Human Activity Recognition on Time Series Accelerometer Sensor Data using LSTM Recurrent Neural Networks

TL;DR

This paper presents an LSTM-based neural network approach for recognizing specific human activities, like eating, from smartwatch accelerometer data, achieving high accuracy in classifying different activities.

Contribution

It introduces a novel LSTM-ANN architecture tailored for activity recognition from accelerometer data, focusing on eating activity detection with high success rate.

Findings

Achieved 90% accuracy in identifying bites during eating

Successfully distinguished eating from smoking, medication, and jogging activities

Demonstrated effectiveness of LSTM-ANN in sensor-based activity recognition

Abstract

The use of sensors available through smart devices has pervaded everyday life in several applications including human activity monitoring, healthcare, and social networks. In this study, we focus on the use of smartwatch accelerometer sensors to recognize eating activity. More specifically, we collected sensor data from 10 participants while consuming pizza. Using this information, and other comparable data available for similar events such as smoking and medication-taking, and dissimilar activities of jogging, we developed a LSTM-ANN architecture that has demonstrated 90% success in identifying individual bites compared to a puff, medication-taking or jogging activities.