Improving Accelerometer-Based Activity Recognition by Using Ensemble of Classifiers

作者: Tahani Daghistani , Riyad Alshammari

DOI: 10.14569/IJACSA.2016.070520

关键词:

摘要: In line with the increasing use of sensors and health application, there are huge efforts on processing collected data to extract valuable information such as accelerometer data. This study will propose activity recognition model aim detect activities by employing ensemble classifiers techniques using Wireless Sensor Data Mining (WISDM). The recognize six namely walking, jogging, upstairs, downstairs, sitting, standing. Many experiments conducted determine best classifier combination for recognition. An improvement is observed in performance when combined than used individually. built AdaBoost decision tree algorithm C4.5. effectively enhances an accuracy level 94.04 %.

参考文章(13)
Gary Mitchell Weiss, Jeffrey Lockhart, The Impact of Personalization on Smartphone-Based Activity Recognition national conference on artificial intelligence. ,(2012)
Fabien Massé, Roman R Gonzenbach, Arash Arami, Anisoara Paraschiv-Ionescu, Andreas R Luft, Kamiar Aminian, None, Improving activity recognition using a wearable barometric pressure sensor in mobility-impaired stroke patients Journal of Neuroengineering and Rehabilitation. ,vol. 12, pp. 72- 86 ,(2015) , 10.1186/S12984-015-0060-2
Cagatay Catal, Selin Tufekci, Elif Pirmit, Guner Kocabag, On the use of ensemble of classifiers for accelerometer-based activity recognition soft computing. ,vol. 37, pp. 1018- 1022 ,(2015) , 10.1016/J.ASOC.2015.01.025
Jeffrey W. Lockhart, Tony Pulickal, Gary M. Weiss, Applications of mobile activity recognition ubiquitous computing. pp. 1054- 1058 ,(2012) , 10.1145/2370216.2370441
Jin Wang, Ronghua Chen, Xiangping Sun, Mary F.H. She, Yuchuan Wu, Recognizing Human Daily Activities From Accelerometer Signal Procedia Engineering. ,vol. 15, pp. 1780- 1786 ,(2011) , 10.1016/J.PROENG.2011.08.331
Isabel Suarez, Andreas Jahn, Christoph Anderson, Klaus David, Improved activity recognition by using enriched acceleration data ubiquitous computing. pp. 1011- 1015 ,(2015) , 10.1145/2750858.2805844
Lei Gao, A.K. Bourke, John Nelson, Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems. Medical Engineering & Physics. ,vol. 36, pp. 779- 785 ,(2014) , 10.1016/J.MEDENGPHY.2014.02.012
Jennifer R. Kwapisz, Gary M. Weiss, Samuel A. Moore, Activity recognition using cell phone accelerometers ACM SIGKDD Explorations Newsletter. ,vol. 12, pp. 74- 82 ,(2011) , 10.1145/1964897.1964918
Media Anugerah Ayu, Siti Aisyah Ismail, Ahmad Faridi Abdul Matin, Teddy Mantoro, A Comparison Study of Classifier Algorithms for Mobile-phone's Accelerometer Based Activity Recognition international symposium on robotics. ,vol. 41, pp. 224- 229 ,(2012) , 10.1016/J.PROENG.2012.07.166
Yanan Song, Shianghau Wu, Human Activity Recognition on Smartphone: A Classification Analysis Indonesian Journal of Electrical Engineering and Computer Science. ,vol. 12, pp. 7041- 7045 ,(2014) , 10.11591/IJEECS.V12.I9.PP7041-7045