Salah Al-Darraji

@uobasrah.edu.iq

Head of Computer Science Department/ College of Computer Science and Information Technology
University of Basrah

Salah Al-Darraji


                     Download Compact PDF  
https://researchid.co/salahflaih

RESEARCH, TEACHING, or OTHER INTERESTS

Artificial Intelligence, Computer Vision and Pattern Recognition
26

Scopus Publications

302

Scholar Citations

9

Scholar h-index

8

Scholar i10-index

Scopus Publications

  • A Hybrid Approach Using Vector Field Histogram and Deep Reinforcement Learning for Dynamic Path Planning
    Maysam Hameed Qasim, Salah Al-Darraji
    Iraqi Journal for Electrical and Electronic Engineering, 2026
    Autonomous mobile robots (AMRs) are becoming increasingly important in different domains such as healthcare, warehouse automation and household duties, but still encounter problems when it comes to moving around unfamiliar and dynamic environments. This study proposes an advanced robotic navigation system which combines the Soft Actor-Critic (SAC) approach and Vector Field Histogram (VFH) for path planning and avoidance obstacles in completely unknown environments. This system leverages the strengths of deep reinforcement learning and real-time obstacle detection to achieve robust and efficient navigation in certain scenarios. The SAC strategy optimizes robot navigation using policy networks and Q-networks, while the VFH method addresses obstacle avoidance by sensor data processing and dynamically adjusting the robot’s angular velocity to avoid collision. For testing and implementing this system, Gazebo simulation and Robot Operating System (ROS) are used. Experimental results demonstrated that the proposed method outperformed the standard technique and achieved a high success rate in path planning and obstacles avoidance.
  • ATTENTION-DRIVEN CNN-LSTM FUSION FOR ROBUST DEEPFAKE DETECTION IN DIGITAL MEDIA
    S. E. Hammed, S. Al-Darraji
    African Journal of Applied Research, 2026
    Purpose: This paper aims to address the growing challenge of deepfake detection, driven by the increasing impact of synthetic media on digital integrity, privacy, and security. Design/Methodology/ Approach: The proposed approach integrates a hybrid deep learning architecture combining Convolutional Neural Networks (CNNs) to extract spatial features and Long Short-Term Memory (LSTM) to model temporal relationships, enhanced by an attention mechanism to focus on important features and subtle manipulation patterns. The methodology includes video preprocessing such as frame extraction, face detection, alignment, and normalisation, followed by sequence-level classification. Research Limitation: The study is limited by its reliance on benchmark datasets, which may not fully represent real-world scenarios, and by potential challenges in generalising to unseen manipulations. Additionally, no funding support was reported. Findings: The model is evaluated on the FaceForensics++ dataset using standard metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, demonstrating improved performance in detecting deepfake videos. Practical Implication: The proposed model can be applied in security systems, social media platforms, and digital forensics to detect and prevent the spread of manipulated video content. Social Implication: The work contributes to reducing misinformation, enhancing trust in digital media, and protecting user privacy and societal security. Originality/Value: The originality of this work lies in integrating CNN, LSTM, and attention mechanisms into a unified framework for spatiotemporal feature learning, providing a scalable and effective solution for deepfake detection.
  • A Multi-Modal Convolutional Neural Network for Face Anti-Spoofing Detection
    Hala S. Mahmood, Salah Al-Darraji
    Iraqi Journal for Electrical and Electronic Engineering, 2026
    Recently, face recognition technology has become more prevalent in various applications, including mobile devices, access control, and financial transactions. Therefore, it is crucial to address potential vulnerabilities that attackers might exploit. In this study, a method for face presentation attack detection (PAD) is introduced. The method utilizes the diversity of modalities provided by some cameras and sensors to detect face spoofing using convolutional neural networks (CNN) within the context of deep learning. To assess the effectiveness of the proposed approach in real-world scenarios, the wide multi-channel presentation attack (WMCA) dataset is used. The presented method exploits the multi-modal data, including RGB, depth, IR, and thermal channels, to enhance system performance and explore different techniques for combining the results from each modality. Furthermore, this study explores diverse techniques for fusing results from each channel in two fusion scenarios, pre-fusion and post-fusion. In the pre-fusion scenario, data from the four channels is combined, resulting in an ACER value of 0.19%. In the post-fusion scenario, the results of each modality are fused using different fusion techniques, such as majority voting, weighted voting, average pooling, and a stacking classifier. The stacking classifier yields the most favorable outcome with an ACER ratio of 0.03%. This performance is notably superior when compared to state-of-the-art methodologies.
  • Local path planning based on Bi-population Swarms optimization algorithms
    Asmaa Shareef, Salah Al-darraji, Suhaib Al-Ansarry, Zaid Ameen Abduljabbar, Vincent Omollo Nyangaresi, et al.
    Results in Control and Optimization, 2025
  • Path Planning for Autonomous Mobile Robots Using the RFO-GWO Optimization Algorithm
    Fetoh H. Ketafa, Salah Al-Darraji
    Iraqi Journal of Science, 2024
    Path planning is a challenging navigation problem that can be handled using multi-objective methods. This paper, present a thre Path planning is a challenging navigation problem that can be handled using multi-objective methods. This paper presents a three-stage multi-objective path-planning method. The first stage is to locate the best or near-best solution path and avoid detected obstacles using a hybrid of the red fox–gray wolf optimizer (RFO–GWO), which finds a route from the start position to the target position. In the second step, a mutation operation using an evolutionary algorithm is utilized to enhance the length, integrity, and smoothness of the route generated by the RFO–GWO algorithm. The final step of the suggested method is refined further using a multiphase technique. By integrating the real sizes of the mobile robots and the size of the barriers and phrasing the issue as a traveling object in the available area, the suggested path-planning method resembles the actual world. The simulation results indicate that this strategy creates the most viable path even in complicated surroundings, overcoming the disadvantages of traditional approaches. Furthermore, when compared to prior path-planning methods, the simulation’s outcomes indicate that the suggested RFO–GWO method is effective in terms of the route, and the strategy is extremely competitive. The results showed a significant improvement, where the total percentage convergence time (in seconds) for RFO–GWO for the three maps was 15%, 12%, and 10%, respectively, whereas it was 35%, 41%, and 43% seconds in GWO and 34%, 35%, and 37% seconds in RFO. There was also a significant improvement in the number of nodes for RFO-GWO (2%, 3%, and 2%) compared to GWO nodes (64%, 65%, and 62%), and RFO nodes (32%, 30%, and 35%) for the same three maps. Subsequently, the smoothness of the path formed by the recommended approach was enhanced using the evolutionary algorithm (EA), where the total percentage length of the path in the worst scenario for GWO was 28% and for RFO was 26% in units, but after improvement with the RFO-GWO with EA, it became 22% in units. stages multi-objective path planning method: The first stage is to locate the best or near-best solution path and avoid the detected obstacles using a hybrid of the Red Fox-Grey Wolf optimizer (RFO-GWO) method, which finds a rout from the start position to the target position. In the second step, a mutation operation by evolutionary, are utilized to enhance the length, integrity, and smooth of the rout generated by the RFO-GWO method. the final step the suggested method is refined further by using the multiphase technique. By integrating both the real sizes of the mobile robots and the size of the barriers and phrasing the issue as a traveling object in the available area, the suggested path planning method resembles the actual world. The simulation results indicate that this strategy creates the best viable path even in complicated surroundings, overcoming the disadvantages of traditional approaches. Furthermore, when contrasted with prior path-planning methods, simulation outcomes indicate that the suggested RFO-GWO in terms of route effectivity, the strategy is extremely competitive.
  • An Efficient Path Planning in Uncertainty Environments using Dynamic Grid-Based and Potential Field Methods
    Suhaib Al-Ansarry, Salah Al-Darraji, Dhafer Honi
    Iraqi Journal for Electrical and Electronic Engineering, 2023
    Path planning is an essential concern in robotic systems, and it refers to the process of determining a safe and optimal path starting from the source state to the goal one within dynamic environments. We proposed an improved path planning method in this article, which merges the Dijkstra algorithm for path planning with Potential Field (PF) collision avoidance. In real-time, the method attempts to produce multiple paths as well as determine the suitable path that’s both short and reliable (safe). The Dijkstra method is employed to produce multiple paths, whereas the Potential Field is utilized to assess the safety of each route and choose the best one. The proposed method creates links between the routes, enabling the robot to swap between them if it discovers a dynamic obstacle on its current route. Relating to path length and safety, the simulation results illustrate that Dynamic Dijkstra-Potential Field (Dynamic D-PF) achieves better performance than the Dijkstra and Potential Field each separately, and going to make it a promising solution for the application of robotic automation within dynamic environments.
  • Bi-Directional Adaptive Probabilistic Method with a Triangular Segmented Interpolation for Robot Path Planning in Complex Dynamic-Environments
    Suhaib Al-Ansarry, Salah Al-Darraji, Asmaa Shareef, Dhafer G. Honi, Francesca Fallucchi
    IEEE Access, 2023
  • Grasshopper optimization algorithm based path planning for autonomous mobile robot
    Asmaa Shareef, Salah Al-Darraji
    Bulletin of Electrical Engineering and Informatics, 2022
    Autonomous mobile robots have become very popular and essential in our life, especially in industry. One of the crucial activities of the robot is planning the path from a start point to a target point, avoiding obstacles in the environment. Recently, path planning received more attention, and many methodologies have been proposed. Path planning studies have shown the effectiveness of swarm intelligence in complex and known or unknown environments. This paper presents a global path planning method based on grasshopper optimization algorithm (GOA) in a known static environment. This algorithm is improved using the bias factor to increase the efficiency and improve the resulting path. The resulting path from this algorithm is further enhanced using an improved version multinomial logistic regression algorithm (MLR). The algorithms were evaluated using three different large environments of varying complexities. The GOA algorithm has been compared with the ant colony optimization algorithm (ACO) using the same environments. The experiments have shown the superiority of our algorithm in terms of time convergence and cost.
  • Face Recognition System Against Adversarial Attack Using Convolutional Neural Network
    Ansam Kadhim, Salah Al-Darraji
    Iraqi Journal for Electrical and Electronic Engineering, 2022
    Face recognition is the technology that verifies or recognizes faces from images, videos, or real-time streams. It can be used in security or employee attendance systems. Face recognition systems may encounter some attacks that reduce their ability to recognize faces properly. So, many noisy images mixed with original ones lead to confusion in the results. Various attacks that exploit this weakness affect the face recognition systems such as Fast Gradient Sign Method (FGSM), Deep Fool, and Projected Gradient Descent (PGD). This paper proposes a method to protect the face recognition system against these attacks by distorting images through different attacks, then training the recognition deep network model, specifically Convolutional Neural Network (CNN), using the original and distorted images. Diverse experiments have been conducted using combinations of original and distorted images to test the effectiveness of the system. The system showed an accuracy of 93% using FGSM attack, 97% using deep fool, and 95% using PGD.
  • Dynamic Multi-Threaded Path Planning Based on Grasshopper Optimization Algorithm
    Asmaa Shareef, Salah Al-Darraji
    2022 Iraqi International Conference on Communication and Information Technologies Iiccit 2022, 2022
    Over the past few years, computer hardware equipment has undergone a great deal of development, especially since multi-core processors were introduced, which increased the speed of performing tasks in various fields. Compared to single-core, multi-core chips can provide higher performance and efficiency. In this paper, a multi-core system is exploited to speed up path planning using the grasshopper optimization algorithm (GOA) as well as finding multiple paths supporting the mobile robot to navigate safely in a dynamic known environment. Then multiple paths can be practiced if the robot encounters a dynamic obstacle to fabricate a new obstacle-free path out of the planned paths. Diverse experiments have shown that the robot always lays hands on the path to the target even with multiple dynamic obstacles that block the way of the robot. Recalculating a path from the existing paths tremendously decreased the required time compared to re-planning the path.
  • Path Planning for an Autonomous Mobile Robot Using Red Fox Optimization Algorithm
    Fetoh H. Ketafa, Salah Al-Darraji
    2022 International Conference on Data Science and Intelligent Computing Icdsic 2022, 2022
  • Privacy preserving scheme for document similarity detection
    AYAD ABDULSADA, SALAH AL-DARRAJI, DHAFER HONI
    Turkish Journal of Electrical Engineering and Computer Sciences, 2022
  • Employee attrition prediction using deep neural networks
    Salah Al-Darraji, Dhafer G. Honi, Francesca Fallucchi, Ayad I. Abdulsada, Romeo Giuliano, et al.
    Computers, 2021
  • Goal location prediction based on deep learning using rgb-d camera
    Heba Hakim, Zaineb Alhakeem, Salah Al-Darraji
    Bulletin of Electrical Engineering and Informatics, 2021
  • Efficient multi-keyword similarity search over encrypted cloud documents
    Ayad I. Abdulsada, Dhafer G. Honi, Salah Al-Darraji
    Indonesian Journal of Electrical Engineering and Computer Science, 2021
  • Hybrid RRT-A*: An Improved Path Planning Method for an Autonomous Mobile Robots
    Suhaib Al-Ansarry, Salah Al-Darraji
    Iraqi Journal for Electrical and Electronic Engineering, 2021
  • Privacy Preserving Image Matching Scheme with Aggregated Local Descriptors
    Dhafer G. Honi, Husam A. Abdulmalik, Ayad I. Abdulsada, Salah Al-Darraji
    Csitss 2021 2021 5th International Conference on Computational Systems and Information Technology for Sustainable Solutions Proceedings, 2021
  • Human action recognition from RGBD videos based on retina model and local binary pattern features
    Rawya Al-Akam, Salah Al-Darraji, Dietrich Paulus
    Computer Science Research Notes, 2018
  • Interactive communication between human and robot using nonverbal cues
    Salah Al-Darraji, Zuhair Zafar, Karsten Berns, Djordje Urukalo, Aleksandar Rodić
    Mechanisms and Machine Science, 2018
  • Human robot interaction using dynamic hand gestures
    Zuhair Zafar, Daniel Alejandro Salazar, Salah Al-Darraji, Djordje Urukalo, Karsten Berns, et al.
    Mechanisms and Machine Science, 2018
  • Ability of humanoid robot to perform emotional body gestures
    Djordje Urukalo, Ljubinko Kevac, Zuhair Zafar, Salah Al-Darraji, Aleksandar Rodić, et al.
    Mechanisms and Machine Science, 2018
  • Action unit based facial expression recognition using deep learning
    Salah Al-Darraji, Karsten Berns, Aleksandar Rodić
    Advances in Intelligent Systems and Computing, 2017
  • Embodiment of human personality with EI-Robots by mapping behaviour traits from live-model
    Aleksandar Rodić, Djordje Urukalo, Milica Vujović, Sofija Spasojević, Marija Tomić, et al.
    Advances in Intelligent Systems and Computing, 2017
  • Real-time perception of non-verbal human feedback in a gaming scenario
    Salah Al-Darraji, Zafar Zuhair, Karsten Berns
    Proceedings of the 30th International Bcs Human Computer Interaction Conference Hci 2016, 2016
  • Nonverbal communication with a humanoid robot via head gestures
    Salah Saleh, Karsten Berns
    8th ACM International Conference on Pervasive Technologies Related to Assistive Environments Petra 2015 Proceedings, 2015
  • Robust perception of an interaction partner using depth information
    Achi 2013 6th International Conference on Advances in Computer Human Interactions, 2013

RECENT SCHOLAR PUBLICATIONS

  • Local path planning based on Bi-population Swarms optimization algorithms
    A Shareef, S Al-darraji, S Al-Ansarry, ZA Abduljabbar, VO Nyangaresi, ...
    Results in Control and Optimization, 100634 , 2025
    2025
  • Unmasking Deepfakes: A Systematic Review of Generation Techniques and Detection Strategies
    S Eidan
    Iraqi Journal of Intelligent Computing and Informatics (IJICI) 4 (2), 134-154 , 2025
    2025
    Citations: 2
  • A Comprehensive Review Cross-Domain Image Translation: A Framework Using Generative Adversarial Networks and Variational Autoencoders
    SJM Al-Kabby, S Aldarraj
    Iraqi Journal of Intelligent Computing and Informatics (IJICI) 4 (2), 103-113 , 2025
    2025
    Citations: 1
  • Traversing Dynamic Environments: Advanced Deep Reinforcement Learning for Mobile Robots Path Planning-A Comprehensive Review
    S Al-Darraji
    Iraqi Journal of Intelligent Computing and Informatics (IJICI) 2 (1) , 2024
    2024
  • A Face Anti-Spoofing Detection with Multi-Modal CNN Enhanced by ResNet: Face Anti-Spoofing Detection
    H Shaker, S Al-Darraji
    Basrah Researches Sciences 50 (1), 12-12 , 2024
    2024
    Citations: 3
  • Path Planning for Autonomous Mobile Robots Using the RFO-GWO Optimization Algorithm
    FH Ketafa, S Al-Darraji
    Iraqi Journal of Science, 1070-1088 , 2024
    2024
    Citations: 5
  • Face Anti-Spoofing Detection with Multi-Modal CNN Enhanced by ResNet.
    HS Mahmood, S Al-Darraji
    Journal of Basrah Researches (Sciences) 50 (1) , 2024
    2024
    Citations: 2
  • Bi-directional Adaptive Probabilistic Method with a Triangular Segmented Interpolation for Robot Path Planning in Complex Dynamic-Environments
    S Al-Ansarry, S Al-Darraji, A Shareef, DG Honi, F Fallucchi
    IEEE Access , 2023
    2023
    Citations: 11
  • A review: On bio-inspired optimization methods for path planning of mobile robot
    F Hason, S Al-Darraji
    Iraqi Journal of Intelligent Computing and Informatics (IJICI) 2 (1), 1-10 , 2023
    2023
    Citations: 7
  • An Efficient Path Planning in Uncertainty Environments using Dynamic Grid-Based and Potential Field Methods
    S Al-Ansarry, S Al-Darraji, DG Honi
    2023
    Citations: 3
  • Grasshopper optimization algorithm based path planning for autonomous mobile robot
    A Shareef, S Al-Darraji
    Bulletin of Electrical Engineering and Informatics 11 (6), 3551-3561 , 2022
    2022
    Citations: 14
  • Path Planning for an Autonomous Mobile Robot Using Red Fox Optimization Algorithm
    FH Ketafa, S Al-Darraji
    2022 International Conference on Data Science and Intelligent Computing … , 2022
    2022
    Citations: 4
  • Dynamic Multi-Threaded Path Planning Based on Grasshopper Optimization Algorithm
    A Shareef, S Al-Darraji
    2022 Iraqi International Conference on Communication and Information … , 2022
    2022
    Citations: 4
  • Privacy preserving scheme for document similarity detection
    A Abdulsada, S Al-Darraji, D HONI
    Turkish Journal of Electrical Engineering and Computer Sciences 30 (3), 609-628 , 2022
    2022
  • Privacy Preserving Image Matching Scheme with Aggregated Local Descriptors
    DG Honi, HA Abdulmalik, AI Abdulsada, S Al-Darraji
    2021 IEEE International Conference on Computation System and Information … , 2021
    2021
  • Employee Attrition Prediction Using Deep Neural Networks
    S Al-Darraji, DG Honi, F Fallucchi, AI Abdulsada, R Giuliano, ...
    Computers 10 (11), 141 , 2021
    2021
    Citations: 89
  • Goal Location Prediction based on Deep Learning using RGB-D Camera
    H Hakim, Z Alhakeem, S Al-Darraji
    Bulletin of Electrical Engineering and Informatics 10 (5) , 2021
    2021
    Citations: 14
  • Efficient multi-keyword similarity search over encrypted cloud documents
    AI Abdulsada, DG Honi, S Al-Darraji
    Indonesian Journal of Electrical Engineering and Computer Science 23 (1 … , 2021
    2021
    Citations: 6
  • Face Recognition System Against Adversarial Attack Using Convolutional Neural Network
    A Kadhim, S Al-Darraji
    2021
    Citations: 4
  • MT Hybrid RRT-A* Regression-based: An Enhanced Path Planning Method for an Autonomous Mobile Robots
    S Al-Ansarry, S Al-Darraji
    2021
    Citations: 7

MOST CITED SCHOLAR PUBLICATIONS

  • Employee Attrition Prediction Using Deep Neural Networks
    S Al-Darraji, DG Honi, F Fallucchi, AI Abdulsada, R Giuliano, ...
    Computers 10 (11), 141 , 2021
    2021
    Citations: 89
  • Hybrid RRT-A*: An Improved Path Planning Method for an Autonomous Mobile Robots
    S Al-Ansarry, S Al-Darraji
    2020
    Citations: 32
  • Action unit based facial expression recognition using deep learning
    S Al-Darraji, K Berns, A Rodić
    International Conference on Robotics in Alpe-Adria Danube Region, 413-420 , 2016
    2016
    Citations: 21
  • Using discrete wavelet transformation to enhance underwater image
    AA Yassin, RM Ghadban, SF Saleh, HZ Neima
    International Journal of Computer Science Issues (IJCSI) 10 (5), 220 , 2013
    2013
    Citations: 18
  • Nonverbal communication with a humanoid robot via head gestures
    S Saleh, K Berns
    Proceedings of the 8th ACM International Conference on PErvasive … , 2015
    2015
    Citations: 15
  • Grasshopper optimization algorithm based path planning for autonomous mobile robot
    A Shareef, S Al-Darraji
    Bulletin of Electrical Engineering and Informatics 11 (6), 3551-3561 , 2022
    2022
    Citations: 14
  • Goal Location Prediction based on Deep Learning using RGB-D Camera
    H Hakim, Z Alhakeem, S Al-Darraji
    Bulletin of Electrical Engineering and Informatics 10 (5) , 2021
    2021
    Citations: 14
  • Bi-directional Adaptive Probabilistic Method with a Triangular Segmented Interpolation for Robot Path Planning in Complex Dynamic-Environments
    S Al-Ansarry, S Al-Darraji, A Shareef, DG Honi, F Fallucchi
    IEEE Access , 2023
    2023
    Citations: 11
  • Perception of Nonverbal Cues for Human-Robot Interaction
    S Al-Darraji
    Dr. Hut Verlag , 2016
    2016
    Citations: 9
  • Embodiment of human personality with EI-robots by mapping behaviour traits from live-model
    A Rodić, D Urukalo, M Vujović, S Spasojević, M Tomić, K Berns, ...
    International Conference on Robotics in Alpe-Adria Danube Region, 438-448 , 2016
    2016
    Citations: 8
  • A review: On bio-inspired optimization methods for path planning of mobile robot
    F Hason, S Al-Darraji
    Iraqi Journal of Intelligent Computing and Informatics (IJICI) 2 (1), 1-10 , 2023
    2023
    Citations: 7
  • MT Hybrid RRT-A* Regression-based: An Enhanced Path Planning Method for an Autonomous Mobile Robots
    S Al-Ansarry, S Al-Darraji
    2021
    Citations: 7
  • A multimodal nonverbal human-robot communication system
    S Saleh, M Sahu, Z Zafar, K Berns
    Proceedings of the Sixth International Conference on Computational … , 2015
    2015
    Citations: 7
  • Efficient multi-keyword similarity search over encrypted cloud documents
    AI Abdulsada, DG Honi, S Al-Darraji
    Indonesian Journal of Electrical Engineering and Computer Science 23 (1 … , 2021
    2021
    Citations: 6
  • Path Planning for Autonomous Mobile Robots Using the RFO-GWO Optimization Algorithm
    FH Ketafa, S Al-Darraji
    Iraqi Journal of Science, 1070-1088 , 2024
    2024
    Citations: 5
  • Robust perception of an interaction partner using depth information
    S Saleh, A Kickton, J Hirth, K Berns
    Proceeding of the International Conference on Advances in Computer-Human … , 2013
    2013
    Citations: 5
  • Path Planning for an Autonomous Mobile Robot Using Red Fox Optimization Algorithm
    FH Ketafa, S Al-Darraji
    2022 International Conference on Data Science and Intelligent Computing … , 2022
    2022
    Citations: 4
  • Dynamic Multi-Threaded Path Planning Based on Grasshopper Optimization Algorithm
    A Shareef, S Al-Darraji
    2022 Iraqi International Conference on Communication and Information … , 2022
    2022
    Citations: 4
  • Face Recognition System Against Adversarial Attack Using Convolutional Neural Network
    A Kadhim, S Al-Darraji
    2021
    Citations: 4
  • A Face Anti-Spoofing Detection with Multi-Modal CNN Enhanced by ResNet: Face Anti-Spoofing Detection
    H Shaker, S Al-Darraji
    Basrah Researches Sciences 50 (1), 12-12 , 2024
    2024
    Citations: 3