A Study of Applications of RBF Network

Abstract

Forecasting is a method of making statements about certain event whose actual results have not been observed. It seems to be an easy process but is actually not. It requires a lot of analysis on current and past outcomes in order to give timely and accurate timely forecasted results.Radial Basis Function (RBF) is a method proposed in machine learning for making predictions and forecasting. It has been used in various real time applications such as weather forecasting, load forecasting, forecasting about number of tourist and many such applications. The paper includes a detailed survey on RBF network on the basis of its evolution and applications. It also covers explanation about combination of RBF with other techniques such as Fuzzy, Neural Networkand Genetic Algorithm.

Machine learning methods for optimal prediction of motor outcome in Parkinson’s disease

“…These are all listed in the Supplement (Part II, Section 1). Specifically, we selected 10 predictor algorithms: 1) LOLIMOT (Local Linear Model Trees) [35,36], 2) RBF (Radial basis Function) [37], 3) MLP-BP (Multilayer Perceptron-Back propagation) [38,39], 4) LASSOLAR (Least Absolute Shrinkage and Selection Operator -Least Angle Regression) [40,41], 5) RFA (Random Forest Algorithm) [42,43], 6) RNN (Recurrent Neural Network) [44,45], 7) BRR (Bayesian Ridge Regression) [46][47][48], 8) DTC (Decision Tree Classification) [49][50][51], 9) PAR (Passive Aggressive Regression) [52][53][54], 10) Thiel-Sen Regression [55-57] and 11) ANFIS (Adaptive neuro fuzzy inference system) [58,59]. In this work, we automatically adjusted intrinsic parameters such as the number of neurons and number of layers in the predictor algorithms etc.…”

Development of new upper body power prediction models for cross-country skiers by using different machine learning methods

“…Yapılan deneylerde, geliştirilen CCN tabanlı modellerin performansını iyileştiren parametrelerin gizli katmandaki çekirdek fonksiyonunun tipi ve havuzdaki aday nöronlarının RBF, biyolojik sinir hücrelerinde görülen etki-tepki davranışlarından esinlenilerek geliştirilmiş bir yöntemdir. Genel yapay sinir ağları mimarisine benzer şekilde giriş katmanı, gizli katman ve çıktı katmanı olmak üzere 3 katman halinde tanımlanmaktadır [11]. Geliştirilen RBF tabanlı modellerin performansını etkileyen en önemli parametreler, gizli katmandaki maksimum nöron sayısı, RBF'in yarıçapı ve regülasyon katsayısı ( λ ) olarak bulunmuştur.…”

Regresión Simbólica aplicada a la Predicción del Consumo Eléctrico a Corto Plazo en el Nivel de Subestación

“…Una red neuronal de tipo Feedforward entrenadas con método de Backpropagation o BPNN (Ahmad, 2012;Kamboj & Avtar, 2013) es una de las arquitecturas más utilizadas por su capacidad de extraer relaciones complejas y no lineales de los datos. Por otro lado, las Redes Neuronales de Función de Base Radial o RBFNN tienen una arquitectura especial y pueden ser utilizadas para la predicción (Arora et al, 2014;Jimenez et al, 2017). Todos estos métodos tienen ciertos inconvenientes, como la difícil parametrización y la posibilidad de que se produzca un sobreajuste u Overfitting (Borges et al, 2013).…”