The Internet of Things (IoT) is transforming various domains, including smart energy management, by enabling the integration of complex digital and physical components in distributed cyber-physical systems (DCPSs). The design of DCPSs has so far been focused on performance-related, non-functional requirements. However, with the growing power consumption and computation expenses, sustainability is becoming an important aspect to consider. This has led to the concept of energy-aware DCPSs, which integrate conventional non-functional requirements with additional attributes for sustainability, such as energy consumption. This research activity aimed to investigate and develop energy-aware architectural models and edge/cloud computing technologies to design next-generation, AI-enabled (and, specifically, deep-learning-enhanced), self-conscious IoT-extended DCPSs. Our key contributions include energy-aware edge-to-cloud architectural models and technologies, the orchestration of a (possibly federated) edge-to-cloud infrastructure, abstractions and unified models for distributed heterogeneous virtualized resources, innovative machine learning algorithms for the dynamic reallocation and reconfiguration of energy resources, and the management of energy communities. The proposed solution was validated through case studies on optimizing renewable energy communities (RECs), or energy-aware DCPSs, which are particularly challenging due to their unique requirements and constraints; in more detail, in this work, we aim to define the optimal implementation of an energy-aware DCPS. Moreover, smart grids play a crucial role in developing energy-aware DCPSs, providing a flexible and efficient power system integrating renewable energy sources, microgrids, and other distributed energy resources. The proposed energy-aware DCPSs contribute to the development of smart grids by providing a sustainable, self-consistent, and efficient way to manage energy distribution and consumption. The performance demonstrates our approach’s effectiveness for consumption and production (based on RMSE and MAE metrics). Our research supports the transition towards a more sustainable future, where communities adopting REC principles become key players in the energy landscape.

In economic activity, recessions represent a period of failure in Gross Domestic Product (GDP) and usually are presented as episodic and non-linear. For this reason, they are difficult to predict and appear as one of the main problems in macroeconomics forecasts. A classic example turns out to be the great recession that occurred between 2008 and 2009 that was not predicted. In this paper, the goal is to give a different, although complementary, approach concerning the classical econometric techniques, and to show how Machine Learning (ML) techniques may improve short-term forecasting accuracy. As a case study, we use Italian data on GDP and a few related variables. In particular, we evaluate the goodness of fit of the forecasting proposed model in a case study of the Italian GDP. The algorithm is trained on Italian macroeconomic variables over the period 1995:Q1-2019:Q2. We also compare the results using the same dataset through Classic Linear Regression Model. As a result, both statistical and ML approaches are able to predict economic downturns but higher accuracy is obtained using Nonlinear Autoregressive with exogenous variables (NARX) model.

Melanoma is a malignant cancer type which develops when DNA damage occurs (mainly due to environmental factors such as ultraviolet rays). Often, melanoma results in intense and aggressive cell growth that, if not caught in time, can bring one toward death. Thus, early identification at the initial stage is fundamental to stopping the spread of cancer. In this paper, a ViT-based architecture able to classify melanoma versus non-cancerous lesions is presented. The proposed predictive model is trained and tested on public skin cancer data from the ISIC challenge, and the obtained results are highly promising. Different classifier configurations are considered and analyzed in order to find the most discriminating one. The best one reached an accuracy of 0.948, sensitivity of 0.928, specificity of 0.967, and AUROC of 0.948.

In the past two decades, several screening instruments were developed to detect toddlers who may be autistic both in clinical and unselected samples. Among others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a quantitative and normally distributed measure of autistic traits that demonstrates good psychometric properties in different settings and cultures. Recently, machine learning (ML) has been applied to behavioral science to improve the classification performance of autism screening and diagnostic tools, but mainly in children, adolescents, and adults. In this study, we used ML to investigate the accuracy and reliability of the Q-CHAT in discriminating young autistic children from those without. Five different ML algorithms (random forest (RF), naïve Bayes (NB), support vector machine (SVM), logistic regression (LR), and K-nearest neighbors (KNN)) were applied to investigate the complete set of Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and the SVM was the most effective, being able to classify autism with 95% accuracy. Furthermore, using the SVM–recursive feature elimination (RFE) approach, we selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was obtained from the 3 best discriminating items in common to ours and the previously reported Q-CHAT-10. This evidence confirms the high performance and cross-cultural validity of the Q-CHAT, and supports the application of ML to create shorter and faster versions of the instrument, maintaining high classification accuracy, to be used as a quick, easy, and high-performance tool in primary-care settings.

In recent years, statistics have confirmed that the number of elderly people is increasing. Aging always has a strong impact on the health of a human being; from a biological of point view, this process usually leads to several types of diseases mainly due to the impairment of the organism. In such a context, healthcare plays an important role in the healing process, trying to address these problems. One of the consequences of aging is the formation of pressure ulcers (PUs), which have a negative impact on the life quality of patients in the hospital, not only from a healthiness perspective but also psychologically. In this sense, e-health proposes several approaches to deal with this problem, however, these are not always very accurate and capable to prevent issues of this kind efficiently. Moreover, the proposed solutions are usually expensive and invasive. In this paper we were able to collect data coming from inertial sensors with the aim, in line with the Human-centric Computing (HC) paradigm, to design and implement a non-invasive system of wearable sensors for the prevention of PUs through deep learning techniques. In particular, using inertial sensors we are able to estimate the positions of the patients, and send an alert signal when he/she remains in the same position for too long a period of time. To train our system we built a dataset by monitoring the positions of a set of patients during their period of hospitalization, and we show here the results, demonstrating the feasibility of this technique and the level of accuracy we were able to reach, comparing our model with other popular machine learning approaches.