The application of DBF neural networks for object recognition

On the basis of DBF nets proposed by Wang Shoujue, the model and properties of DBF neural network were discussed in this paper. When applied in pattern recognition, the algorithm and implement on hardware were presented respectively. We did experiments on recognition of omnidirectionally oriented rigid objects on the same level, using direction basis function neural networks, which acts by the method of covering the high dimensional geometrical distribution of the sample set in the feature space. Many animal and vehicle models (even with rather similar shapes) were recognized omnidirectionally thousands of times. For total 8800 tests, the correct recognition rate is 98.75%, the error rate and the rejection rate are 0.5% and 1.25% respectively. (C) 2003 Elsevier Inc. All rights reserved.

Double synaptic weight neuron theory and its application

In this paper, a novel mathematical model of neuron-Double Synaptic Weight Neuron (DSWN)(l) is presented. The DSWN can simulate many kinds of neuron architectures, including Radial-Basis-Function (RBF), Hyper Sausage and Hyper Ellipsoid models, etc. Moreover, this new model has been implemented in the new CASSANN-II neurocomputer that can be used to form various types of neural networks with multiple mathematical models of neurons. The flexibility of the DSWN has also been described in constructing neural networks. 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-II neurocomputer. In these two special cases, the result showed DSWN neural network had great potential in pattern recognition.

Geometrical learning, descriptive geometry, and biomimetic pattern recognition

Studies on learning problems from geometry perspective have attracted an ever increasing attention in machine learning, leaded by achievements on information geometry. This paper proposes a different geometrical learning from the perspective of high-dimensional descriptive geometry. Geometrical properties of high-dimensional structures underlying a set of samples are learned via successive projections from the higher dimension to the lower dimension until two-dimensional Euclidean plane, under guidance of the established properties and theorems in high-dimensional descriptive geometry. Specifically, we introduce a hyper sausage like geometry shape for learning samples and provides a geometrical learning algorithm for specifying the hyper sausage shapes, which is then applied to biomimetic pattern recognition. Experimental results are presented to show that the proposed approach outperforms three types of support vector machines with either a three degree polynomial kernel or a radial basis function kernel, especially in the cases of high-dimensional samples of a finite size. (c) 2005 Elsevier B.V. All rights reserved.

Differences and commonalities between connectionism and symbolicism

The differences between connectionism and symbolicism in artificial intelligence (AI) are illustrated on several aspects in details firstly; then after conceptually decision factors of connectionism are proposed, the commonalities between connectionism and symbolicism are tested to make sure, by some quite typical logic mathematics operation examples such as "parity"; At last, neuron structures are expanded by modifying neuron weights and thresholds in artificial neural networks through adopting high dimensional space geometry cognition, which give more overall development space, and embodied further both commonalities.

A criterion for local interconvertibility between all-tripartite Gaussian states

We arrive at a necessary and sufficient criterion that can be readily used for interconvertibility between general, all-tripartite Gaussian states under local quantum operation. The derivation involves a systematic reduction that converts the original complex conditions in high-dimensional, 6n x 6n matrix space eventually into 2 x 2 matrix problems.

Research on continuous speech recognition with small vocabulary based on biomimetic pattern recognition

Based on biomimetic pattern recognition theory, we proposed a novel speaker-independent continuous speech keyword-spotting algorithm. Without endpoint detection and division, we can get the minimum distance curve between continuous speech samples and every keyword-training net through the dynamic searching to the feature-extracted continuous speech. Then we can count the number of the keywords by investigating the vale-value and the numbers of the vales in the curve. Experiments of small vocabulary continuous speech with various speaking rate have got good recognition results and proved the validity of the algorithm.

Geometry property of multi-degree of freedom neurons

In this paper, we study a problem of geometric inequalities for a Multi-degree of Freedom Neurons. Some new geometric inequalities for a Multi-degree of Freedom Neurons are established. As special cases, some known inequalities are deduced.

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.

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.

机载SAR实时成像系统中的数据可视化研究

SAR实时成像系统在国防等很多领域都有着重要的应用 ,系统对数据可视化方面的要求也越来越高 ,但目前国内对SAR实时成像系统的数据可视化方面的研究还不多 提出了一种针对SAR实时成像系统的新的数据可视化方案 ,并已在实际的飞行成像中得到了检验 新方案实时提供的信息更全面、更直观、可分析性更强 ,具有较强的信息表现能力和双向实时交互能力 ,能够较好地辅助对图像的在线分析 还对方案的重要组成部分———缩略图的原理和实现算法做了概括介绍

Biomimetic (topological) pattern recognition - A new model of pattern recognition theory and its application

A new theoretical model of Pattern Recognition principles was proposed, which is based on "matter cognition" instead of "matter classification" in traditional statistical Pattern Recognition. This new model is closer to the function of human being, rather than traditional statistical Pattern Recognition using "optimal separating" as its main principle. So the new model of Pattern Recognition is called the Biomimetic Pattern Recognition (BPR)(1). Its mathematical basis is placed on topological analysis of the sample set in the high dimensional feature space. Therefore, it is also called the Topological Pattern Recognition (TPR). The fundamental idea of this model is based on the fact of the continuity in the feature space of any one of the certain kinds of samples. We experimented with the Biomimetic Pattern Recognition (BPR) by using artificial neural networks, which act through covering the high dimensional geometrical distribution of the sample set in the feature space. Onmidirectionally cognitive tests were done on various kinds of animal and vehicle models of rather similar shapes. For the total 8800 tests, the correct recognition rate is 99.87%. The rejection rate is 0.13% and on the condition of zero error rates, the correct rate of BPR was much better than that of RBF-SVM.

Validation and in situ application of an automated dissolved nickel monitor for estuarine studies

The validation of a fully automated dissolved Ni monitor for in situ estuarine studies is presented, based on adsorptive cathodic stripping voltammetry (AdCSV). Dissolved Ni concentrations were determined following on-line filtration and UV digestion, and addition of an AdCSV ligand (dimethyl glyoxime) and pH buffer (N-2-hydroxyethylpiperazine-N′-2-ethanesulphonic acid). The technique is capable of up to six fully quantified Ni measurements per hour. The automated in situ methodology was applied successfully during two surveys on the Tamar estuary (south west Britain). The strongly varying sample matrix encountered in the estuarine system did not present analytical interferences, and each sample was quantified using internal standard additions. Up to 37 Ni measurements were performed during each survey, which involved 13 h of continuous sampling and analysis. The high resolution data from the winter and summer tidal cycle studies allowed a thorough interpretation of the biogeochemical processes in the studied estuarine system.

A study of isomeric diglycosyl flavonoids by SORI CID of Fourier transform ion cyclotron mass Spectrometry in negative ion mode

High-resolution Sustained off resonance irradiation (SORI) CID was employed to distinguish four pairs of isomeric diglycosyl flavonoids in the negative mode using the electrospray ionization Fourier transform ion cyclotron resonance mass spectrometry (ESI FTICR MS). All of these isomers can be distinguished via MS/MS data. For these diglycosyl flavones and flavanones, the deprotonated alpha 1-->6 linkage diglycosyl flavonoids produce fewer fragments than the alpha 1-->2 linkage type compounds and the Retro-Diels-Alder (RDA) reaction in MS/MS only takes place when the aglycone is a flavanone and glycosylated with an alpha 1-->2 intersaccharide linkage disaccharide. The deprotonation sites after collisional activation are discussed according to the high mass accuracy and high-resolution data of tandem spectrometry. Some of these high-resolution SORI CID product ions from alpha 1-->2 linkage diglycosyl flavonoids involve multibond cleavages; the possible mechanism is discussed based on the computer modeling using Gaussian 03 program package at the B3LYP/6-31G level of theory. Unambiguous elementary composition data provides fragmentation information that has not been reported previously.

面向实时控制任务的高速数据采集存储方法

提出一种基于CAN总线,面向实时控制任务的高速数据采集存储方法.该方法将数据实时采集、系统实时控制、数据存储与显示分配在相互独立的处理单元中实现,处理单元之间通过独立的CAN网络进行通信.该数据采集方法解决了数据实时采集与系统实时控制之间的矛盾.利用队列技术,该方法解决了数据存储与数据实时显示之间的矛盾.该数据采集存储方法已成功应用到某大型仿真系统中.

提高勘探成熟区地震资料精度的方法研究

With the Oil field exploration and exploitation, the problem of supervention and enhaning combination gas recovery was faced.then proposing new and higher demands to precision of seismic data. On the basis of studying exploration status,resource potential,and quality of 3D seismic data to internal representative mature Oil field, taking shengli field ken71 zone as study object, this paper takes advantage of high-density 3D seismic technique to solving the complex geologic problem in exploration and development of mature region, deep into researching the acquisition, processing of high-density 3D seismic data. This disseration study the function of routine 3D seismic, high-density 3D seismic, 3D VSP seismic,and multi-wave multi-component seismic to solving the geologic problem in exploration and development of mature region,particular introduce the advantage and shortage of high-density 3D seismic exploration, put forward the integrated study method of giving priority to high-density 3D seismic and combining other seismic data in enhancing exploration accuracy of mature region. On the basis of detailedly studying acquisition method of high-density 3D seismic and 3D VSP seismic,aming at developing physical simulation and numeical simulation to designing and optimizing observation system. Optimizing “four combination” whole acquisition method of acquisition of well with ground seimic and “three synchron”technique, realizing acquisition of combining P-wave with S-wave, acquisition of combining digit geophone with simulation geophone, acquisition of 3D VSP seismic with ground seimic, acquisition of combining interborehole seismic,implementing synchron acceptance of aboveground equipment and downhole instrument, common use and synchron acceptance of 3D VSP and ground shots, synchron acquisition of high-density P-wave and high-density multi-wave, achieve high quality magnanimity seismic data. On the basis of detailedly analysising the simulation geophone data of high-density acquisition ,adopting pertinency processing technique to protecting amplitude,studying the justice matching of S/N and resolution to improving resolution of seismic profile ,using poststack series connection migration,prestack time migration and prestack depth migration to putting up high precision imaging,gained reliable high resolution data.At the same time carrying along high accuracy exploration to high-density digit geophone data, obtaining good improve in its resolution, fidelity, break point clear degree, interbed information, formation characteristics and so on.Comparing processing results ,we may see simulation geophone high-density acquisition and high precision imaging can enhancing resolution, high-density seismic basing on digit geophone can better solve subsurface geology problem. At the same time, fine processing converted wave of synchron acquisition and 3D VSP seismic data,acquiring good result. On the basis of high-density seismic data acquisition and high-density seismic data processing, carry through high precision structure interpretation and inversion, and preliminary interpretation analysis to 3D VSP seismic data and multi-wave multi-component seismic data. High precision interpretation indicates after high resolution processing ,structural diagram obtaining from high-density seismic data better accord with true geoligy situation.