Abstract Tropospheric ozone forecasting is critical for public health, yet the deep learning models that achieve high accuracy often function as black boxes. This lack of transparency, along with the inability of popular explainability techniques like SHapley Additive exPlanations (SHAP) to capture essential temporal dependencies, limits their practical utility and trustworthiness in environmental management. To address this, we propose a novel framework, eXplainable Deep Learning with Spectral Co-clustering for Time Series, that integrates spectral co-clustering to enhance forecasting performance and provide post-hoc structured interpretability for air-quality time series. The methodology comprises data preprocessing, feature engineering (including lagging, rolling statistics, and time-based features), and deep learning architectures (Multilayer Perceptron, Gated Recurrent Unit, and hybrid models). Bayesian optimization is used to fine-tune hyperparameters. The core contribution is a spectral co-clustering technique that simultaneously partitions features and time instances into co-clusters, revealing critical inter-feature relationships and temporal patterns that drive predictions. The framework was rigorously validated through extensive experiments on data from five air quality monitoring stations. The proposed approach achieved RMSE values ranging from 0.73 to 6.08, significantly outperforming existing methods, including a temporal LSTM baseline, with performance improvements of approximately 59.19% to 95.65%. Results demonstrate that the proposed approach not only achieves high forecasting accuracy but also, through post-hoc heatmap visualizations of the objectively selected best-performing co-cluster, identifies the key features and time periods governing model predictions, thereby offering an interpretable understanding of the temporal and feature-level drivers associated with ozone variability. Thus, a transparent and effective solution for ozone forecasting is proposed, with a modular design generalizable to other environmental time series prediction tasks.

Telerehabilitation is a promising solution to ensure continuity of care for people with disabilities by delivering rehabilitation services directly in their homes or other familiar environments. This paper introduces a method for assessing movement execution during telerehabilitation sessions, offering effective support to clinicians during remote monitoring. This approach uses the 3D coordinates of the body joints provided by Microsoft Kinect to evaluate movement based on joint positions and angles. The proposed method identifies key deviations from expected movement patterns and generates graphical feedback to support the clinical evaluation of patients' performance. This system has been validated using the IntelliRehabDS dataset, which includes rehabilitation exercises designed for different pathologies. Preliminary results demonstrate the system's ability to detect deviations from the reference movement pattern, highlighting its potential as a practical tool to enhance remote rehabilitation monitoring.

Effective and efficient disease detection is crucial, particularly for economically important crops like cotton.In this paper, we move from the initial development of a deep-learning model for cotton leaf disease detection, called Deep-CCNet, to a more comprehensive comparison of different feature selection algorithms, such as RainWater Algorithm, Particle Swarm Optimization, Bee Evolutionary Algorithm, Genetic Algorithm, and Binary Dragonfly Algorithm.Although Deep-CCNet achieved satisfactory classification performance, the goal of this study is to improve the classification performance and efficiency of deep learning models with meta-heuristic feature selection techniques.This study aims to determine which feature selection method achieves the best balance between performance and computational efficiency.We used the Kaggle "cotton leaf disease dataset", which has 1,711 images from four classes (namely curl virus, bacterial blight, fusarium wilt, and healthy leaf images), to compare these techniques systematically.Our research attempts to find the most effective method that maximizes model performance while minimizing computing resources, in addition to benchmarking the computational and performance parameters of each approach.The results of this study provide a new approach for the choice of feature selection methods in plant pathology, leading to better early disease diagnosis and increased crop resilience via efficient farming practices.

Alzheimer’s disease represents a growing global health concern, emphasizing the need for early diagnosis to mitigate neurocognitive decline. Speech analysis has emerged as a promising, non-invasive approach, yet limited data availability hinders the development of robust Machine Learning (ML) models. To address this challenge, this study exploits the potentialities of Large Language Models (LLMs)—both their ability to generate synthetic data and their capacity to extract complex linguistic features from speech. We employ GPT-4 to generate synthetic transcripts, thus expanding the ADReSS2020 dataset and enhancing its diversity while preserving semantic and structural coherence. Moreover, we propose a novel multilevel feature extraction framework that integrates Bidirectional Encoder Representations from Transformers (BERT) embeddings fine-tuned with linguistic features obtained through Computerized Language Analysis (CLAN). The study involved two experiments: first, to identify the optimal feature extraction strategy and second, to evaluate the impact of synthetic data generated by GPT-4. In both experiments, the performance of five classifiers was evaluated to determine the most effective configuration. Our results demonstrated that fine-tuned BERT embeddings slightly improve classification performance compared to pre-trained models, highlighting the value of domain-specific fine-tuning. Although adding CLAN-like linguistic features yielded limited benefits, GPT-4-generated synthetic data demonstrated promising potential, particularly when combined with sentence embeddings. Classifiers such as Random Forest showed an improvement in accuracy, increasing from 0.79 to 0.88 when using the augmented dataset. This study paves the way for the use of LLMs to expand the diversity of datasets and improve the robustness of ML models in clinical applications.

Alzheimer’s disease (AD) represents a major public health challenge due to its irreversible progression and increasing prevalence among the aging population. Early diagnosis is crucial, and recent advances in Artificial Intelligence and data analytics have shown promising results in detection methods. This study proposes an approach based on deep neural networks for automatic AD detection from the speech data of the ADReSS2020 dataset, using log-Mel spectrogram representation. To address data limitations and enhance model performance, we applied five data augmentation techniques, which significantly improved accuracy by introducing greater variability in audio characteristics. We evaluated the performance of three models: a CNN-LSTM network and two transfer learning approaches based on ResNet50 and VGG16. Experimental results showed that the CNN-LSTM model performs best, achieving an accuracy of 68%, with a significant improvement of 9.67% over the baseline. ResNet50-LSTM and VGG16-LSTM followed with $\mathbf{6 7} \%$ and $\mathbf{6 6} \%$ accuracy, respectively. This work demonstrates the potential of deep learning-based speech-driven approaches as scalable and noninvasive tools for Alzheimer’s diagnosis and highlights the importance of data enhancement to improve model performance.

This work examines the combined effect of segmentation and data augmentation, two key preprocessing strategies often studied separately, on AI model classification performance and explainability. Three key experiments are conducted. First, the modified MobileNetV2 is applied to 21,165 raw images from the COVID-19 Radiography Database. While classification results are strong, Grad-CAM explanations misfocus on areas below the chest. Second, U-Net segmentation crops chest regions, and applying rotation, flipping, and brightness adjustment achieves a balance between accuracy and explainability. Third, precise cropping using U-Net segmentation masks isolates chest areas but slightly degrades classifier performance without further explainability gains. Findings suggest that combining U-Net segmentation with augmentation enhances explainability while maintaining model precision for COVID-19 detection. Their integration offers a trade-off between accuracy and explainability, reinforcing their complementary role in medical image analysis.

The growing demand for transparent and trustworthy Artificial Intelligence (AI) in healthcare is increasing the focus on the in-terpretability of predictive models, a crucial aspect for the realization of precise Digital Twins (DTs) for health. In this study, we compare intrinsically interpretable models with black-box solutions supported by post-hoc explanation techniques, aiming to improve the predictive capacity of DTs regarding the progression of Multiple Sclerosis (MS). We explore different typologies of models, such as logistic regression and neural networks, and evaluate their predictions using specific metrics for unbalanced clinical datasets, typical of DT simulations. We analyse feature attribution with a special emphasis on the comparison between native interpretability and explanations derived via SHAP (SHapley Additive Explanations), in order to validate the reliability of explanatory analyses in complex DTs. Preliminary results suggest that post-hoc methods can produce feature importance profiles aligned with those of interpretable models. This supports the use of post-hoc methods when greater model complexity is required within a DT architecture. This work highlights the practical considerations involved in balancing model performance and interpretability for decision support in longitudinal clinical settings, a critical aspect for the validation and effective use of digital twins in MS management.

Artificial intelligence and deep learning are powerful tools for extracting knowledge from large datasets, particularly in healthcare. However, their black-box nature raises interpretability concerns, especially in high-stakes applications. Existing eXplainable Artificial Intelligence methods often focus solely on visualization or rule-based explanations, limiting interpretability's depth and clarity. This work proposes a novel explainable AI method specifically designed for medical image analysis, integrating statistical, visual, and rule-based explanations to improve transparency in deep learning models. Statistical features are derived from deep features extracted using a custom Mobilenetv2 model. A two-step feature selection method - zero-based filtering with mutual importance selection - ranks and refines these features. Decision tree and RuleFit models are employed to classify data and extract human-readable rules. Additionally, a novel statistical feature map overlay visualization generates heatmap-like representations of three key statistical measures (mean, skewness, and entropy), providing both localized and quantifiable visual explanations of model decisions. The proposed method has been validated on five medical imaging datasets - COVID-19 radiography, ultrasound breast cancer, brain tumor magnetic resonance imaging, lung and colon cancer histopathological, and glaucoma images - with results confirmed by medical experts, demonstrating its effectiveness in enhancing interpretability for medical image classification tasks.

The use of Super-Resolution SR algorithms applied to Magnetic Resonance Images (MRIs) is increasingly common in the medical field. Increasing the resolution of images allows physicians to more easily observe image details. Over the years, several SR approaches have been tried by researchers. Among the various approaches, Diffusion Models (DMs) have been shown to perform well in the SR task. In this work, we propose the use of a Latent Diffusion Model (LDM) for the SR of medical images. Different studies have shown that LDMs improve the performance of DMs in several SR tasks. To our knowledge, LDMs have not been tested for SR of medical images such as MRIs. We therefore perform fine-tuning of an LDM on medical datasets. To evaluate the SR images generated by the LDM, we compare them to the original high-resolution images using two similarity measurements. We show that the LDM achieves better similarity values than other SR models on the same medical dataset. We also show with visual examples the advantage of applying SR using an LDM.

Stress is considered one of the most prevalent concerns among individuals. Studies have shown that experiencing long-term stress can cause severe health issues such as cardiovascular diseases, hypertension, depression, etc. Preventative measures, such as early stress detection, can help individuals mitigate these health issues. When a person gets stressed, physiological values like blood volume pulse, temperature, and electrodermal activity signals get affected. Machine Learning techniques can be utilized to identify stress by analyzing these physiological signals. This paper presents a machine learning method for detecting stress levels of an individual using the publicly available dataset called "Wearable Stress and Affect Detection"(WESAD), which has physiological data collected from the wrist-worn and chest-worn sensors attached to 15 different subjects. We used physiological signals, including Blood Volume Pulse(BVP), Body Temperature(TEMP), and Electrodermal Activity(EDA) signals, collected from wrist-worn sensors to detect the state of the mind. For the implementation, we used different Machine Learning models, like Logistic Regression, Decision Tree, Random Forest, and Stacking Ensemble Learning technique. During the investigation, personalized models, utilizing individual subject data, and generalized models, amalgamating all subject data, were developed. Evaluation reveals accuracy values reaching up to 99% and 91% for individual subject data and combined data, respectively.

This research presents DeepCRINet, a deep learning (DL) model designed for reliable performance across various Chest Radiography Images (CRIs) datasets, in response to the urgent need for quick and accurate lung disease identification utilizing CRIs. Our method builds on earlier research, which frequently used single-source datasets that might not adequately represent the heterogeneity present in clinical situations. Our model’s diagnostic adaptability and real-world dependability are improved by utilizing images from different datasets, which helps us overcome limitations such as dataset bias, robustness, generalizability, and underrepresentation of conditions. With validation on a broad dataset consisting of 14,096 images (from three different datasets), DeepCRINet provides a solution that demonstrates excellent flexibility in recognizing illnesses including TuBerculosis, Pneumonia, COVID-19, and Lung Opacity. Through data augmentation, we improve the dataset, supporting training and testing procedures and confirming the model’s ability to generalize. We used occlusion sensitivity as a kind of explainable AI to openly identify and visually emphasize regions important to proper classification. This ability not only shows that DeepCRINet is analytically better than other DL models and hybrid techniques, but it also improves patient outcomes and diagnosis, which makes it a vital tool for medical professionals like radiologists.

Tele-rehabilitation has recently emerged as an effective solution for providing assisted living, increasing clinical outcomes, positively enhancing patients' Quality of Life (QoL) and fostering their reintegration into society, also pushing down clinical costs. Cloud computing in combination with Edge Computing, the Internet of Things (IoT), Big Data storage and analytics, and Artificial Intelligence (AI) are the main enablers for tele-rehabilitation. In this paper, we present the Italian founded PRIN 2022 project entitled “Tele-rehabilitation as a Service (TRaaS)”. It aims at creating a piece of reference intelligent Cloud/Edge framework architecture and a standard data model for the development of different kinds of new de-hospitalized tele-rehabilitation services. In particular, the rationale, study design, and methodology are discussed, also highlighting future research directions.

Colon and Lung cancers are two of the most common causes of mortality in adults. They may simultaneously form in organs and have a detrimental effect on human life. There is a high risk that cancer will spread to the two organs if it is not discovered in the early stages. One of the most essential elements of successful therapy is the histological diagnosis of such cancers. Deep learning algorithms have improved the speed and accuracy of time-consuming and challenging procedures, enabling researchers to examine a huge number of patients swiftly and inexpensively. By examining their histological images and applying modern deep learning, this study develops a classification framework called DeepLCCNet to discriminate between five kinds of colon and lung tissues (three malignant and two benign). More precisely, we have classified five tissue types of Lung and Colon Cancer Histopathological Images data set using our model, i.e., benign tissue of the lung, squamous cell carcinoma of the lung, adenocarcinoma of the lung, benign tissue of the colon, and adenocarcinoma of the colon. According to the results, the proposed model can detect cancer tissues with an average accuracy of 99.67% and maximum accuracy of 99.84%. Medical professionals will be able to utilize a precise, automated system for detecting and classifying various kinds of colon and lung cancers.

Edge Analytics and Artificial Intelligence are important features of the current smart connected living community. In a society where people, homes, cities, and workplaces are simultaneously connected through various devices, primarily through mobile devices, a considerable amount of data is exchanged, and the processing and storage of these data are laborious and difficult tasks. Edge Analytics allows the collection and analysis of such data on mobile devices, such as smartphones and tablets, without involving any cloud-centred architecture that cannot guarantee real-time responsiveness. Meanwhile, Artificial Intelligence techniques can constitute a valid instrument to process data, limiting the computation time, and optimising decisional processes and predictions in several sectors, such as healthcare. Within this field, in this article, an approach able to evaluate the voice quality condition is proposed. A fully automatic algorithm, based on Deep Learning, classifies a voice as healthy or pathological by analysing spectrogram images extracted by means of the recording of vowel /a/, in compliance with the traditional medical protocol. A light Convolutional Neural Network is embedded in a mobile health application in order to provide an instrument capable of assessing voice disorders in a fast, easy, and portable way. Thus, a straightforward mobile device becomes a screening tool useful for the early diagnosis, monitoring, and treatment of voice disorders. The proposed approach has been tested on a broad set of voice samples, not limited to the most common voice diseases but including all the pathologies present in three different databases achieving F1-scores, over the testing set, equal to 80%, 90%, and 73%. Although the proposed network consists of a reduced number of layers, the results are very competitive compared to those of other “cutting edge” approaches constructed using more complex neural networks, and compared to the classic deep neural networks, for example, VGG-16 and ResNet-50.

The papers in this special focus on enabling technologies for next generation telehealthcare applications. The use of Information and Communication Technology (ICT) for health and well-being is rapidly increasing in the majority of high-income countries. The interest about telehealthcare allows the provisioning of various kinds of health-related services and applications over the Internet. There are several benefits associated with tele-healthcare, including: the reduction of infection risk due to optimized patients access to clinical centers; optimized healthcare workflows; containment of hospital costs; increased patient safety; improves in the quality of life of both patients and their families. Common telehealthcare applications include tele-nursing, tele-rehabilitation, tele-dialog, tele-monitoring, tele-analysis, tele-pharmacy, tele-care, tele-psychiatry, tele-radiology, tele-pathology, teledermatology, tele-dentistry, tele-audiology, tele-ophthalmology, etc. In the past ten years, key enabling technologies (KETs) such as Internet of Things (IoT), tools for big data management and processing, Cloud/Edge/Fog computing, Artificial Intelligence (AI), Blockchain reached an advanced maturity, and therefore the potential for revolutionizing the whole tele-healthcare sector.

Video summarization (VS) has attracted intense attention recently due to its enormous applications in various computer vision domains, such as video retrieval, indexing, and browsing. Traditional VS researches mostly target at the effectiveness of the VS algorithms by introducing the high quality of features and clusters for selecting representative visual elements. Due to the increased density of vision sensors network, there is a tradeoff between the processing time of the VS methods with reasonable and representative quality of the generated summaries. It is a challenging task to generate a video summary of significant importance while fulfilling the needs of Internet of Things (IoT) surveillance networks with constrained resources. This article addresses this problem by proposing a new computationally effective solution through designing a deep CNN framework with hierarchical weighted fusion for the summarization of surveillance videos captured in IoT settings. The first stage of our framework designs discriminative rich features extracted from deep CNNs for shot segmentation. Then, we employ image memorability predicted from a fine-tuned CNN model in the framework, along with aesthetic and entropy features to maintain the interestingness and diversity of the summary. Third, a hierarchical weighted fusion mechanism is proposed to produce an aggregated score for the effective computation of the extracted features. Finally, an attention curve is constituted using the aggregated score for deciding outstanding keyframes for the final video summary. Experiments are conducted using benchmark data sets for validating the importance and effectiveness of our framework, which outperforms the other state-of-the-art schemes.

Health 4.0 can provide effective ways to improve the health status of subjects by taking advantage of cyber-physical systems and Internet of things technologies for the solution of healthcare problems. One of these is represented by suitably estimating blood pressure values of subjects in a continuous, real-time, and noninvasive way. To address it, we propose an approach only requiring a photoplethysmography (PPG) sensor and a mobile/desktop device. The approach avails itself of genetic programming to automatically find an explicit relationship between blood pressure values and PPG ones. This relationship is tested on a set of 11 subjects and compared against other regression methods, and turns out to be better. Namely, the root-mean-square error values are equal to 8.49 and 6.66 for the systolic and the diastolic blood-pressure values, respectively. Those for the relative error, instead, are equal to 5.55% for the systolic and 6.59% for the diastolic values.

The wide availability of sensing devices in the medical domain causes the creation of large and very large data sets. Hence, tasks as the classification in such data sets becomes more and more difficult. Deep Neural Networks (DNNs) are very effective in classification, yet finding the best values for their hyper-parameters is a difficult and time-consuming task. This paper introduces an approach to decrease execution times to automatically find good hyper-parameter values for DNN through Evolutionary Algorithms when classification task is faced. This decrease is obtained through the combination of two mechanisms. The former is constituted by a distributed version for a Differential Evolution algorithm. The latter is based on a procedure aimed at reducing the size of the training set and relying on a decomposition into cubes of the space of the data set attributes. Experiments are carried out on a medical data set about Obstructive Sleep Anpnea. They show that sub-optimal DNN hyper-parameter values are obtained in a much lower time with respect to the case where this reduction is not effected, and that this does not come to the detriment of the accuracy in the classification over the test set items.

This paper aims to investigate and compare the accuracy of different data mining classification schemes, employing Ensemble Machine Learning Techniques, for the prediction of heart disease. The Cleveland data set for heart diseases, containing 303 instances, has been used as the main database for the training and testing of the developed system. 10-Fold Cross-Validation has been applied in order to increase the amount of data, which would otherwise have been limited. Different classifiers, namely Decision Tree (DT), Naïve Bayes (NB), Multilayer Perceptron (MLP), K-Nearest Neighbor (K-NN), Single Conjunctive Rule Learner (SCRL), Radial Basis Function (RBF) and Support Vector Machine (SVM), have been employed. Moreover, the ensemble prediction of classifiers, bagging, boosting and stacking, has been applied to the dataset. The results of the experiments indicate that the SVM method using the boosting technique outperforms the other aforementioned methods.

The aim of this study is to identify an explicit relationship between life-style and the risk of falling under the form of a mathematical model. Starting from some personal and behavioral information as, e.g., weight, height, age, data about physical activity habits, and concern about falling, the model would easily estimate the score of the Mini-Balance Evaluation Systems (Mini-BES) test. This would make fall risk assessment less invasive, because subjects would not need to undergo the classical Mini-BES test, rather they could estimate it at home by answering some questionnaires. The mathematical model obtained in this study has been tested over a subset of unseen subjects and the results show an average error of ±2.74.

The advent of Cloud computing is changing the way of conceiving information and communication systems in different application fields including Biotechnology. In this context, an emerging research field is Next-Generation Sequencing (NGS) that includes several recent technologies allowing sequencing DNA and that have revolutionized the study of genomics and molecular biology. These cutting-edge sequencing systems produce big datasets that require significant scalable computing resources. In this paper, we analyse and classify the major current NGS Cloud-based solutions adopted in scientific laboratories according to different Cloud service levels. Moreover, by means of a taxonomy, we discuss the challenges and advantages of possible future NGS Cloud-based systems.

Continuous blood pressure (BP) measurement is an important issue in the medical field. The hypothesis of existence of a nonlinear relationship between plethysmography (PPG) and BP values has been investigated in this paper. If this hypothesis is true, then it is possible to indirectly measure patient's BP in a non-invasive way through the application of a wearable wireless PPG sensor to patient's finger and through the use of the results of a regression analysis aimed at linking PPG and BP values. To find the relationship between these two biomedical characteristics we have used here Genetic Programming (GP), because in a regression task it can evolve in an automatic way the structure of the most suitable explicit mathematical model. An analysis of the related scientific literature shows that this is the first attempt to mathematically relate PPG and BP values through GP. In this paper some preliminary experiments on the use of GP in facing this regression task have been carried out. As a result, for both systolic and diastolic BP values explicit mathematical models providing nonlinear relationship between PPG and BP values have been achieved, involving an approximation error of around 2 mmHg in both cases. A prototypal mobile-based system has been realized which is able to continuously estimate in real time the two BP values for any given patient by using only a plethysmography signal and the obtained mathematical models.

Detection and real time monitoring of obstructive sleep apnea (OSA) episodes are very important tasks in healthcare. To suitably face them, this paper proposes an easy-to-use, cheap mobile-based approach relying on three steps. First, single-channel ECG data from a patient are collected by a wearable sensor and are recorded on a mobile device. Second, the automatic extraction of knowledge about that patient takes place offline, and a set of IF…THEN rules containing heart-rate variability (HRV) parameters is achieved. Third, these rules are used in our real-time mobile monitoring system: the same wearable sensor collects the single-channel ECG data and sends them to the same mobile device, which now processes those data online to compute HRV-related parameter values. If these values activate one of the rules found for that patient, an alarm is immediately produced. This approach has been tested on a literature database with 35 OSA patients. A comparison against five well-known classifiers has been carried out.

Automatic fall detection is a major issue in taking care of the health of elderly people. In this task the capability of telling in real time falls from normal daily activities is crucial. To this aim, this paper proposes an approach based on the automatic extraction of knowledge expressed as a set of IF...THEN rules from a database of fall recordings. This set of rules, generated offline, can then be exploited in a real-time mobile monitoring system: data gathered by wearable sensors are processed in real time and, if their values activate some of the rules describing falls, an alarm message is automatically produced. The approach has been compared against other classifiers on a real-world fall database, and its discrimination ability is shown to be higher. Moreover, a test phase for the real-time mobile monitoring system is being carried out over real cases.

Performing detection and real-time monitoring of Obstructive Sleep Apnea (OSA) is a significant healthcare task. An easy, cheap, and mobile approach to monitor patients with OSA is proposed here. It gathers data from a patient by a single-channel ECG, and offline automatically extracts knowledge about that patient as a set of IF...THEN rules containing Heart Rate Variability (HRV) parameters. These rules are then used in the real-time mobile monitoring system: ECG data is collected by a wearable sensor, sent to a mobile device, and processed online to compute HRV-related parameter values. If a rule is activated by those values, the system produces an alarm. A literature database of OSA patients has been used to test the approach.