The week's pick
Reseach Article
Human Activity Recognition through Smartphone’s Tri-Axial Accelerometer using Time Domain Wave Analysis and Machine Learning
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 127 - Number 18 |
| Year of Publication: 2015 |
| Authors: Sarthak Gupta, Ajeet Kumar |
10.5120/ijca2015906733
|
Sarthak Gupta, Ajeet Kumar . Human Activity Recognition through Smartphone’s Tri-Axial Accelerometer using Time Domain Wave Analysis and Machine Learning. International Journal of Computer Applications. 127, 18 ( October 2015), 22-26. DOI=10.5120/ijca2015906733
Abstract
Human activity recognition aims at capturing current state of human in the immediate environment. This article poses a novel approach to predict the human activity by exploiting the data collected from smartphone’s triaxial accelerometer sensor. This approach employs a time domain wave analysis on the collected data and extracts relevant features that intuitively distinguish various activities such as walking, standing, running, jogging and sitting. The method then classifies the extracted features using various Machine learning algorithms comprising of SVM, J48 and AdaBoost and Random Forest. This work attains a steadfast accuracy of 98.8283%. HAR has numerous uses, ranging from healthcare, HCI, ubiquitous networks, to entertainment. The need for ever-increasing accuracy levels is inevitable and this work serves the purpose.
References
- Amin Rasekh, Chien-An Chen Yan Lu, Human Activity Recognition using Smartphone, Texas A&M University
- Akram Bayat∗ , Marc Pomplun, Duc A. Tran Department of Computer Science, A Study on Human Activity Recognition Using Accelerometer Data from Smartphones, Akram Bayat∗ , Marc Pomplun, Duc A. Tran Department of Computer Science, University of
- Vu Ngoc Thanh Sang, Nguyen Duc Thang, Vo Van ToiAffiliated withDepartment of Biomedical Engineering, International University – VNU, Nguyen Duc Hoang, Truong Quang Dang Khoa, Human Activity Recognition and Monitoring Using Smartphones, 5th International Conference on Biomedical Engineering in VietnamVolume 46 of the series IFMBE Proceedings pp 481-485
- Jennifer R. Kwapisz, Gary M. Weiss, Samuel A. Moore, Activity recognition using cell phone accelerometers, ACM SIGKDD Explorations Newsletter Volume 12 Issue 2, December 2010 Pages 74-82.
- XindongWu et al., 2008, Top 10 algorithms in data mining, Springer, KnowlInfSyst (2008) 14:1–37
- Brezmes, T., Gorricho, J.L., and Cotrina, J. 2009. Activity Recognition from accelerometer data on mobile phones In IWANN '09: Proceedings of the 10th International Work- Conference on Artificial Neural Networks, 796-799.
Index Terms
Keywords