Detection and recognition of vehicle licence plates using deep learning in challenging conditions: a systematic review Abdul Awal Quraishi, Farid Feyzi, Asadollah Shahbahrami International Journal of Intelligent Systems Technologies and Applications, 2024 Automatic licence plate detection and recognition (ALPDR) systems are widely used in various sectors such as traffic control, toll payment, parking systems, border control, and law enforcement. However, these systems face challenges in complex scenarios such as different licence plate formats, poor lighting or occlusion, and deliberate manipulation. To address these challenges, researchers have developed various methods. The first set of challenges involves natural conditions like varying light, snow, rain, fog, and dust. The second set includes environmental factors such as camera angle, occlusion, distortion, contrast issues in images, noise interference, dirt on camera lenses, and camera distance from the scene. The third challenge is related to multinational licence plate variations in terms of formats, colours, sizes, fonts, and characters. Lastly, adversarial attacks pose a threat through rotation, noise addition or distortion to licence plates. This study reviews recent literature on ALPDR systems and proposes guidelines for future research.
Studying the effectiveness of deep active learning in software defect prediction Farid Feyzi, Arman Daneshdoost International Journal of Computers and Applications, 2023 Accurate prediction of defective software modules is of great importance for prioritizing quality assurance efforts, reasonably allocating testing resources, reducing costs and improving software quality. Several studies have used machine learning to predict software defects. However, complex structures and imbalanced class distributions in software defect data make learning an effective defect prediction model challenging. In this article, two deep learning-based defect prediction models using static code metrics are proposed. In order to enhance the learning process and improve the performance of the proposed models, pool-based active learning is employed. In this regard, the possibility of using active learning to mitigate the need for a large amount of labeled data in the process of building deep learning models is investigated. To deal with imbalanced distribution of software modules between defective and non-defective classes, Near-Miss under-sampling and KNN, with different number of neighbors, are used. The reason for choosing them is their good performance in binary classification problems. Experiments are performed on two well-known, publicly available datasets, GitHub Bug Dataset and public Unified Bug Dataset for java projects. The evaluation results reveal the effectiveness of our proposed models in comparison to the traditional machine learning algorithms. In the conducted investigations on the Unified Bug Dataset, at the file level, the value of F-measure and AUC criteria have improved by 13 and 11 percent, respectively and at the class level, the values have improved by 14 and 11 percent, respectively.
Model-driven development of self-adaptive multi-agent systems with context-awareness Farid Feyzi International Journal of Computer Aided Engineering and Technology, 2020 Self-adaptive systems are complex and operate in dynamic and heterogeneous environments. They have to dynamically modify their behaviour at run-time in response to different kinds of changes. This paper presents a methodology to develop context-aware self-adaptive systems by employing the model driven architecture (MDA) and agent-oriented technology advantages. The approach aims to combine these two promising technologies to overcome the complexity of developing such systems. The methodology focuses on the key issues in the analysis and design of self-adaptive multi-agent systems. Different abstraction levels based on MDA has been proposed and mappings between models in these levels provided. These mappings bridge the gap between the high-level models produced in computation independent (CIM) and platform independent models (PIM) as well as the low-level models based on specific implementation platform called SADE (Self-adaptation Development Environment). The proposed approach has been evaluated through a case study described in the paper.
Effective test data generation using probabilistic networks Farid Feyzi, Saeed Parsa International Journal of Computing Science and Mathematics, 2020 This paper presents a novel test data generation method called Bayes-TDG. It is based on principles of Bayesian networks (BNs) and provides the possibility of making inference from probabilistic data in the model to increase the prime path coverage ratio (PPCR) for a given program under test (PUT). In this regard, a new program structure-based probabilistic network, TDG-NET, is proposed that is capable of modelling the conditional dependencies among the program basic blocks (BBs) in one hand and conditional dependencies of the transitions between its BBs and input parameters on the other hand. To achieve failure-detection effectiveness, we propose a path selection strategy that works based on the predicted outcome of generated test cases. So, we mitigate the need for a human oracle, and the generated test suite could be directly used in fault localisation. Several experiments are conducted to evaluate the performance of Bayes-TDG. The results reveal that the method is promising and the generated test suite could be quite effective.
Bayes-TDG: Effective test data generation using Bayesian belief network: Toward failure-detection effectiveness and maximum coverage Farid Feyzi, Saeed Parsa Iet Software, 2018 This study presents a novel test data generation method called Bayes‐TDG . It is based on principles of Bayesian networks and provides the possibility of making inference from probabilistic data in the model to increase the prime path‐coverage ratio for a given programme under test (PUT). In this regard, a new programme structure‐based probabilistic network, TDG‐NET, is proposed that is capable of modelling the conditional dependencies among the programme basic blocks (BBs) on one hand and conditional dependencies of the transitions between its BBs and input parameters on the other hand. To achieve failure‐detection effectiveness, the authors propose a path selection strategy that works based on the predicted outcome of generated test cases. So, they mitigate the need for a human oracle, and the generated test suite could be directly used in fault localisation. Several experiments are conducted to evaluate the performance of Bayes‐TDG . The results reveal that the method is promising and the generated test suite could be quite effective.
Large Language Models for Security Operations Centers: A Comprehensive Survey A Habibzadeh, F Feyzi, RE Atani Journal of Electrical and Computer Engineering , 2026 2026 Citations: 12
Efficient Pairwise Association Rules for Personalized Recommendations: Leveraging Caching and Asynchronous Model Updates SM Mortazavi, F Feyzi Computational Sciences and Engineering 4 (2), 237-257 , 2025 2025
Large language models for software vulnerability detection: a guide for researchers on models, methods, techniques, datasets, and metrics SM Taghavi Far, F Feyzi International Journal of Information Security 24 (2), 78 , 2025 2025 Citations: 51
Bad Code Smells in iOS Apps: An Empirical Investigation and Automated Detection Approach AH Kohansal, F Feyzi Computational Sciences and Engineering 5 (1), 39-70 , 2025 2025
Electronic waste management using smart contracts on the blockchain platform A Rafiee, F Feyzi, A Shahbahrami SN Computer Science 5 (7), 896 , 2024 2024 Citations: 8
Detection and recognition of vehicle licence plates using deep learning in challenging conditions: a systematic review AA Quraishi, F Feyzi, A Shahbahrami International Journal of Intelligent Systems Technologies and Applications … , 2024 2024 Citations: 9
Studying the effectiveness of deep active learning in software defect prediction F Feyzi, A Daneshdoost International Journal of Computers and Applications 45 (7-8), 534-552 , 2023 2023 Citations: 8
A New Approach in Diagnosing and Preventing SQLIA with Large Language Models (LLMs) A Rezanejad, AS Danesh, F Feyzi 8th International Conference on Combinatorics, Cryptography, Computer … , 2023 2023 Citations: 2
CGT-FL: using cooperative game theory to effective fault localization in presence of coincidental correctness F Feyzi Empirical Software Engineering 25 (5), 3873-3927 , 2020 2020 Citations: 16
Effective test data generation using probabilistic networks F Feyzi, S Parsa International Journal of Computing Science and Mathematics 11 (4), 357-371 , 2020 2020 Citations: 2
Model-driven development of self-adaptive multi-agent systems with context-awareness F Feyzi International Journal of Computer Aided Engineering and Technology 12 (2 … , 2020 2020 Citations: 8
Inforence : effective fault localization based on information-theoretic analysis and statistical causal inference F Feyzi, S Parsa Frontiers of Computer Science 13 (4), 735-759 , 2019 2019 Citations: 54
Kernel-based Detection of Coincidentally Correct Test Cases to Improve Fault Localization Effectiveness F Feyzi, S Parsa International Journal of Applied Pattern Recognition 5 (2), 119-136 , 2018 2018 Citations: 10
Bayes-TDG: effective test data generation using Bayesian belief network: toward failure-detection effectiveness and maximum coverage F Feyzi, S Parsa IET Software 12 (3), 225-235 , 2018 2018 Citations: 6
FPA-FL: Incorporating static fault-proneness analysis into statistical fault localization F Feyzi, S Parsa Journal of Systems and Software 136, 39-58 , 2018 2018 Citations: 41
Statistical bug localisation by supervised clustering of program predicates F Feyzi, S Parsa, E Nikravan International Journal of Information Systems and Change Management 10 (2 … , 2018 2018
A program slicing-based method for effective detection of coincidentally correct test cases F Feyzi, S Parsa Computing 100 (9), 927-969 , 2018 2018 Citations: 54
FPA-Debug: Effective statistical fault localization considering fault-proneness analysis F Feyzi, E Nikravan, S Parsa Knowledge-Based Engineering and Innovation (KBEI), 2015 2nd International … , 2016 2016 Citations: 7
Enhancing path-oriented test data generation using adaptive random testing techniques E Nikravan, F Feyzi, S Parsa 2015 2nd International Conference on Knowledge-Based Engineering and … , 2015 2015 Citations: 17
MOST CITED SCHOLAR PUBLICATIONS
Inforence : effective fault localization based on information-theoretic analysis and statistical causal inference F Feyzi, S Parsa Frontiers of Computer Science 13 (4), 735-759 , 2019 2019 Citations: 54
A program slicing-based method for effective detection of coincidentally correct test cases F Feyzi, S Parsa Computing 100 (9), 927-969 , 2018 2018 Citations: 54
Large language models for software vulnerability detection: a guide for researchers on models, methods, techniques, datasets, and metrics SM Taghavi Far, F Feyzi International Journal of Information Security 24 (2), 78 , 2025 2025 Citations: 51
FPA-FL: Incorporating static fault-proneness analysis into statistical fault localization F Feyzi, S Parsa Journal of Systems and Software 136, 39-58 , 2018 2018 Citations: 41
Enhancing path-oriented test data generation using adaptive random testing techniques E Nikravan, F Feyzi, S Parsa 2015 2nd International Conference on Knowledge-Based Engineering and … , 2015 2015 Citations: 17
CGT-FL: using cooperative game theory to effective fault localization in presence of coincidental correctness F Feyzi Empirical Software Engineering 25 (5), 3873-3927 , 2020 2020 Citations: 16
Large Language Models for Security Operations Centers: A Comprehensive Survey A Habibzadeh, F Feyzi, RE Atani Journal of Electrical and Computer Engineering , 2026 2026 Citations: 12
Kernel-based Detection of Coincidentally Correct Test Cases to Improve Fault Localization Effectiveness F Feyzi, S Parsa International Journal of Applied Pattern Recognition 5 (2), 119-136 , 2018 2018 Citations: 10
Detection and recognition of vehicle licence plates using deep learning in challenging conditions: a systematic review AA Quraishi, F Feyzi, A Shahbahrami International Journal of Intelligent Systems Technologies and Applications … , 2024 2024 Citations: 9
Electronic waste management using smart contracts on the blockchain platform A Rafiee, F Feyzi, A Shahbahrami SN Computer Science 5 (7), 896 , 2024 2024 Citations: 8
Studying the effectiveness of deep active learning in software defect prediction F Feyzi, A Daneshdoost International Journal of Computers and Applications 45 (7-8), 534-552 , 2023 2023 Citations: 8
Model-driven development of self-adaptive multi-agent systems with context-awareness F Feyzi International Journal of Computer Aided Engineering and Technology 12 (2 … , 2020 2020 Citations: 8
FPA-Debug: Effective statistical fault localization considering fault-proneness analysis F Feyzi, E Nikravan, S Parsa Knowledge-Based Engineering and Innovation (KBEI), 2015 2nd International … , 2016 2016 Citations: 7
Bayes-TDG: effective test data generation using Bayesian belief network: toward failure-detection effectiveness and maximum coverage F Feyzi, S Parsa IET Software 12 (3), 225-235 , 2018 2018 Citations: 6
A New Approach in Diagnosing and Preventing SQLIA with Large Language Models (LLMs) A Rezanejad, AS Danesh, F Feyzi 8th International Conference on Combinatorics, Cryptography, Computer … , 2023 2023 Citations: 2
Effective test data generation using probabilistic networks F Feyzi, S Parsa International Journal of Computing Science and Mathematics 11 (4), 357-371 , 2020 2020 Citations: 2
Efficient Pairwise Association Rules for Personalized Recommendations: Leveraging Caching and Asynchronous Model Updates SM Mortazavi, F Feyzi Computational Sciences and Engineering 4 (2), 237-257 , 2025 2025
Bad Code Smells in iOS Apps: An Empirical Investigation and Automated Detection Approach AH Kohansal, F Feyzi Computational Sciences and Engineering 5 (1), 39-70 , 2025 2025
Statistical bug localisation by supervised clustering of program predicates F Feyzi, S Parsa, E Nikravan International Journal of Information Systems and Change Management 10 (2 … , 2018 2018
