for detection of structural changes in neurological diseases, such as Parkinson's Disease (PD). In this paper, we present a digital image processing study, within the multi-layer network framework, combining more classifiers to evaluate the informative power of the MRI features, for the discrimination of normal controls (NC) and PD subjects. We define a network for each MRI scan; the nodes are the sub-volumes (patches) the images are divided into and the links are defined using the Pearson's pairwise correlation between patches. We obtain a multi-layer network whose important network features, obtained with different feature selection methods, are used to feed a supervised multi-level random forest classifier which exploits this base of knowledge for accurate classification. Method evaluation has been carried out using T1 MRI scans of 354 individuals, including 177 PD subjects and 177 NC from the Parkinson's Progression Markers Initiative (PPMI) database. The experimental results demonstrate that the features obtained from multiplex networks are able to accurately describe PD patterns. Besides, also if a privileged scale for studying PD disease exists, exploring the informative content of more scales leads to a significant improvement of the performances in the discrimination between disease and healthy subjects. In particular, this method gives a comprehensive overview of brain regions statistically affected by the disease, an additional value to the presented study.

Feature selection for neural network based defect classification of ceramic components using high frequency ultrasound.

PubMed

Kesharaju, Manasa; Nagarajah, Romesh

2015-09-01

The motivation for this research stems from a need for providing a non-destructive testing method capable of detecting and locating any defects and microstructural variations within armour ceramic components before issuing them to the soldiers who rely on them for their survival. The development of an automated ultrasonic inspection based classification system would make possible the checking of each ceramic component and immediately alert the operator about the presence of defects. Generally, in many classification problems a choice of features or dimensionality reduction is significant and simultaneously very difficult, as a substantial computational effort is required to evaluate possible feature subsets. In this research, a combination of artificial neural networks and genetic algorithms are used to optimize the feature subset used in classification of various defects in reaction-sintered silicon carbide ceramic components. Initially wavelet based feature extraction is implemented from the region of interest. An Artificial Neural Network classifier is employed to evaluate the performance of these features. Genetic Algorithm based feature selection is performed. Principal Component Analysis is a popular technique used for feature selection and is compared with the genetic algorithm based technique in terms of classification accuracy and selection of optimal number of features. The experimental results confirm that features identified by Principal Component Analysis lead to improved performance in terms of classification percentage with 96% than Genetic algorithm with 94%. Copyright © 2015 Elsevier B.V. All rights reserved.

Pattern learning with deep neural networks in EMG-based speech recognition.

PubMed

Wand, Michael; Schultz, Tanja

2014-01-01

We report on classification of phones and phonetic features from facial electromyographic (EMG) data, within the context of our EMG-based Silent Speech interface. In this paper we show that a Deep Neural Network can be used to perform this classification task, yielding a significant improvement over conventional Gaussian Mixture models. Our central contribution is the visualization of patterns which are learned by the neural network. With increasing network depth, these patterns represent more and more intricate electromyographic activity.

Evolution and selection of river networks: Statics, dynamics, and complexity

PubMed Central

Rinaldo, Andrea; Rigon, Riccardo; Banavar, Jayanth R.; Maritan, Amos; Rodriguez-Iturbe, Ignacio

2014-01-01

Moving from the exact result that drainage network configurations minimizing total energy dissipation are stationary solutions of the general equation describing landscape evolution, we review the static properties and the dynamic origins of the scale-invariant structure of optimal river patterns. Optimal channel networks (OCNs) are feasible optimal configurations of a spanning network mimicking landscape evolution and network selection through imperfect searches for dynamically accessible states. OCNs are spanning loopless configurations, however, only under precise physical requirements that arise under the constraints imposed by river dynamics—every spanning tree is exactly a local minimum of total energy dissipation. It is remarkable that dynamically accessible configurations, the local optima, stabilize into diverse metastable forms that are nevertheless characterized by universal statistical features. Such universal features explain very well the statistics of, and the linkages among, the scaling features measured for fluvial landforms across a broad range of scales regardless of geology, exposed lithology, vegetation, or climate, and differ significantly from those of the ground state, known exactly. Results are provided on the emergence of criticality through adaptative evolution and on the yet-unexplored range of applications of the OCN concept. PMID:24550264

Multiview fusion for activity recognition using deep neural networks

NASA Astrophysics Data System (ADS)

Kavi, Rahul; Kulathumani, Vinod; Rohit, Fnu; Kecojevic, Vlad

2016-07-01

Convolutional neural networks (ConvNets) coupled with long short term memory (LSTM) networks have been recently shown to be effective for video classification as they combine the automatic feature extraction capabilities of a neural network with additional memory in the temporal domain. This paper shows how multiview fusion can be applied to such a ConvNet LSTM architecture. Two different fusion techniques are presented. The system is first evaluated in the context of a driver activity recognition system using data collected in a multicamera driving simulator. These results show significant improvement in accuracy with multiview fusion and also show that deep learning performs better than a traditional approach using spatiotemporal features even without requiring any background subtraction. The system is also validated on another publicly available multiview action recognition dataset that has 12 action classes and 8 camera views.

Drug Target Protein-Protein Interaction Networks: A Systematic Perspective

PubMed Central

2017-01-01

The identification and validation of drug targets are crucial in biomedical research and many studies have been conducted on analyzing drug target features for getting a better understanding on principles of their mechanisms. But most of them are based on either strong biological hypotheses or the chemical and physical properties of those targets separately. In this paper, we investigated three main ways to understand the functional biomolecules based on the topological features of drug targets. There are no significant differences between targets and common proteins in the protein-protein interactions network, indicating the drug targets are neither hub proteins which are dominant nor the bridge proteins. According to some special topological structures of the drug targets, there are significant differences between known targets and other proteins. Furthermore, the drug targets mainly belong to three typical communities based on their modularity. These topological features are helpful to understand how the drug targets work in the PPI network. Particularly, it is an alternative way to predict potential targets or extract nontargets to test a new drug target efficiently and economically. By this way, a drug target's homologue set containing 102 potential target proteins is predicted in the paper. PMID:28691014

Location Sensitive Deep Convolutional Neural Networks for Segmentation of White Matter Hyperintensities.

PubMed

Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; van Uden, Inge W M; Sanchez, Clara I; Litjens, Geert; de Leeuw, Frank-Erik; van Ginneken, Bram; Marchiori, Elena; Platel, Bram

2017-07-11

The anatomical location of imaging features is of crucial importance for accurate diagnosis in many medical tasks. Convolutional neural networks (CNN) have had huge successes in computer vision, but they lack the natural ability to incorporate the anatomical location in their decision making process, hindering success in some medical image analysis tasks. In this paper, to integrate the anatomical location information into the network, we propose several deep CNN architectures that consider multi-scale patches or take explicit location features while training. We apply and compare the proposed architectures for segmentation of white matter hyperintensities in brain MR images on a large dataset. As a result, we observe that the CNNs that incorporate location information substantially outperform a conventional segmentation method with handcrafted features as well as CNNs that do not integrate location information. On a test set of 50 scans, the best configuration of our networks obtained a Dice score of 0.792, compared to 0.805 for an independent human observer. Performance levels of the machine and the independent human observer were not statistically significantly different (p-value = 0.06).

Application of neural networks in the acousto-ultrasonic evaluation of metal-matrix composite specimens

NASA Technical Reports Server (NTRS)

Cios, Krzysztof J.; Tjia, Robert E.; Vary, Alex; Kautz, Harold E.

1992-01-01

Acousto-ultrasonics (AU) is a nondestructive evaluation (NDE) technique that was devised for the testing of various types of composite materials. A study has been done to determine how effectively the AU technique may be applied to metal-matrix composites (MMCs). The authors use the results and data obtained from that study and apply neural networks to them, particularly in the assessment of mechanical property variations of a specimen from AU measurements. It is assumed that there is no information concerning the important features of the AU signal which relate to the mechanical properties of the specimen. Minimally processed AU measurements are used while relying on the network's ability to extract the significant features of the signal.

A study of the temporal robustness of the growing global container-shipping network

PubMed Central

Wang, Nuo; Wu, Nuan; Dong, Ling-ling; Yan, Hua-kun; Wu, Di

2016-01-01

Whether they thrive as they grow must be determined for all constantly expanding networks. However, few studies have focused on this important network feature or the development of quantitative analytical methods. Given the formation and growth of the global container-shipping network, we proposed the concept of network temporal robustness and quantitative method. As an example, we collected container liner companies’ data at two time points (2004 and 2014) and built a shipping network with ports as nodes and routes as links. We thus obtained a quantitative value of the temporal robustness. The temporal robustness is a significant network property because, for the first time, we can clearly recognize that the shipping network has become more vulnerable to damage over the last decade: When the node failure scale reached 50% of the entire network, the temporal robustness was approximately −0.51% for random errors and −12.63% for intentional attacks. The proposed concept and analytical method described in this paper are significant for other network studies. PMID:27713549

Dependency-based long short term memory network for drug-drug interaction extraction.

PubMed

Wang, Wei; Yang, Xi; Yang, Canqun; Guo, Xiaowei; Zhang, Xiang; Wu, Chengkun

2017-12-28

Drug-drug interaction extraction (DDI) needs assistance from automated methods to address the explosively increasing biomedical texts. In recent years, deep neural network based models have been developed to address such needs and they have made significant progress in relation identification. We propose a dependency-based deep neural network model for DDI extraction. By introducing the dependency-based technique to a bi-directional long short term memory network (Bi-LSTM), we build three channels, namely, Linear channel, DFS channel and BFS channel. All of these channels are constructed with three network layers, including embedding layer, LSTM layer and max pooling layer from bottom up. In the embedding layer, we extract two types of features, one is distance-based feature and another is dependency-based feature. In the LSTM layer, a Bi-LSTM is instituted in each channel to better capture relation information. Then max pooling is used to get optimal features from the entire encoding sequential data. At last, we concatenate the outputs of all channels and then link it to the softmax layer for relation identification. To the best of our knowledge, our model achieves new state-of-the-art performance with the F-score of 72.0% on the DDIExtraction 2013 corpus. Moreover, our approach obtains much higher Recall value compared to the existing methods. The dependency-based Bi-LSTM model can learn effective relation information with less feature engineering in the task of DDI extraction. Besides, the experimental results show that our model excels at balancing the Precision and Recall values.

Bilinear Convolutional Neural Networks for Fine-grained Visual Recognition.

PubMed

Lin, Tsung-Yu; RoyChowdhury, Aruni; Maji, Subhransu

2017-07-04

We present a simple and effective architecture for fine-grained recognition called Bilinear Convolutional Neural Networks (B-CNNs). These networks represent an image as a pooled outer product of features derived from two CNNs and capture localized feature interactions in a translationally invariant manner. B-CNNs are related to orderless texture representations built on deep features but can be trained in an end-to-end manner. Our most accurate model obtains 84.1%, 79.4%, 84.5% and 91.3% per-image accuracy on the Caltech-UCSD birds [66], NABirds [63], FGVC aircraft [42], and Stanford cars [33] dataset respectively and runs at 30 frames-per-second on a NVIDIA Titan X GPU. We then present a systematic analysis of these networks and show that (1) the bilinear features are highly redundant and can be reduced by an order of magnitude in size without significant loss in accuracy, (2) are also effective for other image classification tasks such as texture and scene recognition, and (3) can be trained from scratch on the ImageNet dataset offering consistent improvements over the baseline architecture. Finally, we present visualizations of these models on various datasets using top activations of neural units and gradient-based inversion techniques. The source code for the complete system is available at http://vis-www.cs.umass.edu/bcnn.

Competing endogenous RNA regulatory network in papillary thyroid carcinoma.

PubMed

Chen, Shouhua; Fan, Xiaobin; Gu, He; Zhang, Lili; Zhao, Wenhua

2018-05-11

The present study aimed to screen all types of RNAs involved in the development of papillary thyroid carcinoma (PTC). RNA‑sequencing data of PTC and normal samples were used for screening differentially expressed (DE) microRNAs (DE‑miRNAs), long non‑coding RNAs (DE‑lncRNAs) and genes (DEGs). Subsequently, lncRNA‑miRNA, miRNA‑gene (that is, miRNA‑mRNA) and gene‑gene interaction pairs were extracted and used to construct regulatory networks. Feature genes in the miRNA‑mRNA network were identified by topological analysis and recursive feature elimination analysis. A support vector machine (SVM) classifier was built using 15 feature genes, and its classification effect was validated using two microarray data sets that were downloaded from the Gene Expression Omnibus (GEO) database. In addition, Gene Ontology function and Kyoto Encyclopedia Genes and Genomes pathway enrichment analyses were conducted for genes identified in the ceRNA network. A total of 506 samples, including 447 tumor samples and 59 normal samples, were obtained from The Cancer Genome Atlas (TCGA); 16 DE‑lncRNAs, 917 DEGs and 30 DE‑miRNAs were screened. The miRNA‑mRNA regulatory network comprised 353 nodes and 577 interactions. From these data, 15 feature genes with high predictive precision (>95%) were extracted from the network and were used to form an SVM classifier with an accuracy of 96.05% (486/506) for PTC samples downloaded from TCGA, and accuracies of 96.81 and 98.46% for GEO downloaded data sets. The ceRNA regulatory network comprised 596 lines (or interactions) and 365 nodes. Genes in the ceRNA network were significantly enriched in 'neuron development', 'differentiation', 'neuroactive ligand‑receptor interaction', 'metabolism of xenobiotics by cytochrome P450', 'drug metabolism' and 'cytokine‑cytokine receptor interaction' pathways. Hox transcript antisense RNA, miRNA‑206 and kallikrein‑related peptidase 10 were nodes in the ceRNA regulatory network of the selected feature gene, and they may serve import roles in the development of PTC.

Loss of integrity and atrophy in cingulate structural covariance networks in Parkinson's disease.

PubMed

de Schipper, Laura J; van der Grond, Jeroen; Marinus, Johan; Henselmans, Johanna M L; van Hilten, Jacobus J

2017-01-01

In Parkinson's disease (PD), the relation between cortical brain atrophy on MRI and clinical progression is not straightforward. Determination of changes in structural covariance networks - patterns of covariance in grey matter density - has shown to be a valuable technique to detect subtle grey matter variations. We evaluated how structural network integrity in PD is related to clinical data. 3 Tesla MRI was performed in 159 PD patients. We used nine standardized structural covariance networks identified in 370 healthy subjects as a template in the analysis of the PD data. Clinical assessment comprised motor features (Movement Disorder Society-Unified Parkinson's Disease Rating Scale; MDS-UPDRS motor scale) and predominantly non-dopaminergic features (SEverity of Non-dopaminergic Symptoms in Parkinson's Disease; SENS-PD scale: postural instability and gait difficulty, psychotic symptoms, excessive daytime sleepiness, autonomic dysfunction, cognitive impairment and depressive symptoms). Voxel-based analyses were performed within networks significantly associated with PD. The anterior and posterior cingulate network showed decreased integrity, associated with the SENS-PD score, p = 0.001 (β = - 0.265, η p 2  = 0.070) and p = 0.001 (β = - 0.264, η p 2  = 0.074), respectively. Of the components of the SENS-PD score, cognitive impairment and excessive daytime sleepiness were associated with atrophy within both networks. We identified loss of integrity and atrophy in the anterior and posterior cingulate networks in PD patients. Abnormalities of both networks were associated with predominantly non-dopaminergic features, specifically cognition and excessive daytime sleepiness. Our findings suggest that (components of) the cingulate networks display a specific vulnerability to the pathobiology of PD and may operate as interfaces between networks involved in cognition and alertness.

Extracting Intrinsic Functional Networks with Feature-Based Group Independent Component Analysis

ERIC Educational Resources Information Center

Calhoun, Vince D.; Allen, Elena

2013-01-01

There is increasing use of functional imaging data to understand the macro-connectome of the human brain. Of particular interest is the structure and function of intrinsic networks (regions exhibiting temporally coherent activity both at rest and while a task is being performed), which account for a significant portion of the variance in…

Discriminative analysis of early Alzheimer's disease based on two intrinsically anti-correlated networks with resting-state fMRI.

PubMed

Wang, Kun; Jiang, Tianzi; Liang, Meng; Wang, Liang; Tian, Lixia; Zhang, Xinqing; Li, Kuncheng; Liu, Zhening

2006-01-01

In this work, we proposed a discriminative model of Alzheimer's disease (AD) on the basis of multivariate pattern classification and functional magnetic resonance imaging (fMRI). This model used the correlation/anti-correlation coefficients of two intrinsically anti-correlated networks in resting brains, which have been suggested by two recent studies, as the feature of classification. Pseudo-Fisher Linear Discriminative Analysis (pFLDA) was then performed on the feature space and a linear classifier was generated. Using leave-one-out (LOO) cross validation, our results showed a correct classification rate of 83%. We also compared the proposed model with another one based on the whole brain functional connectivity. Our proposed model outperformed the other one significantly, and this implied that the two intrinsically anti-correlated networks may be a more susceptible part of the whole brain network in the early stage of AD.

Marine Vehicle Sensor Network Architecture and Protocol Designs for Ocean Observation

PubMed Central

Zhang, Shaowei; Yu, Jiancheng; Zhang, Aiqun; Yang, Lei; Shu, Yeqiang

2012-01-01

The micro-scale and meso-scale ocean dynamic processes which are nonlinear and have large variability, have a significant impact on the fisheries, natural resources, and marine climatology. A rapid, refined and sophisticated observation system is therefore needed in marine scientific research. The maneuverability and controllability of mobile sensor platforms make them a preferred choice to establish ocean observing networks, compared to the static sensor observing platform. In this study, marine vehicles are utilized as the nodes of mobile sensor networks for coverage sampling of a regional ocean area and ocean feature tracking. A synoptic analysis about marine vehicle dynamic control, multi vehicles mission assignment and path planning methods, and ocean feature tracking and observing techniques is given. Combined with the observation plan in the South China Sea, we provide an overview of the mobile sensor networks established with marine vehicles, and the corresponding simulation results. PMID:22368475

A novel tele-medical environment appropriate for use in tele-advisory and tele-surgery cases.

PubMed

Chatzipapadopoulos, F; Georgantas, N; Kotaras, A; Mamais, G; Tombros, S; Tselikis, G

1996-08-01

Tele-medical systems have been recently introduced in the field of networking as promising applications that can significantly improve the offering of medical treatment by providing services such as tele-advising, tele-surgery and remote monitoring in places where the presence of doctors or any medical specialists is difficult or time consuming. Some already existent networking models can be used for the establishment of a connection between the communicating sides. The offered network's security is also a significant factor. The present paper describes a software environment implementing a particular aspect of a tele-medical system. The developed system includes features such as direct communication between doctors and medical assistants, medical information acquisition and storing and high band information transfer in real-time. TCP/IP point-to-point protocol has been used for the implementation of the non bandwidth-critical connections. The application introduces novel features with the use of ATM connection for supporting the time-critical service of video transfer to and from the medical database.

Classification of reflected signals from cavitated tooth surfaces using an artificial intelligence technique incorporating a fiber optic displacement sensor

NASA Astrophysics Data System (ADS)

Rahman, Husna Abdul; Harun, Sulaiman Wadi; Arof, Hamzah; Irawati, Ninik; Musirin, Ismail; Ibrahim, Fatimah; Ahmad, Harith

2014-05-01

An enhanced dental cavity diameter measurement mechanism using an intensity-modulated fiber optic displacement sensor (FODS) scanning and imaging system, fuzzy logic as well as a single-layer perceptron (SLP) neural network, is presented. The SLP network was employed for the classification of the reflected signals, which were obtained from the surfaces of teeth samples and captured using FODS. Two features were used for the classification of the reflected signals with one of them being the output of a fuzzy logic. The test results showed that the combined fuzzy logic and SLP network methodology contributed to a 100% classification accuracy of the network. The high-classification accuracy significantly demonstrates the suitability of the proposed features and classification using SLP networks for classifying the reflected signals from teeth surfaces, enabling the sensor to accurately measure small diameters of tooth cavity of up to 0.6 mm. The method remains simple enough to allow its easy integration in existing dental restoration support systems.

Classification of reflected signals from cavitated tooth surfaces using an artificial intelligence technique incorporating a fiber optic displacement sensor.

PubMed

Rahman, Husna Abdul; Harun, Sulaiman Wadi; Arof, Hamzah; Irawati, Ninik; Musirin, Ismail; Ibrahim, Fatimah; Ahmad, Harith

2014-05-01

An enhanced dental cavity diameter measurement mechanism using an intensity-modulated fiber optic displacement sensor (FODS) scanning and imaging system, fuzzy logic as well as a single-layer perceptron (SLP) neural network, is presented. The SLP network was employed for the classification of the reflected signals, which were obtained from the surfaces of teeth samples and captured using FODS. Two features were used for the classification of the reflected signals with one of them being the output of a fuzzy logic. The test results showed that the combined fuzzy logic and SLP network methodology contributed to a 100% classification accuracy of the network. The high-classification accuracy significantly demonstrates the suitability of the proposed features and classification using SLP networks for classifying the reflected signals from teeth surfaces, enabling the sensor to accurately measure small diameters of tooth cavity of up to 0.6 mm. The method remains simple enough to allow its easy integration in existing dental restoration support systems.

Concurrent evolution of feature extractors and modular artificial neural networks

NASA Astrophysics Data System (ADS)

Hannak, Victor; Savakis, Andreas; Yang, Shanchieh Jay; Anderson, Peter

2009-05-01

This paper presents a new approach for the design of feature-extracting recognition networks that do not require expert knowledge in the application domain. Feature-Extracting Recognition Networks (FERNs) are composed of interconnected functional nodes (feurons), which serve as feature extractors, and are followed by a subnetwork of traditional neural nodes (neurons) that act as classifiers. A concurrent evolutionary process (CEP) is used to search the space of feature extractors and neural networks in order to obtain an optimal recognition network that simultaneously performs feature extraction and recognition. By constraining the hill-climbing search functionality of the CEP on specific parts of the solution space, i.e., individually limiting the evolution of feature extractors and neural networks, it was demonstrated that concurrent evolution is a necessary component of the system. Application of this approach to a handwritten digit recognition task illustrates that the proposed methodology is capable of producing recognition networks that perform in-line with other methods without the need for expert knowledge in image processing.

A single-layer network unsupervised feature learning method for white matter hyperintensity segmentation

NASA Astrophysics Data System (ADS)

Vijverberg, Koen; Ghafoorian, Mohsen; van Uden, Inge W. M.; de Leeuw, Frank-Erik; Platel, Bram; Heskes, Tom

2016-03-01

Cerebral small vessel disease (SVD) is a disorder frequently found among the old people and is associated with deterioration in cognitive performance, parkinsonism, motor and mood impairments. White matter hyperintensities (WMH) as well as lacunes, microbleeds and subcortical brain atrophy are part of the spectrum of image findings, related to SVD. Accurate segmentation of WMHs is important for prognosis and diagnosis of multiple neurological disorders such as MS and SVD. Almost all of the published (semi-)automated WMH detection models employ multiple complex hand-crafted features, which require in-depth domain knowledge. In this paper we propose to apply a single-layer network unsupervised feature learning (USFL) method to avoid hand-crafted features, but rather to automatically learn a more efficient set of features. Experimental results show that a computer aided detection system with a USFL system outperforms a hand-crafted approach. Moreover, since the two feature sets have complementary properties, a hybrid system that makes use of both hand-crafted and unsupervised learned features, shows a significant performance boost compared to each system separately, getting close to the performance of an independent human expert.

Convolutional neural network features based change detection in satellite images

NASA Astrophysics Data System (ADS)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

Applying Gradient Descent in Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Cui, Nan

2018-04-01

With the development of the integrated circuit and computer science, people become caring more about solving practical issues via information technologies. Along with that, a new subject called Artificial Intelligent (AI) comes up. One popular research interest of AI is about recognition algorithm. In this paper, one of the most common algorithms, Convolutional Neural Networks (CNNs) will be introduced, for image recognition. Understanding its theory and structure is of great significance for every scholar who is interested in this field. Convolution Neural Network is an artificial neural network which combines the mathematical method of convolution and neural network. The hieratical structure of CNN provides it reliable computer speed and reasonable error rate. The most significant characteristics of CNNs are feature extraction, weight sharing and dimension reduction. Meanwhile, combining with the Back Propagation (BP) mechanism and the Gradient Descent (GD) method, CNNs has the ability to self-study and in-depth learning. Basically, BP provides an opportunity for backwardfeedback for enhancing reliability and GD is used for self-training process. This paper mainly discusses the CNN and the related BP and GD algorithms, including the basic structure and function of CNN, details of each layer, the principles and features of BP and GD, and some examples in practice with a summary in the end.

GENET note no. 1

NASA Technical Reports Server (NTRS)

Yeh, J. W.

1971-01-01

The general features of the GENET system for simulating networks are described. A set of features is presented which are desirable for network simulations and which are expected to be achieved by this system. Among these features are: (1) two level network modeling; and (2) problem oriented operations. Several typical network systems are modeled in GENET framework to illustrate various of the features and to show its applicability.

Similarity-based Regularized Latent Feature Model for Link Prediction in Bipartite Networks.

PubMed

Wang, Wenjun; Chen, Xue; Jiao, Pengfei; Jin, Di

2017-12-05

Link prediction is an attractive research topic in the field of data mining and has significant applications in improving performance of recommendation system and exploring evolving mechanisms of the complex networks. A variety of complex systems in real world should be abstractly represented as bipartite networks, in which there are two types of nodes and no links connect nodes of the same type. In this paper, we propose a framework for link prediction in bipartite networks by combining the similarity based structure and the latent feature model from a new perspective. The framework is called Similarity Regularized Nonnegative Matrix Factorization (SRNMF), which explicitly takes the local characteristics into consideration and encodes the geometrical information of the networks by constructing a similarity based matrix. We also develop an iterative scheme to solve the objective function based on gradient descent. Extensive experiments on a variety of real world bipartite networks show that the proposed framework of link prediction has a more competitive, preferable and stable performance in comparison with the state-of-art methods.

The power of social networks and social support in promotion of physical activity and body mass index among African American adults.

PubMed

Flórez, Karen R; Richardson, Andrea S; Ghosh-Dastidar, Madhumita Bonnie; Troxel, Wendy; DeSantis, Amy; Colabianchi, Natalie; Dubowitz, Tamara

2018-04-01

Social support and social networks can elucidate important structural and functional aspects of social relationships that are associated with health-promoting behaviors, including Physical Activity (PA) and weight. A growing number of studies have investigated the relationship between social support, social networks, PA and obesity specifically among African Americans; however, the evidence is mixed and many studies focus exclusively on African American women. Most studies have also focused on either functional or structural aspects of social relationships (but not both) and few have objectively measured moderate-to-vigorous physical activity (MVPA) and body mass index (BMI). Cross-sectional surveys of adult African American men and women living in two low-income predominantly African American neighborhoods in Pittsburgh, PA (N = 799) measured numerous structural features as well as functional aspects of social relationships. Specifically, structural features included social isolation, and social network size and diversity. Functional aspects included perceptions of social support for physical activity from the social network in general as well as from family and friends specifically. Height, weight, and PA were objectively measured. From these, we derived Body Mass Index (BMI) and moderate-to-vigorous physical activity (MVPA). All regression models were stratified by gender, and included age, income, education, employment, marital status, physical limitations, and a neighborhood indicator. Greater social isolation was a significant predictor of lower BMI among men only. Among women only, social isolation was significantly associated with increased MVPA whereas, network diversity was significantly associated with reduced MVPA. Future research would benefit from in-depth qualitative investigations to understand how social networks may act to influence different types of physical activity among African Americans, as well as understand how they can be possible levers for health promotion and prevention.

Global-local feature attention network with reranking strategy for image caption generation

NASA Astrophysics Data System (ADS)

Wu, Jie; Xie, Si-ya; Shi, Xin-bao; Chen, Yao-wen

2017-11-01

In this paper, a novel framework, named as global-local feature attention network with reranking strategy (GLAN-RS), is presented for image captioning task. Rather than only adopting unitary visual information in the classical models, GLAN-RS explores the attention mechanism to capture local convolutional salient image maps. Furthermore, we adopt reranking strategy to adjust the priority of the candidate captions and select the best one. The proposed model is verified using the Microsoft Common Objects in Context (MSCOCO) benchmark dataset across seven standard evaluation metrics. Experimental results show that GLAN-RS significantly outperforms the state-of-the-art approaches, such as multimodal recurrent neural network (MRNN) and Google NIC, which gets an improvement of 20% in terms of BLEU4 score and 13 points in terms of CIDER score.

Electrochemically Smart Bimetallic Materials Featuring Group 11 Metals: In-situ Conductive Network Generation and Its Impact on Cell Capacity

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

Takeuchi, Esther

2016-11-30

Our results for this program “Electrochemically smart bimetallic materials featuring Group 11 metals: in-situ conductive matrix generation and its impact on battery capacity, power and reversibility” have been highly successful: 1) we demonstrated material structures which generated in-situ conductive networks through electrochemical activation with increases in conductivity up to 10,000 fold, 2) we pioneered in situ analytical methodology to map the cathodes at several stages of discharge through the use of Energy Dispersive X-ray Diffraction (EDXRD) to elucidate the kinetic dependence of the conductive network formation, and 3) we successfully designed synthetic methodology for direct control of material properties includingmore » crystallite size and surface area which showed significant impact on electrochemical behavior.« less

Network Analysis of Associations between Serum Interferon Alpha Activity, Autoantibodies, and Clinical Features in Systemic Lupus Erythematosus

PubMed Central

Weckerle, Corinna E.; Franek, Beverly S.; Kelly, Jennifer A.; Kumabe, Marissa; Mikolaitis, Rachel A.; Green, Stephanie L.; Utset, Tammy O.; Jolly, Meenakshi; James, Judith A.; Harley, John B.; Niewold, Timothy B.

2010-01-01

Background Interferon-alpha (IFN-α) is a primary pathogenic factor in systemic lupus erythematosus (SLE), and high IFN-α levels may be associated with particular clinical manifestations. The prevalence of individual clinical and serologic features differs significantly by ancestry. We used multivariate and network analyses to detect associations between clinical and serologic disease manifestations and serum IFN-α activity in a large diverse SLE cohort. Methods 1089 SLE patients were studied (387 African-American, 186 Hispanic-American, and 516 European-American). Presence or absence of ACR clinical criteria for SLE, autoantibodies, and serum IFN-α activity data were analyzed in univariate and multivariate models. Iterative multivariate logistic regression was performed in each background separately to establish the network of associations between variables that were independently significant following Bonferroni correction. Results In all ancestral backgrounds, high IFN-α activity was associated with anti-Ro and anti-dsDNA antibodies (p-values 4.6×10−18 and 2.9 × 10−16 respectively). Younger age, non-European ancestry, and anti-RNP were also independently associated with increased serum IFN-α activity (p≤6.7×10−4). We found 14 unique associations between variables in network analysis, and only 7 of these associations were shared by more than one ancestral background. Associations between clinical criteria were different in different ancestral backgrounds, while autoantibody-IFN-α relationships were similar across backgrounds. IFN-α activity and autoantibodies were not associated with ACR clinical features in multivariate models. Conclusions Serum IFN-α activity was strongly and consistently associated with autoantibodies, and not independently associated with clinical features in SLE. IFN-α may be more relevant to humoral tolerance and initial pathogenesis than later clinical disease manifestations. PMID:21162028

Disrupted topological organization of structural networks revealed by probabilistic diffusion tractography in Tourette syndrome children.

PubMed

Wen, Hongwei; Liu, Yue; Rekik, Islem; Wang, Shengpei; Zhang, Jishui; Zhang, Yue; Peng, Yun; He, Huiguang

2017-08-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder. Although previous TS studies revealed structural abnormalities in distinct corticobasal ganglia circuits, the topological alterations of the whole-brain white matter (WM) structural networks remain poorly understood. Here, we used diffusion MRI probabilistic tractography and graph theoretical analysis to investigate the topological organization of WM networks in 44 drug-naive TS children and 41 age- and gender-matched healthy children. The WM networks were constructed by estimating inter-regional connectivity probability and the topological properties were characterized using graph theory. We found that both TS and control groups showed an efficient small-world organization in WM networks. However, compared to controls, TS children exhibited decreased global and local efficiency, increased shortest path length and small worldness, indicating a disrupted balance between local specialization and global integration in structural networks. Although both TS and control groups showed highly similar hub distributions, TS children exhibited significant decreased nodal efficiency, mainly distributed in the default mode, language, visual, and sensorimotor systems. Furthermore, two separate networks showing significantly decreased connectivity in TS group were identified using network-based statistical (NBS) analysis, primarily composed of the parieto-occipital cortex, precuneus, and paracentral lobule. Importantly, we combined support vector machine and multiple kernel learning frameworks to fuse multiple levels of network topological features for classification of individuals, achieving high accuracy of 86.47%. Together, our study revealed the disrupted topological organization of structural networks related to pathophysiology of TS, and the discriminative topological features for classification are potential quantitative neuroimaging biomarkers for clinical TS diagnosis. Hum Brain Mapp 38:3988-4008, 2017. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Statistical Analysis of Bus Networks in India

PubMed Central

2016-01-01

In this paper, we model the bus networks of six major Indian cities as graphs in L-space, and evaluate their various statistical properties. While airline and railway networks have been extensively studied, a comprehensive study on the structure and growth of bus networks is lacking. In India, where bus transport plays an important role in day-to-day commutation, it is of significant interest to analyze its topological structure and answer basic questions on its evolution, growth, robustness and resiliency. Although the common feature of small-world property is observed, our analysis reveals a wide spectrum of network topologies arising due to significant variation in the degree-distribution patterns in the networks. We also observe that these networks although, robust and resilient to random attacks are particularly degree-sensitive. Unlike real-world networks, such as Internet, WWW and airline, that are virtual, bus networks are physically constrained. Our findings therefore, throw light on the evolution of such geographically and constrained networks that will help us in designing more efficient bus networks in the future. PMID:27992590

Identifying patients with Alzheimer's disease using resting-state fMRI and graph theory.

PubMed

Khazaee, Ali; Ebrahimzadeh, Ata; Babajani-Feremi, Abbas

2015-11-01

Study of brain network on the basis of resting-state functional magnetic resonance imaging (fMRI) has provided promising results to investigate changes in connectivity among different brain regions because of diseases. Graph theory can efficiently characterize different aspects of the brain network by calculating measures of integration and segregation. In this study, we combine graph theoretical approaches with advanced machine learning methods to study functional brain network alteration in patients with Alzheimer's disease (AD). Support vector machine (SVM) was used to explore the ability of graph measures in diagnosis of AD. We applied our method on the resting-state fMRI data of twenty patients with AD and twenty age and gender matched healthy subjects. The data were preprocessed and each subject's graph was constructed by parcellation of the whole brain into 90 distinct regions using the automated anatomical labeling (AAL) atlas. The graph measures were then calculated and used as the discriminating features. Extracted network-based features were fed to different feature selection algorithms to choose most significant features. In addition to the machine learning approach, statistical analysis was performed on connectivity matrices to find altered connectivity patterns in patients with AD. Using the selected features, we were able to accurately classify patients with AD from healthy subjects with accuracy of 100%. Results of this study show that pattern recognition and graph of brain network, on the basis of the resting state fMRI data, can efficiently assist in the diagnosis of AD. Classification based on the resting-state fMRI can be used as a non-invasive and automatic tool to diagnosis of Alzheimer's disease. Copyright © 2015 International Federation of Clinical Neurophysiology. All rights reserved.

Good Features to Correlate for Visual Tracking

NASA Astrophysics Data System (ADS)

Gundogdu, Erhan; Alatan, A. Aydin

2018-05-01

During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.

Morphological self-organizing feature map neural network with applications to automatic target recognition

NASA Astrophysics Data System (ADS)

Zhang, Shijun; Jing, Zhongliang; Li, Jianxun

2005-01-01

The rotation invariant feature of the target is obtained using the multi-direction feature extraction property of the steerable filter. Combining the morphological operation top-hat transform with the self-organizing feature map neural network, the adaptive topological region is selected. Using the erosion operation, the topological region shrinkage is achieved. The steerable filter based morphological self-organizing feature map neural network is applied to automatic target recognition of binary standard patterns and real-world infrared sequence images. Compared with Hamming network and morphological shared-weight networks respectively, the higher recognition correct rate, robust adaptability, quick training, and better generalization of the proposed method are achieved.

Patient-specific connectivity pattern of epileptic network in frontal lobe epilepsy

PubMed Central

Luo, Cheng; An, Dongmei; Yao, Dezhong; Gotman, Jean

2014-01-01

There is evidence that focal epilepsy may involve the dysfunction of a brain network in addition to the focal region. To delineate the characteristics of this epileptic network, we collected EEG/fMRI data from 23 patients with frontal lobe epilepsy. For each patient, EEG/fMRI analysis was first performed to determine the BOLD response to epileptic spikes. The maximum activation cluster in the frontal lobe was then chosen as the seed to identify the epileptic network in fMRI data. Functional connectivity analysis seeded at the same region was also performed in 63 healthy control subjects. Nine features were used to evaluate the differences of epileptic network patterns in three connection levels between patients and controls. Compared with control subjects, patients showed overall more functional connections between the epileptogenic region and the rest of the brain and higher laterality. However, the significantly increased connections were located in the neighborhood of the seed, but the connections between the seed and remote regions actually decreased. Comparing fMRI runs with interictal epileptic discharges (IEDs) and without IEDs, the patient-specific connectivity pattern was not changed significantly. These findings regarding patient-specific connectivity patterns of epileptic networks in FLE reflect local high connectivity and connections with distant regions differing from those of healthy controls. Moreover, the difference between the two groups in most features was observed in the strictest of the three connection levels. The abnormally high connectivity might reflect a predominant attribute of the epileptic network, which may facilitate propagation of epileptic activity among regions in the network. PMID:24936418

Reinforcement learning for routing in cognitive radio ad hoc networks.

PubMed

Al-Rawi, Hasan A A; Yau, Kok-Lim Alvin; Mohamad, Hafizal; Ramli, Nordin; Hashim, Wahidah

2014-01-01

Cognitive radio (CR) enables unlicensed users (or secondary users, SUs) to sense for and exploit underutilized licensed spectrum owned by the licensed users (or primary users, PUs). Reinforcement learning (RL) is an artificial intelligence approach that enables a node to observe, learn, and make appropriate decisions on action selection in order to maximize network performance. Routing enables a source node to search for a least-cost route to its destination node. While there have been increasing efforts to enhance the traditional RL approach for routing in wireless networks, this research area remains largely unexplored in the domain of routing in CR networks. This paper applies RL in routing and investigates the effects of various features of RL (i.e., reward function, exploitation, and exploration, as well as learning rate) through simulation. New approaches and recommendations are proposed to enhance the features in order to improve the network performance brought about by RL to routing. Simulation results show that the RL parameters of the reward function, exploitation, and exploration, as well as learning rate, must be well regulated, and the new approaches proposed in this paper improves SUs' network performance without significantly jeopardizing PUs' network performance, specifically SUs' interference to PUs.

Reinforcement Learning for Routing in Cognitive Radio Ad Hoc Networks

PubMed Central

Al-Rawi, Hasan A. A.; Mohamad, Hafizal; Hashim, Wahidah

2014-01-01

Cognitive radio (CR) enables unlicensed users (or secondary users, SUs) to sense for and exploit underutilized licensed spectrum owned by the licensed users (or primary users, PUs). Reinforcement learning (RL) is an artificial intelligence approach that enables a node to observe, learn, and make appropriate decisions on action selection in order to maximize network performance. Routing enables a source node to search for a least-cost route to its destination node. While there have been increasing efforts to enhance the traditional RL approach for routing in wireless networks, this research area remains largely unexplored in the domain of routing in CR networks. This paper applies RL in routing and investigates the effects of various features of RL (i.e., reward function, exploitation, and exploration, as well as learning rate) through simulation. New approaches and recommendations are proposed to enhance the features in order to improve the network performance brought about by RL to routing. Simulation results show that the RL parameters of the reward function, exploitation, and exploration, as well as learning rate, must be well regulated, and the new approaches proposed in this paper improves SUs' network performance without significantly jeopardizing PUs' network performance, specifically SUs' interference to PUs. PMID:25140350

Interplay of ICP and IXP over the Internet with power-law features

NASA Astrophysics Data System (ADS)

Fan, Zhongyan; Tang, Wallace Kit-Sang

The Internet is the largest artificial network consisting of billions of IP devices, managed by tens of thousands of autonomous systems (ASes). Due to its importance, the Internet has received much attention and its topological features, mainly in AS-level, have been widely explored from the complex network perspective. However, most of the previous studies assume a homogeneous model in which nodes are indistinguishable in nature. It may be good for a general study of topological structure, but unfortunately it fails to reflect the functionality. The Internet ecology is in fact heterogeneous and highly complex. It consists of various elements such as Internet Exchange Points (IXPs), Internet Content Providers (ICPs), and normal Autonomous System (ASes), realizing different roles in the Internet. In this paper, we propose level-structured network models for investigating how ICP performs under the AS-topology with power-law features and how IXP enhances its performance from a complex network perspective. Based on real data, our results reveal that the power-law nature of the Internet facilitates content delivery not only in efficiency but also in path redundancy. Moreover, the proposed multi-level framework is able to clearly illustrate the significant benefits gained by ICP from IXP peerings.

A Novel Connectionist Network for Solving Long Time-Lag Prediction Tasks

NASA Astrophysics Data System (ADS)

Johnson, Keith; MacNish, Cara

Traditional Recurrent Neural Networks (RNNs) perform poorly on learning tasks involving long time-lag dependencies. More recent approaches such as LSTM and its variants significantly improve on RNNs ability to learn this type of problem. We present an alternative approach to encoding temporal dependencies that associates temporal features with nodes rather than state values, where the nodes explicitly encode dependencies over variable time delays. We show promising results comparing the network's performance to LSTM variants on an extended Reber grammar task.

Diagnosis of Diabetes Mellitus by Extraction of Morphological Features of Red Blood Cells Using an Artificial Neural Network.

PubMed

Palanisamy, Vinupritha; Mariamichael, Anburajan

2016-10-01

Background and Aim: Diabetes mellitus is a metabolic disorder characterized by varying hyperglycemias either due to insufficient secretion of insulin by the pancreas or improper utilization of glucose. The study was aimed to investigate the association of morphological features of erythrocytes among normal and diabetic subjects and its gender-based changes and thereby to develop a computer aided tool to diagnose diabetes using features extracted from RBC. Materials and Methods: The study involved 138 normal and 144 diabetic subjects. The blood was drawn from the subjects and the blood smear prepared was digitized using Zeiss fluorescent microscope. The digitized images were pre-processed and texture segmentation was performed to extract the various morphological features. The Pearson correlation test was performed and subsequently, classification of subjects as normal and diabetes was carried out by a neural network classifier based on the features that demonstrated significance at the level of P <0.05. Result: The proposed system demonstrated an overall accuracy, sensitivity, specificity, positive predictive value and negative predictive value of 93.3, 93.71, 92.8, 93.1 and 93.5% respectively. Conclusion: The morphological features exhibited a statistically significant difference (P<0.01) between the normal and diabetic cells, suggesting that it could be helpful in the diagnosis of Diabetes mellitus using a computer aided system. © Georg Thieme Verlag KG Stuttgart · New York.

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method.

PubMed

Guo, Xinyu; Dominick, Kelli C; Minai, Ali A; Li, Hailong; Erickson, Craig A; Lu, Long J

2017-01-01

The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t -test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre-defined brain networks including the default-mode, cingulo-opercular, frontal-parietal, and cerebellum. Thirteen of them are statically significant between ASD and TD groups (two sample t -test p < 0.05) while 19 of them are not. The relationship between the statically significant FCs and the corresponding ASD behavior symptoms is discussed based on the literature and clinician's expert knowledge. Meanwhile, the potential reason of obtaining 19 FCs which are not statistically significant is also provided.

A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery

NASA Astrophysics Data System (ADS)

Wang, Ke; Guo, Ping; Luo, A.-Li

2017-03-01

Spectral feature extraction is a crucial procedure in automated spectral analysis. This procedure starts from the spectral data and produces informative and non-redundant features, facilitating the subsequent automated processing and analysis with machine-learning and data-mining techniques. In this paper, we present a new automated feature extraction method for astronomical spectra, with application in spectral classification and defective spectra recovery. The basic idea of our approach is to train a deep neural network to extract features of spectra with different levels of abstraction in different layers. The deep neural network is trained with a fast layer-wise learning algorithm in an analytical way without any iterative optimization procedure. We evaluate the performance of the proposed scheme on real-world spectral data. The results demonstrate that our method is superior regarding its comprehensive performance, and the computational cost is significantly lower than that for other methods. The proposed method can be regarded as a new valid alternative general-purpose feature extraction method for various tasks in spectral data analysis.

Impact of PON deployment on metro networks

NASA Astrophysics Data System (ADS)

Poirrier, Julien; Herviou, Fabrice; Barboule, Hélène; Moignard, Maryse

2009-01-01

FTTH or FTTC, depending on countries and areas, will be the key technology for operators to differentiate themselves from competitors and win market share. Such a disruptive evolution of the access network should be supported by a significant re-design of the higher network layers. In the present paper, the required features of these new WDM networks are presented. Capacity and cost are the two obvious drivers. But versatility will be crucial to cope with an uncertain context (tedious prediction of traffic, regulation and services) and with very diverse population densities. Finally we also address how PON could benefit from mature WDM technologies to ease the global network design.

On Social e-Learning

NASA Astrophysics Data System (ADS)

Kim, Won; Jeong, Ok-Ran

Social Web sites include social networking sites and social media sites. They make it possible for people to share user-created contents online and to interact and stay connected with their online people networks. The social features of social Web sites, appropriately adapted, can help turn e-learning into social e-learning and make e-learning significantly more effective. In this paper, we develop requirements for social e-learning systems. They include incorporating the many of the social features of social Web sites, accounting for all key stakeholders and learning subjects, and curbing various types of misuses by people. We also examine the capabilities of representative social e-learning Web sites that are available today.

Categorical Structure among Shared Features in Networks of Early-Learned Nouns

ERIC Educational Resources Information Center

Hills, Thomas T.; Maouene, Mounir; Maouene, Josita; Sheya, Adam; Smith, Linda

2009-01-01

The shared features that characterize the noun categories that young children learn first are a formative basis of the human category system. To investigate the potential categorical information contained in the features of early-learned nouns, we examine the graph-theoretic properties of noun-feature networks. The networks are built from the…

Recognition of abstract objects via neural oscillators: interaction among topological organization, associative memory and gamma band synchronization.

PubMed

Ursino, Mauro; Magosso, Elisa; Cuppini, Cristiano

2009-02-01

Synchronization of neural activity in the gamma band is assumed to play a significant role not only in perceptual processing, but also in higher cognitive functions. Here, we propose a neural network of Wilson-Cowan oscillators to simulate recognition of abstract objects, each represented as a collection of four features. Features are ordered in topological maps of oscillators connected via excitatory lateral synapses, to implement a similarity principle. Experience on previous objects is stored in long-range synapses connecting the different topological maps, and trained via timing dependent Hebbian learning (previous knowledge principle). Finally, a downstream decision network detects the presence of a reliable object representation, when all features are oscillating in synchrony. Simulations performed giving various simultaneous objects to the network (from 1 to 4), with some missing and/or modified properties suggest that the network can reconstruct objects, and segment them from the other simultaneously present objects, even in case of deteriorated information, noise, and moderate correlation among the inputs (one common feature). The balance between sensitivity and specificity depends on the strength of the Hebbian learning. Achieving a correct reconstruction in all cases, however, requires ad hoc selection of the oscillation frequency. The model represents an attempt to investigate the interactions among topological maps, autoassociative memory, and gamma-band synchronization, for recognition of abstract objects.

Deep convolutional neural networks for classifying GPR B-scans

NASA Astrophysics Data System (ADS)

Besaw, Lance E.; Stimac, Philip J.

2015-05-01

Symmetric and asymmetric buried explosive hazards (BEHs) present real, persistent, deadly threats on the modern battlefield. Current approaches to mitigate these threats rely on highly trained operatives to reliably detect BEHs with reasonable false alarm rates using handheld Ground Penetrating Radar (GPR) and metal detectors. As computers become smaller, faster and more efficient, there exists greater potential for automated threat detection based on state-of-the-art machine learning approaches, reducing the burden on the field operatives. Recent advancements in machine learning, specifically deep learning artificial neural networks, have led to significantly improved performance in pattern recognition tasks, such as object classification in digital images. Deep convolutional neural networks (CNNs) are used in this work to extract meaningful signatures from 2-dimensional (2-D) GPR B-scans and classify threats. The CNNs skip the traditional "feature engineering" step often associated with machine learning, and instead learn the feature representations directly from the 2-D data. A multi-antennae, handheld GPR with centimeter-accurate positioning data was used to collect shallow subsurface data over prepared lanes containing a wide range of BEHs. Several heuristics were used to prevent over-training, including cross validation, network weight regularization, and "dropout." Our results show that CNNs can extract meaningful features and accurately classify complex signatures contained in GPR B-scans, complementing existing GPR feature extraction and classification techniques.

Overview of timing/synchronization for digital communications

NASA Technical Reports Server (NTRS)

Stover, H. A.

1978-01-01

Systems in general, and switched systems in particular, are explained. It pointed out some of the criteria that greatly influence timing/synchronization subsystem design for a military communications network but have little or no significance for civil systems. Timing techniques were evaluated in terms of fundamental features. Different combinations of these features covered most possibilities from which a synchronous timing system could be chosen.

Multi-image CAD employing features derived from ipsilateral mammographic views

NASA Astrophysics Data System (ADS)

Good, Walter F.; Zheng, Bin; Chang, Yuan-Hsiang; Wang, Xiao Hui; Maitz, Glenn S.; Gur, David

1999-05-01

On mammograms, certain kinds of features related to masses (e.g., location, texture, degree of spiculation, and integrated density difference) tend to be relatively invariant, or at last predictable, with respect to breast compression. Thus, ipsilateral pairs of mammograms may contain information not available from analyzing single views separately. To demonstrate the feasibility of incorporating multi-view features into CAD algorithm, `single-image' CAD was applied to each individual image in a set of 60 ipsilateral studies, after which all possible pairs of suspicious regions, consisting of one from each view, were formed. For these 402 pairs we defined and evaluated `multi-view' features such as: (1) relative position of centers of regions; (2) ratio of lengths of region projections parallel to nipple axis lines; (3) ratio of integrated contrast difference; (4) ratio of the sizes of the suspicious regions; and (5) measure of relative complexity of region boundaries. Each pair was identified as either a `true positive/true positive' (T) pair (i.e., two regions which are projections of the same actual mass), or as a falsely associated pair (F). Distributions for each feature were calculated. A Bayesian network was trained and tested to classify pairs of suspicious regions based exclusively on the multi-view features described above. Distributions for all features were significantly difference for T versus F pairs as indicated by likelihood ratios. Performance of the Bayesian network, which was measured by ROC analysis, indicates a significant ability to distinguish between T pairs and F pairs (Az equals 0.82 +/- 0.03), using information that is attributed to the multi-view content. This study is the first demonstration that there is a significant amount of spatial information that can be derived from ipsilateral pairs of mammograms.

Distinguishing humans from computers in the game of go: A complex network approach

NASA Astrophysics Data System (ADS)

Coquidé, C.; Georgeot, B.; Giraud, O.

2017-08-01

We compare complex networks built from the game of go and obtained from databases of human-played games with those obtained from computer-played games. Our investigations show that statistical features of the human-based networks and the computer-based networks differ, and that these differences can be statistically significant on a relatively small number of games using specific estimators. We show that the deterministic or stochastic nature of the computer algorithm playing the game can also be distinguished from these quantities. This can be seen as a tool to implement a Turing-like test for go simulators.

Characteristics of group networks in the KOSPI and the KOSDAQ

NASA Astrophysics Data System (ADS)

Kim, Kyungsik; Ko, Jeung-Su; Yi, Myunggi

2012-02-01

We investigate the main feature of group networks in the KOSPI and KOSDAQ of Korean financial markets and analyze daily cross-correlations between price fluctuations for the 5-year time period from 2006 to 2010. We discuss the stabilities by undressing the market-wide effect using the Markowitz multi-factor model and the network-based approach. In particular we ascertain the explicit list of significant firms in the few largest eigenvectors from the undressed correlation matrix. Finally, we show the structure of group correlation by applying a network-based approach. In addition, the relation between market capitalizations and businesses is examined.

Constructing Precisely Computing Networks with Biophysical Spiking Neurons.

PubMed

Schwemmer, Michael A; Fairhall, Adrienne L; Denéve, Sophie; Shea-Brown, Eric T

2015-07-15

While spike timing has been shown to carry detailed stimulus information at the sensory periphery, its possible role in network computation is less clear. Most models of computation by neural networks are based on population firing rates. In equivalent spiking implementations, firing is assumed to be random such that averaging across populations of neurons recovers the rate-based approach. Recently, however, Denéve and colleagues have suggested that the spiking behavior of neurons may be fundamental to how neuronal networks compute, with precise spike timing determined by each neuron's contribution to producing the desired output (Boerlin and Denéve, 2011; Boerlin et al., 2013). By postulating that each neuron fires to reduce the error in the network's output, it was demonstrated that linear computations can be performed by networks of integrate-and-fire neurons that communicate through instantaneous synapses. This left open, however, the possibility that realistic networks, with conductance-based neurons with subthreshold nonlinearity and the slower timescales of biophysical synapses, may not fit into this framework. Here, we show how the spike-based approach can be extended to biophysically plausible networks. We then show that our network reproduces a number of key features of cortical networks including irregular and Poisson-like spike times and a tight balance between excitation and inhibition. Lastly, we discuss how the behavior of our model scales with network size or with the number of neurons "recorded" from a larger computing network. These results significantly increase the biological plausibility of the spike-based approach to network computation. We derive a network of neurons with standard spike-generating currents and synapses with realistic timescales that computes based upon the principle that the precise timing of each spike is important for the computation. We then show that our network reproduces a number of key features of cortical networks including irregular, Poisson-like spike times, and a tight balance between excitation and inhibition. These results significantly increase the biological plausibility of the spike-based approach to network computation, and uncover how several components of biological networks may work together to efficiently carry out computation. Copyright © 2015 the authors 0270-6474/15/3510112-23$15.00/0.

Salient object detection based on multi-scale contrast.

PubMed

Wang, Hai; Dai, Lei; Cai, Yingfeng; Sun, Xiaoqiang; Chen, Long

2018-05-01

Due to the development of deep learning networks, a salient object detection based on deep learning networks, which are used to extract the features, has made a great breakthrough compared to the traditional methods. At present, the salient object detection mainly relies on very deep convolutional network, which is used to extract the features. In deep learning networks, an dramatic increase of network depth may cause more training errors instead. In this paper, we use the residual network to increase network depth and to mitigate the errors caused by depth increase simultaneously. Inspired by image simplification, we use color and texture features to obtain simplified image with multiple scales by means of region assimilation on the basis of super-pixels in order to reduce the complexity of images and to improve the accuracy of salient target detection. We refine the feature on pixel level by the multi-scale feature correction method to avoid the feature error when the image is simplified at the above-mentioned region level. The final full connection layer not only integrates features of multi-scale and multi-level but also works as classifier of salient targets. The experimental results show that proposed model achieves better results than other salient object detection models based on original deep learning networks. Copyright © 2018 Elsevier Ltd. All rights reserved.

Decoding of finger trajectory from ECoG using deep learning

NASA Astrophysics Data System (ADS)

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Objective. Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. Approach. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. Main results. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. Significance. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals.

PubMed

Tsiouris, Κostas Μ; Pezoulas, Vasileios C; Zervakis, Michalis; Konitsiotis, Spiros; Koutsouris, Dimitrios D; Fotiadis, Dimitrios I

2018-05-17

The electroencephalogram (EEG) is the most prominent means to study epilepsy and capture changes in electrical brain activity that could declare an imminent seizure. In this work, Long Short-Term Memory (LSTM) networks are introduced in epileptic seizure prediction using EEG signals, expanding the use of deep learning algorithms with convolutional neural networks (CNN). A pre-analysis is initially performed to find the optimal architecture of the LSTM network by testing several modules and layers of memory units. Based on these results, a two-layer LSTM network is selected to evaluate seizure prediction performance using four different lengths of preictal windows, ranging from 15 min to 2 h. The LSTM model exploits a wide range of features extracted prior to classification, including time and frequency domain features, between EEG channels cross-correlation and graph theoretic features. The evaluation is performed using long-term EEG recordings from the open CHB-MIT Scalp EEG database, suggest that the proposed methodology is able to predict all 185 seizures, providing high rates of seizure prediction sensitivity and low false prediction rates (FPR) of 0.11-0.02 false alarms per hour, depending on the duration of the preictal window. The proposed LSTM-based methodology delivers a significant increase in seizure prediction performance compared to both traditional machine learning techniques and convolutional neural networks that have been previously evaluated in the literature. Copyright © 2018 Elsevier Ltd. All rights reserved.

Robust visual tracking via multiscale deep sparse networks

NASA Astrophysics Data System (ADS)

Wang, Xin; Hou, Zhiqiang; Yu, Wangsheng; Xue, Yang; Jin, Zefenfen; Dai, Bo

2017-04-01

In visual tracking, deep learning with offline pretraining can extract more intrinsic and robust features. It has significant success solving the tracking drift in a complicated environment. However, offline pretraining requires numerous auxiliary training datasets and is considerably time-consuming for tracking tasks. To solve these problems, a multiscale sparse networks-based tracker (MSNT) under the particle filter framework is proposed. Based on the stacked sparse autoencoders and rectifier linear unit, the tracker has a flexible and adjustable architecture without the offline pretraining process and exploits the robust and powerful features effectively only through online training of limited labeled data. Meanwhile, the tracker builds four deep sparse networks of different scales, according to the target's profile type. During tracking, the tracker selects the matched tracking network adaptively in accordance with the initial target's profile type. It preserves the inherent structural information more efficiently than the single-scale networks. Additionally, a corresponding update strategy is proposed to improve the robustness of the tracker. Extensive experimental results on a large scale benchmark dataset show that the proposed method performs favorably against state-of-the-art methods in challenging environments.

Real-time object-to-features vectorisation via Siamese neural networks

NASA Astrophysics Data System (ADS)

Fedorenko, Fedor; Usilin, Sergey

2017-03-01

Object-to-features vectorisation is a hard problem to solve for objects that can be hard to distinguish. Siamese and Triplet neural networks are one of the more recent tools used for such task. However, most networks used are very deep networks that prove to be hard to compute in the Internet of Things setting. In this paper, a computationally efficient neural network is proposed for real-time object-to-features vectorisation into a Euclidean metric space. We use L2 distance to reflect feature vector similarity during both training and testing. In this way, feature vectors we develop can be easily classified using K-Nearest Neighbours classifier. Such approach can be used to train networks to vectorise such "problematic" objects like images of human faces, keypoint image patches, like keypoints on Arctic maps and surrounding marine areas.

Design and evaluation of a peer network to support adherence to a web-based intervention for adolescents

PubMed Central

Ho, Joyce; Corden, Marya E.; Caccamo, Lauren; Tomasino, Kathryn Noth; Duffecy, Jenna; Begale, Mark; Mohr, David C.

2016-01-01

Background Depression during adolescence is common but can be prevented. Behavioral intervention technologies (BITs) designed to prevent depression in adolescence, especially standalone web-based interventions, have shown mixed outcomes, likely due to poor intervention adherence. BIT research involving adults has shown that the presence of coaches or peers promotes intervention use. Developmentally, adolescence is a time when peer-based social relationships take precedence. This study examines whether peer-networked support may promote adherence to BITs in this age group. Objective Adopting the framework of the Supportive Accountability model, which defines the types of human support and interactions required to maintain engagement and persistence with BITs, this paper presents a feasibility study of a peer-networked online intervention for depression prevention among adolescents. We described the development of the peer network, the evaluation of participant use of the peer networking features, and qualitative user feedback to inform continued BIT development. Method Two groups of adolescents (N = 13) participated in 10-week programs of the peer networked based online intervention. Adolescents had access to didactic lessons, CBT based mood management tools, and peer networking features. The peer networking features are integrated into the site by making use expectations explicit, allow network members to monitor the activities of others, and to supportively hold each other accountable for meeting use expectations. The study collected qualitative feedback from participants as well as usage of site features and tools. Results Participants logged in an average of 12.8 sessions over an average of 10.4 unique days during the 10-week program. On average, 66% of all use sessions occurred within the first 3 weeks of use. The number of “exchange comments”, that is, comments posted that were part of an exchange between two or more participants, was significantly positively correlated with mean time spent on site (r = 0.62, p = 0.032), use of the Activity Tracker (r = 0.70, p = 0.012) and Didactic Lesson (r = 0.73, p = 0.007). Qualitative interviews revealed that adolescents generally liked and were motivated by the peer networking features during the first weeks of the intervention when general site use by group members was high. However, the decrease of site use by group members during the subsequent weeks negatively affected participants’ desire to log on or engage with group members. Conclusions This pilot study highlights the potential that a BIT designed to harness the connection among a peer network, thereby promoting supportive accountability, may improve adolescent adherence to BITs for depression prevention. PMID:27722095

Link prediction based on local weighted paths for complex networks

NASA Astrophysics Data System (ADS)

Yao, Yabing; Zhang, Ruisheng; Yang, Fan; Yuan, Yongna; Hu, Rongjing; Zhao, Zhili

As a significant problem in complex networks, link prediction aims to find the missing and future links between two unconnected nodes by estimating the existence likelihood of potential links. It plays an important role in understanding the evolution mechanism of networks and has broad applications in practice. In order to improve prediction performance, a variety of structural similarity-based methods that rely on different topological features have been put forward. As one topological feature, the path information between node pairs is utilized to calculate the node similarity. However, many path-dependent methods neglect the different contributions of paths for a pair of nodes. In this paper, a local weighted path (LWP) index is proposed to differentiate the contributions between paths. The LWP index considers the effect of the link degrees of intermediate links and the connectivity influence of intermediate nodes on paths to quantify the path weight in the prediction procedure. The experimental results on 12 real-world networks show that the LWP index outperforms other seven prediction baselines.

Chinese Sentence Classification Based on Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Gu, Chengwei; Wu, Ming; Zhang, Chuang

2017-10-01

Sentence classification is one of the significant issues in Natural Language Processing (NLP). Feature extraction is often regarded as the key point for natural language processing. Traditional ways based on machine learning can not take high level features into consideration, such as Naive Bayesian Model. The neural network for sentence classification can make use of contextual information to achieve greater results in sentence classification tasks. In this paper, we focus on classifying Chinese sentences. And the most important is that we post a novel architecture of Convolutional Neural Network (CNN) to apply on Chinese sentence classification. In particular, most of the previous methods often use softmax classifier for prediction, we embed a linear support vector machine to substitute softmax in the deep neural network model, minimizing a margin-based loss to get a better result. And we use tanh as an activation function, instead of ReLU. The CNN model improve the result of Chinese sentence classification tasks. Experimental results on the Chinese news title database validate the effectiveness of our model.

Semantic image segmentation with fused CNN features

NASA Astrophysics Data System (ADS)

Geng, Hui-qiang; Zhang, Hua; Xue, Yan-bing; Zhou, Mian; Xu, Guang-ping; Gao, Zan

2017-09-01

Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network (CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field (CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.

Online Actions with Offline Impact: How Online Social Networks Influence Online and Offline User Behavior.

PubMed

Althoff, Tim; Jindal, Pranav; Leskovec, Jure

2017-02-01

Many of today's most widely used computing applications utilize social networking features and allow users to connect, follow each other, share content, and comment on others' posts. However, despite the widespread adoption of these features, there is little understanding of the consequences that social networking has on user retention, engagement, and online as well as offline behavior. Here, we study how social networks influence user behavior in a physical activity tracking application. We analyze 791 million online and offline actions of 6 million users over the course of 5 years, and show that social networking leads to a significant increase in users' online as well as offline activities. Specifically, we establish a causal effect of how social networks influence user behavior. We show that the creation of new social connections increases user online in-application activity by 30%, user retention by 17%, and user offline real-world physical activity by 7% (about 400 steps per day). By exploiting a natural experiment we distinguish the effect of social influence of new social connections from the simultaneous increase in user's motivation to use the app and take more steps. We show that social influence accounts for 55% of the observed changes in user behavior, while the remaining 45% can be explained by the user's increased motivation to use the app. Further, we show that subsequent, individual edge formations in the social network lead to significant increases in daily steps. These effects diminish with each additional edge and vary based on edge attributes and user demographics. Finally, we utilize these insights to develop a model that accurately predicts which users will be most influenced by the creation of new social network connections.

Online Actions with Offline Impact: How Online Social Networks Influence Online and Offline User Behavior

PubMed Central

Althoff, Tim; Jindal, Pranav; Leskovec, Jure

2017-01-01

Many of today’s most widely used computing applications utilize social networking features and allow users to connect, follow each other, share content, and comment on others’ posts. However, despite the widespread adoption of these features, there is little understanding of the consequences that social networking has on user retention, engagement, and online as well as offline behavior. Here, we study how social networks influence user behavior in a physical activity tracking application. We analyze 791 million online and offline actions of 6 million users over the course of 5 years, and show that social networking leads to a significant increase in users’ online as well as offline activities. Specifically, we establish a causal effect of how social networks influence user behavior. We show that the creation of new social connections increases user online in-application activity by 30%, user retention by 17%, and user offline real-world physical activity by 7% (about 400 steps per day). By exploiting a natural experiment we distinguish the effect of social influence of new social connections from the simultaneous increase in user’s motivation to use the app and take more steps. We show that social influence accounts for 55% of the observed changes in user behavior, while the remaining 45% can be explained by the user’s increased motivation to use the app. Further, we show that subsequent, individual edge formations in the social network lead to significant increases in daily steps. These effects diminish with each additional edge and vary based on edge attributes and user demographics. Finally, we utilize these insights to develop a model that accurately predicts which users will be most influenced by the creation of new social network connections. PMID:28345078

VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images.

PubMed

Chen, Hao; Dou, Qi; Yu, Lequan; Qin, Jing; Heng, Pheng-Ann

2018-04-15

Segmentation of key brain tissues from 3D medical images is of great significance for brain disease diagnosis, progression assessment and monitoring of neurologic conditions. While manual segmentation is time-consuming, laborious, and subjective, automated segmentation is quite challenging due to the complicated anatomical environment of brain and the large variations of brain tissues. We propose a novel voxelwise residual network (VoxResNet) with a set of effective training schemes to cope with this challenging problem. The main merit of residual learning is that it can alleviate the degradation problem when training a deep network so that the performance gains achieved by increasing the network depth can be fully leveraged. With this technique, our VoxResNet is built with 25 layers, and hence can generate more representative features to deal with the large variations of brain tissues than its rivals using hand-crafted features or shallower networks. In order to effectively train such a deep network with limited training data for brain segmentation, we seamlessly integrate multi-modality and multi-level contextual information into our network, so that the complementary information of different modalities can be harnessed and features of different scales can be exploited. Furthermore, an auto-context version of the VoxResNet is proposed by combining the low-level image appearance features, implicit shape information, and high-level context together for further improving the segmentation performance. Extensive experiments on the well-known benchmark (i.e., MRBrainS) of brain segmentation from 3D magnetic resonance (MR) images corroborated the efficacy of the proposed VoxResNet. Our method achieved the first place in the challenge out of 37 competitors including several state-of-the-art brain segmentation methods. Our method is inherently general and can be readily applied as a powerful tool to many brain-related studies, where accurate segmentation of brain structures is critical. Copyright © 2017 Elsevier Inc. All rights reserved.

Friend suggestion in social network based on user log

NASA Astrophysics Data System (ADS)

Kaviya, R.; Vanitha, M.; Sumaiya Thaseen, I.; Mangaiyarkarasi, R.

2017-11-01

Simple friend recommendation algorithms such as similarity, popularity and social aspects is the basic requirement to be explored to methodically form high-performance social friend recommendation. Suggestion of friends is followed. No tags of character were followed. In the proposed system, we use an algorithm for network correlation-based social friend recommendation (NC-based SFR).It includes user activities like where one lives and works. A new friend recommendation method, based on network correlation, by considering the effect of different social roles. To model the correlation between different networks, we develop a method that aligns these networks through important feature selection. We consider by preserving the network structure for a more better recommendations so that it significantly improves the accuracy for better friend-recommendation.

Identifying Patients with Atrioventricular Septal Defect in Down Syndrome Populations by Using Self-Normalizing Neural Networks and Feature Selection.

PubMed

Pan, Xiaoyong; Hu, Xiaohua; Zhang, Yu Hang; Feng, Kaiyan; Wang, Shao Peng; Chen, Lei; Huang, Tao; Cai, Yu Dong

2018-04-12

Atrioventricular septal defect (AVSD) is a clinically significant subtype of congenital heart disease (CHD) that severely influences the health of babies during birth and is associated with Down syndrome (DS). Thus, exploring the differences in functional genes in DS samples with and without AVSD is a critical way to investigate the complex association between AVSD and DS. In this study, we present a computational method to distinguish DS patients with AVSD from those without AVSD using the newly proposed self-normalizing neural network (SNN). First, each patient was encoded by using the copy number of probes on chromosome 21. The encoded features were ranked by the reliable Monte Carlo feature selection (MCFS) method to obtain a ranked feature list. Based on this feature list, we used a two-stage incremental feature selection to construct two series of feature subsets and applied SNNs to build classifiers to identify optimal features. Results show that 2737 optimal features were obtained, and the corresponding optimal SNN classifier constructed on optimal features yielded a Matthew's correlation coefficient (MCC) value of 0.748. For comparison, random forest was also used to build classifiers and uncover optimal features. This method received an optimal MCC value of 0.582 when top 132 features were utilized. Finally, we analyzed some key features derived from the optimal features in SNNs found in literature support to further reveal their essential roles.

The influence of passenger flow on the topology characteristics of urban rail transit networks

NASA Astrophysics Data System (ADS)

Hu, Yingyue; Chen, Feng; Chen, Peiwen; Tan, Yurong

2017-05-01

Current researches on the network characteristics of metro networks are generally carried out on topology networks without passenger flows running on it, thus more complex features of the networks with ridership loaded on it cannot be captured. In this study, we incorporated the load of metro networks, passenger volume, into the exploration of network features. Thus, the network can be examined in the context of operation, which is the ultimate purpose of the existence of a metro network. To this end, section load was selected as an edge weight to demonstrate the influence of ridership on the network, and a weighted calculation method for complex network indicators and robustness were proposed to capture the unique behaviors of a metro network with passengers flowing in it. The proposed method was applied on Beijing Subway. Firstly, the passenger volume in terms of daily origin and destination matrix was extracted from exhausted transit smart card data. Using the established approach and the matrix as weighting, common indicators of complex network including clustering coefficient, betweenness and degree were calculated, and network robustness were evaluated under potential attacks. The results were further compared to that of unweighted networks, and it suggests indicators of the network with consideration of passenger volumes differ from that without ridership to some extent, and networks tend to be more vulnerable than that without load on it. The significance sequence for the stations can be changed. By introducing passenger flow weighting, actual operation status of the network can be reflected more accurately. It is beneficial to determine the crucial stations and make precautionary measures for the entire network’s operation security.

Maximum entropy methods for extracting the learned features of deep neural networks.

PubMed

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

Prediction of missing links and reconstruction of complex networks

NASA Astrophysics Data System (ADS)

Zhang, Cheng-Jun; Zeng, An

2016-04-01

Predicting missing links in complex networks is of great significance from both theoretical and practical point of view, which not only helps us understand the evolution of real systems but also relates to many applications in social, biological and online systems. In this paper, we study the features of different simple link prediction methods, revealing that they may lead to the distortion of networks’ structural and dynamical properties. Moreover, we find that high prediction accuracy is not definitely corresponding to a high performance in preserving the network properties when using link prediction methods to reconstruct networks. Our work highlights the importance of considering the feedback effect of the link prediction methods on network properties when designing the algorithms.

Firing rate dynamics in recurrent spiking neural networks with intrinsic and network heterogeneity.

PubMed

Ly, Cheng

2015-12-01

Heterogeneity of neural attributes has recently gained a lot of attention and is increasing recognized as a crucial feature in neural processing. Despite its importance, this physiological feature has traditionally been neglected in theoretical studies of cortical neural networks. Thus, there is still a lot unknown about the consequences of cellular and circuit heterogeneity in spiking neural networks. In particular, combining network or synaptic heterogeneity and intrinsic heterogeneity has yet to be considered systematically despite the fact that both are known to exist and likely have significant roles in neural network dynamics. In a canonical recurrent spiking neural network model, we study how these two forms of heterogeneity lead to different distributions of excitatory firing rates. To analytically characterize how these types of heterogeneities affect the network, we employ a dimension reduction method that relies on a combination of Monte Carlo simulations and probability density function equations. We find that the relationship between intrinsic and network heterogeneity has a strong effect on the overall level of heterogeneity of the firing rates. Specifically, this relationship can lead to amplification or attenuation of firing rate heterogeneity, and these effects depend on whether the recurrent network is firing asynchronously or rhythmically firing. These observations are captured with the aforementioned reduction method, and furthermore simpler analytic descriptions based on this dimension reduction method are developed. The final analytic descriptions provide compact and descriptive formulas for how the relationship between intrinsic and network heterogeneity determines the firing rate heterogeneity dynamics in various settings.

Segregated Systems of Human Brain Networks.

PubMed

Wig, Gagan S

2017-12-01

The organization of the brain network enables its function. Evaluation of this organization has revealed that large-scale brain networks consist of multiple segregated subnetworks of interacting brain areas. Descriptions of resting-state network architecture have provided clues for understanding the functional significance of these segregated subnetworks, many of which correspond to distinct brain systems. The present report synthesizes accumulating evidence to reveal how maintaining segregated brain systems renders the human brain network functionally specialized, adaptable to task demands, and largely resilient following focal brain damage. The organizational properties that support system segregation are harmonious with the properties that promote integration across the network, but confer unique and important features to the brain network that are central to its function and behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

Target recognition based on convolutional neural network

NASA Astrophysics Data System (ADS)

Wang, Liqiang; Wang, Xin; Xi, Fubiao; Dong, Jian

2017-11-01

One of the important part of object target recognition is the feature extraction, which can be classified into feature extraction and automatic feature extraction. The traditional neural network is one of the automatic feature extraction methods, while it causes high possibility of over-fitting due to the global connection. The deep learning algorithm used in this paper is a hierarchical automatic feature extraction method, trained with the layer-by-layer convolutional neural network (CNN), which can extract the features from lower layers to higher layers. The features are more discriminative and it is beneficial to the object target recognition.

A new method for enhancer prediction based on deep belief network.

PubMed

Bu, Hongda; Gan, Yanglan; Wang, Yang; Zhou, Shuigeng; Guan, Jihong

2017-10-16

Studies have shown that enhancers are significant regulatory elements to play crucial roles in gene expression regulation. Since enhancers are unrelated to the orientation and distance to their target genes, it is a challenging mission for scholars and researchers to accurately predicting distal enhancers. In the past years, with the high-throughout ChiP-seq technologies development, several computational techniques emerge to predict enhancers using epigenetic or genomic features. Nevertheless, the inconsistency of computational models across different cell-lines and the unsatisfactory prediction performance call for further research in this area. Here, we propose a new Deep Belief Network (DBN) based computational method for enhancer prediction, which is called EnhancerDBN. This method combines diverse features, composed of DNA sequence compositional features, DNA methylation and histone modifications. Our computational results indicate that 1) EnhancerDBN outperforms 13 existing methods in prediction, and 2) GC content and DNA methylation can serve as relevant features for enhancer prediction. Deep learning is effective in boosting the performance of enhancer prediction.

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion.

PubMed

Zafar, Raheel; Dass, Sarat C; Malik, Aamir Saeed

2017-01-01

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain-computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method.

Sex-Specific Patterns of Aberrant Brain Function in First-Episode Treatment-Naive Patients with Schizophrenia.

PubMed

Lei, Wei; Li, Mingli; Deng, Wei; Zhou, Yi; Ma, Xiaohong; Wang, Qiang; Guo, Wanjun; Li, Yinfei; Jiang, Lijun; Han, Yuanyuan; Huang, Chaohua; Hu, Xun; Li, Tao

2015-07-16

Male and female patients with schizophrenia show significant differences in a number of important clinical features, yet the neural substrates of these differences are still poorly understood. Here we explored the sex differences in the brain functional aberrations in 124 treatment-naïve patients with first-episode schizophrenia (61 males), compared with 102 age-matched healthy controls (50 males). Maps of degree centrality (DC) and amplitude of low-frequency fluctuations (ALFF) were constructed using resting-state functional magnetic resonance imaging data and compared between groups. We found that: (1) Selective DC reduction was observed in the right putamen (Put_R) in male patients and the left middle frontal gyrus (MFG) in female patients; (2) Functional connectivity analysis (using Put_R and MFG as seeds) found that male and female patients have disturbed functional integration in two separate networks, i.e., the sensorimotor network and the default mode network; (3) Significant ALFF alterations were also observed in these two networks in both genders; (4) Sex specific brain functional alterations were associated with various symptoms in patients. These results suggested that sex-specific patterns of functional aberration existed in schizophrenia, and these patterns were associated with the clinical features both in male and female patients.

MUFOLD-SS: New deep inception-inside-inception networks for protein secondary structure prediction.

PubMed

Fang, Chao; Shang, Yi; Xu, Dong

2018-05-01

Protein secondary structure prediction can provide important information for protein 3D structure prediction and protein functions. Deep learning offers a new opportunity to significantly improve prediction accuracy. In this article, a new deep neural network architecture, named the Deep inception-inside-inception (Deep3I) network, is proposed for protein secondary structure prediction and implemented as a software tool MUFOLD-SS. The input to MUFOLD-SS is a carefully designed feature matrix corresponding to the primary amino acid sequence of a protein, which consists of a rich set of information derived from individual amino acid, as well as the context of the protein sequence. Specifically, the feature matrix is a composition of physio-chemical properties of amino acids, PSI-BLAST profile, and HHBlits profile. MUFOLD-SS is composed of a sequence of nested inception modules and maps the input matrix to either eight states or three states of secondary structures. The architecture of MUFOLD-SS enables effective processing of local and global interactions between amino acids in making accurate prediction. In extensive experiments on multiple datasets, MUFOLD-SS outperformed the best existing methods and other deep neural networks significantly. MUFold-SS can be downloaded from http://dslsrv8.cs.missouri.edu/~cf797/MUFoldSS/download.html. © 2018 Wiley Periodicals, Inc.

Network anomaly detection system with optimized DS evidence theory.

PubMed

Liu, Yuan; Wang, Xiaofeng; Liu, Kaiyu

2014-01-01

Network anomaly detection has been focused on by more people with the fast development of computer network. Some researchers utilized fusion method and DS evidence theory to do network anomaly detection but with low performance, and they did not consider features of network-complicated and varied. To achieve high detection rate, we present a novel network anomaly detection system with optimized Dempster-Shafer evidence theory (ODS) and regression basic probability assignment (RBPA) function. In this model, we add weights for each sensor to optimize DS evidence theory according to its previous predict accuracy. And RBPA employs sensor's regression ability to address complex network. By four kinds of experiments, we find that our novel network anomaly detection model has a better detection rate, and RBPA as well as ODS optimization methods can improve system performance significantly.

Automatic brain MR image denoising based on texture feature-based artificial neural networks.

PubMed

Chang, Yu-Ning; Chang, Herng-Hua

2015-01-01

Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.

Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks.

PubMed

Yu, Lequan; Chen, Hao; Dou, Qi; Qin, Jing; Heng, Pheng-Ann

2017-04-01

Automated melanoma recognition in dermoscopy images is a very challenging task due to the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of many artifacts in the image. In order to meet these challenges, we propose a novel method for melanoma recognition by leveraging very deep convolutional neural networks (CNNs). Compared with existing methods employing either low-level hand-crafted features or CNNs with shallower architectures, our substantially deeper networks (more than 50 layers) can acquire richer and more discriminative features for more accurate recognition. To take full advantage of very deep networks, we propose a set of schemes to ensure effective training and learning under limited training data. First, we apply the residual learning to cope with the degradation and overfitting problems when a network goes deeper. This technique can ensure that our networks benefit from the performance gains achieved by increasing network depth. Then, we construct a fully convolutional residual network (FCRN) for accurate skin lesion segmentation, and further enhance its capability by incorporating a multi-scale contextual information integration scheme. Finally, we seamlessly integrate the proposed FCRN (for segmentation) and other very deep residual networks (for classification) to form a two-stage framework. This framework enables the classification network to extract more representative and specific features based on segmented results instead of the whole dermoscopy images, further alleviating the insufficiency of training data. The proposed framework is extensively evaluated on ISBI 2016 Skin Lesion Analysis Towards Melanoma Detection Challenge dataset. Experimental results demonstrate the significant performance gains of the proposed framework, ranking the first in classification and the second in segmentation among 25 teams and 28 teams, respectively. This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data.

Classification of cardiac patient states using artificial neural networks

PubMed Central

Kannathal, N; Acharya, U Rajendra; Lim, Choo Min; Sadasivan, PK; Krishnan, SM

2003-01-01

Electrocardiogram (ECG) is a nonstationary signal; therefore, the disease indicators may occur at random in the time scale. This may require the patient be kept under observation for long intervals in the intensive care unit of hospitals for accurate diagnosis. The present study examined the classification of the states of patients with certain diseases in the intensive care unit using their ECG and an Artificial Neural Networks (ANN) classification system. The states were classified into normal, abnormal and life threatening. Seven significant features extracted from the ECG were fed as input parameters to the ANN for classification. Three neural network techniques, namely, back propagation, self-organizing maps and radial basis functions, were used for classification of the patient states. The ANN classifier in this case was observed to be correct in approximately 99% of the test cases. This result was further improved by taking 13 features of the ECG as input for the ANN classifier. PMID:19649222

Learning Efficient Spatial-Temporal Gait Features with Deep Learning for Human Identification.

PubMed

Liu, Wu; Zhang, Cheng; Ma, Huadong; Li, Shuangqun

2018-02-06

The integration of the latest breakthroughs in bioinformatics technology from one side and artificial intelligence from another side, enables remarkable advances in the fields of intelligent security guard computational biology, healthcare, and so on. Among them, biometrics based automatic human identification is one of the most fundamental and significant research topic. Human gait, which is a biometric features with the unique capability, has gained significant attentions as the remarkable characteristics of remote accessed, robust and security in the biometrics based human identification. However, the existed methods cannot well handle the indistinctive inter-class differences and large intra-class variations of human gait in real-world situation. In this paper, we have developed an efficient spatial-temporal gait features with deep learning for human identification. First of all, we proposed a gait energy image (GEI) based Siamese neural network to automatically extract robust and discriminative spatial gait features for human identification. Furthermore, we exploit the deep 3-dimensional convolutional networks to learn the human gait convolutional 3D (C3D) as the temporal gait features. Finally, the GEI and C3D gait features are embedded into the null space by the Null Foley-Sammon Transform (NFST). In the new space, the spatial-temporal features are sufficiently combined with distance metric learning to drive the similarity metric to be small for pairs of gait from the same person, and large for pairs from different persons. Consequently, the experiments on the world's largest gait database show our framework impressively outperforms state-of-the-art methods.

A Risk Stratification Model for Lung Cancer Based on Gene Coexpression Network and Deep Learning

PubMed Central

2018-01-01

Risk stratification model for lung cancer with gene expression profile is of great interest. Instead of previous models based on individual prognostic genes, we aimed to develop a novel system-level risk stratification model for lung adenocarcinoma based on gene coexpression network. Using multiple microarray, gene coexpression network analysis was performed to identify survival-related networks. A deep learning based risk stratification model was constructed with representative genes of these networks. The model was validated in two test sets. Survival analysis was performed using the output of the model to evaluate whether it could predict patients' survival independent of clinicopathological variables. Five networks were significantly associated with patients' survival. Considering prognostic significance and representativeness, genes of the two survival-related networks were selected for input of the model. The output of the model was significantly associated with patients' survival in two test sets and training set (p < 0.00001, p < 0.0001 and p = 0.02 for training and test sets 1 and 2, resp.). In multivariate analyses, the model was associated with patients' prognosis independent of other clinicopathological features. Our study presents a new perspective on incorporating gene coexpression networks into the gene expression signature and clinical application of deep learning in genomic data science for prognosis prediction. PMID:29581968

Some new classification methods for hyperspectral remote sensing

NASA Astrophysics Data System (ADS)

Du, Pei-jun; Chen, Yun-hao; Jones, Simon; Ferwerda, Jelle G.; Chen, Zhi-jun; Zhang, Hua-peng; Tan, Kun; Yin, Zuo-xia

2006-10-01

Hyperspectral Remote Sensing (HRS) is one of the most significant recent achievements of Earth Observation Technology. Classification is the most commonly employed processing methodology. In this paper three new hyperspectral RS image classification methods are analyzed. These methods are: Object-oriented FIRS image classification, HRS image classification based on information fusion and HSRS image classification by Back Propagation Neural Network (BPNN). OMIS FIRS image is used as the example data. Object-oriented techniques have gained popularity for RS image classification in recent years. In such method, image segmentation is used to extract the regions from the pixel information based on homogeneity criteria at first, and spectral parameters like mean vector, texture, NDVI and spatial/shape parameters like aspect ratio, convexity, solidity, roundness and orientation for each region are calculated, finally classification of the image using the region feature vectors and also using suitable classifiers such as artificial neural network (ANN). It proves that object-oriented methods can improve classification accuracy since they utilize information and features both from the point and the neighborhood, and the processing unit is a polygon (in which all pixels are homogeneous and belong to the class). HRS image classification based on information fusion, divides all bands of the image into different groups initially, and extracts features from every group according to the properties of each group. Three levels of information fusion: data level fusion, feature level fusion and decision level fusion are used to HRS image classification. Artificial Neural Network (ANN) can perform well in RS image classification. In order to promote the advances of ANN used for HIRS image classification, Back Propagation Neural Network (BPNN), the most commonly used neural network, is used to HRS image classification.

Hadoop neural network for parallel and distributed feature selection.

PubMed

Hodge, Victoria J; O'Keefe, Simon; Austin, Jim

2016-06-01

In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

NASA Integrated Space Communications Network

NASA Technical Reports Server (NTRS)

Tai, Wallace; Wright, Nate; Prior, Mike; Bhasin, Kul

2012-01-01

The NASA Integrated Network for Space Communications and Navigation (SCaN) has been in the definition phase since 2010. It is intended to integrate NASA s three existing network elements, i.e., the Space Network, Near Earth Network, and Deep Space Network, into a single network. In addition to the technical merits, the primary purpose of the Integrated Network is to achieve a level of operating cost efficiency significantly higher than it is today. Salient features of the Integrated Network include (a) a central system element that performs service management functions and user mission interfaces for service requests; (b) a set of common service execution equipment deployed at the all stations that provides return, forward, and radiometric data processing and delivery capabilities; (c) the network monitor and control operations for the entire integrated network are conducted remotely and centrally at a prime-shift site and rotating among three sites globally (a follow-the-sun approach); (d) the common network monitor and control software deployed at all three network elements that supports the follow-the-sun operations.

Hypotheses generation as supervised link discovery with automated class labeling on large-scale biomedical concept networks

PubMed Central

2012-01-01

Computational approaches to generate hypotheses from biomedical literature have been studied intensively in recent years. Nevertheless, it still remains a challenge to automatically discover novel, cross-silo biomedical hypotheses from large-scale literature repositories. In order to address this challenge, we first model a biomedical literature repository as a comprehensive network of biomedical concepts and formulate hypotheses generation as a process of link discovery on the concept network. We extract the relevant information from the biomedical literature corpus and generate a concept network and concept-author map on a cluster using Map-Reduce frame-work. We extract a set of heterogeneous features such as random walk based features, neighborhood features and common author features. The potential number of links to consider for the possibility of link discovery is large in our concept network and to address the scalability problem, the features from a concept network are extracted using a cluster with Map-Reduce framework. We further model link discovery as a classification problem carried out on a training data set automatically extracted from two network snapshots taken in two consecutive time duration. A set of heterogeneous features, which cover both topological and semantic features derived from the concept network, have been studied with respect to their impacts on the accuracy of the proposed supervised link discovery process. A case study of hypotheses generation based on the proposed method has been presented in the paper. PMID:22759614

Diagnosing Autism Spectrum Disorder from Brain Resting-State Functional Connectivity Patterns Using a Deep Neural Network with a Novel Feature Selection Method

PubMed Central

Guo, Xinyu; Dominick, Kelli C.; Minai, Ali A.; Li, Hailong; Erickson, Craig A.; Lu, Long J.

2017-01-01

The whole-brain functional connectivity (FC) pattern obtained from resting-state functional magnetic resonance imaging data are commonly applied to study neuropsychiatric conditions such as autism spectrum disorder (ASD) by using different machine learning models. Recent studies indicate that both hyper- and hypo- aberrant ASD-associated FCs were widely distributed throughout the entire brain rather than only in some specific brain regions. Deep neural networks (DNN) with multiple hidden layers have shown the ability to systematically extract lower-to-higher level information from high dimensional data across a series of neural hidden layers, significantly improving classification accuracy for such data. In this study, a DNN with a novel feature selection method (DNN-FS) is developed for the high dimensional whole-brain resting-state FC pattern classification of ASD patients vs. typical development (TD) controls. The feature selection method is able to help the DNN generate low dimensional high-quality representations of the whole-brain FC patterns by selecting features with high discriminating power from multiple trained sparse auto-encoders. For the comparison, a DNN without the feature selection method (DNN-woFS) is developed, and both of them are tested with different architectures (i.e., with different numbers of hidden layers/nodes). Results show that the best classification accuracy of 86.36% is generated by the DNN-FS approach with 3 hidden layers and 150 hidden nodes (3/150). Remarkably, DNN-FS outperforms DNN-woFS for all architectures studied. The most significant accuracy improvement was 9.09% with the 3/150 architecture. The method also outperforms other feature selection methods, e.g., two sample t-test and elastic net. In addition to improving the classification accuracy, a Fisher's score-based biomarker identification method based on the DNN is also developed, and used to identify 32 FCs related to ASD. These FCs come from or cross different pre-defined brain networks including the default-mode, cingulo-opercular, frontal-parietal, and cerebellum. Thirteen of them are statically significant between ASD and TD groups (two sample t-test p < 0.05) while 19 of them are not. The relationship between the statically significant FCs and the corresponding ASD behavior symptoms is discussed based on the literature and clinician's expert knowledge. Meanwhile, the potential reason of obtaining 19 FCs which are not statistically significant is also provided. PMID:28871217

Significantly enhanced creep resistance of low volume fraction in-situ TiBw/Ti6Al4V composites by architectured network reinforcements

PubMed Central

Wang, S.; Huang, L. J.; Geng, L.; Scarpa, F.; Jiao, Y.; Peng, H. X.

2017-01-01

We present a new class of TiBw/Ti6Al4V composites with a network reinforcement architecture that exhibits a significant creep resistance compared to monolithic Ti6Al4V alloys. Creep tests performed at temperatures between 773 K and 923 K and stress range of 100 MPa-300 MPa indicate both a significant improvement of the composites creep resistance due to the network architecture made by the TiB whiskers (TiBw), and a decrease of the steady-state creep rates by augmenting the local volume fractions of TiBw in the network region. The deformation behavior is driven by a diffusion-controlled dislocation climb process. Moreover, the activation energies of these composites are significantly higher than that of Ti6Al4V alloys, indicating a higher creep resistance. The increase of the activation energy can be attributed to the TiBw architecture that severely impedes the movements of dislocation and grain boundary sliding and provides a tailoring of the stress transfer. These micromechanical mechanisms lead to a remarkable improvement of the creep resistance of these networked TiBw/Ti6Al4V composites featuring the special networked architecture. PMID:28094350

Identification of Modules in Protein-Protein Interaction Networks

NASA Astrophysics Data System (ADS)

Erten, Sinan; Koyutürk, Mehmet

In biological systems, most processes are carried out through orchestration of multiple interacting molecules. These interactions are often abstracted using network models. A key feature of cellular networks is their modularity, which contributes significantly to the robustness, as well as adaptability of biological systems. Therefore, modularization of cellular networks is likely to be useful in obtaining insights into the working principles of cellular systems, as well as building tractable models of cellular organization and dynamics. A common, high-throughput source of data on molecular interactions is in the form of physical interactions between proteins, which are organized into protein-protein interaction (PPI) networks. This chapter provides an overview on identification and analysis of functional modules in PPI networks, which has been an active area of research in the last decade.

Network Anomaly Detection System with Optimized DS Evidence Theory

PubMed Central

Liu, Yuan; Wang, Xiaofeng; Liu, Kaiyu

2014-01-01

Network anomaly detection has been focused on by more people with the fast development of computer network. Some researchers utilized fusion method and DS evidence theory to do network anomaly detection but with low performance, and they did not consider features of network—complicated and varied. To achieve high detection rate, we present a novel network anomaly detection system with optimized Dempster-Shafer evidence theory (ODS) and regression basic probability assignment (RBPA) function. In this model, we add weights for each senor to optimize DS evidence theory according to its previous predict accuracy. And RBPA employs sensor's regression ability to address complex network. By four kinds of experiments, we find that our novel network anomaly detection model has a better detection rate, and RBPA as well as ODS optimization methods can improve system performance significantly. PMID:25254258

Damage Assessment for Disaster Relief Efforts in Urban Areas Using Optical Imagery and LiDAR Data

NASA Astrophysics Data System (ADS)

Bahr, Thomas

2014-05-01

Imagery combined with LiDAR data and LiDAR-derived products provides a significant source of geospatial data which is of use in disaster mitigation planning. Feature rich building inventories can be constructed from tools with 3D rooftop extraction capabilities, and two dimensional outputs such as DSMs and DTMs can be used to generate layers to support routing efforts in Spatial Analyst and Network Analyst workflows. This allows us to leverage imagery and LiDAR tools for disaster mitigation or other scenarios. Software such as ENVI, ENVI LiDAR, and ArcGIS® Spatial and Network Analyst can therefore be used in conjunction to help emergency responders route ground teams in support of disaster relief efforts. This is exemplified by a case study against the background of the magnitude 7.0 earthquake that struck Haiti's capital city of Port-au-Prince on January 12, 2010. Soon after, both LiDAR data and an 8-band WorldView-2 scene were collected to map the disaster zone. The WorldView-2 scene was orthorectified and atmospherically corrected in ENVI prior to use. ENVI LiDAR was used to extract the DSM, DTM, buildings, and debris from the LiDAR data point cloud. These datasets provide a foundation for the 2D portion of the analysis. As the data was acquired over an area of dense urbanization, the majority of ground surfaces are roads, and standing buildings and debris are actually largely separable on the basis of elevation classes. To extract the road network of Port-au-Prince, the LiDAR-based feature height information was fused with the WorldView-2 scene, using ENVI's object-based feature extraction approach. This road network was converted to a network dataset for further analysis by the ArcGIS Network Analyst. For the specific case of Haiti, the distribution of blue tarps, used as accommodations for refugees, provided a spectrally distinct target. Pure blue tarp pixel spectra were selected from the WorldView-2 scene and input as a reference into ENVI's Spectral Angle Mapper (SAM) classification routine, together with a water-shadow mask to prevent false positives. The resulting blue tarp shape file was input into the ArcGIS Point Density tool, a feature of the Spatial Analyst toolbox. The final distribution map shows the density of blue tarps in Port-au-Prince and can be used to roughly delineate camps of refugees. Analogous, a debris density map was generated after separating the debris elevation class. The combination of this debris density map with the road network allowed to construct an intact road network of Port-au-Prince within the ArcGIS Network Analyst. Moderate density debris was used as a cost-increase barrier feature of the network dataset, and high density debris was used as a total obstruction barrier feature. Based on this information, two hypothetical routing scenarios were analyzed. One involved routing a ground team between two different refugee concentration zones. For the other, potential helicopter landing zones were computed from the LiDAR-derived products and added as facility features to the Network Analyst. Routes from the helicopter landing zones to refugee concentration access points were solved using closest facility logic, again making use of the obstructed network.

Recurrent neural networks for breast lesion classification based on DCE-MRIs

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

Feature Biases in Early Word Learning: Network Distinctiveness Predicts Age of Acquisition

ERIC Educational Resources Information Center

Engelthaler, Tomas; Hills, Thomas T.

2017-01-01

Do properties of a word's features influence the order of its acquisition in early word learning? Combining the principles of mutual exclusivity and shape bias, the present work takes a network analysis approach to understanding how feature distinctiveness predicts the order of early word learning. Distance networks were built from nouns with edge…

Face recognition via Gabor and convolutional neural network

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wu, Menglu; Lu, Tao

2018-04-01

In recent years, the powerful feature learning and classification ability of convolutional neural network have attracted widely attention. Compared with the deep learning, the traditional machine learning algorithm has a good explanatory which deep learning does not have. Thus, In this paper, we propose a method to extract the feature of the traditional algorithm as the input of convolution neural network. In order to reduce the complexity of the network, the kernel function of Gabor wavelet is used to extract the feature from different position, frequency and direction of target image. It is sensitive to edge of image which can provide good direction and scale selection. The extraction of the image from eight directions on a scale are as the input of network that we proposed. The network have the advantage of weight sharing and local connection and texture feature of the input image can reduce the influence of facial expression, gesture and illumination. At the same time, we introduced a layer which combined the results of the pooling and convolution can extract deeper features. The training network used the open source caffe framework which is beneficial to feature extraction. The experiment results of the proposed method proved that the network structure effectively overcame the barrier of illumination and had a good robustness as well as more accurate and rapid than the traditional algorithm.

Social networking in online support groups for health: how online social networking benefits patients.

PubMed

Chung, Jae Eun

2014-01-01

An increasing number of online support groups (OSGs) have embraced the features of social networking. So far, little is known about how patients use and benefit from these features. By implementing the uses-and-gratifications framework, the author conducted an online survey with current users of OSGs to examine associations among motivation, use of specific features of OSG, and support outcomes. Findings suggest that OSG users make selective use of varied features depending on their needs, and that perceptions of receiving emotional and informational support are associated more with the use of some features than others. For example, those with strong motivation for social interaction use diverse features of OSG and make one-to-one connections with other users by friending. In contrast, those with strong motivation for information seeking limit their use primarily to discussion boards. Results also show that online social networking features, such as friending and sharing of personal stories on blogs, are helpful in satisfying the need for emotional support. The present study sheds light on online social networking features in the context of health-related OSGs and provides practical lessons on how to improve the capacity of OSGs to serve the needs of their users.

The application of neural networks to myoelectric signal analysis: a preliminary study.

PubMed

Kelly, M F; Parker, P A; Scott, R N

1990-03-01

Two neural network implementations are applied to myoelectric signal (MES) analysis tasks. The motivation behind this research is to explore more reliable methods of deriving control for multidegree of freedom arm prostheses. A discrete Hopfield network is used to calculate the time series parameters for a moving average MES model. It is demonstrated that the Hopfield network is capable of generating the same time series parameters as those produced by the conventional sequential least squares (SLS) algorithm. Furthermore, it can be extended to applications utilizing larger amounts of data, and possibly to higher order time series models, without significant degradation in computational efficiency. The second neural network implementation involves using a two-layer perceptron for classifying a single site MES based on two features, specifically the first time series parameter, and the signal power. Using these features, the perceptron is trained to distinguish between four separate arm functions. The two-dimensional decision boundaries used by the perceptron classifier are delineated. It is also demonstrated that the perceptron is able to rapidly compensate for variations when new data are incorporated into the training set. This adaptive quality suggests that perceptrons may provide a useful tool for future MES analysis.

Integrating epigenomic data and 3D genomic structure with a new measure of chromatin assortativity.

PubMed

Pancaldi, Vera; Carrillo-de-Santa-Pau, Enrique; Javierre, Biola Maria; Juan, David; Fraser, Peter; Spivakov, Mikhail; Valencia, Alfonso; Rico, Daniel

2016-07-08

Network analysis is a powerful way of modeling chromatin interactions. Assortativity is a network property used in social sciences to identify factors affecting how people establish social ties. We propose a new approach, using chromatin assortativity, to integrate the epigenomic landscape of a specific cell type with its chromatin interaction network and thus investigate which proteins or chromatin marks mediate genomic contacts. We use high-resolution promoter capture Hi-C and Hi-Cap data as well as ChIA-PET data from mouse embryonic stem cells to investigate promoter-centered chromatin interaction networks and calculate the presence of specific epigenomic features in the chromatin fragments constituting the nodes of the network. We estimate the association of these features with the topology of four chromatin interaction networks and identify features localized in connected areas of the network. Polycomb group proteins and associated histone marks are the features with the highest chromatin assortativity in promoter-centered networks. We then ask which features distinguish contacts amongst promoters from contacts between promoters and other genomic elements. We observe higher chromatin assortativity of the actively elongating form of RNA polymerase 2 (RNAPII) compared with inactive forms only in interactions between promoters and other elements. Contacts among promoters and between promoters and other elements have different characteristic epigenomic features. We identify a possible role for the elongating form of RNAPII in mediating interactions among promoters, enhancers, and transcribed gene bodies. Our approach facilitates the study of multiple genome-wide epigenomic profiles, considering network topology and allowing the comparison of chromatin interaction networks.

Scalable Lunar Surface Networks and Adaptive Orbit Access

NASA Technical Reports Server (NTRS)

Wang, Xudong

2015-01-01

Teranovi Technologies, Inc., has developed innovative network architecture, protocols, and algorithms for both lunar surface and orbit access networks. A key component of the overall architecture is a medium access control (MAC) protocol that includes a novel mechanism of overlaying time division multiple access (TDMA) and carrier sense multiple access with collision avoidance (CSMA/CA), ensuring scalable throughput and quality of service. The new MAC protocol is compatible with legacy Institute of Electrical and Electronics Engineers (IEEE) 802.11 networks. Advanced features include efficiency power management, adaptive channel width adjustment, and error control capability. A hybrid routing protocol combines the advantages of ad hoc on-demand distance vector (AODV) routing and disruption/delay-tolerant network (DTN) routing. Performance is significantly better than AODV or DTN and will be particularly effective for wireless networks with intermittent links, such as lunar and planetary surface networks and orbit access networks.

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

PubMed

Kang, Min-Joo; Kang, Je-Won

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security

PubMed Central

Kang, Min-Joo

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus. PMID:27271802

P³DB 3.0: From plant phosphorylation sites to protein networks.

PubMed

Yao, Qiuming; Ge, Huangyi; Wu, Shangquan; Zhang, Ning; Chen, Wei; Xu, Chunhui; Gao, Jianjiong; Thelen, Jay J; Xu, Dong

2014-01-01

In the past few years, the Plant Protein Phosphorylation Database (P(3)DB, http://p3db.org) has become one of the most significant in vivo data resources for studying plant phosphoproteomics. We have substantially updated P(3)DB with respect to format, new datasets and analytic tools. In the P(3)DB 3.0, there are altogether 47 923 phosphosites in 16 477 phosphoproteins curated across nine plant organisms from 32 studies, which have met our multiple quality standards for acquisition of in vivo phosphorylation site data. Centralized by these phosphorylation data, multiple related data and annotations are provided, including protein-protein interaction (PPI), gene ontology, protein tertiary structures, orthologous sequences, kinase/phosphatase classification and Kinase Client Assay (KiC Assay) data--all of which provides context for the phosphorylation event. In addition, P(3)DB 3.0 incorporates multiple network viewers for the above features, such as PPI network, kinase-substrate network, phosphatase-substrate network, and domain co-occurrence network to help study phosphorylation from a systems point of view. Furthermore, the new P(3)DB reflects a community-based design through which users can share datasets and automate data depository processes for publication purposes. Each of these new features supports the goal of making P(3)DB a comprehensive, systematic and interactive platform for phosphoproteomics research.

Probing the functions of long non-coding RNAs by exploiting the topology of global association and interaction network.

PubMed

Deng, Lei; Wu, Hongjie; Liu, Chuyao; Zhan, Weihua; Zhang, Jingpu

2018-06-01

Long non-coding RNAs (lncRNAs) are involved in many biological processes, such as immune response, development, differentiation and gene imprinting and are associated with diseases and cancers. But the functions of the vast majority of lncRNAs are still unknown. Predicting the biological functions of lncRNAs is one of the key challenges in the post-genomic era. In our work, We first build a global network including a lncRNA similarity network, a lncRNA-protein association network and a protein-protein interaction network according to the expressions and interactions, then extract the topological feature vectors of the global network. Using these features, we present an SVM-based machine learning approach, PLNRGO, to annotate human lncRNAs. In PLNRGO, we construct a training data set according to the proteins with GO annotations and train a binary classifier for each GO term. We assess the performance of PLNRGO on our manually annotated lncRNA benchmark and a protein-coding gene benchmark with known functional annotations. As a result, the performance of our method is significantly better than that of other state-of-the-art methods in terms of maximum F-measure and coverage. Copyright © 2018 Elsevier Ltd. All rights reserved.

On the Structure of Cortical Microcircuits Inferred from Small Sample Sizes.

PubMed

Vegué, Marina; Perin, Rodrigo; Roxin, Alex

2017-08-30

The structure in cortical microcircuits deviates from what would be expected in a purely random network, which has been seen as evidence of clustering. To address this issue, we sought to reproduce the nonrandom features of cortical circuits by considering several distinct classes of network topology, including clustered networks, networks with distance-dependent connectivity, and those with broad degree distributions. To our surprise, we found that all of these qualitatively distinct topologies could account equally well for all reported nonrandom features despite being easily distinguishable from one another at the network level. This apparent paradox was a consequence of estimating network properties given only small sample sizes. In other words, networks that differ markedly in their global structure can look quite similar locally. This makes inferring network structure from small sample sizes, a necessity given the technical difficulty inherent in simultaneous intracellular recordings, problematic. We found that a network statistic called the sample degree correlation (SDC) overcomes this difficulty. The SDC depends only on parameters that can be estimated reliably given small sample sizes and is an accurate fingerprint of every topological family. We applied the SDC criterion to data from rat visual and somatosensory cortex and discovered that the connectivity was not consistent with any of these main topological classes. However, we were able to fit the experimental data with a more general network class, of which all previous topologies were special cases. The resulting network topology could be interpreted as a combination of physical spatial dependence and nonspatial, hierarchical clustering. SIGNIFICANCE STATEMENT The connectivity of cortical microcircuits exhibits features that are inconsistent with a simple random network. Here, we show that several classes of network models can account for this nonrandom structure despite qualitative differences in their global properties. This apparent paradox is a consequence of the small numbers of simultaneously recorded neurons in experiment: when inferred via small sample sizes, many networks may be indistinguishable despite being globally distinct. We develop a connectivity measure that successfully classifies networks even when estimated locally with a few neurons at a time. We show that data from rat cortex is consistent with a network in which the likelihood of a connection between neurons depends on spatial distance and on nonspatial, asymmetric clustering. Copyright © 2017 the authors 0270-6474/17/378498-13$15.00/0.

Modeling of the ground-to-SSFMB link networking features using SPW

NASA Technical Reports Server (NTRS)

Watson, John C.

1993-01-01

This report describes the modeling and simulation of the networking features of the ground-to-Space Station Freedom manned base (SSFMB) link using COMDISCO signal processing work-system (SPW). The networking features modeled include the implementation of Consultative Committee for Space Data Systems (CCSDS) protocols in the multiplexing of digitized audio and core data into virtual channel data units (VCDU's) in the control center complex and the demultiplexing of VCDU's in the onboard baseband signal processor. The emphasis of this work has been placed on techniques for modeling the CCSDS networking features using SPW. The objectives for developing the SPW models are to test the suitability of SPW for modeling networking features and to develop SPW simulation models of the control center complex and space station baseband signal processor for use in end-to-end testing of the ground-to-SSFMB S-band single access forward (SSAF) link.

Biomorphic networks: approach to invariant feature extraction and segmentation for ATR

NASA Astrophysics Data System (ADS)

Baek, Andrew; Farhat, Nabil H.

1998-10-01

Invariant features in two dimensional binary images are extracted in a single layer network of locally coupled spiking (pulsating) model neurons with prescribed synapto-dendritic response. The feature vector for an image is represented as invariant structure in the aggregate histogram of interspike intervals obtained by computing time intervals between successive spikes produced from each neuron over a given period of time and combining such intervals from all neurons in the network into a histogram. Simulation results show that the feature vectors are more pattern-specific and invariant under translation, rotation, and change in scale or intensity than achieved in earlier work. We also describe an application of such networks to segmentation of line (edge-enhanced or silhouette) images. The biomorphic spiking network's capabilities in segmentation and invariant feature extraction may prove to be, when they are combined, valuable in Automated Target Recognition (ATR) and other automated object recognition systems.

Mining the key predictors for event outbreaks in social networks

NASA Astrophysics Data System (ADS)

Yi, Chengqi; Bao, Yuanyuan; Xue, Yibo

2016-04-01

It will be beneficial to devise a method to predict a so-called event outbreak. Existing works mainly focus on exploring effective methods for improving the accuracy of predictions, while ignoring the underlying causes: What makes event go viral? What factors that significantly influence the prediction of an event outbreak in social networks? In this paper, we proposed a novel definition for an event outbreak, taking into account the structural changes to a network during the propagation of content. In addition, we investigated features that were sensitive to predicting an event outbreak. In order to investigate the universality of these features at different stages of an event, we split the entire lifecycle of an event into 20 equal segments according to the proportion of the propagation time. We extracted 44 features, including features related to content, users, structure, and time, from each segment of the event. Based on these features, we proposed a prediction method using supervised classification algorithms to predict event outbreaks. Experimental results indicate that, as time goes by, our method is highly accurate, with a precision rate ranging from 79% to 97% and a recall rate ranging from 74% to 97%. In addition, after applying a feature-selection algorithm, the top five selected features can considerably improve the accuracy of the prediction. Data-driven experimental results show that the entropy of the eigenvector centrality, the entropy of the PageRank, the standard deviation of the betweenness centrality, the proportion of re-shares without content, and the average path length are the key predictors for an event outbreak. Our findings are especially useful for further exploring the intrinsic characteristics of outbreak prediction.

Webcam classification using simple features

NASA Astrophysics Data System (ADS)

Pramoun, Thitiporn; Choe, Jeehyun; Li, He; Chen, Qingshuang; Amornraksa, Thumrongrat; Lu, Yung-Hsiang; Delp, Edward J.

2015-03-01

Thousands of sensors are connected to the Internet and many of these sensors are cameras. The "Internet of Things" will contain many "things" that are image sensors. This vast network of distributed cameras (i.e. web cams) will continue to exponentially grow. In this paper we examine simple methods to classify an image from a web cam as "indoor/outdoor" and having "people/no people" based on simple features. We use four types of image features to classify an image as indoor/outdoor: color, edge, line, and text. To classify an image as having people/no people we use HOG and texture features. The features are weighted based on their significance and combined. A support vector machine is used for classification. Our system with feature weighting and feature combination yields 95.5% accuracy.

Cross-modal integration of lexical-semantic features during word processing: evidence from oscillatory dynamics during EEG.

PubMed

van Ackeren, Markus J; Rueschemeyer, Shirley-Ann

2014-01-01

In recent years, numerous studies have provided converging evidence that word meaning is partially stored in modality-specific cortical networks. However, little is known about the mechanisms supporting the integration of this distributed semantic content into coherent conceptual representations. In the current study we aimed to address this issue by using EEG to look at the spatial and temporal dynamics of feature integration during word comprehension. Specifically, participants were presented with two modality-specific features (i.e., visual or auditory features such as silver and loud) and asked to verify whether these two features were compatible with a subsequently presented target word (e.g., WHISTLE). Each pair of features described properties from either the same modality (e.g., silver, tiny  =  visual features) or different modalities (e.g., silver, loud  =  visual, auditory). Behavioral and EEG data were collected. The results show that verifying features that are putatively represented in the same modality-specific network is faster than verifying features across modalities. At the neural level, integrating features across modalities induces sustained oscillatory activity around the theta range (4-6 Hz) in left anterior temporal lobe (ATL), a putative hub for integrating distributed semantic content. In addition, enhanced long-range network interactions in the theta range were seen between left ATL and a widespread cortical network. These results suggest that oscillatory dynamics in the theta range could be involved in integrating multimodal semantic content by creating transient functional networks linking distributed modality-specific networks and multimodal semantic hubs such as left ATL.

Optical-Correlator Neural Network Based On Neocognitron

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1994-01-01

Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.

CNN-BLPred: a Convolutional neural network based predictor for β-Lactamases (BL) and their classes.

PubMed

White, Clarence; Ismail, Hamid D; Saigo, Hiroto; Kc, Dukka B

2017-12-28

The β-Lactamase (BL) enzyme family is an important class of enzymes that plays a key role in bacterial resistance to antibiotics. As the newly identified number of BL enzymes is increasing daily, it is imperative to develop a computational tool to classify the newly identified BL enzymes into one of its classes. There are two types of classification of BL enzymes: Molecular Classification and Functional Classification. Existing computational methods only address Molecular Classification and the performance of these existing methods is unsatisfactory. We addressed the unsatisfactory performance of the existing methods by implementing a Deep Learning approach called Convolutional Neural Network (CNN). We developed CNN-BLPred, an approach for the classification of BL proteins. The CNN-BLPred uses Gradient Boosted Feature Selection (GBFS) in order to select the ideal feature set for each BL classification. Based on the rigorous benchmarking of CCN-BLPred using both leave-one-out cross-validation and independent test sets, CCN-BLPred performed better than the other existing algorithms. Compared with other architectures of CNN, Recurrent Neural Network, and Random Forest, the simple CNN architecture with only one convolutional layer performs the best. After feature extraction, we were able to remove ~95% of the 10,912 features using Gradient Boosted Trees. During 10-fold cross validation, we increased the accuracy of the classic BL predictions by 7%. We also increased the accuracy of Class A, Class B, Class C, and Class D performance by an average of 25.64%. The independent test results followed a similar trend. We implemented a deep learning algorithm known as Convolutional Neural Network (CNN) to develop a classifier for BL classification. Combined with feature selection on an exhaustive feature set and using balancing method such as Random Oversampling (ROS), Random Undersampling (RUS) and Synthetic Minority Oversampling Technique (SMOTE), CNN-BLPred performs significantly better than existing algorithms for BL classification.

Image feature based GPS trace filtering for road network generation and road segmentation

DOE PAGES

Yuan, Jiangye; Cheriyadat, Anil M.

2015-10-19

We propose a new method to infer road networks from GPS trace data and accurately segment road regions in high-resolution aerial images. Unlike previous efforts that rely on GPS traces alone, we exploit image features to infer road networks from noisy trace data. The inferred road network is used to guide road segmentation. We show that the number of image segments spanned by the traces and the trace orientation validated with image features are important attributes for identifying GPS traces on road regions. Based on filtered traces , we construct road networks and integrate them with image features to segmentmore » road regions. Lastly, our experiments show that the proposed method produces more accurate road networks than the leading method that uses GPS traces alone, and also achieves high accuracy in segmenting road regions even with very noisy GPS data.« less

Image feature based GPS trace filtering for road network generation and road segmentation

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

Yuan, Jiangye; Cheriyadat, Anil M.

We propose a new method to infer road networks from GPS trace data and accurately segment road regions in high-resolution aerial images. Unlike previous efforts that rely on GPS traces alone, we exploit image features to infer road networks from noisy trace data. The inferred road network is used to guide road segmentation. We show that the number of image segments spanned by the traces and the trace orientation validated with image features are important attributes for identifying GPS traces on road regions. Based on filtered traces , we construct road networks and integrate them with image features to segmentmore » road regions. Lastly, our experiments show that the proposed method produces more accurate road networks than the leading method that uses GPS traces alone, and also achieves high accuracy in segmenting road regions even with very noisy GPS data.« less

Predicting Drug-Target Interaction Networks Based on Functional Groups and Biological Features

PubMed Central

Shi, Xiao-He; Hu, Le-Le; Kong, Xiangyin; Cai, Yu-Dong; Chou, Kuo-Chen

2010-01-01

Background Study of drug-target interaction networks is an important topic for drug development. It is both time-consuming and costly to determine compound-protein interactions or potential drug-target interactions by experiments alone. As a complement, the in silico prediction methods can provide us with very useful information in a timely manner. Methods/Principal Findings To realize this, drug compounds are encoded with functional groups and proteins encoded by biological features including biochemical and physicochemical properties. The optimal feature selection procedures are adopted by means of the mRMR (Maximum Relevance Minimum Redundancy) method. Instead of classifying the proteins as a whole family, target proteins are divided into four groups: enzymes, ion channels, G-protein- coupled receptors and nuclear receptors. Thus, four independent predictors are established using the Nearest Neighbor algorithm as their operation engine, with each to predict the interactions between drugs and one of the four protein groups. As a result, the overall success rates by the jackknife cross-validation tests achieved with the four predictors are 85.48%, 80.78%, 78.49%, and 85.66%, respectively. Conclusion/Significance Our results indicate that the network prediction system thus established is quite promising and encouraging. PMID:20300175

Seismic signal auto-detecing from different features by using Convolutional Neural Network

NASA Astrophysics Data System (ADS)

Huang, Y.; Zhou, Y.; Yue, H.; Zhou, S.

2017-12-01

We try Convolutional Neural Network to detect some features of seismic data and compare their efficience. The features include whether a signal is seismic signal or noise and the arrival time of P and S phase and each feature correspond to a Convolutional Neural Network. We first use traditional STA/LTA to recongnize some events and then use templete matching to find more events as training set for the Neural Network. To make the training set more various, we add some noise to the seismic data and make some synthetic seismic data and noise. The 3-component raw signal and time-frequancy ananlyze are used as the input data for our neural network. Our Training is performed on GPUs to achieve efficient convergence. Our method improved the precision in comparison with STA/LTA and template matching. We will move to recurrent neural network to see if this kind network is better in detect P and S phase.

Deep convolutional neural network for mammographic density segmentation

NASA Astrophysics Data System (ADS)

Wei, Jun; Li, Songfeng; Chan, Heang-Ping; Helvie, Mark A.; Roubidoux, Marilyn A.; Lu, Yao; Zhou, Chuan; Hadjiiski, Lubomir; Samala, Ravi K.

2018-02-01

Breast density is one of the most significant factors for cancer risk. In this study, we proposed a supervised deep learning approach for automated estimation of percentage density (PD) on digital mammography (DM). The deep convolutional neural network (DCNN) was trained to estimate a probability map of breast density (PMD). PD was calculated as the ratio of the dense area to the breast area based on the probability of each pixel belonging to dense region or fatty region at a decision threshold of 0.5. The DCNN estimate was compared to a feature-based statistical learning approach, in which gray level, texture and morphological features were extracted from each ROI and the least absolute shrinkage and selection operator (LASSO) was used to select and combine the useful features to generate the PMD. The reference PD of each image was provided by two experienced MQSA radiologists. With IRB approval, we retrospectively collected 347 DMs from patient files at our institution. The 10-fold cross-validation results showed a strong correlation r=0.96 between the DCNN estimation and interactive segmentation by radiologists while that of the feature-based statistical learning approach vs radiologists' segmentation had a correlation r=0.78. The difference between the segmentation by DCNN and by radiologists was significantly smaller than that between the feature-based learning approach and radiologists (p < 0.0001) by two-tailed paired t-test. This study demonstrated that the DCNN approach has the potential to replace radiologists' interactive thresholding in PD estimation on DMs.

Estimating standard errors in feature network models.

PubMed

Frank, Laurence E; Heiser, Willem J

2007-05-01

Feature network models are graphical structures that represent proximity data in a discrete space while using the same formalism that is the basis of least squares methods employed in multidimensional scaling. Existing methods to derive a network model from empirical data only give the best-fitting network and yield no standard errors for the parameter estimates. The additivity properties of networks make it possible to consider the model as a univariate (multiple) linear regression problem with positivity restrictions on the parameters. In the present study, both theoretical and empirical standard errors are obtained for the constrained regression parameters of a network model with known features. The performance of both types of standard error is evaluated using Monte Carlo techniques.

Decoding of visual activity patterns from fMRI responses using multivariate pattern analyses and convolutional neural network.

PubMed

Zafar, Raheel; Kamel, Nidal; Naufal, Mohamad; Malik, Aamir Saeed; Dass, Sarat C; Ahmad, Rana Fayyaz; Abdullah, Jafri M; Reza, Faruque

2017-01-01

Decoding of human brain activity has always been a primary goal in neuroscience especially with functional magnetic resonance imaging (fMRI) data. In recent years, Convolutional neural network (CNN) has become a popular method for the extraction of features due to its higher accuracy, however it needs a lot of computation and training data. In this study, an algorithm is developed using Multivariate pattern analysis (MVPA) and modified CNN to decode the behavior of brain for different images with limited data set. Selection of significant features is an important part of fMRI data analysis, since it reduces the computational burden and improves the prediction performance; significant features are selected using t-test. MVPA uses machine learning algorithms to classify different brain states and helps in prediction during the task. General linear model (GLM) is used to find the unknown parameters of every individual voxel and the classification is done using multi-class support vector machine (SVM). MVPA-CNN based proposed algorithm is compared with region of interest (ROI) based method and MVPA based estimated values. The proposed method showed better overall accuracy (68.6%) compared to ROI (61.88%) and estimation values (64.17%).

Mining the modular structure of protein interaction networks.

PubMed

Berenstein, Ariel José; Piñero, Janet; Furlong, Laura Inés; Chernomoretz, Ariel

2015-01-01

Cluster-based descriptions of biological networks have received much attention in recent years fostered by accumulated evidence of the existence of meaningful correlations between topological network clusters and biological functional modules. Several well-performing clustering algorithms exist to infer topological network partitions. However, due to respective technical idiosyncrasies they might produce dissimilar modular decompositions of a given network. In this contribution, we aimed to analyze how alternative modular descriptions could condition the outcome of follow-up network biology analysis. We considered a human protein interaction network and two paradigmatic cluster recognition algorithms, namely: the Clauset-Newman-Moore and the infomap procedures. We analyzed to what extent both methodologies yielded different results in terms of granularity and biological congruency. In addition, taking into account Guimera's cartographic role characterization of network nodes, we explored how the adoption of a given clustering methodology impinged on the ability to highlight relevant network meso-scale connectivity patterns. As a case study we considered a set of aging related proteins and showed that only the high-resolution modular description provided by infomap, could unveil statistically significant associations between them and inter/intra modular cartographic features. Besides reporting novel biological insights that could be gained from the discovered associations, our contribution warns against possible technical concerns that might affect the tools used to mine for interaction patterns in network biology studies. In particular our results suggested that sub-optimal partitions from the strict point of view of their modularity levels might still be worth being analyzed when meso-scale features were to be explored in connection with external source of biological knowledge.

Finding the multipath propagation of multivariable crude oil prices using a wavelet-based network approach

NASA Astrophysics Data System (ADS)

Jia, Xiaoliang; An, Haizhong; Sun, Xiaoqi; Huang, Xuan; Gao, Xiangyun

2016-04-01

The globalization and regionalization of crude oil trade inevitably give rise to the difference of crude oil prices. The understanding of the pattern of the crude oil prices' mutual propagation is essential for analyzing the development of global oil trade. Previous research has focused mainly on the fuzzy long- or short-term one-to-one propagation of bivariate oil prices, generally ignoring various patterns of periodical multivariate propagation. This study presents a wavelet-based network approach to help uncover the multipath propagation of multivariable crude oil prices in a joint time-frequency period. The weekly oil spot prices of the OPEC member states from June 1999 to March 2011 are adopted as the sample data. First, we used wavelet analysis to find different subseries based on an optimal decomposing scale to describe the periodical feature of the original oil price time series. Second, a complex network model was constructed based on an optimal threshold selection to describe the structural feature of multivariable oil prices. Third, Bayesian network analysis (BNA) was conducted to find the probability causal relationship based on periodical structural features to describe the various patterns of periodical multivariable propagation. Finally, the significance of the leading and intermediary oil prices is discussed. These findings are beneficial for the implementation of periodical target-oriented pricing policies and investment strategies.

Electroencephalogram-based decoding cognitive states using convolutional neural network and likelihood ratio based score fusion

PubMed Central

2017-01-01

Electroencephalogram (EEG)-based decoding human brain activity is challenging, owing to the low spatial resolution of EEG. However, EEG is an important technique, especially for brain–computer interface applications. In this study, a novel algorithm is proposed to decode brain activity associated with different types of images. In this hybrid algorithm, convolutional neural network is modified for the extraction of features, a t-test is used for the selection of significant features and likelihood ratio-based score fusion is used for the prediction of brain activity. The proposed algorithm takes input data from multichannel EEG time-series, which is also known as multivariate pattern analysis. Comprehensive analysis was conducted using data from 30 participants. The results from the proposed method are compared with current recognized feature extraction and classification/prediction techniques. The wavelet transform-support vector machine method is the most popular currently used feature extraction and prediction method. This method showed an accuracy of 65.7%. However, the proposed method predicts the novel data with improved accuracy of 79.9%. In conclusion, the proposed algorithm outperformed the current feature extraction and prediction method. PMID:28558002

Automation of lidar-based hydrologic feature extraction workflows using GIS

NASA Astrophysics Data System (ADS)

Borlongan, Noel Jerome B.; de la Cruz, Roel M.; Olfindo, Nestor T.; Perez, Anjillyn Mae C.

2016-10-01

With the advent of LiDAR technology, higher resolution datasets become available for use in different remote sensing and GIS applications. One significant application of LiDAR datasets in the Philippines is in resource features extraction. Feature extraction using LiDAR datasets require complex and repetitive workflows which can take a lot of time for researchers through manual execution and supervision. The Development of the Philippine Hydrologic Dataset for Watersheds from LiDAR Surveys (PHD), a project under the Nationwide Detailed Resources Assessment Using LiDAR (Phil-LiDAR 2) program, created a set of scripts, the PHD Toolkit, to automate its processes and workflows necessary for hydrologic features extraction specifically Streams and Drainages, Irrigation Network, and Inland Wetlands, using LiDAR Datasets. These scripts are created in Python and can be added in the ArcGIS® environment as a toolbox. The toolkit is currently being used as an aid for the researchers in hydrologic feature extraction by simplifying the workflows, eliminating human errors when providing the inputs, and providing quick and easy-to-use tools for repetitive tasks. This paper discusses the actual implementation of different workflows developed by Phil-LiDAR 2 Project 4 in Streams, Irrigation Network and Inland Wetlands extraction.

Deciphering microbial interactions and detecting keystone species with co-occurrence networks.

PubMed

Berry, David; Widder, Stefanie

2014-01-01

Co-occurrence networks produced from microbial survey sequencing data are frequently used to identify interactions between community members. While this approach has potential to reveal ecological processes, it has been insufficiently validated due to the technical limitations inherent in studying complex microbial ecosystems. Here, we simulate multi-species microbial communities with known interaction patterns using generalized Lotka-Volterra dynamics. We then construct co-occurrence networks and evaluate how well networks reveal the underlying interactions and how experimental and ecological parameters can affect network inference and interpretation. We find that co-occurrence networks can recapitulate interaction networks under certain conditions, but that they lose interpretability when the effects of habitat filtering become significant. We demonstrate that networks suffer from local hot spots of spurious correlation in the neighborhood of hub species that engage in many interactions. We also identify topological features associated with keystone species in co-occurrence networks. This study provides a substantiated framework to guide environmental microbiologists in the construction and interpretation of co-occurrence networks from microbial survey datasets.

The Social Origins of Networks and Diffusion.

PubMed

Centola, Damon

2015-03-01

Recent research on social contagion has demonstrated significant effects of network topology on the dynamics of diffusion. However, network topologies are not given a priori. Rather, they are patterns of relations that emerge from individual and structural features of society, such as population composition, group heterogeneity, homophily, and social consolidation. Following Blau and Schwartz, the author develops a model of social network formation that explores how social and structural constraints on tie formation generate emergent social topologies and then explores the effectiveness of these social networks for the dynamics of social diffusion. Results show that, at one extreme, high levels of consolidation can create highly balkanized communities with poor integration of shared norms and practices. As suggested by Blau and Schwartz, reducing consolidation creates more crosscutting circles and significantly improves the dynamics of social diffusion across the population. However, the author finds that further reducing consolidation creates highly intersecting social networks that fail to support the widespread diffusion of norms and practices, indicating that successful social diffusion can depend on moderate to high levels of structural consolidation.

Robust Learning of High-dimensional Biological Networks with Bayesian Networks

NASA Astrophysics Data System (ADS)

Nägele, Andreas; Dejori, Mathäus; Stetter, Martin

Structure learning of Bayesian networks applied to gene expression data has become a potentially useful method to estimate interactions between genes. However, the NP-hardness of Bayesian network structure learning renders the reconstruction of the full genetic network with thousands of genes unfeasible. Consequently, the maximal network size is usually restricted dramatically to a small set of genes (corresponding with variables in the Bayesian network). Although this feature reduction step makes structure learning computationally tractable, on the downside, the learned structure might be adversely affected due to the introduction of missing genes. Additionally, gene expression data are usually very sparse with respect to the number of samples, i.e., the number of genes is much greater than the number of different observations. Given these problems, learning robust network features from microarray data is a challenging task. This chapter presents several approaches tackling the robustness issue in order to obtain a more reliable estimation of learned network features.

Improving deep convolutional neural networks with mixed maxout units.

PubMed

Zhao, Hui-Zhen; Liu, Fu-Xian; Li, Long-Yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that "non-maximal features are unable to deliver" and "feature mapping subspace pooling is insufficient," we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance.

Prediction of interface residue based on the features of residue interaction network.

PubMed

Jiao, Xiong; Ranganathan, Shoba

2017-11-07

Protein-protein interaction plays a crucial role in the cellular biological processes. Interface prediction can improve our understanding of the molecular mechanisms of the related processes and functions. In this work, we propose a classification method to recognize the interface residue based on the features of a weighted residue interaction network. The random forest algorithm is used for the prediction and 16 network parameters and the B-factor are acting as the element of the input feature vector. Compared with other similar work, the method is feasible and effective. The relative importance of these features also be analyzed to identify the key feature for the prediction. Some biological meaning of the important feature is explained. The results of this work can be used for the related work about the structure-function relationship analysis via a residue interaction network model. Copyright © 2017 Elsevier Ltd. All rights reserved.

Autoscoring Essays Based on Complex Networks

ERIC Educational Resources Information Center

Ke, Xiaohua; Zeng, Yongqiang; Luo, Haijiao

2016-01-01

This article presents a novel method, the Complex Dynamics Essay Scorer (CDES), for automated essay scoring using complex network features. Texts produced by college students in China were represented as scale-free networks (e.g., a word adjacency model) from which typical network features, such as the in-/out-degrees, clustering coefficient (CC),…

Deep Spatial-Temporal Joint Feature Representation for Video Object Detection.

PubMed

Zhao, Baojun; Zhao, Boya; Tang, Linbo; Han, Yuqi; Wang, Wenzheng

2018-03-04

With the development of deep neural networks, many object detection frameworks have shown great success in the fields of smart surveillance, self-driving cars, and facial recognition. However, the data sources are usually videos, and the object detection frameworks are mostly established on still images and only use the spatial information, which means that the feature consistency cannot be ensured because the training procedure loses temporal information. To address these problems, we propose a single, fully-convolutional neural network-based object detection framework that involves temporal information by using Siamese networks. In the training procedure, first, the prediction network combines the multiscale feature map to handle objects of various sizes. Second, we introduce a correlation loss by using the Siamese network, which provides neighboring frame features. This correlation loss represents object co-occurrences across time to aid the consistent feature generation. Since the correlation loss should use the information of the track ID and detection label, our video object detection network has been evaluated on the large-scale ImageNet VID dataset where it achieves a 69.5% mean average precision (mAP).

ANALYSIS OF CLINICAL AND DERMOSCOPIC FEATURES FOR BASAL CELL CARCINOMA NEURAL NETWORK CLASSIFICATION

PubMed Central

Cheng, Beibei; Stanley, R. Joe; Stoecker, William V; Stricklin, Sherea M.; Hinton, Kristen A.; Nguyen, Thanh K.; Rader, Ryan K.; Rabinovitz, Harold S.; Oliviero, Margaret; Moss, Randy H.

2012-01-01

Background Basal cell carcinoma (BCC) is the most commonly diagnosed cancer in the United States. In this research, we examine four different feature categories used for diagnostic decisions, including patient personal profile (patient age, gender, etc.), general exam (lesion size and location), common dermoscopic (blue-gray ovoids, leaf-structure dirt trails, etc.), and specific dermoscopic lesion (white/pink areas, semitranslucency, etc.). Specific dermoscopic features are more restricted versions of the common dermoscopic features. Methods Combinations of the four feature categories are analyzed over a data set of 700 lesions, with 350 BCCs and 350 benign lesions, for lesion discrimination using neural network-based techniques, including Evolving Artificial Neural Networks and Evolving Artificial Neural Network Ensembles. Results Experiment results based on ten-fold cross validation for training and testing the different neural network-based techniques yielded an area under the receiver operating characteristic curve as high as 0.981 when all features were combined. The common dermoscopic lesion features generally yielded higher discrimination results than other individual feature categories. Conclusions Experimental results show that combining clinical and image information provides enhanced lesion discrimination capability over either information source separately. This research highlights the potential of data fusion as a model for the diagnostic process. PMID:22724561

Functional mechanisms of probabilistic inference in feature- and space-based attentional systems.

PubMed

Dombert, Pascasie L; Kuhns, Anna; Mengotti, Paola; Fink, Gereon R; Vossel, Simone

2016-11-15

Humans flexibly attend to features or locations and these processes are influenced by the probability of sensory events. We combined computational modeling of response times with fMRI to compare the functional correlates of (re-)orienting, and the modulation by probabilistic inference in spatial and feature-based attention systems. Twenty-four volunteers performed two task versions with spatial or color cues. Percentage of cue validity changed unpredictably. A hierarchical Bayesian model was used to derive trial-wise estimates of probability-dependent attention, entering the fMRI analysis as parametric regressors. Attentional orienting activated a dorsal frontoparietal network in both tasks, without significant parametric modulation. Spatially invalid trials activated a bilateral frontoparietal network and the precuneus, while invalid feature trials activated the left intraparietal sulcus (IPS). Probability-dependent attention modulated activity in the precuneus, left posterior IPS, middle occipital gyrus, and right temporoparietal junction for spatial attention, and in the left anterior IPS for feature-based and spatial attention. These findings provide novel insights into the generality and specificity of the functional basis of attentional control. They suggest that probabilistic inference can distinctively affect each attentional subsystem, but that there is an overlap in the left IPS, which responds to both spatial and feature-based expectancy violations. Copyright © 2016 Elsevier Inc. All rights reserved.

Assessing the performance of multiple spectral-spatial features of a hyperspectral image for classification of urban land cover classes using support vector machines and artificial neural network

NASA Astrophysics Data System (ADS)

Pullanagari, Reddy; Kereszturi, Gábor; Yule, Ian J.; Ghamisi, Pedram

2017-04-01

Accurate and spatially detailed mapping of complex urban environments is essential for land managers. Classifying high spectral and spatial resolution hyperspectral images is a challenging task because of its data abundance and computational complexity. Approaches with a combination of spectral and spatial information in a single classification framework have attracted special attention because of their potential to improve the classification accuracy. We extracted multiple features from spectral and spatial domains of hyperspectral images and evaluated them with two supervised classification algorithms; support vector machines (SVM) and an artificial neural network. The spatial features considered are produced by a gray level co-occurrence matrix and extended multiattribute profiles. All of these features were stacked, and the most informative features were selected using a genetic algorithm-based SVM. After selecting the most informative features, the classification model was integrated with a segmentation map derived using a hidden Markov random field. We tested the proposed method on a real application of a hyperspectral image acquired from AisaFENIX and on widely used hyperspectral images. From the results, it can be concluded that the proposed framework significantly improves the results with different spectral and spatial resolutions over different instrumentation.

Modularity and evolutionary constraints in a baculovirus gene regulatory network

PubMed Central

2013-01-01

Background The structure of regulatory networks remains an open question in our understanding of complex biological systems. Interactions during complete viral life cycles present unique opportunities to understand how host-parasite network take shape and behave. The Anticarsia gemmatalis multiple nucleopolyhedrovirus (AgMNPV) is a large double-stranded DNA virus, whose genome may encode for 152 open reading frames (ORFs). Here we present the analysis of the ordered cascade of the AgMNPV gene expression. Results We observed an earlier onset of the expression than previously reported for other baculoviruses, especially for genes involved in DNA replication. Most ORFs were expressed at higher levels in a more permissive host cell line. Genes with more than one copy in the genome had distinct expression profiles, which could indicate the acquisition of new functionalities. The transcription gene regulatory network (GRN) for 149 ORFs had a modular topology comprising five communities of highly interconnected nodes that separated key genes that are functionally related on different communities, possibly maximizing redundancy and GRN robustness by compartmentalization of important functions. Core conserved functions showed expression synchronicity, distinct GRN features and significantly less genetic diversity, consistent with evolutionary constraints imposed in key elements of biological systems. This reduced genetic diversity also had a positive correlation with the importance of the gene in our estimated GRN, supporting a relationship between phylogenetic data of baculovirus genes and network features inferred from expression data. We also observed that gene arrangement in overlapping transcripts was conserved among related baculoviruses, suggesting a principle of genome organization. Conclusions Albeit with a reduced number of nodes (149), the AgMNPV GRN had a topology and key characteristics similar to those observed in complex cellular organisms, which indicates that modularity may be a general feature of biological gene regulatory networks. PMID:24006890

Overcoming the effects of false positives and threshold bias in graph theoretical analyses of neuroimaging data.

PubMed

Drakesmith, M; Caeyenberghs, K; Dutt, A; Lewis, G; David, A S; Jones, D K

2015-09-01

Graph theory (GT) is a powerful framework for quantifying topological features of neuroimaging-derived functional and structural networks. However, false positive (FP) connections arise frequently and influence the inferred topology of networks. Thresholding is often used to overcome this problem, but an appropriate threshold often relies on a priori assumptions, which will alter inferred network topologies. Four common network metrics (global efficiency, mean clustering coefficient, mean betweenness and smallworldness) were tested using a model tractography dataset. It was found that all four network metrics were significantly affected even by just one FP. Results also show that thresholding effectively dampens the impact of FPs, but at the expense of adding significant bias to network metrics. In a larger number (n=248) of tractography datasets, statistics were computed across random group permutations for a range of thresholds, revealing that statistics for network metrics varied significantly more than for non-network metrics (i.e., number of streamlines and number of edges). Varying degrees of network atrophy were introduced artificially to half the datasets, to test sensitivity to genuine group differences. For some network metrics, this atrophy was detected as significant (p<0.05, determined using permutation testing) only across a limited range of thresholds. We propose a multi-threshold permutation correction (MTPC) method, based on the cluster-enhanced permutation correction approach, to identify sustained significant effects across clusters of thresholds. This approach minimises requirements to determine a single threshold a priori. We demonstrate improved sensitivity of MTPC-corrected metrics to genuine group effects compared to an existing approach and demonstrate the use of MTPC on a previously published network analysis of tractography data derived from a clinical population. In conclusion, we show that there are large biases and instability induced by thresholding, making statistical comparisons of network metrics difficult. However, by testing for effects across multiple thresholds using MTPC, true group differences can be robustly identified. Copyright © 2015. Published by Elsevier Inc.

Learning to Detect Vandalism in Social Content Systems: A Study on Wikipedia

NASA Astrophysics Data System (ADS)

Javanmardi, Sara; McDonald, David W.; Caruana, Rich; Forouzan, Sholeh; Lopes, Cristina V.

A challenge facing user generated content systems is vandalism, i.e. edits that damage content quality. The high visibility and easy access to social networks makes them popular targets for vandals. Detecting and removing vandalism is critical for these user generated content systems. Because vandalism can take many forms, there are many different kinds of features that are potentially useful for detecting it. The complex nature of vandalism, and the large number of potential features, make vandalism detection difficult and time consuming for human editors. Machine learning techniques hold promise for developing accurate, tunable, and maintainable models that can be incorporated into vandalism detection tools. We describe a method for training classifiers for vandalism detection that yields classifiers that are more accurate on the PAN 2010 corpus than others previously developed. Because of the high turnaround in social network systems, it is important for vandalism detection tools to run in real-time. To this aim, we use feature selection to find the minimal set of features consistent with high accuracy. In addition, because some features are more costly to compute than others, we use cost-sensitive feature selection to reduce the total computational cost of executing our models. In addition to the features previously used for spam detection, we introduce new features based on user action histories. The user history features contribute significantly to classifier performance. The approach we use is general and can easily be applied to other user generated content systems.

NIMEFI: gene regulatory network inference using multiple ensemble feature importance algorithms.

PubMed

Ruyssinck, Joeri; Huynh-Thu, Vân Anh; Geurts, Pierre; Dhaene, Tom; Demeester, Piet; Saeys, Yvan

2014-01-01

One of the long-standing open challenges in computational systems biology is the topology inference of gene regulatory networks from high-throughput omics data. Recently, two community-wide efforts, DREAM4 and DREAM5, have been established to benchmark network inference techniques using gene expression measurements. In these challenges the overall top performer was the GENIE3 algorithm. This method decomposes the network inference task into separate regression problems for each gene in the network in which the expression values of a particular target gene are predicted using all other genes as possible predictors. Next, using tree-based ensemble methods, an importance measure for each predictor gene is calculated with respect to the target gene and a high feature importance is considered as putative evidence of a regulatory link existing between both genes. The contribution of this work is twofold. First, we generalize the regression decomposition strategy of GENIE3 to other feature importance methods. We compare the performance of support vector regression, the elastic net, random forest regression, symbolic regression and their ensemble variants in this setting to the original GENIE3 algorithm. To create the ensemble variants, we propose a subsampling approach which allows us to cast any feature selection algorithm that produces a feature ranking into an ensemble feature importance algorithm. We demonstrate that the ensemble setting is key to the network inference task, as only ensemble variants achieve top performance. As second contribution, we explore the effect of using rankwise averaged predictions of multiple ensemble algorithms as opposed to only one. We name this approach NIMEFI (Network Inference using Multiple Ensemble Feature Importance algorithms) and show that this approach outperforms all individual methods in general, although on a specific network a single method can perform better. An implementation of NIMEFI has been made publicly available.

An Evaluation of optional timing/synchronization features to support selection of an optimum design for the DCS digital communication network

NASA Technical Reports Server (NTRS)

Bradley, D. B.; Cain, J. B., III; Williard, M. W.

1978-01-01

The task was to evaluate the ability of a set of timing/synchronization subsystem features to provide a set of desirable characteristics for the evolving Defense Communications System digital communications network. The set of features related to the approaches by which timing/synchronization information could be disseminated throughout the network and the manner in which this information could be utilized to provide a synchronized network. These features, which could be utilized in a large number of different combinations, included mutual control, directed control, double ended reference links, independence of clock error measurement and correction, phase reference combining, and self organizing.

Bag of Visual Words Model with Deep Spatial Features for Geographical Scene Classification

PubMed Central

Wu, Lin

2017-01-01

With the popular use of geotagging images, more and more research efforts have been placed on geographical scene classification. In geographical scene classification, valid spatial feature selection can significantly boost the final performance. Bag of visual words (BoVW) can do well in selecting feature in geographical scene classification; nevertheless, it works effectively only if the provided feature extractor is well-matched. In this paper, we use convolutional neural networks (CNNs) for optimizing proposed feature extractor, so that it can learn more suitable visual vocabularies from the geotagging images. Our approach achieves better performance than BoVW as a tool for geographical scene classification, respectively, in three datasets which contain a variety of scene categories. PMID:28706534

DEKF system for crowding estimation by a multiple-model approach

NASA Astrophysics Data System (ADS)

Cravino, F.; Dellucca, M.; Tesei, A.

1994-03-01

A distributed extended Kalman filter (DEKF) network devoted to real-time crowding estimation for surveillance in complex scenes is presented. Estimation is carried out by extracting a set of significant features from sequences of images. Feature values are associated by virtual sensors with the estimated number of people using nonlinear models obtained in an off-line training phase. Different models are used, depending on the positions and dimensions of the crowded subareas detected in each image.

Reconfigurable optical implementation of quantum complex networks

NASA Astrophysics Data System (ADS)

Nokkala, J.; Arzani, F.; Galve, F.; Zambrini, R.; Maniscalco, S.; Piilo, J.; Treps, N.; Parigi, V.

2018-05-01

Network theory has played a dominant role in understanding the structure of complex systems and their dynamics. Recently, quantum complex networks, i.e. collections of quantum systems arranged in a non-regular topology, have been theoretically explored leading to significant progress in a multitude of diverse contexts including, e.g., quantum transport, open quantum systems, quantum communication, extreme violation of local realism, and quantum gravity theories. Despite important progress in several quantum platforms, the implementation of complex networks with arbitrary topology in quantum experiments is still a demanding task, especially if we require both a significant size of the network and the capability of generating arbitrary topology—from regular to any kind of non-trivial structure—in a single setup. Here we propose an all optical and reconfigurable implementation of quantum complex networks. The experimental proposal is based on optical frequency combs, parametric processes, pulse shaping and multimode measurements allowing the arbitrary control of the number of the nodes (optical modes) and topology of the links (interactions between the modes) within the network. Moreover, we also show how to simulate quantum dynamics within the network combined with the ability to address its individual nodes. To demonstrate the versatility of these features, we discuss the implementation of two recently proposed probing techniques for quantum complex networks and structured environments.

Impact of Terrain Features for Tactical Network Connectivity

DTIC Science & Technology

2013-09-01

Impact of Terrain Features for Tactical Network Connectivity David Tate Lance Joneckis John Fregeau Corinne Kramer David Sparrow I N S T I T U...2000. I N S T I T U T E F O R D E F E N S E A N A LY S E S IDA Document NS D-5026 Impact of Terrain Features for Tactical Network Connectivity...visibility is acceptable when networks operate over flat terrain. Under our simple LOS model of connectivity, mobility has little impact in such an

A Hybrid Swarm Intelligence Algorithm for Intrusion Detection Using Significant Features.

PubMed

Amudha, P; Karthik, S; Sivakumari, S

2015-01-01

Intrusion detection has become a main part of network security due to the huge number of attacks which affects the computers. This is due to the extensive growth of internet connectivity and accessibility to information systems worldwide. To deal with this problem, in this paper a hybrid algorithm is proposed to integrate Modified Artificial Bee Colony (MABC) with Enhanced Particle Swarm Optimization (EPSO) to predict the intrusion detection problem. The algorithms are combined together to find out better optimization results and the classification accuracies are obtained by 10-fold cross-validation method. The purpose of this paper is to select the most relevant features that can represent the pattern of the network traffic and test its effect on the success of the proposed hybrid classification algorithm. To investigate the performance of the proposed method, intrusion detection KDDCup'99 benchmark dataset from the UCI Machine Learning repository is used. The performance of the proposed method is compared with the other machine learning algorithms and found to be significantly different.

A Hybrid Swarm Intelligence Algorithm for Intrusion Detection Using Significant Features

PubMed Central

Amudha, P.; Karthik, S.; Sivakumari, S.

2015-01-01

Intrusion detection has become a main part of network security due to the huge number of attacks which affects the computers. This is due to the extensive growth of internet connectivity and accessibility to information systems worldwide. To deal with this problem, in this paper a hybrid algorithm is proposed to integrate Modified Artificial Bee Colony (MABC) with Enhanced Particle Swarm Optimization (EPSO) to predict the intrusion detection problem. The algorithms are combined together to find out better optimization results and the classification accuracies are obtained by 10-fold cross-validation method. The purpose of this paper is to select the most relevant features that can represent the pattern of the network traffic and test its effect on the success of the proposed hybrid classification algorithm. To investigate the performance of the proposed method, intrusion detection KDDCup'99 benchmark dataset from the UCI Machine Learning repository is used. The performance of the proposed method is compared with the other machine learning algorithms and found to be significantly different. PMID:26221625

Exposing the Backstage: Critical Reflections on a Longitudinal Qualitative Study of Residents’ Care Networks in Assisted Living

PubMed Central

Kemp, Candace L.; Ball, Mary M.; Morgan, Jennifer Craft; Doyle, Patrick J.; Burgess, Elisabeth O.; Dillard, Joy A.; Barmon, Christina E.; Fitzroy, Andrea F.; Helmly, Victoria E.; Avent, Elizabeth S.; Perkins, Molly M.

2018-01-01

In this article, we analyze the research experiences associated with a longitudinal qualitative study of residents’ care networks in assisted living. Using data from researcher meetings, field notes, and memos, we critically examine our design and decision making and accompanying methodological implications. We focus on one complete wave of data collection involving 28 residents and 114 care network members in four diverse settings followed for 2 years. We identify study features that make our research innovative, but that also represent significant challenges. They include the focus and topic; settings and participants; scope and design complexity; nature, modes, frequency, and duration of data collection; and analytic approach. Each feature has methodological implications, including benefits and challenges pertaining to recruitment, retention, data collection, quality, and management, research team work, researcher roles, ethics, and dissemination. Our analysis demonstrates the value of our approach and of reflecting on and sharing methodological processes for cumulative knowledge building. PMID:27651072

Exposing the Backstage: Critical Reflections on a Longitudinal Qualitative Study of Residents' Care Networks in Assisted Living.

PubMed

Kemp, Candace L; Ball, Mary M; Morgan, Jennifer Craft; Doyle, Patrick J; Burgess, Elisabeth O; Dillard, Joy A; Barmon, Christina E; Fitzroy, Andrea F; Helmly, Victoria E; Avent, Elizabeth S; Perkins, Molly M

2017-07-01

In this article, we analyze the research experiences associated with a longitudinal qualitative study of residents' care networks in assisted living. Using data from researcher meetings, field notes, and memos, we critically examine our design and decision making and accompanying methodological implications. We focus on one complete wave of data collection involving 28 residents and 114 care network members in four diverse settings followed for 2 years. We identify study features that make our research innovative, but that also represent significant challenges. They include the focus and topic; settings and participants; scope and design complexity; nature, modes, frequency, and duration of data collection; and analytic approach. Each feature has methodological implications, including benefits and challenges pertaining to recruitment, retention, data collection, quality, and management, research team work, researcher roles, ethics, and dissemination. Our analysis demonstrates the value of our approach and of reflecting on and sharing methodological processes for cumulative knowledge building.

Do Convolutional Neural Networks Learn Class Hierarchy?

PubMed

Bilal, Alsallakh; Jourabloo, Amin; Ye, Mao; Liu, Xiaoming; Ren, Liu

2018-01-01

Convolutional Neural Networks (CNNs) currently achieve state-of-the-art accuracy in image classification. With a growing number of classes, the accuracy usually drops as the possibilities of confusion increase. Interestingly, the class confusion patterns follow a hierarchical structure over the classes. We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data. We found that this hierarchy not only dictates the confusion patterns between the classes, it furthermore dictates the learning behavior of CNNs. In particular, the early layers in these networks develop feature detectors that can separate high-level groups of classes quite well, even after a few training epochs. In contrast, the latter layers require substantially more epochs to develop specialized feature detectors that can separate individual classes. We demonstrate how these insights are key to significant improvement in accuracy by designing hierarchy-aware CNNs that accelerate model convergence and alleviate overfitting. We further demonstrate how our methods help in identifying various quality issues in the training data.

Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

PubMed

Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

2017-12-01

This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18 F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images. Because CNN does not need tumor segmentation or feature calculation, it is more convenient and more objective than the classical methods. However, CNN does not make use of the import diagnostic features, which have been proved more discriminative than the texture features for classifying small-sized lymph nodes. Therefore, incorporating the diagnostic features into CNN is a promising direction for future research.

Classification and pose estimation of objects using nonlinear features

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-03-01

A new nonlinear feature extraction method called the maximum representation and discrimination feature (MRDF) method is presented for extraction of features from input image data. It implements transformations similar to the Sigma-Pi neural network. However, the weights of the MRDF are obtained in closed form, and offer advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We show its use in estimating the class and pose of images of real objects and rendered solid CAD models of machine parts from single views using a feature-space trajectory (FST) neural network classifier. We show more accurate classification and pose estimation results than are achieved by standard principal component analysis (PCA) and Fukunaga-Koontz (FK) feature extraction methods.

Multiple supervised residual network for osteosarcoma segmentation in CT images.

PubMed

Zhang, Rui; Huang, Lin; Xia, Wei; Zhang, Bo; Qiu, Bensheng; Gao, Xin

2018-01-01

Automatic and accurate segmentation of osteosarcoma region in CT images can help doctor make a reasonable treatment plan, thus improving cure rate. In this paper, a multiple supervised residual network (MSRN) was proposed for osteosarcoma image segmentation. Three supervised side output modules were added to the residual network. The shallow side output module could extract image shape features, such as edge features and texture features. The deep side output module could extract semantic features. The side output module could compute the loss value between output probability map and ground truth and back-propagate the loss information. Then, the parameters of residual network could be modified by gradient descent method. This could guide the multi-scale feature learning of the network. The final segmentation results were obtained by fusing the results output by the three side output modules. A total of 1900 CT images from 15 osteosarcoma patients were used to train the network and a total of 405 CT images from another 8 osteosarcoma patients were used to test the network. Results indicated that MSRN enabled a dice similarity coefficient (DSC) of 89.22%, a sensitivity of 88.74% and a F1-measure of 0.9305, which were larger than those obtained by fully convolutional network (FCN) and U-net. Thus, MSRN for osteosarcoma segmentation could give more accurate results than FCN and U-Net. Copyright © 2018 Elsevier Ltd. All rights reserved.

A Comprehensive Pan-Cancer Molecular Study of Gynecologic and Breast Cancers.

PubMed

Berger, Ashton C; Korkut, Anil; Kanchi, Rupa S; Hegde, Apurva M; Lenoir, Walter; Liu, Wenbin; Liu, Yuexin; Fan, Huihui; Shen, Hui; Ravikumar, Visweswaran; Rao, Arvind; Schultz, Andre; Li, Xubin; Sumazin, Pavel; Williams, Cecilia; Mestdagh, Pieter; Gunaratne, Preethi H; Yau, Christina; Bowlby, Reanne; Robertson, A Gordon; Tiezzi, Daniel G; Wang, Chen; Cherniack, Andrew D; Godwin, Andrew K; Kuderer, Nicole M; Rader, Janet S; Zuna, Rosemary E; Sood, Anil K; Lazar, Alexander J; Ojesina, Akinyemi I; Adebamowo, Clement; Adebamowo, Sally N; Baggerly, Keith A; Chen, Ting-Wen; Chiu, Hua-Sheng; Lefever, Steve; Liu, Liang; MacKenzie, Karen; Orsulic, Sandra; Roszik, Jason; Shelley, Carl Simon; Song, Qianqian; Vellano, Christopher P; Wentzensen, Nicolas; Weinstein, John N; Mills, Gordon B; Levine, Douglas A; Akbani, Rehan

2018-04-09

We analyzed molecular data on 2,579 tumors from The Cancer Genome Atlas (TCGA) of four gynecological types plus breast. Our aims were to identify shared and unique molecular features, clinically significant subtypes, and potential therapeutic targets. We found 61 somatic copy-number alterations (SCNAs) and 46 significantly mutated genes (SMGs). Eleven SCNAs and 11 SMGs had not been identified in previous TCGA studies of the individual tumor types. We found functionally significant estrogen receptor-regulated long non-coding RNAs (lncRNAs) and gene/lncRNA interaction networks. Pathway analysis identified subtypes with high leukocyte infiltration, raising potential implications for immunotherapy. Using 16 key molecular features, we identified five prognostic subtypes and developed a decision tree that classified patients into the subtypes based on just six features that are assessable in clinical laboratories. Copyright © 2018 Elsevier Inc. All rights reserved.

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification

NASA Astrophysics Data System (ADS)

Lin, Daoyu; Fu, Kun; Wang, Yang; Xu, Guangluan; Sun, Xian

2017-11-01

With the development of deep learning, supervised learning has frequently been adopted to classify remotely sensed images using convolutional networks (CNNs). However, due to the limited amount of labeled data available, supervised learning is often difficult to carry out. Therefore, we proposed an unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data. MARTA GANs consists of both a generative model $G$ and a discriminative model $D$. We treat $D$ as a feature extractor. To fit the complex properties of remote sensing data, we use a fusion layer to merge the mid-level and global features. $G$ can produce numerous images that are similar to the training data; therefore, $D$ can learn better representations of remotely sensed images using the training data provided by $G$. The classification results on two widely used remote sensing image databases show that the proposed method significantly improves the classification performance compared with other state-of-the-art methods.

Research on intrusion detection based on Kohonen network and support vector machine

NASA Astrophysics Data System (ADS)

Shuai, Chunyan; Yang, Hengcheng; Gong, Zeweiyi

2018-05-01

In view of the problem of low detection accuracy and the long detection time of support vector machine, which directly applied to the network intrusion detection system. Optimization of SVM parameters can greatly improve the detection accuracy, but it can not be applied to high-speed network because of the long detection time. a method based on Kohonen neural network feature selection is proposed to reduce the optimization time of support vector machine parameters. Firstly, this paper is to calculate the weights of the KDD99 network intrusion data by Kohonen network and select feature by weight. Then, after the feature selection is completed, genetic algorithm (GA) and grid search method are used for parameter optimization to find the appropriate parameters and classify them by support vector machines. By comparing experiments, it is concluded that feature selection can reduce the time of parameter optimization, which has little influence on the accuracy of classification. The experiments suggest that the support vector machine can be used in the network intrusion detection system and reduce the missing rate.

Accelerating Innovation that Enhances Resource Recovery in the Wastewater Sector: Advancing a National Testbed Network.

PubMed

Mihelcic, James R; Ren, Zhiyong Jason; Cornejo, Pablo K; Fisher, Aaron; Simon, A J; Snyder, Seth W; Zhang, Qiong; Rosso, Diego; Huggins, Tyler M; Cooper, William; Moeller, Jeff; Rose, Bob; Schottel, Brandi L; Turgeon, Jason

2017-07-18

This Feature examines significant challenges and opportunities to spur innovation and accelerate adoption of reliable technologies that enhance integrated resource recovery in the wastewater sector through the creation of a national testbed network. The network is a virtual entity that connects appropriate physical testing facilities, and other components needed for a testbed network, with researchers, investors, technology providers, utilities, regulators, and other stakeholders to accelerate the adoption of innovative technologies and processes that are needed for the water resource recovery facility of the future. Here we summarize and extract key issues and developments, to provide a strategy for the wastewater sector to accelerate a path forward that leads to new sustainable water infrastructures.

ION Configuration Editor

NASA Technical Reports Server (NTRS)

Borgen, Richard L.

2013-01-01

The configuration of ION (Inter - planetary Overlay Network) network nodes is a manual task that is complex, time-consuming, and error-prone. This program seeks to accelerate this job and produce reliable configurations. The ION Configuration Editor is a model-based smart editor based on Eclipse Modeling Framework technology. An ION network designer uses this Eclipse-based GUI to construct a data model of the complete target network and then generate configurations. The data model is captured in an XML file. Intrinsic editor features aid in achieving model correctness, such as field fill-in, type-checking, lists of valid values, and suitable default values. Additionally, an explicit "validation" feature executes custom rules to catch more subtle model errors. A "survey" feature provides a set of reports providing an overview of the entire network, enabling a quick assessment of the model s completeness and correctness. The "configuration" feature produces the main final result, a complete set of ION configuration files (eight distinct file types) for each ION node in the network.

Probabilistic diffusion tractography reveals improvement of structural network in musicians.

PubMed

Li, Jianfu; Luo, Cheng; Peng, Yueheng; Xie, Qiankun; Gong, Jinnan; Dong, Li; Lai, Yongxiu; Li, Hong; Yao, Dezhong

2014-01-01

Musicians experience a large amount of information transfer and integration of complex sensory, motor, and auditory processes when training and playing musical instruments. Therefore, musicians are a useful model in which to investigate neural adaptations in the brain. Here, based on diffusion-weighted imaging, probabilistic tractography was used to determine the architecture of white matter anatomical networks in musicians and non-musicians. Furthermore, the features of the white matter networks were analyzed using graph theory. Small-world properties of the white matter network were observed in both groups. Compared with non-musicians, the musicians exhibited significantly increased connectivity strength in the left and right supplementary motor areas, the left calcarine fissure and surrounding cortex and the right caudate nucleus, as well as a significantly larger weighted clustering coefficient in the right olfactory cortex, the left medial superior frontal gyrus, the right gyrus rectus, the left lingual gyrus, the left supramarginal gyrus, and the right pallidum. Furthermore, there were differences in the node betweenness centrality in several regions. However, no significant differences in topological properties were observed at a global level. We illustrated preliminary findings to extend the network level understanding of white matter plasticity in musicians who have had long-term musical training. These structural, network-based findings may indicate that musicians have enhanced information transmission efficiencies in local white matter networks that are related to musical training.

Significance of MPEG-7 textural features for improved mass detection in mammography.

PubMed

Eltonsy, Nevine H; Tourassi, Georgia D; Fadeev, Aleksey; Elmaghraby, Adel S

2006-01-01

The purpose of the study is to investigate the significance of MPEG-7 textural features for improving the detection of masses in screening mammograms. The detection scheme was originally based on morphological directional neighborhood features extracted from mammographic regions of interest (ROIs). Receiver Operating Characteristics (ROC) was performed to evaluate the performance of each set of features independently and merged into a back-propagation artificial neural network (BPANN) using the leave-one-out sampling scheme (LOOSS). The study was based on a database of 668 mammographic ROIs (340 depicting cancer regions and 328 depicting normal parenchyma). Overall, the ROC area index of the BPANN using the directional morphological features was Az=0.85+/-0.01. The MPEG-7 edge histogram descriptor-based BPNN showed an ROC area index of Az=0.71+/-0.01 while homogeneous textural descriptors using 30 and 120 channels helped the BPNN achieve similar ROC area indexes of Az=0.882+/-0.02 and Az=0.877+/-0.01 respectively. After merging the MPEG-7 homogeneous textural features with the directional neighborhood features the performance of the BPANN increased providing an ROC area index of Az=0.91+/-0.01. MPEG-7 homogeneous textural descriptor significantly improved the morphology-based detection scheme.

Individual Morphological Brain Network Construction Based on Multivariate Euclidean Distances Between Brain Regions.

PubMed

Yu, Kaixin; Wang, Xuetong; Li, Qiongling; Zhang, Xiaohui; Li, Xinwei; Li, Shuyu

2018-01-01

Morphological brain network plays a key role in investigating abnormalities in neurological diseases such as mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, most of the morphological brain network construction methods only considered a single morphological feature. Each type of morphological feature has specific neurological and genetic underpinnings. A combination of morphological features has been proven to have better diagnostic performance compared with a single feature, which suggests that an individual morphological brain network based on multiple morphological features would be beneficial in disease diagnosis. Here, we proposed a novel method to construct individual morphological brain networks for two datasets by calculating the exponential function of multivariate Euclidean distance as the evaluation of similarity between two regions. The first dataset included 24 healthy subjects who were scanned twice within a 3-month period. The topological properties of these brain networks were analyzed and compared with previous studies that used different methods and modalities. Small world property was observed in all of the subjects, and the high reproducibility indicated the robustness of our method. The second dataset included 170 patients with MCI (86 stable MCI and 84 progressive MCI cases) and 169 normal controls (NC). The edge features extracted from the individual morphological brain networks were used to distinguish MCI from NC and separate MCI subgroups (progressive vs. stable) through the support vector machine in order to validate our method. The results showed that our method achieved an accuracy of 79.65% (MCI vs. NC) and 70.59% (stable MCI vs. progressive MCI) in a one-dimension situation. In a multiple-dimension situation, our method improved the classification performance with an accuracy of 80.53% (MCI vs. NC) and 77.06% (stable MCI vs. progressive MCI) compared with the method using a single feature. The results indicated that our method could effectively construct an individual morphological brain network based on multiple morphological features and could accurately discriminate MCI from NC and stable MCI from progressive MCI, and may provide a valuable tool for the investigation of individual morphological brain networks.

Learning in stochastic neural networks for constraint satisfaction problems

NASA Technical Reports Server (NTRS)

Johnston, Mark D.; Adorf, Hans-Martin

1989-01-01

Researchers describe a newly-developed artificial neural network algorithm for solving constraint satisfaction problems (CSPs) which includes a learning component that can significantly improve the performance of the network from run to run. The network, referred to as the Guarded Discrete Stochastic (GDS) network, is based on the discrete Hopfield network but differs from it primarily in that auxiliary networks (guards) are asymmetrically coupled to the main network to enforce certain types of constraints. Although the presence of asymmetric connections implies that the network may not converge, it was found that, for certain classes of problems, the network often quickly converges to find satisfactory solutions when they exist. The network can run efficiently on serial machines and can find solutions to very large problems (e.g., N-queens for N as large as 1024). One advantage of the network architecture is that network connection strengths need not be instantiated when the network is established: they are needed only when a participating neural element transitions from off to on. They have exploited this feature to devise a learning algorithm, based on consistency techniques for discrete CSPs, that updates the network biases and connection strengths and thus improves the network performance.

Effect of tumor resection on the characteristics of functional brain networks.

PubMed

Wang, H; Douw, L; Hernández, J M; Reijneveld, J C; Stam, C J; Van Mieghem, P

2010-08-01

Brain functioning such as cognitive performance depends on the functional interactions between brain areas, namely, the functional brain networks. The functional brain networks of a group of patients with brain tumors are measured before and after tumor resection. In this work, we perform a weighted network analysis to understand the effect of neurosurgery on the characteristics of functional brain networks. Statistically significant changes in network features have been discovered in the beta (13-30 Hz) band after neurosurgery: the link weight correlation around nodes and within triangles increases which implies improvement in local efficiency of information transfer and robustness; the clustering of high link weights in a subgraph becomes stronger, which enhances the global transport capability; and the decrease in the synchronization or virus spreading threshold, revealed by the increase in the largest eigenvalue of the adjacency matrix, which suggests again the improvement of information dissemination.

Beyond Fine Tuning: Adding capacity to leverage few labels

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

Hodas, Nathan O.; Shaffer, Kyle J.; Yankov, Artem

2017-12-09

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural networks or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning.more » Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.« less

Resource constrained flux balance analysis predicts selective pressure on the global structure of metabolic networks.

PubMed

Abedpour, Nima; Kollmann, Markus

2015-11-23

A universal feature of metabolic networks is their hourglass or bow-tie structure on cellular level. This architecture reflects the conversion of multiple input nutrients into multiple biomass components via a small set of precursor metabolites. However, it is yet unclear to what extent this structural feature is the result of natural selection. We extend flux balance analysis to account for limited cellular resources. Using this model, optimal structure of metabolic networks can be calculated for different environmental conditions. We observe a significant structural reshaping of metabolic networks for a toy-network and E. coli core metabolism if we increase the share of invested resources for switching between different nutrient conditions. Here, hub nodes emerge and the optimal network structure becomes bow-tie-like as a consequence of limited cellular resource constraint. We confirm this theoretical finding by comparing the reconstructed metabolic networks of bacterial species with respect to their lifestyle. We show that bow-tie structure can give a system-level fitness advantage to organisms that live in highly competitive and fluctuating environments. Here, limitation of cellular resources can lead to an efficiency-flexibility tradeoff where it pays off for the organism to shorten catabolic pathways if they are frequently activated and deactivated. As a consequence, generalists that shuttle between diverse environmental conditions should have a more predominant bow-tie structure than specialists that visit just a few isomorphic habitats during their life cycle.

Features Extraction of Flotation Froth Images and BP Neural Network Soft-Sensor Model of Concentrate Grade Optimized by Shuffled Cuckoo Searching Algorithm

PubMed Central

Wang, Jie-sheng; Han, Shuang; Shen, Na-na; Li, Shu-xia

2014-01-01

For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy. PMID:25133210

Improving deep convolutional neural networks with mixed maxout units

PubMed Central

Liu, Fu-xian; Li, Long-yue

2017-01-01

Motivated by insights from the maxout-units-based deep Convolutional Neural Network (CNN) that “non-maximal features are unable to deliver” and “feature mapping subspace pooling is insufficient,” we present a novel mixed variant of the recently introduced maxout unit called a mixout unit. Specifically, we do so by calculating the exponential probabilities of feature mappings gained by applying different convolutional transformations over the same input and then calculating the expected values according to their exponential probabilities. Moreover, we introduce the Bernoulli distribution to balance the maximum values with the expected values of the feature mappings subspace. Finally, we design a simple model to verify the pooling ability of mixout units and a Mixout-units-based Network-in-Network (NiN) model to analyze the feature learning ability of the mixout models. We argue that our proposed units improve the pooling ability and that mixout models can achieve better feature learning and classification performance. PMID:28727737

Supervised learning methods for pathological arterial pulse wave differentiation: A SVM and neural networks approach.

PubMed

Paiva, Joana S; Cardoso, João; Pereira, Tânia

2018-01-01

The main goal of this study was to develop an automatic method based on supervised learning methods, able to distinguish healthy from pathologic arterial pulse wave (APW), and those two from noisy waveforms (non-relevant segments of the signal), from the data acquired during a clinical examination with a novel optical system. The APW dataset analysed was composed by signals acquired in a clinical environment from a total of 213 subjects, including healthy volunteers and non-healthy patients. The signals were parameterised by means of 39pulse features: morphologic, time domain statistics, cross-correlation features, wavelet features. Multiclass Support Vector Machine Recursive Feature Elimination (SVM RFE) method was used to select the most relevant features. A comparative study was performed in order to evaluate the performance of the two classifiers: Support Vector Machine (SVM) and Artificial Neural Network (ANN). SVM achieved a statistically significant better performance for this problem with an average accuracy of 0.9917±0.0024 and a F-Measure of 0.9925±0.0019, in comparison with ANN, which reached the values of 0.9847±0.0032 and 0.9852±0.0031 for Accuracy and F-Measure, respectively. A significant difference was observed between the performances obtained with SVM classifier using a different number of features from the original set available. The comparison between SVM and NN allowed reassert the higher performance of SVM. The results obtained in this study showed the potential of the proposed method to differentiate those three important signal outcomes (healthy, pathologic and noise) and to reduce bias associated with clinical diagnosis of cardiovascular disease using APW. Copyright © 2017 Elsevier B.V. All rights reserved.

An efficient coordination protocol for wireless sensor networks

NASA Astrophysics Data System (ADS)

Paruchuri, Vamsi; Durresi, Arjan; Durresi, Mimoza; Barolli, Leonard

2005-10-01

Backbones infrastructures in wireless sensor networks reduce the communication overhead and energy consumption. In this paper, we present BackBone Routing (BBR), a fully distributed protocol for construction and rotation of backbone networks. BBR reduces energy consumption without significantly diminishing the capacity or connectivity of the network. Another key feature of BBR is its energy balancing nature by distributing the role of being Backbone Node among all the nodes. BBR builds on the observation that when a region of a shared-channel wireless network has a sufficient density of nodes, only a small number of them need be on at any time to forward traffic for active connections. Improvement in system lifetime due to BBR increases as the ratio of idle-to-sleep energy consumption increases, and increases as the density of the network increases. Our experiments show that BBR is more efficient in saving energy and extending network life without deteriorating network performance when compared with geographical shortest path routing.

How does language change as a lexical network? An investigation based on written Chinese word co-occurrence networks

PubMed Central

Chen, Heng; Chen, Xinying

2018-01-01

Language is a complex adaptive system, but how does it change? For investigating this process, four diachronic Chinese word co-occurrence networks have been built based on texts that were written during the last 2,000 years. By comparing the network indicators that are associated with the hierarchical features in language networks, we learn that the hierarchy of Chinese lexical networks has indeed evolved over time at three different levels. The connections of words at the micro level are continually weakening; the number of words in the meso-level communities has increased significantly; and the network is expanding at the macro level. This means that more and more words tend to be connected to medium-central words and form different communities. Meanwhile, fewer high-central words link these communities into a highly efficient small-world network. Understanding this process may be crucial for understanding the increasing structural complexity of the language system. PMID:29489837

How does language change as a lexical network? An investigation based on written Chinese word co-occurrence networks.

PubMed

Chen, Heng; Chen, Xinying; Liu, Haitao

2018-01-01

Language is a complex adaptive system, but how does it change? For investigating this process, four diachronic Chinese word co-occurrence networks have been built based on texts that were written during the last 2,000 years. By comparing the network indicators that are associated with the hierarchical features in language networks, we learn that the hierarchy of Chinese lexical networks has indeed evolved over time at three different levels. The connections of words at the micro level are continually weakening; the number of words in the meso-level communities has increased significantly; and the network is expanding at the macro level. This means that more and more words tend to be connected to medium-central words and form different communities. Meanwhile, fewer high-central words link these communities into a highly efficient small-world network. Understanding this process may be crucial for understanding the increasing structural complexity of the language system.

Evolving Scale-Free Networks by Poisson Process: Modeling and Degree Distribution.

PubMed

Feng, Minyu; Qu, Hong; Yi, Zhang; Xie, Xiurui; Kurths, Jurgen

2016-05-01

Since the great mathematician Leonhard Euler initiated the study of graph theory, the network has been one of the most significant research subject in multidisciplinary. In recent years, the proposition of the small-world and scale-free properties of complex networks in statistical physics made the network science intriguing again for many researchers. One of the challenges of the network science is to propose rational models for complex networks. In this paper, in order to reveal the influence of the vertex generating mechanism of complex networks, we propose three novel models based on the homogeneous Poisson, nonhomogeneous Poisson and birth death process, respectively, which can be regarded as typical scale-free networks and utilized to simulate practical networks. The degree distribution and exponent are analyzed and explained in mathematics by different approaches. In the simulation, we display the modeling process, the degree distribution of empirical data by statistical methods, and reliability of proposed networks, results show our models follow the features of typical complex networks. Finally, some future challenges for complex systems are discussed.

Neonatal Seizure Detection Using Deep Convolutional Neural Networks.

PubMed

Ansari, Amir H; Cherian, Perumpillichira J; Caicedo, Alexander; Naulaers, Gunnar; De Vos, Maarten; Van Huffel, Sabine

2018-04-02

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.

Linear-time general decoding algorithm for the surface code

NASA Astrophysics Data System (ADS)

Darmawan, Andrew S.; Poulin, David

2018-05-01

A quantum error correcting protocol can be substantially improved by taking into account features of the physical noise process. We present an efficient decoder for the surface code which can account for general noise features, including coherences and correlations. We demonstrate that the decoder significantly outperforms the conventional matching algorithm on a variety of noise models, including non-Pauli noise and spatially correlated noise. The algorithm is based on an approximate calculation of the logical channel using a tensor-network description of the noisy state.

Neural net diagnostics for VLSI test

NASA Technical Reports Server (NTRS)

Lin, T.; Tseng, H.; Wu, A.; Dogan, N.; Meador, J.

1990-01-01

This paper discusses the application of neural network pattern analysis algorithms to the IC fault diagnosis problem. A fault diagnostic is a decision rule combining what is known about an ideal circuit test response with information about how it is distorted by fabrication variations and measurement noise. The rule is used to detect fault existence in fabricated circuits using real test equipment. Traditional statistical techniques may be used to achieve this goal, but they can employ unrealistic a priori assumptions about measurement data. Our approach to this problem employs an adaptive pattern analysis technique based on feedforward neural networks. During training, a feedforward network automatically captures unknown sample distributions. This is important because distributions arising from the nonlinear effects of process variation can be more complex than is typically assumed. A feedforward network is also able to extract measurement features which contribute significantly to making a correct decision. Traditional feature extraction techniques employ matrix manipulations which can be particularly costly for large measurement vectors. In this paper we discuss a software system which we are developing that uses this approach. We also provide a simple example illustrating the use of the technique for fault detection in an operational amplifier.

Biased Dropout and Crossmap Dropout: Learning towards effective Dropout regularization in convolutional neural network.

PubMed

Poernomo, Alvin; Kang, Dae-Ki

2018-08-01

Training a deep neural network with a large number of parameters often leads to overfitting problem. Recently, Dropout has been introduced as a simple, yet effective regularization approach to combat overfitting in such models. Although Dropout has shown remarkable results on many deep neural network cases, its actual effect on CNN has not been thoroughly explored. Moreover, training a Dropout model will significantly increase the training time as it takes longer time to converge than a non-Dropout model with the same architecture. To deal with these issues, we address Biased Dropout and Crossmap Dropout, two novel approaches of Dropout extension based on the behavior of hidden units in CNN model. Biased Dropout divides the hidden units in a certain layer into two groups based on their magnitude and applies different Dropout rate to each group appropriately. Hidden units with higher activation value, which give more contributions to the network final performance, will be retained by a lower Dropout rate, while units with lower activation value will be exposed to a higher Dropout rate to compensate the previous part. The second approach is Crossmap Dropout, which is an extension of the regular Dropout in convolution layer. Each feature map in a convolution layer has a strong correlation between each other, particularly in every identical pixel location in each feature map. Crossmap Dropout tries to maintain this important correlation yet at the same time break the correlation between each adjacent pixel with respect to all feature maps by applying the same Dropout mask to all feature maps, so that all pixels or units in equivalent positions in each feature map will be either dropped or active during training. Our experiment with various benchmark datasets shows that our approaches provide better generalization than the regular Dropout. Moreover, our Biased Dropout takes faster time to converge during training phase, suggesting that assigning noise appropriately in hidden units can lead to an effective regularization. Copyright © 2018 Elsevier Ltd. All rights reserved.

Non-invasive classification of gas-liquid two-phase horizontal flow regimes using an ultrasonic Doppler sensor and a neural network

NASA Astrophysics Data System (ADS)

Musa Abbagoni, Baba; Yeung, Hoi

2016-08-01

The identification of flow pattern is a key issue in multiphase flow which is encountered in the petrochemical industry. It is difficult to identify the gas-liquid flow regimes objectively with the gas-liquid two-phase flow. This paper presents the feasibility of a clamp-on instrument for an objective flow regime classification of two-phase flow using an ultrasonic Doppler sensor and an artificial neural network, which records and processes the ultrasonic signals reflected from the two-phase flow. Experimental data is obtained on a horizontal test rig with a total pipe length of 21 m and 5.08 cm internal diameter carrying air-water two-phase flow under slug, elongated bubble, stratified-wavy and, stratified flow regimes. Multilayer perceptron neural networks (MLPNNs) are used to develop the classification model. The classifier requires features as an input which is representative of the signals. Ultrasound signal features are extracted by applying both power spectral density (PSD) and discrete wavelet transform (DWT) methods to the flow signals. A classification scheme of ‘1-of-C coding method for classification’ was adopted to classify features extracted into one of four flow regime categories. To improve the performance of the flow regime classifier network, a second level neural network was incorporated by using the output of a first level networks feature as an input feature. The addition of the two network models provided a combined neural network model which has achieved a higher accuracy than single neural network models. Classification accuracies are evaluated in the form of both the PSD and DWT features. The success rates of the two models are: (1) using PSD features, the classifier missed 3 datasets out of 24 test datasets of the classification and scored 87.5% accuracy; (2) with the DWT features, the network misclassified only one data point and it was able to classify the flow patterns up to 95.8% accuracy. This approach has demonstrated the success of a clamp-on ultrasound sensor for flow regime classification that would be possible in industry practice. It is considerably more promising than other techniques as it uses a non-invasive and non-radioactive sensor.

75 FR 2433 - Special Conditions: Boeing Model 747-8/-8F Airplanes, Systems and Data Networks Security...

Federal Register 2010, 2011, 2012, 2013, 2014

2010-01-15

... design features associated with the architecture and connectivity capabilities of the airplane's computer... novel or unusual design features: digital systems architecture composed of several connected networks. The architecture and network configuration may be used for, or interfaced with, a diverse set of...

A Network-Based Classification Model for Deriving Novel Drug-Disease Associations and Assessing Their Molecular Actions

PubMed Central

Oh, Min; Ahn, Jaegyoon; Yoon, Youngmi

2014-01-01

The growing number and variety of genetic network datasets increases the feasibility of understanding how drugs and diseases are associated at the molecular level. Properly selected features of the network representations of existing drug-disease associations can be used to infer novel indications of existing drugs. To find new drug-disease associations, we generated an integrative genetic network using combinations of interactions, including protein-protein interactions and gene regulatory network datasets. Within this network, network adjacencies of drug-drug and disease-disease were quantified using a scored path between target sets of them. Furthermore, the common topological module of drugs or diseases was extracted, and thereby the distance between topological drug-module and disease (or disease-module and drug) was quantified. These quantified scores were used as features for the prediction of novel drug-disease associations. Our classifiers using Random Forest, Multilayer Perceptron and C4.5 showed a high specificity and sensitivity (AUC score of 0.855, 0.828 and 0.797 respectively) in predicting novel drug indications, and displayed a better performance than other methods with limited drug and disease properties. Our predictions and current clinical trials overlap significantly across the different phases of drug development. We also identified and visualized the topological modules of predicted drug indications for certain types of cancers, and for Alzheimer’s disease. Within the network, those modules show potential pathways that illustrate the mechanisms of new drug indications, including propranolol as a potential anticancer agent and telmisartan as treatment for Alzheimer’s disease. PMID:25356910

Changes in task-based effective connectivity in language networks following rehabilitation in post-stroke patients with aphasia

PubMed Central

Kiran, Swathi; Meier, Erin L.; Kapse, Kushal J.; Glynn, Peter A.

2015-01-01

In this study, we examined regions in the left and right hemisphere language network that were altered in terms of the underlying neural activation and effective connectivity subsequent to language rehabilitation. Eight persons with chronic post-stroke aphasia and eight normal controls participated in the current study. Patients received a 10 week semantic feature-based rehabilitation program to improve their skills. Therapy was provided on atypical examples of one trained category while two control categories were monitored; the categories were counterbalanced across patients. In each fMRI session, two experimental tasks were conducted: (a) picture naming and (b) semantic feature verification of trained and untrained categories. Analysis of treatment effect sizes revealed that all patients showed greater improvements on the trained category relative to untrained categories. Results from this study show remarkable patterns of consistency despite the inherent variability in lesion size and activation patterns across patients. Across patients, activation that emerged as a function of rehabilitation on the trained category included bilateral IFG, bilateral SFG, LMFG, and LPCG for picture naming; and bilateral IFG, bilateral MFG, LSFG, and bilateral MTG for semantic feature verification. Analysis of effective connectivity using Dynamic Causal Modeling (DCM) indicated that LIFG was the consistently significantly modulated region after rehabilitation across participants. These results indicate that language networks in patients with aphasia resemble normal language control networks and that this similarity is accentuated by rehabilitation. PMID:26106314

Neural network classification of sweet potato embryos

NASA Astrophysics Data System (ADS)

Molto, Enrique; Harrell, Roy C.

1993-05-01

Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

Pre-trained convolutional neural networks as feature extractors for tuberculosis detection.

PubMed

Lopes, U K; Valiati, J F

2017-10-01

It is estimated that in 2015, approximately 1.8 million people infected by tuberculosis died, most of them in developing countries. Many of those deaths could have been prevented if the disease had been detected at an earlier stage, but the most advanced diagnosis methods are still cost prohibitive for mass adoption. One of the most popular tuberculosis diagnosis methods is the analysis of frontal thoracic radiographs; however, the impact of this method is diminished by the need for individual analysis of each radiography by properly trained radiologists. Significant research can be found on automating diagnosis by applying computational techniques to medical images, thereby eliminating the need for individual image analysis and greatly diminishing overall costs. In addition, recent improvements on deep learning accomplished excellent results classifying images on diverse domains, but its application for tuberculosis diagnosis remains limited. Thus, the focus of this work is to produce an investigation that will advance the research in the area, presenting three proposals to the application of pre-trained convolutional neural networks as feature extractors to detect the disease. The proposals presented in this work are implemented and compared to the current literature. The obtained results are competitive with published works demonstrating the potential of pre-trained convolutional networks as medical image feature extractors. Copyright © 2017 Elsevier Ltd. All rights reserved.

Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality.

PubMed

Lee, Christine K; Hofer, Ira; Gabel, Eilon; Baldi, Pierre; Cannesson, Maxime

2018-04-17

The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality. The data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index. In-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99). Deep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.

From fuzzy recurrence plots to scalable recurrence networks of time series

NASA Astrophysics Data System (ADS)

Pham, Tuan D.

2017-04-01

Recurrence networks, which are derived from recurrence plots of nonlinear time series, enable the extraction of hidden features of complex dynamical systems. Because fuzzy recurrence plots are represented as grayscale images, this paper presents a variety of texture features that can be extracted from fuzzy recurrence plots. Based on the notion of fuzzy recurrence plots, defuzzified, undirected, and unweighted recurrence networks are introduced. Network measures can be computed for defuzzified recurrence networks that are scalable to meet the demand for the network-based analysis of big data.

Segmentation of retinal blood vessels using artificial neural networks for early detection of diabetic retinopathy

NASA Astrophysics Data System (ADS)

Mann, Kulwinder S.; Kaur, Sukhpreet

2017-06-01

There are various eye diseases in the patients suffering from the diabetes which includes Diabetic Retinopathy, Glaucoma, Hypertension etc. These all are the most common sight threatening eye diseases due to the changes in the blood vessel structure. The proposed method using supervised methods concluded that the segmentation of the retinal blood vessels can be performed accurately using neural networks training. It uses features which include Gray level features; Moment Invariant based features, Gabor filtering, Intensity feature, Vesselness feature for feature vector computation. Then the feature vector is calculated using only the prominent features.

Evolutionary optimization of radial basis function classifiers for data mining applications.

PubMed

Buchtala, Oliver; Klimek, Manuel; Sick, Bernhard

2005-10-01

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. That is, appropriate input features of the classifier must be selected from a given (and often large) set of possible features and structure parameters of the classifier must be adapted with respect to these features and a given data set. This paper describes an evolutionary algorithm (EA) that performs feature and model selection simultaneously for radial basis function (RBF) classifiers. In order to reduce the optimization effort, various techniques are integrated that accelerate and improve the EA significantly: hybrid training of RBF networks, lazy evaluation, consideration of soft constraints by means of penalty terms, and temperature-based adaptive control of the EA. The feasibility and the benefits of the approach are demonstrated by means of four data mining problems: intrusion detection in computer networks, biometric signature verification, customer acquisition with direct marketing methods, and optimization of chemical production processes. It is shown that, compared to earlier EA-based RBF optimization techniques, the runtime is reduced by up to 99% while error rates are lowered by up to 86%, depending on the application. The algorithm is independent of specific applications so that many ideas and solutions can be transferred to other classifier paradigms.

Deciphering microbial interactions and detecting keystone species with co-occurrence networks

PubMed Central

Berry, David; Widder, Stefanie

2014-01-01

Co-occurrence networks produced from microbial survey sequencing data are frequently used to identify interactions between community members. While this approach has potential to reveal ecological processes, it has been insufficiently validated due to the technical limitations inherent in studying complex microbial ecosystems. Here, we simulate multi-species microbial communities with known interaction patterns using generalized Lotka-Volterra dynamics. We then construct co-occurrence networks and evaluate how well networks reveal the underlying interactions and how experimental and ecological parameters can affect network inference and interpretation. We find that co-occurrence networks can recapitulate interaction networks under certain conditions, but that they lose interpretability when the effects of habitat filtering become significant. We demonstrate that networks suffer from local hot spots of spurious correlation in the neighborhood of hub species that engage in many interactions. We also identify topological features associated with keystone species in co-occurrence networks. This study provides a substantiated framework to guide environmental microbiologists in the construction and interpretation of co-occurrence networks from microbial survey datasets. PMID:24904535

Variogram-based feature extraction for neural network recognition of logos

NASA Astrophysics Data System (ADS)

Pham, Tuan D.

2003-03-01

This paper presents a new approach for extracting spatial features of images based on the theory of regionalized variables. These features can be effectively used for automatic recognition of logo images using neural networks. Experimental results on a public-domain logo database show the effectiveness of the proposed approach.

Regional GABA Concentrations Modulate Inter-network Resting-state Functional Connectivity.

PubMed

Chen, Xi; Fan, Xiaoying; Hu, Yuzheng; Zuo, Chun; Whitfield-Gabrieli, Susan; Holt, Daphne; Gong, Qiyong; Yang, Yihong; Pizzagalli, Diego A; Du, Fei; Ongur, Dost

2018-03-28

Coordinated activity within and differential activity between large-scale neuronal networks such as the default mode network (DMN) and the control network (CN) is a critical feature of brain organization. The CN usually exhibits activations in response to cognitive tasks while the DMN shows deactivations; in addition, activity between the two networks is anti-correlated at rest. To address this issue, we used functional MRI to measure whole-brain BOLD signal during resting-state and task-evoked conditions, and MR spectroscopy (MRS) to quantify GABA and glutamate concentrations, in nodes within the DMN and CN (MPFC and DLPFC, respectively) in 19 healthy individuals at 3 Tesla. We found that GABA concentrations in the MPFC were significantly associated with DMN deactivation during a working memory task and with anti-correlation between DMN and CN at rest and during task performance, while GABA concentrations in the DLPFC weakly modulated DMN-CN anti-correlation in the opposite direction. Highlighting specificity, glutamate played a less significant role related to brain activity. These findings indicate that GABA in the MPFC is potentially involved in orchestrating between-network brain activity at rest and during task performance.

Engineering microbial phenotypes through rewiring of genetic networks

PubMed Central

Rodrigues, Rui T.L.; Lee, Sangjin; Haines, Matthew

2017-01-01

Abstract The ability to program cellular behaviour is a major goal of synthetic biology, with applications in health, agriculture and chemicals production. Despite efforts to build ‘orthogonal’ systems, interactions between engineered genetic circuits and the endogenous regulatory network of a host cell can have a significant impact on desired functionality. We have developed a strategy to rewire the endogenous cellular regulatory network of yeast to enhance compatibility with synthetic protein and metabolite production. We found that introducing novel connections in the cellular regulatory network enabled us to increase the production of heterologous proteins and metabolites. This strategy is demonstrated in yeast strains that show significantly enhanced heterologous protein expression and higher titers of terpenoid production. Specifically, we found that the addition of transcriptional regulation between free radical induced signalling and nitrogen regulation provided robust improvement of protein production. Assessment of rewired networks revealed the importance of key topological features such as high betweenness centrality. The generation of rewired transcriptional networks, selection for specific phenotypes, and analysis of resulting library members is a powerful tool for engineering cellular behavior and may enable improved integration of heterologous protein and metabolite pathways. PMID:28369627

deepNF: Deep network fusion for protein function prediction.

PubMed

Gligorijevic, Vladimir; Barot, Meet; Bonneau, Richard

2018-06-01

The prevalence of high-throughput experimental methods has resulted in an abundance of large-scale molecular and functional interaction networks. The connectivity of these networks provides a rich source of information for inferring functional annotations for genes and proteins. An important challenge has been to develop methods for combining these heterogeneous networks to extract useful protein feature representations for function prediction. Most of the existing approaches for network integration use shallow models that encounter difficulty in capturing complex and highly-nonlinear network structures. Thus, we propose deepNF, a network fusion method based on Multimodal Deep Autoencoders to extract high-level features of proteins from multiple heterogeneous interaction networks. We apply this method to combine STRING networks to construct a common low-dimensional representation containing high-level protein features. We use separate layers for different network types in the early stages of the multimodal autoencoder, later connecting all the layers into a single bottleneck layer from which we extract features to predict protein function. We compare the cross-validation and temporal holdout predictive performance of our method with state-of-the-art methods, including the recently proposed method Mashup. Our results show that our method outperforms previous methods for both human and yeast STRING networks. We also show substantial improvement in the performance of our method in predicting GO terms of varying type and specificity. deepNF is freely available at: https://github.com/VGligorijevic/deepNF. vgligorijevic@flatironinstitute.org, rb133@nyu.edu. Supplementary data are available at Bioinformatics online.

Conditional Variational Autoencoder for Prediction and Feature Recovery Applied to Intrusion Detection in IoT.

PubMed

Lopez-Martin, Manuel; Carro, Belen; Sanchez-Esguevillas, Antonio; Lloret, Jaime

2017-08-26

The purpose of a Network Intrusion Detection System is to detect intrusive, malicious activities or policy violations in a host or host's network. In current networks, such systems are becoming more important as the number and variety of attacks increase along with the volume and sensitiveness of the information exchanged. This is of particular interest to Internet of Things networks, where an intrusion detection system will be critical as its economic importance continues to grow, making it the focus of future intrusion attacks. In this work, we propose a new network intrusion detection method that is appropriate for an Internet of Things network. The proposed method is based on a conditional variational autoencoder with a specific architecture that integrates the intrusion labels inside the decoder layers. The proposed method is less complex than other unsupervised methods based on a variational autoencoder and it provides better classification results than other familiar classifiers. More important, the method can perform feature reconstruction, that is, it is able to recover missing features from incomplete training datasets. We demonstrate that the reconstruction accuracy is very high, even for categorical features with a high number of distinct values. This work is unique in the network intrusion detection field, presenting the first application of a conditional variational autoencoder and providing the first algorithm to perform feature recovery.

Conditional Variational Autoencoder for Prediction and Feature Recovery Applied to Intrusion Detection in IoT

PubMed Central

Carro, Belen; Sanchez-Esguevillas, Antonio

2017-01-01

The purpose of a Network Intrusion Detection System is to detect intrusive, malicious activities or policy violations in a host or host’s network. In current networks, such systems are becoming more important as the number and variety of attacks increase along with the volume and sensitiveness of the information exchanged. This is of particular interest to Internet of Things networks, where an intrusion detection system will be critical as its economic importance continues to grow, making it the focus of future intrusion attacks. In this work, we propose a new network intrusion detection method that is appropriate for an Internet of Things network. The proposed method is based on a conditional variational autoencoder with a specific architecture that integrates the intrusion labels inside the decoder layers. The proposed method is less complex than other unsupervised methods based on a variational autoencoder and it provides better classification results than other familiar classifiers. More important, the method can perform feature reconstruction, that is, it is able to recover missing features from incomplete training datasets. We demonstrate that the reconstruction accuracy is very high, even for categorical features with a high number of distinct values. This work is unique in the network intrusion detection field, presenting the first application of a conditional variational autoencoder and providing the first algorithm to perform feature recovery. PMID:28846608

NIMEFI: Gene Regulatory Network Inference using Multiple Ensemble Feature Importance Algorithms

PubMed Central

Ruyssinck, Joeri; Huynh-Thu, Vân Anh; Geurts, Pierre; Dhaene, Tom; Demeester, Piet; Saeys, Yvan

2014-01-01

One of the long-standing open challenges in computational systems biology is the topology inference of gene regulatory networks from high-throughput omics data. Recently, two community-wide efforts, DREAM4 and DREAM5, have been established to benchmark network inference techniques using gene expression measurements. In these challenges the overall top performer was the GENIE3 algorithm. This method decomposes the network inference task into separate regression problems for each gene in the network in which the expression values of a particular target gene are predicted using all other genes as possible predictors. Next, using tree-based ensemble methods, an importance measure for each predictor gene is calculated with respect to the target gene and a high feature importance is considered as putative evidence of a regulatory link existing between both genes. The contribution of this work is twofold. First, we generalize the regression decomposition strategy of GENIE3 to other feature importance methods. We compare the performance of support vector regression, the elastic net, random forest regression, symbolic regression and their ensemble variants in this setting to the original GENIE3 algorithm. To create the ensemble variants, we propose a subsampling approach which allows us to cast any feature selection algorithm that produces a feature ranking into an ensemble feature importance algorithm. We demonstrate that the ensemble setting is key to the network inference task, as only ensemble variants achieve top performance. As second contribution, we explore the effect of using rankwise averaged predictions of multiple ensemble algorithms as opposed to only one. We name this approach NIMEFI (Network Inference using Multiple Ensemble Feature Importance algorithms) and show that this approach outperforms all individual methods in general, although on a specific network a single method can perform better. An implementation of NIMEFI has been made publicly available. PMID:24667482

A Novel Hybrid Classification Model of Genetic Algorithms, Modified k-Nearest Neighbor and Developed Backpropagation Neural Network

PubMed Central

Salari, Nader; Shohaimi, Shamarina; Najafi, Farid; Nallappan, Meenakshii; Karishnarajah, Isthrinayagy

2014-01-01

Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the proposed model in terms of classification accuracy is desirable, promising, and competitive to the existing state-of-the-art classification models. PMID:25419659

Temporal efficiency evaluation and small-worldness characterization in temporal networks

PubMed Central

Dai, Zhongxiang; Chen, Yu; Li, Junhua; Fam, Johnson; Bezerianos, Anastasios; Sun, Yu

2016-01-01

Numerous real-world systems can be modeled as networks. To date, most network studies have been conducted assuming stationary network characteristics. Many systems, however, undergo topological changes over time. Temporal networks, which incorporate time into conventional network models, are therefore more accurate representations of such dynamic systems. Here, we introduce a novel generalized analytical framework for temporal networks, which enables 1) robust evaluation of the efficiency of temporal information exchange using two new network metrics and 2) quantitative inspection of the temporal small-worldness. Specifically, we define new robust temporal network efficiency measures by incorporating the time dependency of temporal distance. We propose a temporal regular network model, and based on this plus the redefined temporal efficiency metrics and widely used temporal random network models, we introduce a quantitative approach for identifying temporal small-world architectures (featuring high temporal network efficiency both globally and locally). In addition, within this framework, we can uncover network-specific dynamic structures. Applications to brain networks, international trade networks, and social networks reveal prominent temporal small-world properties with distinct dynamic network structures. We believe that the framework can provide further insight into dynamic changes in the network topology of various real-world systems and significantly promote research on temporal networks. PMID:27682314

Temporal efficiency evaluation and small-worldness characterization in temporal networks

NASA Astrophysics Data System (ADS)

Dai, Zhongxiang; Chen, Yu; Li, Junhua; Fam, Johnson; Bezerianos, Anastasios; Sun, Yu

2016-09-01

Numerous real-world systems can be modeled as networks. To date, most network studies have been conducted assuming stationary network characteristics. Many systems, however, undergo topological changes over time. Temporal networks, which incorporate time into conventional network models, are therefore more accurate representations of such dynamic systems. Here, we introduce a novel generalized analytical framework for temporal networks, which enables 1) robust evaluation of the efficiency of temporal information exchange using two new network metrics and 2) quantitative inspection of the temporal small-worldness. Specifically, we define new robust temporal network efficiency measures by incorporating the time dependency of temporal distance. We propose a temporal regular network model, and based on this plus the redefined temporal efficiency metrics and widely used temporal random network models, we introduce a quantitative approach for identifying temporal small-world architectures (featuring high temporal network efficiency both globally and locally). In addition, within this framework, we can uncover network-specific dynamic structures. Applications to brain networks, international trade networks, and social networks reveal prominent temporal small-world properties with distinct dynamic network structures. We believe that the framework can provide further insight into dynamic changes in the network topology of various real-world systems and significantly promote research on temporal networks.

Features and heterogeneities in growing network models

NASA Astrophysics Data System (ADS)

Ferretti, Luca; Cortelezzi, Michele; Yang, Bin; Marmorini, Giacomo; Bianconi, Ginestra

2012-06-01

Many complex networks from the World Wide Web to biological networks grow taking into account the heterogeneous features of the nodes. The feature of a node might be a discrete quantity such as a classification of a URL document such as personal page, thematic website, news, blog, search engine, social network, etc., or the classification of a gene in a functional module. Moreover the feature of a node can be a continuous variable such as the position of a node in the embedding space. In order to account for these properties, in this paper we provide a generalization of growing network models with preferential attachment that includes the effect of heterogeneous features of the nodes. The main effect of heterogeneity is the emergence of an “effective fitness” for each class of nodes, determining the rate at which nodes acquire new links. The degree distribution exhibits a multiscaling behavior analogous to the the fitness model. This property is robust with respect to variations in the model, as long as links are assigned through effective preferential attachment. Beyond the degree distribution, in this paper we give a full characterization of the other relevant properties of the model. We evaluate the clustering coefficient and show that it disappears for large network size, a property shared with the Barabási-Albert model. Negative degree correlations are also present in this class of models, along with nontrivial mixing patterns among features. We therefore conclude that both small clustering coefficients and disassortative mixing are outcomes of the preferential attachment mechanism in general growing networks.

Learning representations for the early detection of sepsis with deep neural networks.

PubMed

Kam, Hye Jin; Kim, Ha Young

2017-10-01

Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

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

Ivanov, Ilia N.; Simpson, John T.

A method of preparing a network comprises disposing a solution comprising particulate materials in a solvent onto a superhydrophobic surface comprising a plurality of superhydrophobic features and interfacial areas between the superhydrophobic features. The plurality of superhydrophobic features has a water contact angle of at least about 150.degree.. The method of preparing the network also comprises removing the solvent from the solution of the particulate materials, and forming a network of the particulate materials in the interfacial areas, the particulate materials receding to the interfacial areas as the solvent is removed.

Retina Image Screening and Analysis Software Version 2.0

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

Tobin, Jr., Kenneth W.; Karnowski, Thomas P.; Aykac, Deniz

2009-04-01

The software allows physicians or researchers to ground-truth images of retinas, identifying key physiological features and lesions that are indicative of disease. The software features methods to automatically detect the physiological features and lesions. The software contains code to measure the quality of images received from a telemedicine network; create and populate a database for a telemedicine network; review and report the diagnosis of a set of images; and also contains components to transmit images from a Zeiss camera to the network through SFTP.

Generative adversarial networks recover features in astrophysical images of galaxies beyond the deconvolution limit

NASA Astrophysics Data System (ADS)

Schawinski, Kevin; Zhang, Ce; Zhang, Hantian; Fowler, Lucas; Santhanam, Gokula Krishnan

2017-05-01

Observations of astrophysical objects such as galaxies are limited by various sources of random and systematic noise from the sky background, the optical system of the telescope and the detector used to record the data. Conventional deconvolution techniques are limited in their ability to recover features in imaging data by the Shannon-Nyquist sampling theorem. Here, we train a generative adversarial network (GAN) on a sample of 4550 images of nearby galaxies at 0.01 < z < 0.02 from the Sloan Digital Sky Survey and conduct 10× cross-validation to evaluate the results. We present a method using a GAN trained on galaxy images that can recover features from artificially degraded images with worse seeing and higher noise than the original with a performance that far exceeds simple deconvolution. The ability to better recover detailed features such as galaxy morphology from low signal to noise and low angular resolution imaging data significantly increases our ability to study existing data sets of astrophysical objects as well as future observations with observatories such as the Large Synoptic Sky Telescope (LSST) and the Hubble and James Webb space telescopes.

Objects Classification by Learning-Based Visual Saliency Model and Convolutional Neural Network.

PubMed

Li, Na; Zhao, Xinbo; Yang, Yongjia; Zou, Xiaochun

2016-01-01

Humans can easily classify different kinds of objects whereas it is quite difficult for computers. As a hot and difficult problem, objects classification has been receiving extensive interests with broad prospects. Inspired by neuroscience, deep learning concept is proposed. Convolutional neural network (CNN) as one of the methods of deep learning can be used to solve classification problem. But most of deep learning methods, including CNN, all ignore the human visual information processing mechanism when a person is classifying objects. Therefore, in this paper, inspiring the completed processing that humans classify different kinds of objects, we bring forth a new classification method which combines visual attention model and CNN. Firstly, we use the visual attention model to simulate the processing of human visual selection mechanism. Secondly, we use CNN to simulate the processing of how humans select features and extract the local features of those selected areas. Finally, not only does our classification method depend on those local features, but also it adds the human semantic features to classify objects. Our classification method has apparently advantages in biology. Experimental results demonstrated that our method made the efficiency of classification improve significantly.

Detection of Interictal Discharges With Convolutional Neural Networks Using Discrete Ordered Multichannel Intracranial EEG.

PubMed

Antoniades, Andreas; Spyrou, Loukianos; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid; Cheong Took, Clive

2017-12-01

Detection algorithms for electroencephalography (EEG) data, especially in the field of interictal epileptiform discharge (IED) detection, have traditionally employed handcrafted features, which utilized specific characteristics of neural responses. Although these algorithms achieve high accuracy, mere detection of an IED holds little clinical significance. In this paper, we consider deep learning for epileptic subjects to accommodate automatic feature generation from intracranial EEG data, while also providing clinical insight. Convolutional neural networks are trained in a subject independent fashion to demonstrate how meaningful features are automatically learned in a hierarchical process. We illustrate how the convolved filters in the deepest layers provide insight toward the different types of IEDs within the group, as confirmed by our expert clinicians. The morphology of the IEDs found in filters can help evaluate the treatment of a patient. To improve the learning of the deep model, moderately different score classes are utilized as opposed to binary IED and non-IED labels. The resulting model achieves state-of-the-art classification performance and is also invariant to time differences between the IEDs. This paper suggests that deep learning is suitable for automatic feature generation from intracranial EEG data, while also providing insight into the data.

Organization of excitable dynamics in hierarchical biological networks.

PubMed

Müller-Linow, Mark; Hilgetag, Claus C; Hütt, Marc-Thorsten

2008-09-26

This study investigates the contributions of network topology features to the dynamic behavior of hierarchically organized excitable networks. Representatives of different types of hierarchical networks as well as two biological neural networks are explored with a three-state model of node activation for systematically varying levels of random background network stimulation. The results demonstrate that two principal topological aspects of hierarchical networks, node centrality and network modularity, correlate with the network activity patterns at different levels of spontaneous network activation. The approach also shows that the dynamic behavior of the cerebral cortical systems network in the cat is dominated by the network's modular organization, while the activation behavior of the cellular neuronal network of Caenorhabditis elegans is strongly influenced by hub nodes. These findings indicate the interaction of multiple topological features and dynamic states in the function of complex biological networks.

Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System.

PubMed

Kwon, Yea-Hoon; Shin, Sae-Byuk; Kim, Shin-Dug

2018-04-30

The purpose of this study is to improve human emotional classification accuracy using a convolution neural networks (CNN) model and to suggest an overall method to classify emotion based on multimodal data. We improved classification performance by combining electroencephalogram (EEG) and galvanic skin response (GSR) signals. GSR signals are preprocessed using by the zero-crossing rate. Sufficient EEG feature extraction can be obtained through CNN. Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters. The EEG signal is preprocessed prior to convolution by a wavelet transform while considering time and frequency simultaneously. We use a database for emotion analysis using the physiological signals open dataset to verify the proposed process, achieving 73.4% accuracy, showing significant performance improvement over the current best practice models.

An effective convolutional neural network model for Chinese sentiment analysis

NASA Astrophysics Data System (ADS)

Zhang, Yu; Chen, Mengdong; Liu, Lianzhong; Wang, Yadong

2017-06-01

Nowadays microblog is getting more and more popular. People are increasingly accustomed to expressing their opinions on Twitter, Facebook and Sina Weibo. Sentiment analysis of microblog has received significant attention, both in academia and in industry. So far, Chinese microblog exploration still needs lots of further work. In recent years CNN has also been used to deal with NLP tasks, and already achieved good results. However, these methods ignore the effective use of a large number of existing sentimental resources. For this purpose, we propose a Lexicon-based Sentiment Convolutional Neural Networks (LSCNN) model focus on Weibo's sentiment analysis, which combines two CNNs, trained individually base on sentiment features and word embedding, at the fully connected hidden layer. The experimental results show that our model outperforms the CNN model only with word embedding features on microblog sentiment analysis task.

Dynamics of feature categorization.

PubMed

Martí, Daniel; Rinzel, John

2013-01-01

In visual and auditory scenes, we are able to identify shared features among sensory objects and group them according to their similarity. This grouping is preattentive and fast and is thought of as an elementary form of categorization by which objects sharing similar features are clustered in some abstract perceptual space. It is unclear what neuronal mechanisms underlie this fast categorization. Here we propose a neuromechanistic model of fast feature categorization based on the framework of continuous attractor networks. The mechanism for category formation does not rely on learning and is based on biologically plausible assumptions, for example, the existence of populations of neurons tuned to feature values, feature-specific interactions, and subthreshold-evoked responses upon the presentation of single objects. When the network is presented with a sequence of stimuli characterized by some feature, the network sums the evoked responses and provides a running estimate of the distribution of features in the input stream. If the distribution of features is structured into different components or peaks (i.e., is multimodal), recurrent excitation amplifies the response of activated neurons, and categories are singled out as emerging localized patterns of elevated neuronal activity (bumps), centered at the centroid of each cluster. The emergence of bump states through sequential, subthreshold activation and the dependence on input statistics is a novel application of attractor networks. We show that the extraction and representation of multiple categories are facilitated by the rich attractor structure of the network, which can sustain multiple stable activity patterns for a robust range of connectivity parameters compatible with cortical physiology.

Heuristic urban transportation network design method, a multilayer coevolution approach

NASA Astrophysics Data System (ADS)

Ding, Rui; Ujang, Norsidah; Hamid, Hussain bin; Manan, Mohd Shahrudin Abd; Li, Rong; Wu, Jianjun

2017-08-01

The design of urban transportation networks plays a key role in the urban planning process, and the coevolution of urban networks has recently garnered significant attention in literature. However, most of these recent articles are based on networks that are essentially planar. In this research, we propose a heuristic multilayer urban network coevolution model with lower layer network and upper layer network that are associated with growth and stimulate one another. We first use the relative neighbourhood graph and the Gabriel graph to simulate the structure of rail and road networks, respectively. With simulation we find that when a specific number of nodes are added, the total travel cost ratio between an expanded network and the initial lower layer network has the lowest value. The cooperation strength Λ and the changeable parameter average operation speed ratio Θ show that transit users' route choices change dramatically through the coevolution process and that their decisions, in turn, affect the multilayer network structure. We also note that the simulated relation between the Gini coefficient of the betweenness centrality, Θ and Λ have an optimal point for network design. This research could inspire the analysis of urban network topology features and the assessment of urban growth trends.

How does network structure affect partnerships for promoting physical activity? Evidence from Brazil and Colombia.

PubMed

Parra, Diana C; Dauti, Marsela; Harris, Jenine K; Reyes, Lissette; Malta, Deborah C; Brownson, Ross C; Quintero, Mario A; Pratt, Michael

2011-11-01

The objective of this study was to describe the network structure and factors associated with collaboration in two networks that promote physical activity (PA) in Brazil and Colombia. Organizations that focus on studying and promoting PA in Brazil (35) and Colombia (53) were identified using a modified one-step reputational snowball sampling process. Participants completed an on-line survey between December 2008 and March 2009 for the Brazil network, and between April and June 2009 for the Colombia network. Network stochastic modeling was used to investigate the likelihood of reported inter-organizational collaboration. While structural features of networks were significant predictors of collaboration within each network, the coefficients and other network characteristics differed. Brazil's PA network was decentralized with a larger number of shared partnerships. Colombia's PA network was centralized and collaboration was influenced by perceived importance of peer organizations. On average, organizations in the PA network of Colombia reported facing more barriers (1.5 vs. 2.5 barriers) for collaboration. Future studies should focus on how these different network structures affect the implementation and uptake of evidence-based PA interventions. Copyright © 2011 Elsevier Ltd. All rights reserved.

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

Neural network modeling of a dolphin's sonar discrimination capabilities.

PubMed

Au, W W; Andersen, L N; Rasmussen, A R; Roitblat, H L; Nachtigall, P E

1995-07-01

The capability of an echolocating dolphin to discriminate differences in the wall thickness of cylinders was previously modeled by a counterpropagation neural network using only spectral information from the echoes. In this study, both time and frequency information were used to model the dolphin discrimination capabilities. Echoes from the same cylinders were digitized using a broadband simulated dolphin sonar signal with the transducer mounted on the dolphin's pen. The echoes were filtered by a bank of continuous constant-Q digital filters and the energy from each filter was computed in time increments of 1/bandwidth. Echo features of the standard and each comparison target were analyzed in pairs by a counterpropagation neural network, a backpropagation neural network, and a model using Euclidean distance measures. The backpropagation network performed better than both the counterpropagation network, and the Euclidean model, using either spectral-only features or combined temporal and spectral features. All models performed better using features containing both temporal and spectral information. The backpropagation network was able to perform better than the dolphins for noise-free echoes with Q values as low as 2 and 3. For a Q of 2, only temporal information was available. However, with noisy data, the network required a Q of 8 in order to perform as well as the dolphin.

Feature pruning by upstream drainage area to support automated generalization of the United States National Hydrography Dataset

USGS Publications Warehouse

Stanislawski, L.V.

2009-01-01

The United States Geological Survey has been researching generalization approaches to enable multiple-scale display and delivery of geographic data. This paper presents automated methods to prune network and polygon features of the United States high-resolution National Hydrography Dataset (NHD) to lower resolutions. Feature-pruning rules, data enrichment, and partitioning are derived from knowledge of surface water, the NHD model, and associated feature specification standards. Relative prominence of network features is estimated from upstream drainage area (UDA). Network and polygon features are pruned by UDA and NHD reach code to achieve a drainage density appropriate for any less detailed map scale. Data partitioning maintains local drainage density variations that characterize the terrain. For demonstration, a 48 subbasin area of 1:24 000-scale NHD was pruned to 1:100 000-scale (100 K) and compared to a benchmark, the 100 K NHD. The coefficient of line correspondence (CLC) is used to evaluate how well pruned network features match the benchmark network. CLC values of 0.82 and 0.77 result from pruning with and without partitioning, respectively. The number of polygons that remain after pruning is about seven times that of the benchmark, but the area covered by the polygons that remain after pruning is only about 10% greater than the area covered by benchmark polygons. ?? 2009.

A Study for the Feature Selection to Identify GIEMSA-Stained Human Chromosomes Based on Artificial Neural Network

DTIC Science & Technology

2001-10-25

neural network (ANN) has been adopted for the human chromosome classification. It is important to select optimum features for training neural network...Many studies for computer-based chromosome analysis have shown that it is possible to classify chromosomes into 24 subgroups. In addition, artificial

A Method for Predicting Protein Complexes from Dynamic Weighted Protein-Protein Interaction Networks.

PubMed

Liu, Lizhen; Sun, Xiaowu; Song, Wei; Du, Chao

2018-06-01

Predicting protein complexes from protein-protein interaction (PPI) network is of great significance to recognize the structure and function of cells. A protein may interact with different proteins under different time or conditions. Existing approaches only utilize static PPI network data that may lose much temporal biological information. First, this article proposed a novel method that combines gene expression data at different time points with traditional static PPI network to construct different dynamic subnetworks. Second, to further filter out the data noise, the semantic similarity based on gene ontology is regarded as the network weight together with the principal component analysis, which is introduced to deal with the weight computing by three traditional methods. Third, after building a dynamic PPI network, a predicting protein complexes algorithm based on "core-attachment" structural feature is applied to detect complexes from each dynamic subnetworks. Finally, it is revealed from the experimental results that our method proposed in this article performs well on detecting protein complexes from dynamic weighted PPI networks.

Plasticity-Driven Self-Organization under Topological Constraints Accounts for Non-random Features of Cortical Synaptic Wiring

PubMed Central

Miner, Daniel; Triesch, Jochen

2016-01-01

Understanding the structure and dynamics of cortical connectivity is vital to understanding cortical function. Experimental data strongly suggest that local recurrent connectivity in the cortex is significantly non-random, exhibiting, for example, above-chance bidirectionality and an overrepresentation of certain triangular motifs. Additional evidence suggests a significant distance dependency to connectivity over a local scale of a few hundred microns, and particular patterns of synaptic turnover dynamics, including a heavy-tailed distribution of synaptic efficacies, a power law distribution of synaptic lifetimes, and a tendency for stronger synapses to be more stable over time. Understanding how many of these non-random features simultaneously arise would provide valuable insights into the development and function of the cortex. While previous work has modeled some of the individual features of local cortical wiring, there is no model that begins to comprehensively account for all of them. We present a spiking network model of a rodent Layer 5 cortical slice which, via the interactions of a few simple biologically motivated intrinsic, synaptic, and structural plasticity mechanisms, qualitatively reproduces these non-random effects when combined with simple topological constraints. Our model suggests that mechanisms of self-organization arising from a small number of plasticity rules provide a parsimonious explanation for numerous experimentally observed non-random features of recurrent cortical wiring. Interestingly, similar mechanisms have been shown to endow recurrent networks with powerful learning abilities, suggesting that these mechanism are central to understanding both structure and function of cortical synaptic wiring. PMID:26866369

Clinical application of modified bag-of-features coupled with hybrid neural-based classifier in dengue fever classification using gene expression data.

PubMed

Chatterjee, Sankhadeep; Dey, Nilanjan; Shi, Fuqian; Ashour, Amira S; Fong, Simon James; Sen, Soumya

2018-04-01

Dengue fever detection and classification have a vital role due to the recent outbreaks of different kinds of dengue fever. Recently, the advancement in the microarray technology can be employed for such classification process. Several studies have established that the gene selection phase takes a significant role in the classifier performance. Subsequently, the current study focused on detecting two different variations, namely, dengue fever (DF) and dengue hemorrhagic fever (DHF). A modified bag-of-features method has been proposed to select the most promising genes in the classification process. Afterward, a modified cuckoo search optimization algorithm has been engaged to support the artificial neural (ANN-MCS) to classify the unknown subjects into three different classes namely, DF, DHF, and another class containing convalescent and normal cases. The proposed method has been compared with other three well-known classifiers, namely, multilayer perceptron feed-forward network (MLP-FFN), artificial neural network (ANN) trained with cuckoo search (ANN-CS), and ANN trained with PSO (ANN-PSO). Experiments have been carried out with different number of clusters for the initial bag-of-features-based feature selection phase. After obtaining the reduced dataset, the hybrid ANN-MCS model has been employed for the classification process. The results have been compared in terms of the confusion matrix-based performance measuring metrics. The experimental results indicated a highly statistically significant improvement with the proposed classifier over the traditional ANN-CS model.

Machine Learning Classification Combining Multiple Features of A Hyper-Network of fMRI Data in Alzheimer's Disease

PubMed Central

Guo, Hao; Zhang, Fan; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

Exploring functional interactions among various brain regions is helpful for understanding the pathological underpinnings of neurological disorders. Brain networks provide an important representation of those functional interactions, and thus are widely applied in the diagnosis and classification of neurodegenerative diseases. Many mental disorders involve a sharp decline in cognitive ability as a major symptom, which can be caused by abnormal connectivity patterns among several brain regions. However, conventional functional connectivity networks are usually constructed based on pairwise correlations among different brain regions. This approach ignores higher-order relationships, and cannot effectively characterize the high-order interactions of many brain regions working together. Recent neuroscience research suggests that higher-order relationships between brain regions are important for brain network analysis. Hyper-networks have been proposed that can effectively represent the interactions among brain regions. However, this method extracts the local properties of brain regions as features, but ignores the global topology information, which affects the evaluation of network topology and reduces the performance of the classifier. This problem can be compensated by a subgraph feature-based method, but it is not sensitive to change in a single brain region. Considering that both of these feature extraction methods result in the loss of information, we propose a novel machine learning classification method that combines multiple features of a hyper-network based on functional magnetic resonance imaging in Alzheimer's disease. The method combines the brain region features and subgraph features, and then uses a multi-kernel SVM for classification. This retains not only the global topological information, but also the sensitivity to change in a single brain region. To certify the proposed method, 28 normal control subjects and 38 Alzheimer's disease patients were selected to participate in an experiment. The proposed method achieved satisfactory classification accuracy, with an average of 91.60%. The abnormal brain regions included the bilateral precuneus, right parahippocampal gyrus\\hippocampus, right posterior cingulate gyrus, and other regions that are known to be important in Alzheimer's disease. Machine learning classification combining multiple features of a hyper-network of functional magnetic resonance imaging data in Alzheimer's disease obtains better classification performance. PMID:29209156

Disintegration of Sensorimotor Brain Networks in Schizophrenia.

PubMed

Kaufmann, Tobias; Skåtun, Kristina C; Alnæs, Dag; Doan, Nhat Trung; Duff, Eugene P; Tønnesen, Siren; Roussos, Evangelos; Ueland, Torill; Aminoff, Sofie R; Lagerberg, Trine V; Agartz, Ingrid; Melle, Ingrid S; Smith, Stephen M; Andreassen, Ole A; Westlye, Lars T

2015-11-01

Schizophrenia is a severe mental disorder associated with derogated function across various domains, including perception, language, motor, emotional, and social behavior. Due to its complex symptomatology, schizophrenia is often regarded a disorder of cognitive processes. Yet due to the frequent involvement of sensory and perceptual symptoms, it has been hypothesized that functional disintegration between sensory and cognitive processes mediates the heterogeneous and comprehensive schizophrenia symptomatology. Here, using resting-state functional magnetic resonance imaging in 71 patients and 196 healthy controls, we characterized the standard deviation in BOLD (blood-oxygen-level-dependent) signal amplitude and the functional connectivity across a range of functional brain networks. We investigated connectivity on the edge and node level using network modeling based on independent component analysis and utilized the brain network features in cross-validated classification procedures. Both amplitude and connectivity were significantly altered in patients, largely involving sensory networks. Reduced standard deviation in amplitude was observed in a range of visual, sensorimotor, and auditory nodes in patients. The strongest differences in connectivity implicated within-sensorimotor and sensorimotor-thalamic connections. Furthermore, sensory nodes displayed widespread alterations in the connectivity with higher-order nodes. We demonstrated robustness of effects across subjects by significantly classifying diagnostic group on the individual level based on cross-validated multivariate connectivity features. Taken together, the findings support the hypothesis of disintegrated sensory and cognitive processes in schizophrenia, and the foci of effects emphasize that targeting the sensory and perceptual domains may be key to enhance our understanding of schizophrenia pathophysiology. © The Author 2015. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Using graph theory to analyze biological networks

PubMed Central

2011-01-01

Understanding complex systems often requires a bottom-up analysis towards a systems biology approach. The need to investigate a system, not only as individual components but as a whole, emerges. This can be done by examining the elementary constituents individually and then how these are connected. The myriad components of a system and their interactions are best characterized as networks and they are mainly represented as graphs where thousands of nodes are connected with thousands of vertices. In this article we demonstrate approaches, models and methods from the graph theory universe and we discuss ways in which they can be used to reveal hidden properties and features of a network. This network profiling combined with knowledge extraction will help us to better understand the biological significance of the system. PMID:21527005

Differentiating malignant from benign breast tumors on acoustic radiation force impulse imaging using fuzzy-based neural networks with principle component analysis

NASA Astrophysics Data System (ADS)

Liu, Hsiao-Chuan; Chou, Yi-Hong; Tiu, Chui-Mei; Hsieh, Chi-Wen; Liu, Brent; Shung, K. Kirk

2017-03-01

Many modalities have been developed as screening tools for breast cancer. A new screening method called acoustic radiation force impulse (ARFI) imaging was created for distinguishing breast lesions based on localized tissue displacement. This displacement was quantitated by virtual touch tissue imaging (VTI). However, VTIs sometimes express reverse results to intensity information in clinical observation. In the study, a fuzzy-based neural network with principle component analysis (PCA) was proposed to differentiate texture patterns of malignant breast from benign tumors. Eighty VTIs were randomly retrospected. Thirty four patients were determined as BI-RADS category 2 or 3, and the rest of them were determined as BI-RADS category 4 or 5 by two leading radiologists. Morphological method and Boolean algebra were performed as the image preprocessing to acquire region of interests (ROIs) on VTIs. Twenty four quantitative parameters deriving from first-order statistics (FOS), fractal dimension and gray level co-occurrence matrix (GLCM) were utilized to analyze the texture pattern of breast tumors on VTIs. PCA was employed to reduce the dimension of features. Fuzzy-based neural network as a classifier to differentiate malignant from benign breast tumors. Independent samples test was used to examine the significance of the difference between benign and malignant breast tumors. The area Az under the receiver operator characteristic (ROC) curve, sensitivity, specificity and accuracy were calculated to evaluate the performance of the system. Most all of texture parameters present significant difference between malignant and benign tumors with p-value of less than 0.05 except the average of fractal dimension. For all features classified by fuzzy-based neural network, the sensitivity, specificity, accuracy and Az were 95.7%, 97.1%, 95% and 0.964, respectively. However, the sensitivity, specificity, accuracy and Az can be increased to 100%, 97.1%, 98.8% and 0.985, respectively if PCA was performed to reduce the dimension of features. Patterns of breast tumors on VTIs can effectively be recognized by quantitative texture parameters, and differentiated malignant from benign lesions by fuzzy-based neural network with PCA.

Neural networks in data analysis and modeling for detecting littoral oil-spills by airborne laser fluorosensor remote sensing

NASA Astrophysics Data System (ADS)

Lin, Bin; An, Jubai; Brown, Carl E.; Chen, Weiwei

2003-05-01

In this paper an artificial neural network (ANN) approach, which is based on flexible nonlinear models for a very broad class of transfer functions, is applied for multi-spectral data analysis and modeling of airborne laser fluorosensor in order to differentiate between classes of oil on water surface. We use three types of algorithm: Perceptron Network, Back-Propagation (B-P) Network and Self-Organizing feature Maps (SOM) Network. Using the data in form of 64-channel spectra as inputs, the ANN presents the analysis and estimation results of the oil type on the basis of the type of background materials as outputs. The ANN is trained and tested using sample data set to the network. The results of the above 3 types of network are compared in this paper. It is proved that the training has developed a network that not only fits the training data, but also fits real-world data that the network will process operationally. The ANN model would play a significant role in the ocean oil-spill identification in the future.

Bifurcations: Focal Points of Particle Adhesion in Microvascular Networks

PubMed Central

Prabhakarpandian, Balabhaskar; Wang, Yi; Rea-Ramsey, Angela; Sundaram, Shivshankar; Kiani, Mohammad F.; Pant, Kapil

2011-01-01

Objective Particle adhesion in vivo is dependent on microcirculation environment which features unique anatomical (bifurcations, tortuosity, cross-sectional changes) and physiological (complex hemodynamics) characteristics. The mechanisms behind these complex phenomena are not well understood. In this study, we used a recently developed in vitro model of microvascular networks, called Synthetic Microvascular Network, for characterizing particle adhesion patterns in the microcirculation. Methods Synthetic microvascular networks were fabricated using soft lithography processes followed by particle adhesion studies using avidin and biotin-conjugated microspheres. Particle adhesion patterns were subsequently analyzed using CFD based modeling. Results Experimental and modeling studies highlighted the complex and heterogeneous fluid flow patterns encountered by particles in microvascular networks resulting in significantly higher propensity of adhesion (>1.5X) near bifurcations compared to the branches of the microvascular networks. Conclusion Bifurcations are the focal points of particle adhesion in microvascular networks. Changing flow patterns and morphology near bifurcations are the primary factors controlling the preferential adhesion of functionalized particles in microvascular networks. Synthetic microvascular networks provide an in vitro framework for understanding particle adhesion. PMID:21418388

Detection and clustering of features in aerial images by neuron network-based algorithm

NASA Astrophysics Data System (ADS)

Vozenilek, Vit

2015-12-01

The paper presents the algorithm for detection and clustering of feature in aerial photographs based on artificial neural networks. The presented approach is not focused on the detection of specific topographic features, but on the combination of general features analysis and their use for clustering and backward projection of clusters to aerial image. The basis of the algorithm is a calculation of the total error of the network and a change of weights of the network to minimize the error. A classic bipolar sigmoid was used for the activation function of the neurons and the basic method of backpropagation was used for learning. To verify that a set of features is able to represent the image content from the user's perspective, the web application was compiled (ASP.NET on the Microsoft .NET platform). The main achievements include the knowledge that man-made objects in aerial images can be successfully identified by detection of shapes and anomalies. It was also found that the appropriate combination of comprehensive features that describe the colors and selected shapes of individual areas can be useful for image analysis.

Identifying protein complex by integrating characteristic of core-attachment into dynamic PPI network.

PubMed

Shen, Xianjun; Yi, Li; Jiang, Xingpeng; He, Tingting; Yang, Jincai; Xie, Wei; Hu, Po; Hu, Xiaohua

2017-01-01

How to identify protein complex is an important and challenging task in proteomics. It would make great contribution to our knowledge of molecular mechanism in cell life activities. However, the inherent organization and dynamic characteristic of cell system have rarely been incorporated into the existing algorithms for detecting protein complexes because of the limitation of protein-protein interaction (PPI) data produced by high throughput techniques. The availability of time course gene expression profile enables us to uncover the dynamics of molecular networks and improve the detection of protein complexes. In order to achieve this goal, this paper proposes a novel algorithm DCA (Dynamic Core-Attachment). It detects protein-complex core comprising of continually expressed and highly connected proteins in dynamic PPI network, and then the protein complex is formed by including the attachments with high adhesion into the core. The integration of core-attachment feature into the dynamic PPI network is responsible for the superiority of our algorithm. DCA has been applied on two different yeast dynamic PPI networks and the experimental results show that it performs significantly better than the state-of-the-art techniques in terms of prediction accuracy, hF-measure and statistical significance in biology. In addition, the identified complexes with strong biological significance provide potential candidate complexes for biologists to validate.

Research on NGN network control technology

NASA Astrophysics Data System (ADS)

Li, WenYao; Zhou, Fang; Wu, JianXue; Li, ZhiGuang

2004-04-01

Nowadays NGN (Next Generation Network) is the hotspot for discussion and research in IT section. The NGN core technology is the network control technology. The key goal of NGN is to realize the network convergence and evolution. Referring to overlay network model core on Softswitch technology, circuit switch network and IP network convergence realized. Referring to the optical transmission network core on ASTN/ASON, service layer (i.e. IP layer) and optical transmission convergence realized. Together with the distributing feature of NGN network control technology, on NGN platform, overview of combining Softswitch and ASTN/ASON control technology, the solution whether IP should be the NGN core carrier platform attracts general attention, and this is also a QoS problem on NGN end to end. This solution produces the significant practical meaning on equipment development, network deployment, network design and optimization, especially on realizing present network smooth evolving to the NGN. This is why this paper puts forward the research topic on the NGN network control technology. This paper introduces basics on NGN network control technology, then proposes NGN network control reference model, at the same time describes a realizable network structure of NGN. Based on above, from the view of function realization, NGN network control technology is discussed and its work mechanism is analyzed.

Enhanced Higgs boson to τ(+)τ(-) search with deep learning.

PubMed

Baldi, P; Sadowski, P; Whiteson, D

2015-03-20

The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the statistical power to cross the traditional 5σ significance barrier without more data. Deep learning techniques have the potential to increase the statistical power of this analysis by automatically learning complex, high-level data representations. In this work, deep neural networks are used to detect the decay of the Higgs boson to a pair of tau leptons. A Bayesian optimization algorithm is used to tune the network architecture and training algorithm hyperparameters, resulting in a deep network of eight nonlinear processing layers that improves upon the performance of shallow classifiers even without the use of features specifically engineered by physicists for this application. The improvement in discovery significance is equivalent to an increase in the accumulated data set of 25%.

Deep-learning derived features for lung nodule classification with limited datasets

NASA Astrophysics Data System (ADS)

Thammasorn, P.; Wu, W.; Pierce, L. A.; Pipavath, S. N.; Lampe, P. D.; Houghton, A. M.; Haynor, D. R.; Chaovalitwongse, W. A.; Kinahan, P. E.

2018-02-01

Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

A network model of the interbank market

NASA Astrophysics Data System (ADS)

Li, Shouwei; He, Jianmin; Zhuang, Yaming

2010-12-01

This work introduces a network model of an interbank market based on interbank credit lending relationships. It generates some network features identified through empirical analysis. The critical issue to construct an interbank network is to decide the edges among banks, which is realized in this paper based on the interbank’s degree of trust. Through simulation analysis of the interbank network model, some typical structural features are identified in our interbank network, which are also proved to exist in real interbank networks. They are namely, a low clustering coefficient and a relatively short average path length, community structures, and a two-power-law distribution of out-degree and in-degree.

Characterizing core-periphery structure of complex network by h-core and fingerprint curve

NASA Astrophysics Data System (ADS)

Li, Simon S.; Ye, Adam Y.; Qi, Eric P.; Stanley, H. Eugene; Ye, Fred Y.

2018-02-01

It is proposed that the core-periphery structure of complex networks can be simulated by h-cores and fingerprint curves. While the features of core structure are characterized by h-core, the features of periphery structure are visualized by rose or spiral curve as the fingerprint curve linking to entire-network parameters. It is suggested that a complex network can be approached by h-core and rose curves as the first-order Fourier-approach, where the core-periphery structure is characterized by five parameters: network h-index, network radius, degree power, network density and average clustering coefficient. The simulation looks Fourier-like analysis.

Entropy of network ensembles

NASA Astrophysics Data System (ADS)

Bianconi, Ginestra

2009-03-01

In this paper we generalize the concept of random networks to describe network ensembles with nontrivial features by a statistical mechanics approach. This framework is able to describe undirected and directed network ensembles as well as weighted network ensembles. These networks might have nontrivial community structure or, in the case of networks embedded in a given space, they might have a link probability with a nontrivial dependence on the distance between the nodes. These ensembles are characterized by their entropy, which evaluates the cardinality of networks in the ensemble. In particular, in this paper we define and evaluate the structural entropy, i.e., the entropy of the ensembles of undirected uncorrelated simple networks with given degree sequence. We stress the apparent paradox that scale-free degree distributions are characterized by having small structural entropy while they are so widely encountered in natural, social, and technological complex systems. We propose a solution to the paradox by proving that scale-free degree distributions are the most likely degree distribution with the corresponding value of the structural entropy. Finally, the general framework we present in this paper is able to describe microcanonical ensembles of networks as well as canonical or hidden-variable network ensembles with significant implications for the formulation of network-constructing algorithms.

Model-based analysis of pattern motion processing in mouse primary visual cortex

PubMed Central

Muir, Dylan R.; Roth, Morgane M.; Helmchen, Fritjof; Kampa, Björn M.

2015-01-01

Neurons in sensory areas of neocortex exhibit responses tuned to specific features of the environment. In visual cortex, information about features such as edges or textures with particular orientations must be integrated to recognize a visual scene or object. Connectivity studies in rodent cortex have revealed that neurons make specific connections within sub-networks sharing common input tuning. In principle, this sub-network architecture enables local cortical circuits to integrate sensory information. However, whether feature integration indeed occurs locally in rodent primary sensory areas has not been examined directly. We studied local integration of sensory features in primary visual cortex (V1) of the mouse by presenting drifting grating and plaid stimuli, while recording the activity of neuronal populations with two-photon calcium imaging. Using a Bayesian model-based analysis framework, we classified single-cell responses as being selective for either individual grating components or for moving plaid patterns. Rather than relying on trial-averaged responses, our model-based framework takes into account single-trial responses and can easily be extended to consider any number of arbitrary predictive models. Our analysis method was able to successfully classify significantly more responses than traditional partial correlation (PC) analysis, and provides a rigorous statistical framework to rank any number of models and reject poorly performing models. We also found a large proportion of cells that respond strongly to only one stimulus class. In addition, a quarter of selectively responding neurons had more complex responses that could not be explained by any simple integration model. Our results show that a broad range of pattern integration processes already take place at the level of V1. This diversity of integration is consistent with processing of visual inputs by local sub-networks within V1 that are tuned to combinations of sensory features. PMID:26300738

Problems in the design of multifunction meteor-radar networks

NASA Astrophysics Data System (ADS)

Nechitailenko, V. A.; Voloshchuk, Iu. I.

The design of meteor-radar networks is examined in connection with the need to conduct experiments on a mass scale in meteor geophysics and astronomy. Attention is given to network architecture features and procedures of communication-path selection in the organization of information transfer, with allowance for the features of the meteor communication link. The meteor link is considered as the main means to ensure traffic in the meteor-radar network.

No-reference image quality assessment based on statistics of convolution feature maps

NASA Astrophysics Data System (ADS)

Lv, Xiaoxin; Qin, Min; Chen, Xiaohui; Wei, Guo

2018-04-01

We propose a Convolutional Feature Maps (CFM) driven approach to accurately predict image quality. Our motivation bases on the finding that the Nature Scene Statistic (NSS) features on convolution feature maps are significantly sensitive to distortion degree of an image. In our method, a Convolutional Neural Network (CNN) is trained to obtain kernels for generating CFM. We design a forward NSS layer which performs on CFM to better extract NSS features. The quality aware features derived from the output of NSS layer is effective to describe the distortion type and degree an image suffered. Finally, a Support Vector Regression (SVR) is employed in our No-Reference Image Quality Assessment (NR-IQA) model to predict a subjective quality score of a distorted image. Experiments conducted on two public databases demonstrate the promising performance of the proposed method is competitive to state of the art NR-IQA methods.

Multiscale deep features learning for land-use scene recognition

NASA Astrophysics Data System (ADS)

Yuan, Baohua; Li, Shijin; Li, Ning

2018-01-01

The features extracted from deep convolutional neural networks (CNNs) have shown their promise as generic descriptors for land-use scene recognition. However, most of the work directly adopts the deep features for the classification of remote sensing images, and does not encode the deep features for improving their discriminative power, which can affect the performance of deep feature representations. To address this issue, we propose an effective framework, LASC-CNN, obtained by locality-constrained affine subspace coding (LASC) pooling of a CNN filter bank. LASC-CNN obtains more discriminative deep features than directly extracted from CNNs. Furthermore, LASC-CNN builds on the top convolutional layers of CNNs, which can incorporate multiscale information and regions of arbitrary resolution and sizes. Our experiments have been conducted using two widely used remote sensing image databases, and the results show that the proposed method significantly improves the performance when compared to other state-of-the-art methods.

Deep learning with coherent nanophotonic circuits

NASA Astrophysics Data System (ADS)

Shen, Yichen; Harris, Nicholas C.; Skirlo, Scott; Prabhu, Mihika; Baehr-Jones, Tom; Hochberg, Michael; Sun, Xin; Zhao, Shijie; Larochelle, Hugo; Englund, Dirk; Soljačić, Marin

2017-07-01

Artificial neural networks are computational network models inspired by signal processing in the brain. These models have dramatically improved performance for many machine-learning tasks, including speech and image recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made towards developing electronic architectures tuned to implement artificial neural networks that exhibit improved computational speed and accuracy. Here, we propose a new architecture for a fully optical neural network that, in principle, could offer an enhancement in computational speed and power efficiency over state-of-the-art electronics for conventional inference tasks. We experimentally demonstrate the essential part of the concept using a programmable nanophotonic processor featuring a cascaded array of 56 programmable Mach-Zehnder interferometers in a silicon photonic integrated circuit and show its utility for vowel recognition.

Benford’s Law Applies to Online Social Networks

PubMed Central

Golbeck, Jennifer

2015-01-01

Benford’s Law states that, in naturally occurring systems, the frequency of numbers’ first digits is not evenly distributed. Numbers beginning with a 1 occur roughly 30% of the time, and are six times more common than numbers beginning with a 9. We show that Benford’s Law applies to social and behavioral features of users in online social networks. Using social data from five major social networks (Facebook, Twitter, Google Plus, Pinterest, and LiveJournal), we show that the distribution of first significant digits of friend and follower counts for users in these systems follow Benford’s Law. The same is true for the number of posts users make. We extend this to egocentric networks, showing that friend counts among the people in an individual’s social network also follows the expected distribution. We discuss how this can be used to detect suspicious or fraudulent activity online and to validate datasets. PMID:26308716

Benford's Law Applies to Online Social Networks.

PubMed

Golbeck, Jennifer

2015-01-01

Benford's Law states that, in naturally occurring systems, the frequency of numbers' first digits is not evenly distributed. Numbers beginning with a 1 occur roughly 30% of the time, and are six times more common than numbers beginning with a 9. We show that Benford's Law applies to social and behavioral features of users in online social networks. Using social data from five major social networks (Facebook, Twitter, Google Plus, Pinterest, and LiveJournal), we show that the distribution of first significant digits of friend and follower counts for users in these systems follow Benford's Law. The same is true for the number of posts users make. We extend this to egocentric networks, showing that friend counts among the people in an individual's social network also follows the expected distribution. We discuss how this can be used to detect suspicious or fraudulent activity online and to validate datasets.

Emergence of Rich-Club Topology and Coordinated Dynamics in Development of Hippocampal Functional Networks In Vitro

PubMed Central

Charlesworth, Paul; Kitzbichler, Manfred G.; Paulsen, Ole

2015-01-01

Recent studies demonstrated that the anatomical network of the human brain shows a “rich-club” organization. This complex topological feature implies that highly connected regions, hubs of the large-scale brain network, are more densely interconnected with each other than expected by chance. Rich-club nodes were traversed by a majority of short paths between peripheral regions, underlining their potential importance for efficient global exchange of information between functionally specialized areas of the brain. Network hubs have also been described at the microscale of brain connectivity (so-called “hub neurons”). Their role in shaping synchronous dynamics and forming microcircuit wiring during development, however, is not yet fully understood. The present study aimed to investigate the role of hubs during network development, using multi-electrode arrays and functional connectivity analysis during spontaneous multi-unit activity (MUA) of dissociated primary mouse hippocampal neurons. Over the first 4 weeks in vitro, functional connectivity significantly increased in strength, density, and size, with mature networks demonstrating a robust modular and small-world topology. As expected by a “rich-get-richer” growth rule of network evolution, MUA graphs were found to form rich-clubs at an early stage in development (14 DIV). Later on, rich-club nodes were a consistent topological feature of MUA graphs, demonstrating high nodal strength, efficiency, and centrality. Rich-club nodes were also found to be crucial for MUA dynamics. They often served as broker of spontaneous activity flow, confirming that hub nodes and rich-clubs may play an important role in coordinating functional dynamics at the microcircuit level. PMID:25855164

A Theory of How Columns in the Neocortex Enable Learning the Structure of the World

PubMed Central

Hawkins, Jeff; Ahmad, Subutai; Cui, Yuwei

2017-01-01

Neocortical regions are organized into columns and layers. Connections between layers run mostly perpendicular to the surface suggesting a columnar functional organization. Some layers have long-range excitatory lateral connections suggesting interactions between columns. Similar patterns of connectivity exist in all regions but their exact role remain a mystery. In this paper, we propose a network model composed of columns and layers that performs robust object learning and recognition. Each column integrates its changing input over time to learn complete predictive models of observed objects. Excitatory lateral connections across columns allow the network to more rapidly infer objects based on the partial knowledge of adjacent columns. Because columns integrate input over time and space, the network learns models of complex objects that extend well beyond the receptive field of individual cells. Our network model introduces a new feature to cortical columns. We propose that a representation of location relative to the object being sensed is calculated within the sub-granular layers of each column. The location signal is provided as an input to the network, where it is combined with sensory data. Our model contains two layers and one or more columns. Simulations show that using Hebbian-like learning rules small single-column networks can learn to recognize hundreds of objects, with each object containing tens of features. Multi-column networks recognize objects with significantly fewer movements of the sensory receptors. Given the ubiquity of columnar and laminar connectivity patterns throughout the neocortex, we propose that columns and regions have more powerful recognition and modeling capabilities than previously assumed. PMID:29118696

The New ERA of Journal Ranking: The Consequences of Australia's Fraught Encounter with "Quality"

ERIC Educational Resources Information Center

Cooper, Simon; Poletti, Anna

2011-01-01

Ranking scholarly journals forms a major feature of the Excellence in Research for Australia (ERA) initiative. We argue this process is not only a flawed system of measurement, but more significantly erodes the very contexts that produce "quality" research. We argue that collegiality, networks of international research, the…

Meta-path based heterogeneous combat network link prediction

NASA Astrophysics Data System (ADS)

Li, Jichao; Ge, Bingfeng; Yang, Kewei; Chen, Yingwu; Tan, Yuejin

2017-09-01

The combat system-of-systems in high-tech informative warfare, composed of many interconnected combat systems of different types, can be regarded as a type of complex heterogeneous network. Link prediction for heterogeneous combat networks (HCNs) is of significant military value, as it facilitates reconfiguring combat networks to represent the complex real-world network topology as appropriate with observed information. This paper proposes a novel integrated methodology framework called HCNMP (HCN link prediction based on meta-path) to predict multiple types of links simultaneously for an HCN. More specifically, the concept of HCN meta-paths is introduced, through which the HCNMP can accumulate information by extracting different features of HCN links for all the six defined types. Next, an HCN link prediction model, based on meta-path features, is built to predict all types of links of the HCN simultaneously. Then, the solution algorithm for the HCN link prediction model is proposed, in which the prediction results are obtained by iteratively updating with the newly predicted results until the results in the HCN converge or reach a certain maximum iteration number. Finally, numerical experiments on the dataset of a real HCN are conducted to demonstrate the feasibility and effectiveness of the proposed HCNMP, in comparison with 30 baseline methods. The results show that the performance of the HCNMP is superior to those of the baseline methods.

Energy-aware scheduling of surveillance in wireless multimedia sensor networks.

PubMed

Wang, Xue; Wang, Sheng; Ma, Junjie; Sun, Xinyao

2010-01-01

Wireless sensor networks involve a large number of sensor nodes with limited energy supply, which impacts the behavior of their application. In wireless multimedia sensor networks, sensor nodes are equipped with audio and visual information collection modules. Multimedia contents are ubiquitously retrieved in surveillance applications. To solve the energy problems during target surveillance with wireless multimedia sensor networks, an energy-aware sensor scheduling method is proposed in this paper. Sensor nodes which acquire acoustic signals are deployed randomly in the sensing fields. Target localization is based on the signal energy feature provided by multiple sensor nodes, employing particle swarm optimization (PSO). During the target surveillance procedure, sensor nodes are adaptively grouped in a totally distributed manner. Specially, the target motion information is extracted by a forecasting algorithm, which is based on the hidden Markov model (HMM). The forecasting results are utilized to awaken sensor node in the vicinity of future target position. According to the two properties, signal energy feature and residual energy, the sensor nodes decide whether to participate in target detection separately with a fuzzy control approach. Meanwhile, the local routing scheme of data transmission towards the observer is discussed. Experimental results demonstrate the efficiency of energy-aware scheduling of surveillance in wireless multimedia sensor network, where significant energy saving is achieved by the sensor awakening approach and data transmission paths are calculated with low computational complexity.

A pre-trained convolutional neural network based method for thyroid nodule diagnosis.

PubMed

Ma, Jinlian; Wu, Fa; Zhu, Jiang; Xu, Dong; Kong, Dexing

2017-01-01

In ultrasound images, most thyroid nodules are in heterogeneous appearances with various internal components and also have vague boundaries, so it is difficult for physicians to discriminate malignant thyroid nodules from benign ones. In this study, we propose a hybrid method for thyroid nodule diagnosis, which is a fusion of two pre-trained convolutional neural networks (CNNs) with different convolutional layers and fully-connected layers. Firstly, the two networks pre-trained with ImageNet database are separately trained. Secondly, we fuse feature maps learned by trained convolutional filters, pooling and normalization operations of the two CNNs. Finally, with the fused feature maps, a softmax classifier is used to diagnose thyroid nodules. The proposed method is validated on 15,000 ultrasound images collected from two local hospitals. Experiment results show that the proposed CNN based methods can accurately and effectively diagnose thyroid nodules. In addition, the fusion of the two CNN based models lead to significant performance improvement, with an accuracy of 83.02%±0.72%. These demonstrate the potential clinical applications of this method. Copyright © 2016 Elsevier B.V. All rights reserved.

Broiler weight estimation based on machine vision and artificial neural network.

PubMed

Amraei, S; Abdanan Mehdizadeh, S; Salari, S

2017-04-01

1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chickens' head and tail removed using the Chan-Vese method. 3. The correlations between the body weight and 6 physical extracted features indicated that there were strong correlations between body weight and the 5 features including area, perimeter, convex area, major and minor axis length. 5. According to statistical analysis there was no significant difference between morning and afternoon data over 42 d. 6. In an attempt to improve the accuracy of live weight approximation different ANN techniques, including Bayesian regulation, Levenberg-Marquardt, Scaled conjugate gradient and gradient descent were used. Bayesian regulation with R 2 value of 0.98 was the best network for prediction of broiler weight. 7. The accuracy of the machine vision technique was examined and most errors were less than 50 g.

Comparing success levels of different neural network structures in extracting discriminative information from the response patterns of a temperature-modulated resistive gas sensor

NASA Astrophysics Data System (ADS)

Hosseini-Golgoo, S. M.; Bozorgi, H.; Saberkari, A.

2015-06-01

Performances of three neural networks, consisting of a multi-layer perceptron, a radial basis function, and a neuro-fuzzy network with local linear model tree training algorithm, in modeling and extracting discriminative features from the response patterns of a temperature-modulated resistive gas sensor are quantitatively compared. For response pattern recording, a voltage staircase containing five steps each with a 20 s plateau is applied to the micro-heater of the sensor, when 12 different target gases, each at 11 concentration levels, are present. In each test, the hidden layer neuron weights are taken as the discriminatory feature vector of the target gas. These vectors are then mapped to a 3D feature space using linear discriminant analysis. The discriminative information content of the feature vectors are determined by the calculation of the Fisher’s discriminant ratio, affording quantitative comparison among the success rates achieved by the different neural network structures. The results demonstrate a superior discrimination ratio for features extracted from local linear neuro-fuzzy and radial-basis-function networks with recognition rates of 96.27% and 90.74%, respectively.

A Hybrid Neural Network and Feature Extraction Technique for Target Recognition.

DTIC Science & Technology

target features are extracted, the extracted data being evaluated in an artificial neural network to identify a target at a location within the image scene from which the different viewing angles extend.

Linking metabolic network features to phenotypes using sparse group lasso.

PubMed

Samal, Satya Swarup; Radulescu, Ovidiu; Weber, Andreas; Fröhlich, Holger

2017-11-01

Integration of metabolic networks with '-omics' data has been a subject of recent research in order to better understand the behaviour of such networks with respect to differences between biological and clinical phenotypes. Under the conditions of steady state of the reaction network and the non-negativity of fluxes, metabolic networks can be algebraically decomposed into a set of sub-pathways often referred to as extreme currents (ECs). Our objective is to find the statistical association of such sub-pathways with given clinical outcomes, resulting in a particular instance of a self-contained gene set analysis method. In this direction, we propose a method based on sparse group lasso (SGL) to identify phenotype associated ECs based on gene expression data. SGL selects a sparse set of feature groups and also introduces sparsity within each group. Features in our model are clusters of ECs, and feature groups are defined based on correlations among these features. We apply our method to metabolic networks from KEGG database and study the association of network features to prostate cancer (where the outcome is tumor and normal, respectively) as well as glioblastoma multiforme (where the outcome is survival time). In addition, simulations show the superior performance of our method compared to global test, which is an existing self-contained gene set analysis method. R code (compatible with version 3.2.5) is available from http://www.abi.bit.uni-bonn.de/index.php?id=17. samal@combine.rwth-aachen.de or frohlich@bit.uni-bonn.de. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

[Terahertz Spectroscopic Identification with Deep Belief Network].

PubMed

Ma, Shuai; Shen, Tao; Wang, Rui-qi; Lai, Hua; Yu, Zheng-tao

2015-12-01

Feature extraction and classification are the key issues of terahertz spectroscopy identification. Because many materials have no apparent absorption peaks in the terahertz band, it is difficult to extract theirs terahertz spectroscopy feature and identify. To this end, a novel of identify terahertz spectroscopy approach with Deep Belief Network (DBN) was studied in this paper, which combines the advantages of DBN and K-Nearest Neighbors (KNN) classifier. Firstly, cubic spline interpolation and S-G filter were used to normalize the eight kinds of substances (ATP, Acetylcholine Bromide, Bifenthrin, Buprofezin, Carbazole, Bleomycin, Buckminster and Cylotriphosphazene) terahertz transmission spectra in the range of 0.9-6 THz. Secondly, the DBN model was built by two restricted Boltzmann machine (RBM) and then trained layer by layer using unsupervised approach. Instead of using handmade features, the DBN was employed to learn suitable features automatically with raw input data. Finally, a KNN classifier was applied to identify the terahertz spectrum. Experimental results show that using the feature learned by DBN can identify the terahertz spectrum of different substances with the recognition rate of over 90%, which demonstrates that the proposed method can automatically extract the effective features of terahertz spectrum. Furthermore, this KNN classifier was compared with others (BP neural network, SOM neural network and RBF neural network). Comparisons showed that the recognition rate of KNN classifier is better than the other three classifiers. Using the approach that automatic extract terahertz spectrum features by DBN can greatly reduce the workload of feature extraction. This proposed method shows a promising future in the application of identifying the mass terahertz spectroscopy.

Improved pulmonary nodule classification utilizing quantitative lung parenchyma features.

PubMed

Dilger, Samantha K N; Uthoff, Johanna; Judisch, Alexandra; Hammond, Emily; Mott, Sarah L; Smith, Brian J; Newell, John D; Hoffman, Eric A; Sieren, Jessica C

2015-10-01

Current computer-aided diagnosis (CAD) models for determining pulmonary nodule malignancy characterize nodule shape, density, and border in computed tomography (CT) data. Analyzing the lung parenchyma surrounding the nodule has been minimally explored. We hypothesize that improved nodule classification is achievable by including features quantified from the surrounding lung tissue. To explore this hypothesis, we have developed expanded quantitative CT feature extraction techniques, including volumetric Laws texture energy measures for the parenchyma and nodule, border descriptors using ray-casting and rubber-band straightening, histogram features characterizing densities, and global lung measurements. Using stepwise forward selection and leave-one-case-out cross-validation, a neural network was used for classification. When applied to 50 nodules (22 malignant and 28 benign) from high-resolution CT scans, 52 features (8 nodule, 39 parenchymal, and 5 global) were statistically significant. Nodule-only features yielded an area under the ROC curve of 0.918 (including nodule size) and 0.872 (excluding nodule size). Performance was improved through inclusion of parenchymal (0.938) and global features (0.932). These results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support our hypothesis: the pulmonary parenchyma is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.

GalaxyGAN: Generative Adversarial Networks for recovery of galaxy features

NASA Astrophysics Data System (ADS)

Schawinski, Kevin; Zhang, Ce; Zhang, Hantian; Fowler, Lucas; Krishnan Santhanam, Gokula

2017-02-01

GalaxyGAN uses Generative Adversarial Networks to reliably recover features in images of galaxies. The package uses machine learning to train on higher quality data and learns to recover detailed features such as galaxy morphology by effectively building priors. This method opens up the possibility of recovering more information from existing and future imaging data.

Method and system for mesh network embedded devices

NASA Technical Reports Server (NTRS)

Wang, Ray (Inventor)

2009-01-01

A method and system for managing mesh network devices. A mesh network device with integrated features creates an N-way mesh network with a full mesh network topology or a partial mesh network topology.

Object recognition of real targets using modelled SAR images

NASA Astrophysics Data System (ADS)

Zherdev, D. A.

2017-12-01

In this work the problem of recognition is studied using SAR images. The algorithm of recognition is based on the computation of conjugation indices with vectors of class. The support subspaces for each class are constructed by exception of the most and the less correlated vectors in a class. In the study we examine the ability of a significant feature vector size reduce that leads to recognition time decrease. The images of targets form the feature vectors that are transformed using pre-trained convolutional neural network (CNN).

Cascading Failures and Recovery in Networks of Networks

NASA Astrophysics Data System (ADS)

Havlin, Shlomo

Network science have been focused on the properties of a single isolated network that does not interact or depends on other networks. In reality, many real-networks, such as power grids, transportation and communication infrastructures interact and depend on other networks. I will present a framework for studying the vulnerability and the recovery of networks of interdependent networks. In interdependent networks, when nodes in one network fail, they cause dependent nodes in other networks to also fail. This is also the case when some nodes like certain locations play a role in two networks -multiplex. This may happen recursively and can lead to a cascade of failures and to a sudden fragmentation of the system. I will present analytical solutions for the critical threshold and the giant component of a network of n interdependent networks. I will show, that the general theory has many novel features that are not present in the classical network theory. When recovery of components is possible global spontaneous recovery of the networks and hysteresis phenomena occur and the theory suggests an optimal repairing strategy of system of systems. I will also show that interdependent networks embedded in space are significantly more vulnerable compared to non embedded networks. In particular, small localized attacks may lead to cascading failures and catastrophic consequences.Thus, analyzing data of real network of networks is highly required to understand the system vulnerability. DTRA, ONR, Israel Science Foundation.

A diagnosis model for early Tourette syndrome children based on brain structural network characteristics

NASA Astrophysics Data System (ADS)

Wen, Hongwei; Liu, Yue; Wang, Jieqiong; Zhang, Jishui; Peng, Yun; He, Huiguang

2016-03-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder characterized by the presence of multiple motor and vocal tics. Tic generation has been linked to disturbed networks of brain areas involved in planning, controlling and execution of action. The aim of our work is to select topological characteristics of structural network which were most efficient for estimating the classification models to identify early TS children. Here we employed the diffusion tensor imaging (DTI) and deterministic tractography to construct the structural networks of 44 TS children and 48 age and gender matched healthy children. We calculated four different connection matrices (fiber number, mean FA, averaged fiber length weighted and binary matrices) and then applied graph theoretical methods to extract the regional nodal characteristics of structural network. For each weighted or binary network, nodal degree, nodal efficiency and nodal betweenness were selected as features. Support Vector Machine Recursive Feature Extraction (SVM-RFE) algorithm was used to estimate the best feature subset for classification. The accuracy of 88.26% evaluated by a nested cross validation was achieved on combing best feature subset of each network characteristic. The identified discriminative brain nodes mostly located in the basal ganglia and frontal cortico-cortical networks involved in TS children which was associated with tic severity. Our study holds promise for early identification and predicting prognosis of TS children.

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification

PubMed Central

Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods. PMID:27610128

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification.

PubMed

Pang, Shan; Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.

Feature detection in satellite images using neural network technology

NASA Technical Reports Server (NTRS)

Augusteijn, Marijke F.; Dimalanta, Arturo S.

1992-01-01

A feasibility study of automated classification of satellite images is described. Satellite images were characterized by the textures they contain. In particular, the detection of cloud textures was investigated. The method of second-order gray level statistics, using co-occurrence matrices, was applied to extract feature vectors from image segments. Neural network technology was employed to classify these feature vectors. The cascade-correlation architecture was successfully used as a classifier. The use of a Kohonen network was also investigated but this architecture could not reliably classify the feature vectors due to the complicated structure of the classification problem. The best results were obtained when data from different spectral bands were fused.

Future global SLR network evolution and its impact on the terrestrial reference frame

NASA Astrophysics Data System (ADS)

Kehm, Alexander; Bloßfeld, Mathis; Pavlis, Erricos C.; Seitz, Florian

2018-06-01

Satellite laser ranging (SLR) is an important technique that contributes to the determination of terrestrial geodetic reference frames, especially to the realization of the origin and the scale of global networks. One of the major limiting factors of SLR-derived reference frame realizations is the datum accuracy which significantly suffers from the current global SLR station distribution. In this paper, the impact of a potential future development of the SLR network on the estimated datum parameters is investigated. The current status of the SLR network is compared to a simulated potential future network featuring additional stations improving the global network geometry. In addition, possible technical advancements resulting in a higher amount of observations are taken into account as well. As a result, we find that the network improvement causes a decrease in the scatter of the network translation parameters of up to 24%, and up to 20% for the scale, whereas the technological improvement causes a reduction in the scatter of up to 27% for the translations and up to 49% for the scale. The Earth orientation parameters benefit by up to 15% from both effects.

Automatic feature learning using multichannel ROI based on deep structured algorithms for computerized lung cancer diagnosis.

PubMed

Sun, Wenqing; Zheng, Bin; Qian, Wei

2017-10-01

This study aimed to analyze the ability of extracting automatically generated features using deep structured algorithms in lung nodule CT image diagnosis, and compare its performance with traditional computer aided diagnosis (CADx) systems using hand-crafted features. All of the 1018 cases were acquired from Lung Image Database Consortium (LIDC) public lung cancer database. The nodules were segmented according to four radiologists' markings, and 13,668 samples were generated by rotating every slice of nodule images. Three multichannel ROI based deep structured algorithms were designed and implemented in this study: convolutional neural network (CNN), deep belief network (DBN), and stacked denoising autoencoder (SDAE). For the comparison purpose, we also implemented a CADx system using hand-crafted features including density features, texture features and morphological features. The performance of every scheme was evaluated by using a 10-fold cross-validation method and an assessment index of the area under the receiver operating characteristic curve (AUC). The observed highest area under the curve (AUC) was 0.899±0.018 achieved by CNN, which was significantly higher than traditional CADx with the AUC=0.848±0.026. The results from DBN was also slightly higher than CADx, while SDAE was slightly lower. By visualizing the automatic generated features, we found some meaningful detectors like curvy stroke detectors from deep structured schemes. The study results showed the deep structured algorithms with automatically generated features can achieve desirable performance in lung nodule diagnosis. With well-tuned parameters and large enough dataset, the deep learning algorithms can have better performance than current popular CADx. We believe the deep learning algorithms with similar data preprocessing procedure can be used in other medical image analysis areas as well. Copyright © 2017. Published by Elsevier Ltd.

New approaches to model and study social networks

NASA Astrophysics Data System (ADS)

Lind, P. G.; Herrmann, H. J.

2007-07-01

We describe and develop three recent novelties in network research which are particularly useful for studying social systems. The first one concerns the discovery of some basic dynamical laws that enable the emergence of the fundamental features observed in social networks, namely the nontrivial clustering properties, the existence of positive degree correlations and the subdivision into communities. To reproduce all these features, we describe a simple model of mobile colliding agents, whose collisions define the connections between the agents which are the nodes in the underlying network, and develop some analytical considerations. The second point addresses the particular feature of clustering and its relationship with global network measures, namely with the distribution of the size of cycles in the network. Since in social bipartite networks it is not possible to measure the clustering from standard procedures, we propose an alternative clustering coefficient that can be used to extract an improved normalized cycle distribution in any network. Finally, the third point addresses dynamical processes occurring on networks, namely when studying the propagation of information in them. In particular, we focus on the particular features of gossip propagation which impose some restrictions in the propagation rules. To this end we introduce a quantity, the spread factor, which measures the average maximal fraction of nearest neighbours which get in contact with the gossip, and find the striking result that there is an optimal non-trivial number of friends for which the spread factor is minimized, decreasing the danger of being gossiped about.

Effects of contact network structure on epidemic transmission trees: implications for data required to estimate network structure.

PubMed

Carnegie, Nicole Bohme

2018-01-30

Understanding the dynamics of disease spread is key to developing effective interventions to control or prevent an epidemic. The structure of the network of contacts over which the disease spreads has been shown to have a strong influence on the outcome of the epidemic, but an open question remains as to whether it is possible to estimate contact network features from data collected in an epidemic. The approach taken in this paper is to examine the distributions of epidemic outcomes arising from epidemics on networks with particular structural features to assess whether that structure could be measured from epidemic data and what other constraints might be needed to make the problem identifiable. To this end, we vary the network size, mean degree, and transmissibility of the pathogen, as well as the network feature of interest: clustering, degree assortativity, or attribute-based preferential mixing. We record several standard measures of the size and spread of the epidemic, as well as measures that describe the shape of the transmission tree in order to ascertain whether there are detectable signals in the final data from the outbreak. The results suggest that there is potential to estimate contact network features from transmission trees or pure epidemic data, particularly for diseases with high transmissibility or for which the relevant contact network is of low mean degree. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Feature selection in feature network models: finding predictive subsets of features with the Positive Lasso.

PubMed

Frank, Laurence E; Heiser, Willem J

2008-05-01

A set of features is the basis for the network representation of proximity data achieved by feature network models (FNMs). Features are binary variables that characterize the objects in an experiment, with some measure of proximity as response variable. Sometimes features are provided by theory and play an important role in the construction of the experimental conditions. In some research settings, the features are not known a priori. This paper shows how to generate features in this situation and how to select an adequate subset of features that takes into account a good compromise between model fit and model complexity, using a new version of least angle regression that restricts coefficients to be non-negative, called the Positive Lasso. It will be shown that features can be generated efficiently with Gray codes that are naturally linked to the FNMs. The model selection strategy makes use of the fact that FNM can be considered as univariate multiple regression model. A simulation study shows that the proposed strategy leads to satisfactory results if the number of objects is less than or equal to 22. If the number of objects is larger than 22, the number of features selected by our method exceeds the true number of features in some conditions.

A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks.

PubMed

Alauthaman, Mohammad; Aslam, Nauman; Zhang, Li; Alasem, Rafe; Hossain, M A

2018-01-01

In recent years, Botnets have been adopted as a popular method to carry and spread many malicious codes on the Internet. These malicious codes pave the way to execute many fraudulent activities including spam mail, distributed denial-of-service attacks and click fraud. While many Botnets are set up using centralized communication architecture, the peer-to-peer (P2P) Botnets can adopt a decentralized architecture using an overlay network for exchanging command and control data making their detection even more difficult. This work presents a method of P2P Bot detection based on an adaptive multilayer feed-forward neural network in cooperation with decision trees. A classification and regression tree is applied as a feature selection technique to select relevant features. With these features, a multilayer feed-forward neural network training model is created using a resilient back-propagation learning algorithm. A comparison of feature set selection based on the decision tree, principal component analysis and the ReliefF algorithm indicated that the neural network model with features selection based on decision tree has a better identification accuracy along with lower rates of false positives. The usefulness of the proposed approach is demonstrated by conducting experiments on real network traffic datasets. In these experiments, an average detection rate of 99.08 % with false positive rate of 0.75 % was observed.

A Power Planning Algorithm Based on RPL for AMI Wireless Sensor Networks.

PubMed

Miguel, Marcio L F; Jamhour, Edgard; Pellenz, Marcelo E; Penna, Manoel C

2017-03-25

The advanced metering infrastructure (AMI) is an architecture for two-way communication between electric, gas and water meters and city utilities. The AMI network is a wireless sensor network that provides communication for metering devices in the neighborhood area of the smart grid. Recently, the applicability of a routing protocol for low-power and lossy networks (RPL) has been considered in AMI networks. Some studies in the literature have pointed out problems with RPL, including sub-optimal path selection and instability. In this paper, we defend the viewpoint that careful planning of the transmission power in wireless RPL networks can significantly reduce the pointed problems. This paper presents a method for planning the transmission power in order to assure that, after convergence, the size of the parent set of the RPL nodes is as close as possible to a predefined size. Another important feature is that all nodes in the parent set offer connectivity through links of similar quality.

Historical data learning based dynamic LSP routing for overlay IP/MPLS over WDM networks

NASA Astrophysics Data System (ADS)

Yu, Xiaojun; Xiao, Gaoxi; Cheng, Tee Hiang

2013-08-01

Overlay IP/MPLS over WDM network is a promising network architecture starting to gain wide deployments recently. A desirable feature of such a network is to achieve efficient routing with limited information exchanges between the IP/MPLS and the WDM layers. This paper studies dynamic label switched path (LSP) routing in the overlay IP/MPLS over WDM networks. To enhance network performance while maintaining its simplicity, we propose to learn from the historical data of lightpath setup costs maintained by the IP-layer integrated service provider (ISP) when making routing decisions. Using a novel historical data learning scheme for logical link cost estimation, we develop a new dynamic LSP routing method named Existing Link First (ELF) algorithm. Simulation results show that the proposed algorithm significantly outperforms the existing ones under different traffic loads, with either limited or unlimited numbers of optical ports. Effects of the number of candidate routes, add/drop ratio and the amount of historical data are also evaluated.

UMDR: Multi-Path Routing Protocol for Underwater Ad Hoc Networks with Directional Antenna

NASA Astrophysics Data System (ADS)

Yang, Jianmin; Liu, Songzuo; Liu, Qipei; Qiao, Gang

2018-01-01

This paper presents a new routing scheme for underwater ad hoc networks based on directional antennas. Ad hoc networks with directional antennas have become a hot research topic because of space reuse may increase networks capacity. At present, researchers have applied traditional self-organizing routing protocols (such as DSR, AODV) [1] [2] on this type of networks, and the routing scheme is based on the shortest path metric. However, such routing schemes often suffer from long transmission delays and frequent link fragmentation along the intermediate nodes of the selected route. This is caused by a unique feature of directional transmission, often called as “deafness”. In this paper, we take a different approach to explore the advantages of space reuse through multipath routing. This paper introduces the validity of the conventional routing scheme in underwater ad hoc networks with directional antennas, and presents a special design of multipath routing algorithm for directional transmission. The experimental results show a significant performance improvement in throughput and latency.

SYNAPTIC DEPRESSION IN DEEP NEURAL NETWORKS FOR SPEECH PROCESSING.

PubMed

Zhang, Wenhao; Li, Hanyu; Yang, Minda; Mesgarani, Nima

2016-03-01

A characteristic property of biological neurons is their ability to dynamically change the synaptic efficacy in response to variable input conditions. This mechanism, known as synaptic depression, significantly contributes to the formation of normalized representation of speech features. Synaptic depression also contributes to the robust performance of biological systems. In this paper, we describe how synaptic depression can be modeled and incorporated into deep neural network architectures to improve their generalization ability. We observed that when synaptic depression is added to the hidden layers of a neural network, it reduces the effect of changing background activity in the node activations. In addition, we show that when synaptic depression is included in a deep neural network trained for phoneme classification, the performance of the network improves under noisy conditions not included in the training phase. Our results suggest that more complete neuron models may further reduce the gap between the biological performance and artificial computing, resulting in networks that better generalize to novel signal conditions.

A Power Planning Algorithm Based on RPL for AMI Wireless Sensor Networks

PubMed Central

Miguel, Marcio L. F.; Jamhour, Edgard; Pellenz, Marcelo E.; Penna, Manoel C.

2017-01-01

The advanced metering infrastructure (AMI) is an architecture for two-way communication between electric, gas and water meters and city utilities. The AMI network is a wireless sensor network that provides communication for metering devices in the neighborhood area of the smart grid. Recently, the applicability of a routing protocol for low-power and lossy networks (RPL) has been considered in AMI networks. Some studies in the literature have pointed out problems with RPL, including sub-optimal path selection and instability. In this paper, we defend the viewpoint that careful planning of the transmission power in wireless RPL networks can significantly reduce the pointed problems. This paper presents a method for planning the transmission power in order to assure that, after convergence, the size of the parent set of the RPL nodes is as close as possible to a predefined size. Another important feature is that all nodes in the parent set offer connectivity through links of similar quality. PMID:28346339

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network.

PubMed

Yoon, Jaehong; Lee, Jungnyun; Whang, Mincheol

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain-computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

Spatial and Time Domain Feature of ERP Speller System Extracted via Convolutional Neural Network

PubMed Central

2018-01-01

Feature of event-related potential (ERP) has not been completely understood and illiteracy problem remains unsolved. To this end, P300 peak has been used as the feature of ERP in most brain–computer interface applications, but subjects who do not show such peak are common. Recent development of convolutional neural network provides a way to analyze spatial and temporal features of ERP. Here, we train the convolutional neural network with 2 convolutional layers whose feature maps represented spatial and temporal features of event-related potential. We have found that nonilliterate subjects' ERP show high correlation between occipital lobe and parietal lobe, whereas illiterate subjects only show correlation between neural activities from frontal lobe and central lobe. The nonilliterates showed peaks in P300, P500, and P700, whereas illiterates mostly showed peaks in around P700. P700 was strong in both subjects. We found that P700 peak may be the key feature of ERP as it appears in both illiterate and nonilliterate subjects.

Deep neural networks for texture classification-A theoretical analysis.

PubMed

Basu, Saikat; Mukhopadhyay, Supratik; Karki, Manohar; DiBiano, Robert; Ganguly, Sangram; Nemani, Ramakrishna; Gayaka, Shreekant

2018-01-01

We investigate the use of Deep Neural Networks for the classification of image datasets where texture features are important for generating class-conditional discriminative representations. To this end, we first derive the size of the feature space for some standard textural features extracted from the input dataset and then use the theory of Vapnik-Chervonenkis dimension to show that hand-crafted feature extraction creates low-dimensional representations which help in reducing the overall excess error rate. As a corollary to this analysis, we derive for the first time upper bounds on the VC dimension of Convolutional Neural Network as well as Dropout and Dropconnect networks and the relation between excess error rate of Dropout and Dropconnect networks. The concept of intrinsic dimension is used to validate the intuition that texture-based datasets are inherently higher dimensional as compared to handwritten digits or other object recognition datasets and hence more difficult to be shattered by neural networks. We then derive the mean distance from the centroid to the nearest and farthest sampling points in an n-dimensional manifold and show that the Relative Contrast of the sample data vanishes as dimensionality of the underlying vector space tends to infinity. Copyright © 2017 Elsevier Ltd. All rights reserved.

Constructing networks with correlation maximization methods.

PubMed

Mellor, Joseph C; Wu, Jie; Delisi, Charles

2004-01-01

Problems of inference in systems biology are ideally reduced to formulations which can efficiently represent the features of interest. In the case of predicting gene regulation and pathway networks, an important feature which describes connected genes and proteins is the relationship between active and inactive forms, i.e. between the "on" and "off" states of the components. While not optimal at the limits of resolution, these logical relationships between discrete states can often yield good approximations of the behavior in larger complex systems, where exact representation of measurement relationships may be intractable. We explore techniques for extracting binary state variables from measurement of gene expression, and go on to describe robust measures for statistical significance and information that can be applied to many such types of data. We show how statistical strength and information are equivalent criteria in limiting cases, and demonstrate the application of these measures to simple systems of gene regulation.

The data-driven null models for information dissemination tree in social networks

NASA Astrophysics Data System (ADS)

Zhang, Zhiwei; Wang, Zhenyu

2017-10-01

For the purpose of detecting relatedness and co-occurrence between users, as well as the distribution features of nodes in spreading path of a social network, this paper explores topological characteristics of information dissemination trees (IDT) that can be employed indirectly to probe the information dissemination laws within social networks. Hence, three different null models of IDT are presented in this article, including the statistical-constrained 0-order IDT null model, the random-rewire-broken-edge 0-order IDT null model and the random-rewire-broken-edge 2-order IDT null model. These null models firstly generate the corresponding randomized copy of an actual IDT; then the extended significance profile, which is developed by adding the cascade ratio of information dissemination path, is exploited not only to evaluate degree correlation of two nodes associated with an edge, but also to assess the cascade ratio of different length of information dissemination paths. The experimental correspondences of the empirical analysis for several SinaWeibo IDTs and Twitter IDTs indicate that the IDT null models presented in this paper perform well in terms of degree correlation of nodes and dissemination path cascade ratio, which can be better to reveal the features of information dissemination and to fit the situation of real social networks.

A neural network for noise correlation classification

NASA Astrophysics Data System (ADS)

Paitz, Patrick; Gokhberg, Alexey; Fichtner, Andreas

2018-02-01

We present an artificial neural network (ANN) for the classification of ambient seismic noise correlations into two categories, suitable and unsuitable for noise tomography. By using only a small manually classified data subset for network training, the ANN allows us to classify large data volumes with low human effort and to encode the valuable subjective experience of data analysts that cannot be captured by a deterministic algorithm. Based on a new feature extraction procedure that exploits the wavelet-like nature of seismic time-series, we efficiently reduce the dimensionality of noise correlation data, still keeping relevant features needed for automated classification. Using global- and regional-scale data sets, we show that classification errors of 20 per cent or less can be achieved when the network training is performed with as little as 3.5 per cent and 16 per cent of the data sets, respectively. Furthermore, the ANN trained on the regional data can be applied to the global data, and vice versa, without a significant increase of the classification error. An experiment where four students manually classified the data, revealed that the classification error they would assign to each other is substantially larger than the classification error of the ANN (>35 per cent). This indicates that reproducibility would be hampered more by human subjectivity than by imperfections of the ANN.

Data-driven automated acoustic analysis of human infant vocalizations using neural network tools.

PubMed

Warlaumont, Anne S; Oller, D Kimbrough; Buder, Eugene H; Dale, Rick; Kozma, Robert

2010-04-01

Acoustic analysis of infant vocalizations has typically employed traditional acoustic measures drawn from adult speech acoustics, such as f(0), duration, formant frequencies, amplitude, and pitch perturbation. Here an alternative and complementary method is proposed in which data-derived spectrographic features are central. 1-s-long spectrograms of vocalizations produced by six infants recorded longitudinally between ages 3 and 11 months are analyzed using a neural network consisting of a self-organizing map and a single-layer perceptron. The self-organizing map acquires a set of holistic, data-derived spectrographic receptive fields. The single-layer perceptron receives self-organizing map activations as input and is trained to classify utterances into prelinguistic phonatory categories (squeal, vocant, or growl), identify the ages at which they were produced, and identify the individuals who produced them. Classification performance was significantly better than chance for all three classification tasks. Performance is compared to another popular architecture, the fully supervised multilayer perceptron. In addition, the network's weights and patterns of activation are explored from several angles, for example, through traditional acoustic measurements of the network's receptive fields. Results support the use of this and related tools for deriving holistic acoustic features directly from infant vocalization data and for the automatic classification of infant vocalizations.

Skill complementarity enhances heterophily in collaboration networks

PubMed Central

Xie, Wen-Jie; Li, Ming-Xia; Jiang, Zhi-Qiang; Tan, Qun-Zhao; Podobnik, Boris; Zhou, Wei-Xing; Stanley, H. Eugene

2016-01-01

Much empirical evidence shows that individuals usually exhibit significant homophily in social networks. We demonstrate, however, skill complementarity enhances heterophily in the formation of collaboration networks, where people prefer to forge social ties with people who have professions different from their own. We construct a model to quantify the heterophily by assuming that individuals choose collaborators to maximize utility. Using a huge database of online societies, we find evidence of heterophily in collaboration networks. The results of model calibration confirm the presence of heterophily. Both empirical analysis and model calibration show that the heterophilous feature is persistent along the evolution of online societies. Furthermore, the degree of skill complementarity is positively correlated with their production output. Our work sheds new light on the scientific research utility of virtual worlds for studying human behaviors in complex socioeconomic systems. PMID:26743687

Worm epidemics in wireless ad hoc networks

NASA Astrophysics Data System (ADS)

Nekovee, Maziar

2007-06-01

A dramatic increase in the number of computing devices with wireless communication capability has resulted in the emergence of a new class of computer worms which specifically target such devices. The most striking feature of these worms is that they do not require Internet connectivity for their propagation but can spread directly from device to device using a short-range radio communication technology, such as WiFi or Bluetooth. In this paper, we develop a new model for epidemic spreading of these worms and investigate their spreading in wireless ad hoc networks via extensive Monte Carlo simulations. Our studies show that the threshold behaviour and dynamics of worm epidemics in these networks are greatly affected by a combination of spatial and temporal correlations which characterize these networks, and are significantly different from the previously studied epidemics in the Internet.

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.

Enhancement of the Feature Extraction Capability in Global Damage Detection Using Wavelet Theory

NASA Technical Reports Server (NTRS)

Saleeb, Atef F.; Ponnaluru, Gopi Krishna

2006-01-01

The main objective of this study is to assess the specific capabilities of the defect energy parameter technique for global damage detection developed by Saleeb and coworkers. The feature extraction is the most important capability in any damage-detection technique. Features are any parameters extracted from the processed measurement data in order to enhance damage detection. The damage feature extraction capability was studied extensively by analyzing various simulation results. The practical significance in structural health monitoring is that the detection at early stages of small-size defects is always desirable. The amount of changes in the structure's response due to these small defects was determined to show the needed level of accuracy in the experimental methods. The arrangement of fine/extensive sensor network to measure required data for the detection is an "unlimited" ability, but there is a difficulty to place extensive number of sensors on a structure. Therefore, an investigation was conducted using the measurements of coarse sensor network. The white and the pink noises, which cover most of the frequency ranges that are typically encountered in the many measuring devices used (e.g., accelerometers, strain gauges, etc.) are added to the displacements to investigate the effect of noisy measurements in the detection technique. The noisy displacements and the noisy damage parameter values are used to study the signal feature reconstruction using wavelets. The enhancement of the feature extraction capability was successfully achieved by the wavelet theory.

Coding visual features extracted from video sequences.

PubMed

Baroffio, Luca; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2014-05-01

Visual features are successfully exploited in several applications (e.g., visual search, object recognition and tracking, etc.) due to their ability to efficiently represent image content. Several visual analysis tasks require features to be transmitted over a bandwidth-limited network, thus calling for coding techniques to reduce the required bit budget, while attaining a target level of efficiency. In this paper, we propose, for the first time, a coding architecture designed for local features (e.g., SIFT, SURF) extracted from video sequences. To achieve high coding efficiency, we exploit both spatial and temporal redundancy by means of intraframe and interframe coding modes. In addition, we propose a coding mode decision based on rate-distortion optimization. The proposed coding scheme can be conveniently adopted to implement the analyze-then-compress (ATC) paradigm in the context of visual sensor networks. That is, sets of visual features are extracted from video frames, encoded at remote nodes, and finally transmitted to a central controller that performs visual analysis. This is in contrast to the traditional compress-then-analyze (CTA) paradigm, in which video sequences acquired at a node are compressed and then sent to a central unit for further processing. In this paper, we compare these coding paradigms using metrics that are routinely adopted to evaluate the suitability of visual features in the context of content-based retrieval, object recognition, and tracking. Experimental results demonstrate that, thanks to the significant coding gains achieved by the proposed coding scheme, ATC outperforms CTA with respect to all evaluation metrics.

Multiple Resting-State Networks Are Associated With Tremors and Cognitive Features in Essential Tremor.

PubMed

Fang, Weidong; Chen, Huiyue; Wang, Hansheng; Zhang, Han; Liu, Mengqi; Puneet, Munankami; Lv, Fajin; Cheng, Oumei; Wang, Xuefeng; Lu, Xiurong; Luo, Tianyou

2015-12-01

The heterogeneous clinical features of essential tremor indicate that the dysfunctions of this syndrome are not confined to motor networks, but extend to nonmotor networks. Currently, these neural network dysfunctions in essential tremor remain unclear. In this study, independent component analysis of resting-state functional MRI was used to study these neural network mechanisms. Thirty-five essential tremor patients and 35 matched healthy controls with clinical and neuropsychological tests were included, and eight resting-state networks were identified. After considering the structure and head-motion factors and testing the reliability of the selected resting-state networks, we assessed the functional connectivity changes within or between resting-state networks. Finally, image-behavior correlation analysis was performed. Compared to healthy controls, essential tremor patients displayed increased functional connectivity in the sensorimotor and salience networks and decreased functional connectivity in the cerebellum network. Additionally, increased functional network connectivity was observed between anterior and posterior default mode networks, and a decreased functional network connectivity was noted between the cerebellum network and the sensorimotor and posterior default mode networks. Importantly, the functional connectivity changes within and between these resting-state networks were correlated with the tremor severity and total cognitive scores of essential tremor patients. The findings of this study provide the first evidence that functional connectivity changes within and between multiple resting-state networks are associated with tremors and cognitive features of essential tremor, and this work demonstrates a potential approach for identifying the underlying neural network mechanisms of this syndrome. © 2015 International Parkinson and Movement Disorder Society.

Automatic QRS complex detection using two-level convolutional neural network.

PubMed

Xiang, Yande; Lin, Zhitao; Meng, Jianyi

2018-01-29

The QRS complex is the most noticeable feature in the electrocardiogram (ECG) signal, therefore, its detection is critical for ECG signal analysis. The existing detection methods largely depend on hand-crafted manual features and parameters, which may introduce significant computational complexity, especially in the transform domains. In addition, fixed features and parameters are not suitable for detecting various kinds of QRS complexes under different circumstances. In this study, based on 1-D convolutional neural network (CNN), an accurate method for QRS complex detection is proposed. The CNN consists of object-level and part-level CNNs for extracting different grained ECG morphological features automatically. All the extracted morphological features are used by multi-layer perceptron (MLP) for QRS complex detection. Additionally, a simple ECG signal preprocessing technique which only contains difference operation in temporal domain is adopted. Based on the MIT-BIH arrhythmia (MIT-BIH-AR) database, the proposed detection method achieves overall sensitivity Sen = 99.77%, positive predictivity rate PPR = 99.91%, and detection error rate DER = 0.32%. In addition, the performance variation is performed according to different signal-to-noise ratio (SNR) values. An automatic QRS detection method using two-level 1-D CNN and simple signal preprocessing technique is proposed for QRS complex detection. Compared with the state-of-the-art QRS complex detection approaches, experimental results show that the proposed method acquires comparable accuracy.

Naturalistic FMRI mapping reveals superior temporal sulcus as the hub for the distributed brain network for social perception.

PubMed

Lahnakoski, Juha M; Glerean, Enrico; Salmi, Juha; Jääskeläinen, Iiro P; Sams, Mikko; Hari, Riitta; Nummenmaa, Lauri

2012-01-01

Despite the abundant data on brain networks processing static social signals, such as pictures of faces, the neural systems supporting social perception in naturalistic conditions are still poorly understood. Here we delineated brain networks subserving social perception under naturalistic conditions in 19 healthy humans who watched, during 3-T functional magnetic resonance imaging (fMRI), a set of 137 short (approximately 16 s each, total 27 min) audiovisual movie clips depicting pre-selected social signals. Two independent raters estimated how well each clip represented eight social features (faces, human bodies, biological motion, goal-oriented actions, emotion, social interaction, pain, and speech) and six filler features (places, objects, rigid motion, people not in social interaction, non-goal-oriented action, and non-human sounds) lacking social content. These ratings were used as predictors in the fMRI analysis. The posterior superior temporal sulcus (STS) responded to all social features but not to any non-social features, and the anterior STS responded to all social features except bodies and biological motion. We also found four partially segregated, extended networks for processing of specific social signals: (1) a fronto-temporal network responding to multiple social categories, (2) a fronto-parietal network preferentially activated to bodies, motion, and pain, (3) a temporo-amygdalar network responding to faces, social interaction, and speech, and (4) a fronto-insular network responding to pain, emotions, social interactions, and speech. Our results highlight the role of the pSTS in processing multiple aspects of social information, as well as the feasibility and efficiency of fMRI mapping under conditions that resemble the complexity of real life.

Bayesian network interface for assisting radiology interpretation and education

NASA Astrophysics Data System (ADS)

Duda, Jeffrey; Botzolakis, Emmanuel; Chen, Po-Hao; Mohan, Suyash; Nasrallah, Ilya; Rauschecker, Andreas; Rudie, Jeffrey; Bryan, R. Nick; Gee, James; Cook, Tessa

2018-03-01

In this work, we present the use of Bayesian networks for radiologist decision support during clinical interpretation. This computational approach has the advantage of avoiding incorrect diagnoses that result from known human cognitive biases such as anchoring bias, framing effect, availability bias, and premature closure. To integrate Bayesian networks into clinical practice, we developed an open-source web application that provides diagnostic support for a variety of radiology disease entities (e.g., basal ganglia diseases, bone lesions). The Clinical tool presents the user with a set of buttons representing clinical and imaging features of interest. These buttons are used to set the value for each observed feature. As features are identified, the conditional probabilities for each possible diagnosis are updated in real time. Additionally, using sensitivity analysis, the interface may be set to inform the user which remaining imaging features provide maximum discriminatory information to choose the most likely diagnosis. The Case Submission tools allow the user to submit a validated case and the associated imaging features to a database, which can then be used for future tuning/testing of the Bayesian networks. These submitted cases are then reviewed by an assigned expert using the provided QC tool. The Research tool presents users with cases with previously labeled features and a chosen diagnosis, for the purpose of performance evaluation. Similarly, the Education page presents cases with known features, but provides real time feedback on feature selection.

Fabric defect detection based on visual saliency using deep feature and low-rank recovery

NASA Astrophysics Data System (ADS)

Liu, Zhoufeng; Wang, Baorui; Li, Chunlei; Li, Bicao; Dong, Yan

2018-04-01

Fabric defect detection plays an important role in improving the quality of fabric product. In this paper, a novel fabric defect detection method based on visual saliency using deep feature and low-rank recovery was proposed. First, unsupervised training is carried out by the initial network parameters based on MNIST large datasets. The supervised fine-tuning of fabric image library based on Convolutional Neural Networks (CNNs) is implemented, and then more accurate deep neural network model is generated. Second, the fabric images are uniformly divided into the image block with the same size, then we extract their multi-layer deep features using the trained deep network. Thereafter, all the extracted features are concentrated into a feature matrix. Third, low-rank matrix recovery is adopted to divide the feature matrix into the low-rank matrix which indicates the background and the sparse matrix which indicates the salient defect. In the end, the iterative optimal threshold segmentation algorithm is utilized to segment the saliency maps generated by the sparse matrix to locate the fabric defect area. Experimental results demonstrate that the feature extracted by CNN is more suitable for characterizing the fabric texture than the traditional LBP, HOG and other hand-crafted features extraction method, and the proposed method can accurately detect the defect regions of various fabric defects, even for the image with complex texture.

Multi-Level and Multi-Scale Feature Aggregation Using Pretrained Convolutional Neural Networks for Music Auto-Tagging

NASA Astrophysics Data System (ADS)

Lee, Jongpil; Nam, Juhan

2017-08-01

Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pre-trained convolutional networks separately and aggregate them altogether given a long audio clip. Finally, we put them into fully-connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms previous state-of-the-arts on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

Artificial Neural Network Application in the Diagnosis of Disease Conditions with Liver Ultrasound Images

PubMed Central

Lele, Ramachandra Dattatraya; Joshi, Mukund; Chowdhary, Abhay

2014-01-01

The preliminary study presented within this paper shows a comparative study of various texture features extracted from liver ultrasonic images by employing Multilayer Perceptron (MLP), a type of artificial neural network, to study the presence of disease conditions. An ultrasound (US) image shows echo-texture patterns, which defines the organ characteristics. Ultrasound images of liver disease conditions such as “fatty liver,” “cirrhosis,” and “hepatomegaly” produce distinctive echo patterns. However, various ultrasound imaging artifacts and speckle noise make these echo-texture patterns difficult to identify and often hard to distinguish visually. Here, based on the extracted features from the ultrasonic images, we employed an artificial neural network for the diagnosis of disease conditions in liver and finding of the best classifier that distinguishes between abnormal and normal conditions of the liver. Comparison of the overall performance of all the feature classifiers concluded that “mixed feature set” is the best feature set. It showed an excellent rate of accuracy for the training data set. The gray level run length matrix (GLRLM) feature shows better results when the network was tested against unknown data. PMID:25332717

Finding Statistically Significant Communities in Networks

PubMed Central

Lancichinetti, Andrea; Radicchi, Filippo; Ramasco, José J.; Fortunato, Santo

2011-01-01

Community structure is one of the main structural features of networks, revealing both their internal organization and the similarity of their elementary units. Despite the large variety of methods proposed to detect communities in graphs, there is a big need for multi-purpose techniques, able to handle different types of datasets and the subtleties of community structure. In this paper we present OSLOM (Order Statistics Local Optimization Method), the first method capable to detect clusters in networks accounting for edge directions, edge weights, overlapping communities, hierarchies and community dynamics. It is based on the local optimization of a fitness function expressing the statistical significance of clusters with respect to random fluctuations, which is estimated with tools of Extreme and Order Statistics. OSLOM can be used alone or as a refinement procedure of partitions/covers delivered by other techniques. We have also implemented sequential algorithms combining OSLOM with other fast techniques, so that the community structure of very large networks can be uncovered. Our method has a comparable performance as the best existing algorithms on artificial benchmark graphs. Several applications on real networks are shown as well. OSLOM is implemented in a freely available software (http://www.oslom.org), and we believe it will be a valuable tool in the analysis of networks. PMID:21559480

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 Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

Feature genes in metastatic breast cancer identified by MetaDE and SVM classifier methods.

PubMed

Tuo, Youlin; An, Ning; Zhang, Ming

2018-03-01

The aim of the present study was to investigate the feature genes in metastatic breast cancer samples. A total of 5 expression profiles of metastatic breast cancer samples were downloaded from the Gene Expression Omnibus database, which were then analyzed using the MetaQC and MetaDE packages in R language. The feature genes between metastasis and non‑metastasis samples were screened under the threshold of P<0.05. Based on the protein‑protein interactions (PPIs) in the Biological General Repository for Interaction Datasets, Human Protein Reference Database and Biomolecular Interaction Network Database, the PPI network of the feature genes was constructed. The feature genes identified by topological characteristics were then used for support vector machine (SVM) classifier training and verification. The accuracy of the SVM classifier was then evaluated using another independent dataset from The Cancer Genome Atlas database. Finally, function and pathway enrichment analyses for genes in the SVM classifier were performed. A total of 541 feature genes were identified between metastatic and non‑metastatic samples. The top 10 genes with the highest betweenness centrality values in the PPI network of feature genes were Nuclear RNA Export Factor 1, cyclin‑dependent kinase 2 (CDK2), myelocytomatosis proto‑oncogene protein (MYC), Cullin 5, SHC Adaptor Protein 1, Clathrin heavy chain, Nucleolin, WD repeat domain 1, proteasome 26S subunit non‑ATPase 2 and telomeric repeat binding factor 2. The cyclin‑dependent kinase inhibitor 1A (CDKN1A), E2F transcription factor 1 (E2F1), and MYC interacted with CDK2. The SVM classifier constructed by the top 30 feature genes was able to distinguish metastatic samples from non‑metastatic samples [correct rate, specificity, positive predictive value and negative predictive value >0.89; sensitivity >0.84; area under the receiver operating characteristic curve (AUROC) >0.96]. The verification of the SVM classifier in an independent dataset (35 metastatic samples and 143 non‑metastatic samples) revealed an accuracy of 94.38% and AUROC of 0.958. Cell cycle associated functions and pathways were the most significant terms of the 30 feature genes. A SVM classifier was constructed to assess the possibility of breast cancer metastasis, which presented high accuracy in several independent datasets. CDK2, CDKN1A, E2F1 and MYC were indicated as the potential feature genes in metastatic breast cancer.

Fish swarm intelligent to optimize real time monitoring of chips drying using machine vision

NASA Astrophysics Data System (ADS)

Hendrawan, Y.; Hawa, L. C.; Damayanti, R.

2018-03-01

This study attempted to apply machine vision-based chips drying monitoring system which is able to optimise the drying process of cassava chips. The objective of this study is to propose fish swarm intelligent (FSI) optimization algorithms to find the most significant set of image features suitable for predicting water content of cassava chips during drying process using artificial neural network model (ANN). Feature selection entails choosing the feature subset that maximizes the prediction accuracy of ANN. Multi-Objective Optimization (MOO) was used in this study which consisted of prediction accuracy maximization and feature-subset size minimization. The results showed that the best feature subset i.e. grey mean, L(Lab) Mean, a(Lab) energy, red entropy, hue contrast, and grey homogeneity. The best feature subset has been tested successfully in ANN model to describe the relationship between image features and water content of cassava chips during drying process with R2 of real and predicted data was equal to 0.9.

Reliable Communication Models in Interdependent Critical Infrastructure Networks

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

Lee, Sangkeun; Chinthavali, Supriya; Shankar, Mallikarjun

Modern critical infrastructure networks are becoming increasingly interdependent where the failures in one network may cascade to other dependent networks, causing severe widespread national-scale failures. A number of previous efforts have been made to analyze the resiliency and robustness of interdependent networks based on different models. However, communication network, which plays an important role in today's infrastructures to detect and handle failures, has attracted little attention in the interdependency studies, and no previous models have captured enough practical features in the critical infrastructure networks. In this paper, we study the interdependencies between communication network and other kinds of critical infrastructuremore » networks with an aim to identify vulnerable components and design resilient communication networks. We propose several interdependency models that systematically capture various features and dynamics of failures spreading in critical infrastructure networks. We also discuss several research challenges in building reliable communication solutions to handle failures in these models.« less

Tactile agnosia. Casuistic evidence and theoretical remarks on modality-specific meaning representations and sensorimotor integration.

PubMed

Platz, T

1996-10-01

Somaesthetic, motor and cognitive functions were studied in a man with impaired tactile object-recognition (TOR) in his left hand due to a right parietal convexity meningeoma which had been surgically removed. Primary motor and somatosensory functions were not impaired, and discriminative abilities for various tactile aspects and cognitive skills were preserved. Nevertheless, the patient could often not appreciate the object's nature or significance when it was placed in his left hand and was unable to name or to describe or demonstrate the use of these objects. Therefore, he can be regarded as an example of associative tactile agnosia. The view is taken and elaborated that defective modality-specific meaning representations account for associative tactile agnosia. These meaning representations are conceptualized as learned unimodal feature-entity relationships which are thought to be defective in tactile agnosia. In line with this hypothesis, tactile feature analysis and cross-modal matching of features were largely preserved in the investigated patient, while combining features to form entities was defective in the tactile domain. The alternative hypothesis of agnosia as deficit of cross-modal association of features was not supported. The presumed distributed functional network responsible for TOR is thought to involve perception of features, object recognition and related tactile motor behaviour interactively. A deficit leading primarily to impaired combining features to form entities can therefore be expected to result in additional minor impairment of related perceptual-motor processes. Unilaterality of the gnostic deficit can be explained by a lateralized organization of the functional network responsible for tactile recognition of objects.

Identification of GRB2 and GAB1 Coexpression as an Unfavorable Prognostic Factor for Hepatocellular Carcinoma by a Combination of Expression Profile and Network Analysis

PubMed Central

Yang, Mei; Wang, Danhua; Yu, Lingxiang; Guo, Chaonan; Guo, Xiaodong; Lin, Na

2013-01-01

Aim To screen novel markers for hepatocellular carcinoma (HCC) by a combination of expression profile, interaction network analysis and clinical validation. Methods HCC significant molecules which are differentially expressed or had genetic variations in HCC tissues were obtained from five existing HCC related databases (OncoDB.HCC, HCC.net, dbHCCvar, EHCO and Liverome). Then, the protein-protein interaction (PPI) network of these molecules was constructed. Three topological features of the network ('Degree', 'Betweenness', and 'Closeness') and the k-core algorithm were used to screen candidate HCC markers which play crucial roles in tumorigenesis of HCC. Furthermore, the clinical significance of two candidate HCC markers growth factor receptor-bound 2 (GRB2) and GRB2-associated-binding protein 1 (GAB1) was validated. Results In total, 6179 HCC significant genes and 977 HCC significant proteins were collected from existing HCC related databases. After network analysis, 331 candidate HCC markers were identified. Especially, GAB1 has the highest k-coreness suggesting its central localization in HCC related network, and the interaction between GRB2 and GAB1 has the largest edge-betweenness implying it may be biologically important to the function of HCC related network. As the results of clinical validation, the expression levels of both GRB2 and GAB1 proteins were significantly higher in HCC tissues than those in their adjacent nonneoplastic tissues. More importantly, the combined GRB2 and GAB1 protein expression was significantly associated with aggressive tumor progression and poor prognosis in patients with HCC. Conclusion This study provided an integrative analysis by combining expression profile and interaction network analysis to identify a list of biologically significant HCC related markers and pathways. Further experimental validation indicated that the aberrant expression of GRB2 and GAB1 proteins may be strongly related to tumor progression and prognosis in patients with HCC. The overexpression of GRB2 in combination with upregulation of GAB1 may be an unfavorable prognostic factor for HCC. PMID:24391994

Hierarchical learning architecture with automatic feature selection for multiclass protein fold classification.

PubMed

Huang, Chuen-Der; Lin, Chin-Teng; Pal, Nikhil Ranjan

2003-12-01

The structure classification of proteins plays a very important role in bioinformatics, since the relationships and characteristics among those known proteins can be exploited to predict the structure of new proteins. The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications, the role of appropriate features has not been paid adequate importance. In this investigation we use three novel ideas for multiclass protein fold classification. First, we use the gating neural network, where each input node is associated with a gate. This network can select important features in an online manner when the learning goes on. At the beginning of the training, all gates are almost closed, i.e., no feature is allowed to enter the network. Through the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly, and some gates may be partially open. The second novel idea is to use a hierarchical learning architecture (HLA). The classifier in the first level of HLA classifies the protein features into four major classes: all alpha, all beta, alpha + beta, and alpha/beta. And in the next level we have another set of classifiers, which further classifies the protein features into 27 folds. The third novel idea is to induce the indirect coding features from the amino-acid composition sequence of proteins based on the N-gram concept. This provides us with more representative and discriminative new local features of protein sequences for multiclass protein fold classification. The proposed HLA with new indirect coding features increases the protein fold classification accuracy by about 12%. Moreover, the gating neural network is found to reduce the number of features drastically. Using only half of the original features selected by the gating neural network can reach comparable test accuracy as that using all the original features. The gating mechanism also helps us to get a better insight into the folding process of proteins. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it also reduces the computation time.

Predictive brain networks for major depression in a semi-multimodal fusion hierarchical feature reduction framework.

PubMed

Yang, Jie; Yin, Yingying; Zhang, Zuping; Long, Jun; Dong, Jian; Zhang, Yuqun; Xu, Zhi; Li, Lei; Liu, Jie; Yuan, Yonggui

2018-02-05

Major depressive disorder (MDD) is characterized by dysregulation of distributed structural and functional networks. It is now recognized that structural and functional networks are related at multiple temporal scales. The recent emergence of multimodal fusion methods has made it possible to comprehensively and systematically investigate brain networks and thereby provide essential information for influencing disease diagnosis and prognosis. However, such investigations are hampered by the inconsistent dimensionality features between structural and functional networks. Thus, a semi-multimodal fusion hierarchical feature reduction framework is proposed. Feature reduction is a vital procedure in classification that can be used to eliminate irrelevant and redundant information and thereby improve the accuracy of disease diagnosis. Our proposed framework primarily consists of two steps. The first step considers the connection distances in both structural and functional networks between MDD and healthy control (HC) groups. By adding a constraint based on sparsity regularization, the second step fully utilizes the inter-relationship between the two modalities. However, in contrast to conventional multi-modality multi-task methods, the structural networks were considered to play only a subsidiary role in feature reduction and were not included in the following classification. The proposed method achieved a classification accuracy, specificity, sensitivity, and area under the curve of 84.91%, 88.6%, 81.29%, and 0.91, respectively. Moreover, the frontal-limbic system contributed the most to disease diagnosis. Importantly, by taking full advantage of the complementary information from multimodal neuroimaging data, the selected consensus connections may be highly reliable biomarkers of MDD. Copyright © 2017 Elsevier B.V. All rights reserved.

Diagnosis of helicopter gearboxes using structure-based networks

NASA Technical Reports Server (NTRS)

Jammu, Vinay B.; Danai, Kourosh; Lewicki, David G.

1995-01-01

A connectionist network is introduced for fault diagnosis of helicopter gearboxes that incorporates knowledge of the gearbox structure and characteristics of the vibration features as its fuzzy weights. Diagnosis is performed by propagating the abnormal features of vibration measurements through this Structure-Based Connectionist Network (SBCN), the outputs of which represent the fault possibility values for individual components of the gearbox. The performance of this network is evaluated by applying it to experimental vibration data from an OH-58A helicopter gearbox. The diagnostic results indicate that the network performance is comparable to those obtained from supervised pattern classification.

Dynamic weight evolution network with preferential attachment

NASA Astrophysics Data System (ADS)

Dai, Meifeng; Xie, Qi; Li, Lei

2014-12-01

A dynamic weight evolution network with preferential attachment is introduced. The network includes two significant characteristics. (i) Topological growth: triggered by newly added node with M links at each time step, each new edge carries an initial weight growing nonlinearly with time. (ii) Weight dynamics: the weight between two existing nodes experiences increasing or decreasing in a nonlinear way. By using continuum theory and mean-field method, we study the strength, the degree, the weight and their distributions. We find that the distributions exhibit a power-law feature. In particular, the relationship between the degree and the strength is nonlinear, and the power-law exponents of the three are the same. All the theoretical predictions are successfully contrasted with numerical simulations.

Technology-Mediated ELT Writing: Acceptance and Engagement in an Online Moodle Course

ERIC Educational Resources Information Center

Zyad, Hicham

2016-01-01

In the past fifteen years, Web 2.0 social networking technologies have ushered in a new era of information production, distribution and consumption with significant implications for language teaching and learning. An example of such technology is Moodle, which is a learning management system with several useful features that can transform the…

Considerations on command and response language features for a network of heterogeneous autonomous computers

NASA Technical Reports Server (NTRS)

Engelberg, N.; Shaw, C., III

1984-01-01

The design of a uniform command language to be used in a local area network of heterogeneous, autonomous nodes is considered. After examining the major characteristics of such a network, and after considering the profile of a scientist using the computers on the net as an investigative aid, a set of reasonable requirements for the command language are derived. Taking into account the possible inefficiencies in implementing a guest-layered network operating system and command language on a heterogeneous net, the authors examine command language naming, process/procedure invocation, parameter acquisition, help and response facilities, and other features found in single-node command languages, and conclude that some features may extend simply to the network case, others extend after some restrictions are imposed, and still others require modifications. In addition, it is noted that some requirements considered reasonable (user accounting reports, for example) demand further study before they can be efficiently implemented on a network of the sort described.

Feature selection and definition for contours classification of thermograms in breast cancer detection

NASA Astrophysics Data System (ADS)

Jagodziński, Dariusz; Matysiewicz, Mateusz; Neumann, Łukasz; Nowak, Robert M.; Okuniewski, Rafał; Oleszkiewicz, Witold; Cichosz, Paweł

2016-09-01

This contribution introduces the method of cancer pathologies detection on breast skin temperature distribution images. The use of thermosensitive foils applied to the breasts skin allows to create thermograms, which displays the amount of infrared energy emitted by all breast cells. The significant foci of hyperthermia or inflammation are typical for cancer cells. That foci can be recognized on thermograms as a contours, which are the areas of higher temperature. Every contour can be converted to a feature set that describe it, using the raw, central, Hu, outline, Fourier and colour moments of image pixels processing. This paper defines also the new way of describing a set of contours through theirs neighbourhood relations. Contribution introduces moreover the way of ranking and selecting most relevant features. Authors used Neural Network with Gevrey`s concept and recursive feature elimination, to estimate feature importance.

Haptically Guided Grasping. fMRI Shows Right-Hemisphere Parietal Stimulus Encoding, and Bilateral Dorso-Ventral Parietal Gradients of Object- and Action-Related Processing during Grasp Execution

PubMed Central

Marangon, Mattia; Kubiak, Agnieszka; Króliczak, Gregory

2016-01-01

The neural bases of haptically-guided grasp planning and execution are largely unknown, especially for stimuli having no visual representations. Therefore, we used functional magnetic resonance imaging (fMRI) to monitor brain activity during haptic exploration of novel 3D complex objects, subsequent grasp planning, and the execution of the pre-planned grasps. Haptic object exploration, involving extraction of shape, orientation, and length of the to-be-grasped targets, was associated with the fronto-parietal, temporo-occipital, and insular cortex activity. Yet, only the anterior divisions of the posterior parietal cortex (PPC) of the right hemisphere were significantly more engaged in exploration of complex objects (vs. simple control disks). None of these regions were re-recruited during the planning phase. Even more surprisingly, the left-hemisphere intraparietal, temporal, and occipital areas that were significantly invoked for grasp planning did not show sensitivity to object features. Finally, grasp execution, involving the re-recruitment of the critical right-hemisphere PPC clusters, was also significantly associated with two kinds of bilateral parieto-frontal processes. The first represents transformations of grasp-relevant target features and is linked to the dorso-dorsal (lateral and medial) parieto-frontal networks. The second monitors grasp kinematics and belongs to the ventro-dorsal networks. Indeed, signal modulations associated with these distinct functions follow dorso-ventral gradients, with left aIPS showing significant sensitivity to both target features and the characteristics of the required grasp. Thus, our results from the haptic domain are consistent with the notion that the parietal processing for action guidance reflects primarily transformations from object-related to effector-related coding, and these mechanisms are rather independent of sensory input modality. PMID:26779002

Haptically Guided Grasping. fMRI Shows Right-Hemisphere Parietal Stimulus Encoding, and Bilateral Dorso-Ventral Parietal Gradients of Object- and Action-Related Processing during Grasp Execution.

PubMed

Marangon, Mattia; Kubiak, Agnieszka; Króliczak, Gregory

2015-01-01

The neural bases of haptically-guided grasp planning and execution are largely unknown, especially for stimuli having no visual representations. Therefore, we used functional magnetic resonance imaging (fMRI) to monitor brain activity during haptic exploration of novel 3D complex objects, subsequent grasp planning, and the execution of the pre-planned grasps. Haptic object exploration, involving extraction of shape, orientation, and length of the to-be-grasped targets, was associated with the fronto-parietal, temporo-occipital, and insular cortex activity. Yet, only the anterior divisions of the posterior parietal cortex (PPC) of the right hemisphere were significantly more engaged in exploration of complex objects (vs. simple control disks). None of these regions were re-recruited during the planning phase. Even more surprisingly, the left-hemisphere intraparietal, temporal, and occipital areas that were significantly invoked for grasp planning did not show sensitivity to object features. Finally, grasp execution, involving the re-recruitment of the critical right-hemisphere PPC clusters, was also significantly associated with two kinds of bilateral parieto-frontal processes. The first represents transformations of grasp-relevant target features and is linked to the dorso-dorsal (lateral and medial) parieto-frontal networks. The second monitors grasp kinematics and belongs to the ventro-dorsal networks. Indeed, signal modulations associated with these distinct functions follow dorso-ventral gradients, with left aIPS showing significant sensitivity to both target features and the characteristics of the required grasp. Thus, our results from the haptic domain are consistent with the notion that the parietal processing for action guidance reflects primarily transformations from object-related to effector-related coding, and these mechanisms are rather independent of sensory input modality.

Features of the Correlation Structure of Price Indices

PubMed Central

Gao, Xiangyun; An, Haizhong; Zhong, Weiqiong

2013-01-01

What are the features of the correlation structure of price indices? To answer this question, 5 types of price indices, including 195 specific price indices from 2003 to 2011, were selected as sample data. To build a weighted network of price indices each price index is represented by a vertex, and a positive correlation between two price indices is represented by an edge. We studied the features of the weighted network structure by applying economic theory to the analysis of complex network parameters. We found that the frequency of the price indices follows a normal distribution by counting the weighted degrees of the nodes, and we identified the price indices which have an important impact on the network's structure. We found out small groups in the weighted network by the methods of k-core and k-plex. We discovered structure holes in the network by calculating the hierarchy of the nodes. Finally, we found that the price indices weighted network has a small-world effect by calculating the shortest path. These results provide a scientific basis for macroeconomic control policies. PMID:23593399

Wireless sensor network for wide-area high-mobility applications

NASA Astrophysics Data System (ADS)

del Castillo, Ignacio; Esper-Chaín, Roberto; Tobajas, Félix; de Armas, Valentín.

2013-05-01

In recent years, IEEE 802.15.4-based Wireless Sensor Networks (WSN) have experienced significant growth, mainly motivated by the standard features, such as small size oriented devices, low power consumption nodes, wireless communication links, and sensing and data processing capabilities. In this paper, the development, implementation and deployment of a novel fully compatible IEEE 802.15.4-based WSN architecture for applications operating over extended geographic regions with high node mobility support, is described. In addition, a practical system implementation of the proposed WSN architecture is presented and described for experimental validation and characterization purposes.

Deep learning on temporal-spectral data for anomaly detection

NASA Astrophysics Data System (ADS)

Ma, King; Leung, Henry; Jalilian, Ehsan; Huang, Daniel

2017-05-01

Detecting anomalies is important for continuous monitoring of sensor systems. One significant challenge is to use sensor data and autonomously detect changes that cause different conditions to occur. Using deep learning methods, we are able to monitor and detect changes as a result of some disturbance in the system. We utilize deep neural networks for sequence analysis of time series. We use a multi-step method for anomaly detection. We train the network to learn spectral and temporal features from the acoustic time series. We test our method using fiber-optic acoustic data from a pipeline.

Conceptual Hierarchies in a Flat Attractor Network

PubMed Central

O’Connor, Christopher M.; Cree, George S.; McRae, Ken

2009-01-01

The structure of people’s conceptual knowledge of concrete nouns has traditionally been viewed as hierarchical (Collins & Quillian, 1969). For example, superordinate concepts (vegetable) are assumed to reside at a higher level than basic-level concepts (carrot). A feature-based attractor network with a single layer of semantic features developed representations of both basic-level and superordinate concepts. No hierarchical structure was built into the network. In Experiment and Simulation 1, the graded structure of categories (typicality ratings) is accounted for by the flat attractor-network. Experiment and Simulation 2 show that, as with basic-level concepts, such a network predicts feature verification latencies for superordinate concepts (vegetable ). In Experiment and Simulation 3, counterintuitive results regarding the temporal dynamics of similarity in semantic priming are explained by the model. By treating both types of concepts the same in terms of representation, learning, and computations, the model provides new insights into semantic memory. PMID:19543434

Handwritten digits recognition based on immune network

NASA Astrophysics Data System (ADS)

Li, Yangyang; Wu, Yunhui; Jiao, Lc; Wu, Jianshe

2011-11-01

With the development of society, handwritten digits recognition technique has been widely applied to production and daily life. It is a very difficult task to solve these problems in the field of pattern recognition. In this paper, a new method is presented for handwritten digit recognition. The digit samples firstly are processed and features extraction. Based on these features, a novel immune network classification algorithm is designed and implemented to the handwritten digits recognition. The proposed algorithm is developed by Jerne's immune network model for feature selection and KNN method for classification. Its characteristic is the novel network with parallel commutating and learning. The performance of the proposed method is experimented to the handwritten number datasets MNIST and compared with some other recognition algorithms-KNN, ANN and SVM algorithm. The result shows that the novel classification algorithm based on immune network gives promising performance and stable behavior for handwritten digits recognition.

Detection of pigment network in dermatoscopy images using texture analysis

PubMed Central

Anantha, Murali; Moss, Randy H.; Stoecker, William V.

2011-01-01

Dermatoscopy, also known as dermoscopy or epiluminescence microscopy (ELM), is a non-invasive, in vivo technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. ELM offers a completely new range of visual features. One such prominent feature is the pigment network. Two texture-based algorithms are developed for the detection of pigment network. These methods are applicable to various texture patterns in dermatoscopy images, including patterns that lack fine lines such as cobblestone, follicular, or thickened network patterns. Two texture algorithms, Laws energy masks and the neighborhood gray-level dependence matrix (NGLDM) large number emphasis, were optimized on a set of 155 dermatoscopy images and compared. Results suggest superiority of Laws energy masks for pigment network detection in dermatoscopy images. For both methods, a texel width of 10 pixels or approximately 0.22 mm is found for dermatoscopy images. PMID:15249068

Curvature-processing network in macaque visual cortex

PubMed Central

Yue, Xiaomin; Pourladian, Irene S.; Tootell, Roger B. H.; Ungerleider, Leslie G.

2014-01-01

Our visual environment abounds with curved features. Thus, the goal of understanding visual processing should include the processing of curved features. Using functional magnetic resonance imaging in behaving monkeys, we demonstrated a network of cortical areas selective for the processing of curved features. This network includes three distinct hierarchically organized regions within the ventral visual pathway: a posterior curvature-biased patch (PCP) located in the near-foveal representation of dorsal V4, a middle curvature-biased patch (MCP) located on the ventral lip of the posterior superior temporal sulcus (STS) in area TEO, and an anterior curvature-biased patch (ACP) located just below the STS in anterior area TE. Our results further indicate that the processing of curvature becomes increasingly complex from PCP to ACP. The proximity of the curvature-processing network to the well-known face-processing network suggests a possible functional link between them. PMID:25092328

Evaluation of correlation between CT image features and ERCC1 protein expression in assessing lung cancer prognosis

NASA Astrophysics Data System (ADS)

Tan, Maxine; Emaminejad, Nastaran; Qian, Wei; Sun, Shenshen; Kang, Yan; Guan, Yubao; Lure, Fleming; Zheng, Bin

2014-03-01

Stage I non-small-cell lung cancers (NSCLC) usually have favorable prognosis. However, high percentage of NSCLC patients have cancer relapse after surgery. Accurately predicting cancer prognosis is important to optimally treat and manage the patients to minimize the risk of cancer relapse. Studies have shown that an excision repair crosscomplementing 1 (ERCC1) gene was a potentially useful genetic biomarker to predict prognosis of NSCLC patients. Meanwhile, studies also found that chronic obstructive pulmonary disease (COPD) was highly associated with lung cancer prognosis. In this study, we investigated and evaluated the correlations between COPD image features and ERCC1 gene expression. A database involving 106 NSCLC patients was used. Each patient had a thoracic CT examination and ERCC1 genetic test. We applied a computer-aided detection scheme to segment and quantify COPD image features. A logistic regression method and a multilayer perceptron network were applied to analyze the correlation between the computed COPD image features and ERCC1 protein expression. A multilayer perceptron network (MPN) was also developed to test performance of using COPD-related image features to predict ERCC1 protein expression. A nine feature based logistic regression analysis showed the average COPD feature values in the low and high ERCC1 protein expression groups are significantly different (p < 0.01). Using a five-fold cross validation method, the MPN yielded an area under ROC curve (AUC = 0.669±0.053) in classifying between the low and high ERCC1 expression cases. The study indicates that CT phenotype features are associated with the genetic tests, which may provide supplementary information to help improve accuracy in assessing prognosis of NSCLC patients.

Testing statistical self-similarity in the topology of river networks

USGS Publications Warehouse

Troutman, Brent M.; Mantilla, Ricardo; Gupta, Vijay K.

2010-01-01

Recent work has demonstrated that the topological properties of real river networks deviate significantly from predictions of Shreve's random model. At the same time the property of mean self-similarity postulated by Tokunaga's model is well supported by data. Recently, a new class of network model called random self-similar networks (RSN) that combines self-similarity and randomness has been introduced to replicate important topological features observed in real river networks. We investigate if the hypothesis of statistical self-similarity in the RSN model is supported by data on a set of 30 basins located across the continental United States that encompass a wide range of hydroclimatic variability. We demonstrate that the generators of the RSN model obey a geometric distribution, and self-similarity holds in a statistical sense in 26 of these 30 basins. The parameters describing the distribution of interior and exterior generators are tested to be statistically different and the difference is shown to produce the well-known Hack's law. The inter-basin variability of RSN parameters is found to be statistically significant. We also test generator dependence on two climatic indices, mean annual precipitation and radiative index of dryness. Some indication of climatic influence on the generators is detected, but this influence is not statistically significant with the sample size available. Finally, two key applications of the RSN model to hydrology and geomorphology are briefly discussed.

Evaluating the statistical performance of less applied algorithms in classification of worldview-3 imagery data in an urbanized landscape

NASA Astrophysics Data System (ADS)

Ranaie, Mehrdad; Soffianian, Alireza; Pourmanafi, Saeid; Mirghaffari, Noorollah; Tarkesh, Mostafa

2018-03-01

In recent decade, analyzing the remotely sensed imagery is considered as one of the most common and widely used procedures in the environmental studies. In this case, supervised image classification techniques play a central role. Hence, taking a high resolution Worldview-3 over a mixed urbanized landscape in Iran, three less applied image classification methods including Bagged CART, Stochastic gradient boosting model and Neural network with feature extraction were tested and compared with two prevalent methods: random forest and support vector machine with linear kernel. To do so, each method was run ten time and three validation techniques was used to estimate the accuracy statistics consist of cross validation, independent validation and validation with total of train data. Moreover, using ANOVA and Tukey test, statistical difference significance between the classification methods was significantly surveyed. In general, the results showed that random forest with marginal difference compared to Bagged CART and stochastic gradient boosting model is the best performing method whilst based on independent validation there was no significant difference between the performances of classification methods. It should be finally noted that neural network with feature extraction and linear support vector machine had better processing speed than other.

Prediction of adverse outcomes of acute coronary syndrome using intelligent fusion of triage information with HUMINT

NASA Astrophysics Data System (ADS)

McCullough, Claire L.; Novobilski, Andrew J.; Fesmire, Francis M.

2006-04-01

Faculty from the University of Tennessee at Chattanooga and the University of Tennessee College of Medicine, Chattanooga Unit, have used data mining techniques and neural networks to examine a set of fourteen features, data items, and HUMINT assessments for 2,148 emergency room patients with symptoms possibly indicative of Acute Coronary Syndrome. Specifically, the authors have generated Bayesian networks describing linkages and causality in the data, and have compared them with neural networks. The data includes objective information routinely collected during triage and the physician's initial case assessment, a HUMINT appraisal. Both the neural network and the Bayesian network were used to fuse the disparate types of information with the goal of forecasting thirty-day adverse patient outcome. This paper presents details of the methods of data fusion including both the data mining techniques and the neural network. Results are compared using Receiver Operating Characteristic curves describing the outcomes of both methods, both using only objective features and including the subjective physician's assessment. While preliminary, the results of this continuing study are significant both from the perspective of potential use of the intelligent fusion of biomedical informatics to aid the physician in prescribing treatment necessary to prevent serious adverse outcome from ACS and as a model of fusion of objective data with subjective HUMINT assessment. Possible future work includes extension of successfully demonstrated intelligent fusion methods to other medical applications, and use of decision level fusion to combine results from data mining and neural net approaches for even more accurate outcome prediction.

Spectral Classification of Galaxies at 0.5 <= z <= 1 in the CDFS: The Artificial Neural Network Approach

NASA Astrophysics Data System (ADS)

Teimoorinia, H.

2012-12-01

The aim of this work is to combine spectral energy distribution (SED) fitting with artificial neural network techniques to assign spectral characteristics to a sample of galaxies at 0.5 < z < 1. The sample is selected from the spectroscopic campaign of the ESO/GOODS-South field, with 142 sources having photometric data from the GOODS-MUSIC catalog covering bands between ~0.4 and 24 μm in 10-13 filters. We use the CIGALE code to fit photometric data to Maraston's synthesis spectra to derive mass, specific star formation rate, and age, as well as the best SED of the galaxies. We use the spectral models presented by Kinney et al. as targets in the wavelength interval ~1200-7500 Å. Then a series of neural networks are trained, with average performance ~90%, to classify the best SED in a supervised manner. We consider the effects of the prominent features of the best SED on the performance of the trained networks and also test networks on the galaxy spectra of Coleman et al., which have a lower resolution than the target models. In this way, we conclude that the trained networks take into account all the features of the spectra simultaneously. Using the method, 105 out of 142 galaxies of the sample are classified with high significance. The locus of the classified galaxies in the three graphs of the physical parameters of mass, age, and specific star formation rate appears consistent with the morphological characteristics of the galaxies.

Bridge damage detection using spatiotemporal patterns extracted from dense sensor network

NASA Astrophysics Data System (ADS)

Liu, Chao; Gong, Yongqiang; Laflamme, Simon; Phares, Brent; Sarkar, Soumik

2017-01-01

The alarmingly degrading state of transportation infrastructures combined with their key societal and economic importance calls for automatic condition assessment methods to facilitate smart management of maintenance and repairs. With the advent of ubiquitous sensing and communication capabilities, scalable data-driven approaches is of great interest, as it can utilize large volume of streaming data without requiring detailed physical models that can be inaccurate and computationally expensive to run. Properly designed, a data-driven methodology could enable fast and automatic evaluation of infrastructures, discovery of causal dependencies among various sub-system dynamic responses, and decision making with uncertainties and lack of labeled data. In this work, a spatiotemporal pattern network (STPN) strategy built on symbolic dynamic filtering (SDF) is proposed to explore spatiotemporal behaviors in a bridge network. Data from strain gauges installed on two bridges are generated using finite element simulation for three types of sensor networks from a density perspective (dense, nominal, sparse). Causal relationships among spatially distributed strain data streams are extracted and analyzed for vehicle identification and detection, and for localization of structural degradation in bridges. Multiple case studies show significant capabilities of the proposed approach in: (i) capturing spatiotemporal features to discover causality between bridges (geographically close), (ii) robustness to noise in data for feature extraction, (iii) detecting and localizing damage via comparison of bridge responses to similar vehicle loads, and (iv) implementing real-time health monitoring and decision making work flow for bridge networks. Also, the results demonstrate increased sensitivity in detecting damages and higher reliability in quantifying the damage level with increase in sensor network density.

SPECTRAL CLASSIFICATION OF GALAXIES AT 0.5 {<=} z {<=} 1 IN THE CDFS: THE ARTIFICIAL NEURAL NETWORK APPROACH

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

Teimoorinia, H., E-mail: hteimoo@uvic.ca

2012-12-01

The aim of this work is to combine spectral energy distribution (SED) fitting with artificial neural network techniques to assign spectral characteristics to a sample of galaxies at 0.5 < z < 1. The sample is selected from the spectroscopic campaign of the ESO/GOODS-South field, with 142 sources having photometric data from the GOODS-MUSIC catalog covering bands between {approx}0.4 and 24 {mu}m in 10-13 filters. We use the CIGALE code to fit photometric data to Maraston's synthesis spectra to derive mass, specific star formation rate, and age, as well as the best SED of the galaxies. We use the spectralmore » models presented by Kinney et al. as targets in the wavelength interval {approx}1200-7500 A. Then a series of neural networks are trained, with average performance {approx}90%, to classify the best SED in a supervised manner. We consider the effects of the prominent features of the best SED on the performance of the trained networks and also test networks on the galaxy spectra of Coleman et al., which have a lower resolution than the target models. In this way, we conclude that the trained networks take into account all the features of the spectra simultaneously. Using the method, 105 out of 142 galaxies of the sample are classified with high significance. The locus of the classified galaxies in the three graphs of the physical parameters of mass, age, and specific star formation rate appears consistent with the morphological characteristics of the galaxies.« less

Channel Networks on Large Fans: Refining Analogs for the Ridge-forming Unit, Sinus Meridiani

NASA Technical Reports Server (NTRS)

Wilkinson, Justin

2009-01-01

Stream channels are generally thought of as forming within confined valley settings, separated by interfluves. Sinuous ridges on Mars and Earth are often interpreted as stream channels inverted by subsequent erosion of valley sides. In the case of the ridge-forming unit (RFU), this interpretation fails to explain the (i) close spacing of the ridges, which are (ii) organized in networks, and which (iii) cover large areas (approximately 175,000 km (exp 2)). Channel networks on terrestrial fans develop unconfined by valley slopes. Large fans (100s km long) are low-angle, fluvial features, documented worldwide, with characteristics that address these aspects of the RFU. Ridge patterns Channels on large fans provide an analog for the sinuous and elongated morphology of RFU ridges, but more especially for other patterns such as subparallel, branching and crossing networks. Branches are related to splays (delta-like distributaries are rare), whose channels can rejoin the main channel. Crossing patterns can be caused by even slight sinuosity splay-related side channels often intersect. An avulsion node distant from the fan apex, gives rise to channels with slightly different, and hence intersecting, orientations. Channels on neighboring fans intersect along the common fan margin. 2. Network density Channels are the dominant feature on large terrestrial fans (lakes and dune fields are minor). Inverted landscapes on subsequently eroded fans thus display indurated channels as networks of significantly close-spaced ridges. 3. Channel networks covering large areas Areas of individual large terrestrial fans can reach >200,000 km 2 (105-6 km 2 with nested fans), providing an analog for the wide area distribution of the RFU.

Emergence of rich-club topology and coordinated dynamics in development of hippocampal functional networks in vitro.

PubMed

Schroeter, Manuel S; Charlesworth, Paul; Kitzbichler, Manfred G; Paulsen, Ole; Bullmore, Edward T

2015-04-08

Recent studies demonstrated that the anatomical network of the human brain shows a "rich-club" organization. This complex topological feature implies that highly connected regions, hubs of the large-scale brain network, are more densely interconnected with each other than expected by chance. Rich-club nodes were traversed by a majority of short paths between peripheral regions, underlining their potential importance for efficient global exchange of information between functionally specialized areas of the brain. Network hubs have also been described at the microscale of brain connectivity (so-called "hub neurons"). Their role in shaping synchronous dynamics and forming microcircuit wiring during development, however, is not yet fully understood. The present study aimed to investigate the role of hubs during network development, using multi-electrode arrays and functional connectivity analysis during spontaneous multi-unit activity (MUA) of dissociated primary mouse hippocampal neurons. Over the first 4 weeks in vitro, functional connectivity significantly increased in strength, density, and size, with mature networks demonstrating a robust modular and small-world topology. As expected by a "rich-get-richer" growth rule of network evolution, MUA graphs were found to form rich-clubs at an early stage in development (14 DIV). Later on, rich-club nodes were a consistent topological feature of MUA graphs, demonstrating high nodal strength, efficiency, and centrality. Rich-club nodes were also found to be crucial for MUA dynamics. They often served as broker of spontaneous activity flow, confirming that hub nodes and rich-clubs may play an important role in coordinating functional dynamics at the microcircuit level. Copyright © 2015 the authors 0270-6474/15/355459-12$15.00/0.

Controlling infectious disease through the targeted manipulation of contact network structure

PubMed Central

Gates, M. Carolyn; Woolhouse, Mark E.J.

2015-01-01

Individuals in human and animal populations are linked through dynamic contact networks with characteristic structural features that drive the epidemiology of directly transmissible infectious diseases. Using animal movement data from the British cattle industry as an example, this analysis explores whether disease dynamics can be altered by placing targeted restrictions on contact formation to reconfigure network topology. This was accomplished using a simple network generation algorithm that combined configuration wiring with stochastic block modelling techniques to preserve the weighted in- and out-degree of individual nodes (farms) as well as key demographic characteristics of the individual network connections (movement date, livestock market, and animal production type). We then tested a control strategy based on introducing additional constraints into the network generation algorithm to prevent farms with a high in-degree from selling cattle to farms with a high out-degree as these particular network connections are predicted to have a disproportionately strong role in spreading disease. Results from simple dynamic disease simulation models predicted significantly lower endemic disease prevalences on the trade restricted networks compared to the baseline generated networks. As expected, the relative magnitude of the predicted changes in endemic prevalence was greater for diseases with short infectious periods and low transmission probabilities. Overall, our study findings demonstrate that there is significant potential for controlling multiple infectious diseases simultaneously by manipulating networks to have more epidemiologically favourable topological configurations. Further research is needed to determine whether the economic and social benefits of controlling disease can justify the costs of restricting contact formation. PMID:26342238

Controlling infectious disease through the targeted manipulation of contact network structure.

PubMed

Gates, M Carolyn; Woolhouse, Mark E J

2015-09-01

Individuals in human and animal populations are linked through dynamic contact networks with characteristic structural features that drive the epidemiology of directly transmissible infectious diseases. Using animal movement data from the British cattle industry as an example, this analysis explores whether disease dynamics can be altered by placing targeted restrictions on contact formation to reconfigure network topology. This was accomplished using a simple network generation algorithm that combined configuration wiring with stochastic block modelling techniques to preserve the weighted in- and out-degree of individual nodes (farms) as well as key demographic characteristics of the individual network connections (movement date, livestock market, and animal production type). We then tested a control strategy based on introducing additional constraints into the network generation algorithm to prevent farms with a high in-degree from selling cattle to farms with a high out-degree as these particular network connections are predicted to have a disproportionately strong role in spreading disease. Results from simple dynamic disease simulation models predicted significantly lower endemic disease prevalences on the trade restricted networks compared to the baseline generated networks. As expected, the relative magnitude of the predicted changes in endemic prevalence was greater for diseases with short infectious periods and low transmission probabilities. Overall, our study findings demonstrate that there is significant potential for controlling multiple infectious diseases simultaneously by manipulating networks to have more epidemiologically favourable topological configurations. Further research is needed to determine whether the economic and social benefits of controlling disease can justify the costs of restricting contact formation. Copyright © 2015 The Authors. Published by Elsevier B.V. All rights reserved.

Analyzing the genes related to Alzheimer's disease via a network and pathway-based approach.

PubMed

Hu, Yan-Shi; Xin, Juncai; Hu, Ying; Zhang, Lei; Wang, Ju

2017-04-27

Our understanding of the molecular mechanisms underlying Alzheimer's disease (AD) remains incomplete. Previous studies have revealed that genetic factors provide a significant contribution to the pathogenesis and development of AD. In the past years, numerous genes implicated in this disease have been identified via genetic association studies on candidate genes or at the genome-wide level. However, in many cases, the roles of these genes and their interactions in AD are still unclear. A comprehensive and systematic analysis focusing on the biological function and interactions of these genes in the context of AD will therefore provide valuable insights to understand the molecular features of the disease. In this study, we collected genes potentially associated with AD by screening publications on genetic association studies deposited in PubMed. The major biological themes linked with these genes were then revealed by function and biochemical pathway enrichment analysis, and the relation between the pathways was explored by pathway crosstalk analysis. Furthermore, the network features of these AD-related genes were analyzed in the context of human interactome and an AD-specific network was inferred using the Steiner minimal tree algorithm. We compiled 430 human genes reported to be associated with AD from 823 publications. Biological theme analysis indicated that the biological processes and biochemical pathways related to neurodevelopment, metabolism, cell growth and/or survival, and immunology were enriched in these genes. Pathway crosstalk analysis then revealed that the significantly enriched pathways could be grouped into three interlinked modules-neuronal and metabolic module, cell growth/survival and neuroendocrine pathway module, and immune response-related module-indicating an AD-specific immune-endocrine-neuronal regulatory network. Furthermore, an AD-specific protein network was inferred and novel genes potentially associated with AD were identified. By means of network and pathway-based methodology, we explored the pathogenetic mechanism underlying AD at a systems biology level. Results from our work could provide valuable clues for understanding the molecular mechanism underlying AD. In addition, the framework proposed in this study could be used to investigate the pathological molecular network and genes relevant to other complex diseases or phenotypes.

Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network.

PubMed

Zhang, Junming; Wu, Yan

2018-03-28

Many systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

Robust hepatic vessel segmentation using multi deep convolution network

NASA Astrophysics Data System (ADS)

Kitrungrotsakul, Titinunt; Han, Xian-Hua; Iwamoto, Yutaro; Foruzan, Amir Hossein; Lin, Lanfen; Chen, Yen-Wei

2017-03-01

Extraction of blood vessels of the organ is a challenging task in the area of medical image processing. It is really difficult to get accurate vessel segmentation results even with manually labeling by human being. The difficulty of vessels segmentation is the complicated structure of blood vessels and its large variations that make them hard to recognize. In this paper, we present deep artificial neural network architecture to automatically segment the hepatic vessels from computed tomography (CT) image. We proposed novel deep neural network (DNN) architecture for vessel segmentation from a medical CT volume, which consists of three deep convolution neural networks to extract features from difference planes of CT data. The three networks have share features at the first convolution layer but will separately learn their own features in the second layer. All three networks will join again at the top layer. To validate effectiveness and efficiency of our proposed method, we conduct experiments on 12 CT volumes which training data are randomly generate from 5 CT volumes and 7 using for test. Our network can yield an average dice coefficient 0.830, while 3D deep convolution neural network can yield around 0.7 and multi-scale can yield only 0.6.

Correlation between standardized assessment of concussion scores and small-world brain network in mild traumatic brain injury.

PubMed

Yan, Yan; Song, Jian; Xu, Guozheng; Yao, Shun; Cao, Chenglong; Li, Chang; Peng, Guibao; Du, Hao

2017-10-01

This study investigated the characteristics of the small-world brain network architecture of patients with mild traumatic brain injury (MTBI), and a correlation between brain functional connectivity network properties in the resting-state fMRI and Standardized Assessment of Concussion (SAC) parameters. The neurological conditions of 22 MTBI patients and 17 normal control individuals were evaluated according to the SAC. Resting-state fMRI was performed in all subjects 3 and 7days after injury respectively. After preprocessing the fMRI data, cortex functional regions were marked using AAL90 and Dosenbach160 templates. The small-world network parameters and areas under the integral curves were computed in the range of sparsity from 0.01 to 0.5. Independent-sample t-tests were used to compare these parameters between the MTBI and control group. Significantly different parameters were investigated for correlations with SAC scores; those that correlated were chosen for further curve fitting. The clustering coefficient, the communication efficiency across in local networks, and the strength of connectivity were all higher in MTBI patients relative to control individuals. Parameters in 160 brain regions of the MTBI group significantly correlated with total SAC score and score for attention; the network parameters may be a quadratic function of attention scores of SAC and a cubic function of SAC scores. MTBI patients were characterized by elevated communication efficiency across global brain regions, and in local networks, and strength of mean connectivity. These features may be associated with brain function compensation. The network parameters significantly correlated with SAC total and attention scores. Copyright © 2017 Elsevier Ltd. All rights reserved.

Hierarchy Measure for Complex Networks

PubMed Central

Mones, Enys; Vicsek, Lilla; Vicsek, Tamás

2012-01-01

Nature, technology and society are full of complexity arising from the intricate web of the interactions among the units of the related systems (e.g., proteins, computers, people). Consequently, one of the most successful recent approaches to capturing the fundamental features of the structure and dynamics of complex systems has been the investigation of the networks associated with the above units (nodes) together with their relations (edges). Most complex systems have an inherently hierarchical organization and, correspondingly, the networks behind them also exhibit hierarchical features. Indeed, several papers have been devoted to describing this essential aspect of networks, however, without resulting in a widely accepted, converging concept concerning the quantitative characterization of the level of their hierarchy. Here we develop an approach and propose a quantity (measure) which is simple enough to be widely applicable, reveals a number of universal features of the organization of real-world networks and, as we demonstrate, is capable of capturing the essential features of the structure and the degree of hierarchy in a complex network. The measure we introduce is based on a generalization of the m-reach centrality, which we first extend to directed/partially directed graphs. Then, we define the global reaching centrality (GRC), which is the difference between the maximum and the average value of the generalized reach centralities over the network. We investigate the behavior of the GRC considering both a synthetic model with an adjustable level of hierarchy and real networks. Results for real networks show that our hierarchy measure is related to the controllability of the given system. We also propose a visualization procedure for large complex networks that can be used to obtain an overall qualitative picture about the nature of their hierarchical structure. PMID:22470477

General, crystallized and fluid intelligence are not associated with functional global network efficiency: A replication study with the human connectome project 1200 data set.

PubMed

Kruschwitz, J D; Waller, L; Daedelow, L S; Walter, H; Veer, I M

2018-05-01

One hallmark example of a link between global topological network properties of complex functional brain connectivity and cognitive performance is the finding that general intelligence may depend on the efficiency of the brain's intrinsic functional network architecture. However, although this association has been featured prominently over the course of the last decade, the empirical basis for this broad association of general intelligence and global functional network efficiency is quite limited. In the current study, we set out to replicate the previously reported association between general intelligence and global functional network efficiency using the large sample size and high quality data of the Human Connectome Project, and extended the original study by testing for separate association of crystallized and fluid intelligence with global efficiency, characteristic path length, and global clustering coefficient. We were unable to provide evidence for the proposed association between general intelligence and functional brain network efficiency, as was demonstrated by van den Heuvel et al. (2009), or for any other association with the global network measures employed. More specifically, across multiple network definition schemes, ranging from voxel-level networks to networks of only 100 nodes, no robust associations and only very weak non-significant effects with a maximal R 2 of 0.01 could be observed. Notably, the strongest (non-significant) effects were observed in voxel-level networks. We discuss the possibility that the low power of previous studies and publication bias may have led to false positive results fostering the widely accepted notion of general intelligence being associated to functional global network efficiency. Copyright © 2018 Elsevier Inc. All rights reserved.

Characterization of computer network events through simultaneous feature selection and clustering of intrusion alerts

NASA Astrophysics Data System (ADS)

Chen, Siyue; Leung, Henry; Dondo, Maxwell

2014-05-01

As computer network security threats increase, many organizations implement multiple Network Intrusion Detection Systems (NIDS) to maximize the likelihood of intrusion detection and provide a comprehensive understanding of intrusion activities. However, NIDS trigger a massive number of alerts on a daily basis. This can be overwhelming for computer network security analysts since it is a slow and tedious process to manually analyse each alert produced. Thus, automated and intelligent clustering of alerts is important to reveal the structural correlation of events by grouping alerts with common features. As the nature of computer network attacks, and therefore alerts, is not known in advance, unsupervised alert clustering is a promising approach to achieve this goal. We propose a joint optimization technique for feature selection and clustering to aggregate similar alerts and to reduce the number of alerts that analysts have to handle individually. More precisely, each identified feature is assigned a binary value, which reflects the feature's saliency. This value is treated as a hidden variable and incorporated into a likelihood function for clustering. Since computing the optimal solution of the likelihood function directly is analytically intractable, we use the Expectation-Maximisation (EM) algorithm to iteratively update the hidden variable and use it to maximize the expected likelihood. Our empirical results, using a labelled Defense Advanced Research Projects Agency (DARPA) 2000 reference dataset, show that the proposed method gives better results than the EM clustering without feature selection in terms of the clustering accuracy.

A Quantitative Characterization and Classification of Martian Valley Networks: New Constraints on Mars' Early Climate and Its Variability in Space and Time

NASA Astrophysics Data System (ADS)

Grau Galofre, A.; Jellinek, M.

2014-12-01

Valley networks and outflow channels are among the most arresting features of Mars' surface. Remarkable similarities between the structure and complexity of individual Martian channels with certain fluvial systems on Earth supports a popular picture of a warm wet early Mars. A key assumption in this picture is that "typical" Martian examples adequately capture the average character of the majority of all valley networks. However, a full catalog of the distribution of geomorphologic variability of valley networks over Mars' surface geometry has never been established. Accordingly, we present the first planet-wide map in which we use statistical methods and theoretical arguments to classify Martian channels in terms of the mechanics governing their formation. Using new metrics for the size, shape and complexity of channel networks, which we ground truth against a large suite of terrestrial examples, we distinguish drainage patterns related to glacial, subglacial, fluvial and lava flows. Preliminary results separate lava flows from other flow features and show that these features can be divided into three different groups of increasing complexity. The characteristics of these groups suggest that they represent fluvial, subglacial and glacial features. We show also that the relative proportions of the different groups varies systematically, with higher density of river-like features located in low longitudes and increasing glacial-like features as we move east or west. Our results suggest that the early Martian climate and hydrologic cycle was richer and more diverse than originally thought.

HPNAIDM: The High-Performance Network Anomaly/Intrusion Detection and Mitigation System

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

Chen, Yan

Identifying traffic anomalies and attacks rapidly and accurately is critical for large network operators. With the rapid growth of network bandwidth, such as the next generation DOE UltraScience Network, and fast emergence of new attacks/virus/worms, existing network intrusion detection systems (IDS) are insufficient because they: • Are mostly host-based and not scalable to high-performance networks; • Are mostly signature-based and unable to adaptively recognize flow-level unknown attacks; • Cannot differentiate malicious events from the unintentional anomalies. To address these challenges, we proposed and developed a new paradigm called high-performance network anomaly/intrustion detection and mitigation (HPNAIDM) system. The new paradigm ismore » significantly different from existing IDSes with the following features (research thrusts). • Online traffic recording and analysis on high-speed networks; • Online adaptive flow-level anomaly/intrusion detection and mitigation; • Integrated approach for false positive reduction. Our research prototype and evaluation demonstrate that the HPNAIDM system is highly effective and economically feasible. Beyond satisfying the pre-set goals, we even exceed that significantly (see more details in the next section). Overall, our project harvested 23 publications (2 book chapters, 6 journal papers and 15 peer-reviewed conference/workshop papers). Besides, we built a website for technique dissemination, which hosts two system prototype release to the research community. We also filed a patent application and developed strong international and domestic collaborations which span both academia and industry.« less

Architecture of marine food webs: To be or not be a 'small-world'.

PubMed

Marina, Tomás Ignacio; Saravia, Leonardo A; Cordone, Georgina; Salinas, Vanesa; Doyle, Santiago R; Momo, Fernando R

2018-01-01

The search for general properties in network structure has been a central issue for food web studies in recent years. One such property is the small-world topology that combines a high clustering and a small distance between nodes of the network. This property may increase food web resilience but make them more sensitive to the extinction of connected species. Food web theory has been developed principally from freshwater and terrestrial ecosystems, largely omitting marine habitats. If theory needs to be modified to accommodate observations from marine ecosystems, based on major differences in several topological characteristics is still on debate. Here we investigated if the small-world topology is a common structural pattern in marine food webs. We developed a novel, simple and statistically rigorous method to examine the largest set of complex marine food webs to date. More than half of the analyzed marine networks exhibited a similar or lower characteristic path length than the random expectation, whereas 39% of the webs presented a significantly higher clustering than its random counterpart. Our method proved that 5 out of 28 networks fulfilled both features of the small-world topology: short path length and high clustering. This work represents the first rigorous analysis of the small-world topology and its associated features in high-quality marine networks. We conclude that such topology is a structural pattern that is not maximized in marine food webs; thus it is probably not an effective model to study robustness, stability and feasibility of marine ecosystems.

The improved degree of urban road traffic network: A case study of Xiamen, China

NASA Astrophysics Data System (ADS)

Wang, Shiguang; Zheng, Lili; Yu, Dexin

2017-03-01

The complex network theory is applied to the study of urban road traffic network topology, and we constructed a new measure to characterize an urban road network. It is inspiring to quantify the interaction more appropriately between nodes in complex networks, especially in the field of traffic. The measure takes into account properties of lanes (e.g. number of lanes, width, traffic direction). As much, it is a more comprehensive measure in comparison to previous network measures. It can be used to grasp the features of urban street network more clearly. We applied this measure to the road network in Xiamen, China. Based on a standard method from statistical physics, we examined in more detail the distribution of this new measure and found that (1) due to the limitation of space geographic attributes, traditional research conclusions acquired by using the original definition of degree to study the primal approach modeled urban street network are not very persuasive; (2) both of the direction of the network connection and the degree's odd or even classifications need to be analyzed specifically; (3) the improved degree distribution presents obvious hierarchy, and hierarchical values conform to the power-law distribution, and correlation of our new measure shows some significant segmentation of the urban road network.

Right-side-stretched multifractal spectra indicate small-worldness in networks

NASA Astrophysics Data System (ADS)

Oświȩcimka, Paweł; Livi, Lorenzo; Drożdż, Stanisław

2018-04-01

Complex network formalism allows to explain the behavior of systems composed by interacting units. Several prototypical network models have been proposed thus far. The small-world model has been introduced to mimic two important features observed in real-world systems: i) local clustering and ii) the possibility to move across a network by means of long-range links that significantly reduce the characteristic path length. A natural question would be whether there exist several ;types; of small-world architectures, giving rise to a continuum of models with properties (partially) shared with other models belonging to different network families. Here, we take advantage of the interplay between network theory and time series analysis and propose to investigate small-world signatures in complex networks by analyzing multifractal characteristics of time series generated from such networks. In particular, we suggest that the degree of right-sided asymmetry of multifractal spectra is linked with the degree of small-worldness present in networks. This claim is supported by numerical simulations performed on several parametric models, including prototypical small-world networks, scale-free, fractal and also real-world networks describing protein molecules. Our results also indicate that right-sided asymmetry emerges with the presence of the following topological properties: low edge density, low average shortest path, and high clustering coefficient.

A Comprehensive Pan-Cancer Molecular Study of Gynecologic and Breast Cancers. | Office of Cancer Genomics

Cancer.gov

We analyzed molecular data on 2,579 tumors from The Cancer Genome Atlas (TCGA) of four gynecological types plus breast. Our aims were to identify shared and unique molecular features, clinically significant subtypes, and potential therapeutic targets. We found 61 somatic copy-number alterations (SCNAs) and 46 significantly mutated genes (SMGs). Eleven SCNAs and 11 SMGs had not been identified in previous TCGA studies of the individual tumor types. We found functionally significant estrogen receptor-regulated long non-coding RNAs (lncRNAs) and gene/lncRNA interaction networks.

Assessment of Overlap of Phylogenetic Transmission Clusters and Communities in Simple Sexual Contact Networks: Applications to HIV-1

PubMed Central

Villandre, Luc; Günthard, Huldrych F.; Kouyos, Roger; Stadler, Tanja

2016-01-01

Background Transmission patterns of sexually-transmitted infections (STIs) could relate to the structure of the underlying sexual contact network, whose features are therefore of interest to clinicians. Conventionally, we represent sexual contacts in a population with a graph, that can reveal the existence of communities. Phylogenetic methods help infer the history of an epidemic and incidentally, may help detecting communities. In particular, phylogenetic analyses of HIV-1 epidemics among men who have sex with men (MSM) have revealed the existence of large transmission clusters, possibly resulting from within-community transmissions. Past studies have explored the association between contact networks and phylogenies, including transmission clusters, producing conflicting conclusions about whether network features significantly affect observed transmission history. As far as we know however, none of them thoroughly investigated the role of communities, defined with respect to the network graph, in the observation of clusters. Methods The present study investigates, through simulations, community detection from phylogenies. We simulate a large number of epidemics over both unweighted and weighted, undirected random interconnected-islands networks, with islands corresponding to communities. We use weighting to modulate distance between islands. We translate each epidemic into a phylogeny, that lets us partition our samples of infected subjects into transmission clusters, based on several common definitions from the literature. We measure similarity between subjects’ island membership indices and transmission cluster membership indices with the adjusted Rand index. Results and Conclusion Analyses reveal modest mean correspondence between communities in graphs and phylogenetic transmission clusters. We conclude that common methods often have limited success in detecting contact network communities from phylogenies. The rarely-fulfilled requirement that network communities correspond to clades in the phylogeny is their main drawback. Understanding the link between transmission clusters and communities in sexual contact networks could help inform policymaking to curb HIV incidence in MSMs. PMID:26863322

Constructing storyboards based on hierarchical clustering analysis

NASA Astrophysics Data System (ADS)

Hasebe, Satoshi; Sami, Mustafa M.; Muramatsu, Shogo; Kikuchi, Hisakazu

2005-07-01

There are growing needs for quick preview of video contents for the purpose of improving accessibility of video archives as well as reducing network traffics. In this paper, a storyboard that contains a user-specified number of keyframes is produced from a given video sequence. It is based on hierarchical cluster analysis of feature vectors that are derived from wavelet coefficients of video frames. Consistent use of extracted feature vectors is the key to avoid a repetition of computationally-intensive parsing of the same video sequence. Experimental results suggest that a significant reduction in computational time is gained by this strategy.

Gift-giving and network structure in rural China: utilizing long-term spontaneous gift records.

PubMed

Chen, Xi

2014-01-01

The tradition of keeping written records of gift received during household ceremonies in many countries offers researchers an underutilized means of data collection for social network analysis. This paper first summarizes unique features of the gift record data that circumvent five prevailing sampling and measurement issues in the literature, and we discuss their advantages over existing studies at both the individual level and the dyadic link level using previous data sources. We then document our research project in rural China that implements a multiple wave census-type household survey and a long-term gift record collection. The pattern of gift-giving in major household social events and its recent escalation is analyzed. There are significantly positive correlations between gift network centrality and various forms of informal insurance. Finally, economic inequality and competitive marriage market are among the main demographic and socioeconomic determinants of the observed gift network structure.

Gift-Giving and Network Structure in Rural China: Utilizing Long-Term Spontaneous Gift Records

PubMed Central

Chen, Xi

2014-01-01

The tradition of keeping written records of gift received during household ceremonies in many countries offers researchers an underutilized means of data collection for social network analysis. This paper first summarizes unique features of the gift record data that circumvent five prevailing sampling and measurement issues in the literature, and we discuss their advantages over existing studies at both the individual level and the dyadic link level using previous data sources. We then document our research project in rural China that implements a multiple wave census-type household survey and a long-term gift record collection. The pattern of gift-giving in major household social events and its recent escalation is analyzed. There are significantly positive correlations between gift network centrality and various forms of informal insurance. Finally, economic inequality and competitive marriage market are among the main demographic and socioeconomic determinants of the observed gift network structure. PMID:25111696

Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis

NASA Astrophysics Data System (ADS)

Hsu, Kuo-Lin; Gupta, Hoshin V.; Gao, Xiaogang; Sorooshian, Soroosh; Imam, Bisher

2002-12-01

Artificial neural networks (ANNs) can be useful in the prediction of hydrologic variables, such as streamflow, particularly when the underlying processes have complex nonlinear interrelationships. However, conventional ANN structures suffer from network training issues that significantly limit their widespread application. This paper presents a multivariate ANN procedure entitled self-organizing linear output map (SOLO), whose structure has been designed for rapid, precise, and inexpensive estimation of network structure/parameters and system outputs. More important, SOLO provides features that facilitate insight into the underlying processes, thereby extending its usefulness beyond forecast applications as a tool for scientific investigations. These characteristics are demonstrated using a classic rainfall-runoff forecasting problem. Various aspects of model performance are evaluated in comparison with other commonly used modeling approaches, including multilayer feedforward ANNs, linear time series modeling, and conceptual rainfall-runoff modeling.

Characterizing cartilage microarchitecture on phase-contrast x-ray computed tomography using deep learning with convolutional neural networks

NASA Astrophysics Data System (ADS)

Deng, Botao; Abidin, Anas Z.; D'Souza, Adora M.; Nagarajan, Mahesh B.; Coan, Paola; Wismüller, Axel

2017-03-01

The effectiveness of phase contrast X-ray computed tomography (PCI-CT) in visualizing human patellar cartilage matrix has been demonstrated due to its ability to capture soft tissue contrast on a micrometer resolution scale. Recent studies have shown that off-the-shelf Convolutional Neural Network (CNN) features learned from a nonmedical data set can be used for medical image classification. In this paper, we investigate the ability of features extracted from two different CNNs for characterizing chondrocyte patterns in the cartilage matrix. We obtained features from 842 regions of interest annotated on PCI-CT images of human patellar cartilage using CaffeNet and Inception-v3 Network, which were then used in a machine learning task involving support vector machines with radial basis function kernel to classify the ROIs as healthy or osteoarthritic. Classification performance was evaluated using the area (AUC) under the Receiver Operating Characteristic (ROC) curve. The best classification performance was observed with features from Inception-v3 network (AUC = 0.95), which outperforms features extracted from CaffeNet (AUC = 0.91). These results suggest that such characterization of chondrocyte patterns using features from internal layers of CNNs can be used to distinguish between healthy and osteoarthritic tissue with high accuracy.

Network-induced oscillatory behavior in material flow networks and irregular business cycles

NASA Astrophysics Data System (ADS)

Helbing, Dirk; Lämmer, Stefen; Witt, Ulrich; Brenner, Thomas

2004-11-01

Network theory is rapidly changing our understanding of complex systems, but the relevance of topological features for the dynamic behavior of metabolic networks, food webs, production systems, information networks, or cascade failures of power grids remains to be explored. Based on a simple model of supply networks, we offer an interpretation of instabilities and oscillations observed in biological, ecological, economic, and engineering systems. We find that most supply networks display damped oscillations, even when their units—and linear chains of these units—behave in a nonoscillatory way. Moreover, networks of damped oscillators tend to produce growing oscillations. This surprising behavior offers, for example, a different interpretation of business cycles and of oscillating or pulsating processes. The network structure of material flows itself turns out to be a source of instability, and cyclical variations are an inherent feature of decentralized adjustments.

Attentional Bias in Human Category Learning: The Case of Deep Learning.

PubMed

Hanson, Catherine; Caglar, Leyla Roskan; Hanson, Stephen José

2018-01-01

Category learning performance is influenced by both the nature of the category's structure and the way category features are processed during learning. Shepard (1964, 1987) showed that stimuli can have structures with features that are statistically uncorrelated (separable) or statistically correlated (integral) within categories. Humans find it much easier to learn categories having separable features, especially when attention to only a subset of relevant features is required, and harder to learn categories having integral features, which require consideration of all of the available features and integration of all the relevant category features satisfying the category rule (Garner, 1974). In contrast to humans, a single hidden layer backpropagation (BP) neural network has been shown to learn both separable and integral categories equally easily, independent of the category rule (Kruschke, 1993). This "failure" to replicate human category performance appeared to be strong evidence that connectionist networks were incapable of modeling human attentional bias. We tested the presumed limitations of attentional bias in networks in two ways: (1) by having networks learn categories with exemplars that have high feature complexity in contrast to the low dimensional stimuli previously used, and (2) by investigating whether a Deep Learning (DL) network, which has demonstrated humanlike performance in many different kinds of tasks (language translation, autonomous driving, etc.), would display human-like attentional bias during category learning. We were able to show a number of interesting results. First, we replicated the failure of BP to differentially process integral and separable category structures when low dimensional stimuli are used (Garner, 1974; Kruschke, 1993). Second, we show that using the same low dimensional stimuli, Deep Learning (DL), unlike BP but similar to humans, learns separable category structures more quickly than integral category structures. Third, we show that even BP can exhibit human like learning differences between integral and separable category structures when high dimensional stimuli (face exemplars) are used. We conclude, after visualizing the hidden unit representations, that DL appears to extend initial learning due to feature development thereby reducing destructive feature competition by incrementally refining feature detectors throughout later layers until a tipping point (in terms of error) is reached resulting in rapid asymptotic learning.

Predicting clinical symptoms of attention deficit hyperactivity disorder based on temporal patterns between and within intrinsic connectivity networks.

PubMed

Wang, Xun-Heng; Jiao, Yun; Li, Lihua

2017-10-24

Attention deficit hyperactivity disorder (ADHD) is a common brain disorder with high prevalence in school-age children. Previously developed machine learning-based methods have discriminated patients with ADHD from normal controls by providing label information of the disease for individuals. Inattention and impulsivity are the two most significant clinical symptoms of ADHD. However, predicting clinical symptoms (i.e., inattention and impulsivity) is a challenging task based on neuroimaging data. The goal of this study is twofold: to build predictive models for clinical symptoms of ADHD based on resting-state fMRI and to mine brain networks for predictive patterns of inattention and impulsivity. To achieve this goal, a cohort of 74 boys with ADHD and a cohort of 69 age-matched normal controls were recruited from the ADHD-200 Consortium. Both structural and resting-state fMRI images were obtained for each participant. Temporal patterns between and within intrinsic connectivity networks (ICNs) were applied as raw features in the predictive models. Specifically, sample entropy was taken asan intra-ICN feature, and phase synchronization (PS) was used asan inter-ICN feature. The predictive models were based on the least absolute shrinkage and selectionator operator (LASSO) algorithm. The performance of the predictive model for inattention is r=0.79 (p<10 -8 ), and the performance of the predictive model for impulsivity is r=0.48 (p<10 -8 ). The ICN-related predictive patterns may provide valuable information for investigating the brain network mechanisms of ADHD. In summary, the predictive models for clinical symptoms could be beneficial for personalizing ADHD medications. Copyright © 2017 IBRO. Published by Elsevier Ltd. All rights reserved.

Unsupervised Pattern Classifier for Abnormality-Scaling of Vibration Features for Helicopter Gearbox Fault Diagnosis

NASA Technical Reports Server (NTRS)

Jammu, Vinay B.; Danai, Kourosh; Lewicki, David G.

1996-01-01

A new unsupervised pattern classifier is introduced for on-line detection of abnormality in features of vibration that are used for fault diagnosis of helicopter gearboxes. This classifier compares vibration features with their respective normal values and assigns them a value in (0, 1) to reflect their degree of abnormality. Therefore, the salient feature of this classifier is that it does not require feature values associated with faulty cases to identify abnormality. In order to cope with noise and changes in the operating conditions, an adaptation algorithm is incorporated that continually updates the normal values of the features. The proposed classifier is tested using experimental vibration features obtained from an OH-58A main rotor gearbox. The overall performance of this classifier is then evaluated by integrating the abnormality-scaled features for detection of faults. The fault detection results indicate that the performance of this classifier is comparable to the leading unsupervised neural networks: Kohonen's Feature Mapping and Adaptive Resonance Theory (AR72). This is significant considering that the independence of this classifier from fault-related features makes it uniquely suited to abnormality-scaling of vibration features for fault diagnosis.

Deep visual-semantic for crowded video understanding

NASA Astrophysics Data System (ADS)

Deng, Chunhua; Zhang, Junwen

2018-03-01

Visual-semantic features play a vital role for crowded video understanding. Convolutional Neural Networks (CNNs) have experienced a significant breakthrough in learning representations from images. However, the learning of visualsemantic features, and how it can be effectively extracted for video analysis, still remains a challenging task. In this study, we propose a novel visual-semantic method to capture both appearance and dynamic representations. In particular, we propose a spatial context method, based on the fractional Fisher vector (FV) encoding on CNN features, which can be regarded as our main contribution. In addition, to capture temporal context information, we also applied fractional encoding method on dynamic images. Experimental results on the WWW crowed video dataset demonstrate that the proposed method outperform the state of the art.

The Face-Processing Network Is Resilient to Focal Resection of Human Visual Cortex

PubMed Central

Jonas, Jacques; Gomez, Jesse; Maillard, Louis; Brissart, Hélène; Hossu, Gabriela; Jacques, Corentin; Loftus, David; Colnat-Coulbois, Sophie; Stigliani, Anthony; Barnett, Michael A.; Grill-Spector, Kalanit; Rossion, Bruno

2016-01-01

Human face perception requires a network of brain regions distributed throughout the occipital and temporal lobes with a right hemisphere advantage. Present theories consider this network as either a processing hierarchy beginning with the inferior occipital gyrus (occipital face area; IOG-faces/OFA) or a multiple-route network with nonhierarchical components. The former predicts that removing IOG-faces/OFA will detrimentally affect downstream stages, whereas the latter does not. We tested this prediction in a human patient (Patient S.P.) requiring removal of the right inferior occipital cortex, including IOG-faces/OFA. We acquired multiple fMRI measurements in Patient S.P. before and after a preplanned surgery and multiple measurements in typical controls, enabling both within-subject/across-session comparisons (Patient S.P. before resection vs Patient S.P. after resection) and between-subject/across-session comparisons (Patient S.P. vs controls). We found that the spatial topology and selectivity of downstream ipsilateral face-selective regions were stable 1 and 8 month(s) after surgery. Additionally, the reliability of distributed patterns of face selectivity in Patient S.P. before versus after resection was not different from across-session reliability in controls. Nevertheless, postoperatively, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1 of the resected hemisphere. Diffusion weighted imaging in Patient S.P. and controls identifies white matter tracts connecting retinotopic areas to downstream face-selective regions, which may contribute to the stable and plastic features of the face network in Patient S.P. after surgery. Together, our results support a multiple-route network of face processing with nonhierarchical components and shed light on stable and plastic features of high-level visual cortex following focal brain damage. SIGNIFICANCE STATEMENT Brain networks consist of interconnected functional regions commonly organized in processing hierarchies. Prevailing theories predict that damage to the input of the hierarchy will detrimentally affect later stages. We tested this prediction with multiple brain measurements in a rare human patient requiring surgical removal of the putative input to a network processing faces. Surprisingly, the spatial topology and selectivity of downstream face-selective regions are stable after surgery. Nevertheless, representations of visual space were typical in dorsal face-selective regions but atypical in ventral face-selective regions and V1. White matter connections from outside the face network may support these stable and plastic features. As processing hierarchies are ubiquitous in biological and nonbiological systems, our results have pervasive implications for understanding the construction of resilient networks. PMID:27511014

Dynamic transcriptional signatures and network responses for clinical symptoms in influenza-infected human subjects using systems biology approaches.

PubMed

Linel, Patrice; Wu, Shuang; Deng, Nan; Wu, Hulin

2014-10-01

Recent studies demonstrate that human blood transcriptional signatures may be used to support diagnosis and clinical decisions for acute respiratory viral infections such as influenza. In this article, we propose to use a newly developed systems biology approach for time course gene expression data to identify significant dynamically response genes and dynamic gene network responses to viral infection. We illustrate the methodological pipeline by reanalyzing the time course gene expression data from a study with healthy human subjects challenged by live influenza virus. We observed clear differences in the number of significant dynamic response genes (DRGs) between the symptomatic and asymptomatic subjects and also identified DRG signatures for symptomatic subjects with influenza infection. The 505 common DRGs shared by the symptomatic subjects have high consistency with the signature genes for predicting viral infection identified in previous works. The temporal response patterns and network response features were carefully analyzed and investigated.

Min-max hyperellipsoidal clustering for anomaly detection in network security.

PubMed

Sarasamma, Suseela T; Zhu, Qiuming A

2006-08-01

A novel hyperellipsoidal clustering technique is presented for an intrusion-detection system in network security. Hyperellipsoidal clusters toward maximum intracluster similarity and minimum intercluster similarity are generated from training data sets. The novelty of the technique lies in the fact that the parameters needed to construct higher order data models in general multivariate Gaussian functions are incrementally derived from the data sets using accretive processes. The technique is implemented in a feedforward neural network that uses a Gaussian radial basis function as the model generator. An evaluation based on the inclusiveness and exclusiveness of samples with respect to specific criteria is applied to accretively learn the output clusters of the neural network. One significant advantage of this is its ability to detect individual anomaly types that are hard to detect with other anomaly-detection schemes. Applying this technique, several feature subsets of the tcptrace network-connection records that give above 95% detection at false-positive rates below 5% were identified.

Learning target masks in infrared linescan imagery

NASA Astrophysics Data System (ADS)

Fechner, Thomas; Rockinger, Oliver; Vogler, Axel; Knappe, Peter

1997-04-01

In this paper we propose a neural network based method for the automatic detection of ground targets in airborne infrared linescan imagery. Instead of using a dedicated feature extraction stage followed by a classification procedure, we propose the following three step scheme: In the first step of the recognition process, the input image is decomposed into its pyramid representation, thus obtaining a multiresolution signal representation. At the lowest three levels of the Laplacian pyramid a neural network filter of moderate size is trained to indicate the target location. The last step consists of a fusion process of the several neural network filters to obtain the final result. To perform this fusion we use a belief network to combine the various filter outputs in a statistical meaningful way. In addition, the belief network allows the integration of further knowledge about the image domain. By applying this multiresolution recognition scheme, we obtain a nearly scale- and rotational invariant target recognition with a significantly decreased false alarm rate compared with a single resolution target recognition scheme.

Modeling structure and resilience of the dark network.

PubMed

De Domenico, Manlio; Arenas, Alex

2017-02-01

While the statistical and resilience properties of the Internet are no longer changing significantly across time, the Darknet, a network devoted to keep anonymous its traffic, still experiences rapid changes to improve the security of its users. Here we study the structure of the Darknet and find that its topology is rather peculiar, being characterized by a nonhomogeneous distribution of connections, typical of scale-free networks; very short path lengths and high clustering, typical of small-world networks; and lack of a core of highly connected nodes. We propose a model to reproduce such features, demonstrating that the mechanisms used to improve cybersecurity are responsible for the observed topology. Unexpectedly, we reveal that its peculiar structure makes the Darknet much more resilient than the Internet (used as a benchmark for comparison at a descriptive level) to random failures, targeted attacks, and cascade failures, as a result of adaptive changes in response to the attempts of dismantling the network across time.

Data management issues in mobile ad hoc networks

PubMed Central

HARA, Takahiro

2017-01-01

Research on mobile ad hoc networks (MANETs) has become a hot research topic since the middle 1990’s. Over the first decade, most research focused on networking techniques, ignoring data management issues. We, however, realized early the importance of data management in MANETs, and have been conducting studies in this area for 15 years. In this review, we summarize some key technical issues related to data management in MANETs, and the studies we have done in addressing these issues, which include placement of data replicas, update management, and query processing with security management. The techniques proposed in our studies have been designed with deep considerations of MANET features including network partitioning, node participation/disappearance, limited network bandwidth, and energy efficiency. Our studies published in early 2000’s have developed a new research field as data management in MANETs. Also, our recent studies are expected to be significant guidelines of new research directions. We conclude the review by discussing some future directions for research. PMID:28496052

Data management issues in mobile ad hoc networks.

PubMed

Hara, Takahiro

2017-01-01

Research on mobile ad hoc networks (MANETs) has become a hot research topic since the middle 1990's. Over the first decade, most research focused on networking techniques, ignoring data management issues. We, however, realized early the importance of data management in MANETs, and have been conducting studies in this area for 15 years. In this review, we summarize some key technical issues related to data management in MANETs, and the studies we have done in addressing these issues, which include placement of data replicas, update management, and query processing with security management. The techniques proposed in our studies have been designed with deep considerations of MANET features including network partitioning, node participation/disappearance, limited network bandwidth, and energy efficiency. Our studies published in early 2000's have developed a new research field as data management in MANETs. Also, our recent studies are expected to be significant guidelines of new research directions. We conclude the review by discussing some future directions for research.

Modeling structure and resilience of the dark network

NASA Astrophysics Data System (ADS)

De Domenico, Manlio; Arenas, Alex

2017-02-01

While the statistical and resilience properties of the Internet are no longer changing significantly across time, the Darknet, a network devoted to keep anonymous its traffic, still experiences rapid changes to improve the security of its users. Here we study the structure of the Darknet and find that its topology is rather peculiar, being characterized by a nonhomogeneous distribution of connections, typical of scale-free networks; very short path lengths and high clustering, typical of small-world networks; and lack of a core of highly connected nodes. We propose a model to reproduce such features, demonstrating that the mechanisms used to improve cybersecurity are responsible for the observed topology. Unexpectedly, we reveal that its peculiar structure makes the Darknet much more resilient than the Internet (used as a benchmark for comparison at a descriptive level) to random failures, targeted attacks, and cascade failures, as a result of adaptive changes in response to the attempts of dismantling the network across time.

Inferring the interplay between network structure and market effects in Bitcoin

NASA Astrophysics Data System (ADS)

Kondor, Dániel; Csabai, István; Szüle, János; Pósfai, Márton; Vattay, Gábor

2014-12-01

A main focus in economics research is understanding the time series of prices of goods and assets. While statistical models using only the properties of the time series itself have been successful in many aspects, we expect to gain a better understanding of the phenomena involved if we can model the underlying system of interacting agents. In this article, we consider the history of Bitcoin, a novel digital currency system, for which the complete list of transactions is available for analysis. Using this dataset, we reconstruct the transaction network between users and analyze changes in the structure of the subgraph induced by the most active users. Our approach is based on the unsupervised identification of important features of the time variation of the network. Applying the widely used method of Principal Component Analysis to the matrix constructed from snapshots of the network at different times, we are able to show how structural changes in the network accompany significant changes in the exchange price of bitcoins.

An Investigation of the Application of Artificial Neural Networks to Adaptive Optics Imaging Systems

DTIC Science & Technology

1991-12-01

neural network and the feedforward neural network studied is the single layer perceptron artificial neural network . The recurrent artificial neural network input...features are the wavefront sensor slope outputs and neighboring actuator feedback commands. The feedforward artificial neural network input

Implications of network structure on public health collaboratives.

PubMed

Retrum, Jessica H; Chapman, Carrie L; Varda, Danielle M

2013-10-01

Interorganizational collaboration is an essential function of public health agencies. These partnerships form social networks that involve diverse types of partners and varying levels of interaction. Such collaborations are widely accepted and encouraged, yet very little comparative research exists on how public health partnerships develop and evolve, specifically in terms of how subsequent network structures are linked to outcomes. A systems science approach, that is, one that considers the interdependencies and nested features of networks, provides the appropriate methods to examine the complex nature of these networks. Applying Mays and Scutchfields's categorization of "structural signatures" (breadth, density, and centralization), this research examines how network structure influences the outcomes of public health collaboratives. Secondary data from the Program to Analyze, Record, and Track Networks to Enhance Relationships (www.partnertool.net) data set are analyzed. This data set consists of dyadic (N = 12,355), organizational (N = 2,486), and whole network (N = 99) data from public health collaborations around the United States. Network data are used to calculate structural signatures and weighted least squares regression is used to examine how network structures can predict selected intermediary outcomes (resource contributions, overall value and trust rankings, and outcomes) in public health collaboratives. Our findings suggest that network structure may have an influence on collaborative-related outcomes. The structural signature that had the most significant relationship to outcomes was density, with higher density indicating more positive outcomes. Also significant was the finding that more breadth creates new challenges such as difficulty in reaching consensus and creating ties with other members. However, assumptions that these structural components lead to improved outcomes for public health collaboratives may be slightly premature. Implications of these findings for research and practice are discussed.

Optical implementation of a feature-based neural network with application to automatic target recognition

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

Automatic target recognition using a feature-based optical neural network

NASA Technical Reports Server (NTRS)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Residual Shuffling Convolutional Neural Networks for Deep Semantic Image Segmentation Using Multi-Modal Data

NASA Astrophysics Data System (ADS)

Chen, K.; Weinmann, M.; Gao, X.; Yan, M.; Hinz, S.; Jutzi, B.; Weinmann, M.

2018-05-01

In this paper, we address the deep semantic segmentation of aerial imagery based on multi-modal data. Given multi-modal data composed of true orthophotos and the corresponding Digital Surface Models (DSMs), we extract a variety of hand-crafted radiometric and geometric features which are provided separately and in different combinations as input to a modern deep learning framework. The latter is represented by a Residual Shuffling Convolutional Neural Network (RSCNN) combining the characteristics of a Residual Network with the advantages of atrous convolution and a shuffling operator to achieve a dense semantic labeling. Via performance evaluation on a benchmark dataset, we analyze the value of different feature sets for the semantic segmentation task. The derived results reveal that the use of radiometric features yields better classification results than the use of geometric features for the considered dataset. Furthermore, the consideration of data on both modalities leads to an improvement of the classification results. However, the derived results also indicate that the use of all defined features is less favorable than the use of selected features. Consequently, data representations derived via feature extraction and feature selection techniques still provide a gain if used as the basis for deep semantic segmentation.

Classifying dysmorphic syndromes by using artificial neural network based hierarchical decision tree.

PubMed

Özdemir, Merve Erkınay; Telatar, Ziya; Eroğul, Osman; Tunca, Yusuf

2018-05-01

Dysmorphic syndromes have different facial malformations. These malformations are significant to an early diagnosis of dysmorphic syndromes and contain distinctive information for face recognition. In this study we define the certain features of each syndrome by considering facial malformations and classify Fragile X, Hurler, Prader Willi, Down, Wolf Hirschhorn syndromes and healthy groups automatically. The reference points are marked on the face images and ratios between the points' distances are taken into consideration as features. We suggest a neural network based hierarchical decision tree structure in order to classify the syndrome types. We also implement k-nearest neighbor (k-NN) and artificial neural network (ANN) classifiers to compare classification accuracy with our hierarchical decision tree. The classification accuracy is 50, 73 and 86.7% with k-NN, ANN and hierarchical decision tree methods, respectively. Then, the same images are shown to a clinical expert who achieve a recognition rate of 46.7%. We develop an efficient system to recognize different syndrome types automatically in a simple, non-invasive imaging data, which is independent from the patient's age, sex and race at high accuracy. The promising results indicate that our method can be used for pre-diagnosis of the dysmorphic syndromes by clinical experts.

Evolutionary features of academic articles co-keyword network and keywords co-occurrence network: Based on two-mode affiliation network

NASA Astrophysics Data System (ADS)

Li, Huajiao; An, Haizhong; Wang, Yue; Huang, Jiachen; Gao, Xiangyun

2016-05-01

Keeping abreast of trends in the articles and rapidly grasping a body of article's key points and relationship from a holistic perspective is a new challenge in both literature research and text mining. As the important component, keywords can present the core idea of the academic article. Usually, articles on a single theme or area could share one or some same keywords, and we can analyze topological features and evolution of the articles co-keyword networks and keywords co-occurrence networks to realize the in-depth analysis of the articles. This paper seeks to integrate statistics, text mining, complex networks and visualization to analyze all of the academic articles on one given theme, complex network(s). All 5944 ;complex networks; articles that were published between 1990 and 2013 and are available on the Web of Science are extracted. Based on the two-mode affiliation network theory, a new frontier of complex networks, we constructed two different networks, one taking the articles as nodes, the co-keyword relationships as edges and the quantity of co-keywords as the weight to construct articles co-keyword network, and another taking the articles' keywords as nodes, the co-occurrence relationships as edges and the quantity of simultaneous co-occurrences as the weight to construct keyword co-occurrence network. An integrated method for analyzing the topological features and evolution of the articles co-keyword network and keywords co-occurrence networks is proposed, and we also defined a new function to measure the innovation coefficient of the articles in annual level. This paper provides a useful tool and process for successfully achieving in-depth analysis and rapid understanding of the trends and relationships of articles in a holistic perspective.

IJA: an efficient algorithm for query processing in sensor networks.

PubMed

Lee, Hyun Chang; Lee, Young Jae; Lim, Ji Hyang; Kim, Dong Hwa

2011-01-01

One of main features in sensor networks is the function that processes real time state information after gathering needed data from many domains. The component technologies consisting of each node called a sensor node that are including physical sensors, processors, actuators and power have advanced significantly over the last decade. Thanks to the advanced technology, over time sensor networks have been adopted in an all-round industry sensing physical phenomenon. However, sensor nodes in sensor networks are considerably constrained because with their energy and memory resources they have a very limited ability to process any information compared to conventional computer systems. Thus query processing over the nodes should be constrained because of their limitations. Due to the problems, the join operations in sensor networks are typically processed in a distributed manner over a set of nodes and have been studied. By way of example while simple queries, such as select and aggregate queries, in sensor networks have been addressed in the literature, the processing of join queries in sensor networks remains to be investigated. Therefore, in this paper, we propose and describe an Incremental Join Algorithm (IJA) in Sensor Networks to reduce the overhead caused by moving a join pair to the final join node or to minimize the communication cost that is the main consumer of the battery when processing the distributed queries in sensor networks environments. At the same time, the simulation result shows that the proposed IJA algorithm significantly reduces the number of bytes to be moved to join nodes compared to the popular synopsis join algorithm.

IJA: An Efficient Algorithm for Query Processing in Sensor Networks

PubMed Central

Lee, Hyun Chang; Lee, Young Jae; Lim, Ji Hyang; Kim, Dong Hwa

2011-01-01

One of main features in sensor networks is the function that processes real time state information after gathering needed data from many domains. The component technologies consisting of each node called a sensor node that are including physical sensors, processors, actuators and power have advanced significantly over the last decade. Thanks to the advanced technology, over time sensor networks have been adopted in an all-round industry sensing physical phenomenon. However, sensor nodes in sensor networks are considerably constrained because with their energy and memory resources they have a very limited ability to process any information compared to conventional computer systems. Thus query processing over the nodes should be constrained because of their limitations. Due to the problems, the join operations in sensor networks are typically processed in a distributed manner over a set of nodes and have been studied. By way of example while simple queries, such as select and aggregate queries, in sensor networks have been addressed in the literature, the processing of join queries in sensor networks remains to be investigated. Therefore, in this paper, we propose and describe an Incremental Join Algorithm (IJA) in Sensor Networks to reduce the overhead caused by moving a join pair to the final join node or to minimize the communication cost that is the main consumer of the battery when processing the distributed queries in sensor networks environments. At the same time, the simulation result shows that the proposed IJA algorithm significantly reduces the number of bytes to be moved to join nodes compared to the popular synopsis join algorithm. PMID:22319375

Perceived Close Relationships with Parents, Teachers, and Peers: Predictors of Social, Emotional, and Behavioral Features in Adolescents With LD or Comorbid LD and ADHD

ERIC Educational Resources Information Center

Al-Yagon, Michal

2016-01-01

This study examined the role of adolescents' perceived close relationships with significant others (attachment relationships with mothers/fathers, appraisal of homeroom teacher as secure base, and quality of peer friendship) in explaining differences in their socioemotional and behavioral functioning (peer-network/peer-dyadic loneliness,…

CROSS-DISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY: The Fractal Dimensions of Complex Networks

NASA Astrophysics Data System (ADS)

Guo, Long; Cai, XU

2009-08-01

It is shown that many real complex networks share distinctive features, such as the small-world effect and the heterogeneous property of connectivity of vertices, which are different from random networks and regular lattices. Although these features capture the important characteristics of complex networks, their applicability depends on the style of networks. To unravel the universal characteristics many complex networks have in common, we study the fractal dimensions of complex networks using the method introduced by Shanker. We find that the average 'density' (ρ(r)) of complex networks follows a better power-law function as a function of distance r with the exponent df, which is defined as the fractal dimension, in some real complex networks. Furthermore, we study the relation between df and the shortcuts Nadd in small-world networks and the size N in regular lattices. Our present work provides a new perspective to understand the dependence of the fractal dimension df on the complex network structure.

Networks.

ERIC Educational Resources Information Center

Maughan, George R.; Petitto, Karen R.; McLaughlin, Don

2001-01-01

Describes the connectivity features and options of modern campus communication and information system networks, including signal transmission (wire-based and wireless), signal switching, convergence of networks, and network assessment variables, to enable campus leaders to make sound future-oriented decisions. (EV)

Qualitative dynamics semantics for SBGN process description.

PubMed

Rougny, Adrien; Froidevaux, Christine; Calzone, Laurence; Paulevé, Loïc

2016-06-16

Qualitative dynamics semantics provide a coarse-grain modeling of networks dynamics by abstracting away kinetic parameters. They allow to capture general features of systems dynamics, such as attractors or reachability properties, for which scalable analyses exist. The Systems Biology Graphical Notation Process Description language (SBGN-PD) has become a standard to represent reaction networks. However, no qualitative dynamics semantics taking into account all the main features available in SBGN-PD had been proposed so far. We propose two qualitative dynamics semantics for SBGN-PD reaction networks, namely the general semantics and the stories semantics, that we formalize using asynchronous automata networks. While the general semantics extends standard Boolean semantics of reaction networks by taking into account all the main features of SBGN-PD, the stories semantics allows to model several molecules of a network by a unique variable. The obtained qualitative models can be checked against dynamical properties and therefore validated with respect to biological knowledge. We apply our framework to reason on the qualitative dynamics of a large network (more than 200 nodes) modeling the regulation of the cell cycle by RB/E2F. The proposed semantics provide a direct formalization of SBGN-PD networks in dynamical qualitative models that can be further analyzed using standard tools for discrete models. The dynamics in stories semantics have a lower dimension than the general one and prune multiple behaviors (which can be considered as spurious) by enforcing the mutual exclusiveness between the activity of different nodes of a same story. Overall, the qualitative semantics for SBGN-PD allow to capture efficiently important dynamical features of reaction network models and can be exploited to further refine them.

Multi-threshold white matter structural networks fusion for accurate diagnosis of Tourette syndrome children

NASA Astrophysics Data System (ADS)

Wen, Hongwei; Liu, Yue; Wang, Shengpei; Li, Zuoyong; Zhang, Jishui; Peng, Yun; He, Huiguang

2017-03-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder. To date, TS is still misdiagnosed due to its varied presentation and lacking of obvious clinical symptoms. Therefore, studies of objective imaging biomarkers are of great importance for early TS diagnosis. As tic generation has been linked to disturbed structural networks, and many efforts have been made recently to investigate brain functional or structural networks using machine learning methods, for the purpose of disease diagnosis. However, few studies were related to TS and some drawbacks still existed in them. Therefore, we propose a novel classification framework integrating a multi-threshold strategy and a network fusion scheme to address the preexisting drawbacks. Here we used diffusion MRI probabilistic tractography to construct the structural networks of 44 TS children and 48 healthy children. We ameliorated the similarity network fusion algorithm specially to fuse the multi-threshold structural networks. Graph theoretical analysis was then implemented, and nodal degree, nodal efficiency and nodal betweenness centrality were selected as features. Finally, support vector machine recursive feature extraction (SVM-RFE) algorithm was used for feature selection, and then optimal features are fed into SVM to automatically discriminate TS children from controls. We achieved a high accuracy of 89.13% evaluated by a nested cross validation, demonstrated the superior performance of our framework over other comparison methods. The involved discriminative regions for classification primarily located in the basal ganglia and frontal cortico-cortical networks, all highly related to the pathology of TS. Together, our study may provide potential neuroimaging biomarkers for early-stage TS diagnosis.

Network Receptive Field Modeling Reveals Extensive Integration and Multi-feature Selectivity in Auditory Cortical Neurons.

PubMed

Harper, Nicol S; Schoppe, Oliver; Willmore, Ben D B; Cui, Zhanfeng; Schnupp, Jan W H; King, Andrew J

2016-11-01

Cortical sensory neurons are commonly characterized using the receptive field, the linear dependence of their response on the stimulus. In primary auditory cortex neurons can be characterized by their spectrotemporal receptive fields, the spectral and temporal features of a sound that linearly drive a neuron. However, receptive fields do not capture the fact that the response of a cortical neuron results from the complex nonlinear network in which it is embedded. By fitting a nonlinear feedforward network model (a network receptive field) to cortical responses to natural sounds, we reveal that primary auditory cortical neurons are sensitive over a substantially larger spectrotemporal domain than is seen in their standard spectrotemporal receptive fields. Furthermore, the network receptive field, a parsimonious network consisting of 1-7 sub-receptive fields that interact nonlinearly, consistently better predicts neural responses to auditory stimuli than the standard receptive fields. The network receptive field reveals separate excitatory and inhibitory sub-fields with different nonlinear properties, and interaction of the sub-fields gives rise to important operations such as gain control and conjunctive feature detection. The conjunctive effects, where neurons respond only if several specific features are present together, enable increased selectivity for particular complex spectrotemporal structures, and may constitute an important stage in sound recognition. In conclusion, we demonstrate that fitting auditory cortical neural responses with feedforward network models expands on simple linear receptive field models in a manner that yields substantially improved predictive power and reveals key nonlinear aspects of cortical processing, while remaining easy to interpret in a physiological context.

Network Receptive Field Modeling Reveals Extensive Integration and Multi-feature Selectivity in Auditory Cortical Neurons

PubMed Central

Willmore, Ben D. B.; Cui, Zhanfeng; Schnupp, Jan W. H.; King, Andrew J.

2016-01-01

Cortical sensory neurons are commonly characterized using the receptive field, the linear dependence of their response on the stimulus. In primary auditory cortex neurons can be characterized by their spectrotemporal receptive fields, the spectral and temporal features of a sound that linearly drive a neuron. However, receptive fields do not capture the fact that the response of a cortical neuron results from the complex nonlinear network in which it is embedded. By fitting a nonlinear feedforward network model (a network receptive field) to cortical responses to natural sounds, we reveal that primary auditory cortical neurons are sensitive over a substantially larger spectrotemporal domain than is seen in their standard spectrotemporal receptive fields. Furthermore, the network receptive field, a parsimonious network consisting of 1–7 sub-receptive fields that interact nonlinearly, consistently better predicts neural responses to auditory stimuli than the standard receptive fields. The network receptive field reveals separate excitatory and inhibitory sub-fields with different nonlinear properties, and interaction of the sub-fields gives rise to important operations such as gain control and conjunctive feature detection. The conjunctive effects, where neurons respond only if several specific features are present together, enable increased selectivity for particular complex spectrotemporal structures, and may constitute an important stage in sound recognition. In conclusion, we demonstrate that fitting auditory cortical neural responses with feedforward network models expands on simple linear receptive field models in a manner that yields substantially improved predictive power and reveals key nonlinear aspects of cortical processing, while remaining easy to interpret in a physiological context. PMID:27835647

Transmission in Optically Transparent Core Networks

NASA Astrophysics Data System (ADS)

Kilper, Dan; Jensen, Rich; Petermann, Klaus; Karasek, Miroslav

2007-03-01

Scope of Submission

• Optically transparent system design issues, transmission experiments, and field trials
• Optically transparent network architectures and topologies
• Dispersion management in reconfigurable and mesh systems
• Optically transparent network device and sub-system performance, design, characterization and control, including: amplifiers, transmitters, receivers, switches, add/drop multiplexers
• Transient and fault management
• Physical layer system control
• Monitoring and compensation to support transparency
• Wavelength routing and planning as they relate to physical layer transmission
• Hardware cost and configuration optimization for optically transparent networks

A Biophysical and Economic Profile of South Georgia and the South Sandwich Islands as Potential Large-Scale Antarctic Protected Areas.

PubMed

Rogers, Alex D; Yesson, Christopher; Gravestock, Pippa

2015-01-01

The current hiatus in the establishment of a network of marine protected areas (MPAs) in the Antarctic means that other routes to conservation are required. The protection of overseas territories in the Antarctic and sub-Antarctic represents one way to advance the initiation of such a network. This review of the physical and biological features of the United Kingdom (U.K.) overseas territories of South Georgia and South Sandwich Islands (SGSSI) is undertaken to estimate the importance of the islands in terms of marine conservation in the Southern Ocean and globally. The economy and management of SGSSI are also analysed, and the question of whether the islands already have sufficient protection to constitute part of an Antarctic network of MPAs is assessed. The SGSSI comprise unique geological and physical features, a diverse marine biota, including a significant proportion of endemic species and globally important breeding populations of marine predators. Regardless of past exploitation of biotic resources, such as seals, whales and finfish, SGSSI would make a significant contribution to biological diversity in an Antarctic network of MPAs. At present, conservation measures do not adequately protect all of the biological features that render the islands so important in terms of conservation at a regional and global level. However, a general lack of data on Antarctic marine ecosystems (particularly needed for SGSSSI) makes it difficult to assess this fully. One barrier to achieving more complete protection is the continuing emphasis on fishing effort in these waters by U.K. government. Other non-U.K. Antarctic overseas territories of conservation importance are also compromised as MPAs because of the exploitation of fisheries resources in their waters. The possible non-use values of SGSSI as well as the importance of ecosystem services that are indirectly used by people are outlined in this review. Technology is improving the potential for management of remote MPAs, particularly in the context of incursion by illegal fishing activities and use of satellite surveillance for enforcement of fisheries and conservation regulations. The conflict between commercial exploitation and conservation of Antarctic marine living resources is explored. © 2015 Elsevier Ltd All rights reserved.

Reaction schemes visualized in network form: the syntheses of strychnine as an example.

PubMed

Proudfoot, John R

2013-05-24

Representation of synthesis sequences in a network form provides an effective method for the comparison of multiple reaction schemes and an opportunity to emphasize features such as reaction scale that are often relegated to experimental sections. An example of data formatting that allows construction of network maps in Cytoscape is presented, along with maps that illustrate the comparison of multiple reaction sequences, comparison of scaffold changes within sequences, and consolidation to highlight common key intermediates used across sequences. The 17 different synthetic routes reported for strychnine are used as an example basis set. The reaction maps presented required a significant data extraction and curation, and a standardized tabular format for reporting reaction information, if applied in a consistent way, could allow the automated combination of reaction information across different sources.

Concurrent enhancement of percolation and synchronization in adaptive networks

PubMed Central

Eom, Young-Ho; Boccaletti, Stefano; Caldarelli, Guido

2016-01-01

Co-evolutionary adaptive mechanisms are not only ubiquitous in nature, but also beneficial for the functioning of a variety of systems. We here consider an adaptive network of oscillators with a stochastic, fitness-based, rule of connectivity, and show that it self-organizes from fragmented and incoherent states to connected and synchronized ones. The synchronization and percolation are associated to abrupt transitions, and they are concurrently (and significantly) enhanced as compared to the non-adaptive case. Finally we provide evidence that only partial adaptation is sufficient to determine these enhancements. Our study, therefore, indicates that inclusion of simple adaptive mechanisms can efficiently describe some emergent features of networked systems’ collective behaviors, and suggests also self-organized ways to control synchronization and percolation in natural and social systems. PMID:27251577

Protein disorder in the human diseasome: unfoldomics of human genetic diseases

PubMed Central

Midic, Uros; Oldfield, Christopher J; Dunker, A Keith; Obradovic, Zoran; Uversky, Vladimir N

2009-01-01

Background Intrinsically disordered proteins lack stable structure under physiological conditions, yet carry out many crucial biological functions, especially functions associated with regulation, recognition, signaling and control. Recently, human genetic diseases and related genes were organized into a bipartite graph (Goh KI, Cusick ME, Valle D, Childs B, Vidal M, et al. (2007) The human disease network. Proc Natl Acad Sci U S A 104: 8685–8690). This diseasome network revealed several significant features such as the common genetic origin of many diseases. Methods and findings We analyzed the abundance of intrinsic disorder in these diseasome network proteins by means of several prediction algorithms, and we analyzed the functional repertoires of these proteins based on prior studies relating disorder to function. Our analyses revealed that (i) Intrinsic disorder is common in proteins associated with many human genetic diseases; (ii) Different disease classes vary in the IDP contents of their associated proteins; (iii) Molecular recognition features, which are relatively short loosely structured protein regions within mostly disordered sequences and which gain structure upon binding to partners, are common in the diseasome, and their abundance correlates with the intrinsic disorder level; (iv) Some disease classes have a significant fraction of genes affected by alternative splicing, and the alternatively spliced regions in the corresponding proteins are predicted to be highly disordered; and (v) Correlations were found among the various diseasome graph-related properties and intrinsic disorder. Conclusion These observations provide the basis for the construction of the human-genetic-disease-associated unfoldome. PMID:19594871

Coding Local and Global Binary Visual Features Extracted From Video Sequences.

PubMed

Baroffio, Luca; Canclini, Antonio; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2015-11-01

Binary local features represent an effective alternative to real-valued descriptors, leading to comparable results for many visual analysis tasks while being characterized by significantly lower computational complexity and memory requirements. When dealing with large collections, a more compact representation based on global features is often preferred, which can be obtained from local features by means of, e.g., the bag-of-visual word model. Several applications, including, for example, visual sensor networks and mobile augmented reality, require visual features to be transmitted over a bandwidth-limited network, thus calling for coding techniques that aim at reducing the required bit budget while attaining a target level of efficiency. In this paper, we investigate a coding scheme tailored to both local and global binary features, which aims at exploiting both spatial and temporal redundancy by means of intra- and inter-frame coding. In this respect, the proposed coding scheme can conveniently be adopted to support the analyze-then-compress (ATC) paradigm. That is, visual features are extracted from the acquired content, encoded at remote nodes, and finally transmitted to a central controller that performs the visual analysis. This is in contrast with the traditional approach, in which visual content is acquired at a node, compressed and then sent to a central unit for further processing, according to the compress-then-analyze (CTA) paradigm. In this paper, we experimentally compare the ATC and the CTA by means of rate-efficiency curves in the context of two different visual analysis tasks: 1) homography estimation and 2) content-based retrieval. Our results show that the novel ATC paradigm based on the proposed coding primitives can be competitive with the CTA, especially in bandwidth limited scenarios.

Coding Local and Global Binary Visual Features Extracted From Video Sequences

NASA Astrophysics Data System (ADS)

Baroffio, Luca; Canclini, Antonio; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2015-11-01

Binary local features represent an effective alternative to real-valued descriptors, leading to comparable results for many visual analysis tasks, while being characterized by significantly lower computational complexity and memory requirements. When dealing with large collections, a more compact representation based on global features is often preferred, which can be obtained from local features by means of, e.g., the Bag-of-Visual-Word (BoVW) model. Several applications, including for example visual sensor networks and mobile augmented reality, require visual features to be transmitted over a bandwidth-limited network, thus calling for coding techniques that aim at reducing the required bit budget, while attaining a target level of efficiency. In this paper we investigate a coding scheme tailored to both local and global binary features, which aims at exploiting both spatial and temporal redundancy by means of intra- and inter-frame coding. In this respect, the proposed coding scheme can be conveniently adopted to support the Analyze-Then-Compress (ATC) paradigm. That is, visual features are extracted from the acquired content, encoded at remote nodes, and finally transmitted to a central controller that performs visual analysis. This is in contrast with the traditional approach, in which visual content is acquired at a node, compressed and then sent to a central unit for further processing, according to the Compress-Then-Analyze (CTA) paradigm. In this paper we experimentally compare ATC and CTA by means of rate-efficiency curves in the context of two different visual analysis tasks: homography estimation and content-based retrieval. Our results show that the novel ATC paradigm based on the proposed coding primitives can be competitive with CTA, especially in bandwidth limited scenarios.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System.

PubMed

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L; Wennekers, Thomas; Chicca, Elisabetta

2012-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System

PubMed Central

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L.; Wennekers, Thomas; Chicca, Elisabetta

2011-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems. PMID:22347163

Predicting clinical outcome of neuroblastoma patients using an integrative network-based approach.

PubMed

Tranchevent, Léon-Charles; Nazarov, Petr V; Kaoma, Tony; Schmartz, Georges P; Muller, Arnaud; Kim, Sang-Yoon; Rajapakse, Jagath C; Azuaje, Francisco

2018-06-07

One of the main current challenges in computational biology is to make sense of the huge amounts of multidimensional experimental data that are being produced. For instance, large cohorts of patients are often screened using different high-throughput technologies, effectively producing multiple patient-specific molecular profiles for hundreds or thousands of patients. We propose and implement a network-based method that integrates such patient omics data into Patient Similarity Networks. Topological features derived from these networks were then used to predict relevant clinical features. As part of the 2017 CAMDA challenge, we have successfully applied this strategy to a neuroblastoma dataset, consisting of genomic and transcriptomic data. In particular, we observe that models built on our network-based approach perform at least as well as state of the art models. We furthermore explore the effectiveness of various topological features and observe, for instance, that redundant centrality metrics can be combined to build more powerful models. We demonstrate that the networks inferred from omics data contain clinically relevant information and that patient clinical outcomes can be predicted using only network topological data. This article was reviewed by Yang-Yu Liu, Tomislav Smuc and Isabel Nepomuceno.

Topic segmentation via community detection in complex networks

NASA Astrophysics Data System (ADS)

de Arruda, Henrique F.; Costa, Luciano da F.; Amancio, Diego R.

2016-06-01

Many real systems have been modeled in terms of network concepts, and written texts are a particular example of information networks. In recent years, the use of network methods to analyze language has allowed the discovery of several interesting effects, including the proposition of novel models to explain the emergence of fundamental universal patterns. While syntactical networks, one of the most prevalent networked models of written texts, display both scale-free and small-world properties, such a representation fails in capturing other textual features, such as the organization in topics or subjects. We propose a novel network representation whose main purpose is to capture the semantical relationships of words in a simple way. To do so, we link all words co-occurring in the same semantic context, which is defined in a threefold way. We show that the proposed representations favor the emergence of communities of semantically related words, and this feature may be used to identify relevant topics. The proposed methodology to detect topics was applied to segment selected Wikipedia articles. We found that, in general, our methods outperform traditional bag-of-words representations, which suggests that a high-level textual representation may be useful to study the semantical features of texts.

Modeling the interdependent network based on two-mode networks

NASA Astrophysics Data System (ADS)

An, Feng; Gao, Xiangyun; Guan, Jianhe; Huang, Shupei; Liu, Qian

2017-10-01

Among heterogeneous networks, there exist obviously and closely interdependent linkages. Unlike existing research primarily focus on the theoretical research of physical interdependent network model. We propose a two-layer interdependent network model based on two-mode networks to explore the interdependent features in the reality. Specifically, we construct a two-layer interdependent loan network and develop several dependent features indices. The model is verified to enable us to capture the loan dependent features of listed companies based on loan behaviors and shared shareholders. Taking Chinese debit and credit market as case study, the main conclusions are: (1) only few listed companies shoulder the main capital transmission (20% listed companies occupy almost 70% dependent degree). (2) The control of these key listed companies will be more effective of avoiding the spreading of financial risks. (3) Identifying the companies with high betweenness centrality and controlling them could be helpful to monitor the financial risk spreading. (4) The capital transmission channel among Chinese financial listed companies and Chinese non-financial listed companies are relatively strong. However, under greater pressure of demand of capital transmission (70% edges failed), the transmission channel, which constructed by debit and credit behavior, will eventually collapse.

Multiplex congruence network of natural numbers.

PubMed

Yan, Xiao-Yong; Wang, Wen-Xu; Chen, Guan-Rong; Shi, Ding-Hua

2016-03-31

Congruence theory has many applications in physical, social, biological and technological systems. Congruence arithmetic has been a fundamental tool for data security and computer algebra. However, much less attention was devoted to the topological features of congruence relations among natural numbers. Here, we explore the congruence relations in the setting of a multiplex network and unveil some unique and outstanding properties of the multiplex congruence network. Analytical results show that every layer therein is a sparse and heterogeneous subnetwork with a scale-free topology. Counterintuitively, every layer has an extremely strong controllability in spite of its scale-free structure that is usually difficult to control. Another amazing feature is that the controllability is robust against targeted attacks to critical nodes but vulnerable to random failures, which also differs from ordinary scale-free networks. The multi-chain structure with a small number of chain roots arising from each layer accounts for the strong controllability and the abnormal feature. The multiplex congruence network offers a graphical solution to the simultaneous congruences problem, which may have implication in cryptography based on simultaneous congruences. Our work also gains insight into the design of networks integrating advantages of both heterogeneous and homogeneous networks without inheriting their limitations.

Multiplex congruence network of natural numbers

NASA Astrophysics Data System (ADS)

Yan, Xiao-Yong; Wang, Wen-Xu; Chen, Guan-Rong; Shi, Ding-Hua

2016-03-01

Congruence theory has many applications in physical, social, biological and technological systems. Congruence arithmetic has been a fundamental tool for data security and computer algebra. However, much less attention was devoted to the topological features of congruence relations among natural numbers. Here, we explore the congruence relations in the setting of a multiplex network and unveil some unique and outstanding properties of the multiplex congruence network. Analytical results show that every layer therein is a sparse and heterogeneous subnetwork with a scale-free topology. Counterintuitively, every layer has an extremely strong controllability in spite of its scale-free structure that is usually difficult to control. Another amazing feature is that the controllability is robust against targeted attacks to critical nodes but vulnerable to random failures, which also differs from ordinary scale-free networks. The multi-chain structure with a small number of chain roots arising from each layer accounts for the strong controllability and the abnormal feature. The multiplex congruence network offers a graphical solution to the simultaneous congruences problem, which may have implication in cryptography based on simultaneous congruences. Our work also gains insight into the design of networks integrating advantages of both heterogeneous and homogeneous networks without inheriting their limitations.

Topic segmentation via community detection in complex networks.

PubMed

de Arruda, Henrique F; Costa, Luciano da F; Amancio, Diego R

2016-06-01

Many real systems have been modeled in terms of network concepts, and written texts are a particular example of information networks. In recent years, the use of network methods to analyze language has allowed the discovery of several interesting effects, including the proposition of novel models to explain the emergence of fundamental universal patterns. While syntactical networks, one of the most prevalent networked models of written texts, display both scale-free and small-world properties, such a representation fails in capturing other textual features, such as the organization in topics or subjects. We propose a novel network representation whose main purpose is to capture the semantical relationships of words in a simple way. To do so, we link all words co-occurring in the same semantic context, which is defined in a threefold way. We show that the proposed representations favor the emergence of communities of semantically related words, and this feature may be used to identify relevant topics. The proposed methodology to detect topics was applied to segment selected Wikipedia articles. We found that, in general, our methods outperform traditional bag-of-words representations, which suggests that a high-level textual representation may be useful to study the semantical features of texts.

Constructing fine-granularity functional brain network atlases via deep convolutional autoencoder.

PubMed

Zhao, Yu; Dong, Qinglin; Chen, Hanbo; Iraji, Armin; Li, Yujie; Makkie, Milad; Kou, Zhifeng; Liu, Tianming

2017-12-01

State-of-the-art functional brain network reconstruction methods such as independent component analysis (ICA) or sparse coding of whole-brain fMRI data can effectively infer many thousands of volumetric brain network maps from a large number of human brains. However, due to the variability of individual brain networks and the large scale of such networks needed for statistically meaningful group-level analysis, it is still a challenging and open problem to derive group-wise common networks as network atlases. Inspired by the superior spatial pattern description ability of the deep convolutional neural networks (CNNs), a novel deep 3D convolutional autoencoder (CAE) network is designed here to extract spatial brain network features effectively, based on which an Apache Spark enabled computational framework is developed for fast clustering of larger number of network maps into fine-granularity atlases. To evaluate this framework, 10 resting state networks (RSNs) were manually labeled from the sparsely decomposed networks of Human Connectome Project (HCP) fMRI data and 5275 network training samples were obtained, in total. Then the deep CAE models are trained by these functional networks' spatial maps, and the learned features are used to refine the original 10 RSNs into 17 network atlases that possess fine-granularity functional network patterns. Interestingly, it turned out that some manually mislabeled outliers in training networks can be corrected by the deep CAE derived features. More importantly, fine granularities of networks can be identified and they reveal unique network patterns specific to different brain task states. By further applying this method to a dataset of mild traumatic brain injury study, it shows that the technique can effectively identify abnormal small networks in brain injury patients in comparison with controls. In general, our work presents a promising deep learning and big data analysis solution for modeling functional connectomes, with fine granularities, based on fMRI data. Copyright © 2017 Elsevier B.V. All rights reserved.

A Deep Convolutional Coupling Network for Change Detection Based on Heterogeneous Optical and Radar Images.

PubMed

Liu, Jia; Gong, Maoguo; Qin, Kai; Zhang, Puzhao

2018-03-01

We propose an unsupervised deep convolutional coupling network for change detection based on two heterogeneous images acquired by optical sensors and radars on different dates. Most existing change detection methods are based on homogeneous images. Due to the complementary properties of optical and radar sensors, there is an increasing interest in change detection based on heterogeneous images. The proposed network is symmetric with each side consisting of one convolutional layer and several coupling layers. The two input images connected with the two sides of the network, respectively, are transformed into a feature space where their feature representations become more consistent. In this feature space, the different map is calculated, which then leads to the ultimate detection map by applying a thresholding algorithm. The network parameters are learned by optimizing a coupling function. The learning process is unsupervised, which is different from most existing change detection methods based on heterogeneous images. Experimental results on both homogenous and heterogeneous images demonstrate the promising performance of the proposed network compared with several existing approaches.

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.

Evaluating open-source cloud computing solutions for geosciences

NASA Astrophysics Data System (ADS)

Huang, Qunying; Yang, Chaowei; Liu, Kai; Xia, Jizhe; Xu, Chen; Li, Jing; Gui, Zhipeng; Sun, Min; Li, Zhenglong

2013-09-01

Many organizations start to adopt cloud computing for better utilizing computing resources by taking advantage of its scalability, cost reduction, and easy to access characteristics. Many private or community cloud computing platforms are being built using open-source cloud solutions. However, little has been done to systematically compare and evaluate the features and performance of open-source solutions in supporting Geosciences. This paper provides a comprehensive study of three open-source cloud solutions, including OpenNebula, Eucalyptus, and CloudStack. We compared a variety of features, capabilities, technologies and performances including: (1) general features and supported services for cloud resource creation and management, (2) advanced capabilities for networking and security, and (3) the performance of the cloud solutions in provisioning and operating the cloud resources as well as the performance of virtual machines initiated and managed by the cloud solutions in supporting selected geoscience applications. Our study found that: (1) no significant performance differences in central processing unit (CPU), memory and I/O of virtual machines created and managed by different solutions, (2) OpenNebula has the fastest internal network while both Eucalyptus and CloudStack have better virtual machine isolation and security strategies, (3) Cloudstack has the fastest operations in handling virtual machines, images, snapshots, volumes and networking, followed by OpenNebula, and (4) the selected cloud computing solutions are capable for supporting concurrent intensive web applications, computing intensive applications, and small-scale model simulations without intensive data communication.

Neural network and SVM classifiers accurately predict lipid binding proteins, irrespective of sequence homology.

PubMed

Bakhtiarizadeh, Mohammad Reza; Moradi-Shahrbabak, Mohammad; Ebrahimi, Mansour; Ebrahimie, Esmaeil

2014-09-07

Due to the central roles of lipid binding proteins (LBPs) in many biological processes, sequence based identification of LBPs is of great interest. The major challenge is that LBPs are diverse in sequence, structure, and function which results in low accuracy of sequence homology based methods. Therefore, there is a need for developing alternative functional prediction methods irrespective of sequence similarity. To identify LBPs from non-LBPs, the performances of support vector machine (SVM) and neural network were compared in this study. Comprehensive protein features and various techniques were employed to create datasets. Five-fold cross-validation (CV) and independent evaluation (IE) tests were used to assess the validity of the two methods. The results indicated that SVM outperforms neural network. SVM achieved 89.28% (CV) and 89.55% (IE) overall accuracy in identification of LBPs from non-LBPs and 92.06% (CV) and 92.90% (IE) (in average) for classification of different LBPs classes. Increasing the number and the range of extracted protein features as well as optimization of the SVM parameters significantly increased the efficiency of LBPs class prediction in comparison to the only previous report in this field. Altogether, the results showed that the SVM algorithm can be run on broad, computationally calculated protein features and offers a promising tool in detection of LBPs classes. The proposed approach has the potential to integrate and improve the common sequence alignment based methods. Copyright © 2014 Elsevier Ltd. All rights reserved.

Planning Marine Reserve Networks for Both Feature Representation and Demographic Persistence Using Connectivity Patterns

PubMed Central

Bode, Michael; Williamson, David H.; Weeks, Rebecca; Jones, Geoff P.; Almany, Glenn R.; Harrison, Hugo B.; Hopf, Jess K.; Pressey, Robert L.

2016-01-01

Marine reserve networks must ensure the representation of important conservation features, and also guarantee the persistence of key populations. For many species, designing reserve networks is complicated by the absence or limited availability of spatial and life-history data. This is particularly true for data on larval dispersal, which has only recently become available. However, systematic conservation planning methods currently incorporate demographic processes through unsatisfactory surrogates. There are therefore two key challenges to designing marine reserve networks that achieve feature representation and demographic persistence constraints. First, constructing a method that efficiently incorporates persistence as well as complementary feature representation. Second, incorporating persistence using a mechanistic description of population viability, rather than a proxy such as size or distance. Here we construct a novel systematic conservation planning method that addresses both challenges, and parameterise it to design a hypothetical marine reserve network for fringing coral reefs in the Keppel Islands, Great Barrier Reef, Australia. For this application, we describe how demographic persistence goals can be constructed for an important reef fish species in the region, the bar-cheeked trout (Plectropomus maculatus). We compare reserve networks that are optimally designed for either feature representation or demographic persistence, with a reserve network that achieves both goals simultaneously. As well as being practically applicable, our analyses also provide general insights into marine reserve planning for both representation and demographic persistence. First, persistence constraints for dispersive organisms are likely to be much harder to achieve than representation targets, due to their greater complexity. Second, persistence and representation constraints pull the reserve network design process in divergent directions, making it difficult to efficiently achieve both constraints. Although our method can be readily applied to the data-rich Keppel Islands case study, we finally consider the factors that limit the method’s utility in information-poor contexts common in marine conservation. PMID:27168206

Alterations of fibrin network structure mediated by dermatan sulfate.

PubMed

Lauricella, Ana María; Castañon, María Mercedes; Kordich, Lucía C; Quintana, Irene L

2013-02-01

Dermatan sulfate (DS) is well-known for its anticoagulant activity through binding to heparin cofactor II (HCII) to enhance thrombin inhibition. It has also been reported that DS has a profibrinolytic effect. We have evaluated the effects of DS solutions (4-20 μg/mL) on the formation (by kinetic studies), structure (by electron microscopy and compaction assays) and lysis (with urokinase-type plasminogen activator) of plasma fibrin networks. The results showed that DS significantly prolonged the lag phase and decreased the fibrin formation rate and the optical density of the final networks versus control, in a concentration dependent way. DS-associated networks presented a minor network percentage compared with control, composed of lower number of fibers per field, which resulted significantly thinner and longer. Moreover, DS rendered gels more sensible to rupture by centrifugal force and more susceptible to lysis. When fibrin formation kinetic assays were performed with purified fibrinogen instead of plasma, in the absence of HCII, the optical density of final DS-associated networks was statistically lower than control. Therefore, a direct effect of DS on the thickness of fibers was observed. Since in all in vitro assays low DS concentrations were used, it could be postulated that the fibrin features described above are plausible to be found in in vivo thrombi and therefore, DS would contribute to the formation of less thrombogenic clots.

Feature Extraction Using an Unsupervised Neural Network

DTIC Science & Technology

1991-05-03

with this neural netowrk is given and its connection to exploratory projection pursuit methods is established. DD I 2 P JA d 73 EDITIONj Of I NOV 6s...IS OBSOLETE $IN 0102- LF- 014- 6601 SECURITY CLASSIFICATION OF THIS PAGE (When Daoes Enlered) Feature Extraction using an Unsupervised Neural Network

76 FR 36863 - Special Conditions: Gulfstream Model GVI Airplane; Electronic Systems Security Protection From...

Federal Register 2010, 2011, 2012, 2013, 2014

2011-06-23

... airplane. This airplane will have novel or unusual design features associated with the architecture and... incorporate the following novel or unusual design features: Digital systems architecture composed of several connected networks. The proposed architecture and network configuration may be used for, or interfaced with...

Organization of managed clinical networking for home parenteral nutrition.

PubMed

Baxter, Janet P; McKee, Ruth F

2006-05-01

Home parenteral nutrition (HPN) is an established treatment for intestinal failure, and organization of HPN is variable throughout the UK and Europe. Managed clinical networking is the single most important feature of the UK National Health Service strategy for acute services in Scotland and has the potential to improve the management of HPN patients. This review addresses the role of managed clinical networking in HPN and compares outcome data between centres. The Scottish HPN Managed Clinical Network has published the main body of the current literature supporting the concept of managed clinical networking in this context. The Network is responsible for the organization and quality assurance of HPN provision in Scotland, and has been established for 5 years. It has captured significant patient data for the purpose of clinical audit and illustrates that this is an effective model for the management of this patient population. This review provides advice for other areas wishing to improve equity of access, and to smooth the patient journey between primary, secondary and tertiary health care in the context of artificial nutrition support.

Statistics and dynamics of attractor networks with inter-correlated patterns

NASA Astrophysics Data System (ADS)

Kropff, E.

2007-02-01

In an embodied feature representation view, the semantic memory represents concepts in the brain by the associated activation of the features that describe it, each one of them processed in a differentiated region of the cortex. This system has been modeled with a Potts attractor network. Several studies of feature representation show that the correlation between patterns plays a crucial role in semantic memory. The present work focuses on two aspects of the effect of correlations in attractor networks. In first place, it assesses how a Potts network can store a set of patterns with non-trivial correlations between them. This is done through a simple and biologically plausible modification to the classical learning rule. In second place, it studies the complexity of latching transitions between attractor states, and how this complexity can be controlled.

Topological Principles of Control in Dynamical Networks

NASA Astrophysics Data System (ADS)

Kim, Jason; Pasqualetti, Fabio; Bassett, Danielle

Networked biological systems, such as the brain, feature complex patterns of interactions. To predict and correct the dynamic behavior of such systems, it is imperative to understand how the underlying topological structure affects and limits the function of the system. Here, we use network control theory to extract topological features that favor or prevent network controllability, and to understand the network-wide effect of external stimuli on large-scale brain systems. Specifically, we treat each brain region as a dynamic entity with real-valued state, and model the time evolution of all interconnected regions using linear, time-invariant dynamics. We propose a simplified feed-forward scheme where the effect of upstream regions (drivers) on the connected downstream regions (non-drivers) is characterized in closed-form. Leveraging this characterization of the simplified model, we derive topological features that predict the controllability properties of non-simplified networks. We show analytically and numerically that these predictors are accurate across a large range of parameters. Among other contributions, our analysis shows that heterogeneity in the network weights facilitate controllability, and allows us to implement targeted interventions that profoundly improve controllability. By assuming an underlying dynamical mechanism, we are able to understand the complex topology of networked biological systems in a functionally meaningful way.

Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

PubMed

Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

2018-05-10

The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

Automatic detection of anomalies in screening mammograms

PubMed Central

2013-01-01

Background Diagnostic performance in breast screening programs may be influenced by the prior probability of disease. Since breast cancer incidence is roughly half a percent in the general population there is a large probability that the screening exam will be normal. That factor may contribute to false negatives. Screening programs typically exhibit about 83% sensitivity and 91% specificity. This investigation was undertaken to determine if a system could be developed to pre-sort screening-images into normal and suspicious bins based on their likelihood to contain disease. Wavelets were investigated as a method to parse the image data, potentially removing confounding information. The development of a classification system based on features extracted from wavelet transformed mammograms is reported. Methods In the multi-step procedure images were processed using 2D discrete wavelet transforms to create a set of maps at different size scales. Next, statistical features were computed from each map, and a subset of these features was the input for a concerted-effort set of naïve Bayesian classifiers. The classifier network was constructed to calculate the probability that the parent mammography image contained an abnormality. The abnormalities were not identified, nor were they regionalized. The algorithm was tested on two publicly available databases: the Digital Database for Screening Mammography (DDSM) and the Mammographic Images Analysis Society’s database (MIAS). These databases contain radiologist-verified images and feature common abnormalities including: spiculations, masses, geometric deformations and fibroid tissues. Results The classifier-network designs tested achieved sensitivities and specificities sufficient to be potentially useful in a clinical setting. This first series of tests identified networks with 100% sensitivity and up to 79% specificity for abnormalities. This performance significantly exceeds the mean sensitivity reported in literature for the unaided human expert. Conclusions Classifiers based on wavelet-derived features proved to be highly sensitive to a range of pathologies, as a result Type II errors were nearly eliminated. Pre-sorting the images changed the prior probability in the sorted database from 37% to 74%. PMID:24330643

Rutgers University Subcontract B611610 Final Report

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

Soundarajan, Sucheta; Eliassi-Rad, Tina; Gallagher, Brian

Given an incomplete (i.e., partially-observed) network, which nodes should we actively probe in order to achieve the highest accuracy for a given network feature? For example, consider a cyber-network administrator who observes only a portion of the network at time t and wants to accurately identify the most important (e.g., highest PageRank) nodes in the complete network. She has a limited budget for probing the network. Of all the nodes she has observed, which should she probe in order to most accurately identify the important nodes? We propose a novel and scalable algorithm, MaxOutProbe, and evaluate it w.r.t. four networkmore » features (largest connected component, PageRank, core-periphery, and community detection), five network sampling strategies, and seven network datasets from different domains. Across a range of conditions, MaxOutProbe demonstrates consistently high performance relative to several baseline strategies« less

Interarrival times of message propagation on directed networks.

PubMed

Mihaljev, Tamara; de Arcangelis, Lucilla; Herrmann, Hans J

2011-08-01

One of the challenges in fighting cybercrime is to understand the dynamics of message propagation on botnets, networks of infected computers used to send viruses, unsolicited commercial emails (SPAM) or denial of service attacks. We map this problem to the propagation of multiple random walkers on directed networks and we evaluate the interarrival time distribution between successive walkers arriving at a target. We show that the temporal organization of this process, which models information propagation on unstructured peer to peer networks, has the same features as SPAM reaching a single user. We study the behavior of the message interarrival time distribution on three different network topologies using two different rules for sending messages. In all networks the propagation is not a pure Poisson process. It shows universal features on Poissonian networks and a more complex behavior on scale free networks. Results open the possibility to indirectly learn about the process of sending messages on networks with unknown topologies, by studying interarrival times at any node of the network.

Interarrival times of message propagation on directed networks

NASA Astrophysics Data System (ADS)

Mihaljev, Tamara; de Arcangelis, Lucilla; Herrmann, Hans J.

2011-08-01

One of the challenges in fighting cybercrime is to understand the dynamics of message propagation on botnets, networks of infected computers used to send viruses, unsolicited commercial emails (SPAM) or denial of service attacks. We map this problem to the propagation of multiple random walkers on directed networks and we evaluate the interarrival time distribution between successive walkers arriving at a target. We show that the temporal organization of this process, which models information propagation on unstructured peer to peer networks, has the same features as SPAM reaching a single user. We study the behavior of the message interarrival time distribution on three different network topologies using two different rules for sending messages. In all networks the propagation is not a pure Poisson process. It shows universal features on Poissonian networks and a more complex behavior on scale free networks. Results open the possibility to indirectly learn about the process of sending messages on networks with unknown topologies, by studying interarrival times at any node of the network.

Development of neural network techniques for finger-vein pattern classification

NASA Astrophysics Data System (ADS)

Wu, Jian-Da; Liu, Chiung-Tsiung; Tsai, Yi-Jang; Liu, Jun-Ching; Chang, Ya-Wen

2010-02-01

A personal identification system using finger-vein patterns and neural network techniques is proposed in the present study. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis and classification. The biometric system for verification consists of a combination of feature extraction using principal component analysis and pattern classification using both back-propagation network and adaptive neuro-fuzzy inference systems. Finger-vein features are first extracted by principal component analysis method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed adaptive neuro-fuzzy inference system in the pattern classification, the back-propagation network is compared with the proposed system. The experimental results indicated the proposed system using adaptive neuro-fuzzy inference system demonstrated a better performance than the back-propagation network for personal identification using the finger-vein patterns.

Towards automatic musical instrument timbre recognition

NASA Astrophysics Data System (ADS)

Park, Tae Hong

This dissertation is comprised of two parts---focus on issues concerning research and development of an artificial system for automatic musical instrument timbre recognition and musical compositions. The technical part of the essay includes a detailed record of developed and implemented algorithms for feature extraction and pattern recognition. A review of existing literature introducing historical aspects surrounding timbre research, problems associated with a number of timbre definitions, and highlights of selected research activities that have had significant impact in this field are also included. The developed timbre recognition system follows a bottom-up, data-driven model that includes a pre-processing module, feature extraction module, and a RBF/EBF (Radial/Elliptical Basis Function) neural network-based pattern recognition module. 829 monophonic samples from 12 instruments have been chosen from the Peter Siedlaczek library (Best Service) and other samples from the Internet and personal collections. Significant emphasis has been put on feature extraction development and testing to achieve robust and consistent feature vectors that are eventually passed to the neural network module. In order to avoid a garbage-in-garbage-out (GIGO) trap and improve generality, extra care was taken in designing and testing the developed algorithms using various dynamics, different playing techniques, and a variety of pitches for each instrument with inclusion of attack and steady-state portions of a signal. Most of the research and development was conducted in Matlab. The compositional part of the essay includes brief introductions to "A d'Ess Are ," "Aboji," "48 13 N, 16 20 O," and "pH-SQ." A general outline pertaining to the ideas and concepts behind the architectural designs of the pieces including formal structures, time structures, orchestration methods, and pitch structures are also presented.

Small-World Network Spectra in Mean-Field Theory

NASA Astrophysics Data System (ADS)

Grabow, Carsten; Grosskinsky, Stefan; Timme, Marc

2012-05-01

Collective dynamics on small-world networks emerge in a broad range of systems with their spectra characterizing fundamental asymptotic features. Here we derive analytic mean-field predictions for the spectra of small-world models that systematically interpolate between regular and random topologies by varying their randomness. These theoretical predictions agree well with the actual spectra (obtained by numerical diagonalization) for undirected and directed networks and from fully regular to strongly random topologies. These results may provide analytical insights to empirically found features of dynamics on small-world networks from various research fields, including biology, physics, engineering, and social science.

Human activity recognition based on feature selection in smart home using back-propagation algorithm.

PubMed

Fang, Hongqing; He, Lei; Si, Hao; Liu, Peng; Xie, Xiaolei

2014-09-01

In this paper, Back-propagation(BP) algorithm has been used to train the feed forward neural network for human activity recognition in smart home environments, and inter-class distance method for feature selection of observed motion sensor events is discussed and tested. And then, the human activity recognition performances of neural network using BP algorithm have been evaluated and compared with other probabilistic algorithms: Naïve Bayes(NB) classifier and Hidden Markov Model(HMM). The results show that different feature datasets yield different activity recognition accuracy. The selection of unsuitable feature datasets increases the computational complexity and degrades the activity recognition accuracy. Furthermore, neural network using BP algorithm has relatively better human activity recognition performances than NB classifier and HMM. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

Center for Neural Engineering: applications of pulse-coupled neural networks

NASA Astrophysics Data System (ADS)

Malkani, Mohan; Bodruzzaman, Mohammad; Johnson, John L.; Davis, Joel

1999-03-01

Pulsed-Coupled Neural Network (PCNN) is an oscillatory model neural network where grouping of cells and grouping among the groups that form the output time series (number of cells that fires in each input presentation also called `icon'). This is based on the synchronicity of oscillations. Recent work by Johnson and others demonstrated the functional capabilities of networks containing such elements for invariant feature extraction using intensity maps. PCNN thus presents itself as a more biologically plausible model with solid functional potential. This paper will present the summary of several projects and their results where we successfully applied PCNN. In project one, the PCNN was applied for object recognition and classification through a robotic vision system. The features (icons) generated by the PCNN were then fed into a feedforward neural network for classification. In project two, we developed techniques for sensory data fusion. The PCNN algorithm was implemented and tested on a B14 mobile robot. The PCNN-based features were extracted from the images taken from the robot vision system and used in conjunction with the map generated by data fusion of the sonar and wheel encoder data for the navigation of the mobile robot. In our third project, we applied the PCNN for speaker recognition. The spectrogram image of speech signals are fed into the PCNN to produce invariant feature icons which are then fed into a feedforward neural network for speaker identification.

Identification of the hikikomori syndrome of social withdrawal: Psychosocial features and treatment preferences in four countries.

PubMed

Teo, Alan R; Fetters, Michael D; Stufflebam, Kyle; Tateno, Masaru; Balhara, Yatan; Choi, Tae Young; Kanba, Shigenobu; Mathews, Carol A; Kato, Takahiro A

2015-02-01

Hikikomori, a form of social withdrawal first reported in Japan, may exist globally but cross-national studies of cases of hikikomori are lacking. To identify individuals with hikikomori in multiple countries and describe features of the condition. Participants were recruited from sites in India, Japan, Korea and the United States. Hikikomori was defined as a 6-month or longer period of spending almost all time at home and avoiding social situations and social relationships, associated with significant distress/impairment. Additional measures included the University of California, Los Angeles (UCLA) Loneliness Scale, Lubben Social Network Scale (LSNS-6), Sheehan Disability Scale (SDS) and modified Cornell Treatment Preferences Index. A total of 36 participants with hikikomori were identified, with cases detected in all four countries. These individuals had high levels of loneliness (UCLA Loneliness Scale M = 55.4, SD = 10.5), limited social networks (LSNS-6 M = 9.7, SD = 5.5) and moderate functional impairment (SDS M = 16.5, SD = 7.9). Of them 28 (78%) desired treatment for their social withdrawal, with a significantly higher preference for psychotherapy over pharmacotherapy, in-person over telepsychiatry treatment and mental health specialists over primary care providers. Across countries, participants with hikikomori had similar generally treatment preferences and psychosocial features. Hikikomori exists cross-nationally and can be assessed with a standardized assessment tool. Individuals with hikikomori have substantial psychosocial impairment and disability, and some may desire treatment. © The Author(s) 2014.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule.

PubMed

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-11-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

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

Liu, Hui; Song, Yongduan; Xue, Fangzheng

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less

Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features.

PubMed

Kushibar, Kaisar; Valverde, Sergi; González-Villà, Sandra; Bernal, Jose; Cabezas, Mariano; Oliver, Arnau; Lladó, Xavier

2018-06-15

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

A probabilistic approach to quantifying spatial patterns of flow regimes and network-scale connectivity

NASA Astrophysics Data System (ADS)

Garbin, Silvia; Alessi Celegon, Elisa; Fanton, Pietro; Botter, Gianluca

2017-04-01

The temporal variability of river flow regime is a key feature structuring and controlling fluvial ecological communities and ecosystem processes. In particular, streamflow variability induced by climate/landscape heterogeneities or other anthropogenic factors significantly affects the connectivity between streams with notable implication for river fragmentation. Hydrologic connectivity is a fundamental property that guarantees species persistence and ecosystem integrity in riverine systems. In riverine landscapes, most ecological transitions are flow-dependent and the structure of flow regimes may affect ecological functions of endemic biota (i.e., fish spawning or grazing of invertebrate species). Therefore, minimum flow thresholds must be guaranteed to support specific ecosystem services, like fish migration, aquatic biodiversity and habitat suitability. In this contribution, we present a probabilistic approach aiming at a spatially-explicit, quantitative assessment of hydrologic connectivity at the network-scale as derived from river flow variability. Dynamics of daily streamflows are estimated based on catchment-scale climatic and morphological features, integrating a stochastic, physically based approach that accounts for the stochasticity of rainfall with a water balance model and a geomorphic recession flow model. The non-exceedance probability of ecologically meaningful flow thresholds is used to evaluate the fragmentation of individual stream reaches, and the ensuing network-scale connectivity metrics. A multi-dimensional Poisson Process for the stochastic generation of rainfall is used to evaluate the impact of climate signature on reach-scale and catchment-scale connectivity. The analysis shows that streamflow patterns and network-scale connectivity are influenced by the topology of the river network and the spatial variability of climatic properties (rainfall, evapotranspiration). The framework offers a robust basis for the prediction of the impact of land-use/land-cover changes and river regulation on network-scale connectivity.

A Scalable Distributed Approach to Mobile Robot Vision

NASA Technical Reports Server (NTRS)

Kuipers, Benjamin; Browning, Robert L.; Gribble, William S.

1997-01-01

This paper documents our progress during the first year of work on our original proposal entitled 'A Scalable Distributed Approach to Mobile Robot Vision'. We are pursuing a strategy for real-time visual identification and tracking of complex objects which does not rely on specialized image-processing hardware. In this system perceptual schemas represent objects as a graph of primitive features. Distributed software agents identify and track these features, using variable-geometry image subwindows of limited size. Active control of imaging parameters and selective processing makes simultaneous real-time tracking of many primitive features tractable. Perceptual schemas operate independently from the tracking of primitive features, so that real-time tracking of a set of image features is not hurt by latency in recognition of the object that those features make up. The architecture allows semantically significant features to be tracked with limited expenditure of computational resources, and allows the visual computation to be distributed across a network of processors. Early experiments are described which demonstrate the usefulness of this formulation, followed by a brief overview of our more recent progress (after the first year).

Research on improving image recognition robustness by combining multiple features with associative memory

NASA Astrophysics Data System (ADS)

Guo, Dongwei; Wang, Zhe

2018-05-01

Convolutional neural networks (CNN) achieve great success in computer vision, it can learn hierarchical representation from raw pixels and has outstanding performance in various image recognition tasks [1]. However, CNN is easy to be fraudulent in terms of it is possible to produce images totally unrecognizable to human eyes that CNNs believe with near certainty are familiar objects. [2]. In this paper, an associative memory model based on multiple features is proposed. Within this model, feature extraction and classification are carried out by CNN, T-SNE and exponential bidirectional associative memory neural network (EBAM). The geometric features extracted from CNN and the digital features extracted from T-SNE are associated by EBAM. Thus we ensure the recognition of robustness by a comprehensive assessment of the two features. In our model, we can get only 8% error rate with fraudulent data. In systems that require a high safety factor or some key areas, strong robustness is extremely important, if we can ensure the image recognition robustness, network security will be greatly improved and the social production efficiency will be extremely enhanced.

Quantitative analysis of thyroid tumors vascularity: A comparison between 3-D contrast-enhanced ultrasound and 3-D Power Doppler on benign and malignant thyroid nodules.

PubMed

Caresio, Cristina; Caballo, Marco; Deandrea, Maurilio; Garberoglio, Roberto; Mormile, Alberto; Rossetto, Ruth; Limone, Paolo; Molinari, Filippo

2018-05-15

To perform a comparative quantitative analysis of Power Doppler ultrasound (PDUS) and Contrast-Enhancement ultrasound (CEUS) for the quantification of thyroid nodules vascularity patterns, with the goal of identifying biomarkers correlated with the malignancy of the nodule with both imaging techniques. We propose a novel method to reconstruct the vascular architecture from 3-D PDUS and CEUS images of thyroid nodules, and to automatically extract seven quantitative features related to the morphology and distribution of vascular network. Features include three tortuosity metrics, the number of vascular trees and branches, the vascular volume density, and the main spatial vascularity pattern. Feature extraction was performed on 20 thyroid lesions (ten benign and ten malignant), of which we acquired both PDUS and CEUS. MANOVA (multivariate analysis of variance) was used to differentiate benign and malignant lesions based on the most significant features. The analysis of the extracted features showed a significant difference between the benign and malignant nodules for both PDUS and CEUS techniques for all the features. Furthermore, by using a linear classifier on the significant features identified by the MANOVA, benign nodules could be entirely separated from the malignant ones. Our early results confirm the correlation between the morphology and distribution of blood vessels and the malignancy of the lesion, and also show (at least for the dataset used in this study) a considerable similarity in terms of findings of PDUS and CEUS imaging for thyroid nodules diagnosis and classification. © 2018 American Association of Physicists in Medicine.

Empirical Reference Distributions for Networks of Different Size

PubMed Central

Smith, Anna; Calder, Catherine A.; Browning, Christopher R.

2016-01-01

Network analysis has become an increasingly prevalent research tool across a vast range of scientific fields. Here, we focus on the particular issue of comparing network statistics, i.e. graph-level measures of network structural features, across multiple networks that differ in size. Although “normalized” versions of some network statistics exist, we demonstrate via simulation why direct comparison is often inappropriate. We consider normalizing network statistics relative to a simple fully parameterized reference distribution and demonstrate via simulation how this is an improvement over direct comparison, but still sometimes problematic. We propose a new adjustment method based on a reference distribution constructed as a mixture model of random graphs which reflect the dependence structure exhibited in the observed networks. We show that using simple Bernoulli models as mixture components in this reference distribution can provide adjusted network statistics that are relatively comparable across different network sizes but still describe interesting features of networks, and that this can be accomplished at relatively low computational expense. Finally, we apply this methodology to a collection of ecological networks derived from the Los Angeles Family and Neighborhood Survey activity location data. PMID:27721556

Effect of various features on the life cycle cost of the timing/synchronization subsystem of the DCS digital communications network

NASA Technical Reports Server (NTRS)

Kimsey, D. B.

1978-01-01

The effect on the life cycle cost of the timing subsystem was examined, when these optional features were included in various combinations. The features included mutual control, directed control, double-ended reference links, independence of clock error measurement and correction, phase reference combining, self-organization, smoothing for link and nodal dropouts, unequal reference weightings, and a master in a mutual control network. An overall design of a microprocessor-based timing subsystem was formulated. The microprocessor (8080) implements the digital filter portion of a digital phase locked loop, as well as other control functions such as organization of the network through communication with processors at neighboring nodes.

Co-trained convolutional neural networks for automated detection of prostate cancer in multi-parametric MRI.

PubMed

Yang, Xin; Liu, Chaoyue; Wang, Zhiwei; Yang, Jun; Min, Hung Le; Wang, Liang; Cheng, Kwang-Ting Tim

2017-12-01

Multi-parameter magnetic resonance imaging (mp-MRI) is increasingly popular for prostate cancer (PCa) detection and diagnosis. However, interpreting mp-MRI data which typically contains multiple unregistered 3D sequences, e.g. apparent diffusion coefficient (ADC) and T2-weighted (T2w) images, is time-consuming and demands special expertise, limiting its usage for large-scale PCa screening. Therefore, solutions to computer-aided detection of PCa in mp-MRI images are highly desirable. Most recent advances in automated methods for PCa detection employ a handcrafted feature based two-stage classification flow, i.e. voxel-level classification followed by a region-level classification. This work presents an automated PCa detection system which can concurrently identify the presence of PCa in an image and localize lesions based on deep convolutional neural network (CNN) features and a single-stage SVM classifier. Specifically, the developed co-trained CNNs consist of two parallel convolutional networks for ADC and T2w images respectively. Each network is trained using images of a single modality in a weakly-supervised manner by providing a set of prostate images with image-level labels indicating only the presence of PCa without priors of lesions' locations. Discriminative visual patterns of lesions can be learned effectively from clutters of prostate and surrounding tissues. A cancer response map with each pixel indicating the likelihood to be cancerous is explicitly generated at the last convolutional layer of the network for each modality. A new back-propagated error E is defined to enforce both optimized classification results and consistent cancer response maps for different modalities, which help capture highly representative PCa-relevant features during the CNN feature learning process. The CNN features of each modality are concatenated and fed into a SVM classifier. For images which are classified to contain cancers, non-maximum suppression and adaptive thresholding are applied to the corresponding cancer response maps for PCa foci localization. Evaluation based on 160 patient data with 12-core systematic TRUS-guided prostate biopsy as the reference standard demonstrates that our system achieves a sensitivity of 0.46, 0.92 and 0.97 at 0.1, 1 and 10 false positives per normal/benign patient which is significantly superior to two state-of-the-art CNN-based methods (Oquab et al., 2015; Zhou et al., 2015) and 6-core systematic prostate biopsies. Copyright © 2017 Elsevier B.V. All rights reserved.

Seafloor massive sulfide deposits support unique megafaunal assemblages: Implications for seabed mining and conservation.

PubMed

Boschen, Rachel E; Rowden, Ashley A; Clark, Malcolm R; Pallentin, Arne; Gardner, Jonathan P A

2016-04-01

Mining of seafloor massive sulfides (SMS) is imminent, but the ecology of assemblages at SMS deposits is poorly known. Proposed conservation strategies include protected areas to preserve biodiversity at risk from mining impacts. Determining site suitability requires biological characterisation of the mine site and protected area(s). Video survey of a proposed mine site and protected area off New Zealand revealed unique megafaunal assemblages at the mine site. Significant relationships were identified between assemblage structure and environmental conditions, including hydrothermal features. Unique assemblages occurred at both active and inactive chimneys and are particularly at risk from mining-related impacts. The occurrence of unique assemblages at the mine site suggests that the proposed protected area is insufficient alone and should instead form part of a network. These results provide support for including hydrothermally active and inactive features within networks of protected areas and emphasise the need for quantitative survey data of proposed sites. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

Natural Human Mobility Patterns and Spatial Spread of Infectious Diseases

NASA Astrophysics Data System (ADS)

Belik, Vitaly; Geisel, Theo; Brockmann, Dirk

2011-08-01

We investigate a model for spatial epidemics explicitly taking into account bidirectional movements between base and destination locations on individual mobility networks. We provide a systematic analysis of generic dynamical features of the model on regular and complex metapopulation network topologies and show that significant dynamical differences exist to ordinary reaction-diffusion and effective force of infection models. On a lattice we calculate an expression for the velocity of the propagating epidemic front and find that, in contrast to the diffusive systems, our model predicts a saturation of the velocity with an increasing traveling rate. Furthermore, we show that a fully stochastic system exhibits a novel threshold for the attack ratio of an outbreak that is absent in diffusion and force of infection models. These insights not only capture natural features of human mobility relevant for the geographical epidemic spread, they may serve as a starting point for modeling important dynamical processes in human and animal epidemiology, population ecology, biology, and evolution.

Probabilistic neural networks for diagnosis of Alzheimer's disease using conventional and wavelet coherence.

PubMed

Sankari, Ziad; Adeli, Hojjat

2011-04-15

Recently, the authors presented an EEG (electroencephalogram) coherence study of the Alzheimer's disease (AD) and found statistically significant differences between AD and control groups. In this paper a probabilistic neural network (PNN) model is presented for classification of AD and healthy controls using features extracted in coherence and wavelet coherence studies on cortical connectivity in AD. The model is verified using EEGs obtained from 20 AD probable patients and 7 healthy/control subjects based on a standard 10-20 electrode configuration on the scalp. It is shown that extracting features from EEG sub-bands using coherence, as a measure of cortical connectivity, can discriminate AD patients from healthy controls effectively when a mixed band classification model is applied. For the data set used a classification accuracy of 100% is achieved using the conventional coherence and a spread parameter of the Gaussian function in a particular range found in this research. Copyright © 2011 Elsevier B.V. All rights reserved.

A bounding-based solution approach for the continuous arc covering problem

NASA Astrophysics Data System (ADS)

Wei, Ran; Murray, Alan T.; Batta, Rajan

2014-04-01

Road segments, telecommunication wiring, water and sewer pipelines, canals and the like are important features of the urban environment. They are often conceived of and represented as network-based arcs. As a result of the usefulness and significance of arc-based features, there is a need to site facilities along arcs to serve demand. Examples of such facilities include surveillance equipment, cellular towers, refueling centers and emergency response stations, with the intent of being economically efficient as well as providing good service along the arcs. While this amounts to a continuous location problem by nature, various discretizations are generally relied upon to solve such problems. The result is potential for representation errors that negatively impact analysis and decision making. This paper develops a solution approach for the continuous arc covering problem that theoretically eliminates representation errors. The developed approach is applied to optimally place acoustic sensors and cellular base stations along a road network. The results demonstrate the effectiveness of this approach for ameliorating any error and uncertainty in the modeling process.

An Example of Unsupervised Networks Kohonen's Self-Organizing Feature Map

NASA Technical Reports Server (NTRS)

Niebur, Dagmar

1995-01-01

Kohonen's self-organizing feature map belongs to a class of unsupervised artificial neural network commonly referred to as topographic maps. It serves two purposes, the quantization and dimensionality reduction of date. A short description of its history and its biological context is given. We show that the inherent classification properties of the feature map make it a suitable candidate for solving the classification task in power system areas like load forecasting, fault diagnosis and security assessment.

Sentence alignment using feed forward neural network.

PubMed

Fattah, Mohamed Abdel; Ren, Fuji; Kuroiwa, Shingo

2006-12-01

Parallel corpora have become an essential resource for work in multi lingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross language information retrieval and machine translation applications. In this paper, we present a new approach to align sentences in bilingual parallel corpora based on feed forward neural network classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuate score, and cognate score values. A set of manually prepared training data has been assigned to train the feed forward neural network. Another set of data was used for testing. Using this new approach, we could achieve an error reduction of 60% over length based approach when applied on English-Arabic parallel documents. Moreover this new approach is valid for any language pair and it is quite flexible approach since the feature parameter vector may contain more/less or different features than that we used in our system such as lexical match feature.

Human dorsolateral prefrontal cortex is involved in visual search for conjunctions but not features: a theta TMS study.

PubMed

Kalla, Roger; Muggleton, Neil G; Cowey, Alan; Walsh, Vincent

2009-10-01

Functional neuroimaging studies have shown that the detection of a target defined by more than one feature (for example, a conjunction of colour and orientation) amongst distractors is associated with the activation of a network of brain areas. Dorsolateral prefrontal cortex (DLPFC), along with areas such as the frontal eye fields (FEF) and posterior parietal cortex (PPC), is a component of this network. While transcranial magnetic stimulation (TMS) had shown that both FEF and PPC are necessary for, and not just correlated with, successful conjunction search, this is not the case for DLPFC. To test the hypothesis that this area is also necessary for efficient conjunction search, TMS was applied over DLPFC and the effects on conjunction and feature (in this case colour) search performance compared with those when TMS was delivered over area MT/V5 and a vertex control stimulation condition. DLPFC TMS impaired performance on the conjunction search task but was without effect on feature search, similar to findings when TMS is delivered over PPC or FEF. Vertex TMS had no effects whereas MT/V5 TMS significantly improved performance with a time course that may indicate that this was due to modulation of V4 activity. These findings illustrate that, like FEF and PPC, DLPFC is necessary for fully effective conjunction visual search performance.

Detecting complexes from edge-weighted PPI networks via genes expression analysis.

PubMed

Zhang, Zehua; Song, Jian; Tang, Jijun; Xu, Xinying; Guo, Fei

2018-04-24

Identifying complexes from PPI networks has become a key problem to elucidate protein functions and identify signal and biological processes in a cell. Proteins binding as complexes are important roles of life activity. Accurate determination of complexes in PPI networks is crucial for understanding principles of cellular organization. We propose a novel method to identify complexes on PPI networks, based on different co-expression information. First, we use Markov Cluster Algorithm with an edge-weighting scheme to calculate complexes on PPI networks. Then, we propose some significant features, such as graph information and gene expression analysis, to filter and modify complexes predicted by Markov Cluster Algorithm. To evaluate our method, we test on two experimental yeast PPI networks. On DIP network, our method has Precision and F-Measure values of 0.6004 and 0.5528. On MIPS network, our method has F-Measure and S n values of 0.3774 and 0.3453. Comparing to existing methods, our method improves Precision value by at least 0.1752, F-Measure value by at least 0.0448, S n value by at least 0.0771. Experiments show that our method achieves better results than some state-of-the-art methods for identifying complexes on PPI networks, with the prediction quality improved in terms of evaluation criteria.

Dexmedetomidine Disrupts the Local and Global Efficiencies of Large-scale Brain Networks.

PubMed

Hashmi, Javeria A; Loggia, Marco L; Khan, Sheraz; Gao, Lei; Kim, Jieun; Napadow, Vitaly; Brown, Emery N; Akeju, Oluwaseun

2017-03-01

A clear understanding of the neural basis of consciousness is fundamental to research in clinical and basic neuroscience disciplines and anesthesia. Recently, decreased efficiency of information integration was suggested as a core network feature of propofol-induced unconsciousness. However, it is unclear whether this finding can be generalized to dexmedetomidine, which has a different molecular target. Dexmedetomidine was administered as a 1-μg/kg bolus over 10 min, followed by a 0.7-μg · kg · h infusion to healthy human volunteers (age range, 18 to 36 yr; n = 15). Resting-state functional magnetic resonance imaging data were acquired during baseline, dexmedetomidine-induced altered arousal, and recovery states. Zero-lag correlations between resting-state functional magnetic resonance imaging signals extracted from 131 brain parcellations were used to construct weighted brain networks. Network efficiency, degree distribution, and node strength were computed using graph analysis. Parcellated brain regions were also mapped to known resting-state networks to study functional connectivity changes. Dexmedetomidine significantly reduced the local and global efficiencies of graph theory-derived networks. Dexmedetomidine also reduced the average brain connectivity strength without impairing the degree distribution. Functional connectivity within and between all resting-state networks was modulated by dexmedetomidine. Dexmedetomidine is associated with a significant drop in the capacity for efficient information transmission at both the local and global levels. These changes result from reductions in the strength of connectivity and also manifest as reduced within and between resting-state network connectivity. These findings strengthen the hypothesis that conscious processing relies on an efficient system of information transfer in the brain.

Altered structural connectivity of pain-related brain network in burning mouth syndrome-investigation by graph analysis of probabilistic tractography.

PubMed

Wada, Akihiko; Shizukuishi, Takashi; Kikuta, Junko; Yamada, Haruyasu; Watanabe, Yusuke; Imamura, Yoshiki; Shinozaki, Takahiro; Dezawa, Ko; Haradome, Hiroki; Abe, Osamu

2017-05-01

Burning mouth syndrome (BMS) is a chronic intraoral pain syndrome featuring idiopathic oral pain and burning discomfort despite clinically normal oral mucosa. The etiology of chronic pain syndrome is unclear, but preliminary neuroimaging research has suggested the alteration of volume, metabolism, blood flow, and diffusion at multiple brain regions. According to the neuromatrix theory of Melzack, pain sense is generated in the brain by the network of multiple pain-related brain regions. Therefore, the alteration of pain-related network is also assumed as an etiology of chronic pain. In this study, we investigated the brain network of BMS brain by using probabilistic tractography and graph analysis. Fourteen BMS patients and 14 age-matched healthy controls underwent 1.5T MRI. Structural connectivity was calculated in 83 anatomically defined regions with probabilistic tractography of 60-axis diffusion tensor imaging and 3D T1-weighted imaging. Graph theory network analysis was used to evaluate the brain network at local and global connectivity. In BMS brain, a significant difference of local brain connectivity was recognized at the bilateral rostral anterior cingulate cortex, right medial orbitofrontal cortex, and left pars orbitalis which belong to the medial pain system; however, no significant difference was recognized at the lateral system including the somatic sensory cortex. A strengthened connection of the anterior cingulate cortex and medial prefrontal cortex with the basal ganglia, thalamus, and brain stem was revealed. Structural brain network analysis revealed the alteration of the medial system of the pain-related brain network in chronic pain syndrome.

Channel and feature selection in multifunction myoelectric control.

PubMed

Khushaba, Rami N; Al-Jumaily, Adel

2007-01-01

Real time controlling devices based on myoelectric singles (MES) is one of the challenging research problems. This paper presents a new approach to reduce the computational cost of real time systems driven by Myoelectric signals (MES) (a.k.a Electromyography--EMG). The new approach evaluates the significance of feature/channel selection on MES pattern recognition. Particle Swarm Optimization (PSO), an evolutionary computational technique, is employed to search the feature/channel space for important subsets. These important subsets will be evaluated using a multilayer perceptron trained with back propagation neural network (BPNN). Practical results acquired from tests done on six subjects' datasets of MES signals measured in a noninvasive manner using surface electrodes are presented. It is proved that minimum error rates can be achieved by considering the correct combination of features/channels, thus providing a feasible system for practical implementation purpose for rehabilitation of patients.

Image quality classification for DR screening using deep learning.

PubMed

FengLi Yu; Jing Sun; Annan Li; Jun Cheng; Cheng Wan; Jiang Liu

2017-07-01

The quality of input images significantly affects the outcome of automated diabetic retinopathy (DR) screening systems. Unlike the previous methods that only consider simple low-level features such as hand-crafted geometric and structural features, in this paper we propose a novel method for retinal image quality classification (IQC) that performs computational algorithms imitating the working of the human visual system. The proposed algorithm combines unsupervised features from saliency map and supervised features coming from convolutional neural networks (CNN), which are fed to an SVM to automatically detect high quality vs poor quality retinal fundus images. We demonstrate the superior performance of our proposed algorithm on a large retinal fundus image dataset and the method could achieve higher accuracy than other methods. Although retinal images are used in this study, the methodology is applicable to the image quality assessment and enhancement of other types of medical images.

Functional complexity emerging from anatomical constraints in the brain: the significance of network modularity and rich-clubs

NASA Astrophysics Data System (ADS)

Zamora-López, Gorka; Chen, Yuhan; Deco, Gustavo; Kringelbach, Morten L.; Zhou, Changsong

2016-12-01

The large-scale structural ingredients of the brain and neural connectomes have been identified in recent years. These are, similar to the features found in many other real networks: the arrangement of brain regions into modules and the presence of highly connected regions (hubs) forming rich-clubs. Here, we examine how modules and hubs shape the collective dynamics on networks and we find that both ingredients lead to the emergence of complex dynamics. Comparing the connectomes of C. elegans, cats, macaques and humans to surrogate networks in which either modules or hubs are destroyed, we find that functional complexity always decreases in the perturbed networks. A comparison between simulated and empirically obtained resting-state functional connectivity indicates that the human brain, at rest, lies in a dynamical state that reflects the largest complexity its anatomical connectome can host. Last, we generalise the topology of neural connectomes into a new hierarchical network model that successfully combines modular organisation with rich-club forming hubs. This is achieved by centralising the cross-modular connections through a preferential attachment rule. Our network model hosts more complex dynamics than other hierarchical models widely used as benchmarks.

Functional complexity emerging from anatomical constraints in the brain: the significance of network modularity and rich-clubs

PubMed Central

Zamora-López, Gorka; Chen, Yuhan; Deco, Gustavo; Kringelbach, Morten L.; Zhou, Changsong

2016-01-01

The large-scale structural ingredients of the brain and neural connectomes have been identified in recent years. These are, similar to the features found in many other real networks: the arrangement of brain regions into modules and the presence of highly connected regions (hubs) forming rich-clubs. Here, we examine how modules and hubs shape the collective dynamics on networks and we find that both ingredients lead to the emergence of complex dynamics. Comparing the connectomes of C. elegans, cats, macaques and humans to surrogate networks in which either modules or hubs are destroyed, we find that functional complexity always decreases in the perturbed networks. A comparison between simulated and empirically obtained resting-state functional connectivity indicates that the human brain, at rest, lies in a dynamical state that reflects the largest complexity its anatomical connectome can host. Last, we generalise the topology of neural connectomes into a new hierarchical network model that successfully combines modular organisation with rich-club forming hubs. This is achieved by centralising the cross-modular connections through a preferential attachment rule. Our network model hosts more complex dynamics than other hierarchical models widely used as benchmarks. PMID:27917958

Development of visible-light responsive and mechanically enhanced "smart" UCST interpenetrating network hydrogels.

PubMed

Xu, Yifei; Ghag, Onkar; Reimann, Morgan; Sitterle, Philip; Chatterjee, Prithwish; Nofen, Elizabeth; Yu, Hongyu; Jiang, Hanqing; Dai, Lenore L

2017-12-20

An interpenetrating polymer network (IPN), chlorophyllin-incorporated environmentally responsive hydrogel was synthesized and exhibited the following features: enhanced mechanical properties, upper critical solution temperature (UCST) swelling behavior, and promising visible-light responsiveness. Poor mechanical properties are known challenges for hydrogel-based materials. By forming an interpenetrating network between polyacrylamide (PAAm) and poly(acrylic acid) (PAAc) polymer networks, the mechanical properties of the synthesized IPN hydrogels were significantly improved compared to hydrogels made of a single network of each polymer. The formation of the interpenetrating network was confirmed by Fourier Transform Infrared Spectroscopy (FTIR), the analysis of glass transition temperature, and a unique UCST responsive swelling behavior, which is in contrast to the more prevalent lower critical solution temperature (LCST) behaviour of environmentally responsive hydrogels. The visible-light responsiveness of the synthesized hydrogel also demonstrated a positive swelling behavior, and the effect of incorporating chlorophyllin as the chromophore unit was observed to reduce the average pore size and further enhance the mechanical properties of the hydrogel. This interpenetrating network system shows potential to serve as a new route in developing "smart" hydrogels using visible-light as a simple, inexpensive, and remotely controllable stimulus.

Revealing the Hidden Relationship by Sparse Modules in Complex Networks with a Large-Scale Analysis

PubMed Central

Jiao, Qing-Ju; Huang, Yan; Liu, Wei; Wang, Xiao-Fan; Chen, Xiao-Shuang; Shen, Hong-Bin

2013-01-01

One of the remarkable features of networks is module that can provide useful insights into not only network organizations but also functional behaviors between their components. Comprehensive efforts have been devoted to investigating cohesive modules in the past decade. However, it is still not clear whether there are important structural characteristics of the nodes that do not belong to any cohesive module. In order to answer this question, we performed a large-scale analysis on 25 complex networks with different types and scales using our recently developed BTS (bintree seeking) algorithm, which is able to detect both cohesive and sparse modules in the network. Our results reveal that the sparse modules composed by the cohesively isolated nodes widely co-exist with the cohesive modules. Detailed analysis shows that both types of modules provide better characterization for the division of a network into functional units than merely cohesive modules, because the sparse modules possibly re-organize the nodes in the so-called cohesive modules, which lack obvious modular significance, into meaningful groups. Compared with cohesive modules, the sizes of sparse ones are generally smaller. Sparse modules are also found to have preferences in social and biological networks than others. PMID:23762457

Prediction and functional analysis of the sweet orange protein-protein interaction network.

PubMed

Ding, Yu-Duan; Chang, Ji-Wei; Guo, Jing; Chen, Dijun; Li, Sen; Xu, Qiang; Deng, Xiu-Xin; Cheng, Yun-Jiang; Chen, Ling-Ling

2014-08-05

Sweet orange (Citrus sinensis) is one of the most important fruits world-wide. Because it is a woody plant with a long growth cycle, genetic studies of sweet orange are lagging behind those of other species. In this analysis, we employed ortholog identification and domain combination methods to predict the protein-protein interaction (PPI) network for sweet orange. The K-nearest neighbors (KNN) classification method was used to verify and filter the network. The final predicted PPI network, CitrusNet, contained 8,195 proteins with 124,491 interactions. The quality of CitrusNet was evaluated using gene ontology (GO) and Mapman annotations, which confirmed the reliability of the network. In addition, we calculated the expression difference of interacting genes (EDI) in CitrusNet using RNA-seq data from four sweet orange tissues, and also analyzed the EDI distribution and variation in different sub-networks. Gene expression in CitrusNet has significant modular features. Target of rapamycin (TOR) protein served as the central node of the hormone-signaling sub-network. All evidence supported the idea that TOR can integrate various hormone signals and affect plant growth. CitrusNet provides valuable resources for the study of biological functions in sweet orange.

Scalable Online Network Modeling and Simulation

DTIC Science & Technology

2005-08-01

ONLINE NETWORK MODELING AND SIMULATION 6. AUTHOR(S) Boleslaw Szymanski , Shivkumar Kalyanaraman, Biplab Sikdar and Christopher Carothers 5...performance for a wide range of parameter values (parameter sensitivity), understanding of protocol stability and dynamics, and studying feature ...a wide range of parameter values (parameter sensitivity), understanding of protocol stability and dynamics, and studying feature interactions

Toward a Mobility-Driven Architecture for Multimodal Underwater Networking

DTIC Science & Technology

2017-02-01

applications. By equipping AUVs with short-range, high -bandwidth underwater wireless communications , which feature lower energy-per-bit cost than acoustic...protocols. They suffer from significant transmission path losses at high frequencies , long propagation delays, low and distance-dependent bandwidth, time...of data preprocessing, data compression, and either tethering to a surface buoy able to use radio frequency (RF) communications or using undersea

Social Learning among People Who Are Excluded from the Labor Market. Part One: Context and Case Studies. NALL Working Paper.

ERIC Educational Resources Information Center

Church, Kathryn; Fontan, Jean-Marc; Ng, Roxana; Shragge, Eric

This working paper lays groundwork for a Network for New Approaches to Lifelong Learning study on informal learning by people displaced from the labor market or chronically unemployed, in the context of community organizations. Section 1 examines the context and two particularly significant features--wider changes in the nature of work and related…

Visual Saliency Detection Based on Multiscale Deep CNN Features.

PubMed

Guanbin Li; Yizhou Yu

2016-11-01

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using deep convolutional neural networks (CNNs), which have had many successes in visual recognition tasks. For learning such saliency models, we introduce a neural network architecture, which has fully connected layers on top of CNNs responsible for feature extraction at three different scales. The penultimate layer of our neural network has been confirmed to be a discriminative high-level feature vector for saliency detection, which we call deep contrast feature. To generate a more robust feature, we integrate handcrafted low-level features with our deep contrast feature. To promote further research and evaluation of visual saliency models, we also construct a new large database of 4447 challenging images and their pixelwise saliency annotations. Experimental results demonstrate that our proposed method is capable of achieving the state-of-the-art performance on all public benchmarks, improving the F-measure by 6.12% and 10%, respectively, on the DUT-OMRON data set and our new data set (HKU-IS), and lowering the mean absolute error by 9% and 35.3%, respectively, on these two data sets.

Selective attention to temporal features on nested time scales.

PubMed

Henry, Molly J; Herrmann, Björn; Obleser, Jonas

2015-02-01

Meaningful auditory stimuli such as speech and music often vary simultaneously along multiple time scales. Thus, listeners must selectively attend to, and selectively ignore, separate but intertwined temporal features. The current study aimed to identify and characterize the neural network specifically involved in this feature-selective attention to time. We used a novel paradigm where listeners judged either the duration or modulation rate of auditory stimuli, and in which the stimulation, working memory demands, response requirements, and task difficulty were held constant. A first analysis identified all brain regions where individual brain activation patterns were correlated with individual behavioral performance patterns, which thus supported temporal judgments generically. A second analysis then isolated those brain regions that specifically regulated selective attention to temporal features: Neural responses in a bilateral fronto-parietal network including insular cortex and basal ganglia decreased with degree of change of the attended temporal feature. Critically, response patterns in these regions were inverted when the task required selectively ignoring this feature. The results demonstrate how the neural analysis of complex acoustic stimuli with multiple temporal features depends on a fronto-parietal network that simultaneously regulates the selective gain for attended and ignored temporal features. © The Author 2013. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Neural network-based feature point descriptors for registration of optical and SAR images

NASA Astrophysics Data System (ADS)

Abulkhanov, Dmitry; Konovalenko, Ivan; Nikolaev, Dmitry; Savchik, Alexey; Shvets, Evgeny; Sidorchuk, Dmitry

2018-04-01

Registration of images of different nature is an important technique used in image fusion, change detection, efficient information representation and other problems of computer vision. Solving this task using feature-based approaches is usually more complex than registration of several optical images because traditional feature descriptors (SIFT, SURF, etc.) perform poorly when images have different nature. In this paper we consider the problem of registration of SAR and optical images. We train neural network to build feature point descriptors and use RANSAC algorithm to align found matches. Experimental results are presented that confirm the method's effectiveness.

Extraction of texture features with a multiresolution neural network

NASA Astrophysics Data System (ADS)

Lepage, Richard; Laurendeau, Denis; Gagnon, Roger A.

1992-09-01

Texture is an important surface characteristic. Many industrial materials such as wood, textile, or paper are best characterized by their texture. Detection of defaults occurring on such materials or classification for quality control anD matching can be carried out through careful texture analysis. A system for the classification of pieces of wood used in the furniture industry is proposed. This paper is concerned with a neural network implementation of the features extraction and classification components of the proposed system. Texture appears differently depending at which spatial scale it is observed. A complete description of a texture thus implies an analysis at several spatial scales. We propose a compact pyramidal representation of the input image for multiresolution analysis. The feature extraction system is implemented on a multilayer artificial neural network. Each level of the pyramid, which is a representation of the input image at a given spatial resolution scale, is mapped into a layer of the neural network. A full resolution texture image is input at the base of the pyramid and a representation of the texture image at multiple resolutions is generated by the feedforward pyramid structure of the neural network. The receptive field of each neuron at a given pyramid level is preprogrammed as a discrete Gaussian low-pass filter. Meaningful characteristics of the textured image must be extracted if a good resolving power of the classifier must be achieved. Local dominant orientation is the principal feature which is extracted from the textured image. Local edge orientation is computed with a Sobel mask at four orientation angles (multiple of (pi) /4). The resulting intrinsic image, that is, the local dominant orientation image, is fed to the texture classification neural network. The classification network is a three-layer feedforward back-propagation neural network.

Scalable Multicast Protocols for Overlapped Groups in Broker-Based Sensor Networks

NASA Astrophysics Data System (ADS)

Kim, Chayoung; Ahn, Jinho

In sensor networks, there are lots of overlapped multicast groups because of many subscribers, associated with their potentially varying specific interests, querying every event to sensors/publishers. And gossip based communication protocols are promising as one of potential solutions providing scalability in P(Publish)/ S(Subscribe) paradigm in sensor networks. Moreover, despite the importance of both guaranteeing message delivery order and supporting overlapped multicast groups in sensor or P2P networks, there exist little research works on development of gossip-based protocols to satisfy all these requirements. In this paper, we present two versions of causally ordered delivery guaranteeing protocols for overlapped multicast groups. The one is based on sensor-broker as delegates and the other is based on local views and delegates representing subscriber subgroups. In the sensor-broker based protocol, sensor-broker might lead to make overlapped multicast networks organized by subscriber's interests. The message delivery order has been guaranteed consistently and all multicast messages are delivered to overlapped subscribers using gossip based protocols by sensor-broker. Therefore, these features of the sensor-broker based protocol might be significantly scalable rather than those of the protocols by hierarchical membership list of dedicated groups like traditional committee protocols. And the subscriber-delegate based protocol is much stronger rather than fully decentralized protocols guaranteeing causally ordered delivery based on only local views because the message delivery order has been guaranteed consistently by all corresponding members of the groups including delegates. Therefore, this feature of the subscriber-delegate protocol is a hybrid approach improving the inherent scalability of multicast nature by gossip-based technique in all communications.

Political opinion formation: Initial opinion distribution and individual heterogeneity of tolerance

NASA Astrophysics Data System (ADS)

Jin, Cheng; Li, Yifu; Jin, Xiaogang

2017-02-01

Opinion dynamics on networks have received serious attention for its profound prospects in social behaviours and self-organized systems. However, political opinion formation, as one typical and significant case, remains lacking in discussion. Previous agent-based simulations propose various models that are based on different mechanisms like the coevolution between network topology and status transition. Nonetheless, even under the same network topology and with the same simple mechanism, forming opinions can still be uncertain. In this work, we propose two features, the initial distribution of opinions and the individual heterogeneity of tolerances on opinion changing, in political opinion formation. These two features are imbedded in the network construction phase of a classical model. By comparing multi simple-party systems, along with a detailed analysis on the two-party system, we capture the critical phenomenon of fragmentation, polarization and consensus both in the persistent stable stage and in-process. We further introduce the average ratio of nearest neighbours to characterize the stage of opinion formation. The results show that the initial distribution of opinions leads to different evolution results on similar random networks. In addition, the existence of stubborn nodes plays a special role: only nodes that are extremely stubborn can cause the change of final opinion distribution while in other cases they only delay the time to reach stability. If stubborn nodes are small in number, their effects are confined within a small range. This theoretical work goes deeper on an existing model, it is an early exploration on qualitative and quantitative simulation of party competition.

Classification of clinically useful sentences in clinical evidence resources.

PubMed

Morid, Mohammad Amin; Fiszman, Marcelo; Raja, Kalpana; Jonnalagadda, Siddhartha R; Del Fiol, Guilherme

2016-04-01

Most patient care questions raised by clinicians can be answered by online clinical knowledge resources. However, important barriers still challenge the use of these resources at the point of care. To design and assess a method for extracting clinically useful sentences from synthesized online clinical resources that represent the most clinically useful information for directly answering clinicians' information needs. We developed a Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents. These features included UMLS concepts and their semantic groups, semantic predications extracted by SemRep, patient population identified by a pattern-based natural language processing (NLP) algorithm, and cue words extracted by a feature selection technique. Algorithm performance was measured in terms of precision, recall, and F-measure. The feature-rich approach yielded an F-measure of 74% versus 37% for a feature co-occurrence method (p<0.001). Excluding predication, population, semantic concept or text-based features reduced the F-measure to 62%, 66%, 58% and 69% respectively (p<0.01). The classifier applied to Medline sentences reached an F-measure of 73%, which is equivalent to the performance of the classifier on UpToDate sentences (p=0.62). The feature-rich approach significantly outperformed general baseline methods. This approach significantly outperformed classifiers based on a single type of feature. Different types of semantic features provided a unique contribution to overall classification performance. The classifier's model and features used for UpToDate generalized well to Medline abstracts. Copyright © 2016 Elsevier Inc. All rights reserved.

LWT Based Sensor Node Signal Processing in Vehicle Surveillance Distributed Sensor Network

NASA Astrophysics Data System (ADS)

Cha, Daehyun; Hwang, Chansik

Previous vehicle surveillance researches on distributed sensor network focused on overcoming power limitation and communication bandwidth constraints in sensor node. In spite of this constraints, vehicle surveillance sensor node must have signal compression, feature extraction, target localization, noise cancellation and collaborative signal processing with low computation and communication energy dissipation. In this paper, we introduce an algorithm for light-weight wireless sensor node signal processing based on lifting scheme wavelet analysis feature extraction in distributed sensor network.

Information Security and Privacy in Network Environments.

ERIC Educational Resources Information Center

Congress of the U.S., Washington, DC. Office of Technology Assessment.

The use of information networks for business and government is expanding enormously. Government use of networks features prominently in plans to make government more efficient, effective, and responsive. But the transformation brought about by the networking also raises new concerns for the security and privacy of networked information. This…