Open Access

ARTICLE

A Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller Model Combined with an Improved Particle Swarm Optimization Method for Fall Detection

by Jyun-Guo Wang^*

The Department of Medical Informatics, Tzu Chi University, Hualien County, 97004, Taiwan

* Corresponding Author: Jyun-Guo Wang. Email:

Computer Systems Science and Engineering 2024, 48(5), 1149-1170. https://doi.org/10.32604/csse.2024.052931

Received 19 April 2024; Accepted 02 July 2024; Issue published 13 September 2024

Abstract

In many Eastern and Western countries, falling birth rates have led to the gradual aging of society. Older adults are often left alone at home or live in a long-term care center, which results in them being susceptible to unsafe events (such as falls) that can have disastrous consequences. However, automatically detecting falls from video data is challenging, and automatic fall detection methods usually require large volumes of training data, which can be difficult to acquire. To address this problem, video kinematic data can be used as training data, thereby avoiding the requirement of creating a large fall data set. This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a cost-effective and accurate fall detection system. First, it obtained an optical flow (OF) trajectory diagram from image sequences by using the OF method, and it solved problems related to focal length and object offset by employing the discrete Fourier transform (DFT) algorithm. Second, this study developed the D-IRFCMAC model, which combines spatial and temporal (recurrent) information. Third, it designed an IPSO (Improved Particle Swarm Optimization) algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC (Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller) model in the global search space. The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall, UP-Fall, and PRECIS HAR data sets. The UCF11 dataset had an average accuracy of 93.13%, whereas the UCF101 dataset had an average accuracy of 92.19%. The UR-Fall dataset had an accuracy of 100%, the UP-Fall dataset had an accuracy of 99.25%, and the PRECIS HAR dataset had an accuracy of 99.07%.

---

Keywords

---