Leveraging Ensemble Learning Models for Human Activity Recognition
Abstract
This paper presents a novel method for categorizing human activities by processing sensor data obtained from IoT devices, focusing on improving accuracy. The proposed approach leverages an ensemble learning framework with majority voting, integrating hyperparameter-optimized classifiers to enhance predictive performance.The ensemble approach minimizes individual biases and errors, effectively handling the variability inherent in sensor data. Adequate preprocessing techniques refine data quality before feeding it into the model. A diverse set of base classifiers, such as KNN, Decision Tree, and Random Forests, are considered for classification. Hyperparameter-optimized KNN Grid Search, Gradient-Boosted Decision Trees, and Random Forests with Optimal Trees are ensembled. Extensive experiments were conducted on Human Activity Recognition datasets, WISDM, HAPT, HAR, and KU-HAR.The model performance was rigorously evaluated using classification metrics such as accuracy, precision, recall, and F1-score. Empirical results demonstrate that the proposed ensemble method significantly enhances classification accuracy. Future research will investigate applying deep learning techniques to capture complex feature interactions within sensor data better.
Keywords
References
S. Wan, L. Qi, X. Xu, C. Tong, and Z. Gu, "Deep learning models for real-time human activity recognition with smartphones," Mobile Networks and Applications, vol. 25, no. 2, pp. 743–755, 2020, doi: 10.1007/s11036-019-01445-x.
N. Gupta, S. K. Gupta, and R. K. Pathak, "Human activity recognition in artificial intelligence framework: A narrative review," Artificial Intelligence Review, vol. 55, pp. 4755–4808, 2022, doi: 10.1007/s10462-021-10116-x.
N. Zurbuchen, A. Wilde, and P. Bruegger, "A machine learning multi-class approach for fall detection systems based on wearable sensors with a study on sampling rates selection," Sensors, vol. 21, p. 938, 2021, doi: 10.3390/s21030938.
U. Sarmah, P. Borah, and D. K. Bhattacharyya, "Ensemble learning methods: An empirical study," SN Computer Science, vol. 5, p. 924, 2024, doi: 10.1007/s42979-024-03252-y.
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, p. 322, 2022, doi: 10.3390/electronics11030322.
D. Sharma, A. Roy, S. P. Bag, P. K. Singh, and Y. Badr, "A hybrid deep learning-based approach for human activity recognition using wearable sensors," in Studies in Big Data, vol. 134, pp. 231–259, Springer, 2023, doi: 10.1007/978-3-031-40688-1_11.
D. Thakur and S. Biswas, "Guided regularized random forest feature selection for smartphone-based human activity recognition," Journal of Ambient Intelligence and Humanized Computing, vol. 14, pp. 9767–9779, 2023, doi: 10.1007/s12652-022-03862-5.
S. Mohsen and A. Elkaseer, "Human activity recognition using k-nearest neighbor machine learning algorithm," in Proceedings of the International Conference on Advances in Intelligent Systems and Computing, Springer, pp. 309–320, 2021, doi: 10.1007/978-981-16-6128-0_29.
K. Maswadi, N. A. Ghani, S. Hamid, and M. B. Rasheed, "Human activity classification using Decision Tree and Naïve Bayes classifiers," Multimedia Tools and Applications, vol. 80, no. 14, pp. 21709–21726, 2021.
Y. Li and L. Wang, "Human activity recognition based on residual network and BiLSTM," Sensors (Basel), vol. 22, no. 2, p. 635, 2022.
A. Nadeem, A. Jalal, and K. Kim, "Human actions tracking and recognition based on body parts detection via artificial neural network," in Proc. 2020 3rd Int. Conf. Advancements in Computational Sciences (ICACS), 2020.
Z. Sun, "An improved random forest based on the classification accuracy and correlation measurement of decision trees," Expert Systems with Applications, vol. 237, p. 121549, 2023, doi: 10.1016/j.eswa.2023.121549.
R. K. Priyadarshini, "Gradient boosted decision tree-based classification for recognizing human behavior," in Proc. IEEE Int. Conf. Advances in Communication, Computing and Electronics (ICACCE), 2019, doi: 10.1109/ICACCE46606.2019.9080014.
P. Ramya and R. Rajeswari, "Human action recognition using distance transform and entropy-based features," Multimedia Tools and Applications, vol. 80, no. 6, pp. 8147–8173, 2021.
A. Sánchez-Caballero et al., "3DFCNN: real-time action recognition using 3D deep neural networks with raw depth information," Multimedia Tools and Applications, vol. 81, no. 17, pp. 24119–24143, 2022.
Ilemobayo et al., "Hyperparameter tuning in machine learning: A comprehensive review," Journal of Engineering Research and Reports, vol. 26, no. 6, pp. 388–395, 2024, doi: 10.9734/jerr/2024/v26i61188.
M. E. Ghazi et al., "Optimizing Deep LSTM model through hyperparameter tuning for sensor-based human activity recognition in smart home," Informatica, vol. 47, pp. 109–122, 2023, doi: 10.31449/inf.v47i10.5268.
E. S. Rahayu, E. M. Yuniarno, I. K. E. Purnama, and M. H. Purnomo, "Human activity classification using deep learning based on 3D motion feature," Machine Learning with Applications, vol. 12, p. 100461, 2023.
S. Park, Y. Kim, and S. Lee, "Deep learning approaches for human activity recognition on mobile health data," IEEE Access, vol. 9, pp. 107836–107847, 2021, doi: 10.1109/ACCESS.2021.3100238.
S. Khater, M. Hadhoud, and M. B. Fayek, "A novel human activity recognition architecture: using residual inception ConvLSTM layer," Journal of Engineering and Applied Science, vol. 69, no. 1, 2022, doi: 10.1186/s44147-022-00098-0.
N. Zehra, S. H. Azeem, and M. Farhan, "Human activity recognition through ensemble learning of multiple convolutional neural networks," in Proc. 55th Annu. Conf. Information Science and Systems (CISS), Baltimore, MD, USA, pp. 1–5, 2021.
D. Kim, S. Kim, and C. Kim, "Convolutional neural networks for human activity recognition on 3D Action-Net dataset," Sensors, vol. 22, no. 2, p. 464, 2022, doi: 10.3390/s22020464.
M. S. Rahman, M. M. Hassan, and A. Almogren, "Extreme learning machines for activity recognition using WristSense dataset," IEEE Transactions on Industrial Informatics, vol. 17, pp. 1–1, 2021, doi: 10.1109/TII.2021.3090991.
V. Sheth et al., "A comparative analysis of machine learning algorithms for classification purpose," Procedia Computer Science, vol. 215, pp. 422–431, 2022, doi: 10.1016/j.procs.2022.12.044.
M. Janaki et al., "Human activity recognition using chaotic logistic map guided grey wolf optimization with decision tree," SSRG International Journal of Electrical and Electronics Engineering, vol. 12, no. 1, pp. 142–150, Jan. 2025, doi: 10.14445/23488379/IJEEE-V12I1P113.
H. Saadatfar, S. Khosravi, J. H. Joloudari, A. Mosavi, and S. Shamshirband, "A new K-nearest neighbors classifier for big data based on efficient data pruning," Mathematics, vol. 8, p. 286, 2020, doi: 10.3390/math8020286.
N. Gunasekara and B. Pfahringer, "Gradient boosted trees for evolving data streams," Machine Learning, vol. 113, pp. 3325–3352, 2024, doi: 10.1007/s10994-024-06517-y.
N. Jalal, A. Mehmood, G. S. Choi et al., "A novel improved random forest for text classification using feature ranking and optimal number of trees," Journal of King Saud University – Computer and Information Sciences, vol. 34, pp. 2733–2742, 2022, doi: 10.1016/j.jksuci.2022.03.012.
S. M. Ganie, "An investigation of ensemble learning techniques for obesity risk prediction using lifestyle data," Decision Analytics Journal, vol. 12, 2025, doi: 10.1016/j.dajour.2024.100539.
I. Priyadarshini, "Human activity recognition in cyber-physical systems using optimized machine learning techniques," Cluster Computing, 2022, doi: 10.1007/s10586-022-03662-8.
Refbacks
- There are currently no refbacks.
Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
ISSN 2089-3272
This work is licensed under a Creative Commons Attribution 4.0 International License.