神经组织

But because of some bugs, they cannot be applied more widely. Base on these, a new control method called ""self-organized fuzzy control base on dynamic structure neural network ""is proposed in this article. It syncretizes the strongpoint of Fuzzy control and Neural Net control, and attain optimization control with the adjusting the number of the net's layer.

针对这种时变大时滞被控对象的特点，目前主要采用Smith、Dahlin和IMC控制，这些控制方法在某方面可能得到一定应用，但由于其本身存在某些缺陷，因此不可能得到广泛应用，笔者在此基础上提出了一种基于动态结构的神经网络自组织模糊控制，它融合了神经网络和模糊控制的优点，并能通过在线调整网络的层数以达到最优控制的效果。

Methods Adult male waster rats were randomly divided into the normal control pseudo-group and the experimental operation-group. In the operation-group, the right sciatic nerve was transected and survived for 1, 2, 4, 6 and 8 weeks after operation.

选取健康成年雄性Wister大鼠80只，随机分为假手术组和坐骨神经切断组，分别于术后1、2、4、6、8周五个时相处死后取患侧L4-L6背根神经节，应用Western Blot和免疫组织化学技术检测P-ERK1/2在背根神经节中的表达变化。

How to exactly measure the coal mass of pulverizer in fossil power plant is one of primary causes that the efficiency of milling control is low and the automation is difficult to running. Aiming at the limitation of evidential theory, As the neural network has self-organize, self-learn, collateral distributing manage, strong fault tolerant and robustness, we combined the evidential theory and the neural network and put forward a two-step fusion method.

火电厂中钢球磨煤机筒内存煤量的测量问题一直是制粉控制效率低和自动控制难以投入运行的主要原因之一，针对D-S 证据理论存在的不足，而利用神经网络具有的自组织、自学习、并行分布处理、高度容错性和鲁棒性的特点，本文提出了一种将证据理论与神经网络相结合的数据融合方法，并将其用于解决球磨机存煤量的测量问题。

Compare the effect of different chemical methods for preparation of acellular nerve scaffold and to provide an effective nerve scaffold for tissue engineering.

目的 比较不同化学方法制备去细胞神经支架的效果，提供有效的组织工程神经支架。

Objective To investigate the construction of tissue engineering collagen nerve conduits and repair peripheral nerve defects.

目的 探讨组织工程化胶原神经导管的构建及对外周神经缺损的修复。

This paper presents a Double Kohonen Neural Network lased on the Self－Organize Feature Mapping theory to analyge chomosome automatiolly. The DKNN consists of two layers, each of which is a Kohonen network. The first layer maps a 2－d plane to a 2－d feature space to extract the high－resolution bands of chromosome and to compute the parameters of bands. The second layer maps the arrays of high dimension feature parameters to a 2－d plane to pair and classify the chromosomes automatically.

应用自组织特征映射神经网络原理与方法，建立了双层Kohonen神经网络，其第一层是从二维图象平面到二维特征平面的映射，用于染色体高分辨率带纹的提取和带纹参数的计算，第二层是高维特征参数阵列到二维聚类平面的映射，用于同源染色体的自动配对和分类。

The check of mutation of video camera lens that offerred a kind to be based on BP nerve network newly calculates a standard, this algorithm chooses pattern plate to match poor cent and histogram 2 times 2 times to differ cent to serve as a feature, those who use nerve network from organization, self-study mutation of camera lens of implementation of ability of be used to detects, detect in order to flash next will raise detected dependability.

提出了一种新的基于BP神经网络的视频镜头突变检测算法，该算法选取模板匹配二次差分和直方图二次差分作为特征，利用神经网络的自组织、自学习能力实现镜头突变检测，然后以闪光检测来提高检测的可靠性。

Methods 12 patients with soft tissues defects around the foot of the diabetes were repaired by musculocutaneous,neurocutaneous axial island flaps transfer which included 4 cases of femoral forelateral flap,1 case of latissimus dorsi muscular flap,1 case of tensor fascia lata musculocutaneous flap,3 case of island flaps based on the sural nerve,1 case of island flaps based on the peroneus superficialis nerve and 2 cases of medial crural faee flap.

采用股前外侧皮瓣4例，背阔肌皮瓣1例，阔筋膜张肌皮瓣1例游离移植，腓肠神经营养血管蒂岛状皮瓣逆行转位3例，腓浅神经营养血管蒂岛状皮瓣逆行转位1例，小腿内侧皮瓣2例逆行移植修复糖尿病足组织缺损创面12例。

All the indexes were tested in 2 -. 4 .. 6 weeks of operative intervals respectively. Results:(1) The general observation in the experimental group ,such as spirit, hair, body weight and activity ,was superior to that in the control group.(2) The recovery rate of sciatic nerve functional index (SF1) was statistically significantly higher in the experimental group than in the control group .(3) electrophysciological indexes: m the experimental group ,the tardy rate of induced motorius action potential ,recovery rates of the amplitude of compound muscle action potential and twitch tension and tetanic tension of triceps surae muscle ,were significantly higher than in the control group.(4) Compared with the control group ,the triceps surae muscle wet weight was significantly greater in the experimental group.(5) histomorphological indexes: the count of myelinated nerve fibers ,diameter of regenerated axon, thickness of nerve myelin sheath and area of capillary were much more in the experimental group than in the control group.(6) observation of ultrastructure with the transmission election microscope: more abundant organell a and maturer myelin sheath lay in the injured peripheral nerve of the experimental group, while not lay in the control group.

分别在木后第2、4、6周时进行各项指标的检测，结果发现：（1）实验组SD大鼠在整个实验过程中，其精神、毛发、体重，运动灵活性等一般情况优于对照组；（2）实验组的坐骨神经功能指数恢复率显著优于对照组，P＜0.01；（3）神经电生理指标：实验组运动神经诱发电位潜伏期的延迟率显著优于对照组，P＜0.05；复合肌肉动作电位振幅的恢复率显著高于对照组，两组比较第2周时P＜0.01，第4、6周时，P＜0.05；小腿三头肌单收缩力和强直收缩力的恢复率实验组显著高于对照组，P＜0.01；（4）小腿三头肌湿重的恢复率，第2、4周时实验组高于对照组，差异非常显著，P＜0.01；第6周时，差异仍显著，P＜0.05；（5）组织形态学指标：有髓种经轴突计数、再生轴突直径的恢复率，毛细血管面积，实验组均显著大于对照组，P＜0.01、P＜0.05、P＜0.001；实验组髓鞘厚度的恢复率也显著高于对照组，第2周时P＜0.01，第4、6周时，P＜0.05；（6）透射电镜超微结构观察：实验组再生轴突中细胞器丰富，髓鞘结构成熟，神经再生情况优于对照纽。

In allusion to weak point of traditional PID control can't effectively tracking parametric variation of control system ,utilize neural network have predominance that self-study、self-organization、associative memory、concurrent processing and can get satisfactory result in complex control system on the basis of double closed loop,advance apply adaptive linear element network—Adaline network, which has self-learn and self-adjust ability.

在双闭环控制的基础上，针对经典PID调节器不能有效跟踪控制系统参数变化过程这一弱点，利用神经网络具有自学习、自组织、联想记忆和并行处理等功能和对于复杂系统控制可以达到满意效果的优势，提出了采用具有自学习和自适应能力的单神经元网络——Adaline网络，来构成一种神经网络自校正控制器。

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。