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

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 and context clues, leading to… More >

Jungpil Shin^1,*, Md. Al Mehedi Hasan², Abu Saleh Musa Miah¹, Kota Suzuki¹, Koki Hirooka¹

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.3, pp. 2605-2625, 2024, DOI:10.32604/cmes.2023.046334

Abstract Sign language recognition is vital for enhancing communication accessibility among the Deaf and hard-of-hearing communities. In Japan, approximately 360,000 individuals with hearing and speech disabilities rely on Japanese Sign Language (JSL) for communication. However, existing JSL recognition systems have faced significant performance limitations due to inherent complexities. In response to these challenges, we present a novel JSL recognition system that employs a strategic fusion approach, combining joint skeleton-based handcrafted features and pixel-based deep learning features. Our system incorporates two distinct streams: the first stream extracts crucial handcrafted features, emphasizing the capture of hand and body movements within JSL gestures. Simultaneously,… More >

Rosepreet Kaur Bhogal^1,*, V. Devendran²

Computer Systems Science and Engineering, Vol.47, No.3, pp. 2759-2772, 2023, DOI:10.32604/csse.2023.034862

Abstract Human activity recognition is a recent area of research for researchers. Activity recognition has many applications in smart homes to observe and track toddlers or oldsters for their safety, monitor indoor and outdoor activities, develop Tele immersion systems, or detect abnormal activity recognition. Three dimensions (3D) skeleton data is robust and somehow view-invariant. Due to this, it is one of the popular choices for human action recognition. This paper proposed using a transversal tree from 3D skeleton data to represent videos in a sequence. Further proposed two neural networks: convolutional neural network recurrent neural network_1 (CNN_RNN_1), used to find the… More >

Gyu-Il Kim¹, Hyun Yoo², Kyungyong Chung^3,*

Computer Systems Science and Engineering, Vol.47, No.2, pp. 2135-2152, 2023, DOI:10.32604/csse.2023.041030

Abstract Artificial intelligence is increasingly being applied in the field of video analysis, particularly in the area of public safety where video surveillance equipment such as closed-circuit television (CCTV) is used and automated analysis of video information is required. However, various issues such as data size limitations and low processing speeds make real-time extraction of video data challenging. Video analysis technology applies object classification, detection, and relationship analysis to continuous 2D frame data, and the various meanings within the video are thus analyzed based on the extracted basic data. Motion recognition is key in this analysis. Motion recognition is a challenging… More >

Qingyue Zhao¹, Qiaoyu Gu², Zhijun Gao^3,*, Shipian Shao¹, Xinyuan Zhang¹

CMES-Computer Modeling in Engineering & Sciences, Vol.137, No.2, pp. 1773-1788, 2023, DOI:10.32604/cmes.2023.027500

Abstract Building indoor dangerous behavior recognition is a specific application in the field of abnormal human recognition. A human dangerous behavior recognition method based on LSTM-GCN with attention mechanism (GLA) model was proposed aiming at the problem that the existing human skeleton-based action recognition methods cannot fully extract the temporal and spatial features. The network connects GCN and LSTM network in series, and inputs the skeleton sequence extracted by GCN that contains spatial information into the LSTM layer for time sequence feature extraction, which fully excavates the temporal and spatial features of the skeleton sequence. Finally, an attention layer is designed… More >

Xudong Jiang¹, Chang Liu^1,2,*, Shaohui Zhang³, Weisheng Zhang^1,2, Zongliang Du^1,2, Xiaoyu Zhang³, Huizhong Zeng³, Xu Guo^1,2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.135, No.2, pp. 809-838, 2023, DOI:10.32604/cmes.2023.023561

Abstract This paper proposes an explicit method for topology optimization of stiffened plate structures. The present work is devoted to simultaneously optimizing stiffeners’ shape, size and layout by seeking the optimal geometry parameters of a series of moving morphable components (MMC). The stiffeners with straight skeletons and the stiffeners with curved skeletons are considered to enhance the modeling and optimization capability of the current approach. All the stiffeners are represented under the Lagrangian-description framework in a fully explicit way, and the adaptive ground structure method, as well as dynamically updated plate/shell elements, is used to obtain optimized designs with more accurate… More > Graphic Abstract

Long Chen^1,*, Shuxun Liang², Nan Yan², Xiangqian Yang², Baotong Li³

CMES-Computer Modeling in Engineering & Sciences, Vol.135, No.1, pp. 687-709, 2023, DOI:10.32604/cmes.2022.021986

Abstract Lattice structures with excellent physical properties have attracted great research interest. In this paper, a novel volume parametric modeling method based on the skeleton model is proposed for the construction of three-dimensional lattice structures. The skeleton model is divided into three types of nodes. And the corresponding algorithms are utilized to construct diverse types of volume parametric nodes. The unit-cell is assembled with distinct nodes according to the geometric features. The final lattice structure is created by the periodic arrangement of unit-cells. Several different types of volume parametric lattice structures are constructed to prove the stability and applicability of the… More > Graphic Abstract

Motasem S. Alsawadi^1,*, El-Sayed M. El-kenawy^2,3, Miguel Rio¹

CMC-Computers, Materials & Continua, Vol.74, No.1, pp. 19-36, 2023, DOI:10.32604/cmc.2023.032499

Abstract The ever-growing available visual data (i.e., uploaded videos and pictures by internet users) has attracted the research community's attention in the computer vision field. Therefore, finding efficient solutions to extract knowledge from these sources is imperative. Recently, the BlazePose system has been released for skeleton extraction from images oriented to mobile devices. With this skeleton graph representation in place, a Spatial-Temporal Graph Convolutional Network can be implemented to predict the action. We hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest, it is possible to… More >

LAURA LAFON-HUGHES^1,2,*

BIOCELL, Vol.46, No.12, pp. 2531-2535, 2022, DOI:10.32604/biocell.2022.022713

Abstract Poly(ADP-ribose) (PAR) is a highly negatively charged polymer. PAR is synthesized by poly(ADP-ribose)polymerases (PARPs) and is involved in the assembly and stabilization of macromolecular complexes. Here, the presence and putative roles of poly(ADP-ribosyl)ation (PARylation) associated to adherens junctions (AJ) and the actin cytoskeleton in epithelial and Schwann cells, is reviewed. The hypothesis generated by analogy, stating that PAR is associated to AJ in other cell types, is postulated. According to this hypothesis, PAR associated to puncta adherentia in chemical synapses would participate in plasticity, learning and memory. In turn, PAR associated to fascia adherens in cardiomyocytes, would affect heart beating.… More >

Jiabao Shi¹, Zhao Qiu^1,*, Tao Chen¹, Jiale Lin¹, Hancheng Huang², Yunlong He³, Yu Yang³

Journal of New Media, Vol.4, No.2, pp. 97-106, 2022, DOI:10.32604/jnm.2022.027176

Abstract Big data is a comprehensive result of the development of the Internet of Things and information systems. Computer vision requires a lot of data as the basis for research. Because skeleton data can adapt well to dynamic environment and complex background, it is used in action recognition tasks. In recent years, skeleton-based action recognition has received more and more attention in the field of computer vision. Therefore, the keypoints of human skeletons are essential for describing the pose estimation of human and predicting the action recognition of the human. This paper proposes a skeleton point extraction method combined with object… More >