K聚类加权最小二乘支持向量机在分类中的应用

数据分类作为模式识别、故障诊断技术的基础,在实际应用中常常由于系统的非线性、噪声性以及样本的不平衡采集,使得常规的分类算法存在一定的局限性。将最小二乘加权支持向量机用于分类问题,利用K聚类算法分析样本间内在关系从而确定权值系数,可以很好地减小噪声影响,补偿不同类样本数目上的不平衡,减少训练时间,提高分类正确率。通过一个图像识别过程中多类别分类实例,证明了算法在分类问题中的有效性。该方法可以成为现有方法的有效补充分析工具。     

零售商具有灵活决策目标的供应链协调

建立了零售商具有两种灵活决策目标的供应链模型:期望利润最大化和期望投资回报率最大化.分别研究了批发价策略和双部定价策略两类契约下的博弈动态,推导出各自的均衡结果.在此基础上,结合仿真实例,考察了契约柔性对供应链协调性的影响以及契约柔性价值随决策目标的变化情况.结果表明:契约柔性化是协调策略设计的重要思路之一,但其价值因决策目标差异而不同,期望投资回报率条件下协调难度更大.     

Supply Chain Production-distribution Cost Optimization under Grey Fuzzy Uncertainty

Most supply chain programming problems are restricted to the deterministic situations or stochastic environments. Considering twofold uncertainty combining grey and fuzzy factors, this paper proposes a hybrid uncertain programming model to optimize the supply chain production-distribution cost. The programming parameters of the material suppliers, manufacturer, distribution centers, and the customers are integrated into the presented model. On the basis of the chance measure and the credibility of grey fuzzy variable, the grey fuzzy simulation methodology was proposed to generate input-output data for the uncertain functions. The designed neural network can expedite the simulation process after trained from the generated input-output data. The improved Particle Swarm Optimization (PSO) algorithm based on the Differential Evolution (DE) algorithm can optimize the uncertain programming problems. A numerical example was presented to highlight the significance of the uncertain model and the feasibility of the solution strategy.     

Hybrid Intelligent Approach for the Selection of Third-Party Reverse Logistics Provider under Uncertainty

A hybrid intelligent approach is proposed to help the decision maker to select the appropriate third-party reverse logistics provider. The following process is included： firstly,the evaluation team is established to determine the selection criteria and evaluate them by triangular fuzzy numbers; secondly,calculate the weight of criteria by the proposed hybrid algorithm integrating particle swarm optimization（ PSO） and simulated annealing（ SA）; then, the performance evaluation for each supplier is predicted by the proposed self-feedback neural network（ SFBNN） based on the historical data. A numerical example is also presented to interpret the methodology above.     

随机灰色提前期条件下制造/再制造混合系统库存优化

基于PUSH库存控制策略提出了在不确定生产提前期、恒定顾客需求率和产品回收率条件下的制造/再制造混合生产系统库存控制模型,可用品仓库库存由新产品制造过程和回收产品的再制造过程共同补充。不确定的生产提前期可描述为随机灰色变量,提出的随机灰色模拟技术可为不确定函数产生输入-输出数据,利用该输入-输出数据训练后的神经网络可加速不确定函数的模拟过程,由随机灰色模拟、神经网络和遗传算法集成的混合智能优化算法可求解该库存模型。数值分析结果表明:平均生产成本随给定的顾客服务水平和生产提前期的增加而增加,该不确定模型符合实际库存系统的实际情况,提出的智能优化算法可优化复杂的不确定规划问题。     

一种风险规避供应链的协调研究

研究了一类风险规避供应链的协调问题。建立了零售商权衡期望利润与实现该利润概率的决策模型,分析这类规避特性对供应链协调性的影响。证明了常用协调契约的局限性,并设计出一种新的柔性契约实现协调。对3类风险规避模型进行比较,结果表明风险规避类型是协调差异的重要因素。研究结果为实际供应链中的企业提供了决策依据。