Human Activity Recognition Using Graph Structures and Deep Neural Networks

Human activity recognition (HAR) systems are essential in healthcare, surveillance, and sports analytics, enabling automated movement analysis. This research presents a novel HAR system combining graph structures with deep neural networks to capture both spatial and temporal patterns in activities....

Full description

Saved in:
Bibliographic Details
Main Author: Abed Al Raoof K. Bsoul
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Computers
Subjects:
Online Access:https://www.mdpi.com/2073-431X/14/1/9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832588747408932864
author Abed Al Raoof K. Bsoul
author_facet Abed Al Raoof K. Bsoul
author_sort Abed Al Raoof K. Bsoul
collection DOAJ
description Human activity recognition (HAR) systems are essential in healthcare, surveillance, and sports analytics, enabling automated movement analysis. This research presents a novel HAR system combining graph structures with deep neural networks to capture both spatial and temporal patterns in activities. While CNN-based models excel at spatial feature extraction, they struggle with temporal dynamics, limiting their ability to classify complex actions. To address this, we applied the Firefly Optimization Algorithm to fine-tune the hyperparameters of both the graph-based model and a CNN baseline for comparison. The optimized graph-based system, evaluated on the UCF101 and Kinetics-400 datasets, achieved 88.9% accuracy with balanced precision, recall, and F1-scores, outperforming the baseline. It demonstrated robustness across diverse activities, including sports, household routines, and musical performances. This study highlights the potential of graph-based HAR systems for real-world applications, with future work focused on multi-modal data integration and improved handling of occlusions to enhance adaptability and performance.
format Article
id doaj-art-1c28fcb1167843169a91f397ace1d5c4
institution Kabale University
issn 2073-431X
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Computers
spelling doaj-art-1c28fcb1167843169a91f397ace1d5c42025-01-24T13:27:51ZengMDPI AGComputers2073-431X2024-12-01141910.3390/computers14010009Human Activity Recognition Using Graph Structures and Deep Neural NetworksAbed Al Raoof K. Bsoul0Collage of Computer Science and Information Technology, Yarmouk University, Irbid 21163, JordanHuman activity recognition (HAR) systems are essential in healthcare, surveillance, and sports analytics, enabling automated movement analysis. This research presents a novel HAR system combining graph structures with deep neural networks to capture both spatial and temporal patterns in activities. While CNN-based models excel at spatial feature extraction, they struggle with temporal dynamics, limiting their ability to classify complex actions. To address this, we applied the Firefly Optimization Algorithm to fine-tune the hyperparameters of both the graph-based model and a CNN baseline for comparison. The optimized graph-based system, evaluated on the UCF101 and Kinetics-400 datasets, achieved 88.9% accuracy with balanced precision, recall, and F1-scores, outperforming the baseline. It demonstrated robustness across diverse activities, including sports, household routines, and musical performances. This study highlights the potential of graph-based HAR systems for real-world applications, with future work focused on multi-modal data integration and improved handling of occlusions to enhance adaptability and performance.https://www.mdpi.com/2073-431X/14/1/9human activity recognition (HAR)deep learningfirefly optimization algorithmgraph-based modelsspatial–temporal analysis
spellingShingle Abed Al Raoof K. Bsoul
Human Activity Recognition Using Graph Structures and Deep Neural Networks
Computers
human activity recognition (HAR)
deep learning
firefly optimization algorithm
graph-based models
spatial–temporal analysis
title Human Activity Recognition Using Graph Structures and Deep Neural Networks
title_full Human Activity Recognition Using Graph Structures and Deep Neural Networks
title_fullStr Human Activity Recognition Using Graph Structures and Deep Neural Networks
title_full_unstemmed Human Activity Recognition Using Graph Structures and Deep Neural Networks
title_short Human Activity Recognition Using Graph Structures and Deep Neural Networks
title_sort human activity recognition using graph structures and deep neural networks
topic human activity recognition (HAR)
deep learning
firefly optimization algorithm
graph-based models
spatial–temporal analysis
url https://www.mdpi.com/2073-431X/14/1/9
work_keys_str_mv AT abedalraoofkbsoul humanactivityrecognitionusinggraphstructuresanddeepneuralnetworks