Browse > Article
http://dx.doi.org/10.9717/kmms.2018.21.8.982

Improvement of Activity Recognition Based on Learning Model of AI and Wearable Motion Sensors  

Ahn, Junguk (Dept. of Computer Engineering, Gachon University)
Kang, Un Gu (Dept. of Computer Engineering, Gachon University)
Lee, Young Ho (Dept. of Computer Engineering, Gachon University)
Lee, Byung Mun (Dept. of Computer Engineering, Gachon University)
Publication Information
Journal of Korea Multimedia Society / v.21, no.8, 2018 , pp. 982-990 More about this Journal
Abstract
In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.
Keywords
Motion Sensor; Activity Recognition; Machine Learning Model; Smart Lifecare;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Nike+Fuelbnad, "Nike+SportWatch" for NIKE, http://www.nike.com/cdp/fuelband/ (accessed May, 1, 2018).
2 H.J. Park and H.S. Kim, "Case Studies and Development on Wearable Healthcare Design -Mainly with Diverse Types of User Perspectives," Journal of Digital Design, Vol. 14, No. 3, pp. 135-144, 2014.   DOI
3 Runtastic, Android Application, http://play.google.com/store (accessed May, 1, 2018).
4 Endomondo, Android Application, http://play.google.com/store (accessed May, 1, 2018).
5 K.H. An, E.T. Kim, U.J. Ryu, and Y.S. Chang, "Implementation on SVM Based Step Detection Analyzer," Journal of Korea Multimedia Society, Vol. 16, No. 10, pp. 1147-1155, 2013.   DOI
6 B.M. Lee, "Adaptation of Customized Measurement of Stride Length in Smart Device," Journal of the Korea Contents Association, Vol. 13, No, 4, pp. 35-43, 2013.   DOI
7 W. Lee, H. Lee, and S. Lee, "Calorie Consumption Measurement Platform using GPS and Activity Recognition Based on Accelerometer in Smartphone," Proceeding of the Spring Conference of the Korean Institute of Information Scientists and Engineers, pp. 342-344, 2013.
8 J.H. Wilmore and D.L. Costill, Physiology of Sportand Exercise 3rd Edition, Human Kinetics Publishers, Illinois, 2006.
9 C.M. Jung, J.H. Bang, K.H. Han, H.N. Yeom, and S.Y. Lee, "Smartphone Based Activity Recognition for Real Environment," Proceeding of Korean Institute of Information and Engineers, Proceedings of Korea Computer, pp. 460-462, 2013.
10 J.R. Kwapisz, G.M. Weiss, and S.A. Moore, "Activity Recognition Using Cell Phone Accelerometers," ACM SigKDD Explorations Newsletter, Vol. 12, No. 2, pp. 74-82, 2011.   DOI
11 L. Bao, and S.I. Stephen, "Activity Recognition from User-Annotated Acceleration Data," Proceeding of International Conference on Pervasive Computting, Springer , pp. 1-17, 2004.
12 J.A. Harris and G.B. Francis, "A Biometric Study of Human Basal Metabolism," Proceedings of the National Academy of Sciences, Vol 4, No. 12, pp. 370-373, 1918.   DOI
13 D.E. Rumelhart, E.H. Geoffrey, and J.W. Ronald, Learning Internal Representations by Error Propagation, California Univ San Diego La Jolla Inst for Cognitive Science, 1985.
14 N. Ravi, N. Dandekar, P. Mysore, and M.L. Littman, "Activity Recognition from Accelerometer Data," Association for the Advancement of Artificial Intelligence, Vol. 5, No. 2005, pp. 1541-1546, 2005.
15 S.H. Kim, O.H. Lee, H.S. Lee, and J.Y. Joe, Nutrition and Exercise, Powerbook, Goyang, 2007.
16 J.H. Yoon and I.K. Jung, Human Performance & Exercise Physiology, DKBooks, Seoul, 2011.
17 D.R. Cox, "The Regression Analysis of Binary Sequences," Journal of the Royal Statistical Society, pp. 215-242, 1958.
18 G. Holmes, A. Donkin, and I.H. Witten, "Weka: A Machine Learning Workbench," Proceedings of the 1994 Second Australian and New Zealand Conference, Intelligent Information Systems, pp. 357-361, 1994.
19 S.L. Salzberg, "C4. 5: Programs for Machine Learning," Machine Learning, Vol. 16, No. 3, pp. 235-240, 1994.   DOI