Factores determinantes en el desempeño de los emprendimientos empresariales a escala local en Costa Rica. Herramienta metodológica para su identificación, evaluación y diseño de estrategias para su potenciación

<a class="ep_document_link" href="/17849/1/1-s2.0-S2590005625001043-main.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Ultra Wideband radar-based gait analysis for gender classification using artificial intelligence

Gender classification plays a vital role in various applications, particularly in security and healthcare. While several biometric methods such as facial recognition, voice analysis, activity monitoring, and gait recognition are commonly used, their accuracy and reliability often suffer due to challenges like body part occlusion, high computational costs, and recognition errors. This study investigates gender classification using gait data captured by Ultra-Wideband radar, offering a non-intrusive and occlusion-resilient alternative to traditional biometric methods. A dataset comprising 163 participants was collected, and the radar signals underwent preprocessing, including clutter suppression and peak detection, to isolate meaningful gait cycles. Spectral features extracted from these cycles were transformed using a novel integration of Feedforward Artificial Neural Networks and Random Forests , enhancing discriminative power. Among the models evaluated, the Random Forest classifier demonstrated superior performance, achieving 94.68% accuracy and a cross-validation score of 0.93. The study highlights the effectiveness of Ultra-wideband radar and the proposed transformation framework in advancing robust gender classification.

Producción Científica

Adil Ali Saleem mail , Hafeez Ur Rehman Siddiqui mail , Muhammad Amjad Raza mail , Sandra Dudley mail , Julio César Martínez Espinosa mail ulio.martinez@unini.edu.mx, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Isabel de la Torre Díez mail ,

Saleem

<a href="/17844/1/frai-1-1572645.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

A systematic review of deep learning methods for community detection in social networks

Introduction: The rapid expansion of generated data through social networks has introduced significant challenges, which underscores the need for advanced methods to analyze and interpret these complex systems. Deep learning has emerged as an effective approach, offering robust capabilities to process large datasets, and uncover intricate relationships and patterns. Methods: In this systematic literature review, we explore research conducted over the past decade, focusing on the use of deep learning techniques for community detection in social networks. A total of 19 studies were carefully selected from reputable databases, including the ACM Library, Springer Link, Scopus, Science Direct, and IEEE Xplore. This review investigates the employed methodologies, evaluates their effectiveness, and discusses the challenges identified in these works. Results: Our review shows that models like graph neural networks (GNNs), autoencoders, and convolutional neural networks (CNNs) are some of the most commonly used approaches for community detection. It also examines the variety of social networks, datasets, evaluation metrics, and employed frameworks in these studies. Discussion: However, the analysis highlights several challenges, such as scalability, understanding how the models work (interpretability), and the need for solutions that can adapt to different types of networks. These issues stand out as important areas that need further attention and deeper research. This review provides meaningful insights for researchers working in social network analysis. It offers a detailed summary of recent developments, showcases the most impactful deep learning methods, and identifies key challenges that remain to be explored.

Producción Científica

Mohamed El-Moussaoui mail , Mohamed Hanine mail , Ali Kartit mail , Mónica Gracia Villar mail monica.gracia@uneatlantico.es, Helena Garay mail helena.garay@uneatlantico.es, Isabel de la Torre Díez mail ,

El-Moussaoui

<a href="/17853/1/fmed-12-1600855.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Transformer-based ECG classification for early detection of cardiac arrhythmias

Electrocardiogram (ECG) classification plays a critical role in early detection and trocardiogram (ECG) classification plays a critical role in early detection and monitoring cardiovascular diseases. This study presents a Transformer-based deep learning framework for automated ECG classification, integrating advanced preprocessing, feature selection, and dimensionality reduction techniques to improve model performance. The pipeline begins with signal preprocessing, where raw ECG data are denoised, normalized, and relabeled for compatibility with attention-based architectures. Principal component analysis (PCA), correlation analysis, and feature engineering is applied to retain the most informative features. To assess the discriminative quality of the selected features, t-distributed stochastic neighbor embedding (t-SNE) is used for visualization, revealing clear class separability in the transformed feature space. The refined dataset is then input to a Transformer- based model trained with optimized loss functions, regularization strategies, and hyperparameter tuning. The proposed model demonstrates strong performance on the MIT-BIH benchmark dataset, showing results consistent with or exceeding prior studies. However, due to differences in datasets and evaluation protocols, these comparisons are indicative rather than conclusive. The model effectively classifies ECG signals into categories such as Normal, atrial premature contraction (APC), ventricular premature contraction (VPC), and Fusion beats. These results underscore the effectiveness of Transformer-based models in biomedical signal processing and suggest potential for scalable, automated ECG diagnostics. However, deployment in real-time or resource-constrained settings will require further optimization and validation.

Producción Científica

Sunnia Ikram mail , Amna Ikram mail , Harvinder Singh mail , Malik Daler Ali Awan mail , Sajid Naveed mail , Isabel De la Torre Díez mail , Henry Fabian Gongora mail henry.gongora@uneatlantico.es, Thania Chio Montero mail ,

Ikram

<a href="/17831/1/s43856-025-01020-4.pdf" class="ep_document_link"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Association between blood cortisol levels and numerical rating scale in prehospital pain assessment

Background Nowadays, there is no correlation between levels of cortisol and pain in the prehospital setting. The aim of this work was to determine the ability of prehospital cortisol levels to correlate to pain. Cortisol levels were compared with those of the numerical rating scale (NRS). Methods This is a prospective observational study looking at adult patients with acute disease managed by Emergency Medical Services (EMS) and transferred to the emergency department of two tertiary care hospitals. Epidemiological variables, vital signs, and prehospital blood analysis data were collected. A total of 1516 patients were included, the median age was 67 years (IQR: 51–79; range: 18–103) with 42.7% of females. The primary outcome was pain evaluation by NRS, which was categorized as pain-free (0 points), mild (1–3), moderate (4–6), or severe (≥7). Analysis of variance, correlation, and classification capacity in the form area under the curve of the receiver operating characteristic (AUC) curve were used to prospectively evaluate the association of cortisol with NRS. Results The median NRS and cortisol level are 1 point (IQR: 0–4) and 282 nmol/L (IQR: 143–433). There are 584 pain-free patients (38.5%), 525 mild (34.6%), 244 moderate (16.1%), and 163 severe pain (10.8%). Cortisol levels in each NRS category result in p < 0.001. The correlation coefficient between the cortisol level and NRS is 0.87 (p < 0.001). The AUC of cortisol to classify patients into each NRS category is 0.882 (95% CI: 0.853–0.910), 0.496 (95% CI: 0.446–0.545), 0.837 (95% CI: 0.803–0.872), and 0.981 (95% CI: 0.970–0.991) for the pain-free, mild, moderate, and severe categories, respectively. Conclusions Cortisol levels show similar pain evaluation as NRS, with high-correlation for NRS pain categories, except for mild-pain. Therefore, cortisol evaluation via the EMS could provide information regarding pain status.

Producción Científica

Raúl López-Izquierdo mail , Elisa A. Ingelmo-Astorga mail , Carlos del Pozo Vegas mail , Santos Gracia Villar mail santos.gracia@uneatlantico.es, Luis Alonso Dzul López mail luis.dzul@uneatlantico.es, Silvia Aparicio Obregón mail silvia.aparicio@uneatlantico.es, Rubén Calderón Iglesias mail ruben.calderon@uneatlantico.es, Ancor Sanz-García mail , Francisco Martín-Rodríguez mail ,

López-Izquierdo

<a class="ep_document_link" href="/17838/1/s41598-025-02008-9.pdf"><img class="ep_doc_icon" alt="[img]" src="/style/images/fileicons/text.png" border="0"/></a>

en

open

Botnet detection in internet of things using stacked ensemble learning model

Botnets are used for malicious activities such as cyber-attacks, spamming, and data theft and have become a significant threat to cyber security. Despite existing approaches for cyber attack detection, botnets prove to be a particularly difficult problem that calls for more advanced detection methods. In this research, a stacking classifier is proposed based on K-nearest neighbor, support vector machine, decision tree, random forest, and multilayer perceptron, called KSDRM, for botnet detection. Logistic regression acts as the meta-learner to combine the predictions from the base classifiers into the final prediction with the aim of increasing the overall accuracy and predictive performance of the ensemble. The UNSW-NB15 dataset is used to train machine learning models and evaluate their effectiveness in detecting cyber-attacks on IoT networks. The categorical features are transformed into numerical values using label encoding. Machine learning techniques are adopted to recognize botnet attacks to enhance cyber security measures. The KSDRM model successfully captures the complex patterns and traits of botnet attacks and obtains 99.99% training accuracy. The KSDRM model also performs well during testing by achieving an accuracy of 97.94%. Based on 3, 5, 7, and 10 folds, the k-fold cross-validation results show that the proposed method’s average accuracy is 99.89%, 99.88%, 99.89%, and 99.87%, respectively. Further, the demonstration of experiments and results shows the KSDRM model is an effective method to identify botnet-based cyber attacks. The findings of this study have the potential to improve cyber security controls and strengthen networks against changing threats.

Producción Científica

Mudasir Ali mail , Muhammad Faheem Mushtaq mail , Urooj Akram mail , Daniel Gavilanes Aray mail daniel.gavilanes@uneatlantico.es, Manuel Masías Vergara mail manuel.masias@uneatlantico.es, Hanen Karamti mail , Imran Ashraf mail ,

Ali