María José Lado

Feature selection has emerged as a powerful tool for evaluating the relevance of variables in classification models. In high-dimensional datasets, not all features contribute meaningfully to accurate classification, and their inclusion can negatively affect model performance. Often, only a small subset of features is truly informative; therefore, identifying and removing irrelevant variables is crucial. In this paper, we propose a novel feature selection method based on logistic Generalized Additive Models (GAMs). Model performance was evaluated using the Bayesian Information Criterion (BIC) and the Area Under the ROC - Receiver Operating Characteristic- Curve (AUC). To demonstrate the effectiveness of this approach, we applied it to data from a clinical study aimed at diagnosing Type 2 Diabetes Mellitus (T2DM), distinguishing between diabetic and healthy individuals. The regression model incorporated features derived from Heart Period (HP) and Systolic Arterial Pressure (SAP) time series, as well as Baroreflex Sensitivity (BRS) measures, collected under two conditions: at rest and after active standing. The best-performing models selected between three and five covariates. Among the top 20 models, AUC values ranged from 0.931 to 0.918. The best 3-covariate model achieved a sensitivity of 0.816 with a false positive rate of 0.184. These results highlight the potential of this statistical methodology to enhance the discrimination between T2DM patients and control subjects.

While cardiovascular diseases are the leading causes of death in developed countries, detection of cardiac abnormalities can reduce mortality rates, through early and accurate diagnosis. One of the main assets used to help in the diagnosis process is the electrocardiogram (ECG). A free software tool for electrocardiogram analysis and diagnosis is presented. The tool, named ECGDT, allows: (1) to detect beats present on the ECG, both in single and multi-channel levels, (2) to identify beat waves, and (3) to diagnose different cardiac abnormalities. System evaluation was performed in two ways: (1) diagnostic capabilities were tested with Receiver Operating Characteristic (ROC) analysis, and (2) Graphical Software Interface (GUI) aspects, such as attraction, efficiency, or novelty, were evaluated employing User Experience Questionnaire (UEQ) scores. For disease diagnosis, the mean Area Under the ROC Curve (AUC) was 0.821. The system was also capable of detecting 100% of several cardiac abnormalities, such as bradycardia or tachycardia. Related to the GUI, all usability estimators scored values ranged between 2.208 and 2.750 (overall positive evaluations are obtained for values over 0.8). ECGDT could serve as an aid in the diagnosis of different medical abnormalities. In addition, the suitability of the developed interface has been proven.

Heart rate variability (HRV) analysis is a powerful instrument that provides information about the heart conditions. However, there exist some limitations in the use of HRV in the clinical practice. Examples are the lack of reference values for healthy populations, different HR (Heart Rate) acquisition systems, and varying software packages. Other factors that affect HRV values are the influence of lifestyle, drugs and alcohol consumption, and pollution. In this work, recommendations to perform HRV-based experiments were established. These suggestions refer to best moment of the day to record data, the optimal body position, and the quality and duration of the recorded signals. In this way, HR data from 6 healthy subjects (2 women, 4 men), with median age of 50 years old, were recorded during 15 days, 3 times a day. Recordings were performed in the following situations: both supine and sitting body positions, in the morning, in the afternoon and at night. Data were processed and HRV analysis was performed. Distorting factors affecting HRV have been determined. The most stable HRV indexes (less variation over the days) have also been established. For this task, a variation coefficient was calculated for each parameter, as the ratio between the standard deviation and the mean value. Results indicated that HR data should be recorded in the morning, the sitting position. Related to signals duration, when comparing HR signals, they should be of equal length (same recording time). In addition, HRVi (HRV triangular index) and MADRR (median of the absolute differences between adjacent RR intervals) resulted in the most robust indexes in both low and high frequency domains. For global indexes, the ApEn (approximate entropy) measure emerged as the most stable one. As a conclusion, researchers must be extremely cautious in studies involving HRV analysis; the moment of the day to record data, the body position, or the quality of recorded data will produce different HR signals, and thus, the values of the HRV parameters will be different in each case. This may clearly bias the conclusions of the study.

Nowadays, Computer Science (CS) students must cope with continuous challenges related to programming skill acquisition. In some occasions, they have to deal with the internals of memory management (pointers, pointer arithmetic, and heap management) facing a vision of programming from the low abstraction level offered by C. Even using C++ and references, not all scenarios where objects or collections of objects need to be managed can be covered. Based on the difficulties identified when dealing with such low‐level abstractions, the C‐Sim application, aimed at learning these concepts in an easy way, has been developed. To support the tool, the C programming language was selected. It allows showing concepts, remaining as close as possible both to the hardware and the operating system. To validate C‐Sim, pre and posttests were filled in by a group of 60 first‐year CS students, who employed the tool to learn about memory management. Grades of students using C‐Sim were also obtained and compared with those that did not use the tool the former academic year. As main outcomes, 82.26% of students indicated that they had improved programming and memory management knowledge, and 83.64% pointed out that the use of this type of tools improves the understanding and quality of the practice lessons. Furthermore, the marks of students have significantly increased. Finally, C‐Sim was designed from the ground up as a learning aid and can be useful for lecturers, who can complement their lessons using interactive demonstrations. Students can also employ it to experiment and learn autonomously.

Several works studied the elicitation of emotions through the exposure of individuals to relevant stimuli, using spectral analysis of Heart Rate Variability (HRV) when people are subject to emotional elicitation. If correlation exists between HRV and

This paper presents an algorithm for background modeling and foreground detection that uses scaling coefficients, which are defined with a new color model called LRGB (Lightness-Red-Green-Blue). They are employed to compare two images by finding pixels with scaled lightness. Three backgrounds are used: verified background with pixels that are considered as background, testing background with pixels that are tested several times to check if they belong to the background, and final background that is a combination of the testing and verified background (the testing background is used in places where the verified background is not defined). If a testing background pixel matches pixels from previous frames (the match is tested using scaling coefficients), it is copied to the verified background, otherwise the pixel is set as the weighted average of the corresponding pixels of the last input images. After the background is computed, foreground objects are detected by using the scaling coefficients and additional criteria. The algorithm was evaluated using the SABS Dataset, Wallflower Dataset and a subset of the CDnet 2014 Dataset. The average F measure and sensitivity with the SABS Dataset were 0.7109 and 0.8725 respectively. In the Wallflower Dataset, the total number of errors was 5280 and the total F-measure was 0.9089. In the CDnet 2014 Dataset, the F-measure for the baseline test case was 0.8887 and for the shadow test case was 0.8300.

Background: Nowadays, the assessment of psychopathy relies on semistructured interviews plus file reviews. In order to improve the predictive validity of psychopathy at the individual level, tools that are not based on the rating of signs and symptoms are in great need. Sampling and Methods: The present study was conducted in a representative sample of 204 Spanish sentenced inmates. These inmates have served at least 6 months of their sentence at the Pereiro de Aguiar (Ourense, Spain) penitentiary. Psychopathy signs and symptoms were scored through interview and file review. The Implicit Association Test (IAT) and heart rate variability (HRV) experiments were also conducted. The Iowa Gambling Task (IGT) was performed as a control measure. Results: Spectral HRV indices were able to detect psychopathic inmates at a significant level, while IAT experiments and the IGT could not discriminate them. HRV indices showed a more significant difference when assessing the affective-interpersonal dimensions of psychopathy. Conclusions: An HRV experiment is better than IAT in order to detect psychopathy in a representative sample of Spanish inmates.