Zagazig University Digital Repository
Home
Thesis & Publications
All Contents
Publications
Thesis
Graduation Projects
Research Area
Research Area Reports
Search by Research Area
Universities Thesis
ACADEMIC Links
ACADEMIC RESEARCH
Zagazig University Authors
Africa Research Statistics
Google Scholar
Research Gate
Researcher ID
CrossRef
Multi-ResAtt: Multilevel Residual Network With Attention for Human Activity Recognition Using Wearable Sensors
Faculty
Science
Year:
2022
Type of Publication:
ZU Hosted
Pages:
Authors:
Mohamed El Sayed Ahmed Muhamed
Staff Zu Site
Abstract In Staff Site
Journal:
IEEE Transactions on Industrial Informatics IEEE
Volume:
Keywords :
Multi-ResAtt: Multilevel Residual Network With Attention
Abstract:
Human activity recognition (HAR) applications have received much attention due to their necessary implementations in various domains, including industry 5.0 applications such as smart homes, e-health, and various Internet of things (IoT) applications. Deep learning techniques have shown impressive performance in different classification tasks, including HAR. Accordingly, in this paper, we develop a comprehensive HAR system based on a novel deep learning architecture called Multi-ResAtt (Multilevel residual network with attention). This model incorporates initial blocks and residual modules aligned in parallel. Multi-ResAtt learns data representations on the Inertial Measurement Units (IMUs) level. Multi-ResAtt integrates a recurrent neural network (RNN) with attention to extract time-series features and perform activity recognition. We consider complex human activities collected from wearable sensors to evaluate the Multi-ResAtt using three public datasets, Opportunity, UniMiB-SHAR, and PAMAP2. Additionally, we compare the proposed Multi-ResAtt to several deep learning models and existing HAR systems, and it achieved significant performance.
Author Related Publications
Mohamed El Sayed Ahmed Muhamed, "A Grunwald–Letnikov based Manta ray foraging optimizer for global optimization and image segmentation", Elsevier, 2020
More
Mohamed El Sayed Ahmed Muhamed, "A novel hybrid gradient-based optimizer and grey wolf optimizer feature selection method for human activity recognition using smartphone sensors", MDPI, 2021
More
Mohamed El Sayed Ahmed Muhamed, "Efficient schemes for playout latency reduction in P2P-VOD systems", Springer, 2018
More
Mohamed El Sayed Ahmed Muhamed, "a novel algorithm for source localization based on nonnegative matrix factroization using \alpha 'beta divergence in chochleagram", WSEAS, 2013
More
Mohamed El Sayed Ahmed Muhamed, "Open cluster membership probability based on K-means clustering algorithm", Springer, 2016
More
Department Related Publications
Mira Magdy Sobhy Suliman, "COMPARISON BETWEEN HAAR WAVELET TRANSFORM, DCT AND A PROPOSED COLUMN-MEAN-METHOD BASED IRIS ENCODERS", جامعة الزقازيق-المجلة العلمية, 2014
More
Mohammed Atef Meselhy AbdulHamid, "Hybrid Named Entity Recognition - Application to Arabic Language", IEEE, 2015
More
Mohammed Nour Abdelgawad Ahmed, "Using Industrial Actuators for Rapid Development of Electric Car Applications", WFB Wirtschaftsförderung Bremen, 2014
More
Mohammed Nour Abdelgawad Ahmed, "A simulation-based design of extraterrestrial six-legged robot system", IEEE, 2009
More
Sanaa Fekry Abdelsadek Hassanien Marzok, "Supervised Classification of Cancers Based on Copy Number Variation", Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2018, 2018
More
جامعة المنصورة
جامعة الاسكندرية
جامعة القاهرة
جامعة سوهاج
جامعة الفيوم
جامعة بنها
جامعة دمياط
جامعة بورسعيد
جامعة حلوان
جامعة السويس
شراقوة
جامعة المنيا
جامعة دمنهور
جامعة المنوفية
جامعة أسوان
جامعة جنوب الوادى
جامعة قناة السويس
جامعة عين شمس
جامعة أسيوط
جامعة كفر الشيخ
جامعة السادات
جامعة طنطا
جامعة بنى سويف