Human Activity Recognition Using LSTM-RNN Deep Neural Network Architecture

TL;DR

This paper presents an LSTM-RNN deep neural network architecture for human activity recognition using raw sensor data, achieving over 94% accuracy and demonstrating the model's potential for various practical applications.

Contribution

It introduces a specific LSTM-based model architecture tailored for human activity recognition and discusses dataset features and training results.

Findings

Achieved over 94% accuracy in activity recognition

Model training reached below 30% loss within 500 epochs

Discussed dataset features and model extension possibilities

Abstract

Using raw sensor data to model and train networks for Human Activity Recognition can be used in many different applications, from fitness tracking to safety monitoring applications. These models can be easily extended to be trained with different data sources for increased accuracies or an extension of classifications for different prediction classes. This paper goes into the discussion on the available dataset provided by WISDM and the unique features of each class for the different axes. Furthermore, the design of a Long Short Term Memory (LSTM) architecture model is outlined for the application of human activity recognition. An accuracy of above 94% and a loss of less than 30% has been reached in the first 500 epochs of training.