The multi-weight neuron with geometry algorithm and its application

A novel approach for multi-dimension signals processing, that is multi-weight neural network based on high dimensional geometry theory, is proposed. With this theory, the geometry algorithm for building the multi-weight neuron is mentioned. To illustrate the advantage of the novel approach, a Chinese speech emotion recognition experiment has been done. From this experiment, the human emotions are classified into 6 archetypal classes: fear, anger, happiness, sadness, surprise and disgust. And the amplitude, pitch frequency and formant are used as the feature parameters for speech emotion recognition. Compared with traditional GSVM model, the new method has its superiority. It is noted that this method has significant values for researches and applications henceforth.

基于NN的人形机器人自适应H_∞位置跟踪控制

研究一种正交轮式移动车为载体的类人形机器人的建模与控制问题．首先基于分体建模的思想,采用机理建模和神经网络技术相结合的方法建立了动力学模型;然后依据该模型,提出一种新的基于 NN 的自适应 H_∞位置跟踪控制器,使鲁棒非线性 H_∞控制方法自然地与模型的直接自适应神经网络技术集成为一体,并证明了其鲁棒稳定性．最后,仿真研究验证了该方法的正确性和有效性．

水下机器人神经网络自适应逆控制

水下环境的复杂性以及自身模型的不确定性,给水下机器人的控制带来很大困难。针对水下机器人的特点和控制方面所存在的问题,提出了基于预测 校正控制策略的水下机器人神经网络自适应逆控制结构及训练算法。通过在线辨识系统的前向模型,估计出系统的Jacobian矩阵,然后采用预报误差法实现控制器的自适应。同时,为了提高系统对于外扰的鲁棒性,在伪线性回归算法的基础上,在评价函数中引入微分项。理论分析和仿真结果表明,与原来的算法相比,微分项的引入改善了系统对于外扰的鲁棒性和动态性能。

基于神经网络的一类非线性系统模型参考控制

针对一类非线性系统,提出了一种神经网络模型参考控制方案。在训练实现对象模型的网络和实现控制器的网络时,由状态方程产生训练样本。通过对倒立摆系统的仿真实验验证了控制方案和样本生成策略的有效性,在仿真实验中用不同初始状态验证了训练后的神经网络的泛化能力。

一种基于神经网络的生产调度方法

提出解决具有开、完工期限制的约束Ｊｏｂ－ｓｈｏｐ生产调度问题的一种神经网络方法．该方法通过约束神经网络，描述各种加工约束条件，并对不满足约束的开工时间进行相应调节，得到可行调度方案；然后由梯度搜索算法优化可行调度方案，直至得到最终优化可行调度解．理论分析、仿真实验表明了方法的有效性。

基于LabVIEW的自组织网络的实现与应用

文章介绍了自组织神经网络在故障诊断方面的应用原理,针对自组织神经网络实现问题提出了一种通过在LabVIEW调用MATLAB应用程序实现自组织神经网络的方法。并通过轴承故障诊断的实例,证明了这种方法的有效性。

Parameters Inversion of Fluid-Saturated Porous Media Based on Neural Networks

The multi-layers feedforward neural network is used for inversion of material constants of fluid-saturated porous media. The direct analysis of fluid-saturated porous media is carried out with the boundary element method. The dynamic displacement responses obtained from direct analysis for prescribed material parameters constitute the sample sets training neural network. By virtue of the effective L-M training algorithm and the Tikhonov regularization method as well as the GCV method for an appropriate selection of regularization parameter, the inverse mapping from dynamic displacement responses to material constants is performed. Numerical examples demonstrate the validity of the neural network method.

A novel FOCAL technique based on BP-ANN

In this paper, the feed-forward back-propagation artificial neural network (BP-ANN) algorithm is introduced in the traditional Focus Calibration using Alignment procedure (FOCAL) technique, and a novel FOCAL technique based on BP-ANN is proposed. The effects of the parameters, such as the number of neurons on the hidden-layer and the number of training epochs, on the measurement accuracy are analyzed in detail. It is proved that the novel FOCAL technique based on BP-ANN is more reliable and it is a better choice for measurement of the image quality parameters. (c) 2005 Elsevier GmbH. All rights reserved.

Study on text-dependent speaker recognition based on Biomimetic Pattern Recognition

We studied the application of Biomimetic Pattern Recognition to speaker recognition. A speaker recognition neural network using network matching degree as criterion is proposed. It has been used in the system of text-dependent speaker recognition. Experimental results show that good effect could be obtained even with lesser samples. Furthermore, the misrecognition caused by untrained speakers occurring in testing could be controlled effectively. In addition, the basic idea "cognition" of Biomimetic Pattern Recognition results in no requirement of retraining the old system for enrolling new speakers.

A novel image restoration algorithm based on high-dimensional space geometry

A novel image restoration approach based on high-dimensional space geometry is proposed, which is quite different from the existing traditional image restoration techniques. It is based on the homeomorphisms and "Principle of Homology Continuity" (PHC), an image is mapped to a point in high-dimensional space. Begin with the original blurred image, we get two further blurred images, then the restored image can be obtained through the regressive curve derived from the three points which are mapped form the images. Experiments have proved the availability of this "blurred-blurred-restored" algorithm, and the comparison with the classical Wiener Filter approach is presented in final.

Nanoelectronic Circuit Architectures Based on Single-Electron Turnstiles

Single-electron devices (SEDs) have ultra-low power dissipation and high integration density, which make them promising candidates as basic circuit elements of the next generation VLSI circuits. In this paper, we propose two novel circuit single-electron architectures: the single-electron simulated annealing algorithm (SAA) circuit and the single-electron cellular neural network (CNN). We used the MOSFET-based single-electron turnstile [1] as the basic circuit element. The SAA circuit consists of the voltage-controlled single-electron random number generator [2] and the single-electron multiple-valued memories (SEMVs) [3]. The random-number generation and variable variations in SAA are easily achieved by transferring electrons using the single-electron turnstile. The CNN circuit used the floating-gate single-electron turnstile as the neural synapses, and the number of electrons is used to represent the cells states. These novel circuits are promising in future nanoscale integrated circuits.