Master

Jan 9, 2018 - Aug 16, 2021

Computer engineering

Computer architecture, Digital controller [AL-Hadba University]

Sep 24, 2022 - Apr 26, 2023

Investment Green Internet of Things for Sustainable and Eco-Friendly Smart Cities: Prospects and Future Challenges

Dec 6, 2025

Journal Journal of Rafidain Environment

publisher جامعة الموصل

DOI https://doi.org/10.33899/rengj.2022.130477.1108

Issue 2

Volume 3

The study explores the integration of the Green Internet of Things (IoT) into the development of sustainable and eco-friendly smart cities. It highlights the challenges posed by urbanization, such as pollution, congestion, and resource inefficiencies, and emphasizes the transformative role of IoT in creating innovative urban systems. Green IoT facilitates energy conservation, waste management, air quality monitoring, and efficient transportation through innovative applications and technologies. Key focus areas include leveraging renewable energy sources, optimizing resource utilization, and implementing eco-friendly technologies to reduce greenhouse gas emissions and promote sustainable practices. Despite its potential, challenges such as data management, security concerns, and the energy consumption of IoT devices persist, necessitating the development of advanced solutions. Case studies, including those in Singapore and Barcelona, illustrate the successful implementation of green strategies and technologies in urban environments. The paper concludes by emphasizing future research directions, including improving interoperability, managing electronic waste, and developing energy-efficient Internet of Things (IoT) frameworks to achieve smarter and greener cities. This research examines how the Green Internet of Things (IoT) can make our cities cleaner, smarter, and more sustainable. It explores how smart technologies can enhance everyday aspects such as energy use, waste management, and transportation. The goal is to develop greener cities that are more beneficial for both people and the planet.

Read Publication

Evaluating Facial Emotional Proportion Based on Computer Vision Technique

Sep 17, 2025

Journal Journal of Image and Graphics,

publisher University of Portsmouth

DOI https://www.joig.net/2025/JOIG-V13N5-469.pdf

Issue 5

Volume 13

Emotion detection is a technique to recognize human emotions by addressing facial expressions. It is essential for psychology, security systems, and humancomputer interaction. The ability to perceive and interpret an individual’s facial expressions helps to understand their actions and improve the interaction between a person and a computer. Facial Emotion Recognition (FER) is instrumental whenever there is a need for human-computer interaction for behavioral assessment, like in clinical usage. When using machine learning models in the FER field, the accuracy and robustness remain difficult because of the diversity of human faces and image changes, such as differences in spatial pose and lighting. This research used the FER2013 dataset, which contained approximately 30,000 images divided into seven classes (anger face, disgust face, fear face, happy face, sad face, surprise face, and neutral face). It also used two Convolutional Neural Networks (CNN) models (VGG19 and Sequential). The result of the VGG19 model achieved 68% accuracy, validation accuracy achieved 66%, the Sequential model achieved 78% accuracy, and validation accuracy achieved 67%. To address the limitations of single-stream models, a novel hybrid architecture is proposed that integrates ResNet50, MobileNetV2, and a Convolutional Block Attention Module (CBAM)-enhanced CNN through feature-level fusion. This design enables the model to capture diverse and salient facial features, significantly improving recognition accuracy on the FER2013 dataset. The proposed method achieved 96% accuracy, and the validation accuracy was 91%.

Evaluating Facial Emotional Proportion Based on Computer Vision Technique

Sep 17, 2025

Journal Journal of Image and Graphics,

publisher University of Portsmouth

DOI https://www.joig.net/2025/JOIG-V13N5-469.pdf

Issue 5

Volume 13

Emotion detection is a technique to recognize human emotions by addressing facial expressions. It is essential for psychology, security systems, and humancomputer interaction. The ability to perceive and interpret an individual’s facial expressions helps to understand their actions and improve the interaction between a person and a computer. Facial Emotion Recognition (FER) is instrumental whenever there is a need for human-computer interaction for behavioral assessment, like in clinical usage. When using machine learning models in the FER field, the accuracy and robustness remain difficult because of the diversity of human faces and image changes, such as differences in spatial pose and lighting. This research used the FER2013 dataset, which contained approximately 30,000 images divided into seven classes (anger face, disgust face, fear face, happy face, sad face, surprise face, and neutral face). It also used two Convolutional Neural Networks (CNN) models (VGG19 and Sequential). The result of the VGG19 model achieved 68% accuracy, validation accuracy achieved 66%, the Sequential model achieved 78% accuracy, and validation accuracy achieved 67%. To address the limitations of single-stream models, a novel hybrid architecture is proposed that integrates ResNet50, MobileNetV2, and a Convolutional Block Attention Module (CBAM)-enhanced CNN through feature-level fusion. This design enables the model to capture diverse and salient facial features, significantly improving recognition accuracy on the FER2013 dataset. The proposed method achieved 96% accuracy, and the validation accuracy was 91%.

Adaptive control of a DC servo motor using particle swarm and gray wolf optimization algorithms

May 3, 2025

Journal 3RD INTERNATIONAL CONFERENCE ON MATHEMATICS, AI, INFORMATION AND COMMUNICATION TECHNOLOGIES: ICMAICT2023

publisher AIP Conf. Proc

DOI https://doi.org/10.18196/jrc.v6i1.24958

Servomotors are essential in industrial position control applications, due to their feedback control system, high accuracy, simple controllability, efficiency, and position control capabilities. In this research, a method for adaptive control of a DC servomotor utilizing gray wolf optimization (GWO) and particle swarm optimization (PSO) algorithms is presented. The suggested control strategies aim to decrease (rise time, settling time, and overshooting) to enhance the DC servo engine's performance. Simulations are used to assess the efficacy of the suggested techniques, and the findings show that the (adaptive PSO and GWO-based control) approaches perform noticeably had better than conventional PID control techniques. The suggested techniques present a viable means of improving DC servo engine performance in a range of industrial applications. The most important in this paper depends on the third-order equations that deal with details specifications and parameters of the motor. These parameters will lead to an increase in the complexity of the transfer function for the motor. MATLAB software was used to validate the simulation and calculate the results values. The results show that the (APSO) are most powerful performance, where its rise time is enhanced by (97%), settling time (95%), and overshoot (85%).

Read Publication

Adaptive control of a DC servo motor using particle swarm and gray wolf optimization algorithms

May 3, 2025

Journal 3RD INTERNATIONAL CONFERENCE ON MATHEMATICS, AI, INFORMATION AND COMMUNICATION TECHNOLOGIES: ICMAICT2023

publisher AIP Conf. Proc

DOI https://doi.org/10.18196/jrc.v6i1.24958

Servomotors are essential in industrial position control applications, due to their feedback control system, high accuracy, simple controllability, efficiency, and position control capabilities. In this research, a method for adaptive control of a DC servomotor utilizing gray wolf optimization (GWO) and particle swarm optimization (PSO) algorithms is presented. The suggested control strategies aim to decrease (rise time, settling time, and overshooting) to enhance the DC servo engine's performance. Simulations are used to assess the efficacy of the suggested techniques, and the findings show that the (adaptive PSO and GWO-based control) approaches perform noticeably had better than conventional PID control techniques. The suggested techniques present a viable means of improving DC servo engine performance in a range of industrial applications. The most important in this paper depends on the third-order equations that deal with details specifications and parameters of the motor. These parameters will lead to an increase in the complexity of the transfer function for the motor. MATLAB software was used to validate the simulation and calculate the results values. The results show that the (APSO) are most powerful performance, where its rise time is enhanced by (97%), settling time (95%), and overshoot (85%).

Read Publication

Performance Optimization of BLDC Motor Control Using Sand Cat Swarm Algorithm and Linear Quadratic Regulator

May 2, 2025

Journal Journal of Robotics and Control (JRC)

publisher Universitas Muhammadiyah Yogyakarta in collaboration with Peneliti Teknologi Teknik Indonesia

DOI https://doi.org/10.18196/jrc.v6i1.24958

Issue No. 1 (2025)

Volume Vol. 6

Brushless Direct Current (BLDC) motors are widely utilized in industrial applications due to their precision, efficiency, and ease of control. This study optimizes BLDC motor performance by enhancing the linear quadratic regulator (LQR) using the Matlab program's Sand Cat Swarm Optimization (SCSO) algorithm. The research evaluates key performance metrics, including settling time, overshoot, and cost function, to demonstrate the advantages of the proposed approach. Additionally, a comparative analysis was conducted using the butterfly optimization algorithm (BOA) and conventional LQR to validate the superiority of SCSO. Simulation results show that the LQR-SCSO method significantly improves performance, achieving a 77.2% reduction in settling time, a 91% reduction in overshoot, and a cost function of 0.3376. In comparison, the BOA method achieves reductions of 68.54% in settling time, 67.37% in overshoot, and a cost function of 0.8736, while the conventional LQR achieves reductions of 68% in settling time, 62.3% in overshoot, and a cost function of 1.8393. SCSO has excellent convergence and adaptability; however, the implementation is explored further in terms of computational cost adopted for industrial use in real time. The data are so highly processed that better controls are implemented to repeat simulations across defined parameters. The proposed LQR-SCSO approach is practical and potent in enhancing motor performance, which is a significant advancement and can applied in various fields in the industry, such as robotics and automated systems. However, the proposed method may face obstacles related to the higher computational complexity of higher-order applications, which can be a subject of future studies.

Read Publication

Diagnosing Gingiva Disease Using Artificial Intelligence Techniques

Jan 6, 2025

Journal Diyala Journal of Engineering Sciences

publisher University of Diyala of Engineering Sciences

DOI https://doi.org/10.24237/djes.2024.18211

Issue 2

Volume 18

Gingival and periodontal diseases, such as gingivitis and periodontitis, are critical public health concerns that can lead to severe complications if left untreated. Early and precise diagnosis is crucial to mitigate the progression of these conditions and improve oral health outcomes. This study investigates the application of convolutional neural networks (CNNs) in diagnosing gingival diseases using medical images, including X-rays and intraoral photographs. Several CNN architectures, including VGG16, Sequential CNN, MobileNet, InceptionV3, and suggestions for a voting method to enhance the prediction, were evaluated for their performance in classifying gingival conditions. MobileNet emerged as the most effective model, achieving a test accuracy of 92.73%; the suggested method relies mainly on its positive result. When the MobileNet's result is false, the process takes the voting result using the other methods. This boosts the accuracy to 96%. Surpassing other models in precision and recall metrics. Pre-processing techniques such as normalization using the CIELAB color space and data augmentation significantly enhanced model accuracy. The study employed robust evaluation methods, including 10-fold cross-validation and hyperparameter tuning, to ensure model reliability and generalizability. The findings highlight the transformative potential of AI-powered diagnostic tools in dental healthcare. By leveraging lightweight and efficient architectures like MobileNet, these tools can be deployed in resource-limited settings, offering real-time diagnostic support to healthcare professionals. Future work will focus on expanding datasets, exploring …

Read Publication

Design and Implementation of Model Predictive Controller

Jul 2, 2022

publisher Al-Rafidain Engineering Journal (AREJ)

DOI https://doi.org/10.33899/rengj.2022.130477.1108

Issue No.1,

Volume 27

The precise position control of a DC servo motor is a major concern in today's control theory. This work presents position following and forecast of DC servo engine utilizing an alternate control technique. Control technique is required to limit and diminish the consistent state error. A model predictive controller MPC is utilized to plan and actualize these prerequisites. Two sorts of controlling techniques are presented in this task. The Active Set Method (ASM), the inside point technique (IIP), and have been utilized as controlling strategies. This work distinguishes and depicts the plan decisions identified with a two sorts of controllers and judicious regulator for a DC servo motor. Execution of these regulators has been confirmed through reproduction utilizing MATLAB/SIMULINK programming. As indicated by the recreation results the Comparisons among ASM, IIP. The tuning strategy was increasingly proficient in improving the progression reaction attributes, for example, decreasing the rise time, settling time and most prominent overshoot in Position control of DC servo motor.

Read Publication

Adaptive control of a DC servo motor using particle swarm and gray wolf optimization algorithms

Apr 27, 2024 - Apr 28, 2024

Publisher AIP Conf. Proc

Country Iraq

Location arbil

Visit Conference