Optimum classification of non-Gaussian processes using neuralnetworks

A prerequisite for target detection in synthetic aperture radar and moving target imaging radars is an ability to classify background clutter in an optimal manner. Such radar clutter can frequently be modelled as a correlated nonGaussian process with, for example, Weibull or K statistics. Maximum likelihood (ML) provides an optimum classification scheme but cannot always be formulated when correlations are present. In such circumstances, nonlinear, adaptive filters are required which can learn to classify the clutter types: a role to which neural networks are particularly suited. The authors investigate how closely neural networks can approach optimum classification. To this end, a factorisation technique is presented which aids convergence to the best possible solution obtainable from the training data. The performances of factorised networks are compared with the ML performance and the performances of various intuitive and approximate classification schemes when applied to uncorrelated K distributed images. Furthermore, preliminary results are presented for the classification of correlated processes. It is seen that factorised neural networks can produce an accurate numerical approximation to the ML solution and will thus be of great benefit in radar clutter classification     

Classification of multisensor remote-sensing images by structuredneural networks

Proposes the application of structured neural networks to classification of multisensor remote-sensing images. The purpose of the approach is to allow the interpretation of the “network behavior”, as it can be utilized by photointerpreters for the validation of the neural classifier. In addition, this approach gives a criterion for defining the network architecture, so avoiding the classical trial-and-error process. First of all, the architecture of structured multilayer feedforward networks is tailored to a multisensor classification problem. Then, such networks are trained to solve the problem by the error backpropagation algorithm. Finally, they are transformed into equivalent networks to obtain a simplified representation. The resulting equivalent networks may be interpreted as a hierarchical arrangement of “committees” that accomplish the classification task by checking on a set of explicit constraints on input data. Experimental results on a multisensor (optical and SAR) data set are described in terms of both classification accuracy and network interpretation. Comparisons with fully connected neural networks and with the k-nearest neighbor classifier are also made     

多域光网络生存性的关键技术研究

多域光网络的生存性作为衡量网络性能优劣的关键指标,与实际网络应用的关系最为密切,是当前迫切需要解决的关键问题;聚焦高速化、多业务化驱动的多域光网络环境下的生存性技术.基于光网络的多业务、分布式控制的特性,分析了多域光网络生存性机制的研究现状及面临的挑战;给出了一种针对多域光网络生存性问题的分类方法;结合多域光网络对生存性的需求,对相关关键技术进行了归类和研究,并指明了进一步研究的方向和重点.     

Bayesian network modeling for discovering "dependent synergies" among muscles in reaching movements

The coordinated activities of muscles during reaching movements can be characterized by appropriate analysis of simultaneously-recorded surface electromyograms (sEMGs). Many recent sEMG studies have analyzed muscle synergies using statistical methods such as Independent Component Analysis, which commonly assume a small set of influences upstream of the muscles (e.g., originating from the motor cortex) produce the sEMG signals. Traditionally only the amplitude of the sEMG signal was investigated. Here, we present a fundamentally different approach and model sEMG signals after the effects of amplitude have been minimized. We develop the framework of Bayesian networks (BNs) for modeling muscle activities and for analyzing the overall muscle network structure. Instead of assuming that synergies may be independently activated, we assume that neuronal activity driving a given muscle may be conditionally dependent upon neurons driving other muscles. We call the resulting interactions between muscle activity patterns "dependent synergies". The learned BN networks were explored for the purpose of classification across subjects based on hand dominance or affliction by stroke. Network structure features were investigated as classification input features and it was determined that specific edge connection patterns of 3-node subnetworks were selectively recruited during reaching movements and were differentially recruited after stroke compared to normal control subjects. The resulting classification was robust to inter-subject and within-group variability and yielded excellent classification performance. The proposed framework extends muscle synergy analysis and provides a framework for thinking about muscle activity interactions in motor control.     

Deep global-attention based convolutional network with dense connections for text classification

Text classification is a classic task innatural language process (NLP). Convolutional neural networks (CNNs) have demonstrated its effectiveness in sentence and document modeling. However, most of existing CNN models are applied to the fixed-size convolution filters, thereby unable to adapt different local interdependency. To address this problem, a deep global-attention based convolutional network with dense connections (DGA-CCN) is proposed. In the framework, dense connections are applied to connect each convolution layer to each of the other layers which can accept information from all previous layers and get multiple sizes of local information. Then the local information extracted by the convolution layer is reweighted by deep global-attention to obtain a sequence representation with more valuable information of the whole sequence. A series of experiments are conducted on five text classification benchmarks, and the experimental results show that the proposed model improves upon the state of-the-art baselines on four of five datasets, which can show the effectiveness of our model for text classification.     

Routing and flow control in high-speed wide-area networks

The routing and flow control techniques developed for wide-area, local-area, and metropolitan-area networks are surveyed. A classification that shows the characteristics that are desirable for high-speed wide-area networks is developed. On the basis of the classification, techniques that should and should not be considered for future high-speed networks are identified. In particular, an attempt is made to determine the effect of increasing transmission rates on the routing and flow control algorithms that are used in packet-switched networks     

Fast Classification Networks For Signal Processing

We present a generalization of the corner classification approach to training feedforward neural networks that allows rapid learning of nonbinary data. These generalized networks, called fast classification (FC) networks, are compared against backpropagation and radial basis function networks and are shown to have excellent performance for prediction of time series and pattern recognition. FC networks do not require iterative training and they can be used in many signal processing applications where fast, nonlinear filtering provides an advantage.     

Consensual and Hierarchical Classification of Remotely Sensed Multispectral Images

Consensual and hierarchical approaches are developed for the classification of remotely sensed multispectral images. The proposed method consists of preprocessing of input patterns, generating multiple classification results by hierarchical neural networks, and a combining scheme to generate a consensus of multiple classification results. Transformations of input patterns by random matrices and nonlinear filtering are used for preprocessing. By varying the input patterns, the multiple classification results are generated with sufficiently independent errors by using a single type of classifier. This helps to improve classification performance when the multiple classification results are combined. Hierarchical neural networks involve the use of successive classifiers which are tuned to reduce the remaining errors to increase the classification performance. This structure includes detection schemes to decide whether successive classifiers are utilized for each input. Consensual and hierarchical approaches generate more reliable and accurate results based on group decision.     

WDM-based local lightwave networks. I. Single-hop systems

An overview of emerging all-optical networks is given. The characteristics and alternative architectures for single-hop systems are discussed. The characteristics of lightwave technology that facilitate the design of wavelength-division-multiplexing (WDM) networks are reviewed, and it is explained how WDM local networks can be built based on the single-hop and multihop approaches. Various categories of single-hop systems are discussed: experimental systems, systems based on no pretransmission coordination, and systems based on pretransmission coordination, which also require a separate control channel. A simple classification for single-hop systems is provided     

一种可在线学习的变结构径向基函数网络及其在被动声纳目标识别中的应用

提出一种新颖的隐节点可调的变结构径向基函数,并应用进化规划最优地确定和调节变结构径向基函数网络隐层节点的数目及其核函数的中心和宽度,从而使网络具有在线学习和记忆新的目标模式的功能,并将该网络应用于被动声纳目标的识别和在线学习实验结果表明基于进化规划的变结构径向基函数网络不仅了网络的泛化能力,而且能够有效垢解决传统神经网络技术在被动声纳目标识别过程中在线学习会造成原有记忆遗忘的困难。     

Scalable VLSI implementations for neural networks

This paper discusses research on scalable VLSI implementations of feed-forward and recurrent neural networks. These two families of networks are useful in a wide variety of important applications—classification tasks for feed-forward nets and optimization problems for recurrent nets—but their differences affect the way they should be built. We find that analog computation with digitally programmable weights works best for feed-forward networks, while stochastic processing takes advantage of the integrative nature of recurrent networks. We have shown early prototypes of these networks which compute at rates of 1–2 billion connections per second. These general-purpose neural building blocks can be coupled with an overall data transmission framework that is electronically reconfigured in a local manner to produce arbitrarily large, fault-tolerant networks.     

S-transform-based intelligent system for classification of power quality disturbance signals

In this paper, a new approach is presented for the detection and classification of nonstationary signals in power networks by combining the S-transform and neural networks. The S-transform provides frequency-dependent resolution that simultaneously localizes the real and imaginary spectra. The S-transform is similar to the wavelet transform but with a phase correction. This property is used to obtain useful features of the nonstationary signals that make the pattern recognition much simpler in comparison to the wavelet multiresolution analysis. Two neural network configurations are trained with features from the S-transform for recognizing the waveform class. The classification accuracy for a variety of power network disturbance signals for both types of neural networks is shown and is found to be a significant improvement over multiresolution wavelet analysis with multiple neural networks.     

基于相应簇回声状态网络静态分类方法

借鉴模仿哺乳动物大脑皮层分簇结构的复杂网络拓扑结构,提出一种基于相应簇储备池回声状态网络的分类方法.将时间窗函数机制引入到回声状态网络储备池的构建中,利用具体问题中需分类数据的类别数量,生成具有对应分簇数目的储备池,以期提高分类精度.基于标准数据集和模拟电路故障诊断的实验验证结果表明,本文方法与标准回声状态网络等方法相...     

Self-evolving neural networks for rule-based data processing

Two training algorithms for self-evolving neural networks are discussed for rule-based data analysis. Efficient classification is achieved with a fewer number of automatically added clusters, and application data is analyzed by interpreting the trained neural network as a fuzzy rule-based system. The learning vector quantization algorithm has been modified, acquiring the self-evolvement character in the prototype neuron layer based on sub-Bayesian decision making. The number of required prototypes representing fuzzy rules is automatically determined by the application data set. This method, compared with others, shows better classification results for data sets with high noise or overlapping classification boundaries. The classifying radial basis function networks are generalized into multiple shape basis function networks. The learning algorithm discussed is capable of adding new neurons representing self-evolving clusters of different shapes and sizes dynamically. This shows a clear reduction in number of neurons or the number of fuzzy rules generated, and the classification accuracy is increased significantly. This improvement is highly relevant in developing neural networks that are functionally equivalent to fuzzy classifiers since the transparency is strongly related to the compactness of the system     

Netted radar: Network communications design and optimisation

Networks of phased array radars are generally able to provide better counter stealth target detection and classification. Each radar sensor (or node) generates information which requires transmission to a central authority that is able to evaluate the information. This requires a communications network to be established to allow transmission of information to and from any node. Each radar node is limited by range and degree and relies on the formation of a multi-hop network to facilitate these transmissions.This paper presents a model whereby the radar beam itself is used in the formation of a multi-hop network. The phased array’s multi-functional nature allows rapid switching between communications and radar function. A model of how the communication system could operate is presented, and an evolutionary optimisation algorithm based upon the concept of Pareto optimality is used for the topological design of the network. Finally, a simulation environment is presented to show the simulated performance of the communication model and designed networks.     

基于波分复用的智能光网节点管理模型

分析了基于波分复用(WDM)技术的下一代智能光网络中节点管理系统的功能模型和管理任务,给出了一种综合考虑业务分级和支持多径路由的算法,可在WDM光网中实现基于性能分析的资源动态配置管理。采用自行开发的资源动态配置软件进行了仿真实验,给出了仿真结果。     

Multispectral classification of Landsat-images using neuralnetworks

The authors report the application of three-layer back-propagation networks for classification of Landsat TM data on a pixel-by-pixel basis. The results are compared to Gaussian maximum likelihood classification. First, it is shown that the neural network is able to perform better than the maximum likelihood classifier. Secondly, in an extension of the basic network architecture it is shown that textural information can be integrated into the neural network classifier without the explicit definition of a texture measure. Finally, the use of neural networks for postclassification smoothing is examined     

Intelligent network control middleware platform

As multivendor, multitechnology networks are deployed in a carrier's network, a network operator must integrate these networks to have a unified control platform to lower operational costs and deliver customer-specified QoS. An intelligent network control middleware framework for multivendor networks is described in this article. The architectural framework is designed to control and manage next generation network elements as well as legacy telecom networks. The layers within the framework include mediation, control plane, network resource management, and application programmable interfaces. An independent, distributed control plane aims at service interoperability and network scalability. An experimental study on circuit provisioning using the proposed middleware framework is conducted on Sun Lab servers. The middleware performance results are reported. Experimentation architecture and metrics can be extended to a performance benchmark upon which the control plane products can be evaluated.     

无线传感器网络干扰分类识别机制的研究

针对在优化无线传感器网络传输性能时,识别出网络是否受到干扰并区分网络内与网络间的干扰类型是首要解决的问题。设计并实现了一种能够识别传感器网络干扰并区分网内、网间干扰类型的机制。首先通过实验获得了传感器网络在常见干扰状态下的有关性能参数,并对这些参数进行了相关性分析,之后基于Logistic分类模型建立了干扰状态以及网内、网间干扰类型的识别模型,并根据实测数据确定了该模型的参数。实际测试表明基于该分类模型的分类识别方法的准确率可达到97%以上,能够有效解决发现网络受到干扰的情况以及对网络干扰识别的问题。     

多跳无线网络MAC协议的研究进展

该文简要介绍了多跳无线网络的结构及其MAC协议的分类,简述了近几年来国内外对多跳无线网络MAC协议研究的几个新进展。这些协议均有各自的特点,适用于不同种类的无线网络。最后展望了多跳无线网络MAC协议的发展前景。