http://hdl.handle.net/10498/6787 Mon, 21 Sep 2026 19:29:53 GMT 2026-09-21T19:29:53Z http://hdl.handle.net/10498/40178 MicroCEP: Complex Event Processing on the Edge Ortiz Bellot, Guadalupe; Tena Wilson, Javier; García Bermejo, Adrián; García de Prado Fontela, Alfonso; Reiff Marganiec, Stephan The Internet of Things (IoT) has experienced rapid growth, taking advantage of advanced data processing. While complex event processing (CEP) engines have positioned themselves as a good solution for cloud and fog data processing, there are no CEP solutions designed to run on microcontrollers (MCUs) at the edge. This paper presents MicroCEP, a software architecture for MCUs that enables real-time filtering and correlation of sensor data, both locally obtained and received through message queues at the edge. MicroCEP provides (i) a lightweight CEP architecture for MCUs, (ii) a pattern language to specify complex event patterns, (iii) a REST API for dynamic threshold updates, and (iv) a methodology for designing and deploying MicroCEP-based systems. The solution facilitates the detection of situations of interest and the triggering of actions directly from the MCUs, enabling autonomous decision-making close to the sensors. A proof of concept implementation using RISC-V MCUs provides evidence that MicroCEP can deliver CEP capabilities at the edge on resource.constrained devices.; El Internet de las Cosas (IoT) ha experimentado un rápido crecimiento, aprovechando las capacidades avanzadas de procesamiento de datos. Si bien los motores de procesamiento de eventos complejos (CEP) se han posicionado como una buena solución para el procesamiento de datos en la nube y en entornos fog, no existen soluciones CEP diseñadas para ejecutarse en microcontroladores (MCU) en el borde. Este artículo presenta MicroCEP, una arquitectura de software para MCU que permite el filtrado y la correlación en tiempo real de datos de sensores, tanto obtenidos localmente como recibidos a través de colas de mensajes en el borde. MicroCEP proporciona: (i) una arquitectura CEP ligera para MCU, (ii) un lenguaje de patrones para especificar patrones de eventos complejos, (iii) una API REST para la actualización dinámica de umbrales y (iv) una metodología para diseñar y desplegar sistemas basados en MicroCEP. La solución facilita la detección de situaciones de interés y la activación de acciones directamente desde los MCU, permitiendo una toma de decisiones autónoma cerca de los sensores. Una implementación de prueba de concepto utilizando MCU RISC-V aporta evidencia de que MicroCEP puede proporcionar capacidades CEP en el borde en dispositivos con recursos limitados. Fri, 28 Aug 2026 00:00:00 GMT http://hdl.handle.net/10498/40178 2026-08-28T00:00:00Z http://hdl.handle.net/10498/40004 Facilitating the Adoption of Complex Event Processing for IoT: Framework and Lessons Learned Cano Crespo, Manuel; Ortiz Bellot, Guadalupe; Pautasso, Cesare; García de Prado Fontela, Alfonso This paper introduces a novel framework designed to significantly facilitate the adoption by software developers and domain experts of the entire lifecycle of Complex Event Processing (CEP) for IOT domains. Recognizing the challenges non-technical users face, the framework integrates tools and processes that facilitate synthetic data generation for testing, intuitive definition, storage, and deployment of event types and patterns, and crucial runtime management. It also supports the storage and visualization of generated complex events. Its central component is SEC-AP14CEP, a secure RESTful API enabling dynamic deployment, updating, and undeployment of event patterns at runtime, overcoming limitations of existing solutions, with integrated security. By addressing these critical aspects, the framework empowers software practitioners to leverage CEP for real-time analysis and response without requiring deep technical expertise while also allowing domain experts to graphically design IOT patterns to be detected by the CEP engine.; Este artículo presenta un marco de trabajo novedoso diseñado para facilitar significativamente la adopción por parte de desarrolladores de software y expertos del dominio del ciclo de vida completo del Procesamiento de Eventos Complejos (CEP) para dominios de IoT. Reconociendo los desafíos que enfrentan los usuarios no técnicos, el marco integra herramientas y procesos que facilitan la generación de datos sintéticos para pruebas, la definición intuitiva, almacenamiento y despliegue de tipos de eventos y patrones, y la gestión crucial en tiempo de ejecución. También soporta el almacenamiento y la visualización de los eventos complejos generados. Su componente central es SEC-API4CEP, una API REST segura que permite el despliegue, actualización y desinstalación dinámica de patrones de eventos en tiempo de ejecución, superando las limitaciones de las soluciones existentes, con seguridad integrada. Al abordar estos aspectos críticos, el marco de trabajo empodera a los profesionales del software para aprovechar el CEP para el análisis y la respuesta en tiempo real sin requerir una profunda experiencia técnica, al tiempo que permite a los expertos del dominio diseñar gráficamente patrones de IoT para ser detectados por el motor de CEP. Thu, 12 Feb 2026 00:00:00 GMT http://hdl.handle.net/10498/40004 2026-02-12T00:00:00Z http://hdl.handle.net/10498/39974 Facial attribute-aware DeepFake detection through semi-supervised facial attribute labeling Stile, Vittorio; Caldelli, Roberto; Balderas Díaz, Sara; Guerrero Contreras, Gabriel José; Medina Bulo, María Inmaculada This study investigates the correlation between misclassifications in DeepFake detection and high-level facial attributes. A pre-trained frame-level classifier is used to distinguish manipulated from authentic video content, and its wrong predictions are analyzed in detail. To enrich the dataset, we automatically annotate each video with additional labels, including gender, hair color, hair length, ear visibility, and ethnicity, using a semi-supervised facial-attribute recognition pipeline. We extend this analysis with controlled training-time exclusions on FaceForensics++, keeping a unified test set to isolate generalization bias. Compared to the no-exclusion baseline (Accuracy = 0.806, AUC = 0.823), excluding samples with ears visible yields the largest degradation (Accuracy = 0.741, AUC = 0.763), while excluding non-visible ears has a milder effect (Accuracy = 0.813, AUC = 0.832). Hair length shows a moderate but consistent impact that interacts with ear visibility. We also explain the observed confusion-matrix asymmetry as a consequence of fixed score thresholds and video-level k-of-n aggregation. The results demonstrate that ear visibility is a critical factor for robust FAKE vs. REAL discrimination and motivate attribute-aware training, including targeted data curation, attribute-specific augmentation, and threshold calibration. The proposed framework provides actionable guidance for bias-aware training strategies and supports the development of more interpretable and operationally reliable DeepFake detection systems. Wed, 24 Jun 2026 00:00:00 GMT http://hdl.handle.net/10498/39974 2026-06-24T00:00:00Z http://hdl.handle.net/10498/39765 Detecting statistical anomalies in COVID-19 surveillance database Conde, Inma; Silva Ramírez, Esther Lydia; Gómez Tovar, M. Belén; Ortiz, Angel L.; Cumbrera, F.L. The unexpected unfolding of the COVID-19 pandemic involved the rapid gathering, integration, processing, and dissemination of large volumes of epidemiological data worldwide. In this context, heterogeneous reporting practices and data-integration issues may introduce certain statistical anomalies that can affect the scientific reliability of downstream analyses. Because global surveillance systems continuously aggregate multi-country time series, anomaly screening also becomes a computational problem requiring automated, scalable, and potentially near-real-time analytical workflows, which is relevant to large-scale data processing and high-performance computing environments. The purpose of the present study is to perform a quantitative analysis of COVID-19 surveillance data using Newcomb–Benford’s law and calibrated supervised datasets. As a benchmark, daily new deaths from ten countries, two from each continent, were studied, with a total of 738 records per country. The proposed framework moves beyond a binary conforming/non-conforming diagnosis by estimating the magnitude of deviation through calibrated descriptors and principal-component-based quantification. The comparison between High Income and Low Income aggregates yielded anomaly estimates of 15.27% and 20.55%, respectively, with an uncertainty of 5.2%. Overall, the results indicate that several datasets exhibit non-negligible statistical deviations from the expected digit distribution, interpreted simply as anomaly signals that may support large-scale epidemiological data validation. Disponible en acceso abierto temporalmente en: https://rdcu.be/fn4Mo Fri, 12 Jun 2026 00:00:00 GMT http://hdl.handle.net/10498/39765 2026-06-12T00:00:00Z