Developing an Optimized Model for Human Activity Recognition: A Performance Evaluation
DOI:
https://doi.org/10.112222/ijits.v1.i1.19217Keywords:
Action Recognition, Deep Learning (DL), Machine Learning (ML), Wearable Sensors, Activities of Daily Living (ADL)Abstract
Anticipating and recognizing human activities has significant implications across various domains, including surveillance, human-computer interaction, autonomous navigation, and robotics. The ability to classify and predict human actions precisely is crucial for enhancing system efficiency in these fields. This study proposes an optimized model that employs machine learning techniques to improve multi-label classification for Human Activity Recognition (HAR). By integrating a confusion matrix with an Extra Tree Classifier, the model enhances activity recognition and the prediction of subsequent actions. To facilitate a comparative analysis between deep learning and machine learning approaches, the UCI-HAR dataset, consisting of six interactive attributes, is utilized. The Multiclass-Classification SVM model achieves an accuracy of 0.9778, whereas the Artificial Neural Network (ANN) model, optimized with ADADELTA, attains an accuracy of 0.9984. A comprehensive evaluation of existing recognition methodologies confirms the proposed model's robustness and efficiency
Due to their high accuracy, low response time, and adaptability to real-time sensor inputs, the proposed models hold potential for implementation in wearable health monitoring, elderly fall detection systems, and intelligent home security solutions.
References
M. K. Rahim, “Unified patient information system for Iraqi hospitals,” Int. J. Comput. Appl., vol. 131, no. 4, pp. 11–14, Dec. 2015.
M. K. R. Al-juaifari, A. Abdulmohson, and R. H. A. Al_Sagheer, “Iraqi newborns mortality prediction using naive Bayes classifier,” Int. J. Res. Eng. Innov. (IJREI), vol. 5, no. 2, pp. 123–127, 2020.
M. K. R. AL-JUAIFARI and A. A. ATHARI, “Future human activity prediction using wavelet and LSTM,” J. Duhok Univ., vol. 26, no. 2, pp. 541–550, 2023.
M. K. R. Al-juaifari, A. Abdulmohson, and R. H. A. Al_Sagheer, “Iraqi newborns mortality prediction using naive Bayes classifier,” Int. J. Res. Eng. Innov. (IJREI), vol. 5, no. 2, pp. 123–127, 2020.
Y.-W. Chao, S. Vijayanarasimhan, B. Seybold, D. A. Ross, J. Deng, and R. Sukthankar, “Rethinking the Faster R-CNN architecture for temporal action localization,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Salt Lake City, UT, USA, 2018, pp. 1130–1139, doi: 10.1109/CVPR.2018.00124.
N. Lee et al., “DESIRE: Distant future prediction in dynamic scenes with interacting agents,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, 2017, pp. 2165–2174, doi: 10.1109/CVPR.2017.233.
J. Martinez, M. Black, and J. Romero, “On human motion prediction using recurrent neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Honolulu, HI, USA, 2017, pp. 4674–4683, doi: 10.1109/CVPR.2017.497.
W. N. Ismail, H. A. Alsalamah, M. M. Hassan, and E. Mohamed, “AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design,” Heliyon, vol. 9, no. 2, e13636, 2023.
E. Bulbul, A. Cetin, and I. A. Dogru, “Human activity recognition using smartphones,” in Proc. Int. Symp. Multidiscip. Stud. Innov. Technol. (ISMSIT), Ankara, Turkey, 2018, pp. 1–6, doi: 10.1109/ISMSIT.2018.8567275.
N. Ahmed, J. I. Rafiq, and M. R. Islam, “Enhanced human activity recognition based on smartphone sensor data using hybrid feature selection model,” Sensors, vol. 20, 317, 2020. doi: 10.3390/s20010317.
M. K. R. Al-juaifari and A. Athari, “A novel framework for future human activity prediction using sensor-based data,” Int. J. Intell. Eng. Syst., vol. 16, no. 6, 2023.
S. Balli, E. A. Sağbaş, and M. Peker, “Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm,” Meas. Control, vol. 52, no. 1–2, pp. 37–45, 2019, doi: 10.1177/0020294018813692.
A. Tharwat, H. Mahdi, M. Elhoseny, and A. E. Hassanien, “Recognizing human activity in mobile crowdsensing environment using optimized k-NN algorithm,” Expert Syst. Appl., vol. 107, pp. 32–44, 2018, doi: 10.1016/j.eswa.2018.04.017.
M. Biagi, L. Carnevali, M. Paolieri, F. Patara, and E. Vicario, “A continuous-time model-based approach for activity recognition in pervasive environments,” IEEE Trans. Hum.-Mach. Syst., vol. 49, no. 4, pp. 293–303, Aug. 2019, doi: 10.1109/THMS.2019.2903091.
K. Hu, J. Jin, F. Zheng, et al., “Overview of behavior recognition based on deep learning,” Artif. Intell. Rev., vol. 56, pp. 1833–1865, 2023, doi: 10.1007/s10462-022-10210-8.
R. Mutegeki and D. S. Han, “A CNN-LSTM approach to human activity recognition,” in Proc. Int. Conf. Artif. Intell. Inf. Commun. (ICAIIC), Fukuoka, Japan, 2020, pp. 362–366, doi: 10.1109/ICAIIC48513.2020.9065078.
F. Hernández, L. F. Suárez, J. Villamizar, and M. Altuve, “Human activity recognition on smartphones using a bidirectional LSTM network,” in Proc. Symp. Image, Signal Process. Artif. Vis. (STSIVA), Bucaramanga, Colombia, 2019, pp. 1–5, doi: 10.1109/STSIVA.2019.8730249.
K. Xia, J. Huang, and H. Wang, “LSTM-CNN architecture for human activity recognition,” IEEE Access, vol. 8, pp. 56855–56866, 2020, doi: 10.1109/ACCESS.2020.2982225.
N. Dua, S. N. Singh, and V. B. Semwal, “Multi-input CNN-GRU based human activity recognition using wearable sensors,” Computing, vol. 103, pp. 1461–1478, 2021, doi: 10.1007/s00607-021-00928-8.
H. Guo, X. Changcheng, and S. Chen, “Wearable sensors for human activity recognition based on a self-attention CNN-BiLSTM model,” Sensor Rev., ahead-of-print, 2023.
Z. N. Khan and J. Ahmad, “Attention induced multi-head convolutional neural network for human activity recognition,” Appl. Soft Comput., vol. 110, 107671, 2021, doi: 10.1016/j.asoc.2021.107671.
S. K. Challa, A. Kumar, and V. B. Semwal, “A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data,” Vis. Comput., vol. 38, pp. 4095–4109, 2022, doi: 10.1007/s00371-021-02283-3.
S. Wan, L. Qi, X. Xu, et al., “Deep learning models for real-time human activity recognition with smartphones,” Mob. Netw. Appl., vol. 25, pp. 743–755, 2020, doi: 10.1007/s11036-019-01445-x.
Y. Zhao, R. Yang, G. Chevalier, X. Xu, and Z. Zhang, “Deep residual bidir-LSTM for human activity recognition using wearable sensors,” Math. Probl. Eng., vol. 2018, Art. no. 7316954, 2018.
T.-H. Tan, J.-Y. Wu, S.-H. Liu, and M. Gochoo, “Human activity recognition using an ensemble learning algorithm with smartphone sensor data,” Electronics, vol. 11, no. 3, 322, 2022.
C. Zhang, K. Cao, L. Lu, and T. Deng, “A multi-scale feature extraction fusion model for human activity recognition,” Sci. Rep., vol. 12, no. 1, 20620, 2022.
Y. Zhang, et al., “Smartphone sensors-based human activity recognition using feature selection and deep decision fusion,” IET Cyber-Phys. Syst.: Theory Appl., vol. 8, no. 2, pp. 76–90, 2023.
K. Venkatachalam, Z. Yang, P. Trojovský, N. Bacanin, M. Deveci, and W. Ding, “Bimodal HAR—An efficient approach to human activity analysis and recognition using bimodal hybrid classifiers,” Inf. Sci., vol. 628, pp. 542–557, 2023.
C. Han, L. Zhang, Y. Tang, W. Huang, F. Min, and J. He, “Human activity recognition using wearable sensors by heterogeneous convolutional neural networks,” Expert Syst. Appl., vol. 198, 116764, 2022.
P. Kumar, S. Chauhan, and L. K. Awasthi, “Human activity recognition (HAR) using deep learning: Review, methodologies, progress and future research directions,” Arch. Comput. Methods Eng., vol. 31, no. 1, pp. 179–219, 2024.
T. Mim, T. Rahman, M. Amatullah, S. Afreen, M. A. Yousuf, S. A. Alyami, K. F. Hasan, and M. A. Moni, “GRU-INC: An inception-attention based approach using GRU for human activity recognition,” Expert Syst. Appl., vol. 216, 119419, 2023.
F. Zeng, M. Guo, L. Tan, F. Guo, and X. Liu, “Wearable sensor-based residual multifeature fusion shrinkage networks for human activity recognition,” Sensors, vol. 24, no. 3, 758, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Mohammad Khalaf Rahim Al-juaifari
This work is licensed under a Creative Commons Attribution 4.0 International License.
which allows users to copy, create extracts, abstracts, and new works from the Article, alter and revise the Article, and make commercial use of the Article (including reuse and/or resale of the Article by commercial entities), provided the user gives appropriate credit (with a link to the formal publication through the relevant DOI), provides a link to the license, indicates if changes were made and the licensor is not represented as endorsing the use made of the work.
