A5007067511- Network Security and Intrusion Detection
- Fault Detection and Control Systems
- Anomaly Detection Techniques and Applications
- Advanced Malware Detection Techniques
- E-Learning and Knowledge Management
- Experimental Learning in Engineering
- Effects of Environmental Stressors on Livestock
- Water Quality Monitoring Technologies
- Educational Innovations and Technology
- Animal Behavior and Welfare Studies
- Water Quality Monitoring and Analysis
- Energy Load and Power Forecasting
- Solar Radiation and Photovoltaics
- Advanced Battery Technologies Research
- Advanced Control Systems Optimization
- Smart Grid Security and Resilience
- Food Supply Chain Traceability
- Data Stream Mining Techniques
- Control Systems and Identification
- Time Series Analysis and Forecasting
- Industrial Automation and Control Systems
- Higher Education Teaching and Evaluation
- Genetic and phenotypic traits in livestock
- Machine Fault Diagnosis Techniques
- Internet Traffic Analysis and Secure E-voting
Universidade da Coruña
2021-2024
CITIC Group (China)
2022-2023
Universidad de León
2022
Colciencias
2021
Altera (United States)
2021
Abstract One of the most common attacks is man‐in‐the‐middle (MitM) which, due to its complex behaviour, difficult detect by traditional cyber‐attack detection systems. MitM on internet things systems take advantage special features protocols and cause system disruptions, making them invisible legitimate elements. In this work, an intrusion (IDS), where intelligent models can be deployed, approach type attack considering network alterations. Therefore, paper presents a novel method develop...
The prevalence of Internet Things (IoT) systems deployment is increasing across various domains, from residential to industrial settings.These are typically characterized by their modest computational requirements and use lightweight communication protocols, such as MQTT.However, the rising adoption IoT technology has also led emergence novel attacks, susceptibility these compromise.Among different attacks that can affect main protocols Denial Service (DoS).In this scenario, paper evaluates...
Abstract This paper aims to enhance security in IoT device networks through a visual tool that utilizes three projection techniques, including Beta Hebbian Learning (BHL), t-distributed Stochastic Neighbor Embedding (t-SNE) and ISOMAP, order facilitate the identification of network attacks by human experts. work research begins with creation testing environment devices web clients, simulating over Message Queuing Telemetry Transport (MQTT) for recording all relevant traffic information. The...
Abstract In this research work a novel two-step system for anomaly detection is presented and tested over several real datasets. the first step Exploratory Projection Pursuit, Beta Hebbian Learning algorithm, applied each dataset, either to reduce dimensionality of original dataset or face nonlinear datasets by generating new subspace with lower, even higher, selecting right activation function. Finally, in second Principal Component Analysis detect anomalies improve its classification...
Abstract The present research describes a novel adaptive anomaly detection method to optimize the performance of nonlinear and time-varying systems. proposal integrates centroid-based approach with real-time identification technique Recursive Least Squares. In order find anomalies, compares system dynamics average (centroid) found in earlier states for given setpoint. labels difference as an if it rises over determinate threshold. To validate proposal, two different datasets obtained from...
The increasing importance of water quality has led to optimizing the operation Wastewater Treatment Plants. This implies monitoring many parameters that measure aspects such as solid suspension, conductivity, or chemical components, among others. paper proposes use one-class algorithms learn normal behavior a Plants and detect situations in which crucial Chemical Oxygen Demand, Ammonia, Kjeldahl Nitrogen present unexpected deviations. classifiers are tested using different deviations,...
This research analyzes and compares the application of different intelligent supervised classification techniques for detecting anomalies in power cells. For this purpose, a labeled dataset is obtained generated which samples charge discharge cycles Lithium Iron Phosphate - LiFePO4 (LFP) battery commonly used electric vehicles are collected. The final classifiers present successful results.
LOW-COST HARDWARE PLATFORM IMPLEMENTATION FOR SYSTEM IDENTIFICATION AND EMULATION OF A REAL-LEVEL CONTROL PLANT
Esta experiencia describe el diseño de laboratorios virtuales para la docencia online en ámbito automatización industrial dentro del Máster Ingeniería Industrial Universidade da Coruña. Este proyecto didáctico involucró tanto a estudiantes nacionales como internacionales creación una planta virtual transporte y clasificación paquetes función peso empleando Factory I/O Unity Pro-XLS. se alinea con los Objetivos Desarrollo Sostenible (ODS) contextos educativos. Se realizó evaluación desempeño...
The use of renewable energy is expanding globally, driven by the need to reduce greenhouse gas emissions and mitigate climate change. This study focuses on modelling electrical power generated photovoltaic panels in a bioclimatic home, analyzing performance linear regression multilayer perceptron models, while considering atmospheric factors such as solar radiation ambient temperature. process includes correlation analysis select most relevant variables, followed dataset preprocessing...