基于聚类算法的服装感性数据挖掘方法  

Fashion perceptual data mining based on clustering algorithm

作　　者：吕佳[1] 陈东生[1,2] 

机构地区：[1]江南大学纺织服装学院,江苏无锡214122 [2]闽江学院服装与艺术工程系,福建福州350121

出　　处：《纺织学报》2014年第5期108-112,共5页Journal of Textile Research

基　　金：福建省高校服务海西建设重点项目(闽教高〔2009〕8号);福建省科技厅2011年科技成果转化和产业化项目(2011I0004)

摘　　要：以运动休闲风格男士上衣为例,使用问卷调查的形式收集与之相关的主要设计元素的消费者喜好评价,将离散的设计元素与服装情绪感性信息相对应和量化,并以此为基础设计了消费者感性意向矩阵。将矩阵数据进行归一化处理后,应用专业的数据挖掘软件WEKA,使用K-means聚类算法对数据进行处理。依据输出数据最终构建了4簇典型的设计模型,对获得的大部分消费者的情感选择进行科学分析与处理,拟合出可以指导服装感性设计工作的具有代表性的最佳设计模型。通过所提出的服装感性信息模型构建的方法,可以有效揭示不同类型消费者的偏爱度,并能够筛选出对特定消费行为产生正面积极影响的重要设计元素。The paper collected consumers preference rates of all related design elements through questionnaires, and made discrete design elements correspondent to fashion perceptual data information and then conducted quantization. And based on it, the consumers perceptual intention matrix was designed. Having normalized the matrices data, K-means clustering algorithm was used for data processing through WEKA, a professional data mining software. Finally, in accordance with the output data, four typical design models was built to carry out scientifical analysis and procession of the perceptual preferences of most consumers and obtain, through fitting the best design model which is typical and can guide fashion perceptual desinging work. Through the method of the present study, it can reveal the preference degree of different types of consumer effectively, and screen out the important design elements with positive impact on consume behavior, and provide reference to fashion designers.

关 键 词：男式上衣 感性意向矩阵 情绪偏好 WEKA 聚类模型 

分 类 号：TS941.1[轻工技术与工程—服装设计与工程]