Abstract

The deep learning community has increasingly focused on the critical challenges of human activity segmentation and detection based on sensors, which have numerous real-world applications. In most prior efforts, activity segmentation and recognition have been treated as separate processes, relying on pre-segmented sensor streams. This research proposes an unsupervised deep learning approach for Human Activity Recognition (HAR) that is segment-based, with an emphasis on activity continuity. The approach integrates segment-based SimCLR with Segment Feature Decorrelation (SDFD) and a new framework that leverages pairs of segment data for contrastive learning of visual representations. Furthermore, the Secretary Bird Optimization Algorithm (SBOA) and Channel Attention with Spatial Attention Network (CASANet) are utilized to enhance the performance of sensor-based human activity detection. CASANet effectively extracts key features and spatial dependencies in sensor data, while SBOA optimizes the model for greater accuracy and generalization. Evaluations on two publicly available datasets—Mhealth and PAMAP2—demonstrated an average F1 score of 98%, highlighting the approach’s efficacy in improving activity recognition performance.

Keywords

Secretary Bird Optimisation Algorithm, Channel Attention with Spatial Attention Network, Segmentation, Sensor based Human Activity Recognition, Accelerometer sensors,

Downloads

Download data is not yet available.

References

  1. F. Serpush, M. B. Menhaj, B. Masoumi, B. Karasfi, Wearable sensor-based human activity recognition in the smart healthcare system. Computational Intelligence and Neuroscience, (2022) 1-8. https://doi.org/10.1155/2022/1391906
  2. I. Dirgová Luptáková, M. Kubovčík, J. Pospíchal, Wearable sensor-based human activity recognition with transformer model. Sensors, 22(5), (2022) 1911. https://doi.org/10.3390/s22051911
  3. V. Bijalwan, V. B. Semwal, V. Gupta, Wearable sensor-based pattern mining for human activity recognition: Deep learning approach. Industrial Robot: The International Journal of Robotics Research and Application, 49(1), (2022) 21-33. https://doi.org/10.1108/IR-09-2020-0187
  4. Y.J. Luwe, C.P. Lee, K.M. Lim, Wearable sensor-based human activity recognition with hybrid deep learning model. Informatics, 9(3), (2022) 56. https://doi.org/10.3390/informatics9030056
  5. A. Ferrari, D. Micucci, M. Mobilio, P. Napoletano, Deep learning and model personalization in sensor-based human activity recognition. Journal of Reliable Intelligent Environments, 9(1), (2023) 27-39. https://doi.org/10.1007/s40860-021-00167-w
  6. V. Seedha Devi, K. Sumathi, M. Mahalakshmi, A. Jose Anand, Anita Titus, N. Naga Saranya, Machine Learning Based Efficient Human Activity Recognition System, International Journal of Intelligent Systems and Applications in Engineering, 12(5), (2023) 338–346.
  7. H. Park, N. Kim, G. H. Lee, J. K. Choi, MultiCNN-FilterLSTM: Resource-efficient sensor-based human activity recognition in IoT applications. Future Generation Computer Systems, 139, (2023) 196-209. https://doi.org/10.1016/j.future.2022.09.024
  8. H.M. Balaha, A.E.S. Hassan, Comprehensive machine and deep learning analysis of sensor-based human activity recognition. Neural Computing and Applications, 35(17), (2023) 12793-12831. https://doi.org/10.1007/s00521-023-08374-7
  9. S. Qiu, H. Zhao, N. Jiang, Z. Wang, L. Liu, Y. An, H. Zhao, X. Miao, R. Liu, G. Fortino, Multi-sensor information fusion based on machine learning for real applications in human activity recognition: State-of-the-art and research challenges. Information Fusion, 80, (2022) 241-265. https://doi.org/10.1016/j.inffus.2021.11.006
  10. Z. Zhongkai, S. Kobayashi, K. Kondo, T. Hasegawa, M. Koshino, A comparative study: Toward an effective convolutional neural network architecture for sensor-based human activity recognition. IEEE Access, 10, (2022) 20547-20558. https://doi.org/10.1109/ACCESS.2022.3152530
  11. D. Bhattacharya, D. Sharma, W. Kim, M. F. Ijaz, P. K. Singh, Ensem-HAR: An ensemble deep learning model for smartphone sensor-based human activity recognition for measurement of elderly health monitoring. Biosensors, 12(6), (2022) 393. https://doi.org/10.3390/bios12060393
  12. S. Mekruksavanich, A. Jitpattanakul, Hybrid convolution neural network with channel attention mechanism for sensor-based human activity recognition. Scientific Reports, 13(1), (2023) 12067. https://doi.org/10.1038/s41598-023-39080-y
  13. D. Garcia-Gonzalez, D. Rivero, E. Fernandez-Blanco, M.R. Luaces, New machine learning approaches for real-life human activity recognition using smartphone sensor-based data. Knowledge-Based Systems, 262, (2023) 110260. https://doi.org/10.1016/j.knosys.2023.110260
  14. J. Pan, Z. Hu, S. Yin, M. Li, GRU with dual attentions for sensor-based human activity recognition. Electronics, 11(11), (2022) 1797. https://doi.org/10.3390/electronics11111797
  15. A. Saha, S. Rajak, J. Saha, C. Chowdhury, A survey of machine learning and meta-heuristics approaches for sensor-based human activity recognition systems. Journal of Ambient Intelligence and Humanized Computing, 15, (2022) 29–56. https://doi.org/10.1007/s12652-022-03870-5
  16. B. Vidya, P. Sasikumar, Wearable multi-sensor data fusion approach for human activity recognition using machine learning algorithms. Sensors and Actuators A: Physical, 341, (2022) 113557. https://doi.org/10.1016/j.sna.2022.113557
  17. A. Hussain, S.U. Khan, N. Khan, M. Shabaz, S.W. Baik, AI-driven behavior biometrics framework for robust human activity recognition in surveillance systems. Engineering Applications of Artificial Intelligence, 127, (2024) 107218. https://doi.org/10.1016/j.engappai.2023.107218
  18. N. Hassan, A.S.M. Miah, J. Shin, A deep bidirectional LSTM model enhanced by transfer-learning-based feature extraction for dynamic human activity recognition. Applied Sciences, 14(2), (2024) 603. https://doi.org/10.3390/app14020603
  19. S. Miao, L. Chen, R. Hu, Spatial-temporal masked autoencoder for multi-device wearable human activity recognition. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 7(4), (2024) 1-25. https://doi.org/10.1145/3631415
  20. W. Guo, S. Yamagishi, L. Jing, Human activity recognition via Wi-Fi and inertial sensors with machine learning. IEEE Access, 12, (2024) 18821-18836. https://doi.org/10.1109/ACCESS.2024.3360490
  21. H. Park, G. H. Lee, J. Han, J.K. Choi, Multiclass autoencoder-based active learning for sensor-based human activity recognition. Future Generation Computer Systems, 151, (2024) 71-84. https://doi.org/10.1016/j.future.2023.09.029
  22. S. Wang, L. Wang, W. Liu, Feature decoupling and regeneration towards Wi-Fi-based human activity recognition. Pattern Recognition, 153, (2024) 110480. https://doi.org/10.1016/j.patcog.2024.110480
  23. O. Banos, R. Garcia, J. A. Holgado-Terriza, M. Damas, H. Pomares, I. Rojas, et al., mHealthDroid: A novel framework for agile development of mobile health applications. In International Workshop on Ambient Assisted Living, Springer, Switzerland, (2014) 91-98. https://doi.org/10.1007/978-3-319-13105-4_14
  24. A. Tehrani, M. Yadollahzadeh-Tabari, A. Zehtab-Salmasi, R. Enayatifar, Wearable sensor-based human activity recognition system employing bi-LSTM algorithm. The Computer Journal, 67(3), (2024) 961-975. https://doi.org/10.1093/comjnl/bxad035
  25. A. Reiss, D. Stricker, (2012) Introducing a new benchmarked dataset for activity monitoring. In 16th International Symposium on Wearable Computers, IEEE, UK. https://doi.org/10.1109/ISWC.2012.13
  26. Z. Wu, Y. Xiong, S. X. Yu, D. Lin, (2018) Unsupervised feature learning via non-parametric instance discrimination. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, USA. https://doi.org/10.1109/CVPR.2018.00393
  27. Y. Tao, K. Takagi, K. Nakata, (2021) Clustering-friendly representation learning via instance discrimination and feature decorrelation. arXiv preprint arXiv.
  28. V. Revathi, B. P. Kavin, A. Thirumalraj, E. Gangadevi, B. Balusamy, S. Gite, Image-based feature separation using RBM tech with ADBN tech for accurate fruit classification. In 2024 IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), IEEE, India. https://doi.org/10.1109/IC2PCT60090.2024.10486564
  29. S. Woo, J. Park, J. Y. Lee, I. S. Kweon, CBAM: Convolutional block attention module. In European Conference on Computer Vision (ECCV), Munich, Germany, (2018) 3-19. https://doi.org/10.1007/978-3-030-01234-2_1
  30. Y. Fu, D. Liu, J. Chen, L. He, Secretary bird optimization algorithm: A new metaheuristic for solving global optimization problems. Artificial Intelligence Review, 57(5), (2024) 1-102. https://doi.org/10.1007/s10462-024-10729-y