BSDGAN: Balancing Sensor Data Generative Adversarial Networks for Human Activity Recognition

TL;DR

This paper introduces BSDGAN, a novel generative adversarial network designed to generate synthetic sensor data for minority human activities, thereby balancing datasets and improving activity recognition accuracy.

Contribution

The paper proposes BSDGAN, which uses an autoencoder initialization to generate realistic sensor data for imbalanced human activity datasets, enhancing recognition performance.

Findings

BSDGAN effectively captures real human activity data features.

Generated data improves activity recognition accuracy.

The method outperforms existing approaches on benchmark datasets.

Abstract

The development of IoT technology enables a variety of sensors can be integrated into mobile devices. Human Activity Recognition (HAR) based on sensor data has become an active research topic in the field of machine learning and ubiquitous computing. However, due to the inconsistent frequency of human activities, the amount of data for each activity in the human activity dataset is imbalanced. Considering the limited sensor resources and the high cost of manually labeled sensor data, human activity recognition is facing the challenge of highly imbalanced activity datasets. In this paper, we propose Balancing Sensor Data Generative Adversarial Networks (BSDGAN) to generate sensor data for minority human activities. The proposed BSDGAN consists of a generator model and a discriminator model. Considering the extreme imbalance of human activity dataset, an autoencoder is employed to initialize the training process of BSDGAN, ensure the data features of each activity can be learned. The generated activity data is combined with the original dataset to balance the amount of activity data across human activity classes. We deployed multiple human activity recognition models on two publicly available imbalanced human activity datasets, WISDM and UNIMIB. Experimental results show that the proposed BSDGAN can effectively capture the data features of real human activity sensor data, and generate realistic synthetic sensor data. Meanwhile, the balanced activity dataset can effectively help the activity recognition model to improve the recognition accuracy.