Recent Submissions

  • Supply Chain 5.0: Vision, Challenges, and Perspectives

    Boudouaia, Mohammed Amine; Ouchani, Samir; Mian Qaisar, Saeed; Turki Almaktoom, Abdulaziz; University Collaboration; Artificial Intelligence & Cyber Security Lab; 0; 0; Electrical and Computer Engineering; 0; et al. (IEEE, 2024-03-21)
    The recent technological advancements have transformed the modern supply chains in complex networks. Consequently, modern supply chain systems are facing several challenges, including limited visibility in both upstream and downstream supply chains, lack of trust among the different stakeholders, and transparency plus traceability. Current supply chain systems do not present the needed framework to overcome the existing challenges. On the other hand, the new paradigm of the Supply Chain 5.0 has the potential to effectively address these obstacles and incorporates the foresight of future disruptions. This paper aims to explore the emerging paradigm of supply chain 5.0 and conduct a systematic analysis of recent and relevant works related to this supply chain version. Additionally, it aims to examine its visionary aspects, analyze associated challenges, and provide insights to the potential future directions of supply chain management. We have systematically analyzed the recent and relevant works addressing this new vision of supply chains.
  • Hybrid Metaheuristics for Industry 5.0 Multi-Objective Manufacturing and Supply Chain Optimization

    Bezoui, Madani; Turki Almaktoom, Abdulaziz; Bounceur, Ahcène; Mian Qaisar, Saeed; Chouman, Mervat; University Collaboration; External Collaboration; Artificial Intelligence & Cyber Security Lab; 0; 0; et al. (IEEE, 2024-03-21)
    This paper explores the transition to Industry 5.0, highlighting its focus on sustainable, human-centred and resilient industrial progress. In this new era, the integration of advanced technology with human expertise is crucial, emphasising the importance of balancing efficiency, cost, quality, and sustainability. At the heart of this research is Multi-Objective Optimisation (MOO), which is used to address the complex challenges of modern manufacturing systems. We propose an innovative approach that combines mathematical modelling with swarm intelligence to tackle complex optimisation problems. A detailed Multi-Objective Mixed Integer Linear Programming (MILP) model is developed and its effectiveness is demonstrated through the application of Multi-Objective Particle Swarm Optimisation (MOPSO). The study compares the performance of MOPSO with traditional optimisation methods using synthetic data analysis. The results not only demonstrate the potential of MOPSO in modern manufacturing, but also set the stage for future research to integrate human ergonomics into the optimization framework, thereby contributing to the holistic advancement of Industry 5.0.
  • Optimal placement and sizing of distributed generation for power factor improvement

    Junaid, Muhammad; Waqar, Asad; Mian Qaisar, Saeed; External Collaboration; Energy Lab; 0; 0; Electrical and Computer Engineering; 0; Junaid, Muhammad (IEEE, 2024-03-21)
    The present investigation utilizes the Forward-Backward Sweep (FBS) technique in combination with the Sea Horse Optimization (SHO) algorithm to maximize the distribution network's capacity and arrange Distributed Generators (DGs) according to their intended use case. Through the use of Torrit software and the integration of MATPOWER toolbox in MATLAB, the network is methodically assessed under four scenarios (Case A to Case D), featuring four DG types (type 1, type 2, type 3, and type 4). The most promising of them is Case C, which uses type 3 DGs and shows impressive reductions in reactive and active power loss along with a significant increase in power factor and voltage profile. The conclusions provide utility operators looking for the best DG deployment tactics with insightful information.
  • PWM based Software defined radio Modeling

    Ahmed Sakr; Hussein, Aziza; Ghazal A. Fahmy; Mahmoud A. Abdelghany; External Collaboration; NA; NA; NA; Electrical and Computer Engineering; NA; et al. (IEEE, 2024-02-06)
    Modern wireless networks are allocated in different frequency bands and have different specifications. However, many wireless devices are required to support different standards which is the case for mobile devices and IoT. For example, a modern mobile device usually supports 5G or 4G besides older generations back to 2G, Wi-Fi standards 802.11 a/b/g/n/ac and Bluetooth with its different versions. To support all these standards, an increasing complexity is added to the design of RF front-end that should be more flexible and more programmable.Software-defined-radio SDR aims to achieve a flexible front-end that is fully programmable and flexible in order to support more standards in different frequency bands and with different specifications. It takes advantage of the increasing enhancements in IC fabrication processes which enables performing signal processing in digital domain with high speed and accuracy more than what analog signal processing can achieve.In this work, a review of traditional receivers as well as multistandard receivers and SDRs are performed, then an SDR based on Pulse-width-modulation PWM RF-to-digital receiver is demonstrated. The chosen PWM based SDR is modeled using MATLAB Simulink.
  • Comparison Between Different MPPT Methods Applied to a Three-Port Converter

    Amani S. Alzahrani; Hussein, Aziza; Marwa M. Ahmed; Mohamed A. Enany; External Collaboration; NA; NA; NA; Electrical and Computer Engineering; 1; et al. (Springer, Cham, 2023-08-02)
    Recently, the interest in renewable energy has gained interest since these sources are promising for generating electricity. Solar energy tops the list of renewable energy sources. Solar photovoltaic (PV) panels are used to capture the solar energy radiated from the sun. Since solar energy is unavailable throughout the day, a battery is added. In a PV/battery system, a three-port converter is needed to interface the PV and battery with the load. This paper applies Maximum Power Point Tracking (MPPT) methods to a system with a three-port converter. These methods are Perturb and Observe (P&O) and Incremental Conductance (IC). MATLAB/SIMULINK software is used to perform the simulation. The temperature and irradiance are varied to simulate environmental changes in a real-world environment. Based on the results, the IC method performs slightly better than P&O. This indicates that a three-port converter is more stable regarding environmental changes than regular two-port converters. The usage of a three-port converter has gained recent interest. The significance of this paper is that it compares different MPPT methods applied to a three-port converter to be able to determine the suitable MPPT for a specific application.
  • The Redefinition of mHealth Applications in Metaverse

    ElKafrawy, Passent; Abbas, Hagar; AlFarra, Joud; Alam, Leena; Junaid, Mehreen; Department Collaboration; Virtual Reality Lab; 4; 0; Computer Science; et al. (IEEE, 2023-04-11)
    The term "mobile health" (sometimes spelled "mHealth" or "m-Health") refers to the delivery of medical services via smartphones, tablets, PDAs, and PCs. The metaverse combines the real world and the virtual world, allowing people to interact with their avatars in a setting supported by cutting-edge technologies like high-speed internet, virtual reality, augmented reality, mixed reality, extended reality, blockchain, digital twins, artificial intelligence (AI), all of which are enhanced by practically limitless data. This paper discusses how these technologies might be used in digital medicine in the future, as well as the potential of the medical metaverse. This qualitative study examines and evaluates past articles and websites. The healthcare business depends heavily on physical connection, eye contact, facial expressions, and gestures, which the metaverse can simulate virtually. However, the metaverse may be viewed as a tool to improve the effectiveness of the healthcare system in terms of intervention and treatment, worldwide education, assuring consistent training, and assisting in the development of global databases for research. Finally, the metaverse may be a location where young people can start practicing and acquiring new skills considering how much time they spend in front of screens.
  • Deep Reinforcement Learning for multiobjective Scheduling in Industry 5.0 Reconfigurable Manufacturing Systems⋆

    Madani Bezoui; Abdelfatah Kermali; Ahcène Bounceur; Mian Qaisar, Saeed; External Collaboration; NA; NA; NA; Electrical and Computer Engineering; NA; et al. (HAL open science, 2023-11-28)
    In modern-day manufacturing, it is imperative to react promptly to altering market requirements. Reconfigurable Manufacturing Systems (RMS) are a significant leap forward in achieving this criteria as they offer a flexible and affordable structure to comply with evolving production necessities. The ever-changing nature of RMS demands a sturdy induction of learning algorithms to persistently improve system configurations and scheduling. This study suggests that using Reinforcement Learning (RL), specifically, the Double Deep Q-Network (DDQN) algorithm, is a feasible way to navigate the intricate, multi-objective optimization landscape of RMS. Key points to consider regarding this study include cutting down tardiness costs, ensuring sustainability by reducing wasted liquid and gas emissions during production, optimizing makespan, and improving ergonomics by reducing operator intervention during system reconfiguration. Our proposal consists of two layers. Initially, we suggest a hierarchical and modular architecture for RMS which includes a multi-agent environment at the reconfigurable machine tool level, which improves agent interaction for optimal global results. Secondly, we incorporate DDQN to navigate the multi-objective space in a clever manner, resulting in more efficient and ergonomic reconfiguration and scheduling. The findings indicate that employing RL can help solve intricate optimization issues that come with contemporary manufacturing paradigms, clearing the path for Industry 5.0.
  • Artificial Intelligence Assistive Fire Detection and Seeing the Invisible Through Smoke Using Hyperspectral and Multi-Spectral Images

    Ahed Alboody; Mian Qaisar, Saeed; Gilles Roussel; External Collaboration; NA; NA; NA; Electrical and Computer Engineering; NA; Ahed Alboody (IEEE, 2023-11-10)
    The global warming has serious impact on our climate. Due to this, the frequency and the intensity of forest fires is increasing. It has shown serious challenges such as the protection of resources, human and wild life, health, and property. This study focuses on developing an artificial intelligence assistive innovative solution for active fire detection in the context of smart cities and vicinities. This paper addresses spectral analysis, detection and classification of active fires and seeing the invisible through smoke and thin clouds. The appealing applications are in urban surveillance, smart cities, future industries, forests and earth observation. The idea is realizable by using an intelligent hybridization of machine/deep learning models and using multi-sensor images (aerial, satellite). For this purpose, we use hyperspectral images (Visible, Near Infra-red (NIR) and Short-Wave Infrared (SWIR)) from AVIRIS aerial and Multi-Spectral Sentinel-2 satellite images. AVIRIS images are 224 spectral bands of wavelengths with a spatial resolution of 15 meters, which varies from 366nm (nanometers) up to 2500nm. However, AVIRIS image studied for their spectral richness of wavelengths not yet completely exploited by machine and deep learning and in SWIR to detect active fires. While, Sentinel-2 image has 13 spectral bands (Visible, NIR and SWIR) with three spatial resolutions (10, 20 and 60 meters). First, we explain and describe the preparation phase of hyperspectral and multispectral image databases of forest fires. These databases contain hyperspectral and multispectral endmembers data of different sites for forest fires. Then, we conduct a spectral analysis from these endmembers to characterize the hyperspectral/multispectral reflectance of active fires to identify the distinct wavelengths for fire detection. We identify the wavelengths that can be used for an effective identification of fire and to see through fires smoke and thin clouds. Onward, the selected feature set is processed by robust machine/deep learning algorithms and their performance is compared for automated identification of fire and invisible vision amelioration. The proposed machine/deep learning method secured an overall test accuracy of 99.1%.
  • Boosting Regression Assistive Predictive Maintenance of the Aircraft Engine with Random-Sampling Based Class Balancing

    Ibrahima Barry; Meriem Hafsi; Mian Qaisar, Saeed; External Collaboration; NA; NA; NA; Electrical and Computer Engineering; NA; Ibrahima Barry (Springer, 2024-01-17)
    This study presents the development of a data-driven predictive maintenance model in the context of industry 4.0. The solution is based on a novel hybridization of Remaining Useful Life (RUL) generation, Min-Max normalization, random-sampling based class balancing, and XGBoost regressor. The applicability is tested using the NASA's C-MAPSS dataset, which contains aircraft engine simulation data. The objective is to develop an effective and Artificial Intelligence (AI) assistive automated aircraft engine's RUL predictor. It can maximize the benefits of predictive maintenance. The rules based RUL generation provides a ground truth for evaluating the performance of intended regressors. The Min-Max normalization linearly transforms the intended dataset and scales the multi subject's data in a common range. The imbalance presentation among intended classes can lead towards a biasness in findings. This issue is intelligently resolved using the uniformly distributed random sub-sampling. Onward, the performance of robust machine learning and ensemble learning algorithms is compared for predicting the RUL of the considered aircraft engine by processing the balanced dataset. The results have shown that the XGBoost regressor, uses an ensemble of decision trees, outperforms other considered models. The root mean square error (RMSE) and mean absolute error (MAE) indicators will be used to evaluate the prediction performances. The devised method secures the RMSE value of 12.88%. It confirms a similar or better performance compared to the state-of-the-art counterparts.
  • Exploring the Maze: A Comparative Study of Path Finding Algorithms for PAC-Man Game

    Salem, Nema; Haneya, Hala; Balbaid, Hanin; Asrar, Manal; No Collaboration; NA; 3; 0; Electrical and Computer Engineering; 0; et al. (IEEE, 2024)
    Artificial Intelligence (AI) has become an integral part of our lives, finding applications across various industries. Search algorithms play a crucial role in AI. This paper focuses on the comparison of different search algorithms within the context of path-planning in the UC Berkeley’s PAC-Man’s game. The algorithms under consideration include Depth-First Search (DFS), Breadth-First Search (BFS), Uniform Cost Search (UCS), Iterative Deepening Depth First Search (IDDFS), and A∗ Search. The objective is to identify the most effective algorithm in terms of path-finding performance. The study’s findings reveal that the A∗ search algorithm outperforms the others in terms of score, cost, and node expansion, making it the most suitable choice for finding the shortest path in the PAC-Man’s game.
  • Photovoltaics Maximum Power Tracking by the Hybrid Perturb-Observe and Sliding Mode Control Strategies

    Salem, Nema; Alammari, Eithar; Alamro, Joud; Alashwali, Sara; No Collaboration; NA; 3; 0; Electrical and Computer Engineering; 0; et al. (IEEE, 2024)
    To increase photovoltaic PV power, the point of maximum power, MPPT, must be tracked effectively. The oscillation around the operating point is the main drawback of MPPT, obtaining techniques. This study suggests combining the Perturb and Observe, PO, and Sliding Mode Control, SMC, strategies to reduce this problem and deal with the nonlinearities of the solar panels under different climate situations. The SMC creates a sliding surface that establishes the operational point and increases the stability of the PO. The gate of a DC-DC converter quickly reaches this defined surface, and the duty cycle adjustment ensures maximum power in all conditions. This study utilized MATLAB/Simulink to design and analyze this combined control system. The outcomes supported the PO and SMC strategy’s reliability and successful operation under various environmental circumstances.
  • Boosting Wind Harvest: FOPID Pitch Angle Controller for Turbines

    Jamjoom, Jude; Qashqari, Maha; Alzahrani, Mariah; No Collaboration; NA; 3; 0; Electrical and Computer Engineering; 0; Salem, Nema (IEEE, 2024)
    Wind turbine blades are subjected to a variety of loads, including aerodynamic and gravitational loads. These loads produce aerodynamic strain and vibration in the blades, resulting in rotor blade damage and a reduction in the wind turbine’s system efficiency. This could be prevented by implementing a proper pitch angle controller that plays a crucial role in boosting the energy capture and overall performance of wind power systems. The conventional Proportional-Integral-Derivative, PID, controller has been widely utilized for pitch control, but it often faces challenges in meeting the requirements of complex and dynamic wind conditions. To address these limitations, this study explores the implementation of the Fractional Order Proportional-Integral-Derivative, FOPID, controller for wind turbine pitch control. This paper presents a comparative analysis between the PID and FOPID controllers for wind turbine pitch control. The performance of both controllers is evaluated through Simulink. The results demonstrate that the FOPID controller exhibits superior performance in terms of faster response time, and improved steady-state error compared to the PID controller.
  • Analysis and Design of Various Types of DC-DC Converters: A Comprehensive Study

    Salem, Nema; Almatrafi, Lina; Basmah Shigdar; Alaidaroos, Batool; No Collaboration; NA; 3; 0; Electrical and Computer Engineering; 0; et al. (IEEE, 2024)
    DC-DC converters are essential components in power electronics systems, enabling efficient voltage conversion and regulation. This paper presents a comprehensive study on the analysis and design of different types of DC-DC converter topology including Boost, Cuk, SEPIC, and Zeta converters. The design aspect of DC-DC converters covers the component selection to assist in achieving desired converter performance and meeting specific application requirements. The analysis focuses on examining key performance parameters such as efficiency, voltage ripple, transient response, and output regulation. To validate the theoretical analysis and design principles, simulation tools such as Simulink and MATLAB are employed.
  • Modeling and Analysis of a Thermoelectric Power Generator

    Salem, Nema; No Collaboration; NA; 0; 0; Electrical and Computer Engineering; 0; Salem, Nema (IEEE, 18 Decembe)
    Thermoelectric Generator (TEG) was developed using the Seebeck phenomenon. It consists of many thermocouples connected thermally in parallel and electrically in series to increase energy efficiency. TEGs instantly convert thermal energy to electrical energy with no rotating parts and are less likely to fail due to no moving parts. With the rising cost of fossil fuels and their negative impact on the atmosphere, it is time to consider TEGs as renewable energy sources with applications ranging from mW to W power. This study derives a mathematical model of a TEG module and validates it with MATLAB/SIMULINK.
  • Pole-Placement and Different PID Controller Structures Comparative Analysis for a DC Motor Optimal Performance

    Salem, Nema; Ali, Mirna; No Collaboration; NA; Mirna Ali; 0; Electrical and Computer Engineering; 0; Salem, Nema (IEEE, 2024)
    The pole-placement method is a popular technique used in control system design to assign desired closed loop system poles. By strategically placing these poles, the system’s dynamic response can be tailored to meet specific performance requirements. This study focuses on the design and simulation of the pole-placement method and various structures of Proportional-Integral-Derivative P ID controllers to determine the best-performing controller for a modeled DC motor. The study explores different PID controller structures, including parallel, series, (P I − D), and (I − P D). In addition, it employs a comprehensive analysis by utilizing a range of performance metrics such as settling time, overshoot, and rise time. The pole placement utilizes the state space technique to assign the desired closed loop poles while the controllers are tuned using Ziegler-Nichols, to achieve optimal performance. The results shows that the (I − P D) controller is the optimal controller for this application, with a rise time of 0.507 seconds, a settling time of 2.3 seconds, and an 0.51% overshoot.
  • Performance of LQR and PID Controllers for RS-550VC Motor Speed Enhancement

    Salem, Nema; Mateen, Kulsoom; Alharbi, Wafa; Kamal, Jana; No Collaboration; NA; 3; 0; Electrical and Computer Engineering; 0; et al. (IEEE, 2023-09-25)
    Motor speed control is a critical aspect of many industrial and commercial applications. This paper investigates the performance of two widely used control techniques, Linear Quadratic Regulator LQR and Proportional-Integral-Derivative PID, for motor speed control. We perform a simulation study using MATLAB to compare the performance of these two controllers in terms of their ability to track the reference speed profile. The simulation results show that LQR and PID controllers can achieve accurate speed tracking, but their performance characteristics differ significantly. LQR is better in the steady state and overshoot but slower than PID. Our study provides insights into the trade-offs between these two controllers and can guide the selection of an appropriate control technique for a given motor speed control application.
  • Enhancing Cruise Performance through PID Controller Tuned with Particle Swarm Optimization Technique

    Salem, Nema; Hassan, Rana; Muthanna, Lina; No Collaboration; NA; 2; 0; Electrical and Computer Engineering; 0; Salem, Nema (IEEE, 2023)
    The Proportional-Integral-Derivative (PID) controller is a widely used feedback control mechanism in various applications, including automobile cruise control systems. The performance of a PID controller is highly dependent on the values of its tuning parameters, which can be challenging to determine in practice. Particle Swarm Optimization (PSO) has emerged as a powerful optimization algorithm that can tune the PID controller parameters for optimal performance. The PSO is a metaheuristic optimization algorithm inspired by the social behavior of birds and fish. The PSO-PID is a variant of the PID controller that employs PSO to optimize its tuning parameters. PSO-PID offers several advantages over traditional PID tuning methods, including improved accuracy, stability, and robustness. This paper briefly overviews the PSO-PID algorithm and its application to automobile cruise control systems. The paper discusses the key steps involved in PSO-PID tuning, including initialization, evaluation, update, and termination. It provides an example of how PSO-PID can achieve optimal vehicle speed control. The paper highlights the advantages of PSO-PID over traditional PID tuning methods. PSO-PID is a promising technology for cruise control systems and has the potential to significantly improve the safety, comfort, and efficiency of modern automobiles.
  • A Secured Blockchain Framework for Healthcare Data Management System

    Ahmed, Toqeer; Mian Qaisar, Saeed; Waqar, Asad; External Collaboration; Artificial Intelligence & Cyber Security Lab; 0; 0; Electrical and Computer Engineering; 0; Ahmed, Toqeer (IEEE, 2023-12-11)
    In the healthcare system, electronic medical records are very critical, and they must be authenticated and verified. During the medical check-up, a large amount of patient medical data is generated which includes reports related to blood, life-threatening diseases, and personal information such as credit card numbers and addresses. Any privacy breach in patient medical records will bring various risks. A simple blockchain (Ethereum) can be effective to validate and authenticate stored data by deploying an immutable ledger. However, the main challenge in the simple blockchain is that its data can be easily accessible. In this paper, the authors create a business network for healthcare using Hyperledger fabric, which ensures that data is only available to the concerned person and its access rights are granted and revoked by the concerned participant. Additionally, the authors tested different scenarios to access blockchain security and its benefits.
  • Hybradization of Emperical Mode Decomposition and Machine Learning for Categorization of Cardiac Diseases

    Milyani, Danah; Mian Qaisar, Saeed; Mohammad, Nouf; Alhamdan, Alhanoof; Slama, Rim; Hamour, Nora; Department Collaboration; External Collaboration; Biometrics and Sensory Systems Lab; 3; et al. (IEEE, 2023-11-10)
    The arrhythmia is one of the cardiovascular diseases which has several types. In literature, researchers have presented a broad study on the strategies utilized for Electrocardiogram (ECG) signal investigation. Automated arrhythmia detection by analyzing the ECG data is reported using a number of intriguing techniques and discoveries. In order to effectively categorize arrhythmia, a novel approach based on the hybridization of the denoising filter, QRS complex segmentation, “Empirical Mode decomposition” (EMD), “Intrinsic Mode Functions” (IMFs) based features extraction, and machine learning techniques is developed in this study. To evaluate the categorization accuracy, the 10-fold cross validation (10-CV) strategy is used. Using an arrhythmia dataset that is publically available for research, the performance of our method is evaluated. A 97% average accuracy score is secured by our method for the problem of 5-class arrhythmias. These findings are comparable or better than counterparts.
  • Machine Learning Assistive State of Charge Estimation of Li-Ion Battery

    Mian Qaisar, Saeed; Alboody, Ahed; Aldossary, Shahad; Alhamdan, Alhanoof; Moahammad, Nouf; Turki Almaktoom, Abdulaziz; Department Collaboration; University Collaboration; External Collaboration; Energy Lab; et al. (IEEE, 2023-11-10)
    For an effective and economical deployment of battery-powered electric vehicles, mobile phones, laptops, and medical gadgets, the State of Charge (SoC) of the batteries must be properly assessed. It permits a safe operation, have a longer usable battery life, and prevent malfunctions. In this context, the battery management systems provide diverse SoC estimation solutions. However, the Machine Learning (ML) based SoC estimation mechanisms are becoming popular because of their robustness and higher precision. In this study, the features set is prepared using the intended battery cell charge/discharge curves for voltage, current, and temperature. Utilizing statistical analysis and the shape context, the attributes are extracted. Following that, three credible machine learning (ML) algorithms-decision trees, random forests, and linear regression-process the set of mined attributes. The applicability is tested using the Panasonic Lithium-Ion (Li-Ion) battery cells, publicly provided by the McMaster University. The feature extraction and the ML based SoC prediction modules are implemented in MATLAB. The “correlation coefficient”, “mean absolute error”, and “root mean square error” are used to assess the prediction performance. The results show an outperformance of the random forest regressor among the intended ones by attaining the correlation coefficient value of 0.9988.

View more