Random Field Network Research Articles

Image Semantic Segmentation Approach for Studying Human Behavior on Image Data

Image semantic segmentation is an essential technique for studying human behavior through image data. This paper proposes an image semantic segmentation method for human behavior research. Firstly, an end-to-end convolutional neural network architecture is proposed, which consists of a depth-separable jump-connected fully convolutional network and a conditional random field network; then jump-connected convolution is used to classify each pixel in the image, and an image semantic segmentation method based on convolutional neural network is proposed; and then a conditional random field network is used to improve the effect of image segmentation of human behavior and a linear modeling and nonlinear modeling method based on the semantic segmentation of conditional random field image is proposed. Finally, using the proposed image segmentation network, the input entrepreneurial image data is semantically segmented to obtain the contour features of the person; and the segmentation of the images in the medical field. The experimental results show that the image semantic segmentation method is effective. It is a new way to use image data to study human behavior and can be extended to other research areas.

Aorta Segmentation in 3D CT Images by Combining Image Processing and Machine Learning Techniques.

Aorta segmentation is extremely useful in clinical practice, allowing the diagnosis of numerous pathologies, such as dissections, aneurysms and occlusive disease. In such cases, image segmentation is prerequisite for applying diagnostic algorithms, which in turn allow the prediction of possible complications and enable risk assessment, which is crucial in saving lives. The aim of this paper is to present a novel fully automatic 3D segmentation method, which combines basic image processing techniques and more advanced machine learning algorithms, for detecting and modelling the aorta in 3D CT imaging data. An initial intensity threshold-based segmentation procedure is followed by a classification-based segmentation approach, based on a Markov Random Field network. The result of the proposed two-stage segmentation process is modelled and visualized. The proposed methodology was applied to 16 3D CT data sets and the extracted aortic segments were reconstructed as 3D models. The performance of segmentation was evaluated both qualitatively and quantitatively against other commonly used segmentation techniques, in terms of the accuracy achieved, compared to the actual aorta, which was defined manually by experts. The proposed methodology achieved superior segmentation performance, compared to all compared segmentation techniques, in terms of the accuracy of the extracted 3D aortic model. Therefore, the proposed segmentation scheme could be used in clinical practice, such as in treatment planning and assessment, as it can speed up the evaluation of the medical imaging data, which is commonly a lengthy and tedious process.

A Novel Constructive Unceasement Conditional Random Field and Dynamic Bayesian Network Model for Attack Prediction on Internet of Vehicle

A Novel Constructive Unceasement Conditional Random Field and Dynamic Bayesian Network Model for Attack Prediction on Internet of Vehicle

Context-Aware Attentive Multilevel Feature Fusion for Named Entity Recognition.

In the era of information explosion, named entity recognition (NER) has attracted widespread attention in the field of natural language processing, as it is fundamental to information extraction. Recently, methods of NER based on representation learning, e.g., character embedding and word embedding, have demonstrated promising recognition results. However, existing models only consider partial features derived from words or characters while failing to integrate semantic and syntactic information, e.g., capitalization, inter-word relations, keywords, and lexical phrases, from multilevel perspectives. Intuitively, multilevel features can be helpful when recognizing named entities from complex sentences. In this study, we propose a novel attentive multilevel feature fusion (AMFF) model for NER, which captures the multilevel features in the current context from various perspectives. It consists of four components to, respectively, capture the local character-level (CL), global character-level (CG), local word-level (WL), and global word-level (WG) features in the current context. In addition, we further define document-level features crafted from other sentences to enhance the representation learning of the current context. To this end, we introduce a novel context-aware attentive multilevel feature fusion (CAMFF) model based on AMFF, to fully leverage document-level features from all the previous inputs. The obtained multilevel features are then fused and fed into a bidirectional long short-term memory (BiLSTM)-conditional random field (CRF) network for the final sequence labeling. Extensive experiments on four benchmark datasets demonstrate that our proposed AMFF and CAMFF models outperform a set of state-of-the-art baseline methods and the features learned from multiple levels are complementary.

FCUnet: Refined remote sensing image segmentation method based on a fuzzy deep learning conditional random field network

AbstractImage segmentation is pivotal for the understanding of high‐resolution remote sensing images (HRRS). However, because of the inherent uncertainties in remote sensing images and the highly complex resolution of HRRS, ambiguity often occurs among some geographic entities in the segmentation process, and the fine segmentation of HRRS is not considered sufficiently for most existing segmentation methods. Therefore, in this paper, the authors propose a new collaborative neural network structure called fuzzy deep learning conditional random field network (FCUnet) to solve the refined segmentation of HRRS. First, the authors design a fuzzy U‐Net classification network to obtain effective feature information, which introduces the fuzzy logic unit into the network to process the ambiguity and uncertainty of HRRS. Then, the authors introduce the conditional random field (CRF) at the end of FCUnet to optimize the image segmentation results. Finally, the authors validated the effectiveness and superiority of their approach on three data sets. The experiment results revealed that FCUnet had better refined segmentation performance and generalization ability than state‐of‐the‐art methods.

Neural-FEBI: Accurate function identification in Ethereum Virtual Machine bytecode

Millions of smart contracts have been deployed onto the Ethereum platform, posing potential attack subjects. Therefore, analyzing contract binaries is vital since their sources are unavailable, involving identification comprising function entry identification and detecting its boundaries. Such boundaries are critical to many smart contract applications, e.g. reverse engineering and profiling. Unfortunately, it is challenging to identify functions from these stripped contract binaries due to the lack of internal function call statements and the compiler-inducing instruction reshuffling. Recently, several existing works excessively relied on a set of handcrafted heuristic rules which impose several faults. To address this issue, we propose a novel neural network-based framework for EVM bytecode Function Entries and Boundaries Identification (neural-FEBI) that does not rely on a fixed set of handcrafted rules. Instead, it used a two-level bi-Long Short-Term Memory network and a Conditional Random Field network to locate the function entries. The suggested framework also devises a control flow traversal algorithm to determine the code segments reachable from the function entry as its boundary. Several experiments on 38,996 publicly available smart contracts collected as binary demonstrate that neural-FEBI confirms the lowest and highest F1-scores for the function entries identification task across different datasets of 88.3 to 99.7, respectively. Its performance on the function boundary identification task is also increased from 79.4% to 97.1% compared with state-of-the-art. We further demonstrate that the identified function information can be used to construct more accurate intra-procedural CFGs and call graphs. The experimental results confirm that the proposed framework significantly outperforms state-of-the-art, often based on handcrafted heuristic rules.

Forecasting Energy Demand Using Conditional Random Field and Convolution Neural Network

Electric load forecasting has been identified as an effective strategy to increase output and revenues in electrical manufacturing and distribution organizations. Several strategies for forecasting power consumption have been suggested; however, they all fail to account for small variations in power demand throughout the prediction. Therefore, the aim of this study was to develop a CRF-based power consumption prediction technique (CRF-PCP) to meet the difficulty of estimating energy consumption (EC). The EC of regions in the area is forecasted using convolution neural networks (CNNs) and conditional random fields (CRFs). Then, using the cloud, the predicted results are delivered to the electricity distribution system. To our knowledge, this is the first attempt to forecast electricity demand using CNN and CRF algorithms. In comparison to state-of-the-art algorithms, this proposed technique achieves 98.9 % accuracy. This recommended work also obtained minimum values of root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and mean bias error (MBE) by using 10-fold cross-validation (CV) and a hold-out (CV) methodology.

Brain Tumor Classification Using Conditional Segmentation with Residual Network and Attention Approach by Extreme Gradient Boost

A brain tumor is a tumor in the brain that has grown out of control, which is a dangerous condition for the human body. For later prognosis and treatment planning, the accurate segmentation and categorization of cancers are crucial. Radiologists must use an automated approach to identify brain tumors, since it is an error-prone and time-consuming operation. This work proposes conditional deep learning for brain tumor segmentation, residual network-based classification, and overall survival prediction using structural multimodal magnetic resonance images (MRI). First, we propose conditional random field and convolution network-based segmentation, which identifies non-overlapped patches. These patches need minimal time to identify the tumor. If they overlap, the errors increase. The second part of this paper proposes residual network-based feature mapping with XG-Boost-based learning. In the second part, the main emphasis is on feature mapping in nonlinear space with residual features, since residual features reduce the chances of loss information, and nonlinear space mapping provides efficient tumor information. Features mapping learned by XG-Boost improves the structural-based learning and increases the accuracy class-wise. The experiment uses two datasets: one for two classes (cancer and non-cancer) and the other for three classes (meningioma, glioma, pituitary). The performance on both improves significantly compared to another existing approach. The main objective of this research work is to improve segmentation and its impact on classification performance parameters. It improves by conditional random field and residual network. As a result, two-class accuracy improves by 3.4% and three-class accuracy improves by 2.3%. It is enhanced with a small convolution network. So, we conclude in fewer resources, and better segmentation improves the results of brain tumor classification.

Diagnosis of Alzheimer's Disease by Inspection of Hippocampus Atrophy Using Conditional Random Field, Active Contour and Deep Neural Networks

Diagnosis of Alzheimer's Disease by Inspection of Hippocampus Atrophy Using Conditional Random Field, Active Contour and Deep Neural Networks

Separation Inference: A Unified Framework for Word Segmentation in East Asian Languages

Existing methods consider Word Segmentation (WS) as sequence tagging. Each tag indicates the position of the current character in a segment. The exactness of the position for any non-boundaries character is unnecessary. Any incorrect inner prediction reduces model performance. The position information restricts tag-to-tag transition. Thereby, extra context information and the Conditional Random Field (CRF) network are desired to control unreasonable tag transition. To steer away from the implicit restriction, we propose the Separation(Sp)-Adhesion(Ad), which targets straight on the essential character-to-character connections, to tackle the WS task directly. Merely bigram that is specially tailored for “Sp-Ad” is required and considered as the processing unit to identify the connection states of every two adjacent characters. The elimination of the position restriction makes the model independent of the CRF layer which is widely adopted to revise unreasonable tags. Therefore, CRF can then be substituted with a classification network. We construct the Separation Inference (SpIn) framework based on the bigram features and softmax classification network to tackle the WS task. SpIn significantly reduces the inference complexity, dispels extra context information, and boosts the accuracy of the WS task. Besides its effectiveness in Chinese Word Segmentation, performance boosts on Japanese and Korean Word Segmentation further prove SpIn is universal for East Asian Languages. Moreover, our extensive experiments also verify the cross-domain effectiveness of SpIn by attaining state-of-the-art performances in the benchmark tests of in-domain and cross-domain Chinese Word Segmentation.

Minimum redundancy maximal relevance gene selection of apoptosis pathway genes in peripheral blood mononuclear cells of HIV-infected patients with antiretroviral therapy-associated mitochondrial toxicity

BackgroundWe previously identified differentially expressed genes on the basis of false discovery rate adjusted P value using empirical Bayes moderated tests. However, that approach yielded a subset of differentially expressed genes without accounting for redundancy between the selected genes.MethodsThis study is a secondary analysis of a case–control study of the effect of antiretroviral therapy on apoptosis pathway genes comprising of 16 cases (HIV infected with mitochondrial toxicity) and 16 controls (uninfected). We applied the maximum relevance minimum redundancy (mRMR) algorithm on the genes that were differentially expressed between the cases and controls. The mRMR algorithm iteratively selects features (genes) that are maximally relevant for class prediction and minimally redundant. We implemented several machine learning classifiers and tested the prediction accuracy of the two mRMR genes. We next used network analysis to estimate and visualize the association among the differentially expressed genes. We employed Markov Random Field or undirected network models to identify gene networks related to mitochondrial toxicity. The Spinglass model was used to identify clusters of gene communities.ResultsThe mRMR algorithm ranked DFFA and TNFRSF1A, two of the upregulated proapoptotic genes, on the top. The overall prediction accuracy was 86%, the two mRMR genes correctly classified 86% of the participants into their respective groups. The estimated network models showed different patterns of gene networks. In the network of the cases, FASLG was the most central gene. However, instead of FASLG, ABL1 and LTBR had the highest centrality in controls.ConclusionThe mRMR algorithm and network analysis revealed a new correlation of genes associated with mitochondrial toxicity.

CTD: An information-theoretic algorithm to interpret sets of metabolomic and transcriptomic perturbations in the context of graphical models.

We consider the following general family of algorithmic problems that arises in transcriptomics, metabolomics and other fields: given a weighted graph G and a subset of its nodes S, find subsets of S that show significant connectedness within G. A specific solution to this problem may be defined by devising a scoring function, the Maximum Clique problem being a classic example, where S includes all nodes in G and where the score is defined by the size of the largest subset of S fully connected within G. Major practical obstacles for the plethora of algorithms addressing this type of problem include computational efficiency and, particularly for more complex scores which take edge weights into account, the computational cost of permutation testing, a statistical procedure required to obtain a bound on the p-value for a connectedness score. To address these problems, we developed CTD, “Connect the Dots”, a fast algorithm based on data compression that detects highly connected subsets within S. CTD provides information-theoretic upper bounds on p-values when S contains a small fraction of nodes in G without requiring computationally costly permutation testing. We apply the CTD algorithm to interpret multi-metabolite perturbations due to inborn errors of metabolism and multi-transcript perturbations associated with breast cancer in the context of disease-specific Gaussian Markov Random Field networks learned directly from respective molecular profiling data.

Exposure to and experience of self-harm and self-harm related content: An exploratory network analysis

Exposure to the self-harm behaviour of others plays a role in individuals’ own self-harm thoughts and behaviours, but there has been little consideration of the broader range of mediums through which exposure to self-harm related content may occur. N = 477 participants completed an online study, including questions regarding lifetime history of self-harm thoughts and behaviours and the frequency with which they had been exposed to self-harm via various mediums. Gaussian Markov random field network models were estimated using graphical LASSO and extended Bayesian information criterion. Bootstrapping revealed that exposure mediums with a direct connection to self-harm thoughts and behaviours were the internet (rrp = .34, 95% CI [.26, .42]) and in-passing ‘miscellaneous’ exposure (rrp = .14, 95% CI [.00, .23]). However, stability of the network centrality was low (expected influence stability = 0.52). The node with the greatest increase in expected influence within the network was miscellaneous “in-passing” exposure. In-passing exposure is an understudied exposure medium. Our results may suggest new types of exposure mediums for future research. Data were cross-sectional, so temporal relationships between exposure and behaviour could not be determined. Low stability of the networks suggests that future similar studies would benefit from larger sample sizes.

Discrete convolutional CRF networks for depth estimation from monocular infrared images

Predicting the depth of a scene from monocular infrared images, which plays a crucial role in understanding three-dimensional structures, is one of the challenging tasks in machine learning and computer vision. Considering the lack of texture and color information in infrared images, a novel discrete convolutional conditional random field network is proposed for depth estimation. The proposed method inherits several merits of conditional random fields and deep learning. First, the pairwise features are automatically extracted and optimized through deep architectures. Second, the monocular-images-based depth regression is converted into a multi-class classification, in which the order information of different levels of depths is considered in the loss function. Our experiments demonstrate that this conversion achieves much higher accuracy and faster conversion. Third, to obtain fine-grained level details, we have further proposed a multi-scale discrete convolutional conditional random field network that computes the pairwise features of the discrete conditional random field at different spatial levels. Extensive experiments on the infrared image dataset NUSTMS demonstrate that the proposed method outperforms other depth estimation methods. Specifically, for the proposed method, the mean relative error is 0.181, the mean log10 error is 0.072, and the accuracy with a threshold (t = 1.253) is 95.3%.

Automatic extraction of named entities of cyber threats using a deep Bi-LSTM-CRF network

Countless cyber threat intelligence (CTI) reports are used by companies around the world on a daily basis for security reasons. To secure critical cybersecurity information, analysts and individuals should accordingly analyze information on threats and vulnerabilities. However, analyzing such overwhelming volumes of reports requires considerable time and effort. In this study, we propose a novel approach that automatically extracts core information from CTI reports using a named entity recognition (NER) system. During the process of constructing our proposed NER system, we defined meaningful keywords in the security domain as entities, including malware, domain/URL, IP address, Hash, and Common Vulnerabilities and Exposures. Furthermore, we linked these keywords with the words extracted from the text data of the report. To achieve a higher performance, we utilized the character-level feature vector as an input to bidirectional long-short-term memory using a conditional random field network. We finally achieved an average F1-score of 75.05%. We release 498,000 tag datasets created during our research.

Saliency detection using a deep conditional random field network

Saliency detection has made remarkable progress along with the development of deep learning. While how to integrate the low-level intrinsic context with high-level semantic information to keep the object boundary sharp and restrain the background noise is still a challenging problem. Many attempts on network structures and refinement strategies have been explored, such as using Conditional Random Field (CRF) to improve the accuracy of saliency map, but it is independent from the deep network and cannot be trained end-to-end. To tackle this issue, we propose a novel Deep Conditional Random Field network (DCRF) to take both deep feature and neighbor information into consideration. First, Multi-scale Feature Extraction Module (MFEM) is adopted to capture the low level texture and high level semantic features, multi-stacks of deconvolution layers are employed to improve the spatial resolution of deep layers. Then we employ Backward Optimization Module (BOM) to guide shallower layers by high-level location and shape information derived from deeper layers, which intrinsically enhance the representational capacity of low-level features. Finally, a Deep Conditional Random Field Module (DCRFM) with unary and pairwise potentials is designed to concentrate on spatial neighbor relations to obtain a compact and uniformed saliency map. Extensive experimental results on 5 datasets in terms of 6 evaluation metrics demonstrate that the proposed method achieves state-of-the-art performance.

End-to-End Learning Deep CRF Models for Multi-Object Tracking Deep CRF Models

By bundling multiple complex sub-problems into a unified framework, end-to-end deep learning frameworks reduce the need for hand engineering or tuning of parameters for each component, and optimize different modules jointly to ensure the generalization of the whole deep architecture. Despite tremendous success in numerous computer vision tasks, end-to-end learnings for multi-object tracking (MOT), especially for the assignment problem in data association, have been surprisingly less investigated mainly due to the lack of available training data. Furthermore, it is challenging to discriminate target objects under mutual occlusions or to reduce identity switches in crowded scenes. To tackle these challenges, this paper proposes learning deep conditional random field (CRF) networks, aiming to model the assignment costs as unary potentials and the long-term dependencies among detection results as pairwise potentials. Specifically, we use a bidirectional long short-term memory (LSTM) network to encode the long-term dependencies. We pose the CRF inference as a recurrent neural network learning process using the standard gradient descent algorithm, where unary and pairwise potentials are jointly optimized in an end-to-end manner. Extensive experiments are conducted on the challenging MOT datasets including MOT15, MOT16 and MOT17, and the results show that the proposed algorithm performs favorably against the state-of-the-art methods.

Quantifying the Reliability and Replicability of Psychopathology Network Characteristics

Pairwise Markov random field networks—including Gaussian graphical models (GGMs) and Ising models—have become the “state-of-the-art” method for psychopathology network analyses. Recent research has focused on the reliability and replicability of these networks. In the present study, we compared the existing suite of methods for maximizing and quantifying the stability and consistency of PMRF networks (i.e., lasso regularization, plus the bootnet and NetworkComparisonTest packages in R) with a set of metrics for directly comparing the detailed network characteristics interpreted in the literature (e.g., the presence, absence, sign, and strength of each individual edge). We compared GGMs of depression and anxiety symptoms in two waves of data from an observational study (n = 403) and reanalyzed four posttraumatic stress disorder GGMs from a recent study of network replicability. Taken on face value, the existing suite of methods indicated that overall the network edges were stable, interpretable, and consistent between networks, but the direct metrics of replication indicated that this was not the case (e.g., 39–49% of the edges in each network were unreplicated across the pairwise comparisons). We discuss reasons for these apparently contradictory results (e.g., relying on global summary statistics versus examining the detailed characteristics interpreted in the literature) and conclude that the limited reliability of the detailed characteristics of networks observed here is likely to be common in practice, but overlooked by current methods. Poor replicability underpins our concern surrounding the use of these methods, given that generalizable conclusions are fundamental to the utility of their results.

Annotating and detecting phenotypic information for chronic obstructive pulmonary disease

ObjectivesChronic obstructive pulmonary disease (COPD) phenotypes cover a range of lung abnormalities. To allow text mining methods to identify pertinent and potentially complex information about these phenotypes from textual data, we have developed a novel annotated corpus, which we use to train a neural network-based named entity recognizer to detect fine-grained COPD phenotypic information.Materials and methodsSince COPD phenotype descriptions often mention other concepts within them (proteins, treatments, etc.), our corpus annotations include both outermost phenotype descriptions and concepts nested within them. Our neural layered bidirectional long short-term memory conditional random field (BiLSTM-CRF) network firstly recognizes nested mentions, which are fed into subsequent BiLSTM-CRF layers, to help to recognize enclosing phenotype mentions.ResultsOur corpus of 30 full papers (available at: http://www.nactem.ac.uk/COPD) is annotated by experts with 27 030 phenotype-related concept mentions, most of which are automatically linked to UMLS Metathesaurus concepts. When trained using the corpus, our BiLSTM-CRF network outperforms other popular approaches in recognizing detailed phenotypic information.DiscussionInformation extracted by our method can facilitate efficient location and exploration of detailed information about phenotypes, for example, those specifically concerning reactions to treatments.ConclusionThe importance of our corpus for developing methods to extract fine-grained information about COPD phenotypes is demonstrated through its successful use to train a layered BiLSTM-CRF network to extract phenotypic information at various levels of granularity. The minimal human intervention needed for training should permit ready adaption to extracting phenotypic information about other diseases.

Hierarchical Terrain Classification Based on Multilayer Bayesian Network and Conditional Random Field

This paper presents a hierarchical classification approach for Synthetic Aperture Radar (SAR) images. The Conditional Random Field (CRF) and Bayesian Network (BN) are employed to incorporate prior knowledge into this approach for facilitating SAR image classification. (1) A multilayer region pyramid is constructed based on multiscale oversegmentation, and then, CRF is used to model the spatial relationships among those extracted regions within each layer of the region pyramid; the boundary prior knowledge is exploited and integrated into the CRF model as a strengthened constraint to improve classification performance near the boundaries. (2) Multilayer BN is applied to establish the causal connections between adjacent layers of the constructed region pyramid, where the classification probabilities of those sub-regions in the lower layer, conditioned on their parents’ regions in the upper layer, are used as adjacent links. More contextual information is taken into account in this framework, which is a benefit to the performance improvement. Several experiments are conducted on real ESAR and TerraSAR data, and the results show that the proposed method achieves better classification accuracy.