Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors

TL;DR

This paper introduces a deep residual bidirectional LSTM network for human activity recognition using wearable sensors, combining bidirectional processing and residual connections to improve accuracy and mitigate gradient issues.

Contribution

It proposes a novel deep residual bidirectional LSTM architecture that enhances HAR performance by integrating bidirectional and residual features, addressing gradient vanishing.

Findings

Achieved 4.78% accuracy increase on Opportunity dataset

Achieved 3.68% accuracy increase on UCI dataset

Analyzed confusion matrix for detailed insights

Abstract

Human activity recognition (HAR) has become a popular topic in research because of its wide application. With the development of deep learning, new ideas have appeared to address HAR problems. Here, a deep network architecture using residual bidirectional long short-term memory (LSTM) cells is proposed. The advantages of the new network include that a bidirectional connection can concatenate the positive time direction (forward state) and the negative time direction (backward state). Second, residual connections between stacked cells act as highways for gradients, which can pass underlying information directly to the upper layer, effectively avoiding the gradient vanishing problem. Generally, the proposed network shows improvements on both the temporal (using bidirectional cells) and the spatial (residual connections stacked deeply) dimensions, aiming to enhance the recognition rate. When tested with the Opportunity data set and the public domain UCI data set, the accuracy was increased by 4.78% and 3.68%, respectively, compared with previously reported results. Finally, the confusion matrix of the public domain UCI data set was analyzed.