One-Shot Federated Learning (OSFL) enables collaborative training in a single round, eliminating the need for iterative communication, making it particularly suitable for use in resource-constrained and privacy-sensitive applications. This survey offers a thorough examination of One-Shot FL, highlighting its distinct operational framework compared to traditional federated approaches. One-Shot FL supports resource-limited devices by enabling single-round model aggregation while maintaining data locality. The survey systematically categorizes existing methodologies, emphasizing advancements in client model initialization, aggregation techniques, and strategies for managing heterogeneous data distributions. Furthermore, we analyze the limitations of current approaches, particularly in terms of scalability and generalization in non-IID settings. By analyzing cutting-edge techniques and outlining open challenges, this survey aims to provide a comprehensive reference for researchers and practitioners seeking to design and implement One-Shot FL systems, advancing the development and adoption of One-Shot FL solutions in real-world, resource-constrained settings.

Accurate energy consumption forecasting is becoming increasingly important due to rising global energy demands driven by economic development and population growth. Traditional forecasting models often overlook the impact of contextual factors, such as weather conditions and occupancy trends, which are essential for precise predictions. In this study, we propose a hybrid context-aware simulated scenario generation (CA-SSG) approach that integrates context space theory (CST) with deep learning techniques. This method leverages key contextual features to generate synthetic energy consumption data that more accurately mimics real-world patterns. Using the ASHRAE Great Energy Predictor III dataset, which includes diverse building types across various climates, we demonstrate the effectiveness of CA-SSG. The results show significant improvements in model performance, with reductions in Kullback-Leibler divergence (5%), increases in Pearson Correlation Coefficient (5%), and decreases in computation time compared to traditional approaches. These findings highlight the advantages of contextually enriched generative models for developing smarter energy management systems, enabling more accurate energy forecasting, and supporting strategic planning for energy consumption.

Federated Learning (FL) diverges from traditional Machine Learning (ML) models decentralizing data utilization, addressing privacy concerns. This approach involves iterative model updates, where individual devices compute gradients based on local data, share updates with a central server, and receive an improved global model. High-Performance Computing (HPC) systems enhance FL efficiency by leveraging parallel processing. In this study, we aim to explore FL efficiency using four aggregation methods on three datasets across six clients, assess metrics like global model accuracy and communication efficiency, and evaluate FL on HPC. We employ Flower, a versatile FL framework, in our experiments. Our chosen datasets include MNIST, Digits, and Semeion Handwritten Digit, distributed among two clients each. We utilize NVIDIA GPUs for computation, with aggregation methods such as FedAvg, FedProx, FedOpt, and FedYogi. Metrics include Convergence Time, Global Model Accuracy, Communication Efficiency, and HPC Throughput. The results will provide insights into FL performance, especially in HPC environments, impacting convergence, communication, and resource utilization.

Characterizing the heterogeneity of cancer metabolism requires the knowledge of metabolic fluxes in different tumor types. These fluxes cannot be directly determined, especially at a sub-cellular level. Still, they can be obtained numerically through constraint-based steady-state models after integrating other high-throughput -omics data, such as transcriptomics. In this work, we proposed to study cancer metabolism through data analysis and machine learning methodologies. To this aim, we considered transcriptomics profiles for a large set of cancer cells. Using a core metabolic network as a scaffold, we generated many feasible flux distributions for each cancer cell. Then, we used cluster analysis to analyze these data. This preliminary analysis revealed three well-separated clusters having different metabolic behaviors.

Over the past two years, the COVID-19 pandemic has been one of the most frequently and hotly debated social topics. Lockdowns and restrictions radically change the way of working and socializing due to social distancing and wearing masks; the ongoing pandemic impacts people's life and psychological health. Infection Rate Rthas been the main parameter used by national and local governments worldwide for describing the pandemic behavior synthetically. Rtwas adopted to define containment policies (lockdowns, social distancing, intermittent regional strategies, etc.) that have affected social life. In the present paper, we propose an Artificial Intelligence (AI) approach for the modeling of the COVID-19 Infection Rate Rtby exploiting the novel methodology of the Physics-Informed Neural Networks (PINNs) to compute the susceptible-infected-dead-recovered (SIDR) model. To test the accuracy of the neural network, we predicted the susceptible, infected, dead, and recovered on the next 30 days against the considered period.

Abstract Nowadays, statistical arbitrage is one of the most attractive fields of study for researchers, and its applications are widely used also in the financial industry. In this work, we propose a new approach for statistical arbitrage based on clustering stocks according to their exposition on common risk factors. A linear multifactor model is exploited as theoretical background. The risk factors of such a model are extracted via Principal Component Analysis by looking at different time granularity. Furthermore, they are standardized to be handled by a feature selection technique, namely the Adaptive Lasso, whose aim is to find the factors that strongly drive each stock’s return. The assets are then clustered by using the information provided by the feature selection, and their exposition on each factor is deleted to obtain the statistical arbitrage. Finally, the Sequential Least SQuares Programming is used to determine the optimal weights to construct the portfolio. The proposed methodology is tested on the Italian, German, American, Japanese, Brazilian, and Indian Stock Markets. Its performances, evaluated through a Cross-Validation approach, are compared with three benchmarks to assess the robustness of our strategy.

Summary New technologies, tools, and methodologies have been used in the Cultural Heritage (CH) scenarios to assist the visitor to enrich and enjoy his experiences during the visit. Intelligent information systems based upon machine learning approaches have been specifically designed for CH to enhance the quality of services in art exhibitions and events. In this work, we show an innovative framework that can be specifically designed to help visitors during his/her visit by answering to their questions. We also describe a system architecture and a case study in a well‐defined CH context.

Real-time social multimedia level threat monitoring is becoming harder, due to higher and rapidly increasing data induction. Data induction through electric smart devices is greater compared to information processing capacity. Nowadays, data becomes humongous even coming from the single source. Therefore, when data emanates from all heterogeneous sources distributed over the globe makes data magnitude harder to process up to a needed scale. Big data and Deep learning have become standard in providing well-known solutions built-up using algorithms and techniques in resolving data matching issues. Now, with the involvement of sensors and automation in generating data obscures everything, predicting results to overcome a current era of ever enhancing demands and getting real-time visualization brings the need of feature like human behavior mode extraction to overcome any future threats. Big data analytics can bring the opportunity of predicting any misfortune even before they happen. Map reduce feature of big data supports massive data oriented process execution using distributed processing. Real-time human feature identification and detection can occur through sensors and internet sources. A behavioral prediction can further classify the information collected for introducing enhanced security extents. Real-time sensor devices are producing 24/7-hour data for further processing recording each event. IoT-based sensors can support in behavioral analysis model of a human. Real-time human behavioral monitoring based on image processing and IoT using big data analytics.

Summary Taxi GPS trajectories can be mined and used to optimize urban traffic scheduling. The optimization of traffic scheduling is important, especially in megacities such as Beijing. In this paper, we analyze the traffic features in Beijing by mining taxi GPS trajectories. We define the Congestion Coefficient of each edge of the taxi trajectory as the consumed time of a taxi running over a unit of distance. By analyzing the distribution of congestion coefficients of all taxi trajectories, we can observe that, on working days, (1) the congestion coefficient is between 0 and 2 (average speed is greater than 0.5 m/s) and is acceptable to taxi drivers, (2) the morning rush hours are 7:00 ∼ 10:00, (3) the evening rush hours are 17:00 ∼ 20:00, and (4) the traffic congestion in the morning rush hours is worse than that in the evening rush hours; on the weekend, (1) the congestion coefficient is less than 0.2 (average speed is greater than 5 m/s) and is acceptable to taxi drivers; (2) compared with the traffic congestion on working days, there are no significant morning rush hours on the weekend; and (3) the period of the time between 13:00 and 15:00 could be considered the traffic rush hours on the weekend. These findings can be used to improve urban traffic management.

Summary The mining of human mobility can be exploited to support the design of traffic planning, route recommendations, urban planning, emergency management, and land use. Currently, various methods such as the machine learning algorithms, statistical methods, and semantic analysis are widely applied to identify and extract human mobility patterns. In this paper, we propose a simple and generic paradigm for mining human mobility patterns based on the GPS trajectory data using complex network analysis. The essential ideas behind the proposed paradigm mainly include (1) creating weighted complex networks of GPS trajectories and (2) extracting the human mobility patterns by analyzing the structures and metrics of the created complex networks of GPS trajectories. To evaluate the performance of the proposed paradigm, we design five groups of experiments and identify the mobility patterns of the selected five persons based on the selected five network analysis metrics. Experimental results indicate that (1) the proposed paradigm is effective and (2) the quite interesting potential information about the human mobility can be mined easily. The proposed paradigm is simple and generic, which can be employed to rapidly identify the human mobility patterns based on the GPS trajectory data.

Nowadays, a sustainable and smart city focuses on energy efficiency and the reduction of polluting emissions through smart mobility projects and initiatives to “sensitize” infrastructure. Smart parking is one of the building blocks of intelligent mobility, innovative mobility that aims to be flexible, integrated, and sustainable and consequently integrated into a Smart City. By using the Internet of Things (IoT) sensors located in the parking areas or the underground car parks in combination with a mobile application, which indicates to citizens the free places in the different areas of the city and guides them toward the chosen parking, it is possible to reduce air pollution and fluidifying noise traffic. In this article, we present and discuss an innovative Deep Learning-based ensemble technique in forecasting the parking space occupancy to reduce the search time for parking and to optimize the flow of cars in particularly congested areas, with an overall positive impact on traffic in urban centres. A genetic algorithm has also been used to optimize predictors parameters. The main goal is to design an intelligent IoT-based service that can predict, in the next few hours, the parking spaces occupancy of a street. The proposed approach has been assessed on a real IoT dataset composed by over than 15M of collected sensor records. Obtained results demonstrate that our method outperforms both single predictors and the widely used strategy of the mean providing inherently robust predictions.

Summary An effective strategy for accelerating the calculation of convex hulls is to filter the input points by discarding interior points. In this paper, we present such a straightforward preprocessing approach by discarding the points locating in a convex polygon formed by 16 extreme points. Extreme points of a planar point set do not alter when all points are rotated with the same angle in the plane. Four groups of four extreme points with min or max x or y coordinates can be found for the original point set and three rotated point sets. These 16 extreme points are used to form a planar convex polygon. We discard those points locating in the convex polygon and calculate the desired convex hull of the remaining points. The proposed preprocessing algorithm is evaluated on two computational platforms. Experiments show that, when employing the proposed preprocessing algorithm on the computational platform 1, it achieves speedups of approximately 4 ×∼5× on average and 5 ×∼6× in the best cases over the cases where the proposed approach is not used, while on the computational platform 2, the speedups are approximately 6 ×∼9× on average and 9 ×∼14× in the best cases. Moreover, more than 99% input points can be discarded in most cases.

The influence of the Internet of Things (IoT) and related produced data is destined to revolutionize economic and social society, even more incisively than the advent of digital. The creation of the IoT world would have been much more complicated if a big data structure had not been followed since the latter allows to analyze vast amounts of data. The IoT is the most significant flow of information collected on the Internet and, therefore, the largest supplier for big data systems, artificial intelligence (AI), and data science. Advanced statistical analysis techniques, neural networks, and AI algorithms, but also the ability to create mathematical models that best represent a physical phenomenon or social behavior, these are the new strategic assets in the digital transformation process that is facing the world of industry and services. In fact, collecting data is not enough: they must be managed, integrated, and compared with a mathematical model that formalizes the intrinsic knowledge in the experience and competence of people.

Nowadays, machine learning (ML) techniques can provide new perspectives to identify hidden patterns and classes inside data. Applying ML to the Internet of Things (IoT) and its produced data represents a great challenge in every application domain, since analyzing IoT data increasingly requires the use of advanced mathematical algorithms, novel computational techniques, and services. In this article, we present and discuss the application of unsupervised learning techniques on IoT data collected in a cultural heritage framework. Behavioral data have been gathered in a noninvasive way in order to achieve an ML classification that can be exploited by cultural stakeholders in terms of the medium- to long-term strategy and also in terms of strictly operational decisions. The application of ML and other learning techniques will acquire a key role to complement the more traditional services with new intelligent ones able to satisfy the needs of companies, stakeholders, and consumers.

During the last years, the significant increase in the number of patients in need of rehabilitation has generated an unsustainable economic impact on healthcare systems, implying a reduction in therapeutic supervision and support for each patient. To address this problem, this paper proposes a telerehabilitation system based on serious games and in-cloud data analytics services, in accordance with Industry 4.0 design principles regarding modularity, service orientation, decentralization, virtualization, and real-time capability. The system, specialized for poststroke patients, comprises components for real-time acquisition of patient's motor data and a decision support service for their analysis. Raw data, reports, and recommendations are made available on the cloud to clinical operators to remotely assess rehabilitation outcomes and dynamically improve therapies. Furthermore, the results of a pilot study on the clinical impact deriving from the adoption of the proposed solution, and of a qualitative analysis about its acceptance, are presented and discussed.

In this work, we present a parallel implementation of Hestenes-Jacobi-One-sided method exploiting the CUDA environment of Graphics Processing Units (GPUs). Our approach is based on a scheme which performs multiple orthogonalization processes in parallel, across multiple rows and columns. Driven by an outer loop, executed on the CPU, the algorithm configures the CUDA grid with threads and blocks in order to allow the CUDA-kernels to use the shared memory and avoid multiple accesses to global memory. We use this GPU-parallel algorithm in order to accelerate the Singular Value Decomposition (SVD) process which has a variety of applications in scientific computing, signal processing, automatic control and many other areas. Preliminar experiments show a significant improvements in terms of performances with respect to the CPU version and our previuos GPU version.

Summary Social network analysis is an interdisciplinary topic attracting researchers from biology, economics, psychology, and machine learning, with an existing long history based on graph theory. It has since attracted interests from both the research and business communities for a strong potential and variety of applications. In addition, this interest has been fueled by the large success of online social networking sites and the subsequent abundance of social network data produced. An important aspect in this research field isinfluence maximizationin social networks. The goal is to find a set of individuals to be targeted with the aim to drive social contagion and generate a diffusion cascade. We provide here an overview of the models and approaches used to analyze social networks. In this context, we also discuss data preparation and privacy concerns. We further describe different kind of approaches based on centrality measures, which express a sociological interpretation of the data, and stochastic influence and information propagation techniques, which aim at modeling the underlying diffusion processes that govern social interactions.

Summary This paper focuses on designing and implementing parallel Moving Least Squares (MLS) interpolation algorithms by exploiting the Graphics Processing Unit (GPU) for the usage in Meshfree methods. The MLS method is an approach for scattered points' approximation / interpolation, which is commonly employed as the shape functions in various Meshfree methods. To improve the computational efficiency in building stiffness matrices in Meshfree methods, we are specifically interested in parallelizing the MLS interpolation on the GPU. The accelerated Meshfree methods can be employed to numerically analyze large deformations of soil and rock masses such as the landslides. In this paper, we first introduce our previously proposed method for finding the k nearest neighboring points located within the local region of the interest point in MLS. We then develop one sequential and three parallel implementations for each of three variations of the MLS interpolation, including the serial implementation, the parallel implementation on the multi‐core CPU, the parallel implementation on a single GPU, and the parallel implementation on multi‐GPUs. To evaluate the computational performance of our GPU implementations, five groups of benchmark tests are conducted in both two‐dimensions and three‐dimensions. We observe that our GPU implementations can achieve satisfied speedups over the sequential CPU implementation for varied sizes of testing data. To benefit the community, all source code and testing data related to the presented parallel MLS interpolation are publicly available.

Summary The production of microalgae represents a large and rapidly expanding market with several applications in the fields of food, pharmaceutics, cosmetics, and energy. Microalgae are photosynthetic aquatic microorganisms whose growth is mainly controlled by a few environmental parameters: temperature, light, pH, and nutrient availability. For this reason, monitoring and controlling such parameters is crucial for their production. At the same time, the development of mathematical models to simulate the behavior of biological systems has become a major predictive and control tool of production processes. In this paper, we present an Internet of Things (IoT) system that can couple sensor data collected directly by biotechnological cultivations with a predictive simulation model. The IoT system constitutes the core of a Decision Support System developed to help the end‐user in the management of industrial production processes.

Summary Extract information from data, coming from the real world, is a very fascinating challenge. In the Internet of Things society, sensors, devices, and tools are able to generate a lot of data that could be used to predict behaviours. In this paper, we propose a computational scheme in which the clustering methodology is used to classify information that are adopted as observations of an evolutionary method. A sampling techniques are used to model the unknown of a dynamical system as a random variable, and available information are interpreted as probability density function. The probability density function is approximated by an ensemble of weighted particles. Finally, by using this methodology, we present results on the forecast and track users' behaviours in 2 real‐world case studios.

We focus on the Overcomplete Local Principal Component Analysis (OLPCA) method, which is widely adopted as denoising filter. We propose a programming approach resorting to Graphic Processor Units (GPUs), in order to massively parallelize some heavy computational tasks of the method. In our approach, we design and implement a parallel version of the OLPCA, by using a suitable mapping of the tasks on a GPU architecture with the aim to investigate the performance and the denoising features of the algorithm. The experimental results show improvements in terms of GFlops and memory throughput.

We propose a biologically inspired mathematical model to simulate the personalized interactions of users with cultural heritage objects and spaces in the real case of an exhibition. The main idea is to measure the interests of a spectator with respect to an artwork by means of a model able to describe the users behavioural dynamics. In our approach, the user is assimilated to a computational neuron, and its interests are deduced by counting potential spike trains, generated by external currents. As an effort, we relies on an huge amount of log files that store visitors movements and interactions within a beautiful art exhibition named The Beauty or the Truth located in Naples, Italy. The technological tools deployed within the exhibition aim to create a novel metaphor stimulating user enjoyment and knowledge diffusion and the collected log files are useful data to analyse how such technology an influence and modify user behaviours. We also performed an experimental analysis exploiting clustering facilities to discover natural groups that reflect visiting styles. This is particularly suitable to provide the tuning of a heuristic classifier. The obtained results revealed to be particularly interesting also to understand other important aspects hidden in the data and unattended in our first analysis.

Recursive Filters (RFs) are a well known way to approximate the Gaussian convolution and are intensively used in several research fields.When applied to signals with support in a finite domain, RFs can generate distortions and artifacts, mostly localized at the boundaries of the computed solution.To deal with this issue, heuristic and theoretical end conditions have been proposed in literature.However, these end conditions strategies do not consider the case in which a Gaussian RF is applied more than once, as often happens in several realistic applications.In this paper, we suggest a way to use the end conditions for such a K-iterated Gaussian RF and propose an algorithm that implements the described approach.Tests and numerical experiments show the benefit of the proposed scheme.

We propose a biologically inspired mathematical model to simulate the personalized interactions of users with cultural heritage objects. The main idea is to measure the interests of a spectator w.r.t. an artwork by means of a model able to describe the behaviour dynamics. In this approach, the user is assimilated to a computational neuron, and its interests are deduced by counting potential spike trains, generated by external currents. The main novelty of our approach consists in resorting to clustering task to discover natural groups, which are used in the next step to verify the neuronal response and to tune the computational model. Preliminary experimental results, based on a phantom database and obtained from a real world scenario, are shown. To discuss the obtained results, we report a comparison between the cluster memberships and the number of spikes; our approach resulted to perfectly model cluster assignment and spike emission.

Computational kernel of the three-dimensional variational data assimilation (3D-Var) problem is a linear system, generally solved by means of an iterative method. The most costly part of each iterative step is a matrix-vector product with a very large covariance matrix having Gaussian correlation structure. This operation may be interpreted as a Gaussian convolution, that is a very expensive numerical kernel. Recursive Filters (RFs) are a well known way to approximate the Gaussian convolution and are intensively applied in the meteorology, in the oceanography and in forecast models. In this paper, we deal with an oceanographic 3D-Var data assimilation scheme, named OceanVar, where the linear system is solved by using the Conjugate Gradient (GC) method by replacing, at each step, the Gaussian convolution with RFs. Here we give theoretical issues on the discrete convolution approximation with a first order (1st-RF) and a third order (3rd-RF) recursive filters. Numerical experiments confirm given error bounds and show the benefits, in terms of accuracy and performance, of the 3-rd RF.

In scholar curriculum, the integration of contents from different learning areas has been always a challenging issue, but with very few practical experimentations. This paper reports an experimental project of teaching natural science, mathematics, and computer science (technology education) in the first level of the Italian secondary school, by means of a common integrate path based on practical experiments. We show effectiveness of the conceived interdisciplinary approach by means of a case study in a network of thirty classrooms of 11 years old scholars.