Inter-feature Dependencies Research Articles

Anomaly detection for high-content image-based phenotypic cell profiling.

High-content image-based phenotypic profiling combines automated microscopy and analysis to identify phenotypic alterations in cell morphology and provide insight into the cell's physiological state. Classical representations of the phenotypic profile can not capture the full underlying complexity in cell organization, while recent weakly machine-learning based representation-learning methods are hard to biologically interpret. We used the abundance of control wells to learn the in-distribution of control experiments and use it to formulate a self-supervised reconstruction anomaly-based representation that encodes the intricate morphological inter-feature dependencies while preserving the representation interpretability. The performance of our anomaly-based representations was evaluated for downstream tasks with respect to two classical representations across four public Cell Painting datasets. Anomaly-based representations improved reproducibility, Mechanism of Action classification, and complemented classical representations. Unsupervised explainability of autoencoder-based anomalies identified specific inter-feature dependencies causing anomalies. The general concept of anomaly-based representations can be adapted to other applications in cell biology.

Predicting Vessel Trajectories Using ASTGCN with StemGNN-Derived Correlation Matrix

This study proposes a vessel position prediction method using attention spatiotemporal graph convolutional networks, which addresses the issue of low prediction accuracy due to less consideration of inter-feature dependencies in current vessel trajectory prediction methods. First, the method cleans the vessel trajectory data and uses the Time-ratio trajectory compression algorithm to compress the trajectory data, avoiding data redundancy and providing feature points for vessel trajectories. Second, the Spectral Temporal Graph Neural Network (StemGNN) extracts the correlation matrix that describes the relationship between multiple variables as a priori matrix input to the prediction model. Then the vessel trajectory prediction model is constructed, and the attention mechanism is added to the spatial and temporal dimensions of the trajectory data based on the spatio-temporal graph convolutional network at the same time as the above operations are performed on different time scales. Finally, the features extracted from different time scales are fused through the full connectivity layer to predict the future trajectories. Experimental results show that this method achieves higher accuracy and more stable prediction results in trajectory prediction. The attention-based spatio-temporal graph convolutional networks effectively capture the spatio-temporal correlations of the main features in vessel trajectories, and the spatio-temporal attention mechanism and graph convolution have certain interpretability for the prediction results.

PSGformer: A novel multivariate net load forecasting model for the smart grid

Smart grid intelligently transforms modern power system through the introduction of various advanced techniques, promoting the growth of distributed renewable energy sources and improving the efficiency of load management. The construction of smart grid recognizes the importance of net load forecasting, which represents the difference between the demanded load and the renewable energy generation, and has a significant impact on power system monitoring and control. Recently, some Transformer-based models have shown excellent performances in load forecasting. However, most of them perform weakly in face of net load forecasting due to the lack of emphasis on the specific trend variations and the inter-feature dependencies in cyclical temporal patterns. To address the two issues, we present the PSGformer that consists of multiscale series decomposition, seasonal module and trend module, which can focus on unique properties that affect the accuracy of net load forecasting by processing different components obtained from the series decomposition. The seasonal module seamlessly introduces graph attention network into the Transformer to compensate for the capability of capturing local inter-feature dependencies. The trend module adopts a new segment-wise iterative approach to capture trend patterns. Compared to the six baseline models, PSGformer has higher forecasting accuracy and stability on four load datasets from different countries.

CoInNet: A Convolution-Involution Network With a Novel Statistical Attention for Automatic Polyp Segmentation.

Polyps are very common abnormalities in human gastrointestinal regions. Their early diagnosis may help in reducing the risk of colorectal cancer. Vision-based computer-aided diagnostic systems automatically identify polyp regions to assist surgeons in their removal. Due to their varying shape, color, size, texture, and unclear boundaries, polyp segmentation in images is a challenging problem. Existing deep learning segmentation models mostly rely on convolutional neural networks that have certain limitations in learning the diversity in visual patterns at different spatial locations. Further, they fail to capture inter-feature dependencies. Vision transformer models have also been deployed for polyp segmentation due to their powerful global feature extraction capabilities. But they too are supplemented by convolution layers for learning contextual local information. In the present paper, a polyp segmentation model CoInNet is proposed with a novel feature extraction mechanism that leverages the strengths of convolution and involution operations and learns to highlight polyp regions in images by considering the relationship between different feature maps through a statistical feature attention unit. To further aid the network in learning polyp boundaries, an anomaly boundary approximation module is introduced that uses recursively fed feature fusion to refine segmentation results. It is indeed remarkable that even tiny-sized polyps with only 0.01% of an image area can be precisely segmented by CoInNet. It is crucial for clinical applications, as small polyps can be easily overlooked even in the manual examination due to the voluminous size of wireless capsule endoscopy videos. CoInNet outperforms thirteen state-of-the-art methods on five benchmark polyp segmentation datasets.

Transformer based on channel-spatial attention for accurate classification of scenes in remote sensing image

Recently, the scenes in large high-resolution remote sensing (HRRS) datasets have been classified using convolutional neural network (CNN)-based methods. Such methods are well-suited for spatial feature extraction and can classify images with relatively high accuracy. However, CNNs do not adequately learn the long-distance dependencies between images and features in image processing, despite this being necessary for HRRS image processing as the semantic content of the scenes in these images is closely related to their spatial relationship. CNNs also have limitations in solving problems related to large intra-class differences and high inter-class similarity. To overcome these challenges, in this study we combine the channel-spatial attention (CSA) mechanism with the Vision Transformer method to propose an effective HRRS image scene classification framework using Channel-Spatial Attention Transformers (CSAT). The proposed model extracts the channel and spatial features of HRRS images using CSA and the Multi-head Self-Attention (MSA) mechanism in the transformer module. First, the HRRS image is mapped into a series of multiple planar 2D patch vectors after passing to the CSA. Second, the ordered vector is obtained via the linear transformation of each vector, and the position and learnable embedding vectors are added to the sequence vector to capture the inter-feature dependencies at a distance from the generated image. Next, we use MSA to extract image features and the residual network structure to complete the encoder construction to solve the gradient disappearance problem and avoid overfitting. Finally, a multi-layer perceptron is used to classify the scenes in the HRRS images. The CSAT network is evaluated using three public remote sensing scene image datasets: UC-Merced, AID, and NWPU-RESISC45. The experimental results show that the proposed CSAT network outperforms a selection of state-of-the-art methods in terms of scene classification.

Fully Contextual Network for Hyperspectral Scene Parsing

In this article, we propose fully contextual networks (FullyContNets) for hyperspectral scene parsing. Different from the previous approaches that leveraging the local information, the proposed methods can effectively capture the more generic nonlocal contexts. To this end, we first propose the scale attention module (SAM) that can adaptively aggregate the multiple features through obtaining the interfeature dependencies of multiscale with self-attention mechanism, where the weights are determined by measuring the similarity between features. What is more, two fully contextual modules (FCMs) called pyramid fully contextual module (Pyramid-FCM) and atrous spatial pyramid fully contextual module (ASP-FCM) are separately developed to obtain the contextual information that simultaneously lying across positions, channels, and features when combining the intrafeature information aggregation algorithms with SAM on the foundation of existing multiscale modules, such as pyramid pooling (PP) in PSPNet and atrous spatial pyramid pooling (ASPP) in DeeplabV3. We design four schemes for FCMs to obtain more effective contexts. The corresponding FullyContNet-Pyramid and FullyContNet-ASP are separately constructed based on the Pyramid-FCM or ASP-FCM. There are extensive quantitative and qualitative experiments are conducted, depicting the capability of SAM and FCMs and demonstrating the competitiveness of proposed networks on four public hyperspectral scenes when comparing with the current state-of-the-art approaches.

PBRIT: gene prioritization by correlating functional and phenotypic annotations through integrative data fusion.

MotivationComputational gene prioritization can aid in disease gene identification. Here, we propose pBRIT (prioritization using Bayesian Ridge regression and Information Theoretic model), a novel adaptive and scalable prioritization tool, integrating Pubmed abstracts, Gene Ontology, Sequence similarities, Mammalian and Human Phenotype Ontology, Pathway, Interactions, Disease Ontology, Gene Association database and Human Genome Epidemiology database, into the prediction model. We explore and address effects of sparsity and inter-feature dependencies within annotation sources, and the impact of bias towards specific annotations.ResultspBRIT models feature dependencies and sparsity by an Information-Theoretic (data driven) approach and applies intermediate integration based data fusion. Following the hypothesis that genes underlying similar diseases will share functional and phenotype characteristics, it incorporates Bayesian Ridge regression to learn a linear mapping between functional and phenotype annotations. Genes are prioritized on phenotypic concordance to the training genes. We evaluated pBRIT against nine existing methods, and on over 2000 HPO-gene associations retrieved after construction of pBRIT data sources. We achieve maximum AUC scores ranging from 0.92 to 0.96 against benchmark datasets and of 0.80 against the time-stamped HPO entries, indicating good performance with high sensitivity and specificity. Our model shows stable performance with regard to changes in the underlying annotation data, is fast and scalable for implementation in routine pipelines.Availability and implementation http://biomina.be/apps/pbrit/; https://bitbucket.org/medgenua/pbrit.Supplementary information Supplementary data are available at Bioinformatics online.

Bayesian Networks for Discrete Observation Distributions in Speech Recognition

Traditionally, in speech recognition, the hidden Markov model state emission probability distributions are usually associated to continuous random variables, by using Gaussian mixtures. Thus, complex multimodal inter-feature dependencies are not accurately modeled by Gaussian models, since they are unimodal distributions and mixtures of Gaussians are needed in these complex cases, but this is done in a loose and inefficient way. Graphical models provide a precise and simple mechanism to model the dependencies among two or more variables. This paper proposes the use of discrete random variables as observations and graphical models to extract the internal dependence structure in the feature vectors. Therefore, speech features are quantized to a small number of levels, in order to obtain a tractable model. These quantized speech features provide a mechanism to increase the robustness against noise uncertainty. In addition, discrete random variables allow the learning of joint statistics of the observation densities. A method to estimate a graphical model with a constrained number of dependencies is shown in this paper, being a special kind of Bayesian network. Experimental results show that by using this modeling, better performance can be obtained compared to standard baseline systems.

Velocity and pressure-based partitions of horizontal and vertical trajectories for on-line signature verification

In general, shape of an on-line signature is used as a single discriminating feature. Sometimes shape of signature is used alone for verification purposes and sometimes it is used in combination with some other dynamic features such as velocity, pressure and acceleration. The shape of an on-line signature is basically formed due to the wrist and fingers movements where the wrist movement is represented by the horizontal trajectory and the movement of the fingers is represented by vertical trajectory. As the on-line signature is formed due to the combination of two movements that are essentially independent of each other, it will be more effective to use them as two separate discriminating features. Based on this observation, we propose to use these trajectories in isolation by first decomposing the pressure and velocity profiles into two partitions and then extracting the underlying horizontal and vertical trajectories. So the overall process can be thought as the process which exploits the inter-feature dependencies by decomposing signature trajectories depending upon pressure and velocity information and performs verification on each partition separately. As a result, we are able to extract eight discriminating features and among them the most stable discriminating feature is used in verification process. Further Principal Component Analysis (PCA) has been proposed to make the signatures rotation invariant. Experimental results demonstrate superiority of our approach in on-line signature verification in comparison with other techniques.

Combined use of unsupervised and supervised learning for dynamic security assessment

It is desirable to assess the security and stability of electric power systems after exposure to large disturbances. In this connection, the critical clearing time (CCT) is an attribute which provides significant information about the quality of the postfault system behavior. It may be regarded as a complex mapping of the prefault, fault-on, and postfault system conditions into the time domain. High prediction and generalization capabilities of artificial neural networks provide the basis for synthesis of such a complex mapping carrying input pattern attributes into the single valued space of the CCT. The authors consider the possibility of using unsupervised and supervised learning programs to discover what combination of raw measurements is significant in determining CCT. Correlation analysis and a Euclidean metric are used to specify interfeature dependencies. An example of a four-machine power system is used to illustrate the suggested approach.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>