Article
Computer Science, Artificial Intelligence
Zekeriya Katilmis, Cihan Karakuzu
Summary: Sign language is vital for the communication of hearing impaired individuals. This study focuses on recognizing two-handed dynamic words in Turkish Sign Language (TSL) using the LMC device. By repeating 26 dynamic words selected based on their similarities and differences, two data sets were extracted. A three-stage strategy comprising of data regularization, feature selection, and dimension reduction was applied to these feature sets to present word recognition performances from various aspects. The recognition performance was evaluated using six different ELM networks, and the most effective Meta-ELM classifier was identified.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Samah Abbas, Hassanin Al-Barhamtoshy, Fahad Alotaibi
Summary: Sign language is a common language used by deaf people for communication, but most ordinary people are not familiar with it, so technologies are needed to assist deaf people in daily communication. The paper focuses on the deaf community in Saudi Arabia, proposing a system that translates Arabic Sign Language into voice using natural language processing. Through dataset evaluation and expert assessment, good consistency was found in the Arabic Sign Language video corpus created by signers from different regions of Saudi Arabia.
PEERJ COMPUTER SCIENCE
(2021)
Article
Education & Educational Research
Doaa M. Elbourhamy, Hosnia M. Mohammdi
Summary: This paper proposes a new system for translating Arabic Sign Language (ArSL) using speech recognition and image translation methods. The system has a high translation accuracy and shows significant effectiveness in improving learning for Arab deaf students.
INTERACTIVE LEARNING ENVIRONMENTS
(2023)
Article
Engineering, Electrical & Electronic
Thiago Simoes Dias, Jose Jair Alves Mendes Junior, Sergio Francisco Pichorim
Summary: This paper presents the development and analysis of a system for Brazilian Sign Language (Libras) recognition, which includes an instrumented glove and an acquisition system. The glove is equipped with five flex sensors, an inertial sensor, and two contact sensors. Collected data from five volunteers performing gestures in Libras were segmented into three periods: construction period, alphabet gesture, and relaxation period. The alphabet gesture periods were further segmented and a classifier was designed to recognize the 26 letters. Different classifiers were used to classify the gestures and analyze the system in different scenarios. The highest accuracy of 96.15% was achieved using the Random Forest (RF) classifier for sensor group classification.
IEEE SENSORS JOURNAL
(2022)
Article
Computer Science, Information Systems
Mourad Brour, Abderrahim Benabbou
Summary: ATLASLang is a machine translation system translating Arabic text language into Arabic sign language, with the latest version implemented using neural network technology, which outperforms traditional rule-based approaches. Neuron network approaches have achieved notable results and are more effective compared to other classical methods.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2021)
Article
Multidisciplinary Sciences
Reem Aljuhani, Aseel Alfaidi, Bushra Alshehri, Hajer Alwadei, Eman Aldhahri, Nahla Aljojo
Summary: In this study, a convolutional neural network model is proposed to recognize Arabic alphabet signs in sign language. The experimental results show a recognition accuracy of 94.46%, outperforming previous studies in terms of recognition accuracy.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Ala Addin Sidig, Hamzah Luqman, Sabri Mahmoud, Mohamed Mohandes
Summary: Sign language is the primary mode of communication for the deaf community. Arabic Sign language is utilized in Arab countries, with the development of a benchmarking database like KArSL Database to aid in automatic recognition. Different recognition approaches, including HMM, deep learning image classification, and attention-based captioning systems, have shown promising results for recognizing a large number of Arabic signs.
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
(2021)
Article
Computer Science, Information Systems
Hamzah Luqman, El-Sayed M. El-Alfy
Summary: Sign languages serve as the main visual communication medium between hard-hearing people and their societies. Arabic sign language, like other sign languages, is gaining increasing attention in the research community. The current focus of sign language recognition systems on manual gestures neglects non-manual information, such as facial expressions, leading to challenges in dataset availability and system accuracy improvements.
Article
Computer Science, Information Systems
Muhammad Saad Amin, Syed Tahir Hussain Rizvi, Alessandro Mazzei, Luca Anselma
Summary: Sign language recognition is a challenging task, and researchers have designed smart prototypes using sensor-based, vision-based, and hybrid approaches. The authors of this paper developed sensor-based assistive gloves to capture sign gestures for alphabet and digits, and achieved successful recognition of static gestures.
Article
Computer Science, Artificial Intelligence
Aziz Qaroush, Sara Yassin, Ali Al-Nubani, Ameer Alqam
Summary: An automatic sign language recognition system for Arabic Sign Language is presented in this paper, utilizing information fusion from IMUs sensors and featuring a glove with sensors and a mobile software module. The system achieved high recognition accuracy in experiments, outperforming existing systems for alphabet-level gesture recognition.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Mohammad A. Alzubaidi, Mwaffaq Otoom, Areen M. Abu Rwaq
Summary: This article describes a research aimed at providing an assistive device for people with speech disorders to communicate with others by translating their gestures into spoken voice. The proposed device includes an electronic glove worn on the hand to monitor hand orientation and movement, and an Arduino board to process the signals and voice the meaning of each gesture using audio streams.
ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING
(2023)
Article
Computer Science, Information Systems
Chenghong Lu, Shingo Amino, Lei Jing
Summary: There are communication barriers between hearing-impaired people and hearing people due to difficulties in written communication and understanding sign language. To address this issue, a Sign-Glove system was developed using bend and inertial sensors to recognize hand shape and motion for more comprehensive sign language recognition. A weighted DTW fusion multi-sensor algorithm was created to improve recognition by combining shape and movement, considering the contribution of each sensor. Interfaces were also designed to display the meaning of sign language words, and the system's accuracy and recognition rate were evaluated.
Review
Psychology, Multidisciplinary
Cornelia Loos, Austin German, Richard P. P. Meier
Summary: The visual-gestural modality allows users to simultaneously move multiple independent articulators, enabling simultaneous encoding of information. This paper discusses the simultaneous encoding in emerging and established sign languages, as well as unexpected sequential phenomena. It also explores potential constraints on simultaneity in cognition and motor coordination that may affect the acquisition and use of simultaneous structures.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Information Systems
Mostafa Magdy Balaha, Sara El-Kady, Hossam Magdy Balaha, Mohamed Salama, Eslam Emad, Muhammed Hassan, Mahmoud M. Saafan
Summary: According to WHO, more than 5% of people worldwide are deaf and struggle to communicate with non-deaf individuals. Sign Language Recognition (SLR) studies aim to bridge this gap by replacing the need for interpreters. However, existing sign recognition systems face challenges such as low accuracy and complex gestures. This study presents a dataset of 20 Arabic words and proposes a deep learning architecture combining CNN and RNN, achieving high accuracy rates.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Sara Askari Khomami, Sina Shamekhi
Summary: A wearable device using sEMG and IMU sensors was designed to improve accuracy in sign language recognition. Through experiments on PSL signs and efficient classification methods, the proposed system demonstrated a high average accuracy of 96.13%.
Article
Computer Science, Information Systems
Gamil Ahmed, Tarek Sheltami, Mohamed Deriche, Ansar Yasar
Summary: Internet of Drones (IoD) formation offers diverse applications in military and civilian environments. A critical challenge in IoD missions is avoiding obstacles, and this paper presents an energy-efficient strategy to ensure drones reach their destinations safely by avoiding static and dynamic collisions. The proposed algorithm allows drones to hover, backtrack, or fly vertically, and has been validated for high collision risk in a dense environment with obstacle relative speeds up to 10 meters/sec.
Article
Geochemistry & Geophysics
Bo Liu, Mohamed Mohandes, Huijian Li, Xu Liu, Ali Al-Shaikhi, Ling Zhao
Summary: A novel abrupt-jump detection algorithm for seismic signal deconvolution is developed in this work, which significantly suppresses the effect of sidelobes by modifying likelihood ratios. The proposed method enhances the resolution of reflectivity impulses recovered from seismic traces and proves to be efficient and practical in enhancing the signal quality of seismograms.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Farouq Aliyu, Tarek Sheltami, Mohamed Deriche, Nidal Nasser
Summary: In this paper, a lightweight intrusion detection system (IDS) for fog computing is proposed, which achieves low resource overhead and reduces energy consumption by distributing the functions among fog nodes and the cloud.
JOURNAL OF NETWORK AND SYSTEMS MANAGEMENT
(2022)
Article
Automation & Control Systems
Bo Liu, Mohamed Mohandes, Hilal Nuha, Mohamed Deriche, Faramarz Fekri, James H. McClellan
Summary: This paper proposes a model-based compression scheme for seismic data, modeling seismic traces as multitone sinusoidal waves and utilizing a parameter estimation algorithm for compression. Experimental results demonstrate that the proposed scheme outperforms traditional linear predictive coding algorithm and distributed principal component analysis algorithm.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Multidisciplinary Sciences
Mohammad Amin Akbari, Mohsen Zare, Rasoul Azizipanah-abarghooee, Seyedali Mirjalili, Mohamed Deriche
Summary: Motivated by cheetah hunting strategies, this paper proposes a nature-inspired algorithm called the cheetah optimizer (CO), which is shown to outperform other algorithms in extensive testing on benchmark functions and engineering problems.
SCIENTIFIC REPORTS
(2022)
Article
Automation & Control Systems
Bo Liu, Mohamed Mohandes, Huijian Li, Ali Al-Shaikhi, Xu Liu, Ling Zhao
Summary: This article proposes a likelihood-ratio-based method for recovering sparse reflectivity series from noisy seismic signals. The method is adaptive to the variance of the observational noise, enhancing the robustness of reflectivity series recovery. Experimental results verify the reliability of the proposed method.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Energy & Fuels
Mohana Alanazi, Abdulaziz Alanazi, Mohammad Amin Akbari, Mohamed Deriche, Zulfiqar Ali Memon
Summary: This paper presents new and efficient topology-variable-based linear expressions that can evaluate the reliability indices of practical radial distribution networks, considering the inclusion of renewable distributed generation units. The proposed model can be used in various optimization models to operate and plan distribution networks with reliability concerns, and it shows accuracy and computational effectiveness compared to conventional simulation-based approaches.
Article
Multidisciplinary Sciences
Naveed Iqbal, Mohamed Deriche, Ghassan AlRegib, Sikandar Khan
Summary: Distributed acoustic sensing (DAS) is a new seismic monitoring technology that generates a large amount of data. This paper proposes a denoising method based on a combination of the curvelet transform and a whitening filter, as well as a procedure for estimating noise variance to process the raw seismic data. Experimental results demonstrate that the proposed algorithm achieves the best results under various types of noise.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Ali Al-Shaikhi, Hilal H. Nuha, Abdulmajid Lawal, Shafiqur Rehman, Mohamed Mohandes
Summary: This paper examines the use of CNN-BLSTM to estimate wind speed at different heights based on measurements at lower heights. The extrapolated values obtained using this method are compared with LiDAR reference system-based measurements, and the comparison shows that CNN-BLSTM performs better than other methods with a coefficient of determination of 69.13%.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Information Systems
Habes Alkhraisat, Lamees Mohammad Dalbah, Mohammed Azmi Al-Betar, Mohammed A. A. Awadallah, Khaled Assaleh, Mohamed Deriche
Summary: The problem of truss structure optimization is important in civil engineering applications. This study utilizes a modified Grey Wolf Optimizer (GWOM) with varying mutation operators to solve the size optimization problem in truss structures. The results show that the proposed optimizer outperforms other methods and is suitable for optimization problems in truss structures.
Article
Multidisciplinary Sciences
Mohammed Samara, Mohamed Deriche, Jihad Al-Sadah, Yahya Osais
Summary: This paper presents a proof-of-concept design of a real-time embedded system that can help the visually impaired recognize colors using synthesized sound signals. The experiments confirm that the system is efficient in terms of training time and achieves high accuracy in color detection. It is also cost-effective and robust.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Shafiqur Rehman, Kashif Irshad, Nasiru I. Ibrahim, Ali Alshaikhi, Mohamed A. Mohandes
Summary: This study assesses offshore wind power resources in selected locations in the Gulf of North Suez and recommends L1, L3, and L2 as suitable sites for wind farm development. These locations have favorable wind sources, as indicated by high wind power density, wind variability, and windy site identifier indices.
Article
Computer Science, Information Systems
Mustafa Alfarhan, Mohamed Deriche, Ahmed Maalej
Summary: In this paper, a novel semantic segmentation model is proposed for accurate identification of salt domes and faults in seismic data. The model achieves high detection accuracy through the use of an improved encoder-decoder deep neural network, transfer learning, and residual blocks. Extensive experiments conducted on real-world seismic data confirm the superior performance of the proposed model for multiple events detection in subsurface surveys.
Article
Multidisciplinary Sciences
J. P. Rojas, M. U. Rehman, A. Hussein, A. E'mar, Y. AlRaei, H. AlZaher, M. Mohandes
Summary: This paper presents a novel wearable crowd monitoring system, which is characterized by its simple manufacturing process and strong wearability. The system has been successfully tested in Makkah city.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)
Proceedings Paper
Engineering, Electrical & Electronic
Ali M. Almohammedi, Mohamed Deriche
Summary: The study developed a multitask network version of ILMS over WSN using CDMA to extract tasks, and introduced CTA and ATC methods for data exchange and performance enhancement. Simulation results showed that CTA and ATC approaches improved performance by 2.6 dB and 3.8 dB compared to ILMS CDMA.
2021 4TH INTERNATIONAL SYMPOSIUM ON ADVANCED ELECTRICAL AND COMMUNICATION TECHNOLOGIES (ISAECT)
(2021)