TAQWA: Teaching Adolescents Quality Wadhu/Ablution Contactlessly Using Deep Learning

Hameed, H., Lubna, , Ghadban, N., Usman, M., Arshad, K., Assaleh, K., Alkhayyat, A., Imran, M. A. and Abbasi, Q. (2023) TAQWA: Teaching Adolescents Quality Wadhu/Ablution Contactlessly Using Deep Learning. In: 6th International Conference of Signal Processing and Intelligent Systems (ICSPIS'23), Dubai, United Arab Emirates, 8-9 Nov 2023, pp. 77-81. ISBN 9798350329599 (doi: 10.1109/ICSPIS60075.2023.10343835)

Abstract

This research presents a unique and innovative approach to teaching young children the proper steps of ablution (wazoo/wudu) by utilizing a non-invasive sensing system integrated with deep learning algorithms. However, most existing ablution detection systems rely on cameras, which raise privacy concerns, face challenges with lighting conditions, and require complex training with long video sequences. We conducted experiments with a group of youngsters to evaluate the system’s effectiveness, demonstrating its potential in fostering a deeper appreciation and comprehension of religious practices among young learners. This innovative privacy-preserving ablution system employs state-of-the-art UWB-radar technology with advanced Deep Learning (DL) techniques to effectively address the challenges mentioned above. The core focus of this system is to categorize the four fundamental ablution steps: Wash Face 3x, Wash Hand 3x, Wash Head 1x, and Wash Feet 3x. By transforming the collected data into spectrograms and harnessing the sophisticated DL models VGG16 and VGG19, the proposed system accurately detects these ablution steps, achieving an impressive maximum accuracy of 97.92% across all categories with the utilization of VGG16

• Item Type: Conference Proceedings
• Additional Information: This work is supported by EPSRC Grant No: EP/T021063/1 and AU internal research Grant No: 2022-IRG-ENIT-25.
• Keywords: RF sensing, micro-Doppler signatures, hand gesture, deep learning.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: -, Lubna and Imran, Professor Muhammad and Ghadban, Dr Nour and Abbasi, Professor Qammer and Hameed, Hira
• Authors: Hameed, H., Lubna, , Ghadban, N., Usman, M., Arshad, K., Assaleh, K., Alkhayyat, A., Imran, M. A., and Abbasi, Q.
• College/School: College of Science and Engineering; College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity; College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
• ISSN: 2831-3844
• ISBN: 9798350329599
• Copyright Holders: Copyright © 2023, IEEE
• First Published: First published in 2023 6th International Conference on Signal Processing and Information Security (ICSPIS)
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Organisation