蜂群算法解决集聚约束调度问题

为满足真实调度环境中常见的集聚约束问题,本文提出以蜂群优化为基础的调度算法,形成个性化调度方案。算法通过模仿蜂群的"觅食"和"舞蹈"行为实现寻优操作,通过赋予蜜蜂不同的"信念"实现种群的多样化,通过将集聚约束以社会规范的形式融合到蜜蜂觅食过程中满足用户对调度的个性化要求,通过蜜蜂在舞蹈过程中展示行走路径和选择参考路径实现蜂群"经验"共享。对若干标准算例的测试结果及与其它算法的比较验证了本文算法的有效性。     

Construction of Cryptographically Strong S-Boxes Inspired by Bee Waggle Dance

In this paper, we explore a heuristic method called the bee waggle dance to construct cryptographically strong S-boxes. The S-boxes exhibit good cryptographic properties such as high nonlinearity, low differential uniformity and high algebraic degree. The method involves the use of a trinomial power function as the initial S-box. The elements in the S-box are then permuted using the bee waggle dance algorithm. The S-boxes produced using this method are found to compare reasonably well with other existing S-boxes constructed using alternative heuristic methods. To the best of our knowledge, this is the first attempt to construct cryptographically strong S-boxes using the bee waggle dance algorithm.     

Repetition Estimation

International Journal of Computer Vision - Visual repetition is ubiquitous in our world. It appears in human activity (sports, cooking), animal behavior (a bee’s waggle dance), natural...     

一种双种群差分蜂群算法

人工蜂群算法(ABC)是一种基于蜜蜂群智能搜索行为的随机优化算法.为了有效改善人工蜂群算法的性能,结合差分进化算法,提出一种新的双种群差分蜂群算法(BDABC).该算法首先通过基于反向学习的策略初始化种群,使得初始化的个体尽可能均匀分布在搜索空间,然后将种群中的个体随机分成两组,每组采用不同的优化策略同时进行寻优,并通过在两群体之间引入交互学习的思想,来提高算法的收敛速度.基于6个标准测试函数的仿真实验表明,BDABC算法能有效避免早熟收敛,全局优化能力和收敛速率都有显著提高.     

Multiple colony bees algorithm for continuous spaces

This paper represent a new multiple colony bees algorithm (MCBA) for functional optimization. The MCBA simulates the behaviours of honey bees in their own hive and realizes a communication strategy between the bees living in different hives. However, there is not much information about such a communication strategy between different hives of honey bees. Since information sharing is an essential issue from the optimization point of view, this relevant communication strategy has been based on the similarity between the waggle dance behaviours of real honey bees and the pheromone laying and following behaviours of ants. By the way the MCBA uses the positive feedback mechanism as distinct from the basic bees algorithm and other versions of the bee swarm optimization algorithms. The performance of the proposed MCBA is tested on a set of well-known test functions through a set of computational study, which contains comparison to some other standard meta-heuristics, cooperative approaches and ant-related approaches. The experimental results indicate the effectiveness of the proposed MCBA.     

Swarm-intelligent foraging in honeybees: benefits and costs of task-partitioning and environmental fluctuations

For honeybee colonies, it is crucial to collect nectar in an efficient way. Empiric experiments showed that the process of decision making, which allows the colony to select the optimal nectar source, is based on individual decisions. These decisions are made by returning nectar foragers, which alter their dancing behaviours based on the nectar source’s quality and based on the experienced search time for a receiver bee. Nectar receivers, which represent a shared limited resource for foragers, can modulate the foraging decisions performed by the colony. We investigated the interplay between foragers and receivers by using a multi-agent simulation. Therefore, we implemented agents which are capable of a limited set of behaviours and which spend energy according to their behaviour. In simulation experiments, we tested colonies with various receiver-to-forager ratios and measured colony-level results like the emerging foraging patterns and the colony’s net honey gain. We show that the number of receivers prominently regulates the foraging workforce. All tested environmental fluctuations are predicted to cause energetic costs for the colony. Task-partitioning additionally influences the colony’s decision-making concerning the question whether or not the colony sticks to a nectar source after environmental fluctuations.     

自主式微小型移动机器人群体行为进化的研究

自主式微小型移动机器人群体面临的一些环境常常是未知的、无结构的,同时由于其 自身体积大小的限制,在目前的工业水平上也很难在其上安装一些较为先进的传感器,以致 机器人仅能获取局部的信息,这些原因使得采用传统基于任务的设计方法将十分困难,而采 用基于行为的设计方法时,也很难保证所设计的机器人行为的有效性,为此本文采用了遗传 算法,随机产生了机器人群体中各初始个体的障碍物回避行为及机器设备故障排除行为,当 群体在特定的工作环境中仿真运行时,根据环境的情况和所需实现的任务,使群体行为性能 达到了较为优化的目的．     

改进的人工蜂群算法在神经网络中的应用

人工蜂群算法是模拟蜜蜂采蜜行为而提出的一种新的启发式仿生算法,属于典型的群体智能算法。提出了一种改进的人工蜂群算法,并利用改进后的人工蜂群算法来优化传统BP算法（神经网络算法中的误差方向传播算法）中网络参数的权值。实验结果证明该优化算法提高了BP神经网络收敛解的精度,加快了BP神经网络收敛速度。     

On the performance of artificial bee colony (ABC) algorithm

Artificial bee colony (ABC) algorithm is an optimization algorithm based on a particular intelligent behaviour of honeybee swarms. This work compares the performance of ABC algorithm with that of differential evolution (DE), particle swarm optimization (PSO) and evolutionary algorithm (EA) for multi-dimensional numeric problems. The simulation results show that the performance of ABC algorithm is comparable to those of the mentioned algorithms and can be efficiently employed to solve engineering problems with high dimensionality.     

基于操作风险的双模式传感器管理方法

基于风险理论研究同时面向目标检测和跟踪任务的传感器管理方法.首先,定义目标检测风险和目标跟踪风险,并分别给出计算方法;其次,以目标检测风险最小化为目标函数建立传感器部署模型,以目标检测风险和目标跟踪风险之和最小化为目标函数建立传感器调度模型,且该调度发生在前面传感器部署模型建立的传感器网络之上;然后,针对模型的求解,同时为克服基本人工蜂群算法易陷入局部最优的缺点,提出改进的双向轮盘赌-粒子群-蜂群算法;最后,通过仿真验证模型和算法的有效性.     

基于自组织劳动分工的边云协同任务调度与资源缓存算法

针对边缘计算环境中,边缘设备的计算和存储资源有限的问题,探讨高效的边云协同任务调度和资源缓存策略,研究自组织劳动分工群智能算法模型机理,并以此为基础,提出基于蜂群劳动分工“激发-抑制”模型的边云协同任务调度算法(edge cloud collaborative task scheduling algorithm based on bee colony labor division‘activator-inhibitor’ model, ECCTS-BCLDAI)和基于蚁群劳动分工“刺激-响应”模型的边云协同资源缓存算法(edge cloud collaborative resource caching algorithm based on ant colony labor division ‘stimulus-response’ model,ECCRC-ACLDSR).仿真实验结果表明:所提出的ECCTS-BCLDAI任务调度算法在降低平均任务执行时长、减少边云协同费用上相较于传统算法有更好的表现;所提出的ECCRC-ACLDSR资源缓存算法在降低任务平均时长、优化网络带宽占用率、减少...     

基于ABC-SVM的考生行为自动识别

针对支持向量机在考生行为自动识别中的参数优化问题,提出了一种人工蜂群算法优化支持向量机的考生行为自动识别方法。首先将支持向量机参数编码成为人工蜂群的蜜源,以考生行为识别正确率作为搜索目标,然后通过人工蜂群之间的信息交流和共享找到支持向量机的最优参数,并建立最优考生行为识别模型,最后采用仿真实验测试已建立考生行为识别模型的性能。实验结果表明,本文方法不仅提高了考生行为识别的正确率,而且加快了考生行为识别的速度,可以很好的满足考生行为自动识别实时性要求。     

A hybrid multi-objective tour route optimization algorithm based on particle swarm optimization and artificial bee colony optimization

Computational intelligence techniques have widespread applications in the field of engineering process optimization, which typically comprises of multiple conflicting objectives. An efficient hybrid algorithm for solving multi-objective optimization, based on particle swarm optimization (PSO) and artificial bee colony optimization (ABCO) has been proposed in this paper. The novelty of this algorithm lies in allocating random initial solutions to the scout bees in the ABCO phase which are subsequently optimized in the PSO phase with respect to the velocity vector. The last phase involves loyalty decision-making for the uncommitted bees based on the waggle dance phase of ABCO. This procedure continues for multiple generations yielding optimum results. The algorithm is applied to a real life problem of intercity route optimization comprising of conflicting objectives like minimization of travel cost, maximization of the number of tourist spots visited and minimization of the deviation from desired tour duration. Solutions have been obtained using both pareto optimality and the classical weighted sum technique. The proposed algorithm, when compared analytically and graphically with the existing ABCO algorithm, has displayed consistently better performance for fitness values as well as for standard benchmark functions and performance metrics for convergence and coverage.     

改进人工蜂群算法求解分布式柔性作业车间调度问题

针对分布式柔性作业车间调度问题的特点,提出一种改进人工蜂群算法.首先,建立以最小化最大完工时间为优化目标的分布式柔性作业车间调度优化模型;然后,改进基本人工蜂群算法以使其适用于求解分布式柔性作业车间调度问题,具体的改进包括设计一种包含三维向量的编码方案,结合问题特点针对性地设计多种策略用于种群初始化,在雇佣蜂改良搜索操作中设计多种有效的进化操作算子,并在跟随蜂搜索操作中引入基于关键路径的局部搜索算子以提升算法的局部搜索能力;最后,利用扩展柔性作业车间通用测试集得到的测试数据设计实验验证算法性能,使用正交试验法优化算法参数设置.仿真实验结果表明,改进后的人工蜂群算法能有效求解分布式柔性作业车间调度问题.     

混沌搜索策略的改进人工蜂群算法

针对人工蜂群算法的蜂群缺乏多样性、全局和局部搜索能力差及收敛速度较慢,提出一种基于混沌搜索策略的改进人工蜂群算法。该算法通过载波映射,由混沌-决策变量的变换,产生新的邻域点,为采蜜蜂和被招募的观察蜂提供了更广阔的搜索空间和更优质的位置蜜源,增强蜂群多样性;同时,引进侦查蜂局部蜜源搜索较好地解决了算法易陷入局部极小的问题,改善了人工蜂群算法的收敛性能。最后由6个标准测试函数的仿真验证,得到基于混沌搜索策略的人工蜂群算法性能明显优于标准人工蜂群算法。     

Applications of abduction: testing very long qualitative simulations

We can test a theory of "X" by checking if that theory can reproduce known behavior of "'X." In the general case, this check for time-based simulations is only practical for short simulation runs. We show that, given certain reasonable language restrictions, the complexity of this check reduces to the granularity of the measurements. That is, provided a very long simulation run is only measured infrequently, this check is feasible.     

蜂群算法研究综述*

蜂群算法是一种模仿蜜蜂繁殖、采蜜等行为的新兴的群智能优化技术,近几年备受研究者关注。初步探讨了蜂群算法的理论基础,详细论述了基于蜜蜂繁殖行为和采蜜行为的两类蜂群算法的生物学机理及其最常见算法的应用研究情况,并分析比较了遗传算法、蚁群算法、粒子群算法和蜂群算法的优缺点、适用范围及性能。最后,总结了现有蜂群算法存在的问题,并指出其未来的研究方向。     

基于蜂群算法的多维QoS云计算任务调度

针对云计算环境下用户日益多样化的QoS需求和高效的资源调度要求,提出了基于改进蜂群算法的多维QoS云计算任务调度算法,其中包括构建任务模型、云资源模型和用户QoS模型。为了获得高效的调度,引入蜂群算法。针对该算法在后期收敛速度变慢且易陷入局部最优的问题,引入收益比、跟随比概念及当前个体最优值及随机向量,避免"早熟"现象的出现。通过实验仿真,将该算法HEFT与和ABC算法进行比较,实验表明,该算法能获得较高的调度效率和用户满意度。     

基于人工蜂群算法的电网故障诊断

针对电网故障诊断中的0-1规划问题,从代数和几何角度优化了人工蜂群算法。仿真结果表明,人工蜂群算法具有可行性和合理性,并且综合性能显著优于传统的遗传算法;在两种人工蜂群算法中,基于几何思想的人工蜂群算法具有更好的稳定性和搜索能力,更加适用于对稳定性和精准度要求很高的场合。