Technical Debt (TD) is one of the main obstacles to the quality and sustainability of software in the long term, accumulating "interest" that increases maintenance costs and reduces the productivity of development teams. Among the strategies to manage TD, refactoring stands out for its ability to improve the internal structure of the code without changing its external behavior, contributing to improving the readability, maintainability, and extensibility of the software. This study analyzes the impact of refactoring on TD using metrics extracted from SonarQube and RefactoringMiner at the class level. TD is represented by the "sqale_debt_ratio" and stratified in quartiles to model its levels. The analysis focuses both on the presence or absence of refactoring and on the influence of specific types and levels of applications. Evaluating the role of refactoring is fundamental to understanding how these practices can reduce TD, improve software quality, and optimize maintenance. To ensure the robustness of the models, metrics directly related to TD were removed and collinearity-based selection techniques were applied. The validation of the approach was performed on six open-source software systems available on GitHub. The predictive models, built with machine learning techniques, were analyzed with SHAP (Shapley Additive exPlanations) to identify the most relevant features. The results of the study are promising and demonstrate how the adoption of targeted refactoring practices can effectively reduce TD. The combined approach of prediction and explainability helps to fill a gap in the literature and offers practical guidance for managing TD and optimizing refactoring practices in software systems.

Artificial intelligence and Machine Learning represent a fundamental role in the medical field today, even in the case of neurode-generative diseases such as Parkinson’s disease; particularly in non-invasive diagnostics. This work presents a machine learning-based approach for the early detection of Parkinson’s disease through voice recordings. Additionally, explainability techniques are applied to highlight key vocal features associated with the condition, supporting clinical interpretation and future integration in digital healthcare systems. The study aims to contribute to the timely diagnosis of Parkinson’s, providing an in-depth understanding of the disease to open up new opportunities for a more personalised and precise approach to therapies, representing a first step toward the future of predictive medicine.

Parkinson’s Disease (PD) is a neurodegenerative condition primarily affecting the elderly but also occurring in younger individuals. It is caused by a progressive loss of nerve cells in the brain’s substantia nigra that release dopamine, essential for controlling movements. Dopamine deficiency results in symptoms affecting both motor and non-motor functions, which vary among individuals. Diagnosis relies on clinical symptoms and medical history, often supported by brain scans, as there is no specific diagnostic test available. Diagnosis is challenging due to vague initial symptoms resembling other conditions. Current research indicates that AI can significantly enhance data and image analysis, aiding in the diagnosis and monitoring of PD progression. To this aim, this study proposes a hybrid model allowing the integrated use of clinical data and single photon emission computed tomography images of a patient to predict the presence of the disease. The approach consists of a combination of two types of neural networks, an LSTM for clinical data and a CNN for images. The validation is performed on a widely validated dataset belonging to the Parkinson’s Progression Markers Initiative, from which the data recording visits of 1,814 patients were extracted. The obtained results are interesting and useful to address further investigations.

Today, several chest diseases are on the rise and these are often diagnosed through the use of chest X-rays, a common and economical clinical test to perform. This work uses a machine learning approach for the detection of thoracic diseases using chest X-ray reports and involves leveraging algorithms and models to analyze medical imaging data for the presence of various conditions affecting the chest area. Our main goal is to create a predictive model based on textual reports released by radiologists, with the use of Natural Language Processing. The proposed approach aims to facilitate the examination of textual reports written by radiologists, to predict the onset of diseases in patients. Specifically, reports generated by radiologists are meticulously processed and reviewed using the GloVe and LSI models. This analysis allows you to identify the presence of diseases and provides insights into the specific thoracic pathology. The results obtained through the implementation of our approach (accuracy above 96% for the best model) underline the good performance and potential of the developed predictive model.

Although Internet traffic detection and categorization have been extensively researched over the last decades, it remains a hot issue in the Internet of Things (IoT) context, mainly when traffic is generated in medical structures. Theoretically, it is possible to apply classical methods for IoT traffic categorization and to detect traffic addressed to intelligent devices present in hospital rooms. The problem is always to get a proper medical IoT traffic dataset. In this work, we have created a synthetic dataset of IoT traffic generated by different smart devices put in different hospital rooms. For creating the medical IoT traffic, we have exploited IoT-Flock, an open-source tool for IoT traffic generation supporting CoAP and MQTT, the most used IoT protocols. We have performed, for the first time, a multinomial classification of IoT-Flock-generated traffic considering both normal-traffic and packets of different attacks. The classification has been performed by comparing both traditional machine learning techniques and deep learning network models composed of several hidden layers. The obtained results are very encouraging and can confirm the usability of IoT-Flock data to be used to test and train machine and deep learning models to detect abnormal IoT traffic in a medical scenario.

The architectural space impacts the emotional state of its inhabitants. Nevertheless, no studies have investigated, to date, how it influences the perception of others' affective states, possibly impacting our social behavior. This paper analyzes the eye-gaze data collected during a social scenario recreated after a promenade within virtual architectures. Immersive and dynamic virtual architectures were characterized by decreasing or increasing sidewall distance, ceiling height, windows height, and different colors. At the end of such an experience, participants judged the arousal level expressed by a virtual avatar. For the first time, we apply machine and deep learning techniques to the behavioral, environmental, and eye-gaze features extracted during the dynamic experience of virtual architectures. In order to verify the feasibility of automated classification of the final arousal judgment on the avatar emotional expression, we have considered both interpretable, i.e., decision trees, and black-box models, i.e., dense neural networks. The decision tree reached an accuracy rate of 66%, showing the importance of eye-gaze parameters to classify the participants' arousal judgment. The black-box dense neural network increased the accuracy up to 80%. Overall, our findings demonstrate the capability of artificial intelligence methodologies to classify and possibly predict the arousal judgment of body expressions at the end of a virtual promenade. Such knowledge will serve the design and evaluation of future spaces by combining virtual reality and artificial intelligence within the experience of architecture. In such a way, it will be possible to predict the influence of the surrounding architecture on human social behavior.

Heart disease is becoming the biggest cause of mortality worldwide. Its early detection can considerably lower the risk of mortality and help to promote its successful treatment. However, this early detection necessitates regular monitoring of a wide range of clinical and lifestyle factors. This is why a growing number of studies are being conducted to automate the forecasting of cardiac diseases, beginning with an examination of ECG images, which is the first diagnostic test performed on patients and also the most simple and economical to conduct. This study investigates the use of three groups of ECG images acquired from three separate sets of cardiac patients, with different heart-related illnesses, and a set of healthy controls to predict heart disease using deep learning classifiers. The evaluation is carried out on a real-life dataset, and the results highlight really interesting findings.