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

arXiv: https://arxiv.org/abs/2505.10312 · HTML: https://mlsanity.com/paper/2505.10312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 15 May 2025.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [A Close Look into Human Activity Recognition Models using Deep Learning](https://mlsanity.com/paper/2204.13589/) (2022)
- [Using GAN to Enhance the Accuracy of Indoor Human Activity Recognition](https://mlsanity.com/paper/2004.11228/) (2020)
- [Transformer-Based Approaches for Sensor-Based Human Activity Recognition: Opportunities and Challenges](https://mlsanity.com/paper/2410.13605/) (2024)
- [Human Activity Recognition Using LSTM-RNN Deep Neural Network Architecture](https://mlsanity.com/paper/1905.00599/) (2019)
- [Preliminary Investigation of SSL for Complex Work Activity Recognition in Industrial Domain via MoIL](https://mlsanity.com/paper/2404.13581/) (2024)

## Abstract (arXiv)

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 ± 0.03 and a macro F1 score of 0.64 ± 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.