A5101528704- Network Security and Intrusion Detection
- Recommender Systems and Techniques
- Internet Traffic Analysis and Secure E-voting
- Anomaly Detection Techniques and Applications
- Advanced Bandit Algorithms Research
- Hydrology and Sediment Transport Processes
- Advanced Malware Detection Techniques
- Soil erosion and sediment transport
- Web Data Mining and Analysis
- Mental Health Research Topics
- Hydrology and Watershed Management Studies
- Data Mining Algorithms and Applications
- Flood Risk Assessment and Management
- Modular Robots and Swarm Intelligence
- Customer churn and segmentation
- Information Retrieval and Search Behavior
- Advanced Wireless Network Optimization
- Caching and Content Delivery
- Information and Cyber Security
- Software-Defined Networks and 5G
- Distributed systems and fault tolerance
- Machine Learning in Bioinformatics
- IoT and Edge/Fog Computing
- Data Management and Algorithms
- Mental Health via Writing
Universidade da Coruña
2012-2024
Universidad de Magallanes
2023-2024
European Space Research Institute
2024
ORCID
2022
Fundación Centro Tecnológico de la Información y la Comunicación
2022
Universidad Politécnica de Cartagena
2017-2018
Indra (Spain)
2014
Universidad de Cantabria
2011-2014
University of Koblenz and Landau
2012
The technique of collaborative filtering is especially successful in generating personalized recommendations. More than a decade research has resulted numerous algorithms, although no comparison the different strategies been made. In fact, universally accepted way evaluating algorithm does not exist yet. this work, we compare techniques found literature, and study characteristics each one, highlighting their principal strengths weaknesses. Several experiments have performed, using most...
Major depressive disorder (MDD) or depression is among the most prevalent psychiatric disorders, affecting more than 300 million people globally. Early detection critical for rapid intervention, which can potentially reduce escalation of disorder.This study used data from social media networks to explore various methods early MDDs based on machine learning. We performed a thorough analysis dataset characterize subjects' behavior different aspects their writings: textual spreading, time gap,...
Climate change is profoundly affecting the global water cycle, increasing likelihood and severity of extreme water-related events. Better decision-support systems are vital to accurately predict monitor environmental disasters optimally manage resources. These must integrate advances in remote sensing, situ , citizen observations with high-resolution Earth system modeling, artificial intelligence (AI), information communication technologies, high-performance computing. Digital Twin (DTE)...
With the rise in smart devices, Internet of Things (IoT) has been established as one preferred emerging platforms to fulfil their need for simple interconnections. The use specific protocols such constrained application protocol (CoAP) demonstrated improvements performance networks. However, power-, bandwidth-, and memory-constrained sensing devices constitute a weakness security system. One way mitigate these problems is through anomaly-based intrusion detection systems, which aim estimate...
Peptides are bioactive molecules whose functional versatility in living organisms has led to successful applications diverse fields. In recent years, the amount of data describing peptide sequences and function collected open repositories substantially increased, allowing application more complex computational models study relations between composition function. This work introduces AMP-Detector, a sequence-based classification model for detection peptides’ biological activity, focusing on...
In recent years, Transformer architectures have been extensively applied to image captioning, achieving remarkable performance. The spatial and positional relationships between visual objects play a pivotal role in crafting meaningful accurate captions. To further enhance captioning with Transformers, this paper introduces the \textit{Adaptive Geometry-Integrated Transformer} (AGIT). This novel model incorporates advanced geometry-aware mechanisms into both its encoder decoder, enabling...
With the increase in use of Internet interconnected systems, security has become utmost importance. One key element to guarantee an adequate level is being able detect threat as soon possible, decreasing risk consequences derived from those actions. In this paper, a new metric for early detection system evaluation that takes into account delay defined. Time aware F-score (TaF) number items or individual elements processed determine if anomaly it not relevant be detected. These results are...
Abstract. Riparian zone delineation is a central issue for managing rivers and adjacent areas; however, criteria used to delineate them are still under debate. The area inundated by 50-yr flood has been indicated as an optimal hydrological descriptor riparian areas. This detailed information usually only available populated areas at risk of flooding. In this work we created several floodplain surfaces means two different GIS-based geomorphological approaches using digital elevation models...
The recommendation of queries, known as query suggestion, is a common practice on major Web Search Engines. It aims to help users find the information they are looking for, and usually based knowledge learned from past interactions with search engine. In this paper we propose new model for Shortcut Problem, that consists in recommending "successful" queries allowed other satisfy, past, similar needs. This has several advantages respect traditional suggestion approaches. First, it allows...
Riparian quality and habitat heterogeneity assessment in Cantabrian riversIn this study, we attempted to assess riparian river as part of the conservation status Habitats Directive (EC, 1992) rivers included Nature 2000 network Cantabria, Northern Spain.We chose Qualitat del Bosc de Ribera (QBR) Quality Index (RQI) Índice Habitabilidad Fluvial (IHF) Habitat Assessment (HQA) heterogeneity.The present study aims compare performance QBR RQI for assessing (RQ) IHF HQA (RHH).With a higher score...
With advancements in engineering and science, the application of smart systems is increasing, generating a faster growth IoT network traffic. The limitations due to restricted power computing devices also raise concerns about security vulnerabilities. Machine learning-based techniques have recently gained credibility successful for detection anomalies, including networks. However, machine learning cannot work without representative data. Given scarcity datasets, DAD emerged as an instrument...
The relative simplicity of IoT networks extends service vulnerabilities and possibilities to different network failures exhibiting system weaknesses. Therefore, having a dataset with sufficient number samples, labeled systematic analysis, is essential in order understand how these behave detect traffic anomalies. This work presents DAD: complete containing reproduction certain real-world behaviors as seen from the network. To approximate real environment, data were obtained physical center,...
Network Intrusion Detection Systems (NIDS) are concerned with the discovery of unauthorized accesses to computer networks by analyzing traffic in order detect malicious activity. In event an intrusion, time elapsed until detection is a key factor break Cyber Kill Chain. State-of-the-art studies use traditional evaluation based on standard accuracy metrics (e.g. precision or F-measure) without taking into account required threat. this paper, we formally define early intrusion problem. We...
The management of distributed and intermittent energy generation is a critical challenge within the power domain. This has emerged due to increase renewable resources in networks. Smart Grids are solution integrate dispersed efficiency through introduction Information Communication Technologies. However, require new innovative models, software architectures that enable operate an intelligent self-managing way. To deal with operation grids, this paper presents reference architecture for...
A Web Information Retrieval course is quite appealing to Computer Science students and challenging from the teacher’s perspective, due limited knowledge of IR students. In this paper we present our experience teaching a mainly practical in order exploit programming skills common student. The student required develop its own search engine his evaluation based on features implemented.
Nowadays, the Internet of things (IoT) network, as system interrelated computing devices with ability to transfer data over a is present in many scenarios everyday life. Understanding how traffic behaves can be done more easily if real environment replicated virtualized environment. In this paper, we propose methodology develop systematic approach dataset analysis for detecting anomalies an IoT network. The reader will become familiar specific techniques and tools that are used. have five...