English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The development of IoT technology enables a variety of sensors can beintegrated into mobile devices. Human Activity Recognition (HAR) based onsensor data has become an active research topic in the field of machinelearning and ubiquitous computing. However, due to the inconsistent frequencyof human activities, the amount of data for each activity in the human activitydataset is imbalanced. Considering the limited sensor resources and the highcost of manually labeled sensor data, human activity recognition is facing thechallenge of highly imbalanced activity datasets. In this paper, we proposeBalancing Sensor Data Generative Adversarial Networks (BSDGAN) to generatesensor data for minority human activities. The proposed BSDGAN consists of agenerator model and a discriminator model. Considering the extreme imbalance ofhuman activity dataset, an autoencoder is employed to initialize the trainingprocess of BSDGAN, ensure the data features of each activity can be learned.The generated activity data is combined with the original dataset to balancethe amount of activity data across human activity classes. We deployed multiplehuman activity recognition models on two publicly available imbalanced humanactivity datasets, WISDM and UNIMIB. Experimental results show that theproposed BSDGAN can effectively capture the data features of real humanactivity sensor data, and generate realistic synthetic sensor data. Meanwhile,the balanced activity dataset can effectively help the activity recognitionmodel to improve the recognition accuracy.

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