小神经

By making up of time-frequency local property and multi-scale analytical capability of wavelet transformation and self-learning and prediction function of artificial neural network,chapter three develops a prediction model loose combining wavelet analysis and Radial Basis Functionsneural network,abbreviated as Wavelet-RBFNN.

第三章利用小波变换的时频局域化特性和多尺度分析能力及神经网络的自学习、预测功能，通过小波分析与神经网络的松散型结合方式，建立小波分析和径向基函数神经网络(Wavelet-RBFNN)预测模型。

It is defined that the two integrating ways' characteristics of the wavelet NN and theirs applying on the equipments' intelligence diagnose. Wavelet analysis technology has the ability of analyzing strongly the non-placidity signals' time-frequency, self-studying the NN, of dealing with data distributed and collaterally, of mapping non-linear ability, and it is fit for diagnosing failures.

利用小波分析对非平稳信号强的时频分析能力和神经网络的自学习、分布式并行处理数据及非线性映射能力，以及它们适合于故障诊断的特点，说明小波与神经网络的松散型和和紧致型结合途径下产生的两种小波神经网络的各自特点及其在设备智能诊断中的应用。

Based on analyzing regression analysis, neural network and the least square support vector machines that the three soft computing methods fitting for data fitting, in the paper try to use nonlinear regression analysis, the BP neural network based on Levenberg-Marquardt training algorithm, radial basis function neural network on orthogonal least square training algorithm and least square support vector machines for tracking the position of glass plate.

本文在分析适于数据拟合的回归分析、神经网络、最小二乘支持向量机这三种"软计算"方法的基础上，尝试将非线性回归分析方法，基于Levenberg-Marquardt算法的BP神经网络，基于正交最小二乘训练算法的径向基函数神经网络和最小二乘支持向量机应用于玻璃板位的跟踪中。

The results indicate that the longitudinal nerve fibers in cerebral ganglia and a few of small cells in the surface layer of cerebral ganglia present NOS positive reaction. Abundant NOS positive small cells are in the surface layer of pedal ganglia, and abundant transverse positive nerve fibers in the center of pedal ganglia. A large number of transverse positive nerve fibers are in the center of visceral ganglia; abundant positive small cells and nerve fibers are in two anterior lobes; a few of positive small cells and many encircled positive nerve fibers are in the posterior lobe; a large number of radiate positive nerve fibers are in the lateral lobes.

组织化学显示，存在NOS的部位如下：脑神经节内纵行的神经纤维和表层的少量小细胞；足神经节表层的大量小细胞，中央大量水平分布的神经纤维；脏神经节中部大量水平分布的神经纤维，前叶内大量小细胞和神经纤维，后叶内少量小细胞和许多环行神经纤维，侧叶内大量似放射状分布的神经纤维；脑足和脑脏神经索内的神经纤维。

And we used them into the inspection of these polluted gases. We used them because the constringent speed of wavelet neural network is very fast, they are not sensitive to the inputs of the network and they have the characteristic that they also can effectively approach the functions or signals. Classical neural networks mostly train the network with back propagation algorithm.

在目前常用的一维小波神经网络的基础上，我们研究了用来处理多维数据信息的小波神经网络，并将其应用于室内混合气体检测，主要是基于小波神经网络学习收敛速度较快，对网络输入不是很敏感，以及小波神经网络可以有效的进行函数逼近或者信号逼近的特点。

The tight wavelet neural network was constituted taking the nonlinear Morlet wavelet radices as the stimulant function. The idiographic algorithm was presented. It can combine the advantages of wavelet analysis and neural networks.

以非线性Morlet小波基作为激励函数，形成神经元，结合小波变换与神经网络各自的优点，建立集小波分析与神经网络于一体的紧致型小波神经网络，并给出了具体的算法。

The simulation results show that the search-optimization capacity of wavelet chaotic neural network has been improved and the reformative wavelet chaotic neural network is superior to the primary wavelet chaotic neural networks.

仿真结果表明，改善了小波混沌神经网络的寻优能力，改进的小波混沌神经网络优于原来的小波混沌神经网络。

Objective: To provide anatomic basis for pectoranis minor muscle transplantation by vessels and nerves anastomosis to reconstruct thumb opposition function. Methods: The blood supply and nerve innervation of pectoralis minor muscle, the comparison of the morphology and dimension of both pectoralis minor muscle and thenar muscle were investigated on 20 sides of adult cadaveric thoraxes and hands. According to the locations of the vessels and nerves of the pectoralis minor, the clipped pectoralis minor muscle at the same side were transplanted and fixed to thenar muscles with the same direction of thenar muscle fiber. After that, the process of dragging simulating opposition movement of hand were performed and observed.

目的：为吻合血管神经的选择性胸小肌移植重建拇对掌功能术式提供解剖学依据方法：在20侧成人胸部及手部标本中，解剖观察胸小肌的血管神经分布及胸小肌和大鱼际肌的形态、大小并将一者进行比较；然后按照大鱼际肌纤维走行方向，参考血管神经位置，将胸小肌修剪合适后移植固定于同侧手部大鱼际，模拟正常手部拇对掌功能予以牵拉，观察标本手部拇对掌过程。

Each dorsal root has 8～10 rootlets, and every 4～5 rootlets formed 1～2 subbundles.

一个脊神经后根有8～10个神经小束组成，上位的4～5个神经小束形成1～2个神经亚束；下位的4～5个神经小束形成1～2个神经亚束。

According to the characteristic of wavelet packet transformation and fuzzy neural network, this paper proposed a new method of discriminating fault line for single-phase ground in distribution system based on the wavelet packet transformation and fuzzy neural network. The wavelet packet fuzzy neural network trained by the post fault zero sequence current is used to discriminate the fault line.

根据小波包变换和模糊神经网络的特点，提出了基於小波包变换模糊神经网络的一种小电流接地系统单相接地故障选线方法，即利用经过接地后零序电流训练的小波模糊神经网络来判别接地线路。

The split between the two groups can hardly be papered over.

这两个团体间的分歧难以掩饰。

This approach not only encourages a greater number of responses, but minimizes the likelihood of stale groupthink.

这种做法不仅鼓励了更多的反应，而且减少跟风的可能性。