Mahmoud Bekhit
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mahmoud Bekhit has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Ahmed Fathalla
Suez Canal University
14 shared publications - Ahmad Salah
College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri 516, Oman
12 shared publications - Ahmed Ali
Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia
6 shared publications - Esraa Eldesouky
Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj, Saudi Arabia
6 shared publications - Nur Indah Lestari
University of Technology Sydney (UTS)
4 shared publications - Abubakar Bello
Edge Hill University
3 shared publications
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 427-448
Integrating Category-Specific Risk, Geospatial Irregularities, and Regional Density Analysis for Context-Aware Fraud Detection
- 6 October 2026
- Published by Springer Nature
- p. 427-448
Integrating Category-Specific Risk, Geospatial Irregularities, and Regional Density Analysis for Context-Aware Fraud Detection
- Open Access
- 1 October 2025
- Published by MDPI AG in Information
- Vol. 16 (10) , 851
MoCap-Impute: A Comprehensive Benchmark and Comparative Analysis of Imputation Methods for IMU-Based Motion Capture Data
Motion capture (MoCap) data derived from wearable Inertial Measurement Units is essential to applications in sports science and healthcare robotics. However, a significant amount of the potential of this data is limited due to missing data derived from sensor limitations, network issues, and environmental interference. Such limitations can introduce bias, prevent the fusion of critical data streams, and ultimately compromise the integrity of human activity analysis. Despite the plethora of data imputation techniques available, there have been few systematic performance evaluations of these techniques explicitly for the time series data of IMU-derived MoCap data. We address this by evaluating the imputation performance across three distinct contexts: univariate time series, multivariate across players, and multivariate across kinematic angles. To address this limitation, we propose a systematic comparative analysis of imputation techniques, including statistical, machine learning, and deep learning techniques, in this paper. We also introduce the first publicly available MoCap dataset specifically for the purpose of benchmarking missing value imputation, with three missingness mechanisms: missing completely at random, block missingness, and a simulated value-dependent missingness pattern simulated at the signal transition points. Using data from 53 karate practitioners performing standardized movements, we artificially generated missing values to create controlled experimental conditions. We performed experiments across the 53 subjects with 39 kinematic variables, which showed that discriminating between univariate and multivariate imputation frameworks demonstrates that multivariate imputation frameworks surpassunivariate approaches when working with more complex missingness mechanisms. Specifically, multivariate approaches achieved up to a 50% error reduction (with the MAE improving from 10.8 ± 6.9 to 5.8 ± 5.5) compared to univariate methods for transition point missingness. Specialized time series deep learning models (i.e., SAITS, BRITS, GRU-D) demonstrated a superior performance with MAE values consistently below 8.0 for univariate contexts and below 3.2 for multivariate contexts across all missing data percentages, significantly surpassing traditional machine learning and statistical methods. Notable traditional methods such as Generative Adversarial Imputation Networks and Iterative Imputers exhibited a competitive performance but remained less stable than the specialized temporal models. This work offers an important baseline for future studies, in addition to recommendations for researchers looking to increase the accuracy and robustness of MoCap data analysis, as well as integrity and trustworthiness.
- 1 October 2025
- Published by MDPI AG in Information
- Vol. 16 (10) , 851
Open AccessMoCap-Impute: A Comprehensive Benchmark and Comparative Analysis of Imputation Methods for IMU-Based Motion Capture Data
Motion capture (MoCap) data derived from wearable Inertial Measurement Units is essential to applications in sports science and healthcare robotics. However, a significant amount of the potential of this data is limited due to missing data derived from sensor limitations, network issues, and environmental interference. Such limitations can introduce bias, prevent the fusion of critical data streams, and ultimately compromise the integrity of human activity analysis. Despite the plethora of data imputation techniques available, there have been few systematic performance evaluations of these techniques explicitly for the time series data of IMU-derived MoCap data. We address this by evaluating the imputation performance across three distinct contexts: univariate time series, multivariate across players, and multivariate across kinematic angles. To address this limitation, we propose a systematic comparative analysis of imputation techniques, including statistical, machine learning, and deep learning techniques, in this paper. We also introduce the first publicly available MoCap dataset specifically for the purpose of benchmarking missing value imputation, with three missingness mechanisms: missing completely at random, block missingness, and a simulated value-dependent missingness pattern simulated at the signal transition points. Using data from 53 karate practitioners performing standardized movements, we artificially generated missing values to create controlled experimental conditions. We performed experiments across the 53 subjects with 39 kinematic variables, which showed that discriminating between univariate and multivariate imputation frameworks demonstrates that multivariate imputation frameworks surpassunivariate approaches when working with more complex missingness mechanisms. Specifically, multivariate approaches achieved up to a 50% error reduction (with the MAE improving from 10.8 ± 6.9 to 5.8 ± 5.5) compared to univariate methods for transition point missingness. Specialized time series deep learning models (i.e., SAITS, BRITS, GRU-D) demonstrated a superior performance with MAE values consistently below 8.0 for univariate contexts and below 3.2 for multivariate contexts across all missing data percentages, significantly surpassing traditional machine learning and statistical methods. Notable traditional methods such as Generative Adversarial Imputation Networks and Iterative Imputers exhibited a competitive performance but remained less stable than the specialized temporal models. This work offers an important baseline for future studies, in addition to recommendations for researchers looking to increase the accuracy and robustness of MoCap data analysis, as well as integrity and trustworthiness.
- Open Access
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
CLEVER: A Novel Approach for Improving EV Charging Duration and Load Predictions Using Curriculum Learning Approach
Despite advancements in electric vehicle (EV) charging prediction models, existing approaches are suffering from complex charging patterns. The curriculum learning (CL) is a training approach which resembles the natural human learning progression by introducing training samples through different patterns, hence efficiently structuring the learning process. While the CL has been successfully used in other domains, its application in EV charging prediction remains unexploited. In this work, the CL is to be leveraged for the first time to improve the EV charging behavior predictions in both EV charging duration and charging load prediction. A feature-based curriculum learning approach, named CLEVER (Curriculum Learning EV chargER), is proposed for predicting charging session load and duration. CLEVER employs an advanced data stratification mechanism that introduces training samples progressively according to complexity metrics computed from temperature variations, state of charge variations, and temporal patterns. The CLEVER method integrates a CL strategy with a staged schedule mechanism over four neural network architectures: ANN, DNN, LSTM, and GRU. The performances obtained exhibit notable gains, where CL scores 20.9% reduction of Mean Absolute Error for GRU-based forecasting of EV charging duration and 2.2% improvement for DNN-based charging load forecasting. The CLEVER methodology shows considerable improvements in predicting the duration of EV charging, with, as many as 23.0% reductions in Mean Absolute Error with GRU models on Level 1 chargers and a near 20.7% improvement with DNN models on DC Fast Chargers. For EV charging load forecasts, curriculum learning produces consistent, but modest, gains, with improved up to 2.4% with ANN models on DC Fast Chargers and 1.6-2.1% improvements across different neural network architectures. This comprehensive analysis across different charger types, user groups, vehicle models, temperatures, and temporal patterns makes CL a superior approach to enhancing EV charging infrastructure management and grid stability.
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessCLEVER: A Novel Approach for Improving EV Charging Duration and Load Predictions Using Curriculum Learning Approach
Despite advancements in electric vehicle (EV) charging prediction models, existing approaches are suffering from complex charging patterns. The curriculum learning (CL) is a training approach which resembles the natural human learning progression by introducing training samples through different patterns, hence efficiently structuring the learning process. While the CL has been successfully used in other domains, its application in EV charging prediction remains unexploited. In this work, the CL is to be leveraged for the first time to improve the EV charging behavior predictions in both EV charging duration and charging load prediction. A feature-based curriculum learning approach, named CLEVER (Curriculum Learning EV chargER), is proposed for predicting charging session load and duration. CLEVER employs an advanced data stratification mechanism that introduces training samples progressively according to complexity metrics computed from temperature variations, state of charge variations, and temporal patterns. The CLEVER method integrates a CL strategy with a staged schedule mechanism over four neural network architectures: ANN, DNN, LSTM, and GRU. The performances obtained exhibit notable gains, where CL scores 20.9% reduction of Mean Absolute Error for GRU-based forecasting of EV charging duration and 2.2% improvement for DNN-based charging load forecasting. The CLEVER methodology shows considerable improvements in predicting the duration of EV charging, with, as many as 23.0% reductions in Mean Absolute Error with GRU models on Level 1 chargers and a near 20.7% improvement with DNN models on DC Fast Chargers. For EV charging load forecasts, curriculum learning produces consistent, but modest, gains, with improved up to 2.4% with ANN models on DC Fast Chargers and 1.6-2.1% improvements across different neural network architectures. This comprehensive analysis across different charger types, user groups, vehicle models, temperatures, and temporal patterns makes CL a superior approach to enhancing EV charging infrastructure management and grid stability.
- 27 June 2025
- Published by Springer Nature
- p. 84-96
Leveraging Category-Specific Features and Geographic Context for Enhanced Fraud Detection
- 27 June 2025
- Published by Springer Nature
- p. 84-96
Leveraging Category-Specific Features and Geographic Context for Enhanced Fraud Detection
- 16 April 2025
- Published by Springer Nature
- p. 320-330
Enhancing Autonomous Vehicles Security: A Survey on GAT, Neural Networks, and Reinforcement Learning in AI-Driven Defense
- 16 April 2025
- Published by Springer Nature
- p. 320-330
Enhancing Autonomous Vehicles Security: A Survey on GAT, Neural Networks, and Reinforcement Learning in AI-Driven Defense
- Open Access
- 4 March 2025
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 39 (1)
Predicting Trip Duration and Distance in Bike-Sharing Systems Using Dynamic Time Warping
- 4 March 2025
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 39 (1)
Open AccessPredicting Trip Duration and Distance in Bike-Sharing Systems Using Dynamic Time Warping
- Open Access
- 11 March 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-18
Optimizing Placement and Scheduling for VNF by a Multi-objective Optimization Genetic Algorithm
Virtual network functions (VNFs) have gradually replaced the implementation of traditional network functions. Through efficient placement, the VNF placement technology strives to operate VNFs consistently to the greatest extent possible within restricted resources. Thus, VNF mapping and scheduling tasks can be framed as an optimization problem. Existing research efforts focus only on optimizing the VNFs scheduling or mapping. Besides, the existing methods focus only on one or two objectives. In this work, we proposed addressing the problem of VNFs scheduling and mapping. This work proposed framing the problem of VNFs scheduling and mapping as a multi-objective optimization problem on three objectives, namely (1) minimizing line latency of network link, (2) reducing the processing capacity of each virtual machine, and (3) reducing the processing latency of virtual machines. Then, the proposed VNF-NSGA-III algorithm, an adapted variation of the NSGA-III algorithm, was used to solve this multi-objective problem. Our proposed algorithm has been thoroughly evaluated through a series of experiments on homogeneous and heterogeneous data center environments. The proposed method was compared to several heuristic and recent meta-heuristic methods. The results reveal that the VNF-NSGA-III outperformed the comparison methods.
- 11 March 2024
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 17 (1) , 1-18
Open AccessOptimizing Placement and Scheduling for VNF by a Multi-objective Optimization Genetic Algorithm
Virtual network functions (VNFs) have gradually replaced the implementation of traditional network functions. Through efficient placement, the VNF placement technology strives to operate VNFs consistently to the greatest extent possible within restricted resources. Thus, VNF mapping and scheduling tasks can be framed as an optimization problem. Existing research efforts focus only on optimizing the VNFs scheduling or mapping. Besides, the existing methods focus only on one or two objectives. In this work, we proposed addressing the problem of VNFs scheduling and mapping. This work proposed framing the problem of VNFs scheduling and mapping as a multi-objective optimization problem on three objectives, namely (1) minimizing line latency of network link, (2) reducing the processing capacity of each virtual machine, and (3) reducing the processing latency of virtual machines. Then, the proposed VNF-NSGA-III algorithm, an adapted variation of the NSGA-III algorithm, was used to solve this multi-objective problem. Our proposed algorithm has been thoroughly evaluated through a series of experiments on homogeneous and heterogeneous data center environments. The proposed method was compared to several heuristic and recent meta-heuristic methods. The results reveal that the VNF-NSGA-III outperformed the comparison methods.
- Open Access
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 98707-98722
Optimizing Real-Time Video Transmission for Surgical Tele-Education Through ERV Algorithm
- 1 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 98707-98722
Open AccessOptimizing Real-Time Video Transmission for Surgical Tele-Education Through ERV Algorithm
- Open Access
- 22 July 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (14) , 3219
An Adaptive Jellyfish Search Algorithm for Packing Items with Conflict
The bin packing problem (BPP) is a classic combinatorial optimization problem with several variations. The BPP with conflicts (BPPCs) is not a well-investigated variation. In the BPPC, there are conditions that prevent packing some items together in the same bin. There are very limited efforts utilizing metaheuristic methods to address the BPPC. The current methods only pack the conflict items only and then start a new normal BPP for the non-conflict items; thus, there are two stages to address the BPPC. In this work, an adaption of the jellyfish metaheuristic has been proposed to solve the BPPC in one stage (i.e., packing the conflict and non-conflict items together) by defining the jellyfish operations in the context of the BPPC by proposing two solution representations. These representations frame the BPPC problem on two different levels: item-wise and bin-wise. In the item-wise solution representation, the adapted jellyfish metaheuristic updates the solutions through a set of item swaps without any preference for the bins. In the bin-wise solution representation, the metaheuristic method selects a set of bins, and then it performs the item swaps from these selected bins only. The proposed method was thoroughly benchmarked on a standard dataset and compared against the well-known PSO, Jaya, and heuristics. The obtained results revealed that the proposed methods outperformed the other comparison methods in terms of the number of bins and the average bin utilization. In addition, the proposed method achieved the lowest deviation rate from the lowest bound of the standard dataset relative to the other methods of comparison.
- 22 July 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (14) , 3219
Open AccessAn Adaptive Jellyfish Search Algorithm for Packing Items with Conflict
The bin packing problem (BPP) is a classic combinatorial optimization problem with several variations. The BPP with conflicts (BPPCs) is not a well-investigated variation. In the BPPC, there are conditions that prevent packing some items together in the same bin. There are very limited efforts utilizing metaheuristic methods to address the BPPC. The current methods only pack the conflict items only and then start a new normal BPP for the non-conflict items; thus, there are two stages to address the BPPC. In this work, an adaption of the jellyfish metaheuristic has been proposed to solve the BPPC in one stage (i.e., packing the conflict and non-conflict items together) by defining the jellyfish operations in the context of the BPPC by proposing two solution representations. These representations frame the BPPC problem on two different levels: item-wise and bin-wise. In the item-wise solution representation, the adapted jellyfish metaheuristic updates the solutions through a set of item swaps without any preference for the bins. In the bin-wise solution representation, the metaheuristic method selects a set of bins, and then it performs the item swaps from these selected bins only. The proposed method was thoroughly benchmarked on a standard dataset and compared against the well-known PSO, Jaya, and heuristics. The obtained results revealed that the proposed methods outperformed the other comparison methods in terms of the number of bins and the average bin utilization. In addition, the proposed method achieved the lowest deviation rate from the lowest bound of the standard dataset relative to the other methods of comparison.