Improved Sensor Based Human Activity Recognition via Hybrid Convolutional and Recurrent Neural Networks

Non-intrusive sensor based human activity recognition (HAR) is utilized in a spectrum of applications including fitness tracking devices, gaming, health care monitoring, and smartphone applications. In this paper, we design a multi-layer hybrid architecture with Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM). Based on the exploration of a variety of multi-layer combinations, we present a lightweight, hybrid, and multi-layer model which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model which can achieve a 94.7% activity recognition rate on a benchmark dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between accuracy and efficiency.