A5017096452- Energy Load and Power Forecasting
- Building Energy and Comfort Optimization
- Neural Networks and Applications
- Smart Grid Energy Management
- Time Series Analysis and Forecasting
- Stock Market Forecasting Methods
- Energy Efficiency and Management
- Smart Agriculture and AI
- Solar Radiation and Photovoltaics
- Metaheuristic Optimization Algorithms Research
- Advanced Multi-Objective Optimization Algorithms
- Quantum Computing Algorithms and Architecture
- Evolutionary Algorithms and Applications
- Neural Networks and Reservoir Computing
- Photovoltaic System Optimization Techniques
- Spectroscopy and Chemometric Analyses
- Soil Geostatistics and Mapping
- Advanced Data Processing Techniques
- Cellular Automata and Applications
- Flow Experience in Various Fields
- Soil and Land Suitability Analysis
- Cybercrime and Law Enforcement Studies
- Advanced Image Fusion Techniques
- Smart Parking Systems Research
- IoT-based Smart Home Systems
Universidad de Granada
2016-2024
Software (Spain)
2022-2024
Universidad Pablo de Olavide
2023
Imperial College London
2020-2021
This paper addresses the problem of energy consumption prediction using neural networks over a set public buildings. Since in sector comprises substantial share overall consumption, such represents decisive issue achievement savings. In our experiments, we use data provided by an monitoring system compound faculties and research centers at University Granada, provide methodology to predict future nonlinear autoregressive (NAR) network with exogenous inputs (NARX), respectively. Results...
Thanks to advances in smart metering devices (SM), the electricity sector is undergoing a series of changes, among which it worth highlighting ability control response all events that occur grid with intention making more smart. Predicting consumption data key factor for energy order create completely intelligent optimizes and forecasts future needs. However, currently not enough give prediction (EC), but also necessary as fast possible so can operate shortest time. An approach developing EC...
This study investigates the application of different ML methods for predicting pest outbreaks in Kazakhstan grain crops. Comprehensive data spanning from 2005 to 2022, including population metrics, meteorological data, and geographical parameters, were employed train neural network forecasting dynamics Phyllotreta vittula pests Kazakhstan. By evaluating various configurations hyperparameters, this research considers MLP, MT-ANN, LSTM, transformer, SVR. The transformer consistently...
Photovoltaic solar energy is booming due to the continuous improvement in photovoltaic panel efficiency along with a downward trend production costs. In addition, European Union committed easing implementation of renewable many companies order obtain funding install their own panels. Nonetheless, nature intermittent and uncontrollable. This leads us an uncertain scenario which may cause instability systems. research addresses this problem by implementing intelligent models predict energy....
Colour is a property widely used in many fields to extract information several ways. In soil science, colour provides regarding the chemical and physical characteristics of soil, such as genesis, composition, fertility, amongst others. Thus, accurate estimation essential for disciplines. To achieve this, experts traditionally rely on comparing Munsell charts with samples, which laborious process. this study, we proposed using artificial neural networks catalogue two-step classification....
Pattern sequence-based models are a type of forecasting algorithm that utilizes clustering and other techniques to produce easily interpretable predictions faster than traditional machine learning models. This research focuses on their application in energy demand introduces two significant contributions the field. Firstly, this study evaluates use pattern with large datasets. Unlike previous works only one dataset or multiple datasets less years data, work three different public datasets,...
The goal of this study is to estimate the state consciousness known as Flow, which associated with an optimal experience and can indicate a person’s efficiency in both personal professional settings. To predict we employ artificial intelligence techniques using set variables not directly connected its construct. We analyse significant amount data from psychological tests that measure various personality traits. Data mining support conclusions drawn study. apply linear regression, regression...
The energy supply sector faces significant challenges, such as the ongoing COVID-19 pandemic and conflict in Ukraine, which affect stability efficiency of system. In this study, we highlight importance electricity pricing need for accurate models to estimate consumption prices, with a focus on Spain. Using hourly data, implemented various machine learning models, including linear regression, random forest, XGBoost, LSTM, GRU, forecast prices. Our findings have important policy implications....
Introduction In the last few years, there has been considerable progress in time series forecasting algorithms, which are becoming more and accurate, their applications numerous varied [...]