人工神经网络预测热油环道启动压力

高含蜡原油管道停输后的再启动问题非常复杂。它涉及因素多，问题的非线性很强。而有足够多神经元的S型三层神经网络理论上可逼近任意有理函数。文章采用误差反向传播网络预测环道实验装置中的启动压力，得到了较好结果。     

DS18B20在解决应变测量中的应用

工业现场的温度变化范围大而剧烈，工作在工业现场的传感器大多数都对温度有一定的敏感度，这样就会使传感器的零点发生漂移，导致测量出现附加误差，因此温度补偿问题一直是传感器技术中的关键环节。根据单总线数字式温度传感器DS18820的工作原理、结构，并以电阻应变式传感器为例，提出了具体的补偿方案。     

Analysis of cell aggregation in the culturing of cerebellar granule neurons

We have proposed previously that an increased concentration of growth factor secreted by neurons themselves has a direct effect on survival of the neurons, and thereby cell density serves as a regulator of survival of neurons. In this study, the same idea was used to analyze the aggregation of cerebellar granule neurons in culture experimentally and theoretically. Assuming the transport of growth factor and substrate within an aggregate is by molecular diffusion, the metabolic efficiency of neurons, on the basis of an autocatalytic phenomenon, was increased within an aggregate compared to an identical quantity of dispersed cells. A good agreement in the size of neuronal aggregate between the theoretical prediction and the experimental result was found. This illustrates that growth factors produced by neurons acting in either an autocrine or paracrine manner play an important role during the development of cultured neurons.     

Investigation of morphological and functional changes during neuronal differentiation of PC12 cells by combined hopping probe ion conductance microscopy and patch-clamp technique

PC12 cells derived from rat pheochromocytoma can differentiate into sympathetic-neuron-like cells in response to nerve growth factor (NGF). These cells have been proved to be a useful cell model to study neuronal differentiation. NGF induces rapid changes in membrane morphology, neurite outgrowth, and electrical excitability. However, the relationship between the 3D morphological changes of NGF-differentiated PC12 cells and their electrophysiological functions remains poorly understood.In this study, we combined a recently developed Hopping Probe Ion Conductance Microscopy (HPICM) with patch-clamp technique to investigate the high-resolution morphological changes and functional ion-channel development during the NGF-induced neuronal differentiation of PC12 cells. NGF enlarged TTX-sensitive sodium currents of PC12 cells, which associated with cell volume, membrane surface area, surface roughness of the membrane, and neurite outgrowth. These results demonstrate that the combination of HPICM and patch-clamp technique can provide detailed information of membrane microstructures and ion-channel functions during the differentiation of PC12 cells, and has the potential to become a powerful tool for neuronal research.     

基于LonWorks总线型智能有毒有害气体变送器的设计

介绍一种基于LonWorks总线型智能有毒有害气体变送器的工作原理、硬件电路设计和软件设计。这种智能变送器不仅具有大屏幕液晶显示、声光报警功能,而且带有LonWorks总线接口,能够广泛应用于LonWorks总线系统或其他DCS系统中。     

一种量子神经网络模型及改进学习算法

提出一种量子BP网络模型及改进学习算法,该BP网络模型首先基于量子学中一位相移门和两位受控非门的通用性,构造出一种量子神经元,然后由该量子神经元构造隐含层,采用梯度下降法进行学习。输出层采用传统神经元构造,采用基于改进的带动量自适应学习率梯度下降法学习。在UCI两个数据集上采用该模型及算法,实验结果表明该方法比传统的BP网络具有较好的收敛速度和正确率。     

一种用于立体匹配的改进的神经网络方法

实现了一种用于静态视觉立体匹配的神经网络方法。文献［１］提出了一种用于静态体视匹配的神经网络方案,其方案用于随机点图对时存在严重的缺陷。针对随机点图对的特点,对神经网络的偏置输入进行了修正,改进的神经网络能够有效地提取随机点图对中的立体深度信息。为了进一步提高收敛速度和平滑边缘特征,又在偏置输入中引入射线特征,改进了神经元的初始化。在工作站上进行的大量实验模拟表明,我们所做的改进提高了网络的迭代速度和视差图的边缘特征平滑性。     

A network of pyramidal neurons is sensitive to the timing of its excitatory inputs

The transmission of excitatory inputs by a network of coupled pyramidal cells is investigated by means of numerical simulations. The pyramidal cell models are coupled by excitatory synapses and each one receives an excitatory pulse at a random time extracted from a Gaussian distribution. Moreover, each cell model is injected with a noisy current. It was found that the excitatory coupling promotes the transmission of the synaptic inputs on a time scale of a few ms.     

Multiple resonances with time delays and enhancement by non-Gaussian noise in Newman-Watts networks of Hodgkin-Huxley neurons

In this paper, we study the effect of time delay on the spiking activity in Newman-Watts small-world networks of Hodgkin-Huxley neurons with non-Gaussian noise, and investigate how the non-Gaussian noise affects the delay-induced behaviors. It was found that, as the delay increases, the neuron spiking intermittently performs the most ordered and synchronized behavior when the delay lengths are integer multiples of the spiking periods, which shows multiple temporal resonances and spatial synchronizations, and reveals that the locking between the delay lengths and the spiking periods might be the mechanism behind the behaviors. It was also found that the delay-optimized spiking behaviors could be enhanced when non-Gaussian noise's deviation from the Gaussian noise is appropriate. These results show that time delay and non-Gaussian noise would cooperate to play more constructive and efficient roles in the information processing of neural networks.     

SOM神经网络算法的研究与进展

自组织映射(Self-organizing Maps，SOM)算法是一种无导师学习方法，具有良好的自组织、可视化等特性，已经得到了广泛的应用和研究。该文系统地介绍了SOM算法的产生背景、基本算法。同时对SOM算法的参数设置和其不足进行了分析。重点归纳了其发展过程中的各种改进算法，并对其研究热点及应用领域作了简要的综述，最后展望了该算法的发展方向。