Attention-driven BI-LSTM for Robust Human Activity Recognition and Classification
DOI:
https://doi.org/10.52783/jns.v14.2593Keywords:
Human Activity Recognition (HAR), Attention-Driven BI-LSTM, Machine Learning Models, Deep Learning, Classification Accuracy, Temporal Sequence AnalysisAbstract
Accurate and robust Human Activity Recognition is essential for applications in surveillance, healthcare, and smart environments. However, the unpredictability and complexity of human motions provide significant challenges in obtaining the desired levels of accuracy and robustness. Conventional machine learning models, such as Decision Tree, Gaussian NB, and KNeighbors, have shown limited efficacy, with estimates of accuracy ranging from 78.3% to 89.3%. Cutting-edge techniques like as Random Forest, RBF SVC, and XGB Classifier achieve a maximum accuracy of 93.8%. We present an Attention-Driven BI-LSTM model that uses bi-directional long short-term memory networks improved with a devotion mechanism to prioritize the most important characteristics in order to overcome these constraints. The present model demonstrates exceptional performance, attaining an accuracy of 99.83%, a precision of 99.46%, a recall of 99.75%, and an F1 score of 99.85%, thereby surpassing other approaches by a substantial margin. The obtained findings validate the model's resilience and effectiveness in precisely recognizing and categorizing human actions in different fields and situations.
Downloads
Metrics
References
S. Zhou et al., “A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition,” Neural Networks, vol. 168, pp. 496–507, Nov. 2023, doi: 10.1016/j.neunet.2023.09.031.
H. Fu, J. Gao, and H. Liu, “Human pose estimation and action recognition for fitness movements,” Comput Graph, vol. 116, pp. 418–426, Nov. 2023, doi: 10.1016/j.cag.2023.09.008.
Z. Hu, J. Xiao, L. Li, C. Liu, and G. Ji, “Human-centric multimodal fusion network for robust action recognition,” Expert Syst Appl, vol. 239, p. 122314, Apr. 2024, doi: 10.1016/j.eswa.2023.122314.
A. E. Tasoren and U. Celikcan, “NOVAction23: Addressing the data diversity gap by uniquely generated synthetic sequences for real-world human action recognition,” Comput Graph, vol. 118, pp. 1–10, Feb. 2024, doi: 10.1016/j.cag.2023.10.011.
. H. T. Anh and T.-O. Nguyen, “Enhanced Topology Representation Learning for Skeleton-Based Human Action Recognition,” Procedia Comput Sci, vol. 246, pp. 3093–3102, 2024, doi: 10.1016/j.procs.2024.09.363.
O. Peña-Cáceres, H. Silva-Marchan, M. Albert, and M. Gil, “Recognition of Human Actions through Speech or Voice Using Machine Learning Techniques,” Computers, Materials & Continua, vol. 77, no. 2, pp. 1873–1891, 2023, doi: 10.32604/cmc.2023.043176.
H. Bouzid and L. Ballihi, “SpATr: MoCap 3D human action recognition based on spiral auto-encoder and transformer network,” Computer Vision and Image Understanding, vol. 241, p. 103974, Apr. 2024, doi: 10.1016/j.cviu.2024.103974.
W. Liang and X. Xu, “HgaNets: Fusion of Visual Data and Skeletal Heatmap for Human Gesture Action Recognition,” Computers, Materials & Continua, vol. 79, no. 1, pp. 1089–1103, 2024, doi: 10.32604/cmc.2024.047861.
T. Wang, Z. Liu, L. Wang, M. Li, and X. V. Wang, “Data-efficient multimodal human action recognition for proactive human–robot collaborative assembly: A cross-domain few-shot learning approach,” Robot Comput Integr Manuf, vol. 89, p. 102785, Oct. 2024, doi: 10.1016/j.rcim.2024.102785.
H. Kim, H. Jeon, D. Kim, and J. Kim, “Elevating urban surveillance: A deep CCTV monitoring system for detection of anomalous events via human action recognition,” Sustain Cities Soc, vol. 114, p. 105793, Nov. 2024, doi: 10.1016/j.scs.2024.105793.
Y. Zhang, C. Zhao, Y. Yao, C. Wang, G. Cai, and G. Wang, “Human posture estimation and action recognition on fitness behavior and fitness,” Alexandria Engineering Journal, vol. 107, pp. 434–442, Nov. 2024, doi: 10.1016/j.aej.2024.07.039.
B. Huang, S. Wang, C. Hu, and X. Li, “Semi-supervised human action recognition via dual-stream cross-fusion and class-aware memory bank,” Eng Appl Artif Intell, vol. 136, p. 108937, Oct. 2024, doi: 10.1016/j.engappai.2024.108937.
J.-W. Chang, M.-H. Chen, H.-S. Ma, and H.-L. Liu, “Human movement science-informed multi-task spatio temporal graph convolutional networks for fitness action recognition and evaluation,” Appl Soft Comput, vol. 164, p. 111963, Oct. 2024, doi: 10.1016/j.asoc.2024.111963.
F. Mehmood, X. Guo, E. Chen, M. A. Akbar, A. A. Khan, and S. Ullah, “Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR),” Comput Human Behav, vol. 163, p. 108482, Feb. 2025, doi: 10.1016/j.chb.2024.108482.
Z. Wang, J. Yan, G. Yan, and B. Yu, “Multi-scale control and action recognition based human-robot collaboration framework facing new generation intelligent manufacturing,” Robot Comput Integr Manuf, vol. 91, p. 102847, Feb. 2025, doi: 10.1016/j.rcim.2024.102847.
Z. Wang and J. Yan, “Deep learning based assembly process action recognition and progress prediction facing human-centric intelligent manufacturing,” Comput Ind Eng, vol. 196, p. 110527, Oct. 2024, doi: 10.1016/j.cie.2024.110527.
D. Liu, Y. Huang, Z. Liu, H. Mao, P. Kan, and J. Tan, “A skeleton-based assembly action recognition method with feature fusion for human-robot collaborative assembly,” J Manuf Syst, vol. 76, pp. 553–566, Oct. 2024, doi: 10.1016/j.jmsy.2024.08.019.
W. Lin and X. Li, “GRASNet: A novel graph neural network for improving human action recognition and well-being assessment in smart manufacturing,” Manuf Lett, vol. 41, pp. 1452–1463, Oct. 2024, doi: 10.1016/j.mfglet.2024.09.172.
A. Y. A. B. Ahmad, J. Alzubi, S. James, V. O. Nyangaresi, C. Kutralakani, and A. Krishnan, “Enhancing Human Action Recognition with Adaptive Hybrid Deep Attentive Networks and Archerfish Optimization,” Computers, Materials & Continua, vol. 80, no. 3, pp. 4791–4812, 2024, doi: 10.32604/cmc.2024.052771.
M. H. Ranjbar, A. Abdi, and J. H. Park, “Kinematic matrix: One-shot human action recognition using kinematic data structure,” Eng Appl Artif Intell, vol. 139, p. 109569, Jan. 2025, doi: 10.1016/j.engappai.2024.109569.
S. Kapoor, A. Sharma, and A. Verma, “Diving deep into human action recognition in aerial videos: A survey,” J Vis Commun Image Represent, vol. 104, p. 104298, Oct. 2024, doi: 10.1016/j.jvcir.2024.104298.
S. Wu, G. Lu, Z. Han, and L. Chen, “A robust two-stage framework for human skeleton action recognition with GAIN and masked autoencoder,” Neurocomputing, vol. 623, p. 129433, Mar. 2025, doi: 10.1016/j.neucom.2025.129433.
A. C. Cob-Parro, C. Losada-Gutiérrez, M. Marrón-Romera, A. Gardel-Vicente, and I. Bravo-Muñoz, “A new framework for deep learning video based Human Action Recognition on the edge,” Expert Syst Appl, vol. 238, p. 122220, Mar. 2024, doi: 10.1016/j.eswa.2023.122220.
H. Wu, X. Ma, and Y. Li, “Transformer-based multiview spatiotemporal feature interactive fusion for human action recognition in depth videos,” Signal Process Image Commun, vol. 131, p. 117244, Feb. 2025, doi: 10.1016/j.image.2024.117244.
K. Aouaidjia, C. Zhang, and I. Pitas, “Spatio-temporal invariant descriptors for skeleton-based human action recognition,” Inf Sci (N Y), vol. 700, p. 121832, May 2025, doi: 10.1016/j.ins.2024.121832.
A. Verma, V. Singh, A. P. S. Chouhan, Abhishek, and A. Rawat, “Vision-based action recognition for the human-machine interaction,” in Artificial Intelligence and Multimodal Signal Processing in Human-Machine Interaction, Elsevier, 2025, pp. 363–376. doi: 10.1016/B978-0-443-29150-0.00011-1.
Y. Mitsuzumi, G. Irie, A. Kimura, and A. Nakazawa, “Phase Randomization: A data augmentation for domain adaptation in human action recognition,” Pattern Recognit, vol. 146, p. 110051, Feb. 2024, doi: 10.1016/j.patcog.2023.110051.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
