In the software development process, traceability links between unit tests and code are not explicitly maintained, and dependencies in most cases are manually identified. As a result, a large amount of effort and time is required during the comprehension process to establish the links between these artifacts. Although there are several methods that can infer such links based on different phenomenons, these methods usually produce different set of traceability links. This work expands upon previous traceability link recovery and visualization studies by implementing a combination of traceability recovery methods that automatically retrieve the links, and visualizing them to help developers to overview the links inferred by various recovery techniques, and also to select the right relations for analyses. The results of the usability study show that the visualization model presented herein can effectively support browsing, comprehension, and maintenance of Test-to Code Traceability (TCT) links in a system with enhanced efficiency, as well as visualization of TCT links from multiple sources is better than a visualization of single source of traceability links.

Cyber-physical smart infrastructures integrate sensing devices, communication networks, control components, and service platforms, which makes them vulnerable to malicious activities that may evolve gradually through several attack stages. The objective of this study is to develop and evaluate a simulation-based cybersecurity framework capable of detecting a proposed novel multi-stage cyber attack and identifying its internal progression within a realistic smart infrastructure environment. To achieve this objective, a NetSim-based cyber-physical smart infrastructure was modeled to generate both normal operational traffic and staged malicious traffic. The generated traffic was captured, processed, labeled, and transformed into a stage-aware cybersecurity dataset. An artificial neural network (ANN) model was then trained and evaluated for two detection tasks: binary classification of normal versus attack traffic and multi-class classification of compromise, coordination, and execution attack stages. Twenty experimental configurations were designed to examine the model under progressively broader infrastructure contexts, including sensing, service, gateway, control, backbone, and full-span operational scenarios. The best binary testing performance was achieved in the eighteenth experimental configuration, representing a broad full-span infrastructure scenario, with 97.96% accuracy, 97.80% precision, 97.65% recall, 97.72% F1-score, and 1.06% false positive rate. For stage-aware multi-class detection, the ANN model achieved 96.97% accuracy, 96.36% macro-averaged precision, 96.20% macro-averaged recall, 96.28% macro-averaged F1-score, and 96.55% weighted F1-score. Macro-averaged metrics report the unweighted average performance across classes, while weighted F1-score accounts for class support. These results show that the proposed simulation-based framework can generate realistic attack-aware traffic data and support reliable ANN-based detection of both attack presence and attack-stage progression.

Alzheimer's disease (AD) is chronically progressive neurodegenerative condition associated with substantial diagnostic and therapeutic challenges, particularly in its early stages. Current clinical approaches relying on MRI scans often face variability in image quality and subjective interpretation, limiting early and accurate detection. This study proposes a transparent, AI-driven diagnostic framework that integrates systematic MRI preprocessing with state-of-the-art hybrid deep learning models and explainable artificial intelligence (XAI). We compare preprocessing techniques, including contrastlimited adaptive histogram equalization (CLAHE) and Gaussian blur, and evaluate three model families: convolutional neural networks (CNNs), region-based CNNs (RCNNs), and hybrid models combining VGG16 feature extraction with XGBoost classification. Experiments on two benchmark datasets-the imbalanced AD dataset and Alzheimer's disease national initiative (ADNI) dataset-highlight the impact of preprocessing and model architecture on classification accuracy. Our findings reveal RCNN paired with CLAHE at a 16x16 tile size achieves superior performance on the challenging imbalanced dataset, while all models perform near-perfectly on the balanced ADNI dataset. The integration of Grad-CAM and SHAP enhances model interpretability by linking predictions to known clinical markers. This study underscores the critical role of data preprocessing, hybrid modeling, and explainability in developing reliable AI tools for Alzheimer's diagnosis, while emphasizing the need for further validation on diverse real-world data. [1], [2].

This work investigates the potential of ChatGPT, a cutting-edge large language model (LLM), for software design analysis specifically in detecting architectural patterns and tactics. The evaluation involves comparing ChatGPT’s performance with that of Archie, a traditional Eclipse plugin designed for architectural analysis. The study uses the source code of five open-source software systems as the testing ground. Results reveal that ChatGPT achieves noteworthy performance in both pattern and tactic detection tasks. Specifically, for pattern detection, ChatGPT demonstrates an accuracy of up to 47.06%, while for tactic detection, it achieves a precision of 28.25%. While ChatGPT’s current capabilities are not yet a replacement for specialized tools like Archie, it offers significant potential as a complementary tool in architectural analysis workflows. By bridging the gap between natural language understanding and software engineering, ChatGPT could pave the way for more intelligent and automated solutions in the field. However, a key limitation is its difficulties in handling foundational or traditional tactics, resulting in a lower detection rate in certain areas. This research contributes valuable insights into the application of LLMs in software engineering, highlighting both the strengths and the limitations of ChatGPT in addressing complex architectural tasks.