《智能服装推荐系统Development of a Consumer-Oriented Intelligent Garment Recommendation System》基于模糊技术的智能服装推荐系统，消费者通过电商平台选择服装时，可输入包括体型数据、风格关键词和偏好图像等信息，模糊体型分类算法能智能构建消费者画像数据并生成虚拟人体模型。基于模糊技术的智能服装推荐算法能通过服装专家的知识建立的知识库为消费者推荐服装，消费者还可实时看到虚拟试穿效果，如果对推荐结果不满意，消费者可确定不满意部位，系统能够通过反馈算法智能学习消费者反馈信息自适应的更新知识库。推荐模块能根据更新后的知识库进行二次推荐，直到消费者满意为止，成功推荐的结果会存入成功知识库作为今后推荐的依据，用此系统消费者能提高网购的效率及满意度并减少碳排放。

Geneal Intoduction
Chapte 1 E-commece fo Fashion Poducts
1.1 　E-commece and Recommendation Systems
1.2 　Fashion Poducts and Fashion Makets
1.2.1 The maketing of fashion
1.2.2 Tageting a maket
1.2.3 　Custome pofiles
1.2.4 　Seasonal and occasion makets
1.2.5 　Fashion poducts
1.3 　Fashion Consume Behavio
1.3.1 　Cultual facto
1.3.2 　Social facto
1.3.3 　Individual facto
1.3.4 　Psychological facto
1.4 　Main Ideas
1.4.1 　Successful Cases Data ase Module
1.4.2 Maket Foecasting Module
1.4.3 　Knowledge-ased Recommendation Module
1.4.4 　Knowledge Updating Module
1.5 　Oiginality
Chapte 2 Fashion Data Acquisition fom Social Netwoks and Design of Sensoy Expeiments
2.1 　Social Netwoks
2.2 　Sensoy Evaluation
2.2.1 　Definition and industial application
2.2.2 　Basic notions a out sensoy evaluation
2.3 　Design of Expeiments
2.3.1 　Peliminay knowledge
2.3.2 　Expeiments
2.4 　Conclusions
Chapte 3 Concened Computational Tools
3.1 　Knowledge and Its Featues
3.2 　Fuzzy Sets and Fuzzy Opeations
3.2.1 　Fuzzy sets theoy
3.2.2 　Standad opeations of fuzzy sets
3.2.3 　Popeties of fuzzy sets
3.2.4 　Opeations on fuzzy elations
3.2.5 　Tiangula fuzzy nume
3.2.6 　Similaity degee of fuzzy sets
3.3 　FCEM and Fuzzy AHP
3.3.1 　FCEM
3.3.2 　Fuzzy AHP
3.4 　Complex Netwoks
3.4.1 　Scale-fee netwoks
3.4.2 　Small-wold netwoks
3.5 　Makov Chain
3.6 　Case-ased Reasoning
3.7 　Oganization of the Computational Techniques
Chapte 4 Successful Cases Data ase Module and Maket Foecasting Module
4.1 　Mathematical Fomalization
4.2 　Consume Pofile
4.2.1 　Size ules definition
4.2.2 　Fuzzy desciption of height
4.2.3 　Fuzzy desciption of“fat/thin”
4.2.4 　Application of the FAHP algoithm
4.2.5 　Fuzzy compehensive evaluation method (FCEM)
4.2.6 　A eal case of consume pofile
4.3 　Successful Cases Data ase Module
4.3.1 　Geneal pinciple
4.3.2 　Fomalization, similaity and easoning
4.3.3 　A eal case of successful cases data ase module
4.4 　Maket Foecasting Module
4.4.1 　Geneal pinciple
4.4.2 　Maket data analysis with Makov Chain
4.4.3 　Complex netwok
4.4.4 　A eal case of maket foecasting module
4.5 　Conclusions
Chapte 5 Knowledge-ased Recommendation Module and Knowledge Updating Module
5.1 　Knowledge-ased Recommendation Module
5.1.1 　Geneal pinciple
5.1.2 　Data aggegation fom vaious tainees
5.1.3 　Geneation of the knowledge ase (KB)
5.1.4 　Recommendation pocess though a eal case
5.2 　Knowledge Updating Module
5.2.1 　Geneal pinciple
5.2.2 　Vitual ty-on and evaluation
5.2.3 　Knowledge ase updating
5.2.4 　Knowl