Discussion on the basic mathematical models of neurons - Double synaptic weight neuron in general-purpose neurocomputer, theory and application

Based on the introduction of the traditional mathematical models of neurons in general-purpose neurocomputer, a novel all-purpose mathematical model-Double synaptic weight neuron (DSWN) is presented, which can simulate all kinds of neuron architectures, including Radial-Basis-Function (RBF) and Back-propagation (BP) models, etc. At the same time, this new model is realized using hardware and implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. In this paper, the flexibility of the new model has also been described in constructing neural networks and based on the theory of Biomimetic pattern recognition (BPR) and high-dimensional space covering, a recognition system of omni directionally oriented rigid objects on the horizontal surface and a face recognition system had been implemented on CASSANN-H neurocomputer. The result showed DSWN neural network has great potential in pattern recognition.

Research on multi-degree-of-freedom neurons with weighted graphs

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

Wavelet denoising and feature extraction of seismic signal for footstep detection

Seismic sensors are widely used to detect moving target in ground sensor networks. Footstep detection is very important for security surveillance and other applications. Because of non-stationary characteristic of seismic signal and complex environment conditions, footstep detection is a very challenging problem. A novel wavelet denoising method based on singular value decomposition is used to solve these problems. The signal-to-noise ratio (SNR) of raw footstep signal is greatly improved using this strategy. The feature extraction method is also discussed after denosing procedure. Comparing, with kurtosis statistic feature, the wavelet energy feature is more promising for seismic footstep detection, especially in a long distance surveillance.

Computational information geometry and its applications

Digitization is the main feature of modern Information Science. Conjoining the digits and the coordinates, the relation between Information Science and high-dimensional space is consanguineous, and the information issues are transformed to the geometry problems in some high-dimensional spaces. From this basic idea, we propose Computational Information Geometry (CIG) to make information analysis and processing. Two kinds of applications of CIG are given, which are blurred image restoration and pattern recognition. Experimental results are satisfying. And in this paper, how to combine with groups of simple operators in some 2D planes to implement the geometrical computations in high-dimensional space is also introduced. Lots of the algorithms have been realized using software.

The structure and function of neurons with variable nonlinear transfer function

One novel neuron with variable nonlinear transfer function is firstly proposed, It could also be called as subsection transfer function neuron. With different transfer function components, by virtue of multi-thresholded, the variable transfer function neuron switch on among different nonlinear excitated state. And the comparison of output's transfer characteristics between it and single-thresholded neuron will be illustrated, with some practical application experiments on Bi-level logic operation, at last the simple comparison with conventional BP, RBF, and even DBF NN is taken to expect the development foreground on the variable neuron.. The novel nonlinear transfer function neuron could implement the random nonlinear mapping relationship between input layer and output layer, which could make variable transfer function neuron have one much wider applications on lots of reseach realm such as function approximation pattern recognition data compress and so on.

An algorithm of analysis tools on points distribution in high dimension space: The distance of a point and an infinite sub-space

This paper discusses the algorithm on the distance from a point and an infinite sub-space in high dimensional space With the development of Information Geometry([1]), the analysis tools of points distribution in high dimension space, as a measure of calculability, draw more attention of experts of pattern recognition. By the assistance of these tools, Geometrical properties of sets of samples in high-dimensional structures are studied, under guidance of the established properties and theorems in high-dimensional geometry.

Research on multi-degree-of-freedom neurons with weighted graphs

In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - Multi-Degree-of-Freedorn Neurons (MDFN). Base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. It identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. Experiment results demonstrates the general superiority of this algorithm over the traditional PCA+NN algorithm in terms of efficiency and accuracy.

Continuous speech research based on HyperSausage Neuron

In this paper, we presents HyperSausage Neuron based on the High-Dimension Space(HDS), and proposes a new algorithm for speaker independent continuous digit speech recognition. At last, compared to HMM-based method, the recognition rate of HyperSausage Neuron method is higher than that of in HMM-based method.

A New Discrimination Method of Maize Seed Varieties Based on Near-Infrared Spectroscopy

A new discrimination method for the maize seed varieties based on the near-infrared spectroscopy was proposed. The reflectance spectra of maize seeds were obtained by a FT-NIR spectrometer (12 000-4 000 cm(-1)). The original spectra data were preprocessed by first derivative method. Then the principal component analysis (PCA) was used to compress the spectra data. The principal components with the cumulate reliabilities more than 80% were used to build the discrimination models. The model was established by Psi-3 neuron based on biomimetic pattern recognition (BPR). Especially, the parameter of the covering index was proposed to assist to discriminating the variety of a seed sample. The authors tested the discrimination capability of the model through four groups of experiments. There were 10, 18, 26 and 34 varieties training the discrimination models in these experiments, respectively. Additionally, another seven maize varieties and nine wheat varieties were used to test the capability of the models to reject the varieties not participating in training the models. Each group of the experiment was repeated three times by selecting different training samples at random. The correct classification rates of the models in the four-group experiments were above 91. 8%. The correct rejection rates for the varieties not participating in training the models all attained above 95%. Furthermore, the performance of the discrimination models did not change obviously when using the different training samples. The results showed that this discrimination method can not only effectively recognize the maize seed varieties, but also reject the varieties not participating in training the model. It may be practical in the discrimination of maize seed varieties.

OpenOffice.org对非BMP平面字符支持的实现

Unicode标准中的非BMP平面字符多用于古籍研究或者少数民族语言文字,由于这些字符的使用面特别窄,多数软件系统包括办公软件都不支持对这些字符的处理。本文以开源办公套件OpenOffice.org为基础,分析了它对非BMP平面支持的现状,然后着重探讨了实现对非BMP平面字符的全面支持所需要解决的一系列问题,并分别给出了合理的改进方案,最后以CJK和藏文为例展示了改进后的效果。

天然免疫相关分子的进化

本论文结合功能研究和进化遗传学方法对动物天然免疫（innate immunity）相关分子的进化历程进行深入研究。受体对病原微生物的识别是天然免疫系统发挥功能的基础。作为模式识别受体（pattern recognition receptor, PRR），果蝇肽聚糖识别蛋白SD（PGRP-SD）在识别革兰氏阳性细菌的过程中发挥了重要作用。针对已有的黑腹果蝇（Drosophila melanogaster）群体数据，我们发现PGRP-SD在群体中存在2类高频的等位基因（分别为等位基因1和等位基因2）。以D. simulans为外群，我们追溯了黑腹果蝇2类等位基因上氨基酸的变化。这些氨基酸的结构特征和在蛋白质上所处的位置提示这2类等位基因在功能方面可能存在分化。通过功能研究的方法，我们发现在黑腹果蝇中该基因功能方面发生了显著的变化。等位基因2在有微生物时能激活天然免疫反应，但等位基因1的转基因果蝇成虫只要有外伤即便没有微生物的情况下即能激发天然免疫反应，而带有等位基因2果蝇成虫则不具有该功能。这一结果提示我们，发生在该等位基因上的氨基酸变化导致了其识别功能的变化。与推导的祖先基因相比，等位基因1发生了一个氨基酸的变化，因此导致其功能从识别细菌细胞壁组分肽聚糖转变为一未知的自身组分，即从病原相关分子模式（pathogen-associated molecular pattern，PAMP）识别受体转变为损伤相关识别模式（damage-associated molecular pattern, DAMP）识别受体。通过这一功能变化， 果蝇成虫可以通过仅识别自身损伤即可激活相应的免疫反应，对后续可能侵入的微生物进行杀伤。已有研究结果显示，微生物在进化过程中已经形成针对DAMP和PAMP规避策略。上述2类等位基因的同时存在能使黑腹果蝇同时具备两个机制，更加充分地抵抗病原微生物的入侵。结合功能研究和针对自然群体的群体遗传学分析，我们认为在黑腹果蝇群体中以高频共存的2类PGRP-SD等位基因可能可能受到了平衡选择（balancing selection）作用。上述工作主要研究了天然免疫系统识别受体的进化。而本论文的另一部分则主要针对天然免疫系统的效应分子（effector）进行了研究。作为重要的效应分子，抗菌肽在杀菌方面发挥着最为直接的作用。因此，研究抗菌肽的进化对于探索天然免疫系统的进化具有重要意义。本研究以两栖类动物大蹼铃蟾抗菌肽基因家族为例，通过对分别来自2个大蹼铃蟾个体的皮肤cDNA文库进行测序，我们鉴别出56个不同的抗菌肽cDNA序列。每一个cDNA均编码2个不同的抗菌肽，maximin 和maximin H。基于针对这些cDNA序列的分析，我们发现2类抗菌肽编码序列的非同义替代率均高于同义替代率，呈现高度分化的特征。但是，在信号肽和其它非抗菌肽编码区域并没有发现这种情况。这一结果提示抗菌肽可能受到超显性选择（overdominent selection, 即平衡选择）的影响。同时，我们分别从皮肤和肝脏克隆基因了7个抗菌肽的基因组编码序列并进行了测序。这些从不同组织获得的抗菌肽在各个编码序列中均存在序列的差异的同时呈现了相同的结构。这一结果提示不同抗菌肽间的差异不太可能来自于体细胞突变而是快速序列进化的结果。通过构建来自于同一个体的抗菌肽的不同编码区的基因树，我们发现结构域重排（domain shuffling）和/或基因转换（gene conversion）在这些抗菌肽的进化历程中发挥作用。