神经网络控制结构及所用神经网络

本文阐述了神经网络控制所能解决的控制难题,若干种控制结构及常用的动态神经网络。讨论了神经网络控制研究的重点,在实时控制中的物理可实现性及其发展等问题。     

信息中心网络中基于局部内容活跃度的自适应缓存算法

通过对信息中心网络的网内节点缓存建模,分析发现基于全局内容流行度的替换策略不适用于信息中心网络的分布式模式。继而提出了一种基于局部内容活跃度的缓存替换策略LAU,并基于该策略提出了一种自适应路径缓存算法ACAP,使缓存内容按照本地活跃度依次缓存在访问路径中。仿真结果表明,LAU策略提高了单节点缓存命中率;ACAP相比已有的路径缓存算法,具有较低的服务器命中率和跳数比。最后对该算法适用的缓存结构和拓扑结构进行了讨论和分析。     

基于OPT Cache替换Profiling的Cache提示生成

提出了一个基于最优Cache替换（OPT）Profiling的静态Cache提示生成方法,并通过模拟SPEC2000Int测试程序,对该方法与LRU Cache替换策略进行了性能比较。     

程序的cache使用效率分析

评价程序的存储效率是提高用户程序性能的重要手段。该文首先提出了程序的装入因子的概念,并据此分析了矩阵乘法;其次,根据时间局部化原则,提出了一种“最小时间差方法”,该方法可以有效地减少cacheline的装入数目;最后,为了评价程序的存储延迟,提出了程序数据相关性的概念,据此给出了计算装入因子的公式,用于分析程序的存储效率。这样就可以用big-O模型来表达程序的时间复杂性,并用装入因子来表达程序的存储访问复杂性。     

一种基于神经网络的模糊控制器的算法研究

本文首先简单分析了模糊控制器和神经网络的特点,然后设计了一种将二者结合在一起的控制算法-神经模糊推理控制器,并应用于某实际控制系统,结果证明了算法的有效性。     

机械手存储库缓存替换算法研究及应用

文章首先给出了机械手存储库的缓存模型,针对缓存模型和多媒体应用的特点,提出了两种基于热点能量的新缓存替换算法———近期热点能量缓存算法(RPE)和双缓冲区缓存算法(TSC),通过仿真实验,讨论了几种算法参数的最优取值范围,并且利用对比实验,验证了两种算法的缓存性能在重负载、小缓存条件下要优于传统LRU算法。该文内容为设计和实现大规模数字媒体管理系统提供了重要的依据。     

Spark内存管理及缓存策略研究

Spark系统是基于Map-Reduce模型的大数据处理框架。Spark能够充分利用集群的内存,从而加快数据的处理速度。Spark按照功能把内存分成不同的区域:Shuffle Memory和Storage Memory,Unroll Memory,不同的区域有不同的使用特点。首先,测试并分析了Shuffle Memory和Storage Memory的使用特点。RDD是Spark系统最重要的抽象,能够缓存在集群的内存中;在内存不足时,需要淘汰部分RDD分区。接着,提出了一种新的RDD分布式权值缓存策略,通过RDD分区的存储时间、大小、使用次数等来分析RDD分区的权值,并根据RDD的分布式特征对需要淘汰的RDD分区进行选择。最后,测试和分析了多种缓存策略的性能。     

高速缓冲存储器性能解析

本文分析了高速缓存的结构和工作原理,阐述了高速缓存的工作过程以及对处理器性能的影响。     

Application of Neural Networks for the Measurement of Electronic Temperature in Nuclear Fusion Experiments

Langmuir probes are used in nuclear fusion experiments to derive the electronic temperature of a high temperature ionised gas. For this purpose, the current I flowing through the probe at varying applied potentials V is measured. The shape of the resulting V-I characteristic is exponential, and depends upon the electronic temperature. Traditionally, fitting procedures are used to derive the temperature, but the amount of computation required is high as the measurement is repeated many times during the experiment. In this paper the use of neural networks to derive the electronic temperature from Langmuir probe data is investigated. Neural networks proved to be comparable with traditional methods in the accuracy of the reconstruction, though requiring less computational resources.     

Shared cache architectures for decision support systems

In this paper we evaluate two shared-cache architectures for small-scale multiprocessors. We vary shared cache sizes from 8MB to 1GB, under various block sizes, cache organizations and sizes, and strategies for IO transactions. We use 12 bus trace samples obtained during the execution of a 100GB TPC-H on an eight-way multiprocessor.

To deal with the cold-start misses at the beginning of each sample, we identify the sure misses which are known to be misses in the full trace. The difference between the total number of misses and the number of sure misses is the zone of uncertainty, which may be hits or misses in the full trace. It turns out that the zone of uncertainty is small enough in most cases that useful conclusions can be drawn.

Our conclusions are that a single-cluster configuration with a shared cache—even a very small one—can be very effective for TPC-H. We also show that the coherence traffic between shared caches in a multiple cluster system is very high in the context of TPC-H.     

线性神经网络及在系统辨识中的初步应用

该文从基本的智能控制技术——神经网络(NN)技术出发,探讨了神经网络用于系统辨识与建模的基本理论,分析了线性系统神经网络建模的规律,提出了一种利用线性神经网络进行系统辨识的方法。该辨识方法显示出很强的处理问题的能力,无需辨别系统阶次,辨识结构简单,收敛速度快,仿真结果表明这种方法的有效性和可行性。该文共分为四部分,第一部分介绍了神经网络用于系统辨识的特征,第二部分讲述了线性神经网络的工作原理,包括线性神经网络的模型、传递函数、学习规则及训练过程,第三部分讲述了线性神经网络进行系统辨识的仿真实例,第四部分对上述内容作了简要小结。     

Nonlinear Black Box Modelling – Fuzzy Networks versus Neural Networks

Fuzzy networks and neural networks offer two different approaches of nonlinear black box modelling. Efficient identification methods have been developed to calculate the parameters for a given structure and have been applied successfully in many examples. But the applications proposed in the literature usually miss the comparison of the alternative method, so that the selection of the more suitable approach for a given task is difficult. This paper aims to ease the decision for one of the two methodologies by considering one well-known high quality approximator of each network type, and presenting a fair comparison. For this purpose, two mathematical and three complex technical examples of nonlinear systems are considered. Generally, fuzzy networks and neural networks face the problem of overtraining causing poor validation/generalisation results. A modification of the established identification methods is proposed as a significant improvement for both approaches.     

Neural Networks for Autonomous Path-Following with an Omnidirectional Image Sensor

This paper presents a path-following system implemented with two different types of neural networks, that enables an autonomous mobile robot to return along a previously learned path in a dynamic environment. The path-following is based on data provided by an omnidirectional conical visual system, derived from the COPIS sensor, but with different optical reflective properties. The system uses optical and software processing and a neural network to learn the path, described as a sequence of selected points. In the navigation phase it drives the robot along this learned path. Interesting results have been achieved using low cost equipment. Test and results are presented.     

可用于医学特征的多层神经网络的算法研究

基于医学特征识别处理过程的特点，提出具有反馈的多层混合型神经网络模型，具体研究其学习算法，其有效性得到说明。     

基于网络模拟的多媒体网络性能评价方法

计算机模拟是多媒体网络性能评价的一种重要手段。该文在分析多媒体网络特点及其性能评价指标的基础上,着重讨论了运用计算机模拟技术对多媒体网络进行性能评价的方法。还根据讨论结果完成了一个模拟实验,对一个特定多媒体网络在不同多媒体业务下的一些性能指标进行了分析,并根据分析结果,给出了该性能指标的性能空间。     

嵌入式应用环境下的Cache性能分析

为了提高性能，通用处理器中所广泛采用的cache技术被引入到了嵌入式处理器中。该文采用基于仿真的方法分析了嵌入式应用环境下几个主要的cache结构参数对cache性能的影响。在分析过程中，还考虑了不同主存实现方式带来的影响。     

一种新型神经网络结构模型的应用研究

基于过程先验知识与神经网络结构选择相结合的思想,提出了一类新型神经网络结构,并具体研究了其学习算法.同时给出了一种新的样本抽取方法及其相应的网络训练步骤.这些思想和方法均在复杂尿素生产过程的建模和优化中得到了应用.基于所建神经网络模型知识的专家系统已在某化肥厂得到成功的应用.     

BP人工神经网络在图像分割中的应用

图像分割是图像处理和计算机视觉的重要研究领域,也是图像识别和图像分析的基础性工作之一。图像分割效果的好坏直接影响图像特征的提取、图像识别的精度。BP人工神经网络在理论上具有实现任意非线性映射的能力,具有自学习、自适应及鲁棒性强的特点,在模式识别、模式分类和模糊控制等领域得到广泛应用。作者将BP人工神经网络成功地运用于印鉴图像分割、车牌号码图像的分割等工作中,取得了良好的图像分割效果。     

Emotion Recognition in Speech Using Neural Networks

Emotion recognition in speech is a topic on which little research has been done to-date. In this paper, we discuss why emotion recognition in speech is a significant and applicable research topic, and present a system for emotion recognition using one-class- in-one neural networks. By using a large database of phoneme balanced words, our system is speaker- and context-independent. We achieve a recognition rate of approximately 50% when testing eight emotions.