一种结合层次分析法的改进型主成分评价法及其应用

主成分分析法和层次分析法是计算多目标综合性指标中常用的方法.主成分分析法偏重于对数据所包含信息的处理,而层次分析法更依靠于专家在设定权重过程中的人为经验.通过在主成分分析法中引入层次分析法中的判断矩阵,提出了一种改进型主成分分析法.通过对评选优秀篮球教练员的实证分析,验证了新方法的优越性.     

基于局部线性嵌入与主成分分析的优化的RBF降水预报模型

针对用主成分分析算法对非线性数据降维,存在丢失局部结构数据信息的不足,提出了将主成分分析与局部线性嵌入相结合的正交投影降维算法。首先采用主成分分析方法降维可算出特征空间矩阵,然后采用局部线性嵌入方法降维后提取特征空间矩阵,再将这两种方法获得的特征空间矩阵正交投影进行降维的主要信息作为预报因子,最后利用优化的径向基函数RBF建立网络模型,以此对广西5月区域日降水量进行降水预报,结果显示,该模型在预报性能上优于同期的T213日降水预报。     

基于主成分的稀疏贝叶斯信用分类研究

针对传统信用评价方法分类精度较低、数据集属性变量间存在相关性等问题,提出基于主成分分析的稀疏贝叶斯学习（PCA-SBL）算法。首先对数据集特征变量进行主成分分析,使降维后的变量无相关性|其次,对主成分分析后的数据进行稀疏贝叶斯分类|最后将 PCA-SBL 分类方法分类精度与传统分类方法精度进行比较。分析发现,在 German Credit Data 和 Australian Credit Data 上,与传统 KNN、朴素贝叶斯、SVM、随机森林、决策树相比,改进的 SBL 算法分类精度平均提高了 5.26%、4.65%、2.11%、2.125%、4.66%,与稀疏贝叶斯学习算法（SBL）相比,平均提高 0.965%,从而证明 PCA-SBL 算法具有更高的分类效果。     

FSVM在老年痴呆数据分析中的应用

支持向量机是人工智能研究领域中的重要课题,但该算法不能够对复杂高维的生物医学数据进行准确的分类,而FSVM方法能够利用模糊性对标记样本数据进行较准确的归类,故采用FSVM算法对老年痴呆数据进行分析.通过特征提取方法对数据进行降维,采用主成分分析法提取出数据的11个主成分,并筛选前3个主成分和前2个主成分分别进行分类模型的训练.利用基于FSVM的模糊C均值聚类方法将老年痴呆的121个样本分成了正负两个类别,实验结果表明,FSVM算法能够有效地分析老年痴呆数据.     

人脸识别算法分析与研究

首先针对两种常用的人脸识别方法:改进主成分分析算法与隐马尔科夫模型算法进行了分析和比较:改进主成分分析算法能更好的保持样本间的分类信息,适合分类识别研究,同一人的面部经过隐型马尔科夫模型算法处理能够看作一种状态产生的一系列的实现,而不同的HMM是用来表现不同的人脸等等,然后分别对它们进行了算法改进,最后对这两种算法进行了总结和展望.     

基于梯度下降法与特征值分解的测量矩阵优化方法

压缩感知理论突破了香农采样定律中对信号采样频率的限制.测量矩阵的构造是压缩感知理论中一个重要的部分.减小传感矩阵的互相干系数,选择性能较好的测量矩阵,能够提高重构质量.设计了EigGrd算法,Gram矩阵是由测量矩阵和稀疏变换矩阵乘积构成,使用特征值分解对Gram矩阵进行初始化,在稀疏变换矩阵固定的情况下,利用梯度下降...     

统计分析中主成分分析法与应用

在分析复杂社会经济现象和自然现象过程中,采用主成分分析法,将原始指标组合成新的相互独立的综合指标,利用线性函数理论和处理方法,求出主成分方程后再将原始指标进行标准化处理,求出综合评价值,而后对经济现象做出综合性评价分析。     

基于MATLAB的复合因子方差分析与主成分分析算法

方差分析与主成分分析是工程计算领域重要的统计分析方法,特别是在医学研究、科学试验、生物遗传测序等方面有广泛应用,本文基于MATALB工具,对双因子方差分析、主成分分析两种主要类型进行理论描述和算法设计,从而实现对抽样样本的二维数据分析.     

电能质量信号的KSVD-NRAMP归一化自适应稀疏重构算法

针对稀疏重构算法在电能质量重构中存在实时性差、重构精度低的问题,提出一种基于特征向量归一化的K奇异值分解(KSVD-NRAMP)自适应稀疏重构算法。算法针对电能质量信号的非线性非稳态特征,采用迭代式匹配追踪得到信号稀疏特征矩阵,然后对矩阵进行归一化处理,量化特征向量,加快函数收敛速度。接着对得到的矩阵原子进行奇异值分解,改善迭代步长波动造成信号重构精度低的问题,最后构建信号的高斯随机矩阵并重构信号。当信号压缩率在50%~90%时,该算法重构信噪比其它重构算法的重构信噪比高出26dB~28dB。实验结果表明,该算法重构精度更高且计算时间短,为电能质量信号的研究提供了一种新思路。     

一种基于频域的欠定瞬时混合2步盲分离法（英文）

为了减少传统的截断混合矩阵求逆(ITMM)算法在个别时频点会丢失数据或者产生噪声信号的概率,提出了一种基于频域的2步欠定瞬时盲分离算法.由于现实中存在大量软稀疏(稀疏度不是很大)混合信号,将分离过程分解为ITMM和矩阵补偿2个步骤.首先估计出混合矩阵和利用经典的ITMM算法对混合信号进行初步恢复,然后对初步估计的信号时频矩阵进行矩阵补偿处理,从而达到修补丢失数据和去除多余数据(去噪)的效果.实验仿真验证了所提出的2步分离法相对于传统的ITMM算法能够得到更好的分离效果.此外,对算法的时耗问题进行了研究,相对于传统的ITMM算法,所提算法的时耗增加不到四分之一,却能够得到更好的分离效果.     

构造最短路径树的动态算法综述

对于以链路状态（Link state）为路由协议的大规模网络来说,根据网络流量和拓扑结构的变化来快速调整自身路由表的信息,是非常关键的问题.网络中链路状态发生变化有四种情况：链路费用的增加,链路费用的减少,节点失效,新节点的加入.回顾了以往所提出的具有关键意义的动态算法,分析了它们的创新点;其次,指出了相关文献中提出的应对网络拓扑变化的处理算法的不足之处,并提出了综合处理各种情况的思路.     

Algorithm for Delay-Constrained Minimal Cost Group Multicasting

Group multicast routing algorithms satisfying quality of service requirements of real-time applications are essential for high-speed networks. A heuristic algorithm was presented for group multicast routing with bandwidth and delay constrained. A new metric was designed as a function of available bandwidth and delay of link, And source-specific routing trees for each member were generated in the algorithm by using the metric, which satisfy member＇s bandwidth and end-to-end delay requirements. Simulations over random network were carried out to compare the performance of the proposed algorithm with that from literature. Experimental results show that the algorithm performs better in terms of network cost and ability in constructing feasible multicast trees for group members. Moreover,the algorithm can avoid link blocking and enhance the network behavior efficiently.     

无线传感器网络路由协议研究进展

无线传感器网络作为一种新型的以采集数据为目的、高密度、自组织、低数据率的短距离无线通信网络,在国外相关研究领域一直是热点.文章概要地介绍了无线传感器网络的特点、应用前景以及研究热点,强调了无线传感器网络的路由协议设计方式不同于现有的有线及无线网络.特别阐明了作为一个以环境监测为主要应用的自组织网络,在现有器件的条件下,网络寿命这一关键参数主要取决于对传感器节点的能耗有重大影响的路由协议,着重研究了如何从网络层的路由协议和算法设计着手实现功率控制,以达到节约能耗、延长网络寿命这一目的.     

Cross-layer design of energy-saving AODV routing protocol

Since most ad hoc mobile devices today operate on batteries, the power consumption becomes an important issue. This paper proposes a cross-layer design of energy-aware ad hoc on-demand distance vector (CEAODV) routing protocol which adopts cross-layer mechanism and energy-aware metric to improve AODV routing protocol to reduce the energy consumption and then prolong the life of the whole network. In CEAODV, the link layer and the routing layer work together to choose the optimized transmission power for nodes and the route for packets. The link layer provides the energy consumption information for the routing layer and the routing layer chooses route accordingly and conversely controls the link layer to adjust the transmission power. The simulation result shows that CEAODV can outperform AODV to save more energy. It can reduce the consumed energy by about 8% over traditional energy-aware algorithm. And the performance is better when the traffic load is higher in the network.     

Adaptive ant-based routing in wireless sensor networks using Energy*Delay metrics

To find the optimal routing is always an important topic in wireless sensor networks （WSNs）. Considering a WSN where the nodes have limited energy, we propose a novel Energy^＊Delay model based on ant algorithms （＂E＆D ANTS＂ for short） to minimize the time delay in transferring a fixed number of data packets in an energy-constrained manner in one round. Our goal is not only to maximize the lifetime of the network but also to provide real-time data transmission services. However, because of the tradeoff of energy and delay in wireless network systems, the reinforcement learning （RL） algorithm is introduced to train the model. In this survey, the paradigm of E＆D ANTS is explicated and compared to other ant-based routing algorithms like AntNet and AntChain about the issues of routing information, routing overhead and adaptation. Simulation results show that our method performs about seven times better than AntNet and also outperforms AntChain by more than 150% in terms of energy cost and delay per round.     

复杂感知网络风险控制算法的设计

承载了大数据业务的复杂感知网络在满足业务接入的同时如何应对网络节点面临的业务失效风险,已成为业界研究的热门问题。风险控制算法克服了传统算法在实施风险评估时对节点较高的依赖性。风险控制算法通过构建数学模型为展开信息域参数的计算和更新,并制定筛选策略来锁定潜在风险的异常业务质量(QoS)目标节点。经验证,该算法具有良好的可行性。     

基于Adhoc能量均衡的AODV协议改进

针对Adhoc网络中移动节点能量受限的问题,考虑节点剩余能量和节点能量消耗速率两方面因素,对AODV协议,在选路机制,hello机制几个方面作了改进,改进后的路由协议能够有效均衡负载,保护低能量节点,延长网络生存时间。     

Super Node Routing Strategy in Content-Centric Networking

There were two strategies for the data forwarding in the content-centric networking(CCN): forwarding strategy and routing strategy. Forwarding strategy only considered a separated node rather than the whole network performance, and Interest flooding led to the network overhead and redundancy as well. As for routing strategy in CCN, each node was required to run the protocol. It was a waste of routing cost and unfit for large-scale deployment.This paper presents the super node routing strategy in CCN. Some super nodes selected from the peer nodes in CCN were used to receive the routing information from their slave nodes and compute the face-to-path to establish forwarding information base(FIB). Then FIB was sent to slave nodes to control and manage the slave nodes. The theoretical analysis showed that the super node routing strategy possessed robustness and scalability, achieved load balancing,reduced the redundancy and improved the network performance. In three topologies, three experiments were carried out to test the super node routing strategy. Network performance results showed that the proposed strategy had a shorter delay, lower CPU utilization and less redundancy compared with CCN.     

Two-stage evolutionary algorithm for dynamic multicast routing in mesh network

In order to share multimedia transmissions in mesh networks and optimize the utilization of network resources, this paper presents a Two-stage Evolutionary Algorithm （TEA）, i.e., unicast routing evolution and multicast path composition, for dynamic multicast routing. The TEA uses a novel link-duplicate-degree encoding, which can encode a multicast path in the link-duplicate-degree and decode the path as a link vector easily. A dynamic algorithm for adding nodes to or removing nodes from a multicast group and a repairing algorithm are also covered in this paper. As the TEA is based on global evaluation, the quality of the multicast path remains stabilized without degradation when multicast members change over time. Therefore, it is not necessary to rearrange the multicast path during the life cycle of the multicast sessions. Simulation results show that the TEA is efficient and convergent.     

基于ONE平台传染路由算法合作性分析

针对机会网络的路由算法基本上是考虑完全合作情况下进行设计的.本文对节点的合作性进行了分析,在机会网络环境ONE平台上,通过不同的转发概率对传染路由算法Epidemic的合作性进行了测试和分析.仿真结果表明,节点之间的合作性对路由算法的性能有着不同程度的影响.