Advanced Materials Research Vols. 433-440

Abstract: Wind speed forecast is a non-linear and non-smooth problem. nonlinear and non-stationary are two kinds of mathematical problem, it is difficult to model with a single method, so that, a wavelet neural network model is set, the non-linear process of wind speed is forecast by neural networks and the non-stationary process of wind speed is decomposed into quasi-stationary at different frequency scales by multi-scale characteristics of wavelet transforms. wavelet combined with neural network model avoid the neural network model that can not handle non-stationary questions .while, the effect of indefinite inputs are removed by embedding dimension of phase space to determine neural networks inputs. The simulation results show that phase space reconstruction of wavelet neural network is more accuracy than the ordinary BP neural network. It could be well applied in wind speed forecasts.

Abstract: The novel multilayer feed-forward AND-OR fuzzy neural network (AND-OR FNN) is proposed in this paper. The main feature is shown not only in reducing the input space by special inner structure of neurons, but also auto-extracting the rules by the structure self-organization and parameter self-learning. The equivalent is proved that the network structure and fuzzy inference. The whole structure of network is optimized by genetic algorithm to extract if-then rules. This designing approach is employed to modeling an AND-OR FNN controller for ship control. Simulated results demonstrate that the number of rule base is decreased remarkably and the performance is much better than ordinary fuzzy control, illustrate the approach is practicable, simple and effective.

Abstract: A multi-scale method based on local multi-model monogenic image feature descriptors (LMFD) is proposed to match interest points and estimate disparity map for stereo images. Local multi-model monogenic image features include local orientation and instantaneous phase of the gray monogenic signal, local color phase of the color monogenic signal and local mean colors in the multi-scale color monogenic signal framework. The gray monogenic signal, which is the extension of analytic signal to gray level image using Dirac operator and Laplace equation, consists of local amplitude, local orientation and instantaneous phase of 2D image signal. The color monogenic signal is the extension of monogenic signal to color image based on Clifford algebras. The local color phase can be estimated by computing geometric product between the color monogenic signal and a unit reference vector in RGB color space. Because the proposed feature descriptors contain local geometric, structure and color information, it is robust against noise and brightness change in feature matching and 3D reconstruction. Experiment results on the synthetic and natural stereo images show the performance of the proposed approach.

Abstract: With the development of intelligent building, building intelligence system integration has become the focus of the field of intelligent building. The mutual control mode communication technology can provide strategies against emergency. On the other hand, in order to effectively support the real-time control system, and improve the system of operation, we connect the system with a computer platform by using RS232 serial communication port, and use VC program design platform and ActiveX technology which introduced by Microsoft to produce a operating control platform of the mutual control mode communication machine.

Abstract: The Enzyme-labeled instrument based on ELISA has been widely used in many clinical applications. A dual-CPU system is designed and applied to the Enzyme-labeled instrument in this paper. The master CPU Sync8958 is in charge of data acquisition and LCD displays while the slave MSP430 is in charge of A/D, records, analyzes of the date and the movement of step motor. The communication, analysis and processing of the data are realized by C program. The accuracy and flexibility is improved via employing the optical reference channels and a correction coefficient.

Abstract: A novel numerical analysis was used to investigate the response of non-linear systems undergoing aperiodic excitations based on the Neural Harmonic Response Analysis method (NNHRAM). A numerical method of neural element discretization was proposed to turn the aperiodic excitations into superposition of a series of periodic excitations. The method of perturbation was applied to transform the non-linear governing equation into a series of linear differential equations. The method of NNHRAM could be used to solve the aperiodic steady response. The algebraic algorithm of direct steady-state analysis can improve the computational efficiency. The examples showed that the numerical results match well with the analytic solution.

Abstract: A novel transient component bus protection based on morphological bop-bottom-operator is presented in this paper, which takes the max top-bottom-operator of current traveling wave to fast distinguish the bus internal fault from external fault. The method is based on the principle that the high frequency component of transient traveling wave caused by external fault will be attenuated by the bus capacitance but the traveling wave caused by bus internal fault changes slightly. Simulation is carried out with PSCAD/EMTDC, the result verifies the bus protection is reliable and accurate. The novel bus protection also can treat lightning failure or lightning disturbance happened on transmission lines as bus external fault, without malfunction. Introduction

Abstract: Medical Cyber-Physical System (CPS) is integrations of computation and medical processes. Embedded computers and networks monitor and control the medical processes, usually with feedback loops where medical processes affect computations and vice versa. The medical CPS has many unique features, such as high-confidence, hard–real-time, highly-cooperative, highly- interoperative, etc. In this paper, a prototype architecture of medical CPS based on grid computing is proposed. It is argued that this architecture captures the essential attributes of a medical CPS and lead to identification of many research challenges.

Abstract: This paper introduces the design of telemedicine ECG monitoring system based on GPRS.This system combined holter monitoring technology and advanced wireless public communication network, which realizes user outside the hospital can be achieved by heart disease remote real-time monitoring function.This paper firstly introduced the structure design of this system, and then the electrocardio monitoring terminal, the communication circuit as well as the software and hardware of monitoring centers respectively. Clinical experiments showed that this system can realize remote real-time monitoring, and has important clinical significance.

Abstract: The primary purpose of this research is to resolve the problem of ETL operation failure in execution of ETL (Extraction, Transformation and Loading) by the medical decision-making system due to data content, system factors and defective program design, thereby affect online daily operation of the application system and even customer complaint. This research first research and develop how to record in database, whether successful or not, the number of ETL file conversion program (including tool and self-wrote PL/SQL program) execution process, data status, and execution time; followed by designing control mechanism and write Script for voluminous table restoration for automatic execution by the system; afterwards followed by research and develop system automatic execution of restoration to stop only the affected application programs of the table and design a restoration mechanism. Lastly, through verification, this R&D result would correctly restore the data and table required by ETL procedure.