Phishing attacks have evolved into sophisticated threats, making effective cybersecurity detection strategies essential. While many studies focus on either URL or HTML features, limited work has explored the comparative impact of engineered feature sets across different machine learning models. This study aims to bridge that empirical gap by evaluating the effectiveness of URL-based, HTML-based, and derived features, individually and in combination, on phishing URL detection. The proposed approach utilizes the PhishOFE dataset of 101,063 phishing and legitimate URLs. Features are organized into four sets: (1) URL only, (2) HTML only, (3) URL + HTML, and (4) URL + HTML + derived features. Ten machine learning models are employed, including Random Forest, k-Nearest Neighbors, Logistic Regression, Support Vector Machine, Naive Bayes, and advanced ensemble methods such as LightGBM, XGBoost, and CatBoost. Performance is assessed using accuracy, precision, recall, and F1-score, while permutation importance is used to evaluate feature significance. Experimental results demonstrate that ensemble models outperform traditional classifiers, with CatBoost achieving the highest accuracy of 99.45% using the complete feature set. Moreover, URL features like URLLength and NoOfSubDomain consistently rank high in importance, while derived features such as SuspiciousCharRatio and URLComplexityScore notably enhance detection performance in specific models.

Phishing website detection has been widely explored, yet most existing surveys focus on detection algorithms or general cybersecurity methods, offering only a brief treatment of feature engineering. This systematic literature review addresses this gap by analyzing recent studies on feature engineering for phishing URL detection using machine learning. The review categorizes feature types, such as URL/lexical, HTML/content, domain, behavioral, and emerging derived and hybrid features, and examines the application of feature selection and dimensionality reduction techniques. The findings reveal a persistent reliance on URL/lexical features for their simplicity and broad applicability, despite growing interest in integrating content-based and composite approaches for improved robustness. Key challenges include adapting to evolving phishing tactics, handling dataset limitations, mitigating high dimensionality, and balancing computational efficiency with detection accuracy. The review also identifies opportunities that have been underexplored in prior work, such as leveraging explainable AI methods (e.g., SHAP, LIME) to validate and optimize feature sets, expanding cross-lingual and adversarial-resilient features, and developing lightweight solutions for real-time or resource-constrained environments. This study offers a targeted roadmap for advancing phishing detection research by consolidating and reviewing the role of feature engineering. It highlights its pivotal role in creating more accurate, adaptive, and efficient detection systems.

Artificial intelligence (AI), particularly machine learning and deep learning architectures, has been widely applied to support thyroid cancer diagnosis, but existing evidence on its performance and limitations remains scattered across techniques, tasks, and data types. This systematic review synthesizes recent work on knowledge extraction from heterogeneous imaging and clinical data for thyroid cancer diagnosis and detection published between 2021 and 2025. We searched eight major databases, applied predefined inclusion and exclusion criteria, and assessed study quality using the Newcastle–Ottawa Scale. A total of 150 primary studies were included and analyzed with respect to AI techniques, diagnostic tasks, imaging and non-imaging modalities, model generalization, explainable AI, and recommended future directions. We found that deep learning, particularly convolutional neural networks, U-Net variants, and transformer-based models, dominated recent work, mainly for ultrasound-based benign–malignant classification, nodule detection, and segmentation, while classical machine learning, ensembles, and advanced paradigms remained important in specific structured-data settings. Ultrasound was the primary modality, complemented by cytology, histopathology, cross-sectional imaging, molecular data, and multimodal combinations. Key limitations included diagnostic ambiguity, small and imbalanced datasets, limited external validation, gaps in model generalization, and the use of largely non-interpretable black-box models with only partial use of explainable AI techniques. This review provides a structured, machine learning-oriented evidence map that highlights opportunities for more robust representation learning, workflow-ready automation, and trustworthy AI systems for thyroid oncology.

A user story is commonly applied in requirement elicitation, particularly in agile software development. User story is typically composed in semi-formal natural language, and often follow a predefined template. The user story is used to elicit requirements from the users' perspective, emphasizing who requires the system, what they expect from it, and why it is important. This study aims to acquire a comprehensive understanding of user stories in requirement elicitation. To achieve this aim, this systematic review merged an electronic search of four databases related to computer science. 40 papers were chosen and examined. The majority of selected papers were published through conference channels which comprising 75% of total publications. This study identified 24 problems in user stories related to requirements elicitation, with ambiguity or vagueness being the most frequently occurring problem reported 18 times, followed by incompleteness reported 11 times. Finally, the model approach was the most popular approach reported in the research paper, accounting for 30% of the total approaches reported.

With the rapid expansion of the internet and the growing sophistication of cyber threats, phishing attacks have become a serious cybersecurity challenge for individuals and organizations. Phishing attacks, primarily executed through deceptive URLs, aim to mislead users into providing sensitive information, leading to financial loss, identity theft, and security breaches. The increasing complexity of phishing techniques necessitates the development of robust and intelligent detection frameworks. This paper introduces PhishOFE, a novel machine learning-based framework for phishing URL detection that utilizes Optimized Feature Engineering. The proposed framework extracts URL and HTML-based features and derives composite features to enhance phishing detection accuracy while minimizing dependence on thirdparty data. The PhishOFE dataset is constructed using diverse phishing and legitimate URLs sourced from various repositories, which ensures comprehensive feature representation. Experiments were conducted using ten different machine learning models, and the results show that CatBoost achieves the highest detection accuracy of 99.48%, with superior precision, recall, and F1-score. The framework reduces computational complexity by utilizing an existing machine learning model, making it suitable for real-time applications and its potential for integration into cybersecurity solutions to counter evolving phishing tactics.

Our study examines the growing role of Explainable Artificial Intelligence (XAI) in cancer medical imaging, where transparency and interpretability are essential for trustworthy clinical decision making. Using a PRISMA-guided systematic literature review, 926 records published between 2020 and 2026 were identified from major databases, with 46 studies meeting the inclusion criteria after screening and quality assessment. The review systematically analyzes XAI techniques, model architectures, evaluation approaches, interpretability mechanisms, challenges, and future research directions. The findings show that gradient-based methods, particularly Grad-CAM, dominate the field due to their ease of integration with convolutional neural networks. At the same time, complementary approaches such as LIME, SHAP, and Integrated Gradients provide additional attribution insights. Evaluation practices remain heterogeneous, with a strong reliance on qualitative visual inspection and limited standardized quantitative frameworks. XAI contributes to interpretability primarily through spatial localization, feature attribution, and clinical decision support; however, challenges persist, including instability in explanations, coarse localization, high computational cost, and limited compatibility with transformer-based models. Overall, while XAI enhances transparency in cancer imaging, its clinical reliability remains constrained by methodological and technical limitations. Future work should focus on standardized evaluation, clinician-centered validation, and the development of robust, multimodal, and architecture-aware explainability frameworks.