The recent need of supporting the diffusion of electric mobility around the world to progressively substitute petrol transport means, leads to the development of new hardware and software technologies to make even more convenient the use of electric vehicles (EVs). High purchasing costs and long recharging times are two major factors slowing this transition. In addition, from the end users perspective, using EV in long distance journeys is still not convenient despite the increasing diffusion of fast charging infrastructures. In this context, to facilitate traveling with EVs in long distance trips, this paper proposes a trip planner prototype based on Deep Reinforcement Learning (DRL). The trip planner prototype has the goal to suggest to the drivers the best charge stops to be performed during the trip according to the user needs and preferences. Charging stops are optimized, using the available Charging Points (CPs) along the route from origin to destination, and are shown to the user on a map taking into account important information like the EV State of Charge (SoC), the cruise velocity, and the presence of point of interest (e.g. restaurant, hotel, shops, etc.) close around. The trip plan can be done according to three objectives: minimizing the travel time, minimizing the charging costs, optimizing travel time and cost. The proposed DRL approach is compared against Genetic Algorithm (GA), heuristic, and optimization approaches considering a real-world EV trip.

Parkinson’s Disease (PD) is the second most common neurodegenerative disorder after Alzheimer’s disease, significantly impairing motor functions and quality of life. Early and accurate monitoring of PD progression is essential for improving patient outcomes. Among the innovative approaches, vocal signal analysis has gained traction as a non-invasive tool for assessing disease progression and treatment efficacy. PD patients often experience dysarthria, a neurological speech disorder affecting the pneumo-phono-articulatory system responsible for voice and language production. This study leverages machine learning algorithms to predict the motor and total scores of the Unified Parkinson’s Disease Rating Scale (UPDRS), widely used for tracking PD symptoms. Utilizing a dataset of 5,875 samples, various regression models, including Decision Tree, Random Forest, XGBoost, and Extra Tree, were trained and tested. Additionally, an ensemble Stacking Regressor was implemented to enhance prediction accuracy. The analysis of vocal recordings offers an innovative, non-invasive method for monitoring PD progression, reducing reliance on more subjective and invasive traditional approaches. The use of the ensemble model surpassed the performance of individual models, achieving an R2of 98.31% for predicting total UPDRS and 98.21% for motor UPDRS. Furthermore, the ensemble approach mitigates the risk of overfitting, ensuring greater robustness and reliability in predictions.These findings demonstrate the potential of machine learning in providing reliable and objective tools for PD monitoring, overcoming the subjectivity and limitations of traditional methods.

Being able to walk is one of the most important human abilities. With the increase in life expectancy, the disability rate is also rising, and research is extensively focusing on robotic devices to address this issue. These devices are now being applied in various fields for the assistance and rehabilitation of patients with different types of motor impairments. The aim of this article is to develop a lower limb exoskeleton model controlled using standard regulators in Simulink. After analyzing the construction of the model, the results of various simulations will be presented based on different desired response types and compared with the state of the art.

Vehicular Ad Hoc Networks (VANETs) play a vital role in enabling Intelligent Transportation Systems (ITS) by allowing communication between vehicles and between vehicles and infrastructure. However, these networks are vulnerable to various attacks that can threaten the integrity and safety of the network. One major attack is the Sybil attack, where malicious actors create multiple fake identities to confuse the network and disrupt normal communication and activities. In this work, we develop a real-time detection framework based on machine learning (ML) that processes data generated in real time from simulations using OMNeT++, Veins, and Simulation Urban Mobility frameworks. Our approach leverages four ML models: Random Forest, Gradient Boosting, XGBoost, and LightGBM, along with a stacking ensemble model to enhance detection accuracy. The proposed models are periodically trained on batches of data collected during the simulation, enabling continuous learning. Adaptive training strategies and a web-based dashboard enable continuous monitoring and effective detection of Sybil attacks. Notably, the simulation successfully replicates realistic Sybil attack scenarios and yields a new labeled dataset, which can support future research in this area. Our results demonstrate that the framework effectively detects Sybil attacks in dynamic vehicle networks, highlighting its potential to enhance security in ITS.

This paper addresses two important smart city logistics problems, i.e., Postal Delivery and Waste Collection, using Electric Vehicle Routing Problems. To this aim two Mixed Integer Linear Programming problems are formulated with the objective of carrying out the collection or delivery activities by minimizing the route length, respecting the working time, and considering the Electric Vehicles (EVs) battery charge constraints. While satisfying the customer needs under the mentioned traveling constraints, the proposed models take into account the implementation of smart charging strategies to minimize the demand peaks on the power grid both at district and charge station levels, that is suitable in large scale problems. To address the complexity of the models, a heuristic algorithm implementing clustering and routing strategies is proposed. Two case studies are implemented to demonstrate the effectiveness of the proposed models for Postal Delivery and Waste Collection activities in large systems.

This paper addresses the problem of detecting efficiently the diabetic disease. This disease occurs when the human body is not able to produce enough insulin causing high levels of blood glucose or sugar. It can cause different health issues such as eye issues, hearth, kidney and nerve disease and so on. By using a dataset of 2000 patient records from the Frankfurt Hospital in Germany, we implement a procedure to analyze the outliers and the correlations between dataset features in order to optimize the input data for training and testing phase. In addition, we apply and compare different Machine Learning algorithms, namely XGBoost, Random Forest and Decision Tree, to evaluate their prediction performances based on different standard evaluation metrics such as accuracy, precision, recall and F1-Score. Based on the experimental tests the Random Forest method outperforms the competitors achieving 98% of prediction accuracy.

I n the era of the transition towards electric vehicles (EVs), new services and tools are needed in order to facilitate the use of such vehicles. In this paper, a new tool is designed to optimally plan the long distance trips with an EV. The trip planner tool is realized by using MATLAB software. It implements an algorithm that, based on the EV battery model and on the charging stations information available on the route from departure to destination, determines the best itinerary in term of travel time and cost, minimizing the charge stops. The prototype of the trip planner tool is demonstrated by a real case study.

This study reviews the research works published in the last five years on Digital Twin (DT) technology for intelligent transportation systems, focusing on the use of DT in electromobility and autonomous vehicles. The review is carried out systematically, considering specific domains within intelligent transportation in which DT technology is applied in combination with Internet of Thing and 5G technologies. In addition, the paper discusses the current issues in electric vehicle services, such as tracking, monitoring, battery management systems, and connectivity, and how they can be addressed effectively through DT approaches.

This article presents two methods for solving the electric vehicles (EVs) relocation in EV-sharing system: 1) a centralized method where the decisions are taken by a unique decision-maker by using the complete knowledge of the system and 2) a randomized matheuristic algorithm where decisions are taken by the stations that coordinate for solving the relocation problem. For each methodology, two approaches are proposed for the EV relocation, i.e., the relocation performed by the EV-sharing operators and the relocation involving registered users also with an incentive scheme based on the crowdsourcing concept. In both the methods, two integer linear programming (ILP) problems are formulated to minimize the relocation cost in the two considered approaches. Moreover, in the randomized matheuristic method, a set of smart stations solve local ILP problems to produce a relocation plan. Finally, some instances and a case study are presented to demonstrate the effectiveness of the proposed approaches for the EVs relocation problem.Note to Practitioners—This article is motivated by the need to optimize the relocation process in the electric vehicle (EV)-sharing systems in order to minimize the relocation costs and guarantee the high quality of the service. To this aim, we first propose a centralized optimization that can be applied by the EV-sharing company for incentivizing users to optimally relocate vehicles in the stations. In this context, both the users and the company obtain benefits. Second, the randomized matheuristic optimization allows the stations to reach a decision about the relocation plan by using local information. The presented strategies can be applied in real applications, and in particular, the randomized matheuristic approach appears a promising strategy for large systems by using limited resources with low computational effort. Future research will focus on the EVs relocation problem in free-floating sharing systems.

This work aims to define a system for measuring the "lift" of the anchor (the final part of the shutter) present inside the injector based on the use of Machine Learning classification algorithms. The measurement method determined is a non-invasive method, which guarantees that the internal organs of the injection system are not damaged to carry out the measurement and that it can be performed after welding the injector to prevent the "lift" from changing later. This measurement method provides for the classification of the currents circulating inside the solenoid, each of which can be associated with a specific value of the "injector lift. This approach is part of predictive maintenance techniques, a type of maintenance that tries to predict incorrect behavior of the system avoiding that critical operating conditions are reached.Finally, an analysis of the possible techniques for measuring the injector "lift" is carried out through the use of Machine Learning algorithms

In the electro-mobility sector there is a rising necessity of providing new infrastructures, services, tools and solutions to support the diffusion of electric vehicles (EVs). In this framework, this paper aims to propose an innovative service that can improve the experience of electric vehicle users by providing customized information to reduce the range anxiety risk before starting the trip. In particular, an Information Technology (IT) service based on cooperative virtual sensors (VSs) is designed to predict the charge demand by an electric vehicle, driven by a specific user, to accomplish a predefined trip. To this goal, three virtual sensors are designed as software components each one implementing an algorithm to perform a specific task. It is shown how the cooperation of the three VSs is necessary to achieve the final service objective that is to provide customized information to help the user in preparing the EV for the trip. In addition, the effectiveness of the proposed service is demonstrated through a use case implemented by the developed IT application prototype.

Industry 4.0 revolution is destined to revolutionize the tasks that must be performed within companies and, in this context, new emerging technologies entail the needs for new professional skills. Therefore, it is necessary to think about how the workforce will be affected by the technological changes and how the skills of the workers will change in the future. Nowadays, one of the most critical issues is the misalignment between the needs of the companies and the actual competences of the workers. To face this problem, in this work an innovative approach based on the Analytic Hierarchy Process (AHP) is developed to derive the professional skills needed for Industry 4.0 technologies. In particular, the case of the Adriatic and Ionian area is analyzed in order to show the application of the proposed methodology. The results of the case study allow obtaining Technological Roadmaps to be used by universities and training organizations, companies and authorities in order to provide a more effective and cutting-edge training. Moreover, an overview of the most requested professional profiles in the Adriatic and Ionian area is also provided.

The Key Performance Indicators (KPIs) are usually adopted to evaluate the progress of the stated objectives in a specific framework. In a context where no suitable data are available, the correct estimation of KPIs values is an open issue. Hence, a new methodology is needed to evaluate the baseline values of KPIs. This paper presents an innovative approach to estimate the baseline values for a set of KPIs, that can be already existing or defined for the first time, in absence of historical data. The proposed approach makes use of data retrieved by different suitable sources, such as surveys, questionnaires, etc., comparing them with existing data in similar contexts to estimate KPIs baseline values. A case study is presented and the proposed methodology is applied to estimate specific KPIs in the electro-mobility sector.

The satisfaction of thermal comfort and indoor air quality conditions is one of the main objectives in the design of residential aged care homes such as retirement homes. Furthermore, in this context, the integration of building automation systems can both help the user to interact easier with the building components, and at the same time allows guaranteeing an adequate level of indoor comfort. The aim of this work is to design a Decision Support System able to improve indoor comfort by responding to occupants actions and preferences inside a room unit of a retirement home. In particular, optimized control logics for building automation systems are designed to minimize discomfort conditions within a smart room unit. The indoor environmental conditions and the user thermal-hygrometric comfort are estimated by means of the Fanger's comfort theory, by evaluating the Predicted Mean Vote and the Percentage of Person Dissatisfied indices. With the aim of determining the optimal activation ranges of the Heating, Ventilation, and Air-Conditioning systems that minimize the thermal discomfort conditions, several simulations are conducted by varying the activation temperature set points. The results show how the integration of automation systems may provide significant thermal discomfort reductions by optimizing the air conditioning activation timing.

Serious Games (SGs) represent a new approach to improve learning processes more effectively and economically than traditional methods. This paper aims to present a SG approach for the electro-mobility context, in order to encourage the use of electric light vehicles. The design of the SG is based on the typical elements of the classic “game” with a real gameplay with different purposes. In this work, the proposed SG aims to raise awareness on environmental issues caused by mobility and actively involve users, on improving livability in the city and on real savings using alternative means to traditional vehicles. The objective of the designed tool is to propose elements of fun and entertainment for tourists or users of electric vehicles in the cities, while giving useful information about the benefits of using such vehicles, discovering touristic and interesting places in the city to discover. In this way, the user is stimulated to explore the artistic and historical aspects of the city through an effective learning process: he/she is encouraged to search the origins and the peculiarities of the monuments. A case study in the city of Bari, Italy, shows the application of the proposed SG tool.

In recent years, the rationalization of building energy usage is one of the most virtuous ways to reduce the consumption of fossil fuels and the containment of the environmental impact, associated with the production, distribution and consumption of electrical and thermal energy. In this context, this paper proposes a First Order Hybrid Petri Net (FOHPN) model to simulate and control the energy consumption of the main building electric appliances by a modular approach. The aim of the paper is two-fold: i) helping to recognize how the building electric appliances contribute to peak demand; ii) managing efficiently the building energy consumption. Finally, a case study shows how the FOHPN system works and highlights the advantages of the proposed approach.

In the European electromobility framework, the interoperability of platforms and the standardization of services are becoming the main goals of researchers and practitioners. In this context, the objective of this paper is to propose innovative services for electromobility actors and stakeholders based on the definition of Virtual Sensors (VSs). A VS provides new information to the network by aggregating, elaborating and processing of existing and available electromobility data. To this purpose, each VS functioning, outputs and inputs can be described by UML diagrams. In order to show the proposed methodology, a useful VS for electromobility enhancement is presented, i.e., a personal mobility probability VS.

This paper proposes innovative services in the electro-mobility framework with the goal of enhancing the electric vehicle charging experience. In this context, the objective is to provide a smart charging service that helps drivers to make the best choice for charging their electric vehicles, according to the vehicle real-time position, battery type and autonomy. Moreover, the drivers are allowed to book the preferred charge option according to availability and cost of the charge points. To this purpose, two virtual sensors are designed and defined that allow to perform the smart charging searching service. In particular, an algorithm and a UML diagram are adopted to describe the virtual sensors operations and cooperation. In addition, the proposed virtual sensors functioning and interactions are described as Discrete Event Systems modeled in a Petri Net framework.

This paper aims to present the software functional requirements in the context of electromobility with specific focus on Electric Light Vehicles (EL-Vs). By adopting a consolidated methodology, the Information and Communication Technology (ICT) requirements are defined on the basis of the definition of use cases and their representation with the Unified Modeling Language (UML), through Use Case Diagrams and Activity Diagrams. More specifically, six use cases are described with the main flow of actions. UML use case diagrams are also reported to show the functionalities requested from the ICT service providers, whereas UML activity diagrams show the detailed sequence of actions for each use case. Finally, the case study section reports the results of the application of the proposed methodology and lists the user software requirements for EL-Vs management.

This correspondence paper deals with the sensor placement optimization problem in the context of indoor multiple inhabitants location tracking to solve ambient assisted living problems. Binary sensors, like passive infrared (PIR) sensors, are used to guaranty specific coverage requirements and allow privacy respecting. Moreover, within real home environments, different kinds of obstacles (like walls, high furniture, etc.) can affect the detection capacity of PIR sensors. This paper proposes an integrated framework devoted to optimize the placement of sensors and PIR sensors in smart homes by taking into account physical topologies and coverage precision constraints. An integer linear programming problem is formalized and a case study illustrates the applicability of the proposed approach and the scalability of the optimization method.

This paper deals with the smart placement of motion sensors in smart homes for Ambient Assisted Living, by considering the sensor technology and cost and respecting specific coverage requirements. The core of the proposed methodology is a decision module that can optimize the sensors placement according to different objectives. More precisely, the main objective is the minimization of costs of the deployed sensors. Moreover, the second objective can be the maximization of the overlapping in order to find a robust solution or the minimization of the overlapping of the detection areas in order to improve the inhabitant localization. A case study demonstrates the effectiveness of the proposed strategy on sensors placement in a domestic environment.

The aim of the paper is to provide an optimal placement of sensors for inhabitant location tracking in smart homes, by using only motion detectors. In particular, motion detectors are binary sensors largely used in ambient assisted living applications because they are low cost, non-intrusive and privacy sensors. An approach to optimize the placement of motion detectors in a real home environment by adopting a two-dimensional grid is presented. In this context, the real coverage area of a sensor is computed by considering the obstacles and respecting the specified coverage performance requirements. The optimization problem is formalized and solved as an Integer Linear Programming problem and a case study is presented to show the efficacy of the proposed approach.

This paper presents a building automation strategy for natural ventilation control and reducing building energy consumption. An on-off control is proposed in order to manage the windows opening and realize a natural ventilation flow guaranteeing indoor thermal comfort. The control logic is based on activation thresholds that are optimized to reduce the discomfort for overheating and undercooling. In particular, the temperature comfort range dynamically varies according to the adaptive thermal comfort theory. To this aim, a co-simulation architecture is proposed: the thermal building behavior and ventilation dynamics are simulated by TRNFLOW within the TRNSYS software and a Particle Swarm Optimization algorithm is employed to optimize the thresholds of windows opening. A case study focusing on a residential building situated in the Mediterranean climatic context is presented: the thermal comfort analysis shows that the optimized control logic significantly reduces the overheating discomfort.

This paper presents a district energy management strategy devoted to monitor and control the district power consumption in a twofold human-centered perspective: the respect of user's comfort preferences and the minimization of the power consumption and costs. The presented district energy management system forwards the power profile determined the day ahead to each building energy management system that, in turn, minimizes its real-time power consumption and costs (based on rewards and penalties), respecting the comfort preferences. Successively, the power is redistributed among the district buildings in order to minimize the penalties by applying two approaches: a centralized approach for public buildings and a distributed methodology for private buildings. Such optimization problems are formalized by defining some linear programming problems: two case studies are solved to show the applicability of the proposed management strategies.