Convolutional Network Approach Research Articles

Multi-Directional Long-Term Recurrent Convolutional Network for Road Situation Recognition

Understanding road conditions is essential for implementing effective road safety measures and driving solutions. Road situations encompass the day-to-day conditions of roads, including the presence of vehicles and pedestrians. Surveillance cameras strategically placed along streets have been instrumental in monitoring road situations and providing valuable information on pedestrians, moving vehicles, and objects within road environments. However, these video data and information are stored in large volumes, making analysis tedious and time-consuming. Deep learning models are increasingly utilized to monitor vehicles and identify and evaluate road and driving comfort situations. However, the current neural network model requires the recognition of situations using time-series video data. In this paper, we introduced a multi-directional detection model for road situations to uphold high accuracy. Deep learning methods often integrate long short-term memory (LSTM) into long-term recurrent network architectures. This approach effectively combines recurrent neural networks to capture temporal dependencies and convolutional neural networks (CNNs) to extract features from extensive video data. In our proposed method, we form a multi-directional long-term recurrent convolutional network approach with two groups equipped with CNN and two layers of LSTM. Additionally, we compare road situation recognition using convolutional neural networks, long short-term networks, and long-term recurrent convolutional networks. The paper presents a method for detecting and recognizing multi-directional road contexts using a modified LRCN. After balancing the dataset through data augmentation, the number of video files increased, resulting in our model achieving 91% accuracy, a significant improvement from the original dataset.

Spatial–Temporal Analysis-Based Video Quality Assessment: A Two-Stream Convolutional Network Approach

In system processing, video inevitably suffers from distortion, which leads to quality degradation and affects the user experience. Therefore, it is of great importance to design an accurate and effective objective video quality assessment (VQA) method. In this paper, by considering the multi-dimensional characteristics for video and visual perceptual mechanism, a two-stream convolutional network for VQA is proposed based on spatial–temporal analysis, named TSCNN-VQA. Specifically, for feature extraction, TSCNN-VQA first extracts spatial and temporal features by two different convolutional neural network branches, respectively. After that, the spatial–temporal joint feature fusion is constructed to obtain the joint spatial–temporal features. Meanwhile, the TSCNN-VQA also integrates an attention module to guarantee that the process conforms to the mechanism that the visual system perceives video information. Finally, the overall quality is obtained by non-linear regression. The experimental results in both the LIVE and CSIQ VQA datasets show that the performance indicators obtained by TSCNN-VQA are higher than those of existing VQA methods, which demonstrates that TSCNN-VQA can accurately evaluate video quality and has better consistency with the human visual system.

Deep temporal convolutional networks for F10.7 radiation flux short-term forecasting

Abstract. F10.7, the solar flux at a wavelength of 10.7 cm (F10.7), is often used as an important parameter input in various space weather models and is also a key parameter for measuring the strength of solar activity levels. Therefore, it is valuable to study and forecast F10.7. In this paper, the temporal convolutional network (TCN) approach in deep learning is used to predict the daily value of F10.7. The F10.7 series from 1957 to 2019 are used. The data during 1957–1995 are adopted as the training dataset, the data during 1996–2008 (solar cycle 23) are adopted as the validation dataset, and the data during 2009–2019 (solar cycle 24) are adopted as the test dataset. The leave-one-out method is used to group the dataset for multiple validations. The prediction results for 1–3 d ahead during solar cycle 24 have a high correlation coefficient (R) of 0.98 and a root mean square error (RMSE) of only 5.04–5.18 sfu. The overall accuracy of the TCN forecasts is better than the autoregressive (AR) model (it only takes past values of the F10.7 index as inputs) and the results of the US Space Weather Prediction Center (SWPC) forecasts, especially for 2 and 3 d ahead. In addition, the TCN model is slightly better than other neural network models like the backpropagation (BP) neural network and long short-term memory (LSTM) network in terms of the solar radiation flux F10.7 forecast. The TCN model predicted F10.7 with a lower root mean square error, a higher correlation coefficient, and a better overall model prediction.

Sign Language Word Detection Using LRCN

Sign language is the most effective communication for deaf or hard-of-hearing people. Specialized training is required to understand sign language, and as such, people without disabilities around them cannot communicate effectively. The main objective of this study is to develop a mechanism for streamlining the deep learning model for sign language recognition by utilizing the 30 most prevalent words in our everyday lives. The dataset was designed through 30 ASL (American Sign Language) words consisting of custom-processed video sequences, which consist of 5 subjects and 50 sample videos for each class. The CNN model can be applied to video frames to extract spatial properties. Using CNN’s acquired data, the LSTM model may then predict the action being performed in the video. We present and evaluate the results of two separate datasets—the Pose dataset and the Raw video dataset. The dataset was trained with the Long-term Recurrent Convolutional Network (LRCN) approach. Finally, a test accuracy of 92.66% was reached for the raw dataset, while 93.66% for the pose dataset.

IGCNSDA: unraveling disease-associated snoRNAs with an interpretable graph convolutional network.

Accurately delineating the connection between short nucleolar RNA (snoRNA) and disease is crucial for advancing disease detection and treatment. While traditional biological experimental methods are effective, they are labor-intensive, costly and lack scalability. With the ongoing progress in computer technology, an increasing number of deep learning techniques are being employed to predict snoRNA-disease associations. Nevertheless, the majority of these methods are black-box models, lacking interpretability and the capability to elucidate the snoRNA-disease association mechanism. In this study, we introduce IGCNSDA, an innovative and interpretable graph convolutional network (GCN) approach tailored for the efficient inference of snoRNA-disease associations. IGCNSDA leverages the GCN framework to extract node feature representations of snoRNAs and diseases from the bipartite snoRNA-disease graph. SnoRNAs with high similarity are more likely to be linked to analogous diseases, and vice versa. To facilitate this process, we introduce a subgraph generation algorithm that effectively groups similar snoRNAs and their associated diseases into cohesive subgraphs. Subsequently, we aggregate information from neighboring nodes within these subgraphs, iteratively updating the embeddings of snoRNAs and diseases. The experimental results demonstrate that IGCNSDA outperforms the most recent, highly relevant methods. Additionally, our interpretability analysis provides compelling evidence that IGCNSDA adeptly captures the underlying similarity between snoRNAs and diseases, thus affording researchers enhanced insights into the snoRNA-disease association mechanism. Furthermore, we present illustrative case studies that demonstrate the utility of IGCNSDA as a valuable tool for efficiently predicting potential snoRNA-disease associations. The dataset and source code for IGCNSDA are openly accessible at: https://github.com/altriavin/IGCNSDA.

Locational Detection of False Data Injection Attacks in Smart Grids: A Graph Convolutional Attention Network Approach

Locational Detection of False Data Injection Attacks in Smart Grids: A Graph Convolutional Attention Network Approach

A novel dynamic spatio-temporal graph convolutional network for wind speed interval prediction

It is crucial to predict the wind speed for the utilization of renewable wind energy and the operation of transmission lines with increased capacity. The intermittency and stochastic fluctuations of wind speed pose a significant challenge for the high-quality wind speed prediction, and a novel wind speed interval prediction (WSIP) model is constructed in this study by employing the residual estimation (RE)-oriented dynamic spatio-temporal graph convolutional network (DSTGCN) approach. Firstly, a dynamic adjacency matrix is designed to obtain time-varying global spatial weight allocations among each wind speed node. Then, the spatio-temporal features are extracted by using gated recurrent units (GRUs) and GCNs to construct the wind speed graph networks. Moreover, the RE-oriented strategy incorporating the pinball loss is designed to provide a guidance the parameter training of the constructed model, thus eliminating the quantile crossings problem. As a result, the deterministic point prediction of the wind speed is expanded to the quantile-based probabilistic interval prediction. Finally, the experimental results are presented to demonstrate the validity and superiority of proposed scheme in both qualitative and quantitative performance.

Increasing the Hong Kong Stock Market Predictability: A Temporal Convolutional Network Approach

Increasing the Hong Kong Stock Market Predictability: A Temporal Convolutional Network Approach

Early prediction of dementia using fMRI data with a graph convolutional network approach

Objective. Alzheimer’s disease is a progressive neurodegenerative dementia that poses a significant global health threat. It is imperative and essential to detect patients in the mild cognitive impairment (MCI) stage or even earlier, enabling effective interventions to prevent further deterioration of dementia. This study focuses on the early prediction of dementia utilizing Magnetic Resonance Imaging (MRI) data, using the proposed Graph Convolutional Networks (GCNs). Approach. Specifically, we developed a functional connectivity (FC) based GCN framework for binary classifications using resting-state fMRI data. We explored different types and processing methods of FC and evaluated the performance on the OASIS-3 dataset. We developed the GCN model for two different purposes: (1) MCI diagnosis: classifying MCI from normal controls (NCs); and (2) dementia risk prediction: classifying NCs from subjects who have the potential for developing MCI but have not been clinically diagnosed as MCI. Main results. The results of the experiments revealed several important findings: First, the proposed GCN outperformed both the baseline GCN and Support Vector Machine (SVM). It achieved the best average accuracy of 80.3% (11.7% higher than the baseline GCN and 23.5% higher than SVM) and the highest accuracy of 91.2%. Secondly, the GCN framework with (absolute) individual FC performed slightly better than that with global FC generally. However, GCN using global graphs with appropriate connectivity can achieve equivalent or superior performance to individual graphs in some cases, which highlights the significance of suitable connectivity for achieving performance. Additionally, the results indicate that the self-network connectivity of specific brain network regions (such as default mode network, visual network, ventral attention network and somatomotor network) may play a more significant role in GCN classification. Significance. Overall, this study offers valuable insights into the application of GCNs in brain analysis and early diagnosis of dementia. This contributes significantly to the understanding of MCI and has substantial potential for clinical applications in early diagnosis and intervention for dementia and other neurodegenerative diseases. Our code for GCN implementation is available at: https://github.com/Shuning-Han/FC-based-GCN.

Identification of eight genomic protective alleles for mitochondrial diabetes by Kinship-graph convolutional network.

Nearly 85% of maternally inherited diabetes and deafness (MIDD) are caused by the m.3243A>G mutation in the mitochondrial DNA. However, the clinical phenotypes of MIDD may also be influenced by the nuclear genome, this study aimed to investigate nuclear genome variants that influence clinical phenotypes associated with m.3243A>G mutation in MIDD based on whole-genome sequencing of the patients belonging to pedigrees. We analyzed a whole-genome sequencing (WGS) dataset from blood samples of 38 MIDD patients with the m.3243A > G mutation belonging to 10 pedigrees, by developing a Kinship-graph convolutional network approach, called Ki-GCN, integrated with the conventional genome-wide association study (GWAS) methods. We identified eight protective alleles in the nuclear genome that have protective effects against the onset of MIDD, related deafness, and also type 2 diabetes. Based on these eight protective alleles, we constructed an effective logistic regression model to predict the early or late onset of MIDD patients. There are protective alleles in the nuclear genome that are associated with the onset-age of MIDD patients and might also provide protective effects on the deafness derived from MIDD patients.

Robust recurrent graph convolutional network approach based sequential prediction of illicit transactions in cryptocurrencies

Money laundering has urged the need for machine learning algorithms for combating illicit services in the blockchain of cryptocurrencies due to its increasing complexity. Recent studies have revealed promising results using supervised learning methods in classifying illicit Bitcoin transactions of Elliptic data, one of the largest labelled data of Bitcoin transaction graphs. Nonetheless, all learning algorithms have failed to capture the dark market shutdown event that occurred in this data using its original features. This paper proposes a novel method named recurrent graph neural network model that extracts the temporal and graph topology of Bitcoin data to perform node classification as licit/illicit transactions. The proposed model performs sequential predictions that rely on recent labelled transactions designated by antecedent neighbouring features. Our main finding is that the proposed model against various models on Elliptic data has achieved state-of-the-art with accuracy and f1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$f_1$$\\end{document}-score of 98.99% and 91.75%, respectively. Moreover, we visualise a snapshot of a Bitcoin transaction graph of Elliptic data to perform a case study using a backward reasoning process. The latter highlights the effectiveness of the proposed model from the explainability perspective. Sequential prediction leverages the dynamicity of the graph network in Elliptic data.

SPACEL: deep learning-based characterization of spatial transcriptome architectures

Spatial transcriptomics (ST) technologies detect mRNA expression in single cells/spots while preserving their two-dimensional (2D) spatial coordinates, allowing researchers to study the spatial distribution of the transcriptome in tissues; however, joint analysis of multiple ST slices and aligning them to construct a three-dimensional (3D) stack of the tissue still remain a challenge. Here, we introduce spatial architecture characterization by deep learning (SPACEL) for ST data analysis. SPACEL comprises three modules: Spoint embeds a multiple-layer perceptron with a probabilistic model to deconvolute cell type composition for each spot in a single ST slice; Splane employs a graph convolutional network approach and an adversarial learning algorithm to identify spatial domains that are transcriptomically and spatially coherent across multiple ST slices; and Scube automatically transforms the spatial coordinate systems of consecutive slices and stacks them together to construct a 3D architecture of the tissue. Comparisons against 19 state-of-the-art methods using both simulated and real ST datasets from various tissues and ST technologies demonstrate that SPACEL outperforms the others for cell type deconvolution, for spatial domain identification, and for 3D alignment, thus showcasing SPACEL as a valuable integrated toolkit for ST data processing and analysis.

A community detection model using node embedding approach and graph convolutional network with clustering technique

The communities in a network have distinct characteristics and interrelationships. Community discovery methods based on node embedding and deep learning have surpassed spectral clustering and statistical inference as the preferred methods for handling high-dimensional network data. Community detection in graph networks using graph neural networks (GNNs) is a rapidly expanding field of study that has attracted much attention recently. Inspired by the graph convolutional network (GCN) approach, promising results in evaluating graph structure data, a different method for discovering communities using node embedding using Node2Vec via graph convolutional networks (CD2NE-GCN) model has been proposed. It has been evaluated against the most recent standard methods of graph attention network (GAT), GCN-based approach for Unsupervised Community Detection (GUCD), and Graph Adversarial Networks (GAN). In this paper, a technique for community detection that combines the ideas of graph neural network design with node embedding via message forwarding has been presented. The experimentation has made use of five benchmark datasets: Karate, Cora, CiteSeer, Facebook, and DBLP. In the first set of trials, the node2vec uses the skip-gram with negative sampling (SGNS) approach via biased random walks of the second order to produce node embeddings and feed them to the graph convolutional network. The weighted average matrix and scaled normalized matrices of low-dimensional vertices have been calculated. In the next set of experiments, the average weighted matrix was sent to the 3-layer GCN with the activation function for generating feature vectors and applied clustering technique for predicting communities. The CD2NE-GCN approach outperforms previous literature by detecting graph network communities with accuracy scores of 98.45%, 99.04%, 96.39%, 98.79%, and 97.67% for Karate, Cora, CiteSeer, Facebook, and DBLP datasets, respectively. Thus, graph convolutional network models with a node embedding approach enhance the accuracy.

Distributed photovoltaic power output prediction based on satellite cloud map video frames

To address the challenge of predicting distributed photovoltaic (PV) power output for improved system integration and stability, this study proposes a novel method. Given the expanding scale of distributed PV systems and their economic constraints, accurate power output prediction becomes pivotal. Conventional prediction methods are hindered by the lack of meteorological stations at most distributed PV stations. In response, we present a dynamic convolutional generative adversarial network (DC-GAN) approach coupled with satellite cloud map video frames. By extracting shading features from satellite cloud images and utilizing DC-GAN, our method forecasts short-term cloud shading effects on future radiation. We further integrate radiation data from centralized PV stations, spatial correlations of distributed PV stations, and cloud shading characteristics. This information is used to construct a predictive model combining Convolutional Neural Networks (CNN) and Long short-term memory (LSTM), enhancing prediction accuracy. Comparative experiments confirm the superiority of our proposed method over traditional approaches, substantiating its effectiveness and practicality. Our method achieves notable accuracy improvements, establishing its value in predicting distributed PV power output. This research’s findings offer a valuable contribution to the field of renewable energy integration. In numerical assessments, our method demonstrates a significant increase in prediction accuracy, outperforming conventional techniques by 3.3%. This underscores the practical relevance and efficiency of our proposed approach in enhancing distributed PV power output prediction.

A causal-temporal graphic convolutional network (CT-GCN) approach for TBM load prediction in tunnel excavation

This research proposes a novel deep learning approach named causal-temporal graphic convolutional network (CT-GCN) which aims to provide accurate predictions on tunnel boring machine’s (TBM) load parameters. The causal associations among the key TBM operational parameters are detected and quantified with causal effects through the Peter and Clark momentary conditional independence plus (PCMCI+) method. The discovered causality can be further integrated with a deep learning model that consists of graph convolutional network (GCN) and long short-term memory (LSTM) layers for accurate prediction of TBM’s torque and thrust. Data collected from a realistic tunnel project in Singapore is utilized to demonstrate the effectiveness of the proposed approach. The load parameters are predicted with their historical values and another 7 key operational parameters. The results indicate that (1) The proposed CT-GCN approach can achieve a low mean absolute error (MAE) and root mean squared error (RMSE) of 40.90kN∙m and 64.53kN∙m for thrust force (y1) and that of 635.76kN and 1168.59kN for cutterhead torque (y2), respectively. (2) The proposed CT-GCN method achieves 12.86 % and 24.38 % average improvements in the coefficient of determination (R2) for y1 and y2, respectively when compared with the long-short term memory (LSTM) method and that of 5.62 % and 8.60 % improvements when compared with the GCN-LSTM method. (3) Compared with correlation-based GCN models, the proposed approach exerts an average improvement of 43.10 %, 41.97 %, and 22.72 % in terms of MAE, RMSE, and R2 for torque and much better performance for thrust estimation. This study contributes to improving the understanding of TBM operation by quantifying the causality among the key operational parameters. It also contributes to developing a novel deep-learning method that estimates TBM’s load parameters with high accuracy.

Graph Convolutional Network Approach for Predicting the Severity of Carpal Tunnel Syndrome

Graph Convolutional Network Approach for Predicting the Severity of Carpal Tunnel Syndrome

Limitations of Pacemaker Spike Detection in Capacitive ECGs via Deep Learning

Abstract Pacemaker spike detection is an important step in monitoring paced patients. Capacitive ECG facilitates unobtrusive monitoring of subjects during daily routines such as driving. Robust algorithms are required to deal with low signal quality and artifacts, e.g. by employing fusion of multiple signal channels. Due to the low signal-to-noise ratio of the measurement, there are limitations to detection accuracy compared to conventional ECG monitors. Especially low voltage stimulations such as bipolar pacemaker spikes are hard to detect. We present a convolutional network approach to improve on recent signal processing algorithms.We show a realistic evaluation of its performance using leave-one-subject-out cross validation (LOOCV), its dependence on the size of the receptive field, and an estimation of an upper performance bound.

Data-driven prediction for curved pipe jacking performance during underwater excavation of ancient shipwreck using an attention-based graph convolutional network approach

Thrust is a crucial parameter to ensure the quality of underwater curved pipe jacking construction. A prediction framework based on hybrid deep learning is proposed to realize real-time prediction of thrust. The method contains graph convolutional neural network (GCN), gated recurrent unit (GRU), and self-attention (SA) mechanism. To enhance the interpretability of the method, Shapley Additive Explanations (SHAP), and causal discovery models are introduced within the framework. Taking the salvage project of the “Yangtze Estuary No. 2″ shipwreck as a case study, the prediction performance of the model is verified. The results show that the proposed model achieves excellent performance in thrust prediction for underwater curved pipe jacking, with an average MAE of 11.07 kN, RMSE of 13.96 kN, and R2 value of 0.934. The SHAP analysis reveals that angle, buried depth, and stratum changes exert significant influences on thrust. Furthermore, the spatial correlation and temporal correlation among features are revealed. Compared to other models, the proposed model exhibits superior prediction accuracy and is capable of handling various time step sizes, thereby providing valuable decision support for curved pipe jacking thrust prediction.

A Distributed Densely Connected Convolutional Network Approach for Enhanced Recognition of Health-Related Topics: A Societal Analysis Case Study

A Distributed Densely Connected Convolutional Network Approach for Enhanced Recognition of Health-Related Topics: A Societal Analysis Case Study

Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach

The cosmic microwave background (CMB) is a significant source of knowledge about the origin and evolution of our universe. However, observations of the CMB are contaminated by foreground emissions, obscuring the CMB signal and reducing its efficacy in constraining cosmological parameters. We employ deep learning as a data-driven approach to CMB cleaning from multi-frequency full-sky maps. In particular, we develop a graph-based Bayesian convolutional neural network based on the U-Net architecture that predicts cleaned CMB with pixel-wise uncertainty estimates. We demonstrate the potential of this technique on realistic simulated data based on the Planck mission. We show that our model ac- accurately recovers the cleaned CMB sky map and resulting angular power spectrum while identifying regions of uncertainty. Finally, we discuss the current challenges and the path forward for deploying our model for CMB recovery on real observations.