EMEshaq Aziz Awadh AL Mandhari

Eshaq Aziz Awadh AL Mandhari

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Eshaq Aziz Awadh AL Mandhari has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    An efficient approach for cyber-attack detection by using machine learning and deep learning algorithms

    by Yasir Hussein Shakir, Mahmoud Mohamed Abdelhamied, Eshaq Aziz Awadh AL Mandhari, Ali Alkhazraji, Naglaa M. Reda

    Cybercrime gained traction in the late 20th century. The capabilities of cyber-attackers have improved dramatically. One of the biggest challenges facing cybersecurity developers is safeguarding consumers' security and privacy. Interest in using AI approaches in cybersecurity has grown significantly because of the incredible proficiency these techniques have demonstrated across all domains. Even while machine learning algorithms are very effective at identifying malicious activity, there are still certain issues that lower performance accuracy. This paper has the novelty of deploying the Artificial Bee Colony (ABC) meta-heuristic algorithm with the K-Nearest Neighbors (KNN) classifier to detect cyber-attacks. It proposes a variant approach called KNN+Bee that detects attacks efficiently, achieving 99.86% overall accuracy. The NSL-KDD dataset of cyberattacks has been leveraged in the training and testing phases. The proposed approach has been contrasted with the most popular machine learning. According to experimental findings, the suggested model delves deeper into the identification of cyberattacks. It achieves unprecedented performance, outperforming other models in terms of precision, Recall, F-score and MCC. Furthermore, popular deep learning models have been implemented and examined on the same dataset. Results prove that GRU is the most accurate, reaching 99.71%.

  • Open Access

    DCNNVA: a deep convolutional neural network for volcanic activity classification using satellite imagery

    by Yasir Hussein Shakir, Reem Ali Mutlag, Eshaq Aziz Awadh AL Mandhari, Mohamed Shabbir Abdulnabi

    Monitoring and classifying volcanic activity are a critical task for disaster risk reduction and hazard management. Recent discoveries in machine learning and deep learning have proved excellent satellite image classification and volcanic anomaly identification capabilities, yet the majority of existing methods suffer from small datasets, particularly on solitary data modalities or particular cases, merely as examples. In this research work, we put forward develop deep convolutional neural network for volcanic activity (DCNNVA) classification specifically designed for satellite imagery on volcanic activity. We rigorously benchmarked DCNNVA model's strength against a total of eight state-of-the-art transfer learning models: ResNet50, NASNetLarge, DenseNet121, MobileNet, InceptionV3, Xception, VGG19, and VGG16. Comparative experimental results show that proposed DCNNVA framework's overall performance significantly surpasses its competitors with an accuracy of 99.33%, precision of 100%, recall of 98.67%, and F1-score of 99.33%, significantly beating existing state-of-the-art methods. Also, we create a deployable graphical user interface (GUI) system that is capable of real-time monitoring on volcanic activity and generates multi-modal alert processing that can make this research directly applicable for practical use on disaster management as well as in early warning systems. This research contributes a scalable, strong, as well as practical solution towards volcanic hazard identification as well as a baseline system toward developing future multi-modal as well as real-time geohazard tracking system frameworks.

  • Open Access

    Automated Fetal Health Classification Using Auto-Sklearn Approach for Enhanced Clinical Sensitivity

    by Yasir Hussein Shakir, Reem Ali Mutlag, Eshaq Aziz Awadh AL Mandhari

    يُعد التقييم الدقيق وفي الوقت المناسب لصحة الجنين باستخدام تخطيط نبضات قلب الجنين وانقباضات الرحم (Cardiotocography – CTG) أمرًا بالغ الأهمية للحد من معدلات المراضة والوفيات لدى حديثي الولادة. إن تحقيق دقة تشخيصية مرتفعة باستخدام نماذج التعلم الآلي التقليدية غالبًا ما يتطلب ضبطًا يدويًا مكثفًا للمعاملات الفائقة (Hyperparameters) وهندسة دقيقة للخصائص. تقترح هذه الدراسة منهجية آلية تعتمد على إطار عمل Auto-Sklearn لتصنيف صحة الجنين إلى ثلاث فئات: طبيعي (Normal)، مشتبه به (Suspect)، ومرضي (Pathological). تم استخدام مجموعة بيانات تتكون من 2,126 حالة سريرية، حيث تم تطبيق استراتيجية تحسين بايزية (Bayesian Optimization) بنمط "البداية الباردة" (Cold-Start) مع تجاوز التعلم التلوي (Meta-Learning) عمدًا بهدف تقييم القدرة التحسينية الخام للإطار الآلي. أظهرت النتائج أن خط أنابيب المعالجة الآلي (Automated Pipeline) حقق دقة كلية (Accuracy) بلغت 96.94%، وقيمة F1 مرجحة (Weighted F1-score) قدرها 88.37%. ومن منظور السلامة السريرية، حقق النموذج معدل استدعاء (Recall) بلغ 97.00% للفئة المرضية (Pathological)، مع معدل فقد (Miss Rate) منخفض للغاية بلغ 0.0656، مما يضمن حساسية عالية في اكتشاف حالات ضائقة الجنين وبتحقيق خصوصية (Specificity) بلغت 97.43%، نجح النموذج أيضًا في تقليل الإنذارات الكاذبة بشكل فعال، مما يثبت أن تقنيات التعلم الآلي الآلي (AutoML)...

  • Open Access

    Multi-scale convolutional and temporal modeling for robust face recognition: Introducing ScaleSyncNet

    by Saif Mohanad Kadhim, Johnny Koh Siaw Paw, Yaw Chong Tak, Shahad Thamear Abd Al-Latief, Yasir Hussein Shakir, Eshaq Aziz Awadh AL Mandhari, Fahad Taha Al-Dhief, Nurhizam Safie, Ali Hashim Abbas