Characterization of oil palm fruitlets using artificial neural network

Accurate data of the dielectric properties of oil palm fruitlets and the development of appropriate models are central to the quest of quality sensing and characterization, and Artificial Neural Network (ANN) and Adaptive Neurofuzzy Inference Systems (ANFIS) are becoming increasingly relevant for th...

Full description

Saved in:

Bibliographic Details
Main Author:	Olukayode, Ojo Adedayo
Format:	Thesis
Language:	English
Published:	2014
Subjects:	Oil palm - Analysis
Online Access:	http://psasir.upm.edu.my/id/eprint/64307/1/FK%202014%20121IR.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-upm-ir.64307
record_format	uketd_dc
spelling	my-upm-ir.643072018-06-11T07:32:21Z Characterization of oil palm fruitlets using artificial neural network 2014-06 Olukayode, Ojo Adedayo Accurate data of the dielectric properties of oil palm fruitlets and the development of appropriate models are central to the quest of quality sensing and characterization, and Artificial Neural Network (ANN) and Adaptive Neurofuzzy Inference Systems (ANFIS) are becoming increasingly relevant for this purpose owing to their excellent pattern matching and generalization ability. In this study, a Layer Sensitivity-Based Artificial Neural Network (LSB_ANN) and a Multi-Adaptive Neurofuzzy Inference System (MultiANFIS) were designed to characterize oil palm fruitlets and to model the dielectric phenomena of microwave interacting with oil palm fruitlets within the frequency range of 2-4GHz. The LSB_ANN has a unique weight update mechanism which employs network layer input-output sensitivity analysis. The inputs of the networks are the frequency, the magnitude of the reflection coefficient and the phase of the reflection coefficient while the outputs are the dielectric constant, the loss factor and the oil content. The training data for the models were obtained from dielectric and moisture content measurements and the obtained data were fitted into the quasi-static wave Equations and optimized using MATLAB complex root finding technique to obtain the normalized conductance, susceptance and the complex permittivity of the fruitlets. To further validate the generalization accuracy of the LSB_ANN, its performance was compared with that of a Multi-ANFIS network as well as those of three different ANN training algorithms: Levenberg Marquardt (LM) algorithm, Resilient Backpropagation (RP) algorithm and Gradient Descent with Adaptive learning rate (GDA). Having a testing Variance-For (VAF) of 97.81 and Root Mean Square Error of 3.97, the LSB_ANN was found to possess a better post training generalization ability than the LM, RP and GDA algorithms which had VAF of 93.57, 96.26 and 94.09 respectively, and RMSE of 4.14, 4.38, and 7.98 respectively. The results also showed that contrary to the widely reported gap between the accuracy of the LM algorithm and other feed forward neural network training algorithms, the RP trained network performed as good as that of the LM algorithm for the range of data considered. A user friendly neural network based Graphical User Interface (GUI) was designed suitable for rapid determination of the dielectric constant and percentage oil content of oil palm fruitlets from measured magnitude and phase of reflection coefficient within a frequency range of 2-4GHz. Oil palm - Analysis 2014-06 Thesis http://psasir.upm.edu.my/id/eprint/64307/ http://psasir.upm.edu.my/id/eprint/64307/1/FK%202014%20121IR.pdf text en public masters Universiti Putra Malaysia Oil palm - Analysis
institution	Universiti Putra Malaysia
collection	PSAS Institutional Repository
language	English
topic	Oil palm - Analysis
spellingShingle	Oil palm - Analysis Olukayode, Ojo Adedayo Characterization of oil palm fruitlets using artificial neural network
description	Accurate data of the dielectric properties of oil palm fruitlets and the development of appropriate models are central to the quest of quality sensing and characterization, and Artificial Neural Network (ANN) and Adaptive Neurofuzzy Inference Systems (ANFIS) are becoming increasingly relevant for this purpose owing to their excellent pattern matching and generalization ability. In this study, a Layer Sensitivity-Based Artificial Neural Network (LSB_ANN) and a Multi-Adaptive Neurofuzzy Inference System (MultiANFIS) were designed to characterize oil palm fruitlets and to model the dielectric phenomena of microwave interacting with oil palm fruitlets within the frequency range of 2-4GHz. The LSB_ANN has a unique weight update mechanism which employs network layer input-output sensitivity analysis. The inputs of the networks are the frequency, the magnitude of the reflection coefficient and the phase of the reflection coefficient while the outputs are the dielectric constant, the loss factor and the oil content. The training data for the models were obtained from dielectric and moisture content measurements and the obtained data were fitted into the quasi-static wave Equations and optimized using MATLAB complex root finding technique to obtain the normalized conductance, susceptance and the complex permittivity of the fruitlets. To further validate the generalization accuracy of the LSB_ANN, its performance was compared with that of a Multi-ANFIS network as well as those of three different ANN training algorithms: Levenberg Marquardt (LM) algorithm, Resilient Backpropagation (RP) algorithm and Gradient Descent with Adaptive learning rate (GDA). Having a testing Variance-For (VAF) of 97.81 and Root Mean Square Error of 3.97, the LSB_ANN was found to possess a better post training generalization ability than the LM, RP and GDA algorithms which had VAF of 93.57, 96.26 and 94.09 respectively, and RMSE of 4.14, 4.38, and 7.98 respectively. The results also showed that contrary to the widely reported gap between the accuracy of the LM algorithm and other feed forward neural network training algorithms, the RP trained network performed as good as that of the LM algorithm for the range of data considered. A user friendly neural network based Graphical User Interface (GUI) was designed suitable for rapid determination of the dielectric constant and percentage oil content of oil palm fruitlets from measured magnitude and phase of reflection coefficient within a frequency range of 2-4GHz.
format	Thesis
qualification_level	Master's degree
author	Olukayode, Ojo Adedayo
author_facet	Olukayode, Ojo Adedayo
author_sort	Olukayode, Ojo Adedayo
title	Characterization of oil palm fruitlets using artificial neural network
title_short	Characterization of oil palm fruitlets using artificial neural network
title_full	Characterization of oil palm fruitlets using artificial neural network
title_fullStr	Characterization of oil palm fruitlets using artificial neural network
title_full_unstemmed	Characterization of oil palm fruitlets using artificial neural network
title_sort	characterization of oil palm fruitlets using artificial neural network
granting_institution	Universiti Putra Malaysia
publishDate	2014
url	http://psasir.upm.edu.my/id/eprint/64307/1/FK%202014%20121IR.pdf
_version_	1747812291784474624

Characterization of oil palm fruitlets using artificial neural network

Similar Items