ALGABRI REDHWAN

Redhwan Algabri received the B.Eng., the M.Eng., and Ph.D. degrees in mechanical engineering in 2011, 2015, and 2022 from Al-Baath University, Syria, Cairo University, Egypt, and Sungkyunkwan University, South Korea, respectively. He is currently working as a Research Assistant Professor at Hanyang University in South Korea. His research interests in machine & deep learning and intelligent robotics include person tracking and identification for mobile robots.

Scopus Publications

Human and environmental feature-driven neural network for path-constrained robot navigation using deep reinforcement learning
Nabih Pico, Estrella Montero, Alisher Amirbek, Eugene Auh, Jeongmin Jeon, Manuel S. Alvarez-Alvarado, Babar Jamil, Redhwan Algabri, and Hyungpil Moon
Elsevier BV



An Open-Source 3D Printed Three-Fingered Robotic Gripper for Adaptable and Effective Grasping
Francisco Yumbla, Emiliano Quinones Yumbla, Erick Mendoza, Cristobal Lara, Javier Pagalo, Efraín Terán, Redhwan Algabri, Myeongyun Doh, Tuan Luong, and Hyungpil Moon
MDPI AG
This research focuses on the design of a three-finger adaptive gripper using additive manufacturing and electromechanical actuators, with the purpose of providing a low-cost, efficient, and reliable solution for easy integration with any robot arm for industrial and research purposes. During the development phase, 3D printing materials were employed in the gripper’s design, with Polylactic Acid (PLA) filament used for the rigid mechanical components and Thermoplastic Polyurethane (TPU) for the flexible membranes that distribute pressure to the resistive force sensors. Stress analysis and simulations were conducted to evaluate the performance of the components under load and to gradually refine the design of the adaptive gripper. It was ensured that the mechanism could integrate effectively with the robotic arm and be precisely controlled through a PID controller. Furthermore, the availability of spare parts in the local market was considered essential to guarantee easy and cost-effective maintenance. Tests were conducted on an actual robotic arm, and the designed gripper was able to effectively grasp objects such as a soda can and a pencil. The results demonstrated that the adaptive gripper successfully achieved various types of grasping, offering a scalable and economical solution that represents a significant contribution to the field of robotic manipulation in industrial applications.


Cross-project software defect prediction based on the reduction and hybridization of software metrics
Ahmed Abdu, Zhengjun Zhai, Hakim A. Abdo, Sungon Lee, Mohammed A. Al-masni, Yeong Hyeon Gu, and Redhwan Algabri
Elsevier BV



Semantic and traditional feature fusion for software defect prediction using hybrid deep learning model
Ahmed Abdu, Zhengjun Zhai, Hakim A. Abdo, Redhwan Algabri, Mohammed A. Al-masni, Mannan Saeed Muhammad, and Yeong Hyeon Gu
Springer Science and Business Media LLC
AbstractSoftware defect prediction aims to find a reliable method for predicting defects in a particular software project and assisting software engineers in allocating limited resources to release high-quality software products. While most earlier research has concentrated on employing traditional features, current methodologies are increasingly directed toward extracting semantic features from source code. Traditional features often fall short in identifying semantic differences within programs, differences that are essential for the development of reliable and effective prediction models. In contrast, semantic features cannot present statistical metrics about the source code, such as the code size and complexity. Thus, using only one kind of feature negatively affects prediction performance. To bridge the gap between the traditional and semantic features, we propose a novel defect prediction model that integrates traditional and semantic features using a hybrid deep learning approach to address this limitation. Specifically, our model employs a hybrid CNN-MLP classifier: the convolutional neural network (CNN) processes semantic features extracted from projects’ abstract syntax trees (ASTs) using Word2vec. In contrast, the traditional features extracted from the dataset repository are processed by a multilayer perceptron (MLP). Outputs of CNN and MLP are then integrated and fed into a fully connected layer for defect prediction. Extensive experiments are conducted on various open-source projects to validate CNN-MLP’s effectiveness. Experimental results indicate that CNN-MLP can significantly enhance defect prediction performance. Furthermore, CNN-MLP’s improvements outperform existing methods in non-effort-aware and effort-aware cases.


Deep learning and machine learning techniques for head pose estimation: a survey
Redhwan Algabri, Ahmed Abdu, and Sungon Lee
Springer Science and Business Media LLC



Software Defect Prediction Based on Deep Representation Learning of Source Code From Contextual Syntax and Semantic Graph
Ahmed Abdu, Zhengjun Zhai, Hakim A. Abdo, and Redhwan Algabri
Institute of Electrical and Electronics Engineers (IEEE)



Real-time 6DoF full-range markerless head pose estimation[Formula presented]
Redhwan Algabri, Hyunsoo Shin, and Sungon Lee
Elsevier BV



Development of an artificial intelligence-PLC temperature controller for a cement factory for decreasing contamination
Riyadh Nazar Ali Algburi, Hakim S. Sultan Aljibori, Zaid Al-Huda, Khalid M. Sowoud, Redhwan Algabri, and Mugahed A. Al-Antari
IEEE
In this study, temperature control of the cooling tower (CT) system is developed and implemented using fuzzy-programmable logic controller (PLC) control technology to improve electric static precipitator (ESP) performance, output, and quality while minimizing losses within the CT in the cement plant. This method makes use of the fuzzy logic controller and integrates it into the PLC. The valve system is programmed to avoid the “wet bottom” phenomenon in the CT. A fuzzy valve controller is intended to solve the problem of opening and closing the valve in the return line at the appropriate time in order to regulate the temperature of the CT. A SIMULINK PLC coder converts the program from MATLAB to structured text language (STL). STL is a functional expression that improves the efficiency of the PLC-1200 work system. The amount of dust and flue gas emitted by the particulate control system is measured using continuous emission monitoring systems. The results show a significant improvement in ESP quality following the implementation of fuzzy control temperatures for the CT, which reduced dust emissions from the cement plant by 10% when compared to the traditional operator. This improved monitoring system detects sudden temperature changes and reduces dust emissions to improve cement production.


SSA-Sparse MHD: Singular Spectrum Analysis Paired with Sparse Maximum Harmonics Deconvolution for Detecting Feeble Defect Signals in Industrial Robots
Riyadh Nazar Ali Algburi, Hakim S. Sultan Aljibori, Zaid Al-Huda, Khalid M. Sowoud, Redhwan Algabri, and Mugahed A. Al-Antari
IEEE
This paper introduces a novel methodology for fault diagnosis in industrial robots, utilizing a combination of Single Spectrum Analysis (SSA) and Sparse Maximum Harmonics-Noise-Ratio Deconvolution (SMHD). The SSA technique is employed to decompose rotary encoder signals into their fundamental components: residual signals, periodic oscillations, and trends. Given that trends and oscillations represent monotonous waves, they are excluded from further analysis. Instead, the residual signal is processed using SMHD, which is an innovation inspired by the Minimum Entropy Deconvolution (MED) approach. This technique employs a new indicator as the objective function, iteratively choosing a Finite Impulse Response (FIR) filter to optimize the Harmonics-Noise Ratio (HNR) of the filtered signal. The proposed approach is designed to detect the flaw duration by computing the HNR of the signal’s envelope. During the iterative process, the fault period can be dynamically refined based on the HNR measurements of the envelope of the continuously updated filtered signal, particularly when the flaw duration is uncertain or challenging to estimate accurately. If an exact fault period is known, it simplifies the process by eliminating the need for estimation and refinement, repeatedly applying the known period in each iteration. A sparse parameter is also implemented to reduce chaos and enhance signal-to-noise ratio (SNR) after each filtering stage. Consequently, the method delineated herein advances as a feature-enhancement technique that does not require prior knowledge, offering substantial benefits and wider applicability compared to traditional method such as the Maximum Correlated Kurtosis Deconvolution (MCKD).


HHLP-SSA: Enhanced Fault Diagnosis in Industrial Robots Using Hierarchical Hyper-Laplacian Prior and Singular Spectrum Analysis
Riyadh Nazar Ali Algburi, Hakim S. Sultan Aljibori, Zaid Al-Huda, Khalid M. Sowoud, Redhwan Algabri, and Mugahed A. Al-Antari
IEEE
In industrial applications, the reliability of robots is paramount, necessitating efficient fault diagnosis systems. This research presents a novel fault diagnosis approach combining hierarchical hyper-Laplacian prior (HHLP) with singular spectrum analysis (SSA) for analyzing rotary encoder signals in industrial robots. The SSA method decomposes the encoder signals into residual, periodic oscillations, and trend components. The HHLP algorithm identifies harmonic interference, periodic impulse disturbances, and noise, optimized to maximize posterior probability for accurate detection. The proposed method demonstrates superior performance compared to traditional Laplacian prior models, emphasizing the effectiveness of HHLP in fault feature extraction. Experimental applications validate the SSAHHLP method’s efficacy. The study compares the results with spectral kurtosis and minimax concave regularization, confirming the SSA-HHLP method’s robustness and accuracy.


Head Pose Estimation Based on 5D Rotation Representation
Redhwan Algabri and Sungon Lee
IEEE
Head pose estimation (HPE) is a crucial problem in computer vision, as it significantly enhances the performance of face-related tasks involving a frontal view. However, recent applications demand head analysis across the entire 360° range, which poses significant challenges. This paper introduces an end-to-end method for an HPE task. We propose a continuous 5D rotation representation to address the challenge of discontinuous rotation called 5DResNet, which enables robust and efficient direct regression of the head pose. The proposed method adopted the inverse of the stereographic projection (ISP) with the Gram-Schmidt mapping to orthogonalization procedure in the network. This approach allows our model to learn the full-range angles, exceeding the abilities of most previous techniques that confine pose estimation to a limited angle range to achieve acceptable results. Furthermore, we present an ablation study to gain a deeper understanding of the factors influencing the performance of our method. Our proposed approach demonstrates notable competition over other state-of-the-art methods in comprehensive experiments conducted on the publicly available Carnegie Mellon University (CMU) dataset, which achieved error rates of 5.97° and 6.64° for narrow and full-range angles, respectively.


Graph-Based Feature Learning for Cross-Project Software Defect Prediction
Ahmed Abdu, Zhengjun Zhai, Hakim A. Abdo, Redhwan Algabri, and Sungon Lee
Computers, Materials and Continua (Tech Science Press)



Online Boosting-Based Target Identification among Similar Appearance for Person-Following Robots
Redhwan Algabri and Mun-Taek Choi
MDPI AG
It is challenging for a mobile robot to follow a specific target person in a dynamic environment, comprising people wearing similar-colored clothes and having the same or similar height. This study describes a novel framework for a person identification model that identifies a target person by merging multiple features into a single joint feature online. The proposed framework exploits the deep learning output to extract four features for tracking the target person without prior knowledge making it generalizable and more robust. A modified intersection over union between the current frame and the last frame is proposed as a feature to distinguish people, in addition to color, height, and location. To improve the performance of target identification in a dynamic environment, an online boosting method was adapted by continuously updating the features in every frame. Through extensive real-life experiments, the effectiveness of the proposed method was demonstrated by showing experimental results that it outperformed the previous methods.


Deep Learning-Based Software Defect Prediction via Semantic Key Features of Source Code—Systematic Survey
Ahmed Abdu, Zhengjun Zhai, Redhwan Algabri, Hakim A. Abdo, Kotiba Hamad, and Mugahed A. Al-antari
MDPI AG
Software defect prediction (SDP) methodology could enhance software’s reliability through predicting any suspicious defects in its source code. However, developing defect prediction models is a difficult task, as has been demonstrated recently. Several research techniques have been proposed over time to predict source code defects. However, most of the previous studies focus on conventional feature extraction and modeling. Such traditional methodologies often fail to find the contextual information of the source code files, which is necessary for building reliable prediction deep learning models. Alternatively, the semantic feature strategies of defect prediction have recently evolved and developed. Such strategies could automatically extract the contextual information from the source code files and use them to directly predict the suspicious defects. In this study, a comprehensive survey is conducted to systematically show recent software defect prediction techniques based on the source code’s key features. The most recent studies on this topic are critically reviewed through analyzing the semantic feature methods based on the source codes, the domain’s critical problems and challenges are described, and the recent and current progress in this domain are discussed. Such a comprehensive survey could enable research communities to identify the current challenges and future research directions. An in-depth literature review of 283 articles on software defect prediction and related work was performed, of which 90 are referenced.


Target recovery for robust deep learning-based person following in mobile robots: Online trajectory prediction
Redhwan Algabri and Mun-Taek Choi
MDPI AG
The ability to predict a person’s trajectory and recover a target person in the event the target moves out of the field of view of the robot’s camera is an important requirement for mobile robots designed to follow a specific person in the workspace. This paper describes an extended work of an online learning framework for trajectory prediction and recovery, integrated with a deep learning-based person-following system. The proposed framework first detects and tracks persons in real time using the single-shot multibox detector deep neural network. It then estimates the real-world positions of the persons by using a point cloud and identifies the target person to be followed by extracting the clothes color using the hue-saturation-value model. The framework allows the robot to learn online the target trajectory prediction according to the historical path of the target person. The global and local path planners create robot trajectories that follow the target while avoiding static and dynamic obstacles, all of which are elaborately designed in the state machine control. We conducted intensive experiments in a realistic environment with multiple people and sharp corners behind which the target person may quickly disappear. The experimental results demonstrated the effectiveness and practicability of the proposed framework in the given environment.


Robust Person Following under Severe Indoor Illumination Changes for Mobile Robots: Online Color-Based Identification Update
Redhwan Algabri and Mun-Taek Choi
IEEE
Tracking a specific person in environments with non-uniform illumination is a difficult task for mobile robots. Image information such as color is essential to identify a target person. However, the information is not reliable under severe illumination changes unless the system can accommodate these changes over time. In this paper, we propose a robust identifier that has been combined with a deep learning technique to accommodate varying illumination in the ambient lighting of a scene. Moreover, an enhanced online update strategy for the person identification model is used to deal with the challenge of drifting the target person's appearance changes during tracking. Using the proposed method, the system achieves a successfully tracked rate above 90% on real-world video sequences in which variations in illumination are dominant. We confirmed the effectiveness of the proposed method through target-following experiments using five different clothing colors in a real indoor environment where the lighting conditions change extremely.


Deep-learning-based indoor human following of mobile robot using color feature
Redhwan Algabri and Mun-Taek Choi
MDPI AG
Human following is one of the fundamental functions in human–robot interaction for mobile robots. This paper shows a novel framework with state-machine control in which the robot tracks the target person in occlusion and illumination changes, as well as navigates with obstacle avoidance while following the target to the destination. People are detected and tracked using a deep learning algorithm, called Single Shot MultiBox Detector, and the target person is identified by extracting the color feature using the hue-saturation-value histogram. The robot follows the target safely to the destination using a simultaneous localization and mapping algorithm with the LIDAR sensor for obstacle avoidance. We performed intensive experiments on our human following approach in an indoor environment with multiple people and moderate illumination changes. Experimental results indicated that the robot followed the target well to the destination, showing the effectiveness and practicability of our proposed system in the given environment.

RECENT SCHOLAR PUBLICATIONS

Human and environmental feature-driven neural network for path-constrained robot navigation using deep reinforcement learning
N Pico, E Montero, A Amirbek, E Auh, J Jeon, MS Alvarez-Alvarado, ...
Engineering Science and Technology, an International Journal 64, 101993 2025



An Open-Source 3D Printed Three-Fingered Robotic Gripper for Adaptable and Effective Grasping
F Yumbla, EQ Yumbla, E Mendoza, C Lara, J Pagalo, E Tern, R Algabri, ...
Biomimetics 10 (1), 26 2025



Cross-project software defect prediction based on the reduction and hybridization of software metrics
A Abdu, Z Zhai, HA Abdo, S Lee, MA Al-masni, YH Gu, R Algabri
Alexandria Engineering Journal 112, 161-176 2025



2024 Index IEEE Transactions on Reliability Vol. 73
HA Abdo, A Abdu, D Agiakatsikas, Y Ait-Ameur, R Al Kontar, R Algabri, ...
IEEE Transactions on Reliability 73 (4) 2024



HHLP-SSA: Enhanced Fault Diagnosis in Industrial Robots Using Hierarchical Hyper-Laplacian Prior and Singular Spectrum Analysis
RNA Algburi, HSS Aljibori, Z Al-Huda, KM Sowoud, R Algabri, ...
2024 8th International Artificial Intelligence and Data Processing Symposium 2024



Development of an artificial intelligence-PLC temperature controller for a cement factory for decreasing contamination
RNA Algburi, HSS Aljibori, Z Al-Huda, KM Sowoud, R Algabri, ...
2024 8th International Artificial Intelligence and Data Processing Symposium 2024



SSA-Sparse MHD: Singular Spectrum Analysis Paired with Sparse Maximum Harmonics Deconvolution for Detecting Feeble Defect Signals in Industrial Robots
RNA Algburi, HSS Aljibori, Z Al-Huda, KM Sowoud, R Algabri, ...
2024 8th International Artificial Intelligence and Data Processing Symposium 2024



Deep learning and machine learning techniques for head pose estimation: a survey
R Algabri, A Abdu, S Lee
Artificial Intelligence Review 57 (10), 288 2024



Head pose estimation based on 5d rotation representation
R Algabri, S Lee
2024 IEEE Symposium on Wireless Technology & Applications (ISWTA), 195-199 2024



Semantic and traditional feature fusion for software defect prediction using hybrid deep learning model
A Abdu, Z Zhai, HA Abdo, R Algabri, MA Al-Masni, MS Muhammad, ...
Scientific Reports 14 (1), 14771 2024



Real-time 6dof full-range markerless head pose estimation
R Algabri, H Shin, S Lee
Expert Systems with Applications 239, 122293 2024



Software defect prediction based on deep representation learning of source code from contextual syntax and semantic graph
A Abdu, Z Zhai, HA Abdo, R Algabri
IEEE Transactions on Reliability 73 (2), 820-834 2024



Graph-based feature learning for cross-project software defect prediction
A Abdu, Z Zhai, HA Abdo, R Algabri, S Lee
Computers, Materials and Continua 77 (1) 2023



Online boosting-based target identification among similar appearance for person-following robots
R Algabri, MT Choi
Sensors 22 (21), 8422 2022



Deep learning-based software defect prediction via semantic key features of source code—systematic survey
A Abdu, Z Zhai, R Algabri, HA Abdo, K Hamad, MA Al-antari
Mathematics 10 (17), 3120 2022



Robust person following under severe indoor illumination changes for mobile robots: online color-based identification update
R Algabri, MT Choi
2021 21st International Conference on Control, Automation and Systems (ICCAS 2021



Target recovery for robust deep learning-based person following in mobile robots: Online trajectory prediction
R Algabri, MT Choi
Applied Sciences 11 (9), 4165 2021



Deep-learning-based indoor human following of mobile robot using color feature
R Algabri, MT Choi
Sensors 20 (9), 2699 2020

MOST CITED SCHOLAR PUBLICATIONS

Deep-learning-based indoor human following of mobile robot using color feature
R Algabri, MT Choi
Sensors 20 (9), 2699 2020
Citations: 98



Target recovery for robust deep learning-based person following in mobile robots: Online trajectory prediction
R Algabri, MT Choi
Applied Sciences 11 (9), 4165 2021
Citations: 31



Deep learning-based software defect prediction via semantic key features of source code—systematic survey
A Abdu, Z Zhai, R Algabri, HA Abdo, K Hamad, MA Al-antari
Mathematics 10 (17), 3120 2022
Citations: 29



Software defect prediction based on deep representation learning of source code from contextual syntax and semantic graph
A Abdu, Z Zhai, HA Abdo, R Algabri
IEEE Transactions on Reliability 73 (2), 820-834 2024
Citations: 16



Real-time 6dof full-range markerless head pose estimation
R Algabri, H Shin, S Lee
Expert Systems with Applications 239, 122293 2024
Citations: 12



Robust person following under severe indoor illumination changes for mobile robots: online color-based identification update
R Algabri, MT Choi
2021 21st International Conference on Control, Automation and Systems (ICCAS 2021
Citations: 9



Semantic and traditional feature fusion for software defect prediction using hybrid deep learning model
A Abdu, Z Zhai, HA Abdo, R Algabri, MA Al-Masni, MS Muhammad, ...
Scientific Reports 14 (1), 14771 2024
Citations: 8



Graph-based feature learning for cross-project software defect prediction
A Abdu, Z Zhai, HA Abdo, R Algabri, S Lee
Computers, Materials and Continua 77 (1) 2023
Citations: 5



Online boosting-based target identification among similar appearance for person-following robots
R Algabri, MT Choi
Sensors 22 (21), 8422 2022
Citations: 5



Deep learning and machine learning techniques for head pose estimation: a survey
R Algabri, A Abdu, S Lee
Artificial Intelligence Review 57 (10), 288 2024
Citations: 3



Human and environmental feature-driven neural network for path-constrained robot navigation using deep reinforcement learning
N Pico, E Montero, A Amirbek, E Auh, J Jeon, MS Alvarez-Alvarado, ...
Engineering Science and Technology, an International Journal 64, 101993 2025
Citations: 1



Head pose estimation based on 5d rotation representation
R Algabri, S Lee
2024 IEEE Symposium on Wireless Technology & Applications (ISWTA), 195-199 2024
Citations: 1