Automatic Fall Detection using Deep Neural Networks with Aggregated Residual Transformation
1
Issued Date
2022-01-01
Resource Type
Scopus ID
2-s2.0-85140583630
Journal Title
ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
Start Page
811
End Page
814
Rights Holder(s)
SCOPUS
Bibliographic Citation
ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications (2022) , 811-814
Suggested Citation
Mekruksavanich S., Jantawong P., Hnoohom N., Jitpattanakul A. Automatic Fall Detection using Deep Neural Networks with Aggregated Residual Transformation. ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications (2022) , 811-814. 814. doi:10.1109/ITC-CSCC55581.2022.9895054 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/84353
Title
Automatic Fall Detection using Deep Neural Networks with Aggregated Residual Transformation
Author's Affiliation
Other Contributor(s)
Abstract
The advancement of inertial sensor technology and the growing prevalence of intelligent wearables (including smart-watches, smart bands, and other intelligent devices) have aided in applying science and technology to automated Fall Detection Systems (FDSs). Over the past decade, wearable-based FDSs has garnered considerable scientific attention. In this context, ma-chine learning (ML) techniques have demonstrated remarkable efficacy in differentiating between falls and typical motions or Activities of Daily Living (ADLs) using the data recorded by wearable inertial sensors. Unfortunately, in most research, the effectiveness of machine learning classifiers was restricted by feature extraction and selection processes that relied on human-crafted decisions. A deep neural network was established to en-hance the capacity of fall detection, which combines convolutional layers and aggregated residual transformation in this study. The TensorFlow framework trained the proposed model to identify and categorize 15 special events: three distinct falls and twelve ADLs. On a publicly available benchmark dataset (UMAFall), the proposed model was analyzed and compared to existing baseline models. The findings indicate that the proposed model is superior to other models, with an accuracy of 96.72%.