Please use this identifier to cite or link to this item:
Title: Towards a New Multi-tasking Learning Approach for Human Fall Detection
Authors: Nguyen, Duc Anh
Pham, Cuong
Rob, Argent
Brian, Caulfield
Le, Khac Nhien An
Keywords: fall detection
multi-task learning
human activity recognition
data scarcity
Deep Learning
Issue Date: Jul-2023
Publisher: Springer Nature
Abstract: Many fall detection systems are being used to provide real-time responses to fall occurrences. Automated fall detection is challenging because it requires near perfect accuracy to be clinically acceptable. Recent research has tried to improve the accuracy along with reducing the high rate of false positives. Nevertheless, there are still limitations in terms of having efficient learning approaches and proper datasets to train. To improve the accuracy, one approach is to include non-fall data from public datasets as negative examples to train the deep learning model. However, this approach could increase the imbalance of the training set. In this paper, we propose a multi-task deep learning model to tackle this problem. We divide datasets into multiple training sets for multiple tasks, and we prove this approach gives better results than a single-task model trained on all datasets. Many experiments are conducted to find the best combination of tasks for multi-task model training for fall detection.
Description: Lecture Notes in Networks and Systems (LNNS, volume 734); CITA: Conference on Information Technology and its Applications; pp: 50-61.
ISBN: 978-3-031-36886-8
Appears in Collections:CITA 2023 (International)

Files in This Item:

 Sign in to read

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.