Human behaviour analysis in context of smart environment automation
Abstract
Basic approaches to the automated control of smart environment problem are considered. A new method of solution based on the information about the signal strength of wireless broadcasting devices (considered as beacons) and the heart rate sensor readings is introduced. The model environment is an apartment with Bluetooth beacons; the inhabitant has a heart rate sensor and a RSSI measuring device. An application collecting beacons RSSI and heart rate measurements during the inhabitant activity in the model environment has been implemented. The application provides the user interface to display current state of devices which are objects of automated control. By using machine learning methods the relation between the collected data and device states is obtained. Thus, an automated smart environment control model has been implemented. The estimation of the accuracy of prediction of the devices preferable state has been obtained.
References
[2] A. Babakura et al., “HMM-Based Decision Model for Smart Home Environment,” International Journal of Smart Home, Vol., 8, no.1, pp. 129-138, 2014, doi: 10.14257/ijsh.2014.8.1.14
[3] S. Choi, E. Kim, and S. Oh, “Human behavior prediction for smart homes using deep learning,” in RO-MAN 2013, IEEE, Gyeongju, South Korea, 2013, pp. 173–179 doi: 10.1109/ROMAN.2013.6628440.
[4] S. R. Kulkarni, G. Lugosi, and S. S. Venkatesh, “Learning pattern classification-a survey,” IEEE Transactions on Information Theory, vol., 44, no. 6. pp. 2178–2206, 1998. doi:10.1109/18.720536
[5] P. Langley and H. A. Simon, “Applications of machine learning and rule induction,” Communications of the ACM, vol., 38, no. 11, pp. 54–64, 1995. doi: 10.1145/219717.219768
[6] E. Munguia Tapia “Activity recognition in the home setting using simple and ubiquitous sensors,” Ph. D. dissertation, Massachusetts Institute of Technology, 2003
[7] S. Stenudd, Using machine learning in the adaptive control of a smart environment, Espoo, Finland: VTT Publications 751, 2010.
This work is licensed under a Creative Commons Attribution 4.0 International License.
