Raisin classification based on XGBoost, SVM, MLP and logistic regression

Xinyi Zhou

doi:10.1117/12.2672686

28 March 2023 Raisin classification based on XGBoost, SVM, MLP and logistic regression

Xinyi Zhou

Proceedings Volume 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022); 125970M (2023) https://doi.org/10.1117/12.2672686
Event: Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 2022, Nanjing, China

Abstract

Raisins are made by dehydrating grapes with the help of solar heat or artificial heating. It is popular because of its high sugar content, high nutritional value and easy transportation. Turkey is one of the world’s top grape producers. The paper investigates the classification of two kinds of raisin in Turkey based on XGBoost, SVM, MLP, and Logistic Regression. The aim is to determine which model is optional according to the results. According to the analysis, the accuracy rates are 85.9%, 91%, 87.3% and 86.7% for the above four models, respectively. Apparently, the model with the best accuracy is SVM. Besides, its AUC area is 0.91 so it also has a high authenticity. The most important feature may be raisin’s Extent. These results shed light on guiding further exploration of classifying other raisins or products.

Citation Download Citation

Xinyi Zhou "Raisin classification based on XGBoost, SVM, MLP and logistic regression", Proc. SPIE 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 125970M (28 March 2023); https://doi.org/10.1117/12.2672686

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available