Human Action Recognition based on LSTM Model using Smartphone Sensor
Yull Kyu Han, Young Bok Choi · 2019
We propose a deep learning model for human action recognition in order to quickly detect occurrence of disasters such as fire and terrorism. Using the acceleration and gyroscope sensors built in the smartphone, four kinds of data on human behavior were obtained and human behavior was classified through the LSTM deep learning model. As an experiment, it was confirmed that the LSTM model can be classified 95.47% accurately.