Hyperparameter Optimization of ANN, SVM, and KNN Models for Classification of Hazelnuts Images Based on Shell Cracks and Feature Selection Method
Journal Title: Journal of Agricultural Machinery - Year 2025, Vol 15, Issue 1
Abstract
In some countries, people commonly consume hazelnuts in their shells to extend shelf life or due to technological limitations. Therefore, open-shell hazelnuts are more marketable. At the semi-industrial scale, open-shell and closed-shell hazelnuts are currently separated from each other through visual inspection. This study aims to develop a new algorithm to separate open-shell hazelnuts from cracked or closed-shell hazelnuts. In the first approach, dimension reduction techniques such as Sequential Forward Feature Selection (SFFS) and Principal Component Analysis (PCA) were used to select or extract a combination of color, texture, and grayscale features for the modelâs input. In the second approach, individual features were used directly as inputs. In this study, three famous machine learning models, including Support Vector Machine (SVM), K-nearest neighbors (KNN), and Multi-Layer Perceptron (MLP) were employed. The results indicated that the SFFS method had a greater effect on improving the performance of the models than the PCA method. However, there was no significant difference between the performance of the models developed with combined features (98.00%) and that of the models using individual features (98.67%). The overall results of this study indicated that the MLP model, with one hidden layer, a dropout of 0.3, and 10 neurons using Histogram of Oriented Gradients (HOG) features as input, is a good choice for classifying hazelnuts into two classes of open-shell and closed-shell.
Authors and Affiliations
H. Bagherpour,F. Fatehi,A. Shojaeian,R. Bagherpour,
Keywords
Related Articles
- EP ID EP760023
- DOI https://doi.org/10.22067/jam.2024.87830.1244
- Views 16
- Downloads 0
The effect of injection timing on energy and exergy analysis of a diesel engine with biodiesel fuel
Introduction Nowadays, due to higher environmental pollution and decreasing fossil fuels many countries make decisions to use renewable fuels and restrict using of fossil fuels. Renewable fuels generally produce from bio...
Modeling and Predicting the Forces on Moldboard Plough by using Response Surface and Artificial Neural Network
IntroductionTillage is a very important operation that influences the growth and productivity of agricultural products. It is necessary to introduce some conditions to improve soil physical properties, aeration, permeabi...
Design of ultrasonic probe and evaluation of ultrasonic waves on E.coli in Sour Cherry Juice
Introduction: The common method used for juice pasteurization is the thermal method since thermal methods contribute highly to inactivating microbes. However, applying high temperatures would lead to inefficient effects...
Development and evaluation of a targeted orchard sprayer using machine vision technology
IntroductionIn conventional methods of spraying in orchards, the amount of pesticide sprayed, is not targeted. The pesticide consumption data indicates that the application rate of pesticide in greenhouses and orchards i...
Design, Fabrication and Evaluation of a Novel System for Magnetic Field Application to the Seeds- Case study of Onion Seed
Non-chemical treatments are an approach for improving seed germination. In order to evaluate the effects of the magnetic field application on onion seed germination and seedling growth indices, a quadrupole magnetic fiel...