Bug severity prediction is a critical task in software engineering as it enables more efficient resource allocation and prioritization in software maintenance. While AI-based analyses and models significantly require access to extensive datasets, industrial applications face challenges due to data-sharing constraints and the limited availability of labeled data. In this study, we investigate method-level bug severity prediction using source code metrics and Large Language Models (LLMs) with two widely used datasets. We compare the performance of models trained using centralized learning, federated learning, and synthetic data generation. Our experimental results, obtained using two widely recognized software defect datasets, indicate that models trained with federated learning and synthetic data achieve comparable results to centrally trained models without data sharing. Our finding highlights the potential of privacy-preserving approaches such as federated learning and synthetic data generation to enable effective bug severity prediction in industrial context where data sharing is a major challenge.

The inability of PV panels to store the energy, changes in energy production due to weather conditions, and challenges in maintaining long-term efficiency create significant difficulties. In this study, we propose a comprehensive digital twin framework that integrates IoT, machine learning, mathematical modeling, and 3D visualization. To demonstrate the application of our framework, we conducted an experimental study focused on modeling the energy production of PV panels. To this end, we developed a mathematical model and 3D visualization and compared the performance of online and offline learning models. According to the machine learning results, LSTM was the most successful model (MSE: 0.0002). When online learning (MSE: 0.05) was compared with offline learning (MSE: 0.06), online learning demonstrated better performance in predicting energy production. The findings indicate that our digital twin framework could be a robust basis for energy management systems.

Abstract Refactoring, which aims to improve the internal structure of the software systems preserving their behavior, is the most common payment strategy for technical debt (TD) by removing the code smells. There exist many studies presenting code smell detection approaches/tools or investigating their impact on quality attributes. There are also studies that focus on refactoring techniques, their relation with quality attributes, tool supports, and opportunities for them. Although there are several studies addressing the gap between refactoring and TD indicators, the empirical evidence provided is still limited. In this study, we examine the distribution of 29 refactoring types among the different projects and their relation with code smells or faults. We explore the refactoring types that are most commonly performed together and other activities performed with refactorings. We conduct a large exploratory study with automatically detected 57,528 refactorings, 37,553 smells, 27,340 faults, and 134,812 commits of 33 Java projects. Results show that some refactoring types are more commonly applied by developers. Our analysis indicates that refactorings usually remove or do not affect the code smells, and this contradicts with the previous studies. Also, the commits in which refactoring(s) is performed are three times more fault inducing than those without refactoring.

Vulnerability prediction is a data-driven process that utilizes previous vulnerability records and their associated fixes in software development projects. Vulnerability records are rarely observed compared to other defects, even in large projects, and are usually not directly linked to the related code changes in the bug tracking system. Thus, preparing a vulnerability dataset and building a predicting model is quite challenging. There exist many studies proposing software metrics-based or embedding/token-based approaches to predict software vulnerabilities over code changes. In this study, we aim to compare the performance of two different approaches in predicting code changes that induce vulnerabilities. While the first approach is based on an aggregation of software metrics, the second approach is based on embedding representation of the source code using an Abstract Syntax Tree and skip-gram techniques. We employed Deep Learning and popular Machine Learning algorithms to predict vulnerability-inducing code changes. We report our empirical analysis over code changes on the publicly available SmartSHARK dataset that we extended by adding real vulnerability data. Software metrics-based code representation method shows a better classification performance than embedding-based code representation method in terms of recall, precision and F1-Score.