Estimation of human transport modes by fuzzy spiking neural network and evolution strategy in informationally structured space

Abstract

This paper analyzes the performance of human transport mode estimation by fuzzy spiking neural network in informationally structured space based on smart phone sensor. The importance of information structuralization is considered. In our previous work we applied spiking neural network to extract the human position in a room equipped with sensor network devices. In this paper fuzzy spiking neural network is applied to extract the human activity outdoors when equipped with smart phone sensor. We discuss how to update the base value by preprocessing for generating the input values to the spiking neurons. The learning method of the spiking neural network based on the time series of the measured data is explained as well. Evolution strategy is used for optimizing the parameters of the fuzzy spiking neural network. Several experimental results are presented for confirming the effectiveness of the proposed method.