Vision Based Fall Prediction Using GCNLSTM Model

Erdogan, Bilge Su (2024) Vision Based Fall Prediction Using GCNLSTM Model. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (641kB) | Preview

Abstract

Currently, falling, which has become a nightmare especially for those living alone, significantly affects people's activities. The urgent intervention call of smart systems is very valuable in order to prevent the occurrence of negative situations after falling. For this reason, studies on fall prediction are increasing day by day. These studies are divided into two as sensor-based fall detection and vision-based fall detection. There are obstacles to sensor-based studies such as battery life, the presence of wearable technologies on people or the cost of systems placed on the ground. Ease of installation and visual-based studies that appeal to more than one person in a wide area were preferred in this study. A fall prediction that has not been done before is made with the GCN - LSTM hybrid model by calculating the distance of the head to the ground, the torso angle, the symmetric difference and the parallelism score with the results obtained from the systems that determine the joint points of the human body through images. It is aimed to contribute to the literature for the studies carried out to prevent real-time fall prediction and the negative situations that may occur afterwards.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Hasanuzzaman, Mohammed UNSPECIFIED
Uncontrolled Keywords:	Fall Prediction; Vision-Based; Graf Convulsion Network; Long Short-Term Memory; OpenPose
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HV Social pathology. Social and public welfare > Welfare of older people
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	02 Sep 2025 11:20
Last Modified:	02 Sep 2025 11:20
URI:	https://norma.ncirl.ie/id/eprint/8697

Actions (login required)

View Item