ConvLSTM for Human Activity Recognition

Abstract

The research in Human Activity Recognition (HAR) using wearable probes and pocket devices has intensified to further understand and inherently foresee human behavior and their intentions. The researchers are seeking a system to consume the least amount of allocated resources to identify the consumer’s activity being performed. In this paper, we propose a state-of-the-art deep learning-based activity recognition architecture, a Convolutional Long Short-Term Memory (ConvLSTM) network . This ConvLSTM approach significantly improves the accuracy of classification of the six activities from raw data without the use of any major aspect of feature engineering hence, reducing the complexity of the model with a very minor pre-processing procedure. Our proposed model is able to achieve a staggering 94% accuracy on the UCI HAR public dataset. During performance comparisons with earlier models, we were able to notice profitable improvements against Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) Network, Deep Neural Network (DNN) models, and also against linear and non-linear machine learning models which heavily depend upon manually manufactured featured data.KeywordsHuman Activity Recognition (HAR)Convolutional Neural Network (CNN)Long Short-Term Memory Network (LSTM)Convolutional Long Short-Term Memory (ConvLSTM)Deep learningUCI HAR datasetTime Series Classification (TSC)Neural networkMagnetometersAccelerometersGyroscopesSensorsInertial Measurement Unit (IMU)