An Intelligent Based Symmetrical Classification of Online Shop Selling Counterfeit Products

文化大學機構典藏 CCUR > 理工學院 > 理學院 > 應數系 > 期刊論文 > Item 987654321/50415

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://irlib.pccu.edu.tw/handle/987654321/50415

题名:	An Intelligent Based Symmetrical Classification of Online Shop Selling Counterfeit Products
作者:	Chen, Shyh-Wei Chen, Po-Hsiang Tsai, Ching-Tsorng Liu, Chia-Hui
贡献者:	Department of Applied Mathematics
关键词:	asymmetry information asymmetry information counterfeit website deep neural networks machine learning random forest
日期:	2022-10
上传时间:	2022-11-22 15:09:28 (UTC+8)
出版者:	MDPI
摘要:	In recent years, the social network has become popular and people have started trading transactions on the Internet. Many counterfeit websites have begun to appear which create websites with counterfeit products or use the digital advertiser’s services to promote their websites on social media. Malicious sellers disguise high-quality products to attract consumers since buyers cannot receive transparent information. If there is asymmetry information, a secondary market will be formed. To solve the above problems, this research explored the machine-learning-based method to classify counterfeit and legitimate websites with symmetry information. The data set is 1612 websites used in this paper and a total of 15 feature values and takes 804 counterfeit websites and 808 legitimate websites. The Random Forest and Deep Neural Network algorithms were used to classify fake websites. This study also used statistical tests, such as Chi-square and ANOVA detection, to compare the importance of features in feature selection. The experiment results show that the RF accuracy is 99.2% and the DNN accuracy is 93.2%. The RF Precision and Recall are 100% and 98.5%, respectively. The DNN Precision and Recall are less than RF. Then, the RF F1-score is 99.2% which is higher than DNN.
關聯:	Symmetry 開放取用卷 14, 期 10 October 2022 論文號碼 2132
显示于类别:	[應數系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	212	检视/开启

检视Licence

在CCUR中所有的数据项都受到原著作权保护.

数据加载中.....