Gesture Recognition for Home Automation Using Transfer Learning

Abstract

Gesture recognition has lots of applications in automation including home device control. Nowadays, a smartphone is a very common device which can be utilized to capture gesture information. In this paper, we propose a method to recognize gestures using machine learning, which uses gesture data collected from a gyroscope sensor in a smartphone. We implemented and tested to verify our method, and as a result, we found that the method showed an acceptable rate of recognition for home automation.