IoT-Based Multisensors Fusion for Activity Recognition via Key Features and Hybrid Transfer Learning
IEEE Access · 2025 · 13 · 14727-14742
DOI: 10.1109/access.2024.3524431 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Ahmad Jalal und 6 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 142 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah bint Abdulrahman University Researchers, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
Abstract (Originalsprache)
Human activity recognition (HAR) has attracted significant attention in various fields, including healthcare, smart homes, and human-computer interaction. Accurate HAR can enhance user experience, provide critical health insights, and enable sophisticated context-aware applications. This paper presents a comprehensive system for HAR utilizing both RGB videos and inertial measurement unit (IMU) sensor data. The system employs a multi-stage processing pipeline involving preprocessing, segmentation, feature extraction, and classification to achieve high accuracy in activity recognition. In the preprocessing stage, frames are extracted from RGB videos, and IMU sensor data undergoes denoising. The segmentation phase applies Naive Bayes segmentation for video frames and Hamming windows for sensor data to prepare them for feature extraction. Key features are extracted using techniques such as ORB (Oriented FAST and Rotated BRIEF), MSER (Maximally Stable Extremal Regions), DFT (Discrete Fourier Transform), and KAZE for image data, and LPCC (Linear Predictive Cepstral Coefficients), PSD (Power Spectral Density), AR Coefficient, and entropy for sensor data. Feature fusion is performed using Linear Discriminant Analysis (LDA) to create a unified feature set, which is then classified using ResNet50 (Residual Neural Network) to recognize activities such as using a smartphone, cooking, and reading a newspaper. The system was evaluated using the LARa and HWU-USP datasets, achieving classification accuracies of 92% and 93%, respectively. These results demonstrate the robustness and effectiveness of the proposed HAR system in diverse scenarios.
Förderung
- Princess Nourah bint Abdulrahman University Researchers
- Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
Zitieren
APA
Jalal, A., Khan, D., Sadiq, T., Alotaibi, M., Alotaibi, S. R., Aljuaid, H., & Rahman, H. (2025). IoT-Based Multisensors Fusion for Activity Recognition via Key Features and Hybrid Transfer Learning. IEEE Access, 13, 14727-14742. https://doi.org/10.1109/access.2024.3524431
Vancouver
Jalal A, Khan D, Sadiq T, Alotaibi M, Alotaibi SR, Aljuaid H, et al. IoT-Based Multisensors Fusion for Activity Recognition via Key Features and Hybrid Transfer Learning. IEEE Access. 2025;13:14727-14742. doi:10.1109/access.2024.3524431
BibTeX
@article{Jalal2025,
author = {Jalal, Ahmad and Khan, Danyal and Sadiq, Touseef and Alotaibi, Moneerah and Alotaibi, Sultan Refa and Aljuaid, Hanan and Rahman, Hameedur},
title = {IoT-Based Multisensors Fusion for Activity Recognition via Key Features and Hybrid Transfer Learning},
journal = {IEEE Access},
year = {2025},
volume = {13},
pages = {14727--14742},
doi = {10.1109/access.2024.3524431}
}
EUVIMED