Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data
Author:
Khan Yusuf Ahmed1ORCID, Imaduddin Syed1ORCID, Singh Yash Pratap1ORCID, Wajid Mohd1ORCID, Usman Mohammed2ORCID, Abbas Mohamed34ORCID
Affiliation:
1. Department of Electronics Engineering, ZHCET, Aligarh Muslim University, Aligarh 202002, India 2. Department of Electrical Engineering, King Khalid University, Abha 61411, Saudi Arabia 3. Electrical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia 4. Electronics and Communication Department, College of Engineering, Delta University for Science and Technology, Gamasa 35712, Egypt
Abstract
The integration of Micro Electronic Mechanical Systems (MEMS) sensor technology in smartphones has greatly improved the capability for Human Activity Recognition (HAR). By utilizing Machine Learning (ML) techniques and data from these sensors, various human motion activities can be classified. This study performed experiments and compiled a large dataset of nine daily activities, including Laying Down, Stationary, Walking, Brisk Walking, Running, Stairs-Up, Stairs-Down, Squatting, and Cycling. Several ML models, such as Decision Tree Classifier, Random Forest Classifier, K Neighbors Classifier, Multinomial Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine, were trained on sensor data collected from accelerometer, gyroscope, and magnetometer embedded in smartphones and wearable devices. The highest test accuracy of 95% was achieved using the random forest algorithm. Additionally, a custom-built Bidirectional Long-Short-Term Memory (Bi-LSTM) model, a type of Recurrent Neural Network (RNN), was proposed and yielded an improved test accuracy of 98.1%. This approach differs from traditional algorithmic-based human activity detection used in current wearable technologies, resulting in improved accuracy.
Funder
Deanship of Scientific Research at King Khalid University
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference90 articles.
1. Recent trends in machine learning for human activity recognition—A survey. WIREs Data Min;Ramamurthy;Knowl. Discov.,2018 2. Deep learning for sensor-based human activity recognition: Overview, challenges and opportunities;Chen;ACM Comput. Surv.,2021 3. A Survey on Human Activity Recognition using Wearable Sensors;Lara;IEEE Commun. Surv. Tutor.,2013 4. Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances. Sensors, 22. 5. Khan, A.A.H., Kukkapalli, R., Waradpande, P., Kulandaivel, S., Banerjee, N., Roy, N., and Robucci, R. (2016, January 10–14). RAM: Radar-based activity monitor. Proceedings of the 35th Annual IEEE International Conference on Computer Communications, San Francisco, CA, USA.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|