The convergence of wireless communications and transportation technologies has propelled the evolution of Intelligent Transportation Systems (ITS), enhancing connectivity, safety, and efficiency in vehicular networks. As electric vehicle (EV) adoption grows within connected ecosystems, the need for intuitive charging management solutions has surged. This paper presents a task-oriented, bilingual chatbot to optimize EV charging control via an intelligent human-machine interface (HMI). Using Natural Language Processing (NLP) and Artificial Intelligence (AI), the system enables seamless interaction with charging infrastructure through wireless channels, supporting English and Spanish to address linguistic diversity. Integrated with ITS frameworks, it facilitates real-time monitoring and control, aligning with cooperative sensing and user experience goals. Two approaches are assessed: Voiceflow, for fast prototyping, and BERT (Bidirectional Encoder Representations from Transformers)-based models, implemented as a multilingual system and separate monolingual variants. Results show monolingual BERT models outperform the multilingual model in terms of intent classification accuracy, reinforcing reliability in dynamic settings. By linking wireless connectivity with AI-driven HMI, our proposal enhances EV charging scalability and accessibility within ITS, advancing sustainable transportation and efficient vehicular networking.

Vehicular networks have transformed Intelligent Transportation Systems (ITS) by enabling Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications, enhancing road safety and traffic efficiency. However, these technologies face significant challenges in rural and mountainous environments, where communication infrastructure is limited. In this context, LoRaWAN emerges as a viable solution to extend coverage in vehicular networks, providing connectivity in remote areas where traditional solutions, such as LTE-V2X and 5G-V2X, are insufficient due to their reliance on dense infrastructure.This paper evaluates the use of LoRaWAN in V2I communications in remote areas using FresSim, a simulation tool based on Fresnel Zone analysis and geospatial data. In particular, LoRaWAN coverage has been evaluated considering the strategic placement of gateways, achieving connectivity extension up to 140 km with only five gateways. The results confirm that LoRaWAN enables the transmission of emergency alerts and vehicular data in hard-to-reach environments with minimal infrastructure, optimizing resource utilization and providing an efficient alternative to enhance V2I connectivity on rural roads and highways.

This article introduces the LoRaWAN Fresnel Zone Simulator (FresSim), a tool designed to evaluate the feasibility of LoRaWAN deployments by analyzing the Fresnel Zone and terrain topography, allowing for the early prediction of coverage between nodes and the gateway. Furthermore, unlike other tools, FresSim can integrate real data from platforms such as The Things Network (TTN) and ChirpStack, providing an accurate assessment of potential coverage and signal quality in real deployments. Comparisons between FresSim and LoRaSim, a widely used signal propagation simulator, reveal that FresSim offers superior accuracy in scenarios with complex topography, achieving a 100% success rate in predicting coverage, doubling the 50% accuracy rate of LoRaSim. These results demonstrate that FresSim is a valuable tool for optimizing LoRaWAN networks in open environments, significantly contributing to the improvement of LoRaWAN deployment planning.

Device registration in LoRaWAN systems can be a tedious process, particularly when managing a large number of devices. To automate this task, we previously developed the AutoLoraConfig protocol, although it includes vulnerabilities that attackers can exploit. To solve this, in this work we introduce the SecureAutoLoRa, a protocol designed to enhance security in the automated device registration process for LoRaWAN networks. SecureAutoLoRa blocks abuse of the guest DevEUI used in automated joins by obfuscating registration messages and enforcing a configurable positional security code that dictates where the real DevEUI appears across packets, markedly hindering unauthorized registrations.Results show that SecureAutoLoRa sharply reduces attackers’ success. Compared with AES-128 and SPECK, it complements standard encryption to provide a practical, layered defense suitable for large-scale LoRaWAN onboarding.

The rapid adoption of electric vehicles (EVs) demands advanced residential charging solutions, where user behavior varies widely due to factors like electricity tariffs and weather conditions. Such conditions make charging predictions particularly complex. This study addresses this challenge by predicting the time an EV remains connected to a residential charger using a dataset of 106,260 sessions. To this end, we propose the Connection Time Neural Model (CTNM), a deep neural network designed to model the complex dynamics of domestic charging, and we introduce the Weighted Error Metric (WEM), a novel metric that penalizes overestimations and under-estimations differently to reflect their real-world impacts on both grid management and user experience. Utilizing bidirectional charger data, we focus solely on connection time, bypassing energy prediction. CTNM is benchmarked against state-of-the-art methods (i.e., Random Forest, Dense Neural Network, XGBoost, and Support Vector Regression) using Mean Absolute Error, Root Mean Squared Error, and WEM as performance metrics. Results demonstrate CTNM’s superiority, reducing average error by 18%, and weighted error by 31% compared to Random Forest, thanks to its deep architecture and integration of contextual features, like variable tariffs and weather.

LoRaWAN (Long Range Wide Area Network) is a communications protocol stack based on LoRa which provides long-range connectivity and low power consumption, making it a strong candidate for Internet of Things (IoT) device connectivity. However, unlike other technologies like WiFi or Bluetooth, LoRaWAN lacks an automatic mechanism to facilitate the connection of new devices to a network, which is undoubtedly a limitation for widespread device deployment. This paper presents AutoLoRaConfig, a rule-based system designed to automate the configuration and registration of devices in LoRaWAN networks, reducing the manual intervention required, and therefore minimizing potential human errors. The proposal aims to simplify the work required by users regarding the device configuration and registration process, enabling agile and efficient large-scale deployments. Results indicate that, for a set of 100 devices, automated deployment is 136.6 times faster than the manual procedure.

The use of proprietary systems in Industry 4.0 often involves high economic costs. To address this issue, using low-cost devices with similar capabilities is becoming an increasingly popular alternative. However, these devices are prone to suffer the negative effects of electromagnetic interference (EMI) due to their placement in electrical panels alongside other electromechanical devices. To solve this problem, this article presents the autonomous Data Base Filter (aDBF). aDBF is an enhanced electromagnetic interference filtering mechanism capable of eliminating erroneous signals generated by EMI. aDBF has been specifically designed to autonomously (i.e., without the need for operator supervision or intervention) determine both the number of different product types elaborated in a production line, and the time instants when their manufacturing process starts and ends. In particular, aDBF goes through three stages: (i) pre-filtering, (ii) product change detection, and (iii) identification of valid signals. The results obtained after validating our proposal in three different manufacturing shifts demonstrate that the aDBF filtering mechanism works very accurately, as the maximum error introduced is of 0.93%.

Long Range Wide Area Network (LoRaWAN) is a network protocol specifically designed to leverage the advantages of Long Range technology. LoRaWAN is employed to connect Internet of Things devices through a long-range network infrastructure, providing a secure and efficient communication layer that facilitates connectivity for a vast number of devices in a LoRa network. The aim of this study is to assess the real-life performance of LoRaWAN in different topographical environments. In particular, two scenarios (one flat and one mountainous) are compared, with an analysis of the success rate in data packet reception. The purpose is to examine how topography influences communication between LoRa devices and gateways, as well as to explore alternatives for overcoming challenges in rugged terrain environments. Therefore, in the mountainous environment, the study also investigates whether the use of drones could enhance communications. The findings of this study reveal that the topography of the terrain significantly impacts LoRa communications, resulting in a 58.63% decrease in the number of successfully received packets compared to a flat environment. Moreover, one-third of the nodes failed to establish communication with the ground gateway, and a partial improvement in connectivity was achieved by using gateways deployed on drones.

The development and deployment of the so-called Industrial Internet of Things (IIoT) have significantly increased the control and monitoring capabilities of companies, and thus their potential productivity. In this paper, we propose the use of Raspberry Pi devices in industrial environments to mea-sure productivity parameters. Our proposal can economically and efficiently gather data related with the availability and productivity of industrial machinery. However, since low-cost devices are prone to suffer the negative effects of electromagnetic interferences, we additionally propose an alternative to prevent signal alterations caused by them. More specifically, we propose a filtering mechanism called Smart Coded Filter (SCF), which eliminates wrong signals caused by electromagnetic interferences, and, therefore, highly improves the accuracy when estimating the availability metric. Results obtained demonstrate that our low-cost device provided with the SCF completely ignores 100% of wrong availability data, while reducing up to 70% the number of records stored into the database.

In this paper we present V-tracer, a vehicular trace generator aimed at generating realistic data about mobility of vehicles, as well as their daily operation and wear. The objectives of our approach are two: first, gathering real traces obtained by in-vehicle on-board units (OBUs), and second, as the first target is hard to achieve, generating synthetic data. The final goal will be getting all the information that would be very useful to infer and predict vehicle failures. The traces provided by our generator may be used to perform the predictive maintenance of vehicles in the near future.

Electric Vehicles (EVs) sales are increasing in the recent years due to several factors such as cost reduction, fuel cost increase, pollution reductions, government incentives, among others. At the same time, Intelligent Transportation Systems (ITS) are continuously improving, and researchers use different simulators in order to test their proposals before implementing them in real devices. However, traditional communications-aimed simulations do not include fuel consumption issues that are a key factor in transportation systems. This paper presents the addition of Electric Vehicles consumption to the ns-3 simulator, which currently is one of the most used network simulators. Our proposal follows all the models, coding style, as well as engineering guidelines of ns-3, coupled with the characteristics of each vehicle, to accurately estimate the energy consumption. We also analyze the performance of our proposal while simulating a part of the E313 highway, located in Antwerp, Belgium. In particular, we compare the ns-3 results obtained in terms of energy consumption to those obtained in SUMO. In addition, we study the impact of our proposal on the overall simulation time.

In this paper, we present the Dynamic Small cell Management (DSM) scheme to improve vehicular communications, focusing on the dynamic allocation of small cells when the macrocells cannot cope with the traffic generated by the connected cars. We have considered real base station deployments in the city of Dublin, Ireland, combined with realistic models of vehicle mobility, and small cell deployments. Simulation results demonstrate that our DSM scheme improves communication capabilities (the number of messages correctly received by the infrastructure increases up to a 43.75%), while it also reduces BS overloading (the number of messages managed by the base stations is reduced up to an 8.72%). Therefore, the use of this smart and dynamic solution not only benefits vehicles' communications but also mobile operators.

In Vehicular Networks, some applications require a fast and reliable warning data transmission to the Emergency Services and Traffic Authorities. Nevertheless, communication is not always possible in vehicular environments due to the lack of connectivity. To overcome these issues (i.e., signal propagation problem and delayed warning notification time), an effective, smart, cost-effective, and all-purpose RSU deployment policy should be put into place. In this paper, we propose GARSUD, a system which uses a genetic algorithm that is capable to automatically provide a Roadside Unit deployment suitable for any given road map layout. Simulation results show that our proposal is able to reduce the warning notification time --the time required to inform emergency authorities in traffic danger situations-- and to improve vehicular communication capabilities in different flows of traffic at different times during the day.

In this paper, we study the influence of the roadmap topology and the number of vehicles when accounting for the vehicular communications capabilities, especially in urban scenarios. Additionally, we propose the use of two metrics: the SJ Ratio (SJR) and the Total Distance (TD), as the metrics that better correlate with communications performance. Hence, researchers will better characterize the different urban scenarios. In particular, simulation results demonstrate that roadmaps with both similar SJR and TD present similar communications performance in terms of vehicles informed.

Research works regarding vehicular communications usually obviate assessing the proposals in scenarios including adverse vehicle densities, despite such scenarios are quite common in real urban environments. In this paper, we study the effect of these hostile conditions on the performance of different schemes providing warning message dissemination. We then propose the Junction Store and Forward (JSF) and the Nearest Junction Located (NJL) schemes, which were specially designed to be used in very low and very high density scenarios, respectively. Simulation results using real maps demonstrate how our proposed schemes are able to outperform existing warning message dissemination schemes in urban environments under adverse vehicle density conditions.

In Vehicular ad hoc Networks (VANETs), efficient dissemination of messages is a key factor to speed up the development of useful services and applications. In this paper, we propose a novel algorithm that automatically chooses the best dissemination scheme trying to fit the warning message delivery policy to the current characteristics of each specific vehicular scenario. Our mechanism uses as input parameters the vehicular density and the topological characteristics of the environment where the vehicles are located, in order to decide which dissemination scheme to use. Simulation results demonstrate the feasibility of our approach, which is able to support more efficient warning message dissemination in vehicular environments.