Muna Al-Razgan

Machine learning (ML) has been increasingly applied in usability engineering to evaluate its dimensions, such as efficiency, errors, and satisfaction. However, the learnability of interfaces—an essential aspect of usability—remains underexplored in ML-driven evaluations. This paper presents a predictive framework that refines traditional Cognitive Walkthrough (CW) questions through semantic alignment with learnability factors and integrates expert evaluation outcomes with ML models. Validation proceeded in two stages. In the first, a case study on Microsoft OneNote with predefined tasks assessed the effectiveness of the Enhanced Cognitive Walkthrough (ECW) questions. Results showed that the ECW questions provided clearer and more actionable insights into learnability issues compared to the traditional CW formulation. In the second stage, ECW evaluation outputs were paired with real user feedback to create ground-truth labels for task learnability. Using these user-based labels, three ML models were trained. Results showed moderate predictive performance (Macro-F1 = 0.41–0.55; Balanced Accuracy = 0.55–0.61). Cross-interface testing between OneNote and StarUML showed partial generalization, suggesting that ECW-based expert evaluations can support predicting learnability across interfaces when combined with actual user perception. These results represent a preliminary feasibility demonstration rather than a fully validated predictive model, demonstrate that combining ECW with targeted user feedback provides developers and UX practitioners a clearer, more reliable, and data-driven method to identify and prioritize learnability issues early in the design process.

Chaotic systems are powerful tools for studying complex dynamics and have wide applications in secure communication systems. This paper presents and analyzes a memristive variable-boostable chaotic system (MVBCS). Firstly, a novel memristor model is proposed that simplifies the system structure, enhances design efficiency, and enables precise control over dynamic behaviors, combining sawtooth and trigonometric functions. The dynamic characteristics of the chaotic system integrated with the memristor are then investigated, including the generation of a controllable multi-scroll chaotic attractor, where the number of scrolls can be precisely adjusted to meet diverse application needs. Furthermore, the dynamic evolution of multi-scroll attractors is examined under a self-growth mechanism, demonstrating the system’s ability to grow autonomously bidirectional scrolls without external intervention. These properties make it highly suitable for applications in encryption, secure communications, and random number generation. Finally, hardware implementation using an STM32 microcontroller is explored to demonstrate its practical use in a secure pseudo-random number generator (PRNG).

Refactoring is the process of restructuring existing source code to improve its internal structure without altering its external behavior. Refactoring is essential to maintaining software quality; however, its manual application is labor-intensive, and existing automated techniques often fall short by relying on binary classification, neglecting the co-occurrence of multiple refactoring needs. This study addresses this gap by proposing and evaluating multi-label machine learning models capable of predicting combinations from 20 distinct refactoring operations across class, method, and variable granularities. We systematically investigate three multi-label learning strategies (Label Powerset, Classifier Chains, and Binary Relevance) integrated with five base classifiers: Random Forest, Gradient Boosting, XGBoost, Decision Tree, and Artificial Neural Network. Experiments are conducted using 10-fold cross-validation on a real-world dataset, with relevant feature selection techniques applied. Results indicate that variable-level metrics yield the highest predictive performance, with the Label Powerset strategy combined with Random Forest achieving a Jaccard accuracy of 95.30%. These findings highlight the efficacy of multi-label learning in modeling complex, real-world refactoring scenarios, providing a robust foundation for enhancing automated refactoring tools and advancing software maintenance practices.

Diabetic retinopathy (DR) is a microvascular complication that can lead to blindness if left untreated. Early detection of microaneurysms (MAs) is crucial for effective DR diagnosis. However, detecting MAs is challenging due to their small size, low contrast, and the presence of noise and other artifacts. This paper presents a novel deep learning approach for MA detection using a dilated residual network (DRN) with an Region of interest (ROI) layer. Unlike traditional models such as VGG16 and ResNet, our DRN model achieves a higher input resolution (28 × 28) for ROI pooling, significantly improving MA detection accuracy. Extensive experiments confirm the effectiveness of our approach, achieving superior performance compared to state-of-the-art methods on the e-ophtha-MA, DiaretDB1-MA, and ROCh datasets. Notably, our method achieves the best FROC (free-response receiver operating characteristic) score of 0.6038 on the e-ophtha-MA dataset.

In software engineering, selecting the appropriate architectural style for software systems is risky and sensitive. The selection process is a multicriteria decision‐making (MCDM) problem. Consequently, selecting a suitable architecture is a key challenge in software development. This study presents an automated hybrid methodology based on the analytic hierarchy process (AHP) and fuzzy analytic hierarchy process (FAHP) to evaluate and suggest multiple architectural styles based on quality attributes (QAs) alone rather than relying on expert opinions. A Tera‐PROMISE dataset is presented to illustrate the proposed methodology and then compare the result of the methodology with expert judgments. Moreover, to support the proposed methodology, a case study is carried out to compare the proposed method to previous studies.

This work compares the performance of different algorithms — quantum Fourier transform, Gaussian–Newton method, hyperfast, metropolis-adjusted Langevin algorithm, and nonparametric classification and regression trees — for the classification of fetal health states from FHR signals. In the conducted research, the effectiveness of each algorithm was measured using confusion matrices, which gave information about class precision, recall, and total accuracy in three classes: Normal, Suspect, and Pathological. The QFT algorithm gives an overall accuracy of 90%, where it is highly reliable in recognizing Normal (94% F1-score) and Pathological states (91% F1-score), but performs poorly regarding the Suspect cases, at 58% F1-score. On the other hand, using the GNM method gives an accuracy of 88%, whereby it performed well on Normal cases, at 93% F1-score, and poor performance with Suspect, at 50% F1-score, and Pathological classifications, at 82% F1-score. The hyperfast algorithm yielded an accuracy of 89%, thus performing well on Normal classifications with an F1-score of 93%, but less well on the Suspect states with an F1-score of 56%. The MALA algorithm outperformed all other algorithms tested in this study, giving an overall accuracy of 91% and adequately classifying Normal, Suspect, and Pathological states with corresponding F1-scores of 94%, 63%, and 90%, respectively; therefore, the algorithm is quite robust and reliable for fetal health monitoring. The NCART algorithm achieved an accuracy of 89%, thus showing great capability for classification in Normal cases with 94% F1-score and in Pathological cases with 88% F1-score; this is moderate for Suspect cases with 53% F1-score. Overall, while all algorithms exhibit potential for fetal health classification, MALA stands out as the most effective, offering reliable classification across all health states. These findings highlight the need for further refinement, particularly in enhancing the detection of Suspect conditions, to ensure comprehensive and accurate fetal health monitoring.