Research of IDSS Architecture Based on Hybrid Systems

This paper discusses the necessity of building IDSS on hybrid systems, and adopts XML technology to manage isomeric knowledge in hybrid systems. The paper proposes a new architecture of hybrid systems based IDSS whose core system is isomeric knowledge system. The architecture is composed of knowledge component, problems processing system, data component and intelligent user interface. This new architecture aims to enhance the capability of integrating hybrid systems, to improve the supporting effectiveness of decision-making and the intelligent level of IDSS, and tries a new way to elevate the system＇s ability of handling and learning knowledge.     

A Computational Model for the Prediction of Seam Pucker

This paper reports on a computational model established based on discriminant analysis for predicting the occur-rence of seam pucker and advising on the correction of causing variables (e. g. fabric properties) to prevent seam pucker. The model has a self - updating feature, viz. automatically up - dating model parameters to im-prove the reliability of the model as new data becomes available. It has been successfully implemented in a re-cently developed sewability system.     

Rank sum method for related gene selection and its application to tumor diagnosis

Tumor diagnosis by analyzing gene expression profiles becomes an interesting topic in bioinformatics and the main problem is to identify the genes related to a tumor. This paper proposes a rank sum method to identify the related genes based on the rank sum test theory in statistics. The tumor diagnosis system is constructed by the support vector machine (SVM) trained on the set of the related gene expression profiles. The experiments demonstrate that the constructed tumor diagnosis system with the rank sum method and SVM can reach an accuracy level of 96.2% on the colon data and 100% on the leukemia data.     

Dynamic prediction of building subsidence deformation with data-based mechanistic self-memory model

This paper describes a building subsidence deformation prediction model with the self-memorization principle.According to the non-linear specificity and monotonic growth characteristics of the time series of building subsidence deformation,a data-based mechanistic self-memory model considering randomness and dynamic features of building subsidence deformation is established based on the dynamic data retrieved method and the self-memorization equation.This model first deduces the differential equation of the building subsidence deformation system using the dynamic retrieved method,which treats the monitored time series data as particular solutions of the nonlinear dynamic system.Then,the differential equation is evolved into a difference-integral equation by the self-memory function to establish the self-memory model of dynamic system for predicting nonlinear building subsidence deformation.As the memory coefficients of the proposed model are calculated with historical data,which contain useful information for the prediction and overcome the shortcomings of the average prediction,the model can predict extreme values of a system and provide higher fitting precision and prediction accuracy than deterministic or random statistical prediction methods.The model was applied to subsidence deformation prediction of a building in Xi’an.It was shown that the model is valid and feasible in predicting building subsidence deformation with good accuracy.     

Fault-Tolerant Technique in the Cluster Computation of the Digital Watershed Model

This paper describes a parallel computing platform using the existing facilities for the digital watershed model. In this paper, distributed multi-layered structure is applied to the computer cluster system, and the MPI-2 is adopted as a mature parallel programming standard. An agent is introduced which makes it possible to be multi-level fault-tolerant in software development. The communication protocol based on checkpointing and rollback recovery mechanism can realize the transaction reprocessing. Compared with conventional platform, the new system is able to make better use of the computing resource. Experimental results show the speedup ratio of the platform is almost 4 times as that of the conventional one, which demonstrates the high efficiency and good performance of the new approach.     

Prediction of Solid-Liquid Equilibrium for KCI in Mixed Water-Ethanol Solutions Using the LIQUAC Model

The LIQUAC model is often used to predict vapor-liquid equilibria, osmotic coefficients, and mean ion activity coefficients for electrolyte systems. This paper describes a thermodynamic method to analyze solid-liquid equilibrium for electrolytes in mixed solvents solutions using the LIQUAC model. The KCI solubilities in mixed water-ethanol solutions are predicted with the LIQUAC model and its original interaction parameters. This method is also used to obtain new K^＋-ethanol interaction parameters in the LIQUAC model from the solubility data. The new interaction parameters accurately predict the vapor-liquid equilibrium data of K^＋ salts （including KCI, KBr, and KCOOCH3） in mixed water-ethanol solutions. The results illustrate the flexibility of the LIQUAC model which can predict not only vapor-liquid equilibrium but also solid-liquid equilibrium in mixed solvent systems.     

Nonlinear fault diagnosis method based on kernel principal component analysis

To ensure the system run under working order, detection and diagnosis of faults play an important role in industrial process. This paper proposed a nonlinear fault diagnosis method based on kernel principal component analysis (KPCA). In proposed method, using essential information of nonlinear system extracted by KPCA, we constructed KPCA model of nonlinear system under normal working condition. Then new data were projected onto the KPCA model. When new data are incompatible with the KPCA model,it can be concluded that the nonlinear system is out of normal working condition. Proposed method was applied to fault diagnosis on rolling bearings. Simulation results show proposed method provides an effective method for fault detection and diagnosis of nonlinear system.     

A Dynamic Active Multicast Group Access Control Framework Based on Trust Management System

The current multicast model provides no access control mechanism. Any host can send data directly to a multicast address or join a multicast group to become a member, which brings safety problems to multicast. In this paper, we present a new active multicast group access control mechanism that is founded on trust management. This structure can solve the problem that exists in multicast members＇ access control and distributing authorization of traditional IP multicast.     

Control and Communication Network in Hybrid Fuel Cell Vehicles

This paper describes the control and communication network in fuel cell vehicles, including both the protocol and the hardware. Based on the current protocol (ISO-11898 and SAE J1939), a new practical protocol is proposed and implemented for the control and communication network in fuel ceil vehicles. To improve the reliability of data communication and to unify the network management, a new network system based on dual-port RAM is also implemented.     

Cost of Multicast Logical Key Tree Based on Hierarchical Data Processing

How to design a multicast key management system with high performance is a hot issue now. This paper will apply the idea of hierarchical data processing to construct a common analytic model based on directed logical key tree and supply two important metrics to this problem： re-keying cost and key storage cost. The paper gives the basic theory to the hierarchical data processing and the analyzing model to multieast key management based on logical key tree. It has been proved that the 4-ray tree has the best performance in using these metrics. The key management problem is also investigated based on user probability model, and gives two evaluating parameters to re-keying and key storage cost.     

Regional Prediction of Impending Debris Flow Based on Doppler Weather Radar

Debris flow prediction is one of the important means to reduce the loss caused by debris flow. This paper built a regional prediction model of impending debris flow based on regional environmental background （including topography, geology, land use, and etc.）, rainfall and debris flow data. A system of regional prediction of impending debris flow was set up on ArcGIS 9.0 platform according to the model. The system used forecast precipitation data of Doppler weather radar and observational precipitation data as its input data. It could provide a prediction about the possibility of debris flow one to three hours before it happened, and was put into use in Liangshan Meteorological Observatory in Sichuan province in the monsoon of 2006.     

Neural network approach for modification and fitting of digitized data in reverse engineering

Reverse engineering in the manufacturing field is a process in which the digitized data are obtained from an existing object model or a part of it, and then the CAD model is reconstructed. This paper presents an RBF neural network approach to modify and fit the digitized data. The centers for the RBF are selected by using the orthogonal least squares learning algorithm. A mathematically known surface is used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculating points from the equations. Moreover, a series of practice digitizing curves are used to test the approach. The results showed that this approach is effective in modifying and fitting digitized data and generating data points to reconstruct the surface model.     

The Modeling of Fuzzy ART Neural Network Based on Self-defined Closeness Degree and Its Application

This paper defines and proves a new closeness degree firstly, and then presents an improved-CFART neural network model, after introducing the closeness degree into the standard fuzzy ART model. This paper also develops an information analysis and simulation system based on the recognition of industrial real-time data from field. The results of simulation experiments demonstrate that the CFART model has excellent capability of pattern recognition for dynamic waveform.     

On the Relation Redundancy in Fuzzy Databases

This paper concentrates on the problem of data redundancy under the extended-possibility-based model. Based on the information gain in data classification, a measure - relation redundancy - is proposed to evaluate the degree of a given relation being redundant in whole. The properties of relation redundancy are also investigated. This new measure is useful in dealing with data redundancy.     

New feature extraction in gene expression data for tumor classification

Using gene expression data to discriminate tumor from the normal ones is a powerful method. However, it is sometimes difficult because the gene expression data are in high dimension and the object number of the data sets is very small. The key technique is to find a new gene expression profiling that can provide understanding and insight into tumor related cellular processes. In this paper, we propose a new feature extraction method based on variance to the center of the class and employ the support vector machine to recognize the gene data either normal or tumor. Two tumor data sets are used to demonstrate the effectiveness of our methods. The results show that the performance has been significantly improved.     

ZBF-DMTD SYNTHETICAL METHOD FOR SHORT-TERM FREQUENCY STABILITY MEASUREMENT

This paper presents a zero beat frequency double mixer time difference (ZBF-DMTD) synthetical method for measuring short-term.frequency stability Allen variance σy^2(τ) of frequency sourse. The new method has a high measurement preclsion and is easy to realize and spread in engineering. The paper dlscribes the structure and design of the ZBFDMTD automatic measurement system,and gives the contrast measurement results.     

A Distributed Data Mining System Based on Multi-agent Technology

Distributed Data Mining is expected to discover preciously unknown, implicit and valuable information from massive data set inherently distributed over a network. In recent years several approaches to distributed data mining have been developed, but only a few of them make use of intelligent agents. This paper provides the reason for applying Multi-Agent Technology in Distributed Data Mining and presents a Distributed Data Mining System based on Multi-Agent Technology that deals with heterogeneity in such environment. Based on the advantages of both the CS model and agent-based model, the system is being able to address the specific concern of increasing scalability and enhancing performance.     

Size Effect for Normal Strength Concrete in Uniaxial Tension

This paper presents a new size effect model for normal strength concrete subjected to uniaxial tension. The model is based on two extremes, sand cement paste in uniaxial tension and a sand-cementpaste/rock interface in uniaxial tension. Uniaxial tension tests with normal strength concrete measuring the tensile strength of normal strength concrete specimens with different geometrical shapes and different ratios of the aggregate size to the characteristic dimension of the concrete specimen show a significant size effect.The theoretical size effect law prediction agrees well with the experimental data.     

Coefficients de-noising with wavelet transform for magnetic flux leakage data obtained from oil pipeline

This paper considers the problem of noise cancellation for the magnetic flux leakage （MFL） data obtained from the inspection of oil pipelines. MFL data is contaminated by various sources of noise, and the noise can considerably reduce the detectability of flaw signals in MFL data. This paper presents a new denoising approach for removing the system noise contained in the MFL data by using the coefficients denoising with wavelet transform. Experimental results are presented to demonstrate the advantages of this de-noising approach over the conventional wavelet de-noising method.