Applying Data Mining Techniques on Continuous Sensed Data for Daily Living Activity Recognition

Abstract:

In this paper, several data mining techniques were discussed and analyzed in order to achieve the objective of human daily activities recognition based on a continuous sensing data set. The data mining techniques of decision tree, Naïve Bayes and Neural Network were successfully applied to the data set. The paper also proposed an idea of combining the Neural Network with the Decision Tree, the result shows that it works much better than the typical Neural Network and the typical Decision Tree model.

• Periodical: Applied Mechanics and Materials (Volumes 738-739)
• Pages: 191-196
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.738-739.191
• Online since: March 2015
• Authors: Yun Jie Li*, Hui Song
• Keywords: Activities Recognition, Continuous Sensed Data, Data Mining Technique, Decision Tree, Naive Bayes, Neural Network

References

[1] Yu-Jin Hong, Ig-Jae Kim, Sang Chul Ahn, Hyoung-Gon Kim, Activity Recognition using Wearable Sensors for Elder Care, IEEE journal on Future Generation Communication and Networking, vol. 2, 2008, pp.302-305.

DOI: 10.1109/fgcn.2008.165

[2] Uslu G., Altun O., Baydere S., A Bayesian approach for indoor human activity monitoring, IEEE International Conference on Hybrid Intelligent Systems (HIS), 2011, pp.324-327.

DOI: 10.1109/his.2011.6122126

[3] Sharma, A. ;  Young-Dong Lee ; Wan-Young Chung, High Accuracy Human Activity Monitoring Using Neural Network, Convergence and Hybrid Information Technology, vol. 1, 2008, pp.430-435.

DOI: 10.1109/iccit.2008.394

[4] Xi Long ; Bin Yin ; Aarts, R.M., Single-accelerometer-based daily physical activity classification, Engineering in Medicine and Biology Society, EMBC 2009. Annual International Conference of the IEEE, 2009, pp.6107-7110.

DOI: 10.1109/iembs.2009.5334925

[5] Chernbumroong, S. ;  Atkins, A.S. ; Hongnian Yu, Activity classification using a single wrist-worn accelerometer, IEEE International Conference on Software, Knowledge Information, Industrial Management and Applications (SKIMA), 2011, pp.1-6.

DOI: 10.1109/skima.2011.6089975

[6] Roggen, D. ; Calatroni, A. ; Rossi, M. ; Holleczek, T. ; Forster, K. ; Troster, G. ; Lukowicz, P. ; Bannach, D. ; Pirkl, G. ; Ferscha, A. ; Doppler, J. ; Holzmann, C. ; Kurz, M. ; Holl, G. ; Chavarriaga, R. ; Sagha, H. ; Bayati, H. ; Creatura, M. ; del R Millan, J., Collecting complex activity datasets in highly rich networked sensor environments, Seventh International Conference on Networked Sensing Systems (INSS), 2010, pp.233-240.

DOI: 10.1109/inss.2010.5573462

[7] Lukowicz, P. ; Pirkl, G. ; Bannach, D. ; Wagner, F. ; Calatroni, A. ; Foerster, K. ; Holleczek, T. ; Rossi, M. ; Roggen, D.; Troester, G. ; Doppler, J. ; Holzmann, C. ; Riener, A. ; Ferscha, A. ; Chavarriaga, R., Recording a Complex, Multi Modal Activity Data Set for Context Recognition, 23rd International Conference on Architecture of Computing Systems (ARCS), 2010, pp.1-6.

DOI: 10.1109/wowmom.2009.5282442

[8] Jolliffe, I.T., Principal Component Analysis, second edition (Springer), 2002,  p.487.