Evolutionary Models for Computing Photosynthetically Active Radiation.

      Аннотация: This book is intended primarily for students, lecturers, researchers, analysts, statistical estimators, machine learning and other soft computing evaluators, institutions, government and non-governmental agencies, corporate bodies, and the public in the field of photosynthetically active radiation (PAR), renewable energy, ecology, solar and atmospheric physics, atmospheric and meteorological physics, plant science, agricultural meteorology and horticultural studies etc., to quantify, analyze, evaluate and model many challenges in a simple and logical way to present a few solutions application of, well-understandable and high-tech principles, knowledge and knowledge of PAR modeling. The purpose is to take readers' understanding into consideration of analytical procedure, techniques, applications and optimization techniques based on empirical algorithm, machine learning and evolutionary techniques applied in statistical machine learning modeling; and the confidence and skills necessary to effectively analyze, interpret, quantify and model PAR data.

Ключевые слова: Photosynthetically active radiation, gene expression programming, Empirical models, Bayesian optimization, linear regression optimization, artificial neural network, Fuzzy logic, Support Vector Machines, wavelet transform, Multi-layer Perceptron, Radial Basis Neural Network, Generalized Regression Neural Networks, Deep Learning neural network