Description: 为了有效地应用遗传算法解决 鲁棒控制系统设计问题，将遗传算法与局部优化方法相结合，提出了基于降维扫描方法的自适应多目标遗传算法（DRSA-MOGA）。通过引入适应度函数标准化方法、基于最优Pareto解集搜索的降维扫描方法和适应度函数自适应调整方法，提高了算法的全局优化性能和局部搜索能力。仿真结果表明，DRSA-MOGA算法在不损失解的均匀度的情况下可以达到很高的逼近度-For effective application of genetic algorithms to solve robust control system design problems, genetic algorithms and local optimization method, based on reduced-order adaptive scanning method multi-objective genetic algorithm (DRSA-MOGA). Fitness function through the introduction of standardized methods, based on the Pareto optimal solution set of search methods and dimensionality reduction scan fitness function adaptive adjustment method, the algorithm improve the performance of global optimization and local search capabilities. The simulation results show that, DRSA-MOGA algorithm solution without loss of uniformity can be achieved under a high degree of approximation Platform: |
Size: 14336 |
Author:cekong |
Hits:
Description: An Improved PSO Algorithm to Optimize BP Neural Network
Abstract
This paper presents a new BP neural network
algorithm which is based on an improved particle swarm
optimization (PSO) algorithm. The improved PSO (which
is called IPSO) algorithm adopts adaptive inertia weight
and acceleration coefficients to significantly improve the
performance of the original PSO algorithm in global
search and fine-tuning of the solutions. This study uses the
IPSO algorithm to optimize authority value and threshold
value of BP nerve network and IPSO-BP neural network
algorithm model has been established. The results
demonstrate that this model has significant advantages
inspect of fast convergence speed, good generalization
ability and not easy to yield minimal local results Platform: |
Size: 252928 |
Author:dasu |
Hits:
Description: Choice of Wavelets for Image Compression
In wavelet-based image coding the choice of wavelets is crucial and determines the coding
performance. Current techniques use computationally intensive search procedures to find the optimal basis (type,
order and tree). In this paper, we show that searching for optimal wavelet does not always offer a substantial
improvement in coding performance over "good" standard wavelets. We propose some guidelines for determining
the need to search for the "optimal" wavelets based on the statistics of the image to be coded. In addition, we
propose an adaptive wavelet packet decomposition algorithm based on the local transform gain of each stage of
the decomposition. The proposed algorithm provides a good coding performance at a substantially reduced
complexity. Platform: |
Size: 76800 |
Author:hussam |
Hits:
Description: 矩形件优化排样是一个NPC问题，在工业界有着广泛的应用．针对该问题，提出一种自适应模拟退火遗传算法．采用一种基于环形交叉算子和环形变异算子的自适应遗传算法来自动调整交叉和变异概率；同时引入模拟退火算法对个体适应度大于平均适应度的个体进行退火处理．自适应模拟退火遗传算法充分发挥了自适应遗传算法与模拟退火算法各自的全局搜索能力与局部搜索能力．对比实验表明，该算法结合改进的最左最下布局算法解决矩形件优化排样问题更加有效．-Optimal layout is rectangular pieces of a NPC problem, in the industrial sector has a wide range of applications. For this problem, an adaptive simulated annealing genetic algorithm. Using a ring-based crossover operator and mutation operator ring adaptive genetic algorithm to automatically adjust the crossover and mutation and introduce simulated annealing is greater than the average fitness of the individual fitness of individuals annealing. Adaptive simulated annealing genetic algorithm fully adaptive genetic algorithm and simulated annealing their global search capability and local search capabilities. Comparative experiments show that the algorithm is left with the most improved layout algorithm to solve the most under the optimal nesting rectangular pieces of the problem more effectively. Platform: |
Size: 471040 |
Author:木易 |
Hits:
Description: 根据DE自适应交叉率的EA方法用于人口刷新和本地搜索-An EA based on DE with adaptive crossover rate, population refresh and local search Platform: |
Size: 10240 |
Author:赵雯 |
Hits:
Description: 为了平衡粒子群算法的全局搜索能力和改良局部能力，采用非线性的动态惯性权重即自适应权重法。给出一个用自适应权重的粒子群算法求多元复杂函数的最小值实例。-To balance the PSO global search capability and improved local capacity, the use of non-linear dynamic adaptive inertia weight that the weighting method. Gives an adaptive weights PSO seeking the minimum of multiple instances of complex functions. Platform: |
Size: 1024 |
Author:suzhiwei |
Hits:
Description: This paper is a survey of greedy randomized adaptive search procedures
(GRASP). GRASP is a multi-start or iterative procedure where each GRASP iteration con-
sists of a construction phase, where a feasible solution is constructed, followed by a local
search procedure that finds a locally optimal solution. The construction phase of GRASP
is essentially a randomized greedy algorithm. Repeated applications of the construction
procedure yields diverse starting solutions for the local search. We review a basic GRASP,
followed by enhancements to the basic procedure. We conclude by surveying operations
research and industrial applications of GRASP. Platform: |
Size: 106496 |
Author:Nydiron |
Hits:
Description:
基于dijkstra和广度搜索的加权有向图有必经点的点对点的最短路径算法，路径必须经过要求的必经点，且不成环。
该算法采用了一种自适应调整的方法，经过多次迭代，使解收敛。 但只是寻找了一个略优的可行解（每次迭代都基于贪婪算法寻找），不能保证最优解。而且如果图过于稀疏，因为收敛速度过快，可能导致问题无解（收敛于一个局部最优解，没有经过所有点）。 解决相对稠密的图（每个点的平均出入度4以上），表现良好。
备注：里面有一个QT的工程，可以直接打开（源码里没用QT的库）-Weighted Dijkstra and breadth first search based on a shortest path algorithm must point to point to the map, the path must pass through points, and not a ring.
This algorithm adopts an adaptive method to adjust, after several iterations, the convergence of solution. But only to find a slightly better feasible solution (each iteration is based on the greedy algorithm to find), can not guarantee the optimal solution. And if the graph is too sparse, because the convergence speed is too fast, it may lead to the problem of no solution (convergence to a local optimal solution, not after all points). To solve the relatively dense graphs (each entry point average above 4), good performance. Platform: |
Size: 16384 |
Author:凌凯 |
Hits:
Description: 该算法既保留了遗传算法的搜索特性，又利用了免疫算法的多机制求解多目标函数最优解的自适应特性，在很大程度上避免了“早熟”，收敛于局部极值。
生物体的免疫系统是一个高度进化、复杂的系统，它能自适应地识别和排除入侵肌体的抗原性异物，保护机体免受损害及维持内坏境稳定，并具有学习、记忆和自适应调节的能力。当抗原入侵时，免疫系统通过自体耐受对‘自己’和‘非己’进行识别，并产生最恰当的抗体排除抗原，通过抗体与抗体之间、抗原与抗体之间的相互刺激和抑制关系，降低抗原对免疫细胞的刺激，抑制抗体的过度分化、增殖，保证免疫平衡并维持抗体的多样性。同时在免疫过程中将产生抗体的部分细胞作为记忆细胞保存下来，对于今后侵入的同类抗原，相应的记忆细胞受到激发而产生大量的抗体。为提高生物体的免疫机能，医学上往往根据抗原性异物提取疫苗给生物体接种，接种过的生物体由于免疫细胞预先获得了抗原染色体的特征信息，因而在类似抗原入侵时，能迅速产生亲和度很高的抗体，有效抵御入侵。-The search algorithm only retains the characteristics of genetic algorithms, and use multiple mechanisms of immune algorithm for solving multi-objective characteristics of adaptive optimal solutions, in large part to avoid the " premature" , converge to local minima. Organism' s immune system is a highly evolved, complex system which adaptively identify and remove foreign matter intrusion antigenic body, protecting the body injury and maintain internal stability bad environment, and has learning, memory and adaptive Ability. When the antigen invasion of immune system tolerance to autologous ' own' and ' non-self' to identify and produce the most appropriate antigen antibody excluded by between antibody and antibody, antigen and antibody mutual stimulation and inhibition of the relationship between reduce the antigen to stimulate immune cells, antibodies inhibit excessive differentiation, proliferation, immune balance and ensure the maintenance of antibody dive Platform: |
Size: 110592 |
Author:snowtiger |
Hits:
Description: GRASP (greedy randomized adaptive search Procedure) is an algorithm commonly applied to problems of combinatorial optimization. As various construction methods, the application of grasp is to create an initial solution and then perform a local search to improve the quality of the solution. Your differential to other methods is the generation of initial solution, based on the first three stages of its acronym in English: greedy (Greedy), random (trial) and adaptive (Adaptive). Platform: |
Size: 1024 |
Author:wesleymagasat
|
Hits:
Search - adaptive local search