Performance Analysis of Machine Learning Methods

Machine Learning has been studied worldwide for its functions in data science and artificial intelligence (AI) fields. Previous works have shown the excellent performance of machine learning methods in image classification. This paper uses various machine learning methods for fashion product classif...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2023-02, Vol.2428 (1), p.12039
Main Authors: Liang, Dinghai, Jin, Xuan, Yuan, Yuchen, Zou, Ruyuan
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Classification
Datasets
Image classification
Machine learning
Physics
Support vector machines
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine Learning has been studied worldwide for its functions in data science and artificial intelligence (AI) fields. Previous works have shown the excellent performance of machine learning methods in image classification. This paper uses various machine learning methods for fashion product classification. This paper aims to analyze the result of predictions for all classes and the first three ranked classes, and meanwhile, compare and discuss Support Vector Machine (SVM), K Nearest Neighbor (KNN), Convolution Neural Network (CNN), Contrastive Language-Image Pre-training (CLIP) methods’ performance. The results show that the F-Score is increased if just predicted for the first three ranked classes, and among SVM, KNN, and CNN models, CNN is the best in both conditions. From the performance of all four models, CLIP was the best model with better learning ability. Besides, the results suggest that an imbalanced dataset may harm predictions, and the CLIP method yields the best result. In the future, CLIP methods may be more likely recommended in an image classification problem with lots of classes, and an imbalanced dataset adjusted will provide new insights into unsolved and unimproved classification problems.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2428/1/012039