Study on Simultaneous-Action Discrimination Method Using Deep Learning

摘要

With the spread of smartphones, accidents caused by “Simultaneous-Action” such as “Simultaneous-Walking” which is walking while operating a smartphone and “Simultaneous-Cycling” which is cycling while operating a smartphone are increasing. So far, we have examined a method to discriminate “Simultaneous-Action” using neural network based on the information of the sensor mounted on the smartphone. In this study, we applied deep learning that can learn features contained in data step rather than machine learning such as support vector machine and neural network, and examined its effectiveness.