A5054373442- Time Series Analysis and Forecasting
- Data Stream Mining Techniques
- Energy Load and Power Forecasting
- Stock Market Forecasting Methods
- Neural Networks and Applications
- Anomaly Detection Techniques and Applications
- Smart Grid Energy Management
- Flood Risk Assessment and Management
- Remote Sensing in Agriculture
- Smart Agriculture and AI
- Groundwater and Watershed Analysis
- Seismic Performance and Analysis
- Cell Image Analysis Techniques
- Air Quality Monitoring and Forecasting
- Electric Power System Optimization
- Geological and Geophysical Studies Worldwide
- Remote Sensing and LiDAR Applications
- Computational Physics and Python Applications
- Spectroscopy and Chemometric Analyses
- Image Processing Techniques and Applications
- Online Learning and Analytics
- SARS-CoV-2 and COVID-19 Research
- Traffic Prediction and Management Techniques
- Explainable Artificial Intelligence (XAI)
- Tropical and Extratropical Cyclones Research
Universidad Politécnica de Madrid
2024
Universidad Pablo de Olavide
2020-2023
Universidad de Sevilla
2023
A novel bioinspired metaheuristic is proposed in this work, simulating how the coronavirus spreads and infects healthy people. From an initial individual (the patient zero), new patients at known rates, creating populations of infected Every can either die or infect and, afterwards, be sent to recovered population. Relevant terms such as re-infection probability, super-spreading rate traveling are introduced model order simulate accurately possible activity. The Coronavirus Optimization...
Real-time algorithms have to adapt and adjust new incoming patterns provide timely accurate responses. This paper presents a distributed forecasting algorithm for streaming time series called StreamWNN. StreamWNN starts with an offline stage in which model based on tuples of information fusion is created historical data. In particular, this consists the composed past values future their k-nearest neighbors. Afterwards, data arrive. The incrementally updated online using buffer that more...
Precision agriculture focuses on the development of site-specific harvest considering variability each crop area. Vegetation indices allow study and delineation different characteristics field zone, generally invisible to naked-eye. This paper introduces a new big data triclustering approach based evolutionary algorithms. The algorithm shows its capability discover three-dimensional patterns basis vegetation from vine crops. Different have been tested find in results reported using vineyard...
Time series data can be defined as a chronological sequence of observations on variable interest. A streaming time is that arrives continuously at high speed and has distribution may change over time. Streaming usually comes from electronic devices such sensors many the applications dealing with in Industry 4.0 require real-time responses. Performing forecasting offers possibility to consider new types patterns incoming data, which not possible when working batch models. This paper presents...
Floods remain one of the most devastating weather-induced disasters worldwide, resulting in numerous fatalities each year and severely impacting socio-economic development environment. Therefore, ability to predict flood-prone areas advance is crucial for effective risk management. The objective this research assess compare three convolutional neural networks, U-Net, WU-Net, U-Net++, spatial prediction pluvial flood with a case study at tropical area north Vietnam. They are relative new...
Abstract This work presents a novel approach to forecast streaming big time series based on nearest similar patterns. combines clustering algorithm with classifier and the neighbours algorithm. It two separate stages: offline online. The phase is for training finding best models clustering, classification online predict in real time. In phase, data are divided into clusters forecasting model trained each cluster. addition, using cluster assignments previously generated by predicts label of...
One of the techniques that provides systematic insights into biological processes is High-Content Screening (HCS). It measures cells phenotypes simultaneously. When analysing these images, features like fluorescent colour, shape, spatial distribution and interaction between components can be found. STriGen, which works in real-time environment, leads to possibility studying time evolution real-time. In addition, data streaming algorithms are able process flows a fast way. this article,...
Identifying areas with high groundwater spring potential is crucial as it enables better decision-making concerning water supply, sustainable development, and the protection of sensitive ecosystems; therefore, necessary to predict highly accurate models. This study aims assess compare effectiveness deep neural networks (DeepNNs) swarm-optimized random forests (SwarmRFs) in predicting potential. focuses on a case conducted Gia Lai province, located Central Highland Vietnam. To accomplish this...
Abstract Predicting the occurrence of crop pests is becoming a crucial task in modern agriculture to facilitate farmers’ decision-making. One most significant olive fruit fly, public concern because it causes damage that compromises oil quality, increasing acidity and altering its flavor. This paper proposes hybrid deep learning model predict presence flies crops. based on an autoencoder automated feed-forward neural network. First, network learns representation data then automatically...
Electricity demand forecasting is very useful for the different actors involved in energy sector to plan supply chain (generation, storage and distribution of energy). Nowadays data are streaming coming from smart meters has be processed real-time more efficient management. In addition, this kind can present changes over time such as new patterns, trends, etc. Therefore, algorithms have adapt adjust online arriving order provide timely accurate responses. This work presents a algorithm...