Intelligent autonomous driving in off-road environments is an emerging field with great potential to impact areas such as agriculture, forestry, and rescue operations. Perception in these scenarios presents unique challenges due to the diversity of elements and weather conditions, along with the inherent ambiguity in class definitions. Consequently, off-road visual semantic segmentation datasets remain underdeveloped, roughly ten times smaller than their urban counterparts, hindering dependable performance assessment and potentially compromising the safety of autonomous systems. To address these challenges, we present a comprehensive cross-dataset evaluation of visual semantic segmentation models for autonomous off-road navigation. We propose a unified ontology that harmonizes class definitions across relevant datasets, enabling their combination for both training and testing. This approach ensures fair model comparisons and reliable assessment of generalization to unseen domains. We further benchmark models on the original datasets, analyze the impact of different ontology harmonization criteria and conversion strategies, and evaluate the trade-off between segmentation performance and computational cost. Results show that Transformer-based architectures achieve the most consistent segmentation performance across datasets. While often computationally demanding, some variants maintain real-time inference ( ≈ 12 ms) with top-tier accuracy. The unified ontology simplifies the segmentation task, yielding more reliable models and about 40% faster training convergence. Cross-dataset training further enhances generalization, improving mean IoU by up to +20% on RUGD and +13% on WildScenes compared to RELLIS-3D-only training. Overall, this study provides valuable insights for developing robust perception modules for off-road autonomous vehicles.

Heart failure exacerbations (HFE) represent a critical challenge in healthcare due to their significant role in global mortality. The rise of home and wearable devices capable of monitoring cardiac conditions provides valuable opportunities for data-driven analysis and HFE detection. However, these devices frequently generate low-quality measurements with irregular sampling frequencies and high rates of missing data. Our paper presents a methodology that processes these measurements as a three-dimensional tensor, applying a low-rank tensor completion scheme to manage missing data effectively, thus facilitating anomaly detection without necessitating data imputation. We validate our method on a dataset from 4 patients with chronic HF in the compensation phase, collected at the Hospital Fondazione Policlinico Universitario Campus Bio-Medico in Rome, Italy. Our results demonstrate the tensor-based method’s superiority over traditional techniques, highlighting its potential for detecting anomalies within complex multivariate time series data. This research emphasizes the critical role of advanced data analysis in enhancing HFE identification, which could lead to improved patient care and reduced hospitalization rates.

Bacterial resistance to antibiotics has been rapidly increasing, resulting in low antibiotic effectiveness even treating common infections. The presence of resistant pathogens in environments such as a hospital Intensive Care Unit (ICU) exacerbates the critical admission-acquired infections. This work focuses on the prediction of antibiotic resistance in Pseudomonas aeruginosa nosocomial infections at the ICU, using Long Short-Term Memory (LSTM) artificial neural networks as the predictive method. The analyzed data were extracted from the Electronic Health Records (EHR) of patients admitted to the University Hospital of Fuenlabrada from 2004 to 2019 and were modeled as Multivariate Time Series. A data-driven dimensionality reduction method is built by adapting three feature importance techniques from the literature to the considered data and proposing an algorithm for selecting the most appropriate number of features. This is done using LSTM sequential capabilities so that the temporal aspect of features is taken into account. Furthermore, an ensemble of LSTMs is used to reduce the variance in performance. Our results indicate that the patient's admission information, the antibiotics administered during the ICU stay, and the previous antimicrobial resistance are the most important risk factors. Compared to other conventional dimensionality reduction schemes, our approach is able to improve performance while reducing the number of features for most of the experiments. In essence, the proposed framework achieve, in a computationally cost-efficient manner, promising results for supporting decisions in this clinical task, characterized by high dimensionality, data scarcity, and concept drift.

This research was funded by the Spanish Research Agency, grant numbers PID2021-122392OB-I00, PID2019-106623RB-C41/AEI/10.13039/501100011033 and PID2019-107768RA-I00; and by Universidad Rey Juan Carlos (URJC) and Community of Madrid, Spain , grant number 2020-66.

The most recent Clinical Decision Support Systems use the potential of Machine Learning techniques to target clinical problems, avoiding the use of explicit rules. In this paper, a model to monitor and predict the risk of unfavourable evolution (UE) during hospitalization of COVID-19 patients is proposed. It combines Self Organizing Maps and local Naïve Bayes (NB) classifiers because of interpretation purposes. We used the results of six blood tests (leukocytes, D-dimer, among others) provided by a Spanish hospital group. The probabilistic approach allows us to get the daily risk of UE for each patient in an interpretable way. Several variants of the NB classifiers family have been explored, mainly weighting and likelihood estimation (parametric and nonparametric). Despite the over-simplified assumptions of the NB classifiers, they provided good predictive results in terms of sensitivity and specificity. The model with nonparametric likelihood estimation provided the best risk prediction over time even when designed with a limited number of samples. Specifically, the median value and interquartil range for the risk prediction were quite reliable even 10 days before the event day for patients hospitalized longer than 7 days. The risk median values also agree with the gold-standard for patients with a hospital stay shorter than 7 days, though the interquartil range can be too wide (probably because of the variability in the inpatient days - sometimes, just 2 days). Though a deepest analysis considering more patients and features would be convenient, our results show the potential of the proposed approach, both from a technical and clinical viewpoint.

Electronic health records provide rich, heterogeneous data about the evolution of the patients’ health status. However, such data need to be processed carefully, with the aim of extracting meaningful information for clinical decision support. In this paper, we leverage interpretable (deep) learning and signal processing tools to deal with multivariate time-series data collected from the Intensive Care Unit (ICU) of the University Hospital of Fuenlabrada (Madrid, Spain). The presence of antimicrobial multidrug-resistant (AMR) bacteria is one of the greatest threats to the health system in general and to the ICUs in particular due to the critical health status of the patients therein. Thus, early identification of bacteria at the ICU and early prediction of their antibiotic resistance are key for the patients’ prognosis. While intelligent data-based processing and learning schemes can contribute to this early prediction, their acceptance and deployment in the ICUs require the automatic schemes to be not only accurate but also understandable by clinicians. Accordingly, we have designed trustworthy intelligent models for the early prediction of AMR based on the combination of meaningful feature selection with interpretable recurrent neural networks. These models were created using irregularly sampled clinical measurements, both considering the health status of the patient and the global ICU environment. We explored several strategies to cope with strongly imbalance data, since only a few ICU patients are infected by AMR bacteria. It is worth noting that our approach exhibits a good balance between performance and interpretability, especially when considering the difficulty of the classification task at hand. A multitude of factors are involved in the emergence of AMR (several of them not fully understood), and the records only contain a subset of them. In addition, the limited number of patients, the imbalance between classes, and the irregularity of the data render the problem harder to solve. Our models are also enriched with SHAP post-hoc interpretability and validated by clinicians who considered model understandability and trustworthiness of paramount concern for pragmatic purposes. Moreover, we use linguistic fuzzy systems to provide clinicians with explanations in natural language. Such explanations are automatically generated from a pool of interpretable rules that describe the interaction among the most relevant features identified by SHAP. Notice that clinicians were especially satisfied with new insights provided by our models. Such insights helped them to trust the automatic schemes and use them to make (better) decisions to mitigate AMR spreading in the ICU. All in all, this work paves the way towards more comprehensible time-series analysis in the context of early AMR prediction in ICUs and reduces the time of detection of infectious diseases, opening the door to better hospital care.

This paper presents a rigorous but tractable study of sparsity. We postulate a definition of sparsity that is as broad as possible, so that it generates all the various measures that are useful in practice, but narrow enough that the fundamental properties of generalized sparsity still hold. As we work through the various ways of demonstrating the advantageous properties of sparsity, we illustrate its meaning from geometrical and operational perspectives. Thereafter, we construct specific measures of sparsity which are successfully qualified in complexity analysis and sparse optimization scenarios. Overall, our main objective is to construct measures of sparsity that will facilitate and enhance the design of the next innovative sensing technologies.

Since COVID-19 appeared in December 2019, scientists are researching new ways to improve the management of the disease. Considering machine learning approaches have proven to be very useful tools to discover hidden patterns in data, we propose in this paper to apply a Self Organizing Map (SOM) to characterize the health-status evolution of COVID-19 patients. The SOM is a neural network whose neurons can be represented as cells in a bi-dimensional grid preserving the mapping from the original space to the map units. We consider real-world data of hospitalized COVID-19 patients in a Spanish hospital during the first wave of the pandemic. Patients are represented by six blood tests (leukocytes and D-dimer, among others) in a daily basis. Besides, each patient is associated with one of two different health-status: favorable evolution (discharged home) and unfavorable evolution (exitus or admission to the intensive care unit). We show the potential of our approach by detailing the mapping of the health trajectory associated with different particular cases and drawing their trajectory on the bi-dimensional map of the SOM.

Infections caused by multidrug resistant (MR) bacteria severely jeopardize the public’s health given the inefficiency of current antibiotics to treat them. This results in a major global concern that affects any hospital service and the Intensive Care Unit (ICU) in particular. This paper aims to anticipate the antibiogram outcomes associated with MR bacteria in ICU patients by applying machine learning (ML) techniques. For this purpose, multiple clinical variables obtained from the Electronic Health Record have been employed, as the own patient’s antibiotics consumption and the drugs taken by the remaining ICU patients. A collection of 3476 patients admitted to the ICU at the University Hospital of Fuenlabrada from 2004 to 2020 were considered, 628 with MR bateria. A feature engineering (FE) and feature selection (FS) process has been conducted to extract valuable statistics from the original temporal data. The highest Accuracy and Specificity results achieved were 77% and 82%, respectively, both implementing Random Forest as classifier and without considering any FS method. The highest Sensitivity (69%) and ROC-AUC (76%) were attained with the features selected using the Chi-Square test and with both Logistic Regression and XGBoost classifiers. This work provides a promising approach to support therapy decisions by the early identification of MR infections among ICU patients.

Electronic health records (EHRs) are a valuable data source that, in conjunction with deep learning (DL) methods, have provided important outcomes in different domains, contributing to supporting decision-making. Owing to the remarkable advancements achieved by DL-based models, autoencoders (AE) are becoming extensively used in health care. Nevertheless, AE-based models are based on nonlinear transformations, resulting in black-box models leading to a lack of interpretability, which is vital in the clinical setting. To obtain insights from AE latent representations, we propose a methodology by combining probabilistic models based on Gaussian mixture models and hierarchical clustering supported by Kullback-Leibler divergence. To validate the methodology from a clinical viewpoint, we used real-world data extracted from EHRs of the University Hospital of Fuenlabrada (Spain). Records were associated with healthy and chronic hypertensive and diabetic patients. Experimental outcomes showed that our approach can find groups of patients with similar health conditions by identifying patterns associated with diagnosis and drug codes. This work opens up promising opportunities for interpreting representations obtained by the AE-based model, bringing some light to the decision-making process made by clinical experts in daily practice.

The COVID-19 pandemic presents unprecedented challenges to the healthcare systems around the world. In 2020, Spain was among the countries with the highest Intensive Care Unit (ICU) hospitalization and mortality rates. This work analyzes data of COVID-19 patients admitted to a Spanish ICU during the first wave of the pandemic. The patients in our study either died (deceased patients) or were discharged from the ICU (non-deceased patients) and underwent the following landmarks: beginning of symptoms; arrival at the emergency department; beginning of the hospital stay; and ICU admission. Our goal is to create a graph-based data-science methodology to find associations among patients' comorbidities, previous medication, symptoms, and the COVID-19 treatment, and to analyze their evolution across landmarks. Towards that end, we first perform a hypothesis test based on bootstrap to identify discriminative features among deceased and non-deceased patients. Then, we leverage graph-based representations and network analytics to determine pairwise associations and complex relations among clinical features. The descriptive statistical analysis confirms that deceased patients exhibit multiple comorbidities with stronger levels of association and are treated with a wider range of drugs during the ICU stay. We also observe that the most common treatment was the simultaneous administration of lopinavir/ritonavir with hydroxychloroquine, regardless of the patients' outcome. Our results illustrate how graph tools and representations yield insights on the relations among comorbidities, drug treatments, and patients' evolution. All in all, the approach puts forth a new data-analysis tool for clinicians that can be applied to analyze (post-COVID) symptom/patient evolution.

Contemporary societies are suffering from negative population growth, with the consequent population aging. The prevalence of some chronic diseases, of slow progress and long duration, have become one of the main problems for healthcare systems. In particular, high blood pressure, diabetes mellitus, chronic obstructive pulmonary disease, and depression are health-status with a high economic and social burden. In collaboration with University Hospital of Fuenlabrada (Spain), we analyze in this work data (mainly diagnoses and drugs, both coded) from patients suffering from these chronic conditions. Given the high dimensionality of the data, we performed a hypothesis test with bootstrapping in order to select discriminative features that we subsequently analyzed using Multiple Correspondence Analysis (MCA). MCA allowed us to find associations among features and health-statuses, which may reveal not evident relationships. From the analysis carried out, on the one hand, some evidences are concluded, which can be used to validate the methodology followed in this work. On the other hand, we have drawn some conclusions that could assist in clinical decision-making, such as for example, offering more specialized care to patients stratified in the same health-status.

BACKGROUND: Chronic diseases are becoming more widespread each year in developed countries, mainly due to increasing life expectancy. Among them, diabetes mellitus (DM) and essential hypertension (EH) are two of the most prevalent ones. Furthermore, they can be the onset of other chronic conditions such as kidney or obstructive pulmonary diseases. The need to comprehend the factors related to such complex diseases motivates the development of interpretative and visual analysis methods, such as classification trees, which not only provide predictive models for diagnosing patients, but can also help to discover new clinical insights. RESULTS: In this paper, we analyzed healthy and chronic (diabetic, hypertensive) patients associated with the University Hospital of Fuenlabrada in Spain. Each patient was classified into a single health status according to clinical risk groups (CRGs). The CRGs characterize a patient through features such as age, gender, diagnosis codes, and drug codes. Based on these features and the CRGs, we have designed classification trees to determine the most discriminative decision features among different health statuses. In particular, we propose to make use of statistical data visualizations to guide the selection of features in each node when constructing a tree. We created several classification trees to distinguish among patients with different health statuses. We analyzed their performance in terms of classification accuracy, and drew clinical conclusions regarding the decision features considered in each tree. As expected, healthy patients and patients with a single chronic condition were better classified than patients with comorbidities. The constructed classification trees also show that the use of antipsychotics and the diagnosis of chronic airway obstruction are relevant for classifying patients with more than one chronic condition, in conjunction with the usual DM and/or EH diagnoses. CONCLUSIONS: We propose a methodology for constructing classification trees in a visually guided manner. The approach allows clinicians to progressively select the decision features at each of the tree nodes. The process is guided by exploratory data analysis visualizations, which may provide new insights and unexpected clinical information.

Heavy-tailed distributions are present in the characterization of different modern systems such as high-resolution imaging, cloud computing, and cognitive radio networks. Commonly, the cumulants of these distributions cannot be defined from a certain order, and this restricts the applicability of traditional methods. To fill this gap, the present letter extends the traditional Edgeworth and Cornish-Fisher expansions, which are based on the cumulants, to analogous asymptotic expansions based on the log-cumulants. The proposed expansions inherit the capability of log-cumulants to characterize heavy-tailed distributions and parallel traditional expansions. Thus, they are readily implemented. Interestingly, the proposed expansions are applicable for light-tailed distributions as well.

The Method of Moments (MoM) and Method of Log-cumulants (MoLC) estimate the distribution parameters in terms of First Kind Statistics (FKS) and Second Kind Statistics (SKS), respectively. Although SKS offer a suitable framework to analyze heavy-tailed (and asymmetric) distributions, which are commonly-found in aggregate interference modeling, statistical methods developed within this framework has been understudied. For networks following point processes of varying regularity, this paper evaluates the MoM and MoLC methods to estimate the distribution parameters of interference under Rayleigh fading and log-normal shadowing. The results confirm that the gamma and log-normal models offer accurate approximations only when the interference does not present a heavy-tail. For heavy-tailed interference, the MoLC allows an accurate and fast estimation for the α-stable model.

The current development of cloud computing is completely changing the paradigm of data knowledge extraction in huge databases. An example of this technology in the cardiac arrhythmia field is the SCOOP platform, a national-level scientific cloud-based big data service for implantable cardioverter defibrillators. In this scenario, we here propose a new methodology for automatic classification of intracardiac electrograms (EGMs) in a cloud computing system, designed for minimal signal preprocessing. A new compression-based similarity measure (CSM) is created for low computational burden, so-called weighted fast compression distance, which provides better performance when compared with other CSMs in the literature. Using simple machine learning techniques, a set of 6848 EGMs extracted from SCOOP platform were classified into seven cardiac arrhythmia classes and one noise class, reaching near to 90% accuracy when previous patient arrhythmia information was available and 63% otherwise, hence overcoming in all cases the classification provided by the majority class. Results show that this methodology can be used as a high-quality service of cloud computing, providing support to physicians for improving the knowledge on patient diagnosis.

In this paper, we propose the use of an ad-hoc wireless network formed by a fraction of the passing vehicles (sensor vehicles) to periodically recover their positions and speeds. A static roadside unit (RSU) gathers data from passing sensor vehicles. Finally, the speed/position information or space-time velocity (STV) field is then reconstructed in a data fusion center with simple interpolation techniques. We use widely accepted theoretical traffic models (i.e., car-following, multilane, and overtake-enabled models) to replicate the nonlinear characteristics of the STV field in representative situations (congested, free, and transitional traffic). To obtain realistic packet losses, we simulate the multihop ad-hoc wireless network with an IEEE 802.11p PHY layer. We conclude that: 1) for relevant configurations of both sensor vehicle and RSU densities, the wireless multihop channel performance does not critically affect the STV reconstruction error, 2) the system performance is marginally affected by transmission errors for realistic traffic conditions, 3) the STV field can be recovered with minimal mean absolute error for a very small fraction of sensor vehicles (FSV) ≈ 9%, and 4) for that FSV value, the probability that at least one sensor vehicle transits the spatiotemporal regions that contribute the most to reduce the STV reconstruction error sharply tends to 1. Thus, a random and sparse selection of wireless sensor vehicles, in realistic traffic conditions, is sufficient to get an accurate reconstruction of the STV field.

Indoor location systems based on IEEE 802.11b (WiFi) mobile devices often rely on the received signal strength indicator to estimate the user position. Two key characteristics of these systems have not yet been fully analyzed, namely, the temporal and spatial sampling process required to adequately describe the distribution of the electromagnetic field in indoor scenarios; and the device calibration, necessary for supporting different mobile devices within the same system. By using a previously proposed nonparametric methodology for system comparison, we first analyzed the time-space sampling requirements for WiFi indoor location systems in terms of conventional sampling theory and system performance. We also proposed and benchmarked three new algorithms for device calibration, with increasing levels of complexity and performance. We conclude that feasible time and space sampling rates can be used, and that calibration algorithms make possible the handling of previously unknown mobile devices in the system.

This paper addresses the problem of finding an analytical expression for the end-to-end Average Bit Error Rate (ABER) in multihop Decode-and-Forward(DAF) routes within the context of wireless networks. We provide an analytical recursive expression for the most generic case of any number of hops and any single-hop ABER for every hop in the route. Then, we solve the recursive relationship in two scenarios to obtain simple expressions for the end-to-end ABER, namely: (a) The simplest case, where all the relay channels have identical statistical behaviour; (b) The most general case, where every relay channel has a different statistical behaviour. Along with the theoretical proofs, we test our results against simulations. We then use the previous results to obtain closed analytical expressions for the end-to-end ABER considering DAF relays over Nakagami-m fading channels and with various modulation schemes. We compare these results with the corresponding expressions for Amplify-and-Forward (AAF) and, after corroborating the theoretical results with simulations, we conclude that DAF strategy is more advantageous than the AAF over Nakagami-m fading channels as both the number of relays and m-index increase.

Indoor location (IL) using received signal strength (RSS) is receiving much attention, mainly due to its ease of use in deployed IEEE 802.11b (Wi-Fi) wireless networks. Fingerprinting is the most widely used technique. It consists of estimating position by comparison of a set of RSS measurements, made by the mobile device, with a database of RSS measurements whose locations are known. However, the most convenient data structure to be used and the actual performance of the proposed fingerprinting algorithms are still controversial. In addition, the statistical distribution of indoor RSS is not easy to characterize. Therefore, we propose here the use of nonparametric statistical procedures for diagnosis of the fingerprinting model, specifically: 1) A nonparametric statistical test, based on paired bootstrap resampling, for comparison of different fingerprinting models and 2) new accuracy measurements (the uncertainty area and its bias) which take into account the complex nature of the fingerprinting output. The bootstrap comparison test and the accuracy measurements are used for RSS-IL in our Wi-Fi network, showing relevant information relating to the different fingerprinting schemes that can be used.

In this paper, we analyze stochastic gradient learning rules for posterior probability estimation using networks with a single layer of weights and a general nonlinear activation function. We provide necessary and sufficient conditions on the learning rules and the activation function to obtain probability estimates. Also, we extend the concept of well-formed cost function, proposed by Wittner and Denker, to multiclass problems, and we provide theoretical results showing the advantages of this kind of objective functions.

Deals with an application of image sequence analysis. In particular, it addresses the problem of determining the number of people who get into and out of a train carriage when it is crowded, and background and/or illumination changes. The proposed system analyzes image sequences and processes them using an algorithm based on the use of several morphological tools, which are presented in detail in the paper.

Among the many techniques available for information concealment, those based on spread spectrum modulations have proven to yield improved results when robustness against attack is at a premium. In this paper, we propose a new spread spectrum-based watermarking procedure that combines space and frequency marks to provide good robustness properties against both spatial (affine) and transform-based compression attacks, without needing the original image as a reference (blind detection). It provides a mechanism for N-bit concealment and also improves the detection-of-presence process by gathering all the watermark energy into a single value (sufficient statistic for detection). The recovery of every single bit is also improved by taking into account the so-called "watermark-print" or "waterprint" instead of looking at a single correlation value. It additionally provides the means to recover synchronization under affine transformations in the blind detection scenario. These characteristics are analyzed by means of several practical examples.

The paper deals with an application of image sequence analysis. In particular, it addresses the problem of determining the number of people who get into and out of a train carriage when it is crowded and background and/or illumination might change. The proposed system analyses image sequences and processes them using an algorithm based on the use of several morphological tools and optical flow motion estimation.