SOS: A Shuffle Order Strategy for Data Augmentation in Industrial Human Activity Recognition

TL;DR

This paper proposes a shuffle order strategy for data augmentation in Human Activity Recognition, improving model robustness and accuracy by disrupting temporal dependencies and homogenizing data distribution.

Contribution

It introduces a novel data augmentation method using data shuffling to enhance HAR performance and robustness, addressing data heterogeneity and variability challenges.

Findings

Achieved up to 0.70 ± 0.03 accuracy

Macro F1 score of 0.64 ± 0.01

Shuffling improves classification robustness

Abstract

In the realm of Human Activity Recognition (HAR), obtaining high quality and variance data is still a persistent challenge due to high costs and the inherent variability of real-world activities. This study introduces a generation dataset by deep learning approaches (Attention Autoencoder and conditional Generative Adversarial Networks). Another problem that data heterogeneity is a critical challenge, one of the solutions is to shuffle the data to homogenize the distribution. Experimental results demonstrate that the random sequence strategy significantly improves classification performance, achieving an accuracy of up to 0.70 $\pm$ 0.03 and a macro F1 score of 0.64 $\pm$ 0.01. For that, disrupting temporal dependencies through random sequence reordering compels the model to focus on instantaneous recognition, thereby improving robustness against activity transitions. This approach not only broadens the effective training dataset but also offers promising avenues for enhancing HAR systems in complex, real-world scenarios.