基于自适应VPKNN-NET算法的无模糊相似图像时尚产品推荐。

IF 2.4 Q3 COMPUTER SCIENCE, INFORMATION SYSTEMS
Frontiers in Big Data Pub Date : 2025-08-07 eCollection Date: 2025-01-01 DOI:10.3389/fdata.2025.1557779
R Sabitha, D Sundar
{"title":"基于自适应VPKNN-NET算法的无模糊相似图像时尚产品推荐。","authors":"R Sabitha, D Sundar","doi":"10.3389/fdata.2025.1557779","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Recommender systems are essential in e-commerce for assisting users in navigating large product catalogs, particularly in visually driven domains like fashion. Traditional keyword-based systems often struggle to capture subjective style preferences.</p><p><strong>Methods: </strong>This study proposes a novel fashion recommendation framework using an Adaptive VPKNN-net algorithm. The model integrates deep visual feature extraction using a pre-trained VGG16 Convolutional Neural Network (CNN), dimensionality reduction through Principal Component Analysis (PCA), and a modified K-Nearest Neighbors (KNN) algorithm that combines Euclidean and cosine similarity metrics to enhance visual similarity assessment.</p><p><strong>Results: </strong>Experiments were conducted using the \"Fashion Product Images (Small)\" dataset from Kaggle. The proposed system achieved high accuracy (98.69%) and demonstrated lower RMSE (0.8213) and MAE (0.6045) compared to baseline models such as Random Forest, SVM, and standard KNN.</p><p><strong>Discussion: </strong>The proposed Adaptive VPKNN-net framework significantly improves the precision, interpretability, and efficiency of visual fashion recommendations. It eliminates the limitations of fuzzy similarity models and offers a scalable solution for visually oriented e-commerce platforms, particularly in cold-start scenarios and low-data conditions.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"8 ","pages":"1557779"},"PeriodicalIF":2.4000,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12367692/pdf/","citationCount":"0","resultStr":"{\"title\":\"A fashion product recommendation based on adaptive VPKNN-NET algorithm without fuzzy similar image.\",\"authors\":\"R Sabitha, D Sundar\",\"doi\":\"10.3389/fdata.2025.1557779\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Introduction: </strong>Recommender systems are essential in e-commerce for assisting users in navigating large product catalogs, particularly in visually driven domains like fashion. Traditional keyword-based systems often struggle to capture subjective style preferences.</p><p><strong>Methods: </strong>This study proposes a novel fashion recommendation framework using an Adaptive VPKNN-net algorithm. The model integrates deep visual feature extraction using a pre-trained VGG16 Convolutional Neural Network (CNN), dimensionality reduction through Principal Component Analysis (PCA), and a modified K-Nearest Neighbors (KNN) algorithm that combines Euclidean and cosine similarity metrics to enhance visual similarity assessment.</p><p><strong>Results: </strong>Experiments were conducted using the \\\"Fashion Product Images (Small)\\\" dataset from Kaggle. The proposed system achieved high accuracy (98.69%) and demonstrated lower RMSE (0.8213) and MAE (0.6045) compared to baseline models such as Random Forest, SVM, and standard KNN.</p><p><strong>Discussion: </strong>The proposed Adaptive VPKNN-net framework significantly improves the precision, interpretability, and efficiency of visual fashion recommendations. It eliminates the limitations of fuzzy similarity models and offers a scalable solution for visually oriented e-commerce platforms, particularly in cold-start scenarios and low-data conditions.</p>\",\"PeriodicalId\":52859,\"journal\":{\"name\":\"Frontiers in Big Data\",\"volume\":\"8 \",\"pages\":\"1557779\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2025-08-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12367692/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Big Data\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/fdata.2025.1557779\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2025/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q3\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Big Data","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fdata.2025.1557779","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

简介:推荐系统在电子商务中是必不可少的,它可以帮助用户浏览大型产品目录,特别是在时尚等视觉驱动的领域。传统的基于关键字的系统往往难以捕捉主观风格偏好。方法:本研究提出了一种基于自适应VPKNN-net算法的时尚推荐框架。该模型集成了使用预训练的VGG16卷积神经网络(CNN)进行深度视觉特征提取,通过主成分分析(PCA)进行降维,以及结合欧氏和余弦相似度度量的改进k -近邻(KNN)算法来增强视觉相似性评估。结果:使用Kaggle的“Fashion Product Images (Small)”数据集进行实验。与随机森林、支持向量机和标准KNN等基线模型相比,该系统具有较高的准确率(98.69%),RMSE(0.8213)和MAE(0.6045)较低。讨论:提出的自适应VPKNN-net框架显著提高了视觉时尚推荐的精度、可解释性和效率。它消除了模糊相似模型的限制,并为面向视觉的电子商务平台提供了可扩展的解决方案,特别是在冷启动场景和低数据条件下。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

A fashion product recommendation based on adaptive VPKNN-NET algorithm without fuzzy similar image.

A fashion product recommendation based on adaptive VPKNN-NET algorithm without fuzzy similar image.

A fashion product recommendation based on adaptive VPKNN-NET algorithm without fuzzy similar image.

A fashion product recommendation based on adaptive VPKNN-NET algorithm without fuzzy similar image.

Introduction: Recommender systems are essential in e-commerce for assisting users in navigating large product catalogs, particularly in visually driven domains like fashion. Traditional keyword-based systems often struggle to capture subjective style preferences.

Methods: This study proposes a novel fashion recommendation framework using an Adaptive VPKNN-net algorithm. The model integrates deep visual feature extraction using a pre-trained VGG16 Convolutional Neural Network (CNN), dimensionality reduction through Principal Component Analysis (PCA), and a modified K-Nearest Neighbors (KNN) algorithm that combines Euclidean and cosine similarity metrics to enhance visual similarity assessment.

Results: Experiments were conducted using the "Fashion Product Images (Small)" dataset from Kaggle. The proposed system achieved high accuracy (98.69%) and demonstrated lower RMSE (0.8213) and MAE (0.6045) compared to baseline models such as Random Forest, SVM, and standard KNN.

Discussion: The proposed Adaptive VPKNN-net framework significantly improves the precision, interpretability, and efficiency of visual fashion recommendations. It eliminates the limitations of fuzzy similarity models and offers a scalable solution for visually oriented e-commerce platforms, particularly in cold-start scenarios and low-data conditions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.20
自引率
3.20%
发文量
122
审稿时长
13 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信