Ali Alrammahi

Dr. Ali Alrammahi

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2025 in International Journal of Information Technology
Verified
Journal Article
Open access
PDF file
AAAli Alrammahi
Ali Alrammahi
FOFarah abbas Obaid
Farah abbas Obaid
ZMZahraa Azhar Muhammad
Zahraa Azhar Muhammad
MKMustafa Noaman Kadhim
Mustafa Noaman Kadhim
DADhiah Al-Shammary
Dhiah Al-Shammary
AIAyman Ibaida
Ayman Ibaida
This paper explores the combined effect of diverse datasets and advanced feature extraction techniques on the performance of email spam detection using unsupervised clustering algorithms Fuzzy C-Means and K-Means. Leveraging the Enron Email Dataset and the SMS Spam Collection Dataset, we extract both traditional features (TF-IDF) and novel attributes (punctuation count, capital letter usage, and body length) that reflect spam characteristics. Clustering is applied to group emails based on these features, and the generated cluster labels are subsequently used to train supervised classifiers, including K-Nearest Neighbours, Naive Bayes, Support Vector Machines, and XGBoost. Comparative analysis reveals that clustering significantly enhances classification accuracy by uncovering latent structures within high-dimensional data. Moreover, our results highlight the strengths and limitations of Fuzzy C-Means versus K-Means in this context. The study demonstrates that integrating unsupervised clustering with rich feature engineering contributes to more robust and efficient spam detection, paving the way for future hybrid spam filtering models.

1 January 2024 in International Journal of Electrical and Electronic Engineering & Telecommunications
Verified
Journal Article
Open access
AAAli Alrammahi
Ali Alrammahi
Today, organizations of all sizes face many difficulties in protecting their data, systems, and tools. One issue of particular concern is the insider threat. Insiders seek to use their privileges to undermine data confidentiality, validity, and availability. Any sabotage committed by someone within a company significantly harms the company’s integrity, credibility, and financial profits. Automated feature extraction methods face challenges when used to classify data due to their tendency sometimes to return inaccurate results, leading to overfitting. Furthermore, analyzing irregular data requires extensive manual feature detection. We propose an algorithm that represents an expert system that detects insiders and determines their risk level as well. After that, the decisive step will be to intersect the results obtained from a classification using multiple algorithms with those obtained from the internal detection algorithm using expert rules. This research uses several classification methods that can deal with this type of data to predict the status of insiders within a computer network. The main goal of this study is to improve the accuracy and efficiency of identifying insiders within a computer network. Model performance evaluation includes important parameters such as precision, recall, and F1 score. The highest classification accuracy is obtained at 0.99, and after combining these results with the results of the proposed algorithm, the accuracy is 100%. These results highlight the remarkable ability of these models to detect internal states accurately, providing encouraging possibilities for improving cyber security within a computer network.

1 January 2025 in International Journal of Electrical and Electronic Engineering & Telecommunications
Verified
Journal Article
Open access
AAAli Alrammahi
Ali Alrammahi
Distributed Denial of Service (DDoS) attacks have recently emerged as one of the most destructive threats to network systems. This paper aims to develop a technique that efficiently identifies DDoS attacks in networked systems by leveraging improved clustering techniques and machine learning algorithms. This methodology employs a Modified Fuzzy C-Means (MFCM) clustering algorithm to partition the available DDoS attack dataset and integrate a classification algorithm to accurately detect attacks and classify data based on specific network characteristics derived from the transformed data packets. The clustering algorithm predominantly relies on distance measurements derived from fuzzy coefficients, significantly limiting its ability to identify and classify emerging attack scenarios. The current study introduces the integration of the MFCM clustering algorithm with sophisticated classification techniques to enhance accuracy and minimize errors. The efficacy of the modified clustering algorithm was evaluated using the entropy criterion, and a value of 0.99 was attained, demonstrating superior performance relative to traditional algorithms. The training algorithm was rigorously evaluated utilizing established performance metrics, such as accuracy, detection rate, and false positive rate. The results indicate that the accuracy improved consistently across all classification algorithms applied, contributing to an enhanced attack detection rate.

1 January 2025 in International Journal of Electrical and Electronic Engineering & Telecommunications
Verified
Journal Article
Open access
AAAli Alrammahi
Ali Alrammahi
This thesis demonstrates an intelligent system for the early detection of plant diseases using deep learningbased image processing. The primary objective is to support food security and enhance agricultural productivity. The proposed system utilizes Contrast-Limited Adaptive Histogram Equalization (CLAHE) and a U-shaped convolutional Neural Network (U-Net) for image segmentation, aiming to enhance image quality and accurately localize diseased regions. The feature extraction includes integration of deep features of Convolutional Neural Networks (CNN) and the Residual Network-18 architecture-based model GramNet together with the texture feature extracted from the graylevel co-occurrence matrix. All features are concatenated to create a comprehensive feature representation. A stacking ensemble approach is adopted for classification, utilizing support vector machines, K-nearest neighbors, and extreme gradient boosting as base classifiers. In contrast, the light gradient boosting machine is the final meta-classifier. An experimental evaluation was conducted on a publicly available rice disease dataset containing 11,790 samples, which demonstrates that the model achieves 99.99% accuracy on the training data and 96.90% on the testing data. This work demonstrates the effectiveness of integrating preprocessing, hybrid feature extraction, and ensemble learning in the early detection of plant diseases.

1 January 2025 in International Journal of Electrical and Electronic Engineering & Telecommunications
Verified
Journal Article
Open access
HAHassanein Yarob Saeed Albakaa
Hassanein Yarob Saeed Albakaa
AAAli Alrammahi
Ali Alrammahi
This study proposes an automated framework for detecting and tracking concealed weapons in thermal video, aimed at real-time surveillance in high-security public areas like airports and stadiums. Due to the lack of relevant public datasets, thermal videos were recorded using an infrared camera in scenarios simulating concealed weapons. Frames extracted from the videos were automatically annotated using the GroundedSAM model, which aligns textual prompts ("gun", "knife") with image content, eliminating manual labeling. A YOLOv11n model was trained on over 6,200 labeled thermal images, achieving 81% precision, 82% recall, and 87% mAP@50. For tracking across frames, a Graph Neural Network (GNN) connected detected objects over time, 0.88 consistency for guns, and 0.66 consistency for knives. The integration of smart annotation, thermal-aware detection, and GNN tracking demonstrates strong potential for real-time, robust weapon detection in crowded, security-sensitive environments.