Comprehensive Convolutional Neural Network Approach for Fall Detection using Deep Learning

DOI

10.2991/978-94-6463-884-4_69How to use a DOI?

Keywords

Convolutional Neural Network (CNN); Fall Detection; Healthcare; Image Processing; Safety; Scratch

Abstract

Fall detection constitutes an important and critical aspect of the safety and welfare of individuals. This paper presents a fall detection system for institutions in which people have high risk of falling, such as healthcare facilities and elder care home. The system setup comprises a lightweight scratch Convolutional Neural Network (CNN) model that has been trained on a highly curated dataset for detecting falls. The images have gone through various preprocessing methods like resizing, augmentation and normalization, improving model performance thus increasing the accuracy of the detection. This lightweight architecture lowers the computational complexity while keeping high precision. The accuracy achieved on the validation data is 88%. It is much better than traditional methods, as found in significant improvement recorded in precision, recall, and F1-score metrics. These results provide a chance for real-time applications of the lightweight scratch CNN model for immediate warning to at-risk persons for quick medical assistance.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Nayamat Ullah Chowdhury
AU  - Somaya Shikder
AU  - Shuhena Salam Aonty
PY  - 2025
DA  - 2025/11/18
TI  - Comprehensive Convolutional Neural Network Approach for Fall Detection using Deep Learning
BT  - Proceedings of the 8th International Conference on Engineering Research, Innovation, and Education 2025 (ICERIE 2025)
PB  - Atlantis Press
SP  - 575
EP  - 581
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-884-4_69
DO  - 10.2991/978-94-6463-884-4_69
ID  - Chowdhury2025
ER  -