基于遗传算法优化神经网络的藻类繁殖状态软测量方法

为了提高BP神经网络模型对海洋藻类生长状态软测量的准确性,提出了一种基于遗传优化算法优化BP神经网络的软测量方法.利用遗传算法优化BP神经网络的权值和阈值,然后训练BP神经网络预测模型以求得最优解,再将该预测结果与传统BP网络预测模型的预测结果进行对比.对仿真结果进行有效性验证后,结果表明,通过这种软测量方法,经遗传算法优化后的BP神经网络可以在更短的时间里创造更高的预测准确性,大大提高了对海洋藻类生长状态预测的效率.     

集成电路版图自动设计的进展

<正> 由于集成电路的发展已进入超大规模集成电路阶段,因此需要高度的设计自动化技术来满足设计周期和设计正确性的要求。目前主要研究的课题有下列几方面。 (1)多目标优化算法 早期研究布局和布线算法时集中在单目标优化。作为整个布图优化目标来说,这样的要求是不够的。但是,多目标优化算法太复杂,不能处理规模较大的电路。 (2)布图的专家系统 专家系统是把专家知织或试验总结为规律,置于系统中作为处理问题之用。用专家系统处理多目标优化问题可能是一种较为现实的方法。     

基于改进PSO-BP神经网络的回弹预测研究

在V形自由折弯中,准确地预测板料回弹,有利于实际生产中精确地控制回弹以提高生产效率。由于板料回弹的影响因素众多,呈现出复杂的非线性变化特征,采用传统的BP神经网络难以满足高精度的预测要求,因此为了进一步有效预测板料的回弹,提出基于改进粒子群算法优化的BP神经网络预测模型。对标准粒子群算法的缺陷进行改进,利用改进粒子群算法的全局搜索能力对BP神经网络的权值和阈值进行优化求解,提高了BP神经网络预测模型的收敛精度和泛化能力。将改进PSO-BP神经网络预测模型应用在板料回弹预测中,并与LM-BP神经网络预测模型进行对比仿真,结果表明改进PSO-BP神经网络预测模型具有更高的非线性拟合优度和预测精度。     

遗传算法优化BP神经网络的大功率LED结温预测

将遗传算法(GA)与BP神经网络相结合,对研发的120W LED双进双出的射流冲击水冷散热系统中LED阵列的结温进行预测。采用GA优化BP网络的权值和阈值,利用BP算法训练网络,改善了单独使用BP网络容易陷入局部极小值和收敛速度慢的缺点。并且在训练过程中为了使网络输出有足够长的空间,改进了GA的数据处理。结果表明,经GA优化的BP神经网络较使用Levenberg-Marquardt(LM)算法优化的BP神经网络的大功率LED结温预测精确度提高了14.14%,且预测效果较稳定。GA和BP神经网络相结合的结温预测模型较传统的结温测量方法更能掌握散热结构设计的主动性,对大功率LED寿命的延长有较高的实用价值。     

基于自适应优化多层GA-BP的脱硫效率预测模型

针对湿法脱硫装置运行参数多且相互高度耦合,脱硫效率定量描述困难的问题,以及传统BP网络存在的问题,提出一种基于自适应优化多层GA-BP的脱硫效率预测模型。将基于主成分分析后的降维数据作为输入变量,采用双层基因优化BP网络结构,并引入自适应变异和交叉概率,对BP网络初始权值、阈值进行改进,利用优化后的网络对脱硫效率进行预测。该模型已成功应用于大唐三门峡1000MW机组脱硫装置,结果表明：实际脱硫效率平均绝对误差小于0.5%,较传统BP算法与GA-BP算法分别降低25.82%和16.10%,具有更高的预测精度。     

基于划分的力矢量布局算法

提出了一个全新的基于划分的力矢量布局算法.针对大规模集成电路的布局问题,采用基于并行结群技术的递归划分方法进行分解解决,并结合改进的力矢量算法对划分所得的子电路进行迭代布局优化.通过对MCNC标准单元测试电路的实验,与FengShui布局工具相比,该布局算法在花费稍长一点的时间内获得了平均减少12%布局总线长度的良好效果.     

基于划分的力矢量布局算法

提出了一个全新的基于划分的力矢量布局算法．针对大规模集成电路的布局问题，采用基于并行结群技术的递归划分方法进行分解解决，并结合改进的力矢量算法对划分所得的子电路进行迭代布局优化．通过对MCNC标准单元测试电路的实验，与FengShui布局工具相比，该布局算法在花费稍长一点的时间内获得了平均减少12%布局总线长度的良好效果．     

基于遗传算法优化BP神经网络雾霾预测模型的研究

对BP神经网络雾霾预测模型误差较大的问题,提出用遗传算法优化BP网络雾霾预测的方法,通过遗传算法对BP网络雾霾预测模型的权值和阈值的优化,然后用优化后的BP神经网络对实际的数据进行预测,实验表明:遗传算法优化BP网络雾霾模型具有更高的预测精度。     

微电子学、集成电路

TN42007060826适于数模混合集成电路的可布性分析模型/李桢荣,刘晓彦,张锡盛(北京大学深圳研究生院)//北京大学学报(自然科学版).―2007,43(1).―61～66.布局、布线是集成电路后端物理设计的两个主要环节,可布性分析作为连接布局和布线的枢纽,对优化布局和提高布线的布通率具有非常重要的作用。作者提出一种不可切割(non-slicing)结构的非均匀划分算法,大幅度减少了划分后的区域数量,同时建立了与此相应的适用于数模混合集成电路布局的可布性分析模型。对于实验电路的分析证实了该模型的准确性和高效性。图6表1参11TN42007060827芯片功能…     

智能集成VBR MPEG视频流量预测模型

作为数字媒体网络视频通信的主要方式,VBR MPEG视频流量的预测能力是直接关系缓冲区设计、动态带宽分配及拥塞控制等提高网络服务质量的关键因素.因此针对MPEG视频流的复杂特性,充分利用人工智能方法的优势,提出并建立了基于模糊神经网络的智能集成VBR MPEG 视频流量预测模型.采用模糊预测模型提高预测精度,利用神经网络解决预测的实时性问题.实验结果表明,与标准AR预测模型相比,该模型预测的准确度和可靠性显著提高,且算法简单易于推广到其他方法中使用.     

Cloud security situation prediction method based on grey wolfoptimization and BP neural network

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed.Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve theconvergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the positionupdate formula of GWO algorithm, which is used to select the features of the cloud security situation prediction dataand optimize the parameters of the BP neural network prediction model to minimize the prediction output error.Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm toincrease the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloudplatform are predicted. The simulation results show that the proposed method has lower mean square error (MSE)and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm(GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based onGWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.     

Performance evaluation of a routing algorithm based on Hopfield Neural Network for network-on-chip

Network on chip (NoC) has emerged as a solution to overcome the system on chip growing complexity and design challenges. A proper routing algorithm is a key issue of an NoC design. An appropriate routing method balances load across the network channels and keeps path length as short as possible. This survey investigates the performance of a routing algorithm based on Hopfield Neural Network. It is a dynamic programming to provide optimal path and network monitoring in real time. The aim of this article is to analyse the possibility of using a neural network as a router. The algorithm takes into account the path with the lowest delay (cost) form source to destination. In other words, the path a message takes from source to destination depends on network traffic situation at the time and it is the fastest one. The simulation results show that the proposed approach improves average delay, throughput and network congestion efficiently. At the same time, the increase in power consumption is almost negligible.     

DraLCD:一种新的数据中心流量工程方法

流量均衡是为了避免网络拥塞而作为流量工程中的路由优化目标提出来的,由于数据中心网络的流量特性,使得传统IP网络的流量工程方法不一定适合.为此,本文在SDN(Software Defined Network)的框架下,提出了一种基于链路关键度的自适应负载均衡流量工程方法:DraLCD(Dynamic Routing Algorithm based on Link Critical Degree).该方法通过对全局视图的网络管控,并充分利用了网络中存在的冗余路径,在完成细粒度流量均衡的同时,能够降低控制器的计算开销以及与交换机之间的通信开销,最终完成路由优化的目标.最后,基于DraLCD设计的原型系统,通过在Mininet仿真平台中部署并进行仿真实验,与现有的等开销多路径路由算法ECMP(Equal-Cost Multi-Path)以及GFF(Global First Fit)路由算法相比较,能够明显地提升网络性能.     

SRNoC: A novel high performance Shared-Resource routing scheme for Network-on-Chip

This paper proposes a novel Shared-Resource routing scheme, SRNoC, that not only enhances network transmission performance, but also provides a high efficient load-balance solution for NoC design. The proposed SRNoC scheme expands the NoC design space and provides a novel effective NoC framework. SRNoC scheme mainly consists of the topology and routing algorithm. The proposed topology of SRNoC is based on the Shared-Resource mechanism, in which the routers are divided into groups and each group of routers share a set of specified link resource. Because of the usage of Shared Resource mechanism, SRNoC could effectively distribute the workload uniformly onto the network so as to improve the utilization of the resource and alleviate the network congestion. The proposed routing algorithm is a minimal oblivious routing algorithm. It could improve average latency and saturation load owing to its flexibility and high efficiency. In order to evaluate the load-balance property of the network, we proposed a method to calculate the Φ which represents the characteristic value of load-balance. The smaller the Φ, the better the performance in load-balance. Simulation results show that the average latency and saturation load are dramatically improved by SRNoC both in synthetic traffic patterns and real application traffic trace with negligible hardware overhead. Under the same simulation condition, SRNoC could cut down the total network workload to 48.67% at least. Moreover, SRNoC reduces the value of Φ 45% at least compared with other routing algorithms, which means it achieves better load-balance feature.     

Research on the identification of the production origin of Angelica dahurica using LIBS technology combined with machine learning algorithms

The origin of Angelica dahurica medicinal herbs varies, and their pharmacological effects also differ. In order to achieve rapid and accurate identification of the origin of Angelica dahurica medicinal herbs, this study utilizes laser induced breakdown spectroscopy(LIBS) technology combined with machine learning algorithms to identify the original source of Angelica dahurica. Sliced samples of Angelica dahurica were taken from four regions: Hebei, Henan, Zhejiang, and Sichuan. The spectral data ...     

基于生成对抗网络的高光谱图像分类

为了解决简单卷积神经网络(convolutional neural network, CNN)不能有效提取与充分利用高光谱图像特征信息的问题,提出了一种 基于残差网络的多层特征匹配生成对抗网络模型。提出的模型引入残差网络以挖掘高光谱图 像的深层特征,生成可分性更高的高光谱图像,并通过一个特征融合层进行特征融合,充分 利用网络的各层特征。提出的算法在Indian Pines、Pavia University和Salinas数据集 上的分类精度分别达到了97.6%,99.3%,99.1%,与径向基函数支持向量机(radial basis function-support vector machine, RBF-SVM)、堆叠自动编码器(stacked autoencoder, SAE)、深度置信网络(deep belief network, DBN)、PPF-CNN (CNN based on pixel-pair feature)、CNN和三维卷积网络 (three-dimensional convolutional neural network, 3D-CNN)方法相比较,其分类精度具有明显的提高。实验结果表明,提出的方法是一种有效 的高光谱图像分类方法。     

粒子群优化BP神经网络的激光铣削质量预测模型

为了有效地控制激光铣削层质量,建立了激光铣削层质量（铣削层宽度、铣削层深度）与铣削层参数（激光功率、扫描速度和离焦量）的BP神经网络预测模型。采用粒子群算法优化了BP神经网络的权值和阈值,构建了基于粒子群神经网络的质量预测模型。所提出的PSO-BP算法解决了一般BP算法迭代速度慢,且易出现局部最优的问题,并以Al2O3陶瓷激光铣削质量预测为例,进行算法实现。仿真结果表明:提出的PSO-BP算法迭代次数大大减少,且预测误差明显减少。所构建的质量预测模型具有较高的预测精度和实用价值。     

基于并行BP神经网络的路由查找算法

结合Bloom-filter算法和并行反向传播神经网络,提出了一种新的基于并行神经网络的路由查找算法(BFBP)。该算法满足路由查找的需求,只需学习路由条目的网络ID,且易于扩展到IPv6地址查询。研究结果表明,相比于己有的神经网络路由查找方法,该算法需要学习的条目数平均减少了520倍,提高了学习效率,为神经网络应用于路由查找创造了有利条件。     

A policy based framework for quality of service management in software defined networks

Growth in multimedia traffic over the Internet increases congestion in the network architecture. Software-Defined Networking (SDN) is a novel paradigm that solves the congestion problem and allows the network to be dynamic, intelligent, and it centrally controls the network devices. SDN has many advantages in comparison to traditional networks, such as separation of forwarding and control plane from devices, global centralized control, management of network traffic. We design a policy-based framework to enhance the Quality of Service (QoS) of multimedia traffic flows in a potential SDN environment. We phrase a max-flow-min-cost routing problem to determine the routing paths and presented a heuristic method to route the traffic flows in the network in polynomial time. The framework monitors the QoS parameters of traffic flows and identifies policy violations due to link congestion in the network. The introduced approach dynamically implements policy rules to SDN switches upon detection of policy violations and reroutes the traffic flows. The results illustrate that the framework achieves a reduction in end-to-end delay, average jitter, and QoS violated flows by 24%, 37%, and 25%, respectively, as compared to the Delay Minimization method. Furthermore, the proposed approach has achieved better results when compared to SDN without policy-based framework and reduced end-to-end delay, average jitter, and QoS violated flows by 51%, 62%, and 28%, respectively.

     

Task-oriented resource prediction and adjustment algorithm for space-based information network

The tasks of a space-based information network are complex and diverse, but the resources of a space-based environment are minimal. The existing methods are challenging to match task demand to resource supply accurately. Aiming at the problem of accurate prediction from task to resource, we propose a resource prediction adjustment strategy. First, we propose a multidimensional resource prediction algorithm based on improved particle swarm optimization and back propagation (IPSO-BP) neural network. The improved PSO is used to optimize the weight and threshold of BP neural network to make up for the defects that BP neural network is easy to fall into local minimum and the predicted output value is not unique. Second, to meet the quality of service (QoS) of tasks, we propose a density-based performance evaluation algorithm (DPEA) to adjust resources. This method uses the idea of local sensitive hash to select the evaluation subset for the configuration task, then dynamically selects the $k$ nearest neighbors of the configuration task, and uses the idea of weighted average to evaluate the QoS performance index of the configuration task. Simulation results show that the proposed resource prediction and adjustment strategy effectively reduces the scheduling time overhead and improves resource utilization.