Support Vector Machine Classification in a Device-Free Passive Localisation (DfPL) Scenario
The holy grail of tracking people indoors is being able to locate them when they are not carrying any wireless tracking devices. The aim is to be able to track people just through their physical body interfering with a standard wireless network that would be in most peoples home. The human body contains about 70% water which attenuates the wireless signal reacting as an absorber. The changes in the signal along with prior fingerprinting of a physical location allow identification of a person’s location. This paper is focused on taking the principle of Device-free Passive Localisation (DfPL) and applying it to be able to actually distinguish if there is more than one person in the environment. In order to solve this problem, we tested a Support Vector Machine (SVM) classifier with kernel functions such as Linear, Quadratic, Polynomial, Gaussian Radial Basis Function (RBF) and Multilayer Perceptron (MLP) in order to detect movement based on changes in the wireless signal strength.
KeywordsSuport Vector Machine Wireless Sensor Network Kernel Function Receive Signal Strength Indicator Gaussian Radial Basis Function
Unable to display preview. Download preview PDF.
- 2.Ma, L., Zhang, Z., Tan, X.: A novel through-wall imaging method using ultra wideband pulse system. In: International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2006, pp. 147–150 (December 2006)Google Scholar
- 4.Aryanfar, F., Sarabandi, K.: Through wall imaging at microwave frequencies using space-time focusing. In: IEEE Antennas and Propagation Society International Symposium, vol. 3, pp. 3063–3066 (June 2004)Google Scholar
- 6.Valtonen, M., Maentausta, J., Vanhala, J.: Tiletrack: Capacitive human tracking using floor tiles. In: IEEE International Conference on Pervasive Computing and Communications, PerCom 2009, pp. 1–10 (March 2009)Google Scholar
- 7.Krumm, J.: Ubiquitous Computing Fundamentals. CRC Press (2010)Google Scholar
- 8.Krumm, J., Harris, S., Meyers, B., Brumitt, B., Hale, M., Shafer, S.: Multi-camera multi-person tracking for easy living. In: Proceedings of Third IEEE International Workshop on Visual Surveillance, pp. 3–10 (2000)Google Scholar
- 9.Microsoft Research. Easy Living (2011), http://www.research.microsoft.com/
- 10.Deak, G., Curran, K., Condell, J.: Filters for RSSI-based measurements in a Device-free Passive Localisation Scenario. International Journal on Image Processing & Communications 15(1), 23–34 (2011)Google Scholar
- 11.Deak, G., Curran, K., Condell, J.: History Aware Device-free Passive (DfP) Localisation. International Journal on Image Processing & Communications 16(3-4), 21–30 (2012)Google Scholar
- 12.Moussa, M., Youssef, M.: Smart cevices for smart environments: Device-free passive detection in real environments. In: IEEE International Conference on Pervasive Computing and Communications, PerCom 2009, pp. 1–6 (2009)Google Scholar
- 13.Youssef, M., Mah, M., Agrawala, A.: Challenges: device-free passive localization for wireless environments. In: Proceedings of the 13th Annual ACM International Conference on Mobile Computing and Networking, pp. 222–229 (2007)Google Scholar
- 14.Kosba, A., Abdelkader, E., Youssef, A., Analysis, M.: of a device-free passive tracking system in typical wireless environments. In: 2009 3rd International Conference on New Technologies, Mobility and Security, NTMS, pp. 1–5 (December 2009)Google Scholar
- 16.Mathworks. R2012a Documentation, Bioinformatics Toolbox (2012), http://www.mathworks.co.uk/help/toolbox/bioinfo/