In air-pollution studies, accurate estimation of pollutant levels at unmonitored locations is essential due to the spatial mismatch between fixed monitoring stations and experimentation. When dealing with multi pollutant datasets, Principal Component Analysis (PCA) is commonly applied to extract a low rank structure, which serves as a prior reducing dimensionality and improving the accuracy of subsequent spatial prediction models. However, both classical interpolation techniques and recent deep learning approaches fail to provide reliable estimates under conditions of data sparsity and low spatial sampling rates. To address this, we present a fast and accurate infinitely wide convolutional neural network approach to perform matrix imputation for air pollutant estimation in an urban environments. Speed comes from the convolutional neural tangent kernel computed from the infinite width network whose training dynamics can be fully described by a closed form formula. Experiments on two real world air pollution datasets demonstrate that our strategy accurately estimates from uneven data and significantly outperforms traditional interpolation methods.

The provisioning of advanced vehicular mobility services requires highly resilient communication infrastructures capable of bridging high-capacity optical backbones with diverse wireless access technologies. However, coordinating these multitenant environments while enforcing strict security and privacy standards poses a substantial challenge for network operators. This paper presents the ONOFRE-4 framework, a comprehensive approach to infrastructure planning and resource orchestration tailored for the Beyond 5G (B5G) ecosystem. We propose an architectural model that leverages dynamic resource allocation, flexible data plane routing, and distributed cloud-to-edge workload execution. To practically validate this theoretical design, its components are mapped onto an operational smart-campus experimental facility equipped with multi-tier radio, edge, and core capabilities. We also introduce a specialized vehicular simulation environment calibrated against our physical testbed. Finally, the framework's robustness is demonstrated through two distinct cybersecurity scenarios: Mitigating physical vulnerabilities in optical transport links and enforcing privacy-preserving identity verification for decentralized B5G applications.

Air pollution has become an increasingly urgent global concern, with significant implications for public health and environmental sustainability. This paper investigates the problem of predicting Carbon Monoxide (CO) concentrations through time series analysis, using data gathered by urban sensors in Cartagena as a case study. A comprehensive set of Machine Learning and statistical approaches is evaluated, leveraging the sktime Python library and Optuna for hyperparameter optimization. We assess classical time series models (ARIMA, ETS, etc.), regression-based approaches (k-nearest neighbors), and deep learning architectures (CNNRegressor), and also explore how different training window sizes (ranging from one week to several months) affect forecasting accuracy and runtime. Multiple metrics, including SMAPE, RMSE, MAE, and R2, are used to compare forecast accuracy, and execution times are also reported. Results show that certain relatively simple models, such as ETS or ARIMA, can achieve robust performance across various sensors, while a k-NN reduction approach offers an appealing trade-off between speed and accuracy. These findings emphasize the potential of adequately tuned algorithms for short-term CO forecasting in urban environments, supporting proactive air quality management.

LoRaWAN is increasingly considered for mobile IoT applications, yet its performance under dynamic conditions is still subject to thorough evaluation. This study investigates the impact of mobility on LoRaWAN communications in vehicular scenarios, focusing on key performance indicators such as packet loss, signal strength, and inter-packet gap. Experiments were conducted on an isolated road segment using a LoRaWAN field tester mounted on an e-scooter and a car, with motion speeds of 40, 60, and 80 km/h. Three spreading factors (SF7, SF9, SF12) were evaluated under identical conditions. Results show that a trade-off is necessary between good communication range and mobility support, since lower SFs provide reliable connectivity at higher speeds, while higher ones, despite better sensitivity, suffers from significant degradation due to Doppler effect, changing environmental conditions, and longer time on air. Findings emphasize the importance of selecting transmission parameters based on mobility profiles and environmental conditions. The work contributes to the understanding of LoRaWAN behavior under mobility and supports the development of more resilient and adaptive communication strategies for dynamic IoT deployments.

Upon the massive deployment of Cooperative Intelligent Transportation Systems (C-ITS), services developed for connected vehicles need an efficient, reliable and predictable network access to assure proper operation. European Telecommunications Standards Institute (ETSI) Release 2 services cannot be deployed using a single control channel, and require the management of multiple channels used simultaneously by applications. Because of this, ETSI defined a mechanism called Multi-Channel Operation (MCO). Two simple MCO load allocation mechanisms have been recommended, load balancing and sequential filling, but they have not been evaluated in detail until now. In this paper, these two mechanisms, as well as their congestion control variants, are evaluated. An open-source simulation framework has been implemented for such a work, which is open to future extensions. Then, through multiple evaluations following the ETSI simulation setup, we discuss the behavior of these mechanisms under scenarios with a highly congested medium, employing different traffic loads and vehicular densities. Our results show that MCO improvement is limited under high-load conditions, by saturation of channels before switching to a new one (sequential filling) and synchronization of channel assignment among vehicles (load balancing), and the introduction of a simple reactive congestion control does not improve their performance. The main limitations are examined, and recommendations are provided to guide the evolution of these mechanisms.

While ETSI Release 1 C-ITS applications operated adequately on a single 10 MHz channel in the 5.9 GHz band, evolving use cases under Release 2 generate substantially more data and require the concurrent use of multiple channels. To address this, ETSI introduced the Multi-Channel Operation (MCO) framework, defined in a series of Release 2 technical specifications, to coordinate multichannel access and enable flexible, standardized vehicle-to-vehicle communication. Within this framework, two advanced broadcast mechanisms—sequential filling and elastic—have been recommended, both relying on a predefined association policy. However, their performance has not yet been evaluated. In this paper, we assess these two mechanisms through multiple simulations in realistic scenarios, analyzing their behavior and identifying their main limitations. Based on the obtained results, we provide practical recommendations and conclude that the elastic mechanism generally achieves better performance, making it the preferable option whenever feasible.

People with type 1 diabetes (T1D) need to monitor their blood glucose level frequently and use insulin to regulate it. T1D typically develops in young individuals and requires lifelong insulin injections for glycemic control. High or low blood glucose levels can lead to serious health issues. To address the challenges posed by regular monitoring and manual insulin injections, automated glucose control methods have been developed. Various insulin regimes are used to manage blood sugar levels, such as traditional regimes that involve one or two injections per day or multiple daily injection therapy, which offers more flexibility in the diet and dosage but still requires patients to monitor their carbohydrate intake and insulin injections. A proportional integral derivative (PID) controller is an automated glucose control method that is commonly used in commercial and research settings due to its simplicity and robustness. However, despite its effectiveness, this method can be affected by external factors like food, exercise, and illness. This study proposes to set an individualized observation frequency (OF) per user for the PID controller for blood glucose control in T1D. Optimizing the OF improves the PID controller’s performance, maintaining or elevating median glucose levels. Tuning the OF offers a simple and effective enhancement for the widely used PID controller.

ETSI has considered a new set of services for the Release 2, which cannot be implemented using the single control channel. Therefore, it is necessary to regulate the operation of applications on multiple channels, what is called Multi-Channel Operation (MCO). In this case the interference from the first adjacent channel is not negligible and is recommended to manage it by congestion control mechanisms. We propose an elastic channel usage scheme for MCO, based on an optimal scheduler whose goal is to maximize the traffic on the channels while minimizing the adjacent channel interference generated by that load and controlling the congestion. We formulate the interference and congestion control as a constrained convex optimization problem and derive as solution a distributed algorithm called MINOS (MultI-chaNnel operation Optimal Scheduler). MINOS seamlessly work when vehicles have a different number of network interfaces available, and constraints and priorities can be set individually and dynamically, which provides flexibility to implement more sophisticated services on top of the framework. Our results show that MINOS effectively controls the congestion and reduces the interference, achieving an increased packet reception ratio across all channels and a higher allocated traffic, compared to other proposals.

This letter presents wideband measurements and simulations ranging from 2 to 28 GHz conducted in a parking lot, with and without cars. The measurements have been carried out considering a transmitter placed in an elevated position, with an omnidirectional antenna. The receivers have been distributed in the parking area also using omnidirectional antennas. Furthermore, the OPAL open-source ray launching tool has been used to simulate the different propagation mechanisms. The CI, FI, CIF and ABC propagation models have been considered, showing a consistent behavior of the propagation path loss exponent with the frequency. The results suggest that the presence of cars has a minimal impact on the path loss along all frequencies.

Accurate environmental monitoring is becoming the basis for assuring sustainable development in administrations at different levels, including cities and industry as key actors. However, current techniques rely on static stations that may not be representative of larger areas, for the case of outdoor scenarios, or even not considering indoor spaces where people can remain for long periods. This is the case of vehicles. The COVID-19 pandemic has remarked the importance of measuring air quality indoors, for instance. With the aim of solving this two-fold issue, this work proposes an in-cabin and outdoor air pollution monitoring system to assure healthy conditions when travelling, driving and operating vehicles, and to analyse the evolution of environmental parameters in cities. This effort is carried out exploiting distributed computing with micro-services, betting for an on-board hardware solution provided with sensors for measuring particulate matter, CO, CO2, NO2, O3, temperature and humidity. While basic data pre-processing is carried out in this acquisition unit, edge processing is performed on a single board computer aboard and intermediary communication nodes in the network path from the vehicle to the cloud. Vehicle connectivity is provided by 4G cellular and Low-Power Wide-Area (LPWAN) networks. Global environmental perception is acquired by cloud-based software powered by machine learning and time series analysis. The whole solution has been validated and tested in the city of Cartagena (Spain), with good performance in terms of data collection, communication links and service offered.

The on-demand provisioning of network and computing resources from cloud to edge in novel connected mobility use cases presents challenges related to the management of heterogeneous, distributed devices, dynamic quality of service (QoS) requirements, security and privacy concerns, multi-access coordination and control, integration of 5G and future 6G networks, among others. The ONOFRE-3 project presents a comprehensive architecture for enabling on-demand provisioning of network and computing resources from cloud to edge in con-nected mobility scenarios. ONOFRE-3 addresses the challenges of managing diverse devices across edge, fog, and cloud by leveraging artificial intelligence (AI) and machine learning (ML) techniques for dynamic QoS monitoring and orchestration, as well as dis-tributed and federated learning paradigms to empower secure distributed applications across the cloud computing continuum and among peer domains. The architecture features mechanisms for core and network infrastructure planning, online resource provisioning, management of multiple radio access technologies, and computation offloading. Security trust zone capabilities are enhanced through analytics-based proactive actions and network slicing isolation. ONOFRE-3 also includes two complementary testbeds and a simulation platform, where partial evaluations of selected architecture features have been carried out.

Electromagnetic field exposure (EMF) has grown to be a critical concern as a consequence of the ongoing installation of fifth-generation cellular networks (5G). The lack of measurements makes it difficult to accurately assess the EMF in a specific urban area, as Spectrum cartography (SC) relies on a set of measurements recorded by spatially distributed sensors for the generation of exposure maps. However, when the spatial sampling rate is limited, significant estimation errors occur. To overcome this issue, the exposure map estimation is addressed as a missing data imputation task. We compute a convolutional neural tangent kernel (CNTK) for an infinitely wide convolutional neural network whose training dynamics can be completely described by a closed-form formula. This CNTK is employed to impute the target matrix and estimate EMF exposure from few sensors sparsely located in an urban environment. Experimental results show that the kernel, even when only sparse sensor data are available, can produce accurate estimates. It is a promising solution for exposure map reconstruction that does not require large training sets. The proposed method is compared with other deep learning approaches and Gaussian Process regression.

The digitalization of cities and the development of smart, green, and integrated transport are societal challenges to transform cities into places with good quality of life now and in the future. The Internet of Things (IoT) comes with new advances to connect a multitude of sensing devices and even actuators, and they are presenting the cornerstone of Smart City deployments worldwide. So far, these advances have focused on static sensors in scenarios such as gardens, smart lighting, climate monitoring, or traffic management. However, moving sensors could rise the monitoring capabilities of smart cities to the next level, helping to better reflect the status of large areas without replicating fixed stations. This work proposes taking advantage of urban vehicles and, especially, personal mobility vehicles (PMVs), to implement such a perspective. Hence, a low-cost and energy-aware onboard unit (OBU) is designed to gather environmental data and support sustainable mobility applications. This on-board platform is provided with Low-Power Wide Area Network (LPWAN) communication technologies, enabling an Internet connection following an IoT scheme. The unit is equipped with sensors to measure air pollution in terms of NO2, CO, SO2, O3 and PMx, noise, and weather parameters. While moving across the city, PMVs mounting this device can collect data in a crowdsensing scheme. This data feed is complemented by a set of wireless traffic sensors, and they are subject to intelligent processing to monitor pollution and mobility parameters. For this, a back-end software module is powered with temporal series analysis to generate predictions based on tendencies detected in both pollution and mobility values. A front-end Web application has been implemented to show all past, current, and predicted data, offering functionalities to monitor urban mobility, minimize travel times, detect pollution areas, and recommend healthy routes across streets with low contamination levels.

To increase channel capacity, MIMO techniques are often used, and now, with the development of the 5G technique, massive transmitting arrays become to be widely implemented. For vehicular communication, the dedicated frequency band is around 5.9 GHz, and, to our knowledge, there are very few contributions to massive MIMO in tunnels and especially in road tunnels. In this paper, the case of a highway rectangular tunnel is treated, being its width much larger than its height. The Tx array is a square array of 64 elements and the correlation between array elements, deduced from simulation and measurements, is first presented. Due to the shape of the tunnel cross-section, it appears that the correlation between vertically aligned elements is much greater than that occurring between elements situated on a horizontal line, and, as an example, the correlation between elements 7.5 cm apart, can be equal to 0.9 and 0.7, respectively. Consequently, the way of partitioning the massive array is studied to find the best compromise between channel capacity and complexity of the transmission scheme, taking the number of radio frequency chains into account. Illustrations are given for transmission techniques based either on beamforming or singular values decomposition of the transfer matrix. Lastly, for a MIMO transmission, the precoding matrices must be periodically updated when the mobile moves along the tunnel, due to changes in the transfer matrix. The longitudinal correlation distance and the channel stationarity are thus calculated for correlation values equal to 0.7 or 0.9.

The adoption of Low-Power Wide-Area Networks (LP-WAN) for interconnecting remote wireless sensors has become a reality in smart scenarios, covering communications needs of large Internet of Things (IoT) deployments. The correct operation and expected performance of such network scenarios, which can range hundreds or thousands of nodes and tens of squared kilometres, should be assessed before carrying out the deployment to save installation and maintenance costs. Common network planning tools can help to roughly study potential coverage, but network simulation offers fine-grained information about network performance. Nevertheless, current simulation frameworks include limited propagation models based on statistical and empirical measurements that do not consider scenario particularities, such as terrain elevation, buildings or vegetation. This is critical in urban settings. In this line, this paper presents a simulation framework including a network simulator, a 3D engine and a ray-tracing tool, which models realistically the performance of Long-Range Wide-Area Network (LoRaWAN) communication technology. We have evaluated the performance of the solution taking as reference experimental campaigns in the city of Cartagena (Spain), comparing data obtained when simulating with the commonly employed propagation models such as Okumura-Hata or path loss. Results indicate that our framework, set-up with data from open geographical information systems, accurately fits experimental values, reporting improvements between 10% and 50% in the error committed when estimating signal strength in challenging urban streets with signal obstruction, as compared with the better performing classical model, Okumura-Hata.

BACKGROUND:The application of data-driven methods is expected to play an increasingly important role in healthcare. However, a lack of personnel with the necessary skills to develop these models and interpret its output is preventing a wider adoption of these methods. To address this gap, we introduce and describe ORIENTATE, a software for automated application of machine learning classification algorithms by clinical practitioners lacking specific technical skills. ORIENTATE allows the selection of features and the target variable, then automatically generates a number of classification models and cross-validates them, finding the best model and evaluating it. It also implements a custom feature selection algorithm for systematic searches of the best combination of predictors for a given target variable. Finally, it outputs a comprehensive report with graphs that facilitates the explanation of the classification model results, using global interpretation methods, and an interface for the prediction of new input samples. Feature relevance and interaction plots provided by ORIENTATE allow to use it for statistical inference, which can replace and/or complement classical statistical studies.RESULTS:Its application to a dataset with healthy and special health care needs (SHCN) children, treated under deep sedation, was discussed as case study. On the example dataset, despite its small size, the feature selection algorithm found a set of features able to predict the need for a second sedation with a f1 score of 0.83 and a ROC (AUC) of 0.92. Eight predictive factors for both populations were found and ordered by the relevance assigned to them by the model. A discussion of how to derive inferences from the relevance and interaction plots and a comparison with a classical study is also provided.CONCLUSIONS:ORIENTATE automatically finds suitable features and generates accurate classifiers which can be used in preventive tasks. In addition, researchers without specific skills on data methods can use it for the application of machine learning classification and as a complement to classical studies for inferential analysis of features. In the case study, a high prediction accuracy for a second sedation in SHCN children was achieved. The analysis of the relevance of the features showed that the number of teeth with pulpar treatments at the first sedation is a predictive factor for a second sedation.

Patients with Type 1 diabetes must closely monitor their blood glucose levels and inject insulin to control them. Automated glucose control methods that remove the need for human intervention have been proposed, and reinforcement learning has been used recently as an effective control method in simulation environments. However, its real-world application would require trial and error interaction with patients. As an alternative, offline reinforcement learning does not require interaction with humans and initial studies suggest promising results can be obtained with offline datasets, similar to classical machine learning algorithms. However, its application to glucose control has not yet been evaluated. In this study, we evaluated two offline reinforcement learning algorithms for blood glucose control and discussed their potential and shortcomings. We also evaluated the influence on training and performance of the method that generates the training datasets, as well as the influence of the type of trajectories used (single-method or mixed trajectories), the quality of the trajectories, and the size of the datasets. Our results show that one of the offline reinforcement learning algorithms evaluated, Trajectory Transformer, is able to perform at the same level as commonly used baselines such as PID and Proximal Policy Optimization.

With the ongoing fifth-generation cellular network (5G) deployment, electromagnetic field exposure has become a critical concern. However, measurements are scarce, and accurate electromagnetic field reconstruction in a geographic region remains challenging. This work proposes a conditional generative adversarial network to address this issue. The main objective is to reconstruct the electromagnetic field exposure map accurately according to the environment’s topology from a few sensors located in an outdoor urban environment. The model is trained to learn and estimate the propagation characteristics of the electromagnetic field according to the topology of a given environment. In addition, the conditional generative adversarial network-based electromagnetic field mapping is compared with simple kriging. Results show that the proposed method produces accurate estimates and is a promising solution for exposure map reconstruction.

Diabetes mellitus is a disease associated with abnormally high levels of blood glucose due to a lack of insulin. Combining an insulin pump and continuous glucose monitor with a control algorithm to deliver insulin is an alternative to patient self-management of insulin doses to control blood glucose levels in diabetes mellitus patients. In this work, we propose a closed-loop control for blood glucose levels based on deep reinforcement learning. We describe the initial evaluation of several alternatives conducted on a realistic simulator of the glucoregulatory system and propose a particular implementation strategy based on reducing the frequency of the observations and rewards passed to the agent, and using a simple reward function. We train agents with that strategy for three groups of patient classes, evaluate and compare it with alternative control baselines. Our results show that our method is able to outperform baselines as well as similar recent proposals, by achieving longer periods of safe glycemic state and low risk.