共查询到20条相似文献，搜索用时 203 毫秒
1.
人工鱼群算法是一种新兴的元启发式仿生群集智能优化算法。在分析生物鱼类特点的基础上,对人工鱼个体的模型进行了总结,概括了人工鱼群算法的参数改进研究现状以及混合鱼群算法的研究。对人工鱼群算法的应用领域进行了总结,并提出了今后人工鱼群算法的研究方向。 相似文献
2.
3.
萤火虫算法是一种新的智能算法,被广泛的使用在优化问题的解决方面,针对算法存在收敛速度慢,求解精度低的缺点,提出了引入人工鱼群算法中的聚群行为和追尾行为改进算法,仿真实验采用3个经典测试函数来测试本文算法和萤火虫算法,实验结果说明了本文算法能够有效的提高性能。 相似文献
4.
5.
人工蜂群算法是一种新型的元启发式仿生算法。算法中每个蜜蜂都可以看作一个智能体,通过蜂群个体间协同作用达到群体智能的效果。在分析蜜蜂群采蜜原理的基础上,将求解函数优化问题的过程转化为蜜蜂群寻找优良蜜源的过程,对函数进行求解。文中采用了13种不同维数和多样复杂的测试函数来验证此算法,再与其他几种算法进行比较,实验结果表明此方法寻优效果最好,能够更好的得到函数最优值。 相似文献
6.
针对旅行商(traveling salesman problem,TSP)是一个NP问题,本文使用改进的人工鱼群算法(improved artificial fish swarm algorithm,AFSA)进行线路的优化.首先阐述了TSP问题基本概念,其次针对基本的人工鱼群算法分别优化:(1)使用Laplace进行种群初始化,提高种群多样性;(2)使用正弦余弦算法取代觅食行为,保证算法在全局和局部范围内具有一定的平衡性;(3)利用人工蜂群算法对每一次迭代后的个体进行筛选,保证了算法的解的质量.仿真实验中本文算法在TSP路径规划方面具有一定的效果. 相似文献
7.
针对当前可用输电能力计算存在着易早熟、收敛速度慢等问题,提出了一种改进的人工鱼群算法进行求解,提高了计算结果的准确性、收敛性能以及计算速度。人工鱼群算法是群智能随机全局优化技术,该算法引入了禁忌搜索算法中的记忆功能,可以有效避免迂回搜索并提高计算的效率。在对人工鱼搜索的机制进行研究的基础上,对寻优行为进行改进,采用最好解优先选择前进的路径并以排序选择的方式接受劣解,从而进一步提高算法的效率。修改过的IEEE 30节点系统的计算结果表明,改进人工鱼群算法用于可用输电能力计算是有效的,具有良好的全局收敛性能和较高的计算效率。 相似文献
8.
蛙跳算法是一种启发式的智能算法,在优化问题中具有广泛的应用,针对该算法求解精度低,收敛速度慢,容易陷入局部的缺点,从4个方面提出了改进:(1)引入Tent混沌来改进蛙跳的种群初始化;(2)通过最大化搜索策略提高局部搜索;(3)最差个体中引入柯西因子进行优化;(4)采用模式搜索来优化最优个体.通过5个测试函数说明本文的算法能够有效的提高算法的性能. 相似文献
9.
提出了一种基于感知域的鲁棒性语音认证算法,将语音的感知特性与签名算法相结合,在满足内容认证和身份认证的同时,能够有效地抵抗通信噪声微扰.算法基于语音的掩蔽效应和非线性效应等人耳感知特性,着重去除其时频域掩蔽阈值下的冗余信息,进行非线性滤波后提取感知参数,并运用改进的Rainbow算法对这些语音参数进行签名.实验证明,该算法的唯一性和针对通信噪声的鲁棒性都很好,兼有Rainbow签名的安全性保证,可以满足语音通信中的鲁棒性认证要求. 相似文献
10.
11.
中国近年寒区地下水试验研究进展 总被引：1，自引：0，他引：1
占国土面积一半左右的寒区是中国重要的地理区域之一,由于特殊的低温环境,使得在寒区开展地下水赋存、运动和演化研究的过程中,比较倚重于试验基础。梳理分析可见,有关寒区地下水的试验研究可以大致归结为如下四类。①冻融过程中土壤水热盐迁移试验,这类试验数量最多,试验的目标内容在于监测、探究不同覆被/不同土质/不同冻融过程条件下土壤非饱和带水/热/盐单项或耦合迁移特征及其定量描述方法;②冻土水理性质试验,这类试验多结合寒区工程展开,其目的在于探究固/液二相不同组成条件下冻土的冻融特征参数与其工程力学性质的关系;③在东北、西北、青藏高原等寒区开展的具有显著地域特征和明确目标指向的应用类试验,主要针对各自区域的典型问题展开;④有关试验仪器、试验方法的研究。进一步梳理可知,中科院寒旱所和《冰川冻土》是国内支撑和交流寒区地下水试验研究的最重要的平台。 相似文献
12.
《Information processing & management》2023,60(2):103221
Disease spread control is a challenging task with growing importance in recent years. Infectious disease networks have been proven to be a helpful resource for controlling the epidemic by targeting a smaller population. However, the information on these networks is often imprecise, diffused, concealed, and misleading, making it challenging to obtain a complete set of real-world data, i.e., some links might be missing, which can be a risk to the widespread of the pandemic. The former studies on infectious disease networks ignore the influence of neighborhood missing links in the infectious disease network topology, thus massively targeting the irrelevant population, resulting in poor epidemic control performance. In this paper, to address such a problem, we study how a small portion of the population should be targeted with incomplete network information to effectively prevent the pandemic. We propose an algorithm, namely, the Neighborhood Relation Aware Network Dismantling Algorithm (NRAND), to efficiently address the infectious disease network’s dismantling problem. For comparison, four network dismantling strategies are employed in our experiments. An extensive empirical study of real-world networks suggests that the proposed algorithm NRAND’s dismantling performance is significantly greater than the state-of-the-art algorithms, indicating that NRAND can be a smarter option for dismantling real-world infectious disease networks. 相似文献
13.
《Information processing & management》2022,59(5):103004
Although the Knowledge Graph (KG) has been successfully applied to various applications, there is still a large amount of incomplete knowledge in the KG. This study proposes a Knowledge Graph Completion (KGC) method based on the Graph Attention Faded Mechanism (GAFM) to solve the problem of incomplete knowledge in KG. GAFM introduces a graph attention network that incorporates the information in multi-hop neighborhood nodes to embed the target entities into low dimensional space. To generate a more expressive entity representation, GAFM gives different weights to the neighborhood nodes of the target entity by adjusting the attention value of neighborhood nodes according to the variation of the path length. The attention value is adjusted by the attention faded coefficient, which decreases with the increase of the distance between the neighborhood node and the target entity. Then, considering that the capsule network has the ability to fit features, GAFM introduces the capsule network as the decoder to extract feature information from triple representations. To verify the effectiveness of the proposed method, we conduct a series of comparative experiments on public datasets (WN18RR and FB15k-237). Experimental results show that the proposed method outperforms baseline methods. The Hits@10 metric is improved by 8% compared with the second-place KBGAT method. 相似文献
14.
本文首先利用有限混合模型对前向神经网络的交叉覆盖算法进行优化,再将优化后的覆盖算法应用于已进行分词预处理的中文文本数据库。从实验结果来看,优化后的覆盖算法在测试精度上取得了令人满意的结果,10次实验所得到的平均精度除经济类外,其余都不同程度高于原覆盖算法处理同类数据的分类精度。 相似文献
15.
16.
17.
This paper investigates adaptive finite-time practical consensus protocols for a class of second-order multiagent systems with a positive odd power, nonsymmetric input dead zone and uncertain dynamics under a directed communication topology. In this study, three major steps are employed to address the existence of the positive odd power, nonsymmetric input dead zone and uncertain dynamics. Overall, based on the technique of adding one power integrator, useful preliminary results are obtained by configuring a suitable fraction power. Furthermore, to circumvent input dead-zone nonlinearity, an adaptive fuzzy logic (FL) method is used to estimate the width of the dead zone. Finally, the difficulty in designing finite-time practical consensus protocols for the multiagent systems with uncertain dynamics is handled by using radial basis function neural networks (RBFNNs) to approximate the related unknown nonlinear functions. Then, given some reasonable assumptions, it is shown that finite-time practical consensus of the second-order multiagent systems is obtained by using the proposed distributed control protocols and adaptive laws. In addition, the proper approach for selecting parameters is provided such that the neighborhood position error and parameter estimate errors for each agent converge to predesigned small regions of the origin in a finite time. The effectiveness of the developed algorithm is finally validated through a numerical simulation. 相似文献
18.
随着图像或视频的网络应用日益普及,各种各样的新型应用不断涌现.由于图像或视频在网络中传输时,网络本身的安全措施并不能完全阻止非法截取事件的发生,因此人们对于图像数据传输的有效性和安全性提出新的要求.提出一种新的方法,其基本思想是通过结合使用离散小波变换(DWT)、嵌入式零树小波编码(EZW)和高级加密标准(AES),在对需要传输的图像充分压缩的基础上,对编码码流加密置乱,从而同时达到有效和安全传输的目的.实验结果表明,该方法在保持较高压缩效率的同时,增强了码流在传输过程中的安全性. 相似文献
19.
中国省域农业碳生产率的空间分异特征及依赖效应 总被引：2，自引：0，他引：2
科学测度农业碳生产率并探究其空间关联状况是构建兼具差异化和协调性的碳减排政策的基石。本文对2001-2012年中国31个省（市、区）的农业碳生产率进行测度,在此基础上利用空间相关性指数对其空间相关性、聚类状况进行考察,并运用空间杜宾模型分析农业碳生产率变动的主要影响因素及空间效应。结果表明：①2001-2012年中国各省区农业碳生产率均呈现较为明显的提升趋势,除个别省域外,省域农业碳生产率与其所属地区的经济发展程度基本一致;与此同时,农业碳生产率区域间“异质化”与区域内“均质化”的趋势显现,且以地区间农业碳生产率的“分化”与“极化”的现象较为严重;②省域农业碳生产率存在着较强的空间自相关性,各省区农业产业结构对本地区农业碳生产率具有负向影响,农村教育水平和农业开放程度对其具有正向影响,而农业经济发展水平、受灾程度和农业公共投资对其影响不甚明显;此外,省域农业碳生产率在空间上存在较为明显的溢出效应,其中一省区农村教育水平和农业开放水平对邻域农业碳生产率的提高具有正向带动作用,农业经济发展水平对其则起到抑制作用,而农业产业结构、自然灾害和农业公共投资对周边地区农业碳生产率的影响并不明显。 相似文献
20.
Efficient depth selection for the implementation of noisy quantum approximate optimization algorithm
《Journal of The Franklin Institute》2022,359(18):11273-11287
Noise on near-term quantum devices will inevitably limit the performance of Quantum Approximate Optimization Algorithm (QAOA). One significant consequence is that the performance of QAOA may fail to monotonically improve with control depth. In principle, optimal depth can be found at a certain point where the noise effects just outweigh the benefits brought by increasing the depth. In this work, we propose to use the regularized model selection algorithm to identify the optimal depth with just a few iterations of regularization parameters. Numerical experiments show that the algorithm can efficiently locate the optimal depth under relaxation and dephasing noises. 相似文献