Development of Intelligent Garment Coordination and Virtual Try-on System for Fashion Retailing with RFID Technology

Improving customer experience has become a more and more important role in enhancing customer service in fashion retailing business. In this study, a kind of intelligent garment coordination and try-on system for fashion retailing was proposed.Radio Frequency Identification (RFID) teclmology was used to identify customer and garment item automatically. The intelligent procedure for garment coordination recommendation using Artificial Neural Network (ANN) was developed to imitate fashion designers' decision-making on garment coordination. Virtual try-on algorithm based on the customer's 2D imago was accomplished using image-warping technique. The system architecture and the software framework were also described. The results show that the system is a practical and useful application for fashion retailers.     

CI战略中的服装设计师

服装企业Cl品牌战略是个系统工程,服装设计师在这个系统工程中的地位和作用应该正确确定。结合国内外服装业实际情况,对当前国内服装业不重视设计和设计师的情况提出一些看法,认为某些服装企业急功近利的做法时企业本身和中国的服装设计事业都是有害的,如不形成科学的客观的认识,将后患无穷。本文提出的设计文化概念是服装企业品牌战略的重要环节,指出:对服装设计师设计声誉的作用视而不见或剥夺抵制,是毫无远见的、落后的非理智行为——尽管这种行为普遍存在于中国的服装企业中。因此,尽快认识服装Cl战略中的设计文化,认识设计文化中的服装设计师,对一个具有现代企业概念的真正的服装企业家来说是至关重要的,并且对企业制定和落实Cl战略具有积极的现实意义和指导意义。     

基于VRML的服装协同设计系统

基于虚拟现实技术，提出了一个服装协同设计的原型系统．该系统采用VRML技术构建，以三维服装模型为设计对象，为异地设计师交流协作提供了平台．分析了服装设计的特定要求，建立了该原型系统的各主要功能模块，探讨了组建该协同环境的关键技术．该系统是服装业应用虚拟现实技术实现数字化的一项有益尝试．     

A Strategic Study of Establishing the Industrial Needs in Pattern Design and Technology in Mainland China

Pattern design and, technology play a very important role in the garment industry. In order to improve the level of pattern making and design of the garment industry, a survey was conducted to investigate the industrial needs in pattern design and technology in mainland China. The data were collected from the employers and employees from the garment industry and students in the major of fashion and clothing studies. It indicated that there was a gap between the employer and employee, especially the requirements of the industrial needs and the course contents covered by the tertiary schools. The employers expected to recruit more experienced pattern designers, at the same time, they were not reluctant to hire fresh graduates and spent more resources on the training of employees. The students knew little about their employment situation of the garment industry, spent too little time on the course study and learned too little practical skills in pattern design. They could not make use of the knowledge which prevented them from being employed by the garment industry. Efforts should be taken by both the tertiary schools and the garment industry. The students should be aspirated towards the profession of pattern cutters and the syllabuses of pattern making should be more practical and industrial orientated. The solution might benefit the garment industry a lot in a long run.     

基于本体的服装知识表示方法研究

领域本体提供了丰富的概念集,是领域知识共享的基础。采用领域本体来表示服装领域知识,可以有效地实现知识共享、复用和检索。分析了服装知识的特点,开发出服装领域本体,建立了概念及概念之间的约束关系来表达服装领域知识,用本体表示语言OWL对其进行表示,作为面向服装的知识管理系统开发平台的知识来源。     

WAVELET PACKET AND FUZZY NEURAL NETWORK FOR TOOL CONDITION MONITORING *

在自动化制造中,线监控刀具状况以保护刀具与加工工件显得越来越重要．近年来,许多研究者在此领域进行了广泛的研究,然而由于加工过程的不确定性,现有的刀具监控系统的可靠性还有待提高．本文提出了一种基于小波包分析与模糊神经网络的自适应刀具监控系统,该系统利用小波包分析方法将加工过程振动信号分解为不同的频率段,并在此基础上,建立了自适应特征提取方法,为模糊神经网络提供最优的特征输入,然后模糊神经网络据此进行决策,分析刀具磨损状况．实验结果表明：该系统模糊神经网络能有效通过学习人类模糊知识和在线学习样本来提高刀具监控精度．     

Prediction of the Performance of the Fabrics in Garment Manufacturing by Artificial Neural Network

An artificial neural network is used to predict the performance of fabrics in clothing manufacturing. The predictions are based on fabric mechanical properties measured on the FAST system. The influences of the different ANN‘s construct on the convergence speed and the prediction accuracy are investigated. The result indicates that the BP neural network is an efficiency technique and has a wide prospect in the application to garment processing.     

基于知识的服装款式设计系统的研究

分析了服装款式辅助设计应用程度较低的原因,通过对服装款式设计过程的分析，进行了系统的体系结构设计、风格化部件库建立、知识的表示。实现了以风格化设计为基础具有一定智能性的款式设计系统。对服装款式辅助设计的进一步研究及应用推广有着重要意义。     

日本服装原型的应用

从胸围、肩线、衣长３ 方面论述了日本服装原型裁剪法的原理．通过分析归纳，探讨了其运用规律．为设计者提供理论依据．     

带模糊语义的神经网络规则提取

针对传统的规则提取方法在处理连续值输入属性时带有很大的盲目性,且其描述也不符合人类的认知习惯的弊端,在对比原有方法的基础上,引入模糊语义,提出了新的处理连续值函数的方法,从神经网络中提取出带模糊语义的符号规则,提高了规则的可理解性。因此,使用者可以很方便地验证它的正确性。通过把连续值神经网络转化成二值网络,利用二值网络布尔规则提取方法来提取带模糊语义的规则,更符合人们的思维习惯。     

服装效果图的特征和发展

本文叙述服装效果图的性质是设计工具，进而阐述计算机在服装设计中的应用     

模糊神经网络分析方法用于心肌缺血诊断的研究

介绍一种神经网络－模糊推理协作系统。神经网络有很好的学习能力和准确拟合任意非线性函数的能力。模糊模型将专家知识转换到神经网络中，然后把它应用于诊断系统，从而使得心血管疾病（心肌缺血）的诊断准确率大大提高。     

非线性系统建模的复合型模糊神经网络研究

针对非线性系统建模问题,提出了一类由函数逼近和规则推理网络构成的复合型模糊神经网络,其规则网络基于过程先验知识用于对操作区间的划分,而函数网络采用改进型模糊神经网络结构完成非线性函数逼近。采用一类非线性函数模型进行了仿真研究,结果表明,复合型模糊神经网络较之普通模糊神经网络在建模收敛速度和预测精度等方面都有较大的改善。     

流行色特性分析与流行色信息系统应用探讨

从信息系统的角度,探讨了流行色的特性及应用中的各种影响因素.鉴于流行色的动态性及关联性,以服装为例分析了建立流行色信息系统对服装行业的影响及作用,提出只有建立一个机制健全的动态系统,才能使色彩更准确、更有效地应用,进而为企业求得最大的经济效益.     

服装结构设计课程教学中原型法与比例法的综合运用

原型法、比例法是服装结构设计中两种常用的方法,二法各有所长.由于原型法灵活多变的特点,被许多院校作为《服装结构设计》课程的授课方法;比例法由于它的直接、快捷特征,被我国许多服装企业应用于实际生产中.作为服装专业的主干课程,《服装结构设计》课程起着联系服装设计和服装工艺课程的纽带作用.若将两种方法结合应用于教学中,用基本款式为原型讲述结构变化,可以开拓学生的结构设计手段,更加适应社会需求.     

Reliability Analysis of Lithography Wafer Stage Based on Fuzzy Bayesian Networks

Bayesian network（ BN） is a powerful tool of uncertainty reasoning. Considering the insufficient information,incorporating fuzzy probability into BN is an effective method. Fuzzy BN was used to solve this problem. In this paper,fuzzy BN was applied in wafer stage system,which was an important part of lithography. BN of wafer stage was transferred from fault tree（ FT）. The quantitative assessment based on fuzzy BN was carried out. The Birnbaum importance factors of basic events were calculated. Therefore,the system failure probability and the vulnerable components could be gotten.     

基于自组织模糊神经网络的市场占有率模型

针对现有市场占有率模型(如传统的统计方法和近年来出现的模糊模型与神经网络模型)实际预测效果并不理想的问题,结合模糊神经网络和自组织理论建立了基于自组织模糊神经网络的市场占有率预测模型．该模型无需事先确定模糊控制规则,并能通过神经网络的结构及参数学习调整模糊神经网络的结构．最后结合实例进行了仿真．结果显示该模型优于其它模型,能为企业提供有力的市场占有率定量分析工具．     

电力系统时间配合法的渐近算法

本文引用了有关时间保护配合的新概念,将整个系统继电器和系统设备的动作列成一组最优化公式和约束条件.目的是要寻求一个最优保护整定值,以便减少系统干扰时间和电力供应中断时间.渐进算法是作为一个满足约束条件的最优化工具来寻求最优继电器整定值.     

DSP在模糊神经网络控制器中的应用

将模糊控制所具备较强的逻辑推理功能和神经网络的学习功能融为一体，组合而成模糊神经网络，通过预测神经网络和模糊神经网络的协调作用，利用梯度法可以实时地调整模糊神经网络每个隶属函数的参数值。     

Moldability Evaluation for Molded Parts Based on Fuzzy Reasoning

Moldability evaluation for molded parts,which is the basis of concurrent design,is a key design stage in injection molding design.By moldability evaluation the design problems can be found timely and an optimum plastic part design achieved.In this paper,a systematic methodology for moldability evaluation based on fuzzy logic is proposed.Firstly,fuzzy set modeling for six key design attributes of molded parts is carried out respectively.Secondly,on the basis of this,the relationship between fuzzy sets for design attributes and fuzzy sets for moldability is established by fuzzy rules that are based on domain experts‘ experience and knowledge.At last the integral moldability for molded parts is obtained through fuzzy reasoning.The neural network based fuzzy reasoning approach presented in this paper can improve fuzzy reasoning efficiency greatly,especially for system having a large number of rules and complicated membership functions.An example for moldability evaluation is given to show the feasibility of this proposed methodology.