基于无交叉遗传算法的物流车辆路径问题研究

设计并实现了一种求解基本车辆路径问题的无交叉遗传算法,阐述了无交叉遗传算法求解物流车辆路径问题的关键技术,包括编码方案、初始种群生成方案、适应度函数、种群选择方案和变异操作等;并对比了使用目标函数倒数法和目标函数做差法构造适应度函数时的求解效果。实验结果表明,给出的无交叉遗传算法在求解车辆路径问题上具有良好的性能。     

基于遗传算法的城际客运专线列车开行方案研究

分析城际客运专线列车开行方案的特点。以旅客时间消耗最小为目标，建立城际客运专线旅客列车开行方案的最小费用流模型。根据模型的特点，设计相应的遗传算法，并对遗传算法的适应值函数、算法步骤和算法复杂度进行分析。分析结果表明，该算法是一个收敛于全局最优解的近似有效算法。     

A monotonically converging algorithm for the severity of ruin in a discrete semi-markov risk model

This paper deals with the severity of ruin in a discrete semi-Markov risk model. It is shown that the work of Reinhard and Snoussi (Stochastic Models, 18) can be extended to cover the case where the premium is an integer value and no restriction on the annual result is imposed. In particular, it is shown that the severity of ruin without initial surplus is solution of a system of equations. It can be obtained by a monotonically converging algorithm when the claims are bounded.     

A hybrid parallel genetic algorithm for yard crane scheduling

This paper aims at postulating a novel strategy in terms of yard crane scheduling. In this study, a dynamic scheduling model using objective programming for yard cranes is initially developed based on rolling-horizon approach. To resolve the NP-complete problem regarding the yard crane scheduling, a hybrid algorithm, which employs heuristic rules and parallel genetic algorithm (PGA), is then employed. Then a simulation model is developed for evaluating this approach. Finally, numerical experiments on a specific container terminal yard are used for system illustration. Computational results suggest that the proposed method is able to solve the problem efficiently.     

基于改进的BP-LM在中国人口老龄化预测中的应用

由于人口老龄化率的预测具有高度非线性特征，这与BP神经网络能够处理非线性问题的特征相符合，但BP神经网络算法易使解陷入局部极小。基于L-M算法的改进BP神经网络可以有效克服这一问题，而且收敛速度快。通过具体的仿真及实践结果验证了改进BP的有效性，并对未来五年的中国老龄化率进行了预测。     

岩土边坡稳定性的遗传算法分析

非线性优化方法主要缺陷在于当边坡土层为非均质复杂条件时,无法保证搜索到安全系数的全局最小解,而只能搜索到局部极小解。基于遗传算法,建立了搜索岩土边坡稳定性分析最小安全系数和滑移面中心坐标与半径的数值方法。问题的可行解在变量搜索区间内搜索,包括滑弧的圆心坐标和半径。数值模拟结果表明,遗传算法搜索到的边坡稳定最小安全系数与理论解是一致的。     

APPLYING A GENETIC ALGORITHM TO INTERNATIONAL DIVERSIFICATION OF EQUITY PORTFOLIOS: A SOUTH AFRICAN INVESTOR PERSPECTIVE

This paper uses the genetic algorithm (GA) approach to generate a portfolio optimisation scenario of a South African investor who seeks to maximise return from investing in S&P500, FTSE100, NASDAQ, DOWJONES, CAC40 and the DAX from January 1, 2005, to January 31, 2008, but facing exchange rate risk. The GA searches for the optimal solution in the entire set of financial constraints without looking for partial derivatives of the utility function. Whereas most financial problems require a non‐linear and time‐varying model, the GA, with its survival principle of offspring chromosomes, is better suited to this type of problem than local optimisation methods. The performance of the GA is compared with two non‐linear models, namely the quadratic mean‐variance (QMV), which maximises the portfolio mean‐variance, and the quadratic variance minimisation (QVM), which minimises the portfolio variance. The results show that neither the QMV nor the QVM takes into account the domestic investors' risk attitude towards investing in foreign equities and therefore does not provide any international diversification benefits. In addition, the bootstrapping scenario of 10,000 simulations reveals that neither the QMV nor the QVM outperforms the GA in terms of Sharpe ratio and flexibility in dealing with investors' risk attitude towards investing in foreign equities denominated in foreign currencies.     

How effective are heuristic solutions for electricity planning in developing countries

Heuristic algorithms have been widely used to provide computationally feasible means of exploring the cost effective balance between grid versus off grid sources for universal electrification in developing countries. By definition in such algorithms however, global optimality is not guaranteed. We present a computationally intensive but globally optimal mixed integer non-linear programming (MINLP) model for electricity planning and use it in a Monte Carlo simulation procedure to test the relative performance of a widely used heuristic algorithm due to [28]. We show that the overall difference in cost is typically small suggesting that the heuristic algorithm is generally cost effective in many situations. However we find that the relative performance of the heuristic algorithm deteriorates with increasing degree of spatial dispersion of unelectrified settlements, as well as increasing spatial remoteness of the settlements from the grid network, suggesting that the effectiveness of the heuristic algorithm is context specific. Further, we find that allocation of off grid sources in the heuristic algorithm solution is often significantly greater than in the MINLP model suggesting that heuristic methods can overstate the role of off-grid solutions in certain situations.     

挪威国家生物库——世界级医学研究资料库

建立在生命科学、生物医学和生物信息学的快速发展基础上,生物库成为西方发达国家近些年来大力投资的基础科研设施,通过生物库收集到的人体材料(如血液、尿样等),科研人员开始利用现代医学技术,研究、利用人类遗传资源进行流行病的诊断和个性化治疗.挪威历经40年的实践,建立起了国家生物库,并在国际合作中占有突出地位.通过着重研究挪威生物库发展历程,分析其生物库的科研优势及面临的各种挑战,以期对我国医疗服务体系的发展提供有益借鉴.     

Mark-Choose-Cut Algorithms For Fair And Strongly Fair Division

This paper proposes a new criterion to evaluate algorithms for cake division, by the number of resulting pieces. Then, inspired by the idea of "cut-and-choose", we present "mark-choose-cut" algorithms for fair and strongly fair cake division problems. They are game-theoretic algorithms. The number of resulting pieces is bounded by 2 × 3n-2 + 1 and 4 × 3n-2 + 1, for fair and strongly fair division respectively.