Qusai Shambour

The rapid growth of digital communication has intensified spam-related threats, including phishing and malware, which employ advanced evasion tactics. Traditional filtering methods struggle to keep pace, driving the need for sophisticated machine learning (ML) solutions. The effectiveness of ML models hinges on selecting high-quality input features, especially in high-dimensional datasets where irrelevant or redundant attributes impair performance and computational efficiency. Guided by principles of symmetry to achieve an optimal balance between model accuracy, complexity, and interpretability, this study proposes an Enhanced Hybrid Quantum-Inspired Firefly and Artificial Bee Colony (EHQ-FABC) algorithm for feature selection in spam detection. EHQ-FABC leverages the Firefly Algorithm’s local exploitation and the Artificial Bee Colony’s global exploration, augmented with quantum-inspired principles to maintain search space diversity and a symmetrical balance between exploration and exploitation. It eliminates redundant attributes while preserving predictive power. For interpretability, Shapley Additive Explanations (SHAPs) are employed to ensure symmetry in explanation, meaning features with equal contributions are assigned equal importance, providing a fair and consistent interpretation of the model’s decisions. Evaluated on the ISCX-URL2016 dataset, EHQ-FABC reduces features by over 76%, retaining only 17 of 72 features, while matching or outperforming filter, wrapper, embedded, and metaheuristic methods. Tested across ML classifiers like CatBoost, XGBoost, Random Forest, Extra Trees, Decision Tree, K-Nearest Neighbors, Logistic Regression, and Multi-Layer Perceptron, EHQ-FABC achieves a peak accuracy of 99.97% with CatBoost and robust results across tree ensembles, neural, and linear models. SHAP analysis highlights features like domain_token_count and NumberOfDotsinURL as key for spam detection, offering actionable insights for practitioners. EHQ-FABC provides a reliable, transparent, and efficient symmetry-aware solution, advancing both accuracy and explainability in spam detection.

The exponential growth of online healthcare platforms has resulted in an overwhelming volume of medication information, posing challenges for patients seeking appropriate treatments for their specific conditions. Recommendation systems have emerged as valuable tools in various applications, including healthcare, helping users navigate information overload. However, their effectiveness in recommending medications is often limited by data sparsity, which arises from insufficient user-item interaction data and hinders accurate prediction. This study proposes a collaborative multi-criteria filtering approach that improves medication recommendations without relying on external knowledge sources. The proposed approach leverages multi-criteria ratings, implicit user and item similarities, similarity transitivity, and global similarity concepts. By effectively utilizing implicit information embedded within existing user-item multi-criteria ratings, the proposed approach effectively expands user and medication neighborhoods, resulting in more accurate and diverse recommendations, even in sparse data scenarios. Empirical analysis on a real-world medicine dataset demonstrated that the proposed approach significantly outperformed existing recommendation methods, resulting in substantial improvements in predictive accuracy and recommendation coverage, particularly in sparse environments.

The Harris Hawks optimization (HHO) was used in this study to enhance spam identification. Only the features with a high influence on spam detection have been selected using the HHO metaheuristic technique. The HHO technique's assessment of the selected features was conducted using the ISCX-URL2016 dataset. The ISCX-URL2016 dataset has 72 features, but the HHO technique reduces that to just 10 features. Extra tree (ET), extreme gradient boosting (XGBoost), and support vector machine (SVM) techniques are used to complete the classification assignment. 99.81% accuracy is attained by the ET, 99.60% by XGBoost, and 98.74% by SVM. As we can see, with the ET, XGBoost, and k-nearest neighbor (KNN) techniques, the HHO technique achieves accuracy above 98%. Nonetheless, the ET technique outperforms the XGBoost and KNN techniques. ET outperforms other methods due to its robust ensemble approach, which benefits from the diverse and relevant feature subset selected by HHO. HHO's effective reduction of noisy or redundant features enhances ET's ability to generalize and avoid overfitting, making it a highly efficient combination for spam detection. Thus, it looks promising to combat spam emails by combining the ET technique for classification with the HHO technique for feature selection.

Uniform resource locator (URL) defacement attack can be defined as any cyberattack in which the attacker replaces the appearance or content of the targeted webpage with their own that is intended to disgrace, mislead, or malign the website. Detecting URL defacement attacks is significant to avoid breaching the security of the website content or its configuration files, modifying the file locations, templates, or attacks on the website environment and applications. A machine learning (ML) technique can be used to detect the defacement attack on any website with complex content and structure, as opposed to the classical techniques for detection, such as Diff comparison, Document Object model tree analysis, and checksum, which can only be applied to static websites. This article proposes a feature selection model based on particle swarm optimization with support vector machine, decision tree, random forest, Naive Bayes, and k-nearest neighbor ML classification algorithms. The proposed model aims to improve the URL defacement attack detection by selecting the best features from the ISCX-URL-2016 dataset. Then, the reduced set of features produced by the proposed model step is used as input to evaluate and compare the results of the used ML classifiers. The results showed that the proposed model has significantly reduced the features, regarding the classification's feature reduction, the random forest classifier outperformed other classifiers in terms of true positive rates, accuracy, precision, sensitivity, and F-measure, whereas the proposed model with random forest classifier has 99.21% True positive rates, 99.29% accuracy rate, 99.38% precision rate, 99.21% sensitivity rate, and 99.29% F-measure rate. In the future directions of this article, more research should be done on a variety of things, including varying and sophisticated techniques of altering the URL defacement since it would better calibrate the model for application in real-life situations. Received: 28 October 2024 | Revised: 16 December 2024 | Accepted: 1 January 2025 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in URL dataset (ISCX-URL2016) at: https://www.unb.ca/cic/datasets/url-2016.html. Author Contribution Statement Omar Almomani: Conceptualization, Methodology, Software, Investigation, Writing – original draft, Supervision, Project administration. Adeeb Alsaaidah: Conceptualization, Formal analysis, Writing – original draft. Ahmad Adel Abu-Shareha: Methodology, Formal analysis, Investigation, Data curation, Writing – review & editing, Visualization. Abdullah Alzaqebah: Software, Resources, Data curation, Writing–review & editing, Visualization. Mohammed Amin Almaiah: Validation, Resources, Writing – original draft. Qusai Shambour: Resources, Writing – original draft

Aim/Purpose: The primary aim of this study is to address the persistent challenge of delayed autism spectrum disorder (ASD) diagnosis in toddlers. Early detection enables timely interventions that can improve developmental outcomes; however, conventional approaches rely on lengthy and resource-intensive behavioral assessments. We therefore introduce an interpretable AI screening framework designed to accelerate ASD triage while providing clinically understandable rationales to support decision-making. Background: Traditional ASD diagnosis depends on expert behavioral evaluation and parent reports which, despite their value, are time-consuming and capacity-limited, delaying access to early intervention. With ASD prevalence rising, scalable and effective approaches are urgently needed. This study proposes a robust AI framework for early ASD detection that integrates targeted preprocessing, feature selection, principled model optimization, and post-hoc explanations, aiming to improve diagnostic utility and clarity for end users in clinical and community settings. Methodology: We develop a unified, reproducible pipeline that combines data preprocessing, class balancing, feature selection, and Bayesian hyperparameter tuning. The pipeline also incorporates SHapley Additive exPlanations (SHAP) to provide model explanations. Six diverse machine learning models – Extreme Gradient Boosting (XGB), Histogram-based Gradient Boosting (HGB), Random Forest (RF), Naïve Bayes (NB), Mixture Discriminant Analysis (MDA), and Multi-layer Perceptron (MLP) – are evaluated to assess framework robustness rather than to crown a single best classifier. A cross-cultural dataset of toddlers aged 12–36 months (n=1,560) is constructed by merging two public sources containing Q-CHAT-10 items with demographic attributes. Preprocessing removes non-informative variables and encodes categorical features; Gaussian noise-based upsampling (GNUS) mitigates post-merge imbalance; RobustScaler stabilizes training. Gradient Boosting Feature Selection (GBFS) ranks and reduces features to enhance parsimony and interpretability. Performance is reported via accuracy, precision, recall, F1, and Matthews Correlation Coefficient (MCC). Model behavior is elucidated with SHAP to reveal feature contributions and decision pathways. Contribution: This work presents an interpretable AI framework for early ASD detection that couples performance with clinician-oriented explanation in a single pipeline. Rather than optimizing for accuracy alone, we emphasize synergy among preprocessing, balancing, feature selection, and explanation – the multimodel evaluation evidence adaptability across algorithmic families. GBFS and SHAP are used to ensure concise, explainable predictions. Notably, the framework achieved very strong internal validation results (high F1 and MCC across folds) with XGB, while SHAP-derived patterns aligned with clinical heuristics. Results are promising but preliminary, pending external, multi-site validation. Findings: GNUS and robust normalization improved generalization on the cross-cultural dataset. With GBFS-selected features, XGB achieved near-ceiling internal scores across key metrics, a trend observed – though to a lesser extent – in other models after comparable optimization. SHAP consistently highlighted behaviors such as gaze-following and social/emotional responsiveness among the most influential predictors, in line with clinical practice. Collectively, the findings indicate that interpretable ML can complement conventional screening, while warranting prospective and external validation to assess generalizability and potential dataset shift. Recommendations for Practitioners: Clinicians and community programs may consider adopting interpretable ML as a screening aid to prioritize referrals and shorten time-to-assessment. Attention to features repeatedly identified as influential can guide focused early interventions and resource allocation. Recommendation for Researchers: Future studies should test the framework on larger and more diverse cohorts to evaluate generalizability. Exploring ensembles and deeper architectures, as well as alternative preprocessing, resampling, and feature selection strategies, may further enhance performance, particularly for cases that are borderline. Impact on Society: Earlier, more reliable screening can improve access to services during critical neurodevelopmental windows. Integrating interpretable AI into practice may also strengthen clinician confidence in ML-assisted tools, supporting responsible, human-centered deployment and broader public health benefits. Future Research: Next steps include conducting real-world pilots across various clinical/community settings, integrating with complementary diagnostic tools to build multimodal platforms, and systematically evaluating balancing/optimization choices. These directions will help translate the framework into practical impact and inspire analogous applications in pediatric neurodevelopmental assessment.

This research explores the impact of malware on the digital world and presents an innovative system to detect and classify malware instances. The suggested system combines a random forest (RF) classifier and gray wolf optimizer (GWO) to identify and detect malware effectively. Therefore, the suggested system is called RFGWO-Mal. The RFGWO-Mal system employs the GWO for feature selection in binary and multiclass classification scenarios. Then, the RFGWO-Mal system uses a novel self-union feature selection approach, combining features from different subsets of binary and multiclass classification extracted using the GWO optimizer. The RF classifier is then applied for classifying malware and benign data. The comprehensive Obfuscated-MalMem2022 dataset was utilized to evaluate the suggested RFGWO-Mal system, which has been implanted using Python. The suggested RFGWO-Mal system achieves significantly improved results using the novel self-union feature selection approach. Specifically, the RFGWO-Mal system achieves an outstanding accuracy of 99.95% in binary classification and maintains a high accuracy of 86.57% with multiclass classification. The findings underscore the achievement of a self-union feature selection approach in enhancing the performance of malware detection systems, providing a valuable contribution to cybersecurity.

In recent years, recommender systems have become a crucial tool, assisting users in discovering and engaging with valuable information and services. Multi-criteria recommender systems have demonstrated significant value in assisting users to identify the most relevant items by considering various aspects of user experiences. Deep learning (DL) models demonstrated outstanding performance across different domains: computer vision, natural language processing, image analysis, pattern recognition, and recommender systems. In this study, we introduce a deep learning model using VAE to improve multi-criteria recommendation systems. Specifically, we propose a variational autoencoder-based model for multi-criteria recommendation systems (VAE-MCRS). The VAE-MCRS model is sequentially trained across multiple criteria to uncover patterns that allow for better representation of user–item interactions. The VAE-MCRS model utilizes the latent features generated by the VAE in conjunction with user–item interactions to enhance recommendation accuracy and predict ratings for unrated items. Experiments carried out using the Yahoo! Movies multi-criteria dataset demonstrate that the proposed model surpasses other state-of-the-art recommendation algorithms, achieving a Mean Absolute Error (MAE) of 0.6038 and a Root Mean Squared Error (RMSE) of 0.7085, demonstrating its superior performance in providing more precise recommendations for multi-criteria recommendation tasks.

Artificial Intelligence Techniques for Early Autism Detection in Toddlers: A Comparative Analysis