This study presents a Digital Twin (DT)-based system to solve the last-mile delivery problem. The city is divided in zones, each zone is associated to a hub where the trucks arrive and the last-mile deliveries are performed by a set of robots. The DT architecture is composed of an application layer that optimize the robot initial routes, a simulation layer connected with the physical layer to manage unexpected events, such as traffic congestion and road closures. A Mixed Integer Linear Programming (MILP) optimization model is designed to determine the optimal routes of the robots and a simulation model is implemented for the rerouting application. The system is validated through two case studies conducted in the city of Bari, Italy, using the MILP model to reduce travel distances and energy consumption of robots and the Simulation of Urban Mobility tool for reproducing the DT physical layer. The results demonstrate the effectiveness and adaptability of the proposed approach.

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.

In the age of intelligent transportation systems and smart cities, teleoperated driving aims to bridge the gap between human and fully autonomous driving. However, the reliability of teleoperated driving is heavily dependent on the quality of the cellular networks, a limitation that could be addressed by 6G networks, which aims to enhance ultralow latency and high reliability. This study proposes an integrated simulator for teleoperated driving by utilizing Deep Reinforcement Learning (DRL) in a framework of 6G and Network Digital Twin. The presented simulation framework combines different tools (i.e., SUMO, OMNeT++, and Simu5G) to model realistic traffic and network dynamics. In addition, the Random Forest algorithm is used for the coverage prediction system and maintaining stable connectivity, and a DRL model optimizes vehicle routing by balancing path length and signal coverage. A case study is simulated considering the city of Bari (Italy). The framework demonstrates robust communication between teleoperated vehicles and 6G Digital Twin infrastructure.

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 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.