基于双自适应Lasso惩罚的随机效应分位回归模型研究

研究目标：解决随机效应分位回归模型中固定效应和随机效应系数同时估计和选择问题。研究方法：对固定效应和随机效应系数同时实施自适应Lasso惩罚,并为参数估计设计交替迭代算法。研究发现：新方法不仅对随机误差分布具有较强的稳健性,而且在不同稀疏度模型下均有着良好的表现,尤其是在高维情形时。研究创新：本文提出的方法在对模型中重要自变量进行选择的同时能够充分考虑随机效应的影响;交替迭代算法不仅有效解决了需要选择两个惩罚参数的困境,而且收敛速度快。研究价值：为实际工作者对面板数据和纵向数据的分析提供了有效的建模方法。     

Computing open-loop noncooperative solution in discrete dynamic games

The purpose of this paper is to introduce a new algorithm for the approximation of non-quadratic, non-linear open-loop Nash Cournot equilibrium in a difference game of fixed duration (multiperiod) and initial state. The algorithm based on adaptive search procedure called genetic algorithm has been used to optimize strategies for N-person dynamic games. Since genetic algorithms require little knowledge of the problem itself, computations based on these algorithms are very attractive to complex dynamic optimization problems. The empirical evidences are also provided to show the success of the algorithm developed. A typical example in US macroeconomic policy selection for 1933-1936 yields evidence of political inference in the economy.     

基于遗传算法(GA)的配送路径优化问题研究

文章在建立配送车辆路径优化问题数学模型的基础上，构造了遗传算法来求解该问题，并在算法中引入了自然选择、交叉操作、变异操作等思想：实验结果表明，此算法可以有效求得车辆路径问题的优化解或近似优化解．是求解车辆路径问题的一个较好的方案。     

Implementation with coalition formation: A complete characterization

The basic difference between Nash and strong (Nash) implementations originates from the possibility of coalition formation. The results of Nash implementation are applicable when agents in no group can cooperate (or form a coalition) and those of strong implementation are applicable when agents in every group can cooperate. In the present paper we consider an environment where agents in some groups can cooperate and agents in other groups cannot. We completely characterize the set of correspondences that are implementable in such a general environment, and we provide an algorithm which enables us to verify whether a correspondence satisfies the condition that appears in the characterization results. By applying the algorithm in an exchange economy, we show that the core, the definition of which depends on the possibility of cooperation, is implementable in the equilibrium corresponding to the cooperation possibility.     

基于连通可靠性的车辆路径问题

物流配送车辆路径问题(VRP)是一个NP-hard问题,很多求解方法仅考虑路网连通无穷大的情况,将其看成平均旅行时间问题,对于突发事件下造成路网拥堵情况下的车辆路径问题很少涉及,对此结合蚁群算法,对突发事件下各路段的连通可靠性进行比较后选择合适路段通过,用以提高路网的通行能力。     

二次指派问题的蚁群算法研究

蚁群算法是受自然界蚂蚁觅食过程中,基于信息素的最短路径搜索食物行为启发,提出的一种智能优化算法。在采用蚁群算法求解二次指派问题中,针对蚁群算法存在的过早收敛问题,使用距离及流量作为启发式信息并引入局部优化,对蚁群算法的结果加以改进,计算机仿真结果表明,蚁群算法对求解二次指派问题有较好的效果。     

基于遗传算法的客运站到发线优化安排

合理安排列车占用到发线计划是编制阶段计划的关键。建立的客运站到发线运用模型是非线性的整数规划模型,直接求解较为困难,为此采用遗传算法通过交叉变异等操作,构建车站到发线运用的染色体结构和适应度函数,并进行遗传算子设计,可取得较优的结果。以成都站为例,运用模型计算生成到发线运用计划,说明其结果优化效果明显。     

A tale of two recommender systems: The moderating role of consumer expertise on artificial intelligence based product recommendations

Recommender systems are used in e-Commerce websites to make product recommendations or deliver personalized content to users. We constructed a beer recommendation program using review data from existing online community to test the hypotheses. This research aims to bridge the gap between marketing and computer science by investigating the moderating effects of consumer knowledge (expertise) on the performance and evaluation of two widely-used recommendation systems – user-based collaborative filtering and content-based. The results show that expert consumers prefer user-based collaborative filtering systems, whereas there is no difference between the two systems among novice consumers. Theoretical and managerial implications are discussed.     

移动电子商务中的信息安全算法与JAVA实现

基于JAVA的安全机制,讨论经典加密算法DSA在移动电子商务信息安全中的应用.给出一个手机彩票投注系统的交易信息安全设计与实施方案,并进一步提出混合密码模型是实现信息安全算法的有效选择.     

数字化语音减速保调播放插值算法及实现

对数字化语音减速保调播放问题进行了研究并提出了一种播值算法。实验表明，算法既保证了语音质量，又有良好的实时性。