Design of Neural Network Predictor for the Physical Properties of Almond Nuts
| Autor: | Feyza Gürbüz, Sezai Ercisli, Zeynel Abidin Kuş, İkbal Eski, Kadir Ugurtan Yilmaz, Mehmet Uzun, Bünyamin Demir |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Adaptive neuro fuzzy inference system
Aspect ratio Neuro-fuzzy Mean squared error 04 agricultural and veterinary sciences 02 engineering and technology Horticulture Sphericity Statistics 040103 agronomy & agriculture 0202 electrical engineering electronic engineering information engineering Projected area 0401 agriculture forestry and fisheries 020201 artificial intelligence & image processing Geometric mean Arithmetic mean Mathematics |
| Zdroj: | Erwerbs-Obstbau. 60:153-160 |
| ISSN: | 1439-0302 0014-0309 |
| Popis: | In this study, an adaptive neuro fuzzy interface system (ANFIS) based predictor was designed to predict the physical properties of four almond types. Measurements of the dimensions, length, width and thickness were carried out for one hundred randomly selected samples of each type. With using these three major perpendicular dimensions, some physical parameters such as projected area, arithmetic mean diameter, geometric mean diameter, sphericity, surface area, volume, shape index and aspect ratio were estimated. In in a various Artificial Neural Network (ANN) structures, ANFIS structure which has given the best results was selected. The parameters analytically estimated and those predicted were given in the form of figures. The root mean-squared error (RMSE) was found to be 0.0001 which is quite low. ANFIS approach has given a superior outcome in the prediction of the Physical Properties of Almond Nuts. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink