蚁群算法解决连续优化问题的新途径

为了克服蚁群算法难以直接处理连续优化问题的缺陷,在保持蚁群算法基本框架的基础上,将传统蚁群算法中蚂蚁由解分量的信息素和启发式的乘积值按比例来决定取值概率的方式,改为根据连续的概率分布函数来取值.并将函数在各个维上的极值点方向作为蚂蚁搜索的启发式信息.在标准测试函数上的试验结果显示,该算法不但具有较快的收敛速度,而且能够有效地提高解的精确性,增强了算法的稳定性.     

蚁群算法中基于知识引导的信息素控制策略

针对蚁群算法在求解旅行商问题性能方面的不足,提出了一种基于知识引导的信息素控制策略.该策略利用问题先验知识初始化信息素,旨在提高算法运行初期信息素对蚂蚁搜索的启发能力;采用群知识引导信息素更新,加强信息素对蚂蚁搜索的引导能力,增强蚂蚁搜索的目的性.实验结果表明,基于这种信息素控制策略的蚁群算法的总体性能明显优于当前最先进的蚁群算法.     

基于Grid-VFACO的数字化车间WSNs路由算法

针对数字化车间中无线传感器网络(WSNs)对数据采集频率高,能量消耗快,提出了基于网格和虚拟力导向的蚁群优化(Grid-VFACO)高能效WSNs路由算法。该算法根据最优簇首数将数据采集区划分成网格,在网格中采用基于候选者的机制选择簇首,实现簇首均匀分布。在簇首形成的上层网络中,利用节点间的虚拟吸引力作为蚁群算法中转移概率规则启发因子,寻找最优数据转发路径。仿真实验结果表明:该算法能够有效减少网络能耗,保证数字化车间WSNs长时间稳定地工作。     

Applying Ant Colony Optimization to configuring stacking ensembles for data mining

An ensemble is a collective decision-making system which applies a strategy to combine the predictions of learned classifiers to generate its prediction of new instances. Early research has proved that ensemble classifiers in most cases can be more accurate than any single component classifier both empirically and theoretically. Though many ensemble approaches are proposed, it is still not an easy task to find a suitable ensemble configuration for a specific dataset. In some early works, the ensemble is selected manually according to the experience of the specialists. Metaheuristic methods can be alternative solutions to find configurations. Ant Colony Optimization (ACO) is one popular approach among metaheuristics. In this work, we propose a new ensemble construction method which applies ACO to the stacking ensemble construction process to generate domain-specific configurations. A number of experiments are performed to compare the proposed approach with some well-known ensemble methods on 18 benchmark data mining datasets. The approach is also applied to learning ensembles for a real-world cost-sensitive data mining problem. The experiment results show that the new approach can generate better stacking ensembles.     

改进蚁群算法和支持向量机的网络入侵检测

为了提高网络入侵检测的正确率,提出一种改进蚁群优化算法（ACO）和支持向量机（SVM）相融合的网络入侵检测方法（ACO-SVM）。将SVM模型参数作为蚂蚁的位置向量,采用动态随机抽取的方法来确定目标个体引导蚁群进行全局搜索,同时在最优蚂蚁邻域内进行小步长局部搜索,找到SVM最优参数,采用最优参数建立网络入侵检测模型。利用KDDCUP99数据集对ACO-SVM性能进行测试,结果表明,ACO-SVM提高了网络入侵检测正确率,降低了误报率,可以为网络安全提供有效保证。     

带约束的清洁排班问题模型及其求解

保洁服务公司的清洁任务往往具有不同级别、不同时长和不同周期等特点,缺乏通用清洁排班问题模型,现阶段主要依赖人工排班方案,存在耗时费力且排班质量不稳定等问题。因此提出了属于NP难问题的带约束的清洁排班问题的数学模型,并使用模拟退火算法（SA）、蜂群算法（BCO）、蚁群算法（ACO）和粒子群优化算法（PSO）对该模型进行求解,最后以某清洁服务公司实际排班情况进行了实证分析。实验结果表明,与人工排班方案进行对比,启发式智能优化算法求解带约束的清洁排班问题具有明显优势,获得的清洁排班表的人力需求明显减少。具体来说,在一年排班周期内这些算法比人工排班方案可节省清洁人力218.62~513.30 h。可见基于启发式智能优化算法的数学模型对带约束的清洁排班问题的求解可行且有效,能为保洁服务公司提供科学管理的决策支持。     

一种求解机器人作业调度的智能优化算法

作业调度是多机器人管理控制的一个重要方面.研完了柔性机器人焊接系统中的作业优化调度问题,该系统中的机器人都具有一定的柔性,某些焊接工序由不同的机器人来完成,且不同工件所需的焊接时间也可以不同.采用蚁群优化算法求解机器人焊接系统的作业问题,并通过算例验证了该算法的有效性.     

Mission-oriented ant-team ACO for min–max MTSP

The multiple traveling salesman problem (mTSP) is a combinatorial optimization problem and an extension of the famous traveling salesman problem (TSP). Not only does the mTSP possess academic research value, but its application is extensive. For example, the vehicle routing problem and operations scheduling can all be reduced to mTSP solutions. The mTSP is an NP-hard problem, and multifaceted discussions of its solutions are worthwhile. This study assigned ants to teams with mission-oriented approaches to enhance ant colony optimization algorithms. Missions were appointed to ant teams before they departed (each ant had a different focal search direction). In addition to attempting to complete its own mission, each ant used the Max–Min strategy to work together to optimize the solution. The goal of appointing missions is to reduce the total distance, whereas the goal of using the max–min search method for paths was to achieve Min–Max , or the goal of labor balance. Four main elements were involved in the search process of the ant teams: mission pheromone, path pheromone, greedy factor, and Max–Min ant firing scheme. The experimental results revealed this novel approach to be constructive and effective.     

Multiple objective optimisation of composite sandwich structures for rail vehicle floor panels

This paper describes the application of an ant colony optimisation (ACO) algorithm to the multiple objective optimisation of a rail vehicle floor sandwich panel. The ACO algorithm was used to search a design space that was defined by sandwich theory and a material database in order to identify constructions that were optimal with respect to low mass and low cost. A broad range of mass and cost optimal sandwich material designs were identified successfully. These provided mass savings of up to 60% compared to existing plywood-based flooring systems, although mass savings above 40% had an associated cost premium.     

An enhanced ant colony optimiser for multi-attribute partner selection in virtual enterprises

Increasing global competition drives enterprises, especially small and medium-sized enterprises, to collaborate in order to respond faster to customers’ needs, reduce operating costs, increase capacity, and produce customised products to reach the market quicker. A virtual enterprise (VE) is an important manufacturing paradigm to address this trend in the dynamic global economy. Partner selection is a key issue tightly coupled to the success of a VE coalition, and because of its complexity, it is considered a multi-attribute optimisation problem. In this paper, an enhanced ant colony optimiser (ACO) is proposed to address the partner selection problem. Five attributes (namely, cost, time, quality, reputation, and risk) considering both qualitative and quantitative aspects have been investigated to evaluate the candidate partners. Experiments have been conducted to validate the performance of the enhanced ACO algorithm, and the results show that the enhanced ACO algorithm can produce better results in terms of search accuracy and computing time.