Xinlu Zong^*, Fan Yu, Zhen Chen, Xue Xia

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 3517-3537, 2025, DOI:10.32604/cmc.2024.057494 - 17 February 2025

Abstract Accurate traffic flow prediction has a profound impact on modern traffic management. Traffic flow has complex spatial-temporal correlations and periodicity, which poses difficulties for precise prediction. To address this problem, a Multi-head Self-attention and Spatial-Temporal Graph Convolutional Network (MSSTGCN) for multiscale traffic flow prediction is proposed. Firstly, to capture the hidden traffic periodicity of traffic flow, traffic flow is divided into three kinds of periods, including hourly, daily, and weekly data. Secondly, a graph attention residual layer is constructed to learn the global spatial features across regions. Local spatial-temporal dependence is captured by using a More >

Ange Chen, Chengdong Wu^*, Chuanjiang Leng

CMC-Computers, Materials & Continua, Vol.82, No.1, pp. 173-191, 2025, DOI:10.32604/cmc.2024.059284 - 03 January 2025

Abstract Previous multi-view 3D human pose estimation methods neither correlate different human joints in each view nor model learnable correlations between the same joints in different views explicitly, meaning that skeleton structure information is not utilized and multi-view pose information is not completely fused. Moreover, existing graph convolutional operations do not consider the specificity of different joints and different views of pose information when processing skeleton graphs, making the correlation weights between nodes in the graph and their neighborhood nodes shared. Existing Graph Convolutional Networks (GCNs) cannot extract global and deep-level skeleton structure information and view… More >

Ying Wang¹, Weijun Zhang¹, Fei Cai¹, Yong Tao^2,*

Congenital Heart Disease, Vol.19, No.6, pp. 653-669, 2024, DOI:10.32604/chd.2025.060406 - 27 January 2025

Abstract Background: Previous studies combined integrated scRNA-seq with bulk RNA data to screen biomarkers for cardiomyopathy. This study extended this approach to identify biomarkers specific for hypertrophic cardiomyopathy (HCM). Methods: Datasets GSE36961, GSE130036, GSE249925 and GSE203274 were analyzed in this study. ScRNA-seq analysis was employed to identify distinct cell populations. Differentially expression analysis was conducted to screen vascular endothelial cells (VECs)-related feature genes. After calculating VECs score, WGCNA was used to correlate gene modules with the VECs score. Key HCM biomarkers were determined using random forest analysis, and LASSO regression analyses to construct a diagnostic model… More >

ZHEN WANG¹, JUN FU¹, SAISAI ZHU¹, HAODONG TANG², KUI SHI¹, JIHUA YANG³, MENG WANG³, MENGGE WU¹, DUNFENG QI^1,*

Oncology Research, Vol.32, No.12, pp. 1851-1866, 2024, DOI:10.32604/or.2024.055286 - 13 November 2024

Abstract Background: Pancreatic ductal adenocarcinoma (PDAC) has a rich and complex tumor immune microenvironment (TIME). M2 macrophages are among the most extensively infiltrated immune cells in the TIME and are necessary for the growth and migration of cancers. However, the mechanisms and targets mediating M2 macrophage infiltration in pancreatic cancer remain elusive. Methods: The M2 macrophage infiltration score of patients was assessed using the xCell algorithm. Using weighted gene co-expression network analysis (WGCNA), module genes associated with M2 macrophages were identified, and a predictive model was designed. The variations in immunological cell patterns, cancer mutations, and… More > Graphic Abstract

Kaiyue Hong, Yasmina Radani, Teja Manda, Jinhui Chen, Liming Yang^*

Phyton-International Journal of Experimental Botany, Vol.93, No.3, pp. 413-425, 2024, DOI:10.32604/phyton.2024.047739 - 28 March 2024

Abstract This study explores CAMTA genes in the rare and endangered Chinese plant species, Liriodendron chinense. Despite the completion of whole-genome sequencing, the roles of CAMTA genes in calcium regulation and stress responses in this species remain largely unexplored. Within the L. chinense genome, we identified two CAMTA genes, Lchi09764 and Lchi222536, characterized by four functional domains: CG-1, TIG, ANK repeats, and IQ motifs. Our analyses, including phylogenetic investigations, cis-regulatory element analyses, and chromosomal location studies, aim to elucidate the defining features of CAMTA genes in L. chinense. Applying Weighted Gene Co-Expression Network Analysis (WGCNA), we explored the impact of CAMTA genes on More >

Yunhe Wang¹, Yuxin Xia², Shuai Liu^2,*

CMC-Computers, Materials & Continua, Vol.78, No.3, pp. 4489-4507, 2024, DOI:10.32604/cmc.2024.048813 - 26 March 2024

Abstract In recent years, skeleton-based action recognition has made great achievements in Computer Vision. A graph convolutional network (GCN) is effective for action recognition, modelling the human skeleton as a spatio-temporal graph. Most GCNs define the graph topology by physical relations of the human joints. However, this predefined graph ignores the spatial relationship between non-adjacent joint pairs in special actions and the behavior dependence between joint pairs, resulting in a low recognition rate for specific actions with implicit correlation between joint pairs. In addition, existing methods ignore the trend correlation between adjacent frames within an action… More >

Yajing Ma^1,2,3, Gulila Altenbek^1,2,3,*, Yingxia Yu¹

CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 695-712, 2024, DOI:10.32604/cmc.2023.045486 - 30 January 2024

Abstract Due to the structural dependencies among concurrent events in the knowledge graph and the substantial amount of sequential correlation information carried by temporally adjacent events, we propose an Independent Recurrent Temporal Graph Convolution Networks (IndRT-GCNets) framework to efficiently and accurately capture event attribute information. The framework models the knowledge graph sequences to learn the evolutionary representations of entities and relations within each period. Firstly, by utilizing the temporal graph convolution module in the evolutionary representation unit, the framework captures the structural dependency relationships within the knowledge graph in each period. Meanwhile, to achieve better event… More >

HENG LI^1,#, YOUMING LEI^3,#, GAOFENG LI¹, YUNCHAO HUANG^2,*

Oncology Research, Vol.32, No.1, pp. 187-197, 2024, DOI:10.32604/or.2023.030656 - 15 November 2023

Abstract Lung cancer is a prevalent malignancy, and fatalities of the disease exceed 400,000 cases worldwide. Lung squamous cell carcinoma (LUSC) has been recognized as the most common pathological form of lung cancer. The comprehensive understanding of molecular features related to LUSC progression has great significance in LUSC prognosis assessment and clinical management. In this study, we aim to identify a panel of signature genes closely associated with LUSC, which can provide novel insights into the progression of LUSC. Gene expression profiles were retrieved from public resources including gene expression omnibus (GEO) and the cancer genome… More >

Chengfei Hua^1,2,3, Wenzhong Yang^2,3,*, Liejun Wang^2,3, Fuyuan Wei^2,3, KeZiErBieKe HaiLaTi^2,3, Yuanyuan Liao^2,3

CMC-Computers, Materials & Continua, Vol.77, No.1, pp. 893-909, 2023, DOI:10.32604/cmc.2023.040862 - 31 October 2023

Abstract With the development of social media and the prevalence of mobile devices, an increasing number of people tend to use social media platforms to express their opinions and attitudes, leading to many online controversies. These online controversies can severely threaten social stability, making automatic detection of controversies particularly necessary. Most controversy detection methods currently focus on mining features from text semantics and propagation structures. However, these methods have two drawbacks: 1) limited ability to capture structural features and failure to learn deeper structural features, and 2) neglecting the influence of topic information and ineffective utilization… More >

Tao Liu¹, Kejia Zhang^1,*, Jingsong Yin¹, Yan Zhang¹, Zihao Mu¹, Chunsheng Li¹, Yanan Hu²

Computer Systems Science and Engineering, Vol.47, No.2, pp. 2563-2582, 2023, DOI:10.32604/csse.2023.041228 - 28 July 2023

Abstract Spatio-temporal heterogeneous data is the database for decision-making in many fields, and checking its accuracy can provide data support for making decisions. Due to the randomness, complexity, global and local correlation of spatiotemporal heterogeneous data in the temporal and spatial dimensions, traditional detection methods can not guarantee both detection speed and accuracy. Therefore, this article proposes a method for detecting the accuracy of spatiotemporal heterogeneous data by fusing graph convolution and temporal convolution networks. Firstly, the geographic weighting function is introduced and improved to quantify the degree of association between nodes and calculate the weighted… More >