{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:08:02Z","timestamp":1776053282309,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hebei Provincial Department of Human Resources and Social Security","award":["C20230333"],"award-info":[{"award-number":["C20230333"]}]},{"name":"Hebei Provincial Department of Human Resources and Social Security","award":["203777119D"],"award-info":[{"award-number":["203777119D"]}]},{"name":"Hebei Provincial Department of Human Resources and Social Security","award":["ZD2021056"],"award-info":[{"award-number":["ZD2021056"]}]},{"name":"Key research and development project of Science and Technology Research in Hebei Province","award":["C20230333"],"award-info":[{"award-number":["C20230333"]}]},{"name":"Key research and development project of Science and Technology Research in Hebei Province","award":["203777119D"],"award-info":[{"award-number":["203777119D"]}]},{"name":"Key research and development project of Science and Technology Research in Hebei Province","award":["ZD2021056"],"award-info":[{"award-number":["ZD2021056"]}]},{"name":"Hebei Provincial University Science Research Project-Key Project","award":["C20230333"],"award-info":[{"award-number":["C20230333"]}]},{"name":"Hebei Provincial University Science Research Project-Key Project","award":["203777119D"],"award-info":[{"award-number":["203777119D"]}]},{"name":"Hebei Provincial University Science Research Project-Key Project","award":["ZD2021056"],"award-info":[{"award-number":["ZD2021056"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to the increasing severity of aging populations in modern society, the accurate and timely identification of, and responses to, sudden abnormal behaviors of the elderly have become an urgent and important issue. In the current research on computer vision-based abnormal behavior recognition, most algorithms have shown poor generalization and recognition abilities in practical applications, as well as issues with recognizing single actions. To address these problems, an MSCS\u2013DenseNet\u2013LSTM model based on a multi-scale attention mechanism is proposed. This model integrates the MSCS (Multi-Scale Convolutional Structure) module into the initial convolutional layer of the DenseNet model to form a multi-scale convolution structure. It introduces the improved Inception X module into the Dense Block to form an Inception Dense structure, and gradually performs feature fusion through each Dense Block module. The CBAM attention mechanism module is added to the dual-layer LSTM to enhance the model\u2019s generalization ability while ensuring the accurate recognition of abnormal actions. Furthermore, to address the issue of single-action abnormal behavior datasets, the RGB image dataset RIDS (RGB image dataset) and the contour image dataset CIDS (contour image dataset) containing various abnormal behaviors were constructed. The experimental results validate that the proposed MSCS\u2013DenseNet\u2013LSTM model achieved an accuracy, sensitivity, and specificity of 98.80%, 98.75%, and 98.82% on the two datasets, and 98.30%, 98.28%, and 98.38%, respectively.<\/jats:p>","DOI":"10.3390\/s24155064","type":"journal-article","created":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T13:57:28Z","timestamp":1722866248000},"page":"5064","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Research into the Applications of a Multi-Scale Feature Fusion Model in the Recognition of Abnormal Human Behavior"],"prefix":"10.3390","volume":"24","author":[{"given":"Congcong","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Hebei Agricultural University, Baoding 071001, China"},{"name":"Hebei Key Laboratory of Agricultural Big Data, Baoding 071001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Li","sequence":"additional","affiliation":[{"name":"Hebei Key Laboratory of Agricultural Big Data, Baoding 071001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Hebei Key Laboratory of Agricultural Big Data, Baoding 071001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuting","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Hebei Agricultural University, Baoding 071001, China"},{"name":"Hebei Key Laboratory of Agricultural Big Data, Baoding 071001, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,8,5]]},"reference":[{"key":"ref_1","unstructured":"(2024, August 01). Seventh National Population Census Key Data\u2014National Bureau of Statistics (stats.gov.cn), Available online: https:\/\/www.stats.gov.cn\/sj\/pcsj\/rkpc\/d7c\/."},{"key":"ref_2","unstructured":"Peng, X., and Zhou, X. (2024). Addressing Population Development and Aging in China. New Financ., 8\u201313."},{"key":"ref_3","unstructured":"(2024, August 01). National Health Commission of the People\u2019s Republic of China (nhc.gov.cn), Available online: http:\/\/www.nhc.gov.cn\/lljks\/s7786\/202110\/44ab702461394f51ba73458397e87596.shtml."},{"key":"ref_4","unstructured":"(2022, September 12). United Nations Population Division. Available online: https:\/\/www.un.org\/development\/desa\/pd\/content\/World-PopulationProspects-2022."},{"key":"ref_5","first-page":"154","article-title":"Action recognition based on spatiotemporal heterogeneous two-stream cnn","volume":"39","author":"Ding","year":"2022","journal-title":"Comput. Appl. Softw."},{"key":"ref_6","unstructured":"Chen, W., Tang, H., and Wang, T. (2024). Improved GaitSet method for gait recognition via fusion of silhouette enhancement and attention mechanism. J. Electron. Meas. Instrum., 1\u20139. Available online: http:\/\/kns.cnki.net\/kcms\/detail\/11.2488.TN.20240301.0944.008.html."},{"key":"ref_7","first-page":"452","article-title":"A Fall Detection Algorithm Based on Convolutional Neural Network and Multi-Discriminant Feature","volume":"35","author":"Wang","year":"2023","journal-title":"J. Comput. Aided Des. Comput. Graph."},{"key":"ref_8","unstructured":"Liang, R., and Yang, H. (2024). Lightweight fall detection algorithm framework based on RPEpose and XJ-GCN. J. Comput. Appl., 1\u201310. Available online: http:\/\/kns.cnki.net\/kcms\/detail\/51.1307.TP.20240129.0903.004.html."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/5.554205","article-title":"An introduction to multisensor data fusion","volume":"85","author":"Hall","year":"1997","journal-title":"Proc. IEEE"},{"key":"ref_10","first-page":"3835","article-title":"View-invariant Deep Architecture for Human Action Recognition using Two-stream Motion and Shape Temporal Dynamics","volume":"29","author":"Chhavi","year":"2020","journal-title":"IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc."},{"key":"ref_11","first-page":"757","article-title":"An Indoor Fall Detection Algorithm Based on Res2Net-YOLACT and Fused Features","volume":"42","author":"Zhang","year":"2022","journal-title":"Comput. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1109\/TCSVT.2021.3077512","article-title":"Spatiotemporal Multimodal Learning with 3D CNNs for Video Action Recognition","volume":"32","author":"Wu","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_13","first-page":"139","article-title":"Gait recognition algorithm based on multi-feature fusion convolution","volume":"41","author":"Yang","year":"2024","journal-title":"Comput. Appl. Softw."},{"key":"ref_14","first-page":"244","article-title":"Behavior recognition based on sensors in multiple scenarios","volume":"45","author":"An","year":"2024","journal-title":"Comput. Eng. Des."},{"key":"ref_15","unstructured":"Chu, D. (2023). Research on Automatic Detection of Epileptic Seizures Based on Transformer. [Master\u2019s Thesis, Shandong Normal University]."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"43563","DOI":"10.1109\/ACCESS.2018.2861331","article-title":"A Novel Monitoring System for Fall Detection in Older People","volume":"6","author":"Taramasco","year":"2018","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.neucom.2021.06.102","article-title":"Towards effective detection of elderly falls with CNN-LSTM neural networks","volume":"500","author":"Villar","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_18","first-page":"2159","article-title":"Falls in the elderly","volume":"61","author":"Fuller","year":"2000","journal-title":"Am. Fam. Physician"},{"key":"ref_19","first-page":"89","article-title":"Human action recognition algorithm of feature fusion CNN-Bi-LSTM based on split-attention","volume":"36","author":"She","year":"2022","journal-title":"J. Electron. Meas. Instrum."},{"key":"ref_20","unstructured":"Cao, X. (2021). Research on Abnormal Gait Detection of Parkinson\u2019s Patients Based on Vision. [Master\u2019s Thesis, Changchun University of Science and Technology]."},{"key":"ref_21","first-page":"459","article-title":"An algorithm for elderly fall detection based on optimization YOLOv5s","volume":"44","author":"Li","year":"2023","journal-title":"J. Hebei Univ. Sci. Technol."},{"key":"ref_22","first-page":"1580","article-title":"Double Residual Network Recognition Method for Falling Abnormal Behavior","volume":"14","author":"Wang","year":"2020","journal-title":"J. Front. Comput. Sci. Technol."},{"key":"ref_23","unstructured":"Jia, Z., Zhang, H., and Zhang, C. (2024). Action recognition algorithm based on global frequency domain pooling. Appl. Res. Comput., 1\u20137."},{"key":"ref_24","first-page":"3467","article-title":"GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set","volume":"44","author":"Chao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"3495","DOI":"10.1007\/s11760-023-02573-4","article-title":"Two-branch 3D convolution neural network for gait recognition","volume":"17","author":"Huang","year":"2023","journal-title":"Signal Image Video Process."},{"key":"ref_26","first-page":"53","article-title":"Fall Detection Algorithm Based on TSSI and STB-CNN","volume":"40","author":"Huang","year":"2023","journal-title":"J. Guangdong Univ. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","article-title":"Long-term recurrent convolutional networks for visual recognition and description","volume":"39","author":"Donahue","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_28","unstructured":"Wang, L.M., Xiong, Y.J., Wang, Z., and Qiao, Y. (2015). Towards good practices for very deep two-stream convnets. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sukkar, M., Kumar, D., and Sindha, J. (2021, January 6\u20138). Real-time pedestrians detection by YOLOv5. Proceedings of the 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India.","DOI":"10.1109\/ICCCNT51525.2021.9579808"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"115857","DOI":"10.1109\/ACCESS.2020.3004473","article-title":"An SVM-based AdaBoost cascade classifier for sonar image","volume":"8","author":"Xu","year":"2020","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhou, T., Ye, X.Y., Lu, H.L., Zheng, X., Qiu, S., and Liu, Y. (2022). Dense convolutional network and its application in medical image analysis. BioMed Res. Int., 2022.","DOI":"10.1155\/2022\/2384830"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018, January 18\u201323). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1235","DOI":"10.1162\/neco_a_01199","article-title":"A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures","volume":"31","author":"Yong","year":"2019","journal-title":"Neural Comput."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"11085","DOI":"10.1016\/j.ceramint.2021.12.328","article-title":"Ceramic tile surface defect detection based on deep learning","volume":"48","author":"Guang","year":"2022","journal-title":"Ceram. Int."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"17556","DOI":"10.1109\/ACCESS.2019.2962778","article-title":"A two-stream approach to fall detection with mobilevgg","volume":"8","author":"Han","year":"2020","journal-title":"IEEE Access"},{"key":"ref_37","first-page":"96","article-title":"A fall detection method based on two-stream convolutional neural network","volume":"45","author":"Yuan","year":"2017","journal-title":"J. Henan Norm. Univ."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"9671","DOI":"10.3390\/app12199671","article-title":"Research on CNN-BiLSTM Fall Detection Algorithm Based on Improved Attention Mechanism","volume":"12","author":"Li","year":"2022","journal-title":"Appl. Sci."},{"key":"ref_39","first-page":"2621","article-title":"Real-time fall action detection based on two stream convolutional","volume":"42","author":"Jin","year":"2021","journal-title":"Comput. Eng. Des."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/5064\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:30:19Z","timestamp":1760110219000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/15\/5064"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":39,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["s24155064"],"URL":"https:\/\/doi.org\/10.3390\/s24155064","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,5]]}}}