Soft Computing for the Analysis of People Movement Classification
This article presents a study of the best data acquisition conditions regarding movements of extremities in people. By using an accelerometer, there exist different ways of collecting and storing the data captured while people moving. To know which one of these options is the best one, in terms of classification, an empirical study is presented in this paper. As a soft computing technique for validation, Self-Organizing maps have been chosen due to their visualization capability. Empirical verification and comparison of the proposed classification methods are performed in a real domain, where three similar movements in the real-life are analyzed.
KeywordsActivity Recognition Soft Computing Dynamic Time Warp Artificial Intelligence Technique Well Matching Unit
Unable to display preview. Download preview PDF.
- 1.Comparing Self-Organizing Maps, ICANN 1996, vol. 1112 (1996) Google Scholar
- 6.Analog Devices. Adxl335, Accelerometer (2012)Google Scholar
- 9.Kohonen, T.: Self-Organizing Maps. Springer Series in Information Sciences. Springer (2001)Google Scholar
- 12.Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the rprop algorithm. In: IEEE International Conference on Neural Networks, vol. 1(3), pp. 586–591 (1993)Google Scholar
- 14.Van Laerhoven, K., Cakmakci, O.: What shall we teach our pants? (2000)Google Scholar
- 15.Vesanto, J.: Data mining techniques based on the self-organizing map. Master’s thesis, Helsinki University of Technology (May 1997)Google Scholar