Assessment of ML Classifiers in Complex Human  Activity Recognition Using Wearable Sensors Data

Saira Hamid; M. Arshad Awan; Mubashar Saeed

Authors

Saira Hamid Department of Computer Science, Allama Iqbal Open University (AIOU), Islamabad, Pakistan. 46000
M. Arshad Awan Department of Computer Science, Allama Iqbal Open University (AIOU), Islamabad, Pakistan. 46000
Mubashar Saeed Department of Computer Science, Allama Iqbal Open University (AIOU), Islamabad, Pakistan. 46000

Keywords:

Human Activity Recognition, Machine Learning, Classification, Wearable Sensor, Complex Activity.

Abstract

Human Activity Recognition (HAR) is essential for understanding daily behavior patterns, and wearable sensor data serves as a reliable source for monitoring complex activities. This study uniquely evaluates the performance of nine machine learning classifiers in the context of complex human activity recognition, relying solely on wearable sensors. It offers valuable insights into classifier effectiveness for real-world applications. Data from the PAMAP2 dataset, which was collected using three wearable IMUs placed on the hand, chest, and ankle, along with a heart rate sensor, was utilized to identify six daily complex activities. A 70/30 train-test split methodology was implemented to assess classifier performance. The Random Forest (RF) classifier achieved the highest performance, boasting 93% accuracy, precision, recall, and F1-score, followed closely by the K-Nearest Neighbors (KNN) classifier, which recorded 91% across all metrics. In contrast, the Logistic Regression (LR) classifier underperformed, achieving only 55% accuracy, likely due to its limitations in handling non-linear data. These results demonstrate that RF and KNN classifiers are effective for complex human activity recognition, while linear classifiers like LR are less suitable for such tasks. Overall, the Random Forest and KNN classifiers provide reliable performance for complex human activity recognition using wearable sensors, making them excellent choices for practical applications.

References

Y. Wang et al., "Ensemble Classification of Accelerometry Data for Continuous Activity Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 9, pp. 1868-1880, Sep. 2016.

M. Shoaib et al., "A Survey of Deep Learning Techniques for Social Signal Processing," IEEE Access, vol. 7, pp. 118634-118678, 2019.

O. D. Luis et al., "Deep Learning for Human Activity Recognition using Multiple Sensors," IEEE Sensors Journal, vol. 16, no. 12, pp. 5366-5375, Dec. 2016.

A. M. Khan et al., "Towards Wearable Systems for Gait Analysis: A Survey," IEEE Reviews in Biomedical Engineering, vol. 7, pp. 1-13, 2014.

Reiss, A. (2012). PAMAP2 Physical Activity Monitoring. UCI Machine Learning Repository. [Online]. Available: https://doi.org/10.24432/C5NW2H.

Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011). Activity recognition using cell phone accelerometers. ACM SIGKDD Explorations Newsletter, 12(2), 74-82.

Anguita, D., Ghio, A., Oneto, L., Parra, X., & Reyes-Ortiz, J. L. (2013). A public domain dataset for human activity recognition using smartphones. 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).

Bao, L., & Intille, S. S. (2004). Activity recognition from user-annotated acceleration data. Pervasive computing, 3001, 1-17.

Ronao, C. A., & Cho, S. B. (2016). Human activity recognition with smartphone sensors using deep learning neural networks. Expert Systems with Applications, 59, 235-244.

Ordóñez, F. J., & Roggen, D. (2016). Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors, 16(1), 115.

Chen, L., Duan, Y., Zhang, J., & Wang, J. (2020). Transfer learning for human activity recognition: A survey. IEEE Access, 8, 57909-57928.

Hamid, R., Tufail, A., Alam, M. M., & Saba, T. (2018). Deep convolutional neural networks for human activity recognition using mobile sensors. Wireless Personal Communications, 103(2), 889-901.

Banerjee, S., Bhardwaj, A., Misra, A., & Saha, A. (2020). Human activity recognition using wearable sensors and deep learning. Procedia Computer Science, 167, 279-288.

Banos, O., Galvez, J. M., Damas, M., Pomares, H., & Rojas, I. (2014). Window size impact in human activity recognition. Sensors, 14(4), 6474-6499.

A. Bulling, U. Blanke, and G. Schiele, "A Tutorial on Human Activity Recognition Using Body-Worn Inertial Sensors," ACM Computing Surveys (CSUR), vol. 46, no. 2, pp. 1-33, Oct. 2014.

Figo, D., Diniz, P. C., Ferreira, D. R., & Cardoso, J. M. (2010). Preprocessing techniques for context recognition from accelerometer data. Personal and Ubiquitous Computing, 14(7), 645662.

Ellis, K., Godbole, S., Kerr, J., Lanckriet, G., & Wing, D. (2016). Multi-sensor physical activity recognition in free-living. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'16), 506-517.

Khan, A. M., Siddiqi, M. H., & Lee, S. W. (2010). Human activity recognition using hierarchical hidden Markov models with automatic feature selection. Journal of Ambient Intelligence and Humanized Computing, 1(1), 43-52.

Ravi, D., Wong, C., Lo, B., & Yang, G. Z. (2016). Deep learning for human activity recognition: A resource-efficient implementation on low-power devices. Proceedings of the ACM Conference on Embedded Networked Sensor Systems (SenSys'16), 71-84.

illemsen, P., Schermer, T., & Coninx, K. (2013). Recognizing activities with a Kinect sensor. Proceedings of the 15th International Conference on Multimodal Interaction (ICMI'13), 533-540.

Lee, Y. S., & Mase, K. (2002). Activity and location recognition using wearable sensors. IEEE Pervasive Computing, 1(3), 24-32.

He, Y., Li, Y., Duan, L., & Chen, W. (2015). Activity recognition with smartphone sensors. Tsinghua Science and Technology, 20(3), 235-249.

Gjoreski, M., Ciliberto, M., D'Andrea, V., Di Castro, D., Ermes, M., Gjoreski, H., & Lombriser, C. (2016). Activity recognition on smartphones and smartwatches. Pervasive and Mobile Computing, 36, 1-17.

Wu, M., & Hu, Y. (2016). Real-time activity recognition on smartphones using deep learning. Journal of Ambient Intelligence and Humanized Computing, 7(6), 783-798.

Alsheikh, M. A., Selim, A., Niyato, D., Doyle, L., Lin, S., & Tan, H. P. (2016). Deep activity recognition models with triaxial accelerometers. Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI'16), 2670-2676.

Wang, H., Li, Z., & Huang, K. (2014). Human activity recognition based on smartphone sensors using hybrid feature selection. Journal of Sensors, 2014, 1-10.

Liu, H., & Lee, W. S. (2017). Recognizing daily activities from accelerometer data on smartphones. Proceedings of the 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom'17), 240-248.

Cleland, I., Kikhia, B., Nugent, C., Boytsov, A., Hallberg, J., Synnes, K., ... & McClean, S. (2013). Optimal placement of accelerometers for the detection of everyday activities. Sensors, 13(7), 9183-9200.

Ignatov, A. D., & Samuylov, K. E. (2016). Human activity recognition using quaternions and machine learning algorithms. Journal of Sensors, 2016, 1-10.

Bulling, A., Roggen, D., & Tröster, G. (2014). Wearable ECG for human activity recognition: A review. Sensors, 14(4), 6107-6128.

Kaur, K., & Batth, J. S. (2024, June). Human Activity Recognition using Machine Learning. In 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0 (pp. 1-5). IEEE.

Balaha, H. M., & Hassan, A. E. S. (2023). Comprehensive machine and deep learning analysis of sensor-based human activity recognition. Neural Computing and Applications, 35(17), 12793-12831.

Nia, N. G., Kaplanoglu, E., Nasab, A., & Qin, H. (2023, June). Human activity recognition using machine learning algorithms based on IMU data. In 2023 5th International Conference on Bio-engineering for Smart Technologies (BioSMART) (pp. 1-8). IEEE.