Reprint

Predicting the Future

Big Data and Machine Learning

Edited by
August 2020
148 pages
  • ISBN978-3-03936-619-4 (Hardback)
  • ISBN978-3-03936-620-0 (PDF)

This book is a reprint of the Special Issue Predicting the Future—Big Data and Machine Learning that was published in

Chemistry & Materials Science
Engineering
Environmental & Earth Sciences
Physical Sciences
Summary

Due to the increased capabilities of microprocessors and the advent of graphics processing units (GPUs) in recent decades, the use of machine learning methodologies has become popular in many fields of science and technology. This fact, together with the availability of large amounts of information, has meant that machine learning and Big Data have an important presence in the field of Energy. This Special Issue entitled “Predicting the Future—Big Data and Machine Learning” is focused on applications of machine learning methodologies in the field of energy. Topics include but are not limited to the following: big data architectures of power supply systems, energy-saving and efficiency models, environmental effects of energy consumption, prediction of occupational health and safety outcomes in the energy industry, price forecast prediction of raw materials, and energy management of smart buildings.

Format
  • Hardback
License
© 2020 by the authors; CC BY-NC-ND license
Keywords
short-term loads forecasting; CCHP systems; convolutional neural network; short-term memory network; dropout layer; crack tip opening displacement; steels; welded or bonded joints; multivariate regression model; marine structures; neural network; deep learning; climate; photosynthesis; ecology; FLUXNET; crude oil prices; forecasting; complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN); multi-layer gated recurrent unit (ML-GRU); raw material; price forecasting; artificial neural network; predictor variable; lagged variable size; rolling window; coking coal; natural gas; crude oil; coal; sick leave; absenteeism; energy sector; genetic algorithms (GA); multivariate adaptive regression splines (MARS); biomass; bioenergy; energy production system; NILM; disaggregation methods; non-intrusive load monitoring; appliance consumptions; soft computing; n/a