A Comparison Analysis of Conventional Classifiers and Deep Learning Model for Activity Recognition in Smart Homes based on Multi-label Classification
Subject Areas : Machine learning
John Kasubi
1
(The Local Government Training Institute, Dodoma, Tanzania)
Manjaiah D. Huchaiah
2
(Mangalore University)
Ibrahim Gad
3
(Tanta Univeristy)
Mohammad Kazim Hooshmand
4
(Mangalore University)
Keywords: Conventional Classifiers, Deep Learning Model, Activity Recognition, Smart Homes, Multi-label classification,
Abstract :
Activity Recognition is essential for exploring the various activities that humans engage in within Smart Homes in the presence of multiple sensors as residents interact with household appliances. Smart homes use intelligent IoT devices linked to residents' homes to track changes in human behavior as the humans interact with the home's equipment, which may improve healthcare and security issues for the residents. This study presents a research work that compares conventional classifiers such as DT, LDA, Adaboost, GB, XGBoost, MPL, KNN, and DL, focusing on recognizing human activities in Smart Homes using Activity Recognizing Ambient Sensing (ARAS). The experimental results demonstrated that DL Model outperformed with excellent accuracy compared to conventional classifiers in recognizing human activities in Smart Homes. This work proves that DL Models perform best in analyzing ARAS datasets compared to traditional machine learning algorithms.
[1] De-La-Hoz-Franco, E, et al. "Sensor-based datasets for human activity recognition–a systematic review of the literature." IEEE Access 6 (2018): 59192-59210.
[2] Fang, Z., Wang, Y., Peng, L., & Hong, H. Integration of convolutional neural network and conventional machine learning classifiers for landslide susceptibility mapping. Computers & Geosciences, (2020):139, 104470.
[3] Jyotiyana, M, Nishtha, K, and Munish, K. "A Deep Learning Approach for Classification and Diagnosis of Parkinson's Disease." (2021).
[4] Mohammadi, Mehdi, et al. "Deep learning for IoT big data and streaming analytics: A survey." IEEE Communications Surveys & Tutorials 20.4 (2018): 2923-2960.
[5] Hassan, Mohammed Mehedi, et al. "A robust human activity recognition system using smartphone sensors and deep learning." Future Generation Computer Systems 81 (2018): 307-313.
[6] Natani, A, Abhishek, S, Thinagaran, P, and Suman, S. "Deep learning for multi-resident activity recognition in ambient sensing smart homes." In 2019 IEEE 8th Global conference on consumer electronics (GCCE), pp. 340-341. IEEE, 2019.
[7] Bhattacharjee, S, Swapnil, K, and Aleena, S. "A comparative study of supervised learning techniques for human activity monitoring using smart sensors." 2018 Second International Conference on Advances in Electronics, Computers, and Communications (ICAECC). IEEE, 2018.
[8] Jindong, W, Yiqiang, C, Shuji, H, Xiaohui, P, and Lisha, H. Deep learning for sensor-based activity recognition: A survey. Pattern Recognition Letters, 119:3-11, 2019.
[9] Daniele, L, Michele, B, Luca, R, and Emanuele, F. A sequential deep learning application for recognizing human activities in smart homes. Neurocomputing, 2019.
[10] Homay, D, M and Huseyin, P. Human activity recognition in Smart Homes with the deep learning approach. In 2019 7th International Istanbul Smart Grids and Cities Congress and Fair (ICSG), pages 149-153. IEEE, 2019.
[11] Vakili, M, M, G and Masoumeh, R. "Performance Analysis and Comparison of Machine and Deep Learning Algorithms for IoT Data Classification." arXiv preprint arXiv:2001.09636 (2020).
[12] Alshammari, Talal, et al. "Evaluating machine learning techniques for activity classification in smart home environments." Int. J. Comput. Electr. Autom. Control Inf. Eng 12 (2018): 48-54.
[13] Son N T, Dung N, Tung-Son, N, Xuan-Son, V, Long, H, Qing, Z, and Mohan, K. On multi-resident activity recognition in ambient smart- homes. Arti_cial Intelligence Review, pages 1-17, 2019.
[14] Park, J, Kiyoung, J, and Sung-Bong, Y. "Deep neural networks for activity recognition with multi-sensor data in a smart home." 2018 IEEE 4th World Forum on Internet of Things (WF-IoT). IEEE, 2018.
[15] Akour, Mohammed, et al. "The effectiveness of using deep learning algorithms in predicting daily activities." International Journal 8.5 (2019).
[16] Yun, J, and Jiyoung, W. "A Comparative Analysis of Deep Learning and Machine Learning on Detecting Movement Directions Using PIR Sensors." IEEE Internet of Things Journal 7.4 (2019): 2855-2868.
[17] Djavanshir, G. R., Chen, X., & Yang, W. A Review of Artificial Intelligence's Neural Networks (Deep Learning) Applications in Medical Diagnosis and Prediction. IT Professional, 23(3), 58-62, 2021.
[18] Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges, and Opportunities. ACM Computing Surveys (CSUR), 54(4), 1-40, 2021.
[19] Liaqat, S., Dashtipour, K., Shah, S. A., Rizwan, A., Alotaibi, A. A., Althobaiti, T., & Ramzan, N. Novel Ensemble Algorithm for Multiple Activity Recognition in Elderly People Exploiting Ubiquitous Sensing Devices. IEEE Sensors Journal, 2021.
[20] Siirtola, P., & Röning, J. Context-aware incremental learning-based method for personalized human activity recognition. Journal of Ambient Intelligence and Humanized Computing, 1-15, 2021.
[21] Tarafdar, P., & Bose, I. Recognition of human activities for wellness management using a smartphone and a smartwatch: a boosting approach. Decision Support Systems, 140, 113426, 2021.
[22] Sekiguchi, R, Kenji, A, Takumi, Y, Masayasu, K, and Masaki, K. "Ensemble learning for human activity recognition." In Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers, pp. 335-339. 2020.
[23] Indumathi, V, and S. Prabakeran. "A Comparative Analysis on Sensor-Based Human Activity Recognition Using Various Deep Learning Techniques." In Computer Networks, Big Data and IoT, pp. 919-938. Springer, Singapore, 2021.
[24] Jian, Q, Shisheng, G, Pengyun, C, Peilun, W, and Guolong, C. "A Robust Real-time Human Activity Recognition method Based on Attention-Augmented GRU." In 2021 IEEE Radar Conference (RadarConf21), pp. 1-5. IEEE, 2021.
[25] Hashim, B, A Mohammed, and R. Amutha. "Machine Learning-based Human Activity Recognition using Neighbourhood Component Analysis." In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), pp. 1080-1084. IEEE, 2021.
[26] Liu, Y, Yong, M, Keyu, C, Yiming, L, and Jinghuan, G. "Daily activity feature selection in smart homes based on Pearson correlation coefficient." Neural Processing Letters (2020): 1-17.
[27] Montazery, M, and Nic W. "Scaling-invariant maximum margin preference learning." International Journal of Approximate Reasoning 128 (2021): 69-101.
[28] Hamad, R, A, Masashi, K, and Jens, L. "Efficacy of imbalanced data handling methods on deep learning for smart homes environments." SN Computer Science 1, no. 4 (2020): 1-10.
[29] Hande, A and Cem, E. Multi-resident activity tracking and recognition in smart environments. Journal of Ambient Intelligence and Humanized Computing, 8(4):513-529, 2017.
[30] Yacouby, R, and Dustin, A. "Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models."