A fuzzy-based customer clustering approach with hierarchical structure for logistics network optimization

Customer clustering is an essential step to reduce the complexity of large-scale logistics network optimization. By properly grouping those customers with similar characteristics, logistics operators are able to reduce operational costs and improve customer satisfaction levels. However, due to the heterogeneity and high-dimension of customers’ characteristics, the customer clustering problem has not been widely studied. This paper presents a fuzzy-based customer clustering algorithm with a hierarchical analysis structure to address this issue. Customers’ characteristics are represented using linguistic variables under major and minor criteria, and then, fuzzy integration method is used to map the sub-criteria into the higher hierarchical criteria based on the trapezoidal fuzzy numbers. A fuzzy clustering algorithm based on Axiomatic Fuzzy Set is developed to group the customers into multiple clusters. The clustering validity index is designed to evaluate the effectiveness of the proposed algorithm and find the optimal clustering solution. Results from a case study in Anshun, China reveal that the proposed approach outperforms the other three prevailing algorithms to resolve the customer clustering problem. The proposed approach also demonstrates its capability of capturing the similarity and distinguishing the difference among customers. The tentative clustered regions, determined by five decision makers in Anshun City, are used to evaluate the effectiveness of the proposed approach. The validation results indicate that the clustered results from the proposed method match the actual clustered regions from the real world well. The proposed algorithm can be readily implemented in practice to help the logistics operators reduce operational costs and improve customer satisfaction levels. In addition, the proposed algorithm is potential to apply in other research domains.     

一种人工免疫算法优化的高有效性模糊聚类图像分割

针对传统模糊聚类初值敏感、易陷入局部最优的缺陷,将具有良好勘探和开采能力的人工免疫算法用于模糊聚类的优化并提出了相应的图像分割算法.利用改进的Hausdorff距离提出一种新的抗体浓度评价算子并定义了相应的免疫算子,简化了免疫操作,增强了算法自适应寻优能力.采用最近提出的一种有效性函数作为聚类适应度函数,以人工免疫算法寻优,从而自适应地确定聚类数日与中心,实现自动图像分割.仿真实验表明,该算法可以实现图像的自动高有效性分割.     

基于RFM模型的半监督聚类算法

客户分类作为客户关系管理（CRM）的重要管理方法,是企业进行市场营销的重要依据.通过对客户进行分类,有利于对客户价值进行准确评估,方便进行精准营销.本文通过对RFM模型数据集本身潜藏的先验结构化信息进行研究,标记出两组客户数据作为先验类别标记,进而得到两个初始聚类中心.基于传统K-means算法使用自适应方法确定K值和初始聚类中心.引入Must-link和Cannot-link两种约束将类别标记转换为成对约束信息,基于HMRF-KMeans成对约束,引入约束惩罚项和约束奖励项,实现对聚类引导和聚类结果的调整.使用改进的半监督聚类算法（RFM-SS-means）对标准数据集进行了测试,同时使用Food mart数据集对比了RFM-SS-means算法与传统K-means算法、two-steps算法的聚类效果.由实验结果可知,RFM-SS-means的CH系数最大,无需事先确定K值和初始聚类中心,聚类效果良好.     

联合手肘法和期望最大化的高斯混合聚类电力系统客户分群算法

为进一步提升电力系统客户的用户体验，针对现有聚类算法寻优能力差、紧凑性不足以及较难求解聚类数目最优值的问题，提出一种联合手肘法与期望最大化（EM）的高斯混合聚类算法，挖掘大量客户数据中的潜在信息。该算法通过EM算法迭代出良好的聚类结果，而针对传统的高斯混合聚类算法需要提前获取用户分群数量的缺点，利用手肘法合理找出客户的分群数量。案例分析表明，所提算法与层次聚类算法和K-Means算法相比，FM、AR指标的增幅均超过10%，紧凑度（CI）和分离度（DS）的降幅分别低于15%和25%，可见性能有较大提升。     

基于改进??学习的知识化制造自适应动态调度策略

针对知识化制造系统生产环境的不确定性, 构建一个基于多Agent 的知识化动态调度仿真系统. 为了保证设备Agent 能够根据当前的系统状态选择合适的中标作业, 提出一种基于聚类-动态搜索的改进??学习算法, 以指导不确定生产环境下动态调度策略的自适应选择, 并给出算法的复杂性分析. 所提出的动态调度策略采用顺序聚类以降低系统状态维数, 根据状态差异度和动态贪婪搜索策略进行学习. 通过仿真实验验证了所提出动态调度策略的适应性和有效性.

     

联合手肘法和期望最大化的高斯混合聚类电力系统客户分群算法

为进一步提升电力系统客户的用户体验,针对现有聚类算法寻优能力差、紧凑性不足以及较难求解聚类数目最优值的问题,提出一种联合手肘法与期望最大化（EM）的高斯混合聚类算法,挖掘大量客户数据中的潜在信息。该算法通过EM算法迭代出良好的聚类结果,而针对传统的高斯混合聚类算法需要提前获取用户分群数量的缺点,利用手肘法合理找出客户的分群数量。案例分析表明,所提算法与层次聚类算法和K-Means算法相比,FM、AR指标的增幅均超过10%,紧凑度（CI）和分离度（DS）的降幅分别低于15%和25%,可见性能有较大提升。     

基于双层模糊聚类的多车场车辆路径遗传算法

对大规模多车场车辆路径问题,设计了基于双层模糊聚类的改进遗传算法求解框架,上层静态区域划分利用k-means技术将多车场到多客户的问题转化为一对多的子问题,下层模糊聚类从保证客户满意度和整合物流资源的角度出发,利用模糊聚类算法根据客户需求属性形成基于客户订单配送的动态客户群。进一步,通过改进选择算子和交叉算子来设计车辆路径优化的遗传算法。通过随机算例仿真实验,证明了提出方法和求解策略的有效性。     

基于偏好的客户模糊聚类方法

在电子商务环境下,如何按照顾客的购买兴趣进行聚类分析并为其提供个性化服务,是电子商务应用中研究的热点课题之一时.顾客的浏览行为及兴趣进行了研究,提出了利用偏好度的方法来度量顾客的兴趣度,在此基础上给出了基于偏好的客户群聚类算法.在该算法中,依据Web日志数据计算顾客偏好度,建立偏好度矩阵,再利用模糊聚类方法对顾客进行聚类.并用实例说明了具体的聚类过程.     

基于层次分析的客服中心实时数据流自动监测方法

为了提高客服中心的智能管理和信息调度能力,结合大数据分析方法进行客服中心实时数据监测和自动采集设计。提出一种基于模糊规则特征量挖掘和层次分析聚类的客服中心实时数据流自动监测方法。建立客服中心的网格分布结构模型并进行客服中心实时数据流监测统计特征分析,进行客服中心实时监测数据属性集的向量量化特征分解,对客服中心实时数据采用信息融合和模糊层析性分析方法实现信息融合,进行关联数据自适应特征提取,挖掘客服中心实时监测数据信息流的正相关性特征量。在层次性聚类算法基础上采用自回归分析进行客服中心实时数据流的模糊聚类和信息预测,提高客服中心实时数据监测的准确性,同时降低了客服服务中心数据流监测的风险。仿真结果表明,采用该方法进行客服中心实时数据监测的聚类性较高,预测性较好,能降低数据聚类的误分率,提高了客服中心实时数据监测能力。     

A cooperative coevolutionary algorithm for design of platform-based mass customized products

As a new business model, mass customization (MC) intends to enable enterprises to comply with customer requirements at mass production efficiencies. A widely advocated approach to implement MC is platform product customization (PPC). In this approach, a product variant is derived from a given product platform to satisfy customer requirements. Adaptive PPC is such a PPC mode in which the given product platform has a modular architecture where customization is achieved by swapping standard modules and/or scaling modular components to formulate multiple product variants according to market segments and customer requirements. Adaptive PPC optimization includes structural configuration and parametric optimization. This paper presents a new method, namely, a cooperative coevolutionary algorithm (CCEA), to solve the two interrelated problems of structural configuration and parametric optimization in adaptive PPC. The performance of the proposed algorithm is compared with other methods through a set of computational experiments. The results show that CCEA outperforms the existing hierarchical evolutionary approaches, especially for large-scale problems tested in the experiments. From the experiments, it is also noticed that CCEA is slow to converge at the beginning of evolutionary process. This initial slow convergence property of the method improves its searching capability and ensures a high quality solution.     

Mapping Product Design Specification for Mass Customization

Mass customization is an emerging field in manufacturing research community where customer satisfaction is achieved by complying with exact customer requirements at mass production efficiencies. Product varieties have mostly failed in the aspect of satisfying customer requirements, since knowing beforehand exactly what customer needs is beyond the scope of any manufacturing or marketing paradigm. So design to order and build to order is widely talked in the industry to capture heterogeneous market segments. In order to achieve the challenging task of customization at mass production efficiencies, a tight integration of the various entities involved is necessary. Gathering customer requirements, finalizing product design and eventual manufacturing need to be seamlessly integrated to achieve mass production efficiencies. Product designs are classified into customizable product platform families, and then searched based on customer requirements to identify the most conformal design family. Finally the design parameter transport is carried out from customer domain to product domain. Eventually a valid and realizable product specification is generated. The paper will address these issues of classification, selection and ultimately the mapping of parameters. A methodology to classify the product design information, which can easily accommodate design variations based on product platform architecture is proposed. Further, adaptive design customization, which relates most design parameters with the scalable platform design parameters using matrix formulation, is discussed. The proposed design parameter classification and adaptive synthesis of design parameters is applied to a spring design example.     

基于马尔可夫混合模型的电子商务搜索引擎用户行为聚类

对搜索引擎用户行为进行聚类分析有利于为用户提供个性化的服务。为了能准确地刻画用户行为的动态性,提出利用马尔可夫混合模型,对电子商务搜索引擎的用户行为模式聚类。模型假设每一类用户行为可表示为一个马尔可夫模型,当用户使用搜索引擎时,每个用户以一定的概率属于某一聚类;该用户的行为序列,由对应的马尔可夫模型产生。同时,为了解决参数估计和模型自动选择的问题,将贝叶斯阴阳和谐学习理论应用于该混合模型,提出针对该模型的和谐度函数及自适应梯度算法。仿真实验结果表明,与传统的最大期望（EM）算法相比,基于贝叶斯阴阳机的自适应梯度算法能更高效和准确地同时进行参数学习和模型选择。最后,将所提出的聚类方法应用于真实的电子商务搜索引擎点击日志,初步验证了本模型的有效性。     

An interactive clothing design and personalized virtual display system

An interactive clothing design and a personalized virtual display with user’s own face are presented in this paper to meet the requirement of personalized clothing customization. A customer interactive clothing design approach based on genetic engineering ideas is analyzed by taking suit as an example. Thus, customers could rearrange the clothing style elements, chose available color, fabric and come up with their own personalized suit style. A web 3D customization prototype system of personalized clothing is developed based on the Unity3D and VR technology. The layout of the structure and functions combined with the flow of the system are given. Practical issues such as 3D face scanning, suit style design, fabric selection, and accessory choices are addressed also. Tests to the prototype system indicate that it could show realistic clothing and fabric effect and offer effective visual and customization experience to users.

     

一种改进的多目标粒子群优化算法及其应用

针对多目标粒子群优化算法在求解约束优化问题时存在难以兼顾收敛性能和求解质量这一问题,提出一种基于免疫网络的改进多目标粒子群优化算法.该算法通过免疫网络互通种群最优信息达到粒子群算法与人工免疫网络算法的协同搜索,同时给出了速度迁移策略、自适应方差变异策略和基于聚类的免疫网络策略.最后将所提出的方法应用于求解电弧炉供电优化模型,达到了减少电量消耗、缩短冶炼时间、延长炉衬使用寿命的目的,同时表明了该算法的有效性.     

基于人工免疫算法的交通时段自动划分方法

多时段定时控制是城市交通信号控制的重要方式之一,交通时段的合理划分是制定多时段定时控制方案的基础.为克服传统时段划分方法的局限性,实现城市交通时段的自动划分,论文提取生物免疫系统的隐喻机制,基于免疫网络理论和克隆选择原理,建立了一种人工免疫数据聚类分析算法,并详细阐述了聚类算法在城市交通时段自动划分中的具体应用.实例分析表明,该算法可以有效减少聚类数据的冗余信息,特别适合于解决分级聚类等传统方法不适应的大数据量聚类问题,对解决城市交通时段的自动划分等数据聚类问题是可行的和有效的.     

双聚类算法在电信高价值客户细分的应用

针对传统客户价值细分方法在高价值客户细分时不够精细化的问题,引入了大均值子矩阵(LAS)双聚类算法。该方法在客户样本和消费属性两个维度上对消费记录进行双向聚类,可以挖掘出高消费、高价值的客户群体。以某电信公司的高价值客户细分为实例,通过定义一个价值尺度和构建一个PA指标,将所提算法与K均值(K-means)算法进行性能比较,实验结果表明,所提算法能挖掘出更多的高价值客户群体,且能够对客户属性进行更加精细的划分,因此它更适合应用于高价值客户市场的识别和细分。     

基于模糊聚类分析的客户分类算法研究

用可定制的评估指标树来描述客户分类的评价体系,让用户自主确定每个评价指标。在此基础上,提出了一种基于模糊聚类分析的客户分类算法,对客户进行分类管理,并给出了一个计算实例,取得了正确的计算结果。该计算实例表明,这个算法可以用于关于客户关系管理的决策支持系统中。     

An adaptive artificial-fish-swarm-inspired fuzzy C-means algorithm

Fuzzy C-means (FCM) is a classical algorithm of cluster analysis which has been applied to many fields including artificial intelligence, pattern recognition, data aggregation and their applications in software engineering, image processing, IoT, etc. However, it is sensitive to the initial value selection and prone to get local extremum. The classification effect is also unsatisfactory which limits its applications severely. Therefore, this paper introduces the artificial-fish-swarm algorithm (AFSA) which has strong global search ability and adds an adaptive mechanism to make it adaptively adjust the scope of visual value, improves its local and global optimization ability, and reduces the number of algorithm iterations. Then it is applied to the improved FCM which is based on the Mahalanobis distance, named as adaptive AFSA-inspired FCM(AAFSA-FCM). The optimal solution obtained by adaptive AFSA (AAFSA) is used for FCM cluster analysis to solve the problems mentioned above and improve clustering performance. Experiments show that the proposed algorithm has better clustering effect and classification performance with lower computing cost which can be better to apply to every relevant area, such as IoT, network analysis, and abnormal detection.

     

基于遗传算法的顾客购买行为特征提取

提出一种基于遗传算法的顾客行为特征提取算法。首先,采用Tanimoto 相似度来度量顾客间购买行为,并设计遗传聚类算法对顾客群体进行划分,把具有相似购买行为顾客聚集为一类。然后,针对不同顾客群体的购买行为特征,设计一种基于遗传算法的多种群特征提取方法,从各个子群体中发现顾客的购买行为的知识。为了增强种群内部协同进化能力和规则质量,我们采用最近邻替代遗传策略和局部搜索策略。使用实际零售数据集对整个算法进行验证,并与经典的Apriori算法进行比较。实验结果表明该算法在不需要产生频繁项集的情况下,可较高效生成精简规则集,在规则形式方面也更加灵活。最后,对实验结果进行详细分析。     

一种基于信息嫡的多维流数据噪声检测算法

针对传统数据流聚类算法自适应性不强、对问题的依赖性过高以及聚类质量不够理想、聚类效率低下等缺陷,提出一种基于人工免疫原理的数据流聚类IMStream算法。该算法通过引入衰减函数和时刻权重来反映过去的数据与当前流入的数据在整个数据流中的地位,通过计算抗体期望克隆率E(xi)来限制抗体克隆的数目以及保持抗体的多样性,通过采取网络中的淘汰策略使最终的网络结构更符合原始数据流的内在特性。在真实数据集和人工数据集上的实验表明,IMStream算法比传统的数据流聚类算法具有更好的性能。