IP交换中流分类的神经网络方法

本文对IP交换机中流的分类问题进行了探讨。首先对现有的X／Y分类器进行了分析,指出其不足之处,然后总结了进行流判断时应考虑的各种因素。之后提出了一种利用Hopfield神经网络进行流分类的方法,并对其参数的选取进行了讨论。仿真结果表明,神经网络分类器可根据网络中流的具体情况,自动调节分类阈值,保证IP交换机利用的VC数基本稳定。与常规X／Y分类器相比,神经网络分类器可利用更少的VC交换更多的数据包。     

An integrated hybrid neural network and hidden Markov modelclassifier for sonar signals

We present here an integrated hybrid hidden Markov model and neural network (HMM/NN) classifier that combines the time normalization property of the HMM classifier with the superior discriminative ability of the neural net (NN). In the proposed classifier, a left-to-right HMM module is used first to segment the observation sequence of every exemplar into a fixed number of states. Subsequently, all the frames belonging to the same state are replaced by one average frame. Thus, every exemplar, irrespective of its time-state variation, is transformed into a fixed number of frames, i.e., a static pattern. The multilayer perceptron (MLP) neural net is then used as the classifier for these time-normalized exemplars. Some experimental results using sonar biologic signals are presented to demonstrate the superiority of the hybrid integrated classifier     

基于模型输出敏感度分析的动态神经网络结构设计

神经网络的性能由其训练算法和拓扑结构共同确定。为了解决设计网络结构的动态调整问题,论文给出了一种神经网络结构动态设计方法。以隐含层神经元输出的贡献对模型输出敏感度进行分析,从而调整神经网络结构,对贡献太小的神经元予以删除,对贡献值太大的神经元利用最邻近法在其附近插入新的神经元。通过对非线性函数进行逼近和对非线性系统关键参数进行预测证明了该方法的有效性。     

Neural networks for frequency line tracking

This paper investigates the application of neural networks to frequency line tracking. Recently, hidden Markov models (HMM's) have been successfully applied to this problem, and here, we study a neural network architecture called Mnet, which is based on an underlying Markov model representation. A supervised learning algorithm is developed for Mnet, and a method of analytically deriving the connection weights for the Mnet is also mentioned. Two more conventional neural networks are also studied; a multilayer feedforward network and a multilayer network with feedback. The simulation results show that all three neural networks are comparable in performance to a hidden Markov model when applied to the frequency line tracking problem     

一种自适应的小波神经网络

本文受感知域划分思想的启发，将小波的多分辨分析与BP网结构相结合，构造了一种新的小波神经网络．该小波神经网络利用多分辨分析生成小波树，小波树的生长与网络的训练相结合，自适应地生成隐层结点，并且删除分类不佳的结点．以声纳信号进行了实验，结果表明：该网络充分发挥了小波的特点，将模式识别的特征抽取与分类器设计融为一体．     

基于小波网络和HMM的语音识别方法

利用隐马尔可夫模型(HMM)的动态时间序列建模能力及神经网络的模式分类能力,构成混合语音识别模型,同时考虑到语音信号的非平稳性,采用小波分析方法提取语音特征向量。通过时间规整方法,将所有具有可变长度的语音特征向量转换为相同维数的特征向量,从而简化了神经网络的结构。仿真结果表明,采用混合语音识别模型以及时间规整方法,不仅可提高识别率,同时大大缩减了训练时间,获得了很好的识别效果。     

神经网络在DMMP红外光谱判别中的应用

介绍了神经网络在化学毒剂红外遥感监测领域应用的概况，探讨了反向传播人工神经网络分类器应用于红外光谱鉴别的可能性。用一个甲基膦酸二甲酯红外光谱数据样本集进行了实际的训练和鉴别性能预测。训练结果表明，这种分类器在一定条件下可以将959／5以上的样本正确分离；预测结果表明，经过适当训练的神经网络分类器可以获得70％以上的鉴别率，具备了一定的识别能力。     

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     

An enhance excavation equipments classification algorithm based on acoustic spectrum dynamic feature

Underground pipeline network surveillance system attracts increasingly attentions recently due to severe breakages caused by external excavation equipments in the mainland of China. In this paper, we study excavation equipments classification algorithm based on acoustic signal processing and machine learning algorithms. A cross-layer microphone array with four elements is designed to collect the acoustic database of representative excavation equipments on real construction sites. The generalized sidelobe canceller algorithm is employed for background noise reduction. The improved spectrum dynamic feature extraction algorithm is then implemented for the benchmark acoustic feature database construction of excavation equipments. To perform classification and background noise identification, the single hidden layer feedforward neural network is employed as the classifier. An improved algorithm based on the popular extreme learning machine (ELM) is proposed for classifier learning. The leave-one-out cross validation strategy is adopted for the regularization parameter optimization in ELM. Comprehensive experiments are conducted to test the effectiveness of the proposed algorithm. Comparisons with state-of-art classifiers and the Mel-frequency cepstrual coefficients acoustic features are also provided to demonstrate the superiority of our approach.     

多层前馈网络在模式识别中的理论和应用

本文从理论上证明了具有线性输出单元的多层前馈网络能用作最优特征提取器。同时还证明了多层前馈网络分类器的输出函数是最小均方误差意义下对Ｂａｙｅｓ决策函数的逼近，对于具有线性输出单元的三层前馈网络，当隐层单元数足够多时，这种逼近能达到任意精度。在此基础上，我们提出了一个综合了特征提取网络和分类器网络的组合神经网络模型，其性能好于单个的三层前馈网络。     

INVESTIGATION ON THE COMPUTATIONAL PROPERTIES OF INTRANEURONAL DYNAMICS

This paper aims at exploring computational properties of dynamic processes in neu-ral systems,studying their mathematical formulation,and applying the results to artificial neuralnetwork modeling.The stimulus-response processes in neurons are first introduced briefly,thenproperties of neurons described by the Hodgkin-Huxley equations are analyzed.After studyinghow to simplify,the Hodgkin-Huxley equations while maintaining its properties,the concept of dy-namic neuron model is proposed.It is pointed out that the neuron model should include internalstates in order to obtain time-variant thresholds,such as refractory periods of neurons.Finallywe discuss problems related to neural network models based on pulse-stream communication andthe contribution of intraneuronal dynamics to collective properties of the neural network.     

基于LSTM神经网络的频谱感知算法

在频谱感知中经典的能量检测算法在低信噪比时检测性能较低且门限难以估计,基于机器学习的感知算法受限于检验统计量的构造会造成接收信号原有结构信息的丢失。针对这些问题,本文提出一种基于LSTM神经网络的频谱感知方法,首先利用接收信号序列作为神经网络的输入特征向量,然后使用LSTM神经网络进行训练得到分类器,最后使用训练好的模型实现频谱感知。该方法无需估计检测门限值,也无需构造特征向量,仿真结果表明,所提算法在采样点和次级用户更少的情况下仍优于对比算法。      

基于PSO-BP算法的无线传感器网络定位优化

在研究现有定位算法的基础上,针对基于接收信号强度指示(RSSI)定位模型中的参数易受环境影响等问题,提出了一种新型的粒子群优化(PSO)算法与后向传播(BP)神经网络相结合的算法.BP网络算法权值的修正依赖于非线性梯度值,易形成局部极值,同时学习次数较多,需先通过粒子群算法进行优化.为了提高定位精度,首先采用速度常量法滤波处理,然后通过改进的混合优化算法对BP神经网络初始权值和阈值进行优化,并分析算法的性能.试验中隐层节点个数采用试错法,从12到19变化,以确定合适数目.实验结果表明,与一般加权算法和传统BP算法相比,改进的混合优化算法可大幅改善测距误差对定位误差的影响,同时可使25 m内最小定位误差小于0.27 m.     

基于负相关神经网络集成的货币识别算法研究

为了提高货币识别率,提出了用负相关学习算法来提高神经网络集成的泛化能力.将紫外光照射下的纸币图片作为实验样本,将负相关学习法的集成神经网络用于分类器设计,选择6种面额纸币在不同噪声下的样本共300个作为训练样本,对单个神经网络分类器和神经网络集成分类器进行了MATLAB仿真,并对仿真所得的可靠性、识别率进行对比.实验结果表明,基于负相关学习的神经网络集成对货币识别分类有很好的效果,与应用单个神经网络的系统和独立训练个体网络的集成神经网络相比,它的识别率平均可以高出4％.     

听觉模型用于语音识别以及与一般方法的比较

本文在文献（１）建立的外周听觉系统以及部分中枢听觉神经系统的基础上，建立了一个主意识别器。它由听觉模型作为语音声学前端处理器（即特征提取），由具有ｔｏｎｏｔｏｐｉｃ组织结构的神经网络作为识别分类器。大量实验表明，由该听觉模型提取的特征参数不仅能很好地表示主意区别意义，而且对于噪声环境下的语音特征表示有较好ｔｏｂｕｓｔｎｅｓｓ。语音识别实验表明：在有噪声的情况下，采用听觉模型参数的识别器，其识别率明     

基于人工神经网络的通信信号分类识别

通信信号的分类识别是一种典型的统计模式识别问题。系统地论述了通信信号特征选择、特征提取和分类识别的原理和方法。设计了人工神经网络分类器,包括神经网络模型的选择、分类器的输入输出表示、神经网络拓扑结构和训练算法,并提出了分层结构的神经网络分类器。     

Intracranial Epileptic Seizures Detection Based on an Optimized Neural Network Classifier

Automatic identification of intracranial electroencephalogram (iEEG) signals has become more and more important in the field of medical diagnostics. In this paper, an optimized neural network classifier is proposed based on an improved feature extraction method for the identification of iEEG epileptic seizures. Four kinds of entropy, Sample entropy, Approximate entropy, Shannon entropy, Log energy entropy are extracted from the database as the feature vectors of Neural network (NN) during the identification process. Four kinds of classification tasks, namely Pre-ictal v Post-ictal (CD), Pre-ictal v Epileptic (CE), Post-ictal v Epileptic (DE), Pre-ictal v Post-ictal v Epileptic (CDE), are used to test the effect of our classification method. The experimental results show that our algorithm achieves higher performance in all tasks than previous algorithms. The effect of hidden layer nodes number is investigated by a constructive approach named growth method. We obtain the optimized number ranges of hidden layer nodes for the binary classification problems CD, CE, DE, and the multitask classification problem CDE, respectively.     

基于GA-BP神经网络的VOD代理节目预取模型

VOD代理服务器的节目预取方法决定了园区网VOD系统的整体运行效率。提出一种节目预取模型,采用BP神经网络构建分类器并对VOD节目进行分类,再根据分类结果采用基于分组的方法实现代理服务器的节目预取。模型中引入遗传算法对已建立的分类模型进行改进,以克服局部极小值问题。仿真实验表明,该预取模型具有较高的命中率,能有效提高代理服务器的利用率。     

A novel genetic-algorithm-based neural network for short-term load forecasting

This paper presents a neural network with a novel neuron model. In this model, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer. This neural network provides better performance than a traditional feedforward neural network, and fewer hidden nodes are needed. The parameters of the proposed neural network are tuned by a genetic algorithm with arithmetic crossover and nonuniform mutation. Some applications are given to show the merits of the proposed neural network.     

Automatic target recognition using a feature-decomposition anddata-decomposition modular neural network

A modular neural network classifier has been applied to the problem of automatic target recognition using forward-looking infrared (FLIR) imagery. The classifier consists of several independently trained neural networks. Each neural network makes a decision based on local features extracted from a specific portion of a target image. The classification decisions of the individual networks are combined to determine the final classification. Experiments show that decomposition of the input features results in performance superior to a fully connected network in terms of both network complexity and probability of classification. Performance of the classifier is further improved by the use of multiresolution features and by the introduction of a higher level neural network on the top of the individual networks, a method known as stacked generalization. In addition to feature decomposition, we implemented a data-decomposition classifier network and demonstrated improved performance. Experimental results are reported on a large set of real FLIR images.