		FeedBack \| Contact Us \| Links \| Site Map

Welcome to Journal of Theoretical and Applied Information Technology

Submit Paper / Call for Papers

Journal receives papers in continuous flow and we will consider articles from a wide range of Information Technology disciplines encompassing the most basic research to the most innovative technologies. Please submit your papers electronically to our submission system at http://jatit.org/submit_paper.php in an MSWord, Pdf or compatible format so that they may be evaluated for publication in the upcoming issue. This journal uses a blinded review process; please remember to include all your personal identifiable information in the manuscript before submitting it for review, we will edit the necessary information at our side. Submissions to JATIT should be full research / review papers (properly indicated below main title).

Journal of Theoretical and Applied Information Technology
November 2012 | Vol. 45 No.2

Title:	MODELING AND SIMULATION OF GRID-CONNECTED PHOTOVOLTAIC DISTRIBUTED GENERATION SYSTEM
Author:	M. MAKHLOUF , F.MESSAI, H.BENALLA
Abstract:	Compared to the traditional energy resources, photovoltaic (PV) system that uses the solar energy to produce electricity considered as one of renewable energies has a great potential and developing increasingly fast compared to its counterparts of renewable energies. Such systems can be either stand-alone or connected to utility grid. However, the disadvantage is that PV generation depended on weather conditions. Thus there is also a need for developing control techniques for three phase grid connected PV systems including a method for DC link voltage control that stabilizes the voltage at the inverter input to insure a continuous flow of energy exchange between the grid and the PV system. An LC filter also is necessary to filter the output current and voltage from the harmonics and protect the grid from their destructive effect. This paper presents detailed modeling of the grid-connected photovoltaic generation system components, in Simulink / MATLAB software. Simulation results presented here validate the component models and the chosen control schemes.
Keywords:	Grid Connected PV Systems, DC-DC Converter, PWM Inverter, MPPT, PI Controller.
Source:	Journal of Theoretical and Applied Information Technology pp 378 - 386 Vol. 45. No. 2 -- 2012
Full Text

Title:	A NOVEL FRAMEWORK FOR EFFICIENT CONGESTION CONTROL PROTOCOL AND QoS ENHANCEMENT IN AD HOC WIRELESS NETWORKS
Author:	K. MANIKANDAN, M. A. SALEEM DURAI
Abstract:	Internet with its wide application has contributed a lot to the fast growth of the world and there are many limitations in ad hoc networks. There are two main failures that occur in the network namely wireless packet loss and congestion. The performance of SCTP in wireless network is considered the active research area. The detection of failure in the wireless network is very important for analysing the performance of networks. In this research work, the route is established by demand routing technique in which many features like the energy of the node, location and bandwidth of the packet are analysed. So when the packet needs to be sent, it analyses all the features and establishes the route with the efficient node that has one hop count by using the SCTP transport protocol. On transmitting the packets some energy from the node gets reduced. So there is a high vulnerability of congestion, since the capacity of the node is reduced. This can be avoided by the proactive approach ECCP by reducing the traffic, send by the source, when the node level reaches threshold. By using the multi-homing technique in the SCTP approach, the packets can be sent till the alternative route is re-established. Thus, the packet loss rate and end to end delay is reduced and QoS is increased in adhoc networks.
Keywords:	Adhoc Networks, Congestion Control, Bandwidth, Qos, Packet Loss
Source:	Journal of Theoretical and Applied Information Technology pp 387 - 396 Vol. 45. No. 2 -- 2012
Full Text

Title:	ADAPTIVE VELOCITY AND DISTANCE BASED ROUTING PROTOCOL FOR MANET
Author:	BISENGAR AHMED, OUADOUDI ZYTOUNE, ENNEYA NOURDDINE, RZIZA MOHAMED, OUADOU MOHAMED
Abstract:	A mobile ad-hoc network (MANET) is a collection of wireless mobile nodes communicating without any infrastructure. Due to the availability of small and inexpensive wireless communicating nodes, the MANET field has attracted a lot of attention from industry and academia. MANETs can be used in various applications such as mobile classrooms, battlefield communication and disaster relief applications. They may be divided into homogeneous and heterogeneous ones. Homogeneous Ad-hoc Networks nodes possess the same transmission range, but not for heterogeneous ones (i.e, networks consisting of different wireless mobile devices such as laptops, PDAs and cell phones). In AODV routing protocol, the shortest path between source and destination nodes is always selected, without collecting topology information. In this paper, we propose an improvement of AODV protocol called MDAODV (Mobility aware modified AODV). The new algorithm finds optimum path based on distance, relative velocity between two nodes and hop count. It is confirmed by simulation that this improvement has higher packet delivery ratio than standard AODV protocol.
Keywords:	Mobile Ad Hoc Networks, AODV, Distance, Transmission Range, Relative Velocity, Weight Function
Source:	Journal of Theoretical and Applied Information Technology pp 397 - 405 Vol. 45. No. 2 -- 2012
Full Text

Title:	IMAGE RESTORATION USING NONLINEAR FILTERING BASED RANDOM TRAIL METHOD
Author:	FERAS N. HASOON, NEBRAS N. HASSON
Abstract:	The achievement of high image restoration with more image details sharpening median filter based on the random trail method (RTM) is proposed to be used .This paper proposes a weight coefficients (WC) use in median filter (MF) scheme to improve the quality of standard images by removing the salt and pepper noise while simultaneously preserving the other minutiae. The proposed scheme will be tested on noisy standard images and compared to other schemes. The quality of the filtered images will be assessed by computing the mean square error (MSE).
Keywords:	Random Trail Method (RTM), Weight Coefficient (WC), Median Filter, Salt and Pepper Noise
Source:	Journal of Theoretical and Applied Information Technology pp 406 - 409 Vol. 45. No. 2 -- 2012
Full Text

Title:	ARTIFICIAL NEURAL NETWORK APPLICATION IN GROSS DOMESTIC PRODUCT FORECASTING AN INDONESIA CASE
Author:	LILIANA, TOGAR ALAM NAPITUPULU
Abstract:	Gross Domestic Product (GDP) is a benchmark for economic production conditions of a country. Estimates of economic growth in the coming year in a country has important roles, among others as a benchmark in determining business plans for business entities, and the basis for devising government fiscal policy. Artificial Neural Network (ANN) has been increasingly recognized as a good forecasting tool in various fields. Its nature that can mimic the workings of the human brain makes it flexible for non-linear and non-parametric data. GDP growth forecasting techniques using ANN has been widely used in various countries, such as the United States, Canada, Germany, Austria, Iran, China, Japan and others. In Indonesia, forecasting of GDP is only done by government institutions, namely National Planning Board, using macroeconomic model. In this study, ANN is used as a tool for forecasting GDP growth in Indonesia, using some variables, such as GDP growth in the two previous periods, population growth rate, inflation, exchange rate and political stability and security conditions in Indonesia. Results from this study indicate that ANN forecasts GDP relatively better than the one issued by the government. Further study would be to use ANN to predict other economic indicators.
Keywords:	GDP growth, ANN, Forecasting
Source:	Journal of Theoretical and Applied Information Technology pp 410 - 415 Vol. 45. No. 2 -- 2012
Full Text

Title:	SPATIAL TOPOLOGY ASSOCIATION MINING WITH CONSTRAIN CONDITION
Author:	XU JIA-LIANG , FANG GANG ,YE XIAO-QIN
Abstract:	Aiming at present mining algorithms can not extract spatial topology association with constrain condition, and traditional constrain association rules mining algorithms have repeated computing and superfluous candidate in the time of mining spatial topology association rules, an algorithm of spatial topology association mining with constrain condition is proposed, which is suitable for mining topology association with constrain condition in multi-spatial relation pattern. The algorithm uses topology binary to turn spatial relation transaction into integer, and uses value ascending of constrain condition to form candidate frequent item sets. To efficiently improve mining efficiency, the algorithm uses Boolean operation to compute support, and uses number attribute to reduce the number of scanned spatial transaction. The algorithm is used to mine spatial topology association rules with constrain condition, and this experiment indicates that the efficiency is fast and efficient.
Keywords:	Topology Association; Constrain Condition; Value Ascending; Topology Binary; Spatial Association Rules
Source:	Journal of Theoretical and Applied Information Technology pp 416 - 419 Vol. 45. No. 2 -- 2012
Full Text

Title:	NEW DIGITAL ANGLE MEASUREMENT FACILITY BASED ON FPGA
Author:	HAO ZHAO, HAO FENG
Abstract:	A new structure angle measurement facility is presented, the principle of facility is linear interpolation subdivided to electric grating with high-frequency pulses, the mechanical structure of measurement facility is simplified, and avoiding the difficulty of subdivision angle on physical condition while compared with the ordinary high accuracy angle sensor. The signal processing of facility based on Filed Programmable Gate Array and single-chip microprocessor realized non-contacted angle measurement. The error of facility is analyzed and tested by experiments; the high theoretical accuracy of measurement facility is verified according to the test, so this system is promising.
Keywords:	Angle; FPGA; High-Frequency Pulse; USM
Source:	Journal of Theoretical and Applied Information Technology pp 420 - 424 Vol. 45. No. 2 -- 2012
Full Text

Title:	THE RESEARCHING OF PLOTTING LOGARITHMIC PHASE FREQUENCY RESPONSE CURVE
Author:	WANG HONG, MEN XIAOSHUANG, ZHANG YUXIAN
Abstract:	In this paper, a simple method of plotting bode chart is introduced. Through composed of each typical links, the logarithmic phase frequency response curve for usually open-loop systems can be replaced by regular fold lines and the traditional method for the process is simplified, the velocity of the plotting logarithmic phase frequency response curve is fast. So the application value of plotting logarithmic phase frequency response curve for open-loop systems is greatly enhanced.
Keywords:	Frequency Response. Open-Loop Systems. Logarithmic Phase Frequency Response Curve
Source:	Journal of Theoretical and Applied Information Technology pp 425 - 429 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN RFID-BASED CRM SYSTEM IN APPAREL RETAILING
Author:	SHAN YANG, GUOLIAN LIU, MENGMENG XU, HONGQIN DAI
Abstract:	An RFID-based CRM system with intelligent characteristics for apparel retail has been proposed in this paper. It is composed of five functional modules: RFID-based garment information management module, RFID-based customer information management module, personalized recommendation and service module, sales management module, web-based communication and service module. The core function of this system is to identify a customer automatically and make personal recommendation to him/her by using RFID. With the implementation of this system, apparel retailers can achieve the purpose of building up a close but discriminating relationship with each customer.
Keywords:	RFID; CRM System; Personalized Recommendation; Apparel Retailing
Source:	Journal of Theoretical and Applied Information Technology pp 430 - 434 Vol. 45. No. 2 -- 2012
Full Text

Title:	RESEARCH ON CENVERGENCE OF ANT ALGORITHM
Author:	ZHANG LI
Abstract:	A basic ant algorithm based on elite strategy to resolve the shortest path problem is given, In terms of stochastic processes and functional analysis methods; the abstract description of the basic ant algorithm is established. By using the basic ant algorithm, the iteration feature of problem-solving is studied, the conclusion can be drawn that the solution sequence is asymptotic convergence.
Keywords:	Ant Algorithm; Markov Process; Convergence; Fixed Point
Source:	Journal of Theoretical and Applied Information Technology pp 435 - 438 Vol. 45. No. 2 -- 2012
Full Text

Title:	THE NOVEL IMAGE DIFFUSION ALGORITHM BASED ON THE PSEUDO RANDOM BLOCK
Author:	ZONGYING LI
Abstract:	In this article, we firstly introduce a novel image diffusion algorithm, which is based on the two pseudo random image block, and then we encrypt the digital image with it. The large number of simulations is carried on, and the simulation results show that the proposed algorithm is a very efficient diffusion algorithm.
Keywords:	Tent Map, Pseudo Random Distance Sequence, Histogram, Entropy
Source:	Journal of Theoretical and Applied Information Technology pp 439 - 443 Vol. 45. No. 2 -- 2012
Full Text

Title:	RESEARCH ON INTELLIGENT CONTROL CONSERVATION SYSTEM OF FREEZE STATIONS
Author:	ZHENG XIAOLIANG, HU YELIN, ZHU LONGJI, CHEN ZHAOQUAN, SHA CHENG
Abstract:	The intelligent control technology with the traditional control theory formats intelligent compound controller in order to learn from each other and improve the overall advantage of complementary features. Fuzzy PID control neuron PID control, fuzzy sliding mode control, and optimal control of the neural network. This paper discusses the current situation and development of smart composite control system, and describes the smart composite controller structure based on theory and research results in recent years.
Keywords:	Intelligent Control; Traditional Control; Composite Control
Source:	Journal of Theoretical and Applied Information Technology pp 444 - 447 Vol. 45. No. 2 -- 2012
Full Text

Title:	NUMERICAL ANALYSIS OF THERMAL ENVIRONMENT IN A NATURAL VENTILATION SUNLIGHT GREENHOUSE
Author:	ZHENYU DU, LEI JIA, DIDI XUE
Abstract:	This paper using the corresponding test data gained from the continuous environmental test in a natural ventilation sunlight greenhouse in Taiyuan, established a mathematical model of the thermal environment in such a greenhouse based on the conservation laws of mass, momentum and energy. The complex boundary conditions in CFD simulation of a sunlight greenhouse was dealt preferably with this new model. According to the unsteady simulation of the distribution and change of the temperature field in natural ventilation sunlight greenhouse based on the new model, simulation result highly matches up to the locale test data under the unsteady condition, and this model can be used to predict the thermal environment of such a greenhouse and optimize the prediction.
Keywords:	Sunlight Greenhouse, Natural Ventilation, Thermal Environment, Numerical Simulation, Computational Fluid Dynamics
Source:	Journal of Theoretical and Applied Information Technology pp 448 - 455 Vol. 45. No. 2 -- 2012
Full Text

Title:	A TABLE-FILLING SCHEDULING ALGORITHM FOR THE ROUND ROBIN CALENDAR PROBLEM WITH ARBITRARY COMPETITORS
Author:	JIANYONG LI, DAOYING HUANG, BING HAN, ANLIN ZHANG
Abstract:	A novel table-filling schedule algorithm is proposed for the round robin calendar problem with arbitrary competitors. Among schedules calendar, the number of rows is the ID of each competitor and elements of the schedule correspond to a certain round serial number of some two competitors. Competition schedule can be completed by the algorithm when the number of competitors is even. If the number of competitors is odd, the schedule will be filled through three steps, even transforming, table filling and even eliminating. It is proved that time and space complexity of the algorithm are all .
Keywords:	Round Robin Scheduling, Table-filling Algorithm, Complexity
Source:	Journal of Theoretical and Applied Information Technology pp 456 - 461 Vol. 45. No. 2 -- 2012
Full Text

Title:	ULTRASONIC TIME OF FLIGHT COMPUTED TOMOGRAPHY FOR CONCRETE INSPECTION
Author:	HONGHUI FAN, HONGJIN ZHU
Abstract:	This research aims to evaluate the internal structure of concrete material configuration using an immersed ultrasonic computed tomography imaging technique. We propose a relative difference method of time of flight data to remove distortions in imaging process of concrete. Time of flight data for 306 paths were measured in total by manual scanning for one computer tomography image, we examined interpolation of time of flight data as the density which has a considerable effect on image quality in Filtered Back Projection (FPB) method. The relative difference of time of flight and interpolation is examined in detail using concrete phantoms. The accuracy of defect detection in concrete was significantly improved by the proposed technique.
Keywords:	Ultrasonic Computed Tomography, Time Of Flight, Concrete, Reconstruction Image
Source:	Journal of Theoretical and Applied Information Technology pp 462 - 467 Vol. 45. No. 2 -- 2012
Full Text

Title:	BACK STEPPING CONTROL FOR NONLINEAR SYSTEMS OF OFFSHORE PLATFORMS
Author:	YANJUN LIANG, YUNTONG LIU
Abstract:	The vibration control problem of offshore jacket platforms is studied. According to Morison equation, the total wave force acting on the offshore structure is obtained and is generated by an exosystem. Considering the nonlinear interaction of pile-soil, which is described by a fifth order anti-symmetric polynomial, the nonlinear dynamical model of offshore platforms affected by the wave load disturbances is established and its state-space described model is constructed by introducing the state vector. Based on Lyapunov stability theory, two Lyapunov candidate functions are chosen, then a back stepping controller is developed for the nonlinear systems of offshore structures under wave loading, and the nonlinear vibration control systems of the offshore platforms is exponentially stable. Numerical simulations illustrate the effectiveness of the proposed controller.
Keywords:	Nonlinear Systems, Backstepping Control, Offshore Platforms
Source:	Journal of Theoretical and Applied Information Technology pp 468 - 471 Vol. 45. No. 2 -- 2012
Full Text

Title:	SYSTEMATIC SIMULATION ON SAFE DRIVING BEHAVIOR IN STEEP CURVED SECTIONS OF TWO-LANE
Author:	ZHIGUO ZHOU, HAICHENG ZHANG, YUANWU ZHAN
Abstract:	Three models are established under the multivariate nonlinear regression analysis technology, and on the base of the existing and survey data, which are the double-lane road alignment safety evaluation model, the psychological reaction of driver safety evaluation model and the driving safety comprehensive evaluation model. Then, a quantitative evaluation of the experimental section is made by the comprehensive established evaluation model, and the security level is gained. Moreover, how to improve the security level of the experimental section is advanced, that is to set the hollow LED variable speed-limit sign. Finally, a comparison of the experimental section’s security level before and after carrying out the hollow LED variable speed-limit sign is made by using the simulation software to verify the effectiveness and feasibility of this measure.
Keywords:	Steep Curved Sections, Driving Safety Model, Hollow LED Variable Speed-Limit Sign, System Simulation
Source:	Journal of Theoretical and Applied Information Technology pp 472 - 479 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN ALGORITHM FOR MOVING VEHICLE DETECTION AND TRACKING BASED ON ADAPTIVE BACKGROUND MODELING
Author:	FENG YOU, RONGHUI ZHANG, HUIYING WEN, JIANMIN XU
Abstract:	In modern traffic surveillance, computer vision methods have commonly been utiliezed to detect vehicles because of the rich information content contained in an image. And detection and tracking of moving vehicle in traffic environment is one of the most important components in intelligent transportation system (ITS). The adaptive background modeling method was used to eliminate the negative effects from moving vehicle and rebuild the background images. The moving vehicles were segmented with difference images between background and current images. To suppress noise caused by segmentation and improve robust performance of vehicle detection, a template with 3-by-3 window was utilized to decrease isolated noise points around vehicle contours. Then, the morphological filtering, including erosion and dilation operation, was also applied, which minimizes the influence of the discontinuous block noise. Finally, to reduce the searching scope of vehicle detected and improve the calculation speed, Kalman filter model was performed to track motive vehicles. The experimental results verifid the effectiveness and real-time of algorithm.
Keywords:	Vehicle Detection, Mixture Gaussian Distribution, Computer Vision, Morphological Filtering, Extended Kalman Filtering, Intelligent Transportation System
Source:	Journal of Theoretical and Applied Information Technology pp 480 - 485 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN EFFICIENT MAC PROTOCOL FOR SUPPORTING QOS IN WIRELESS SENSOR NETWORKS
Author:	YINGHUI QIU
Abstract:	Wireless sensor network can be employed in wide range of application areas, such as target detection and tracking, military, and environmental monitoring. Media access control protocol is one of the most critical issues for wireless sensor network. A lot of efforts have been dedicated to MAC protocol and many MAC protocols have been proposed for different purposes. In this paper, a modified TDMA based MAC protocol is proposed. The proposed protocol support three different types of traffics and can assign slots for them flexibly. The proposed MAC protocol employs slots reuse scheme to dynamically use slots to transmit traffics and dynamically employs sleep and wake up scheme to reduce radio energy expenditure and then to extend lifetime of WSN network. Simulation results on numerous problem instances show efficiency of the proposed MAC protocol.
Keywords:	Wireless Sensor Networks, Media Access Control, QOS
Source:	Journal of Theoretical and Applied Information Technology pp 486 - 490 Vol. 45. No. 2 -- 2012
Full Text

Title:	ANALYSIS OF TRANSIENT LAMINAR FLOW IN SWRO WITH HYBRID MEMBRANE CHANNELS
Author:	CHUNXIA JIA
Abstract:	In spite that three-quarters of the Earth's surface is covered by water, the shortage of freshwater supply is posing a great threat to human survival. Therefore, seawater desalination has been considered a useful method to produce freshwater, and their use has increased significantly over the past two decades. This paper presented a mathematical model for the transient laminar flow in the seawater reverse-osmosis (SWRO) desalination with hybrid membrane channels. The flow simulations were made by the computational fluid dynamics modeling (CFD) software ANSYS 13.0. The results of the simulations showed the significant influence of the membrane in the flow.
Keywords:	Membrane Channels, Desalination, Seawater Reverse-)smosis, Computational Fluid Dynamics Modeling
Source:	Journal of Theoretical and Applied Information Technology pp 491 - 501 Vol. 45. No. 2 -- 2012
Full Text

Title:	A NOVEL ACO ALGORITHM BASED ON AVERAGE ENTROPY FOR REAL ESTATE PORTFOLIO OPTIMIZATION
Author:	YANCANG LI, BEIBEI HENG, SHUJING ZHOU, RONG CHEN, SUFANG LIU
Abstract:	Portfolio is an import measure of risk distribution in real estate development. In order to provide a more effective algorithm and overcome the shortcomings of the common portfolio optimization algorithms, an improved ant colony optimization algorithm based on average entropy was proposed. The average entropy can adjust the parameters of the algorithm adaptively. After the establishment of the portfolio optimization model, the improved algorithm is introduced into the real estate portfolio optimization. Application results show its efficiency and robustness in solving the real estate portfolio optimization problems.
Keywords:	Real Estate, Portfolio, ACO, Ant Colony Algorithm, Average Entropy
Source:	Journal of Theoretical and Applied Information Technology pp 502 - 507 Vol. 45. No. 2 -- 2012
Full Text

Title:	NONLINEAR PDE APPROACH FOR OPTION PRICING WITH STOCHASTIC VOLATILITY BY USING FUZZY SETS THEORY
Author:	HUA LIA, ANTHONY WAREB, ANATOLIY SWISHCHUKB
Abstract:	This paper is to price European options for assets with stochastic volatility in using fuzzy set theory. The main idea is to transform the probability distribution of stochastic volatility to its possibility distribution (from `volatility smile to volatility frown') and reduce the problem to a fuzzy stochastic process for underlying asset with volatility as a fuzzy number associated with initial stochastic volatility. We then price the corresponding European options by introducing the non-linear fuzzy PDE approach.
Keywords:	European Option, Stochastic Volatility, Fuzzy Sets, Fuzzy Stochastic Process, Nonlinear PDE
Source:	Journal of Theoretical and Applied Information Technology pp 508 - 514 Vol. 45. No. 2 -- 2012
Full Text

Title:	A DIGITAL PREDISTORTION THEORY BASED ON SELF-ADAPTIVE ALGORITHM
Author:	HUIFEN LIAO
Abstract:	In this paper, the author researches the problem of the analysis and optimization of broadband digital predistortion. In the development process of mobile communication system, improving the transmission quality and spectral efficiency always acts as a main research focus. As the traditional multi-carrier modulation system has broadband linear modulating signals with high Peak-to-Average Power Ratio (PAPR), which would cause nonlinear distortion and memory effects after the amplification of RF power amplifier. In order to solve this problem, the author proposes a digital pre-distortion method based on broadband self-adaptivity, updates and optimizes the parameters of pre-distorter with improved self-adaptive algorithm. The simulation results prove that the predistorter could improve the spectrum out of band for about 12dB through the self-adaptive algorithm, which effectively compensates the nonlinear distortion and memory effects of amplifier and improves the efficiency of the digital wireless receiver.
Keywords:	Broadband, Digital Pre-Distortion, Genetic Algorithm, Self-Adaptivity
Source:	Journal of Theoretical and Applied Information Technology pp 515 - 519 Vol. 45. No. 2 -- 2012
Full Text

Title:	HUMAN FACE RECOGNITION METHOD BASED ON MULTI-LINEAR FUNCTIONS
Author:	SHUYUE MA
Abstract:	This paper undertakes the researches of face recognition problems in the conditions of different illuminations and viewing angles. To solve the problem of decreased human face recognition, this paper proposes a tensor-based multi-linear human face recognition method. First, we adopt the form of tensor to represent the image in human face database, and then, depending on different training individuals, we divide the original human face space into some subspaces, and obtain reflection transformation equations for their corresponding subspaces. In the recognition process, we can transform the reflection of the measured face images in different sub-spaces. Meanwhile, we have to calculate the amount of lost information before and after transformation. Thus, we have the human faces classified and identified. The main advantages of this method are reflected as follow: 1) Maintain the spatial relationships between the face images in the adjacent row vector and column vector by using tensor. 2) We can realize human faces recognition by adopting a simple linear transformation, with which we can have this algorithm been with a high recognition rate and a better computational complexity.
Keywords:	Human Face, Tensor, Nonlinear
Source:	Journal of Theoretical and Applied Information Technology pp 520 - 524 Vol. 45. No. 2 -- 2012
Full Text

Title:	ANALYSIS ON THE TMNP- SCHEDULING ALGORITHM FOR INDUSTRIAL WIRELESS NETWORK
Author:	JUN WANG, JINGTAO HU
Abstract:	In order to improve real-time in industrial wireless network, the TMNP-scheduling algorithm (scheduling algorithm based on throughput maximization of non-periodic communication tasks) is proposed in this paper. The basic principles of TMNP-scheduling algorithm are analyzed, and a theory proof has been finished. The theory proof shows that TMNP-scheduling algorithm optimizes communication window debris. Compared with typical scheduling strategy of application layer in industrial control network, the TMNP-scheduling algorithm improves throughput of non-periodic communication tasks in industrial wireless network. At the same time, the nonlinear programming model is founded to generate scheduling timetable based on TMNP-scheduling algorithm. Finally, a simulation model of industrial wireless network is established. The simulation shows that TMNP-scheduling algorithm is not only effective in reducing time-out problems of periodic communication tasks, but also improving throughput of non-periodic communication tasks.
Keywords:	Performance Analysis, TMNP- scheduling Algorithm, Industrial Wireless Network
Source:	Journal of Theoretical and Applied Information Technology pp 525 - 529 Vol. 45. No. 2 -- 2012
Full Text

Title:	RELIABILITY ASSESSMENT OF FIRE IN HIGH-RISE BUILDING BASED ON CLEAR RATIONAL NUMBER
Author:	YANCANG LI, CHENGUANG BAN, SHUJING ZHOU, SHUANGHONG PENG, LINGREN KONG
Abstract:	Reliability assessment is more and more important for the design and construction of the building. The common models used today have the shortcomings of subjectivity. In order to find a more effective method for the structure reliability assessment, a novel mathematic, the clear mathematics was proposed. After the brief introduction of the basic knowledge of the clear mathematic, the assessment model based on the clear set was set up. Engineering practice in the fire reliability assessment of a high-rise building shows the efficiency and the rationality of the method. This study provides a novel method for the structure fire reliability assessment and other comprehensive assessment.
Keywords:	Fire Reliability Assessment, Clear Mathematics, Clear Rational Number
Source:	Journal of Theoretical and Applied Information Technology pp 530 - 534 Vol. 45. No. 2 -- 2012
Full Text

Title:	A NOVEL SQUARE ROOT CUBATURE KALMAN FILTER USING MODEL-ENHANCED GAUSSIAN PROCESS STATE-SPACE MODELS
Author:	ZHIKUN HE, GUANGBIN LIU, XIJING ZHAO, ZHICHENG YAO, BO ZHANG
Abstract:	A novel nonlinear filter called model-enhanced Gaussian process square root cubature Kalman filter (MEGP-SRCKF) is proposed to estimate the state of nonlinear dynamic systems where their state-space models are unknown or insufficiently accurate. The algorithm integrates Gaussian process regression (GPR) into square root cubature Kalman filter (SRCKF). Given the training data, GPR model is used to learn and represent the residual of system after factoring the contributions of the parametric model. The combination of GPR and parametric models enhances the performance of either model alone. It improves the accuracy of the transition and measurement models. The resulting MEGP-SRCKF algorithm has several advantages over standard extended Kalman filter (EKF), nonaugmented unscented Kalman filter (UKF), augmented UKF, and SRCKF. Two cases are used to test these filters and the superiority of the proposed filter is demonstrated, where the MEGP-SRCKF can obtain the better results whether an accurate parametric state-space model is obtained.
Keywords:	Bayesian Filter, Cubature Rule, Gaussian Process Regression, Model-Enhanced, Parametric Model, State-Space model, Nonlinear Dynamic System
Source:	Journal of Theoretical and Applied Information Technology pp 535 541 Vol. 45. No. 2 -- 2012
Full Text

Title:	AERODYNAMIC ANALYSIS AND WIND TUNNEL TEST FOR FLAPPING-WING MAVS
Author:	LAN LIU, XIJING ZHANG, ZHAOXIA HE
Abstract:	A lightweight flapping-wing micro air vehicle (MAV) was designed and built and successfully filed in the sky. The unsteady aerodynamics associated with this MAV was detailedly studied by using the method of computational fluid dynamics (CFD).The variations of different parameters of the flapping MAV, such as flapping amplitude, pitch amplitude and flapping frequency, were investigated with numerical simulation. The Fluid-Structure coupling mechanics for flexible flapping-wings were subsequently researched and discussed. According to the practically developed MAV, a 2-D model for flexible flapping-wings was established. Fluid-Solid interaction deformation and its effects on the aero dynamic performance were analyzed, which offers a theoretical basis for design of the aircraft with flexible flapping-wing. The results of numerical simulation for the rigid and flexible flapping-wings were finally verified by conduct the aerodynamic performance tests in a low turbulence and low Reynolds number wind tunnel.
Keywords:	Flapping-wing MAV, Flexible Wings, Fluid-Solid Interaction, Wind Tunnel Test
Source:	Journal of Theoretical and Applied Information Technology pp 542 - 550 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN ALGORITHM FOR THE COLOR IMAGE SEGMENTATION OF LEVEL SETBASED ON HIS COLOR SPACE
Author:	YUE ZHAO, XIN XU, CHAO CHEN, YAN ZHAO
Abstract:	This paper proposed a rapid level sets method based on HIS color space for the color image segmentation. First, we adopt the method of rapid level sets based on CV mode to improve the segmentation speed. Second, the segmentation of color image can be made with the introduction of the concept of color difference under HIS color mode. In this case, the segmentation can be made exactly even the grey color is very close or the same since the color information is fully employed. The experimental results show that the proposed method is more effective in color image segmentation than the traditional segmentation method of level sets.
Keywords:	Level Set, C-V Model, Image Segmentation, Color Difference, HSI Color Space
Source:	Journal of Theoretical and Applied Information Technology pp 551 - 556 Vol. 45. No. 2 -- 2012
Full Text

Title:	ENTROPY THEORY: AN EFFECTIVE TOOL OF IMPROVING THE COMPUTATIONAL TRANSLATION
Author:	JUANJUAN SUO, HUIQQING TIAN, YANCANG LI
Abstract:	Elimination of the ambiguity is the key to the computational translation. In order to find an effective way to improve the accuracy of the computational translation, the cross entropy was introduced. After the analysis of the reasons of the low accuracy, the information entropy was introduced into the disambiguation. The practice of ambiguity elimination shows the method has high accuracy and this study provides an effective way to improve the computational translation. The study has significance in theory and practice for the development of computational translation.
Keywords:	Computational Translation, Ambiguity Elimination, Entropy
Source:	Journal of Theoretical and Applied Information Technology pp 557 - 561 Vol. 45. No. 2 -- 2012
Full Text

Title:	EMBEDDED MACHINE FOR MEASURING PAVEMENT DEFLECTION BASED ON LPC2214
Author:	ZHIGANG LV, 1PENG WANG, CUIXIA LIU
Abstract:	In order to improve precision and efficiency of measuring pavement deflection in the transport area of China, a measuring machine based on embedded operating system μC/OS-II is designed with LPC2214 MCU. In the design, wireless communication technology, embedded technology, filter technology of software and hardware, anti-jamming technology and other advanced technologies are applied. The machine is divided into two parts: main-machine and sub-machine. The former is used to measure voltages from laser displacement, which will be sent to main-machine from wireless communication channel. The lather is used to calculate, store, display and print the deflection value. All the deflection heights and results will be sent to PC, which can be processed in further. Based on the machine, many experiments are carried out on different highways. The experiment results showed that error of road deflection was below 0.01mm and consuming time for each test was about 60 seconds.
Keywords:	Road Deflection, μC/OS-II, LPC2214, NRF24L01
Source:	Journal of Theoretical and Applied Information Technology pp 562 - 567 Vol. 45. No. 2 -- 2012
Full Text

Title:	FAULT PROGNOSTICS AND RELIABILITY ESTIMATION OF DC MOTOR USING TIME SERIES ANALYSIS BASED ON DEGRADATION DATA
Author:	LI WANG, HUIYAN ZHANG, HONG XUE
Abstract:	This paper presents a method of fault prognostics and reliability estimation for DC motor using time series modeling procedure based on DC motor performance degradation data. DC motor performance degradation data are treated as a time series data and stochastic process are utilized to describe the degradation process for predicting long-term trend. A degradation test is processed for DC motor until they failed and the degradation data are collected for fault prognostics and reliability estimation. Degradation path of DC motors are predicted using time series analysis based on short time period degradation data. A comparison between the predicted failure time and the real failure time of DC motors is processed and the results show that the fault prognostics and reliability estimation of DC motors using time series analysis is effective.
Keywords:	Fault Prognostics, Reliability Estimation, DC Motor, Time Series, Degradation Data
Source:	Journal of Theoretical and Applied Information Technology pp 568 - 572 Vol. 45. No. 2 -- 2012
Full Text

Title:	INTER-TURN SHORT CIRCUIT FAULT DIAGNOSIS OF INDUCTION MOTORS USING THE SVM OPTIMIZED BY BARE-BONES PARTICLE SWARM OPTIMIZATION
Author:	PANPAN WANG, LIPING SHI
Abstract:	In order to accurately recognize the stator winding inter-turn short circuit fault of induction motors, a novel method for fault diagnosis was proposed based on a bare-bones particle swarm optimization algorithm (BBPSO) and support vector machine (SVM); and feasible diagnostic steps were also introduced. In this method, the feature vector of induction motor in different conditions was extracted with wavelet packet, and was considered as the input vector of SVM. The SVM was used to solve the classification problem, and the parameter-free BBPSO and cross-validation were taken to optimize model parameters, which avoided the blindness of parameter selection. Finally, the experiment shows that the proposed method is effective to diagnose the stator winding inter-turn short circuit fault of induction motors.
Keywords:	Induction Motors, Stator Winding Inter-turn Short Circuit, Bare-Bones Particle Swarm Optimization, Support Vector Machine, Fault Diagnosis
Source:	Journal of Theoretical and Applied Information Technology pp 573 - 578 Vol. 45. No. 2 -- 2012
Full Text

Title:	FUZZY BP NETWORK FOR FAULT SELF-DIAGNOSIS SYSTEM OF AUTOMATIC TRANSMISSION
Author:	XUEYUAN WANG
Abstract:	According to the design procedure of fault self-diagnosis system and features of automatic transmission system, the list of relation and mapping between fault symptoms and fault causes are made in this paper. Applying the approach of fault self-diagnosis based on fuzzy neural network, fault diagnosis of the automatic transmission electronic control system is realized. The structure of fuzzy neural network and its corresponding learning method and retreating strategy about the training samples are introduced in this paper. Using MATLAB as simulation platform, this fault diagnosis method is simulated with neural networks toolbox. The simulation results show that this fault diagnosis approach is effective and applied.
Keywords:	Fuzzy Logic, Neural Network Technique, Automatic Transmission (AT), Fault Diagnosis
Source:	Journal of Theoretical and Applied Information Technology pp 579 - 586 Vol. 45. No. 2 -- 2012
Full Text

Title:	INTEREST DEGREE ANALYSIS BASED ON BROWSING BEHAVIOURS
Author:	XIAO MA
Abstract:	This paper analyzes the relationship between user's browsing behavior and interest. User interest is reflected by typical user’s browsing behavior that can be categorized as: Saving page, Printing page, Adding page to Favorites, copying page content, the same page browsing times and page browsing time. Considering the five factors of user’s browsing behaviors as well as the size of a page, an algorithm based on the speed of a page browsing was derived for the user interest degree. Meanwhile, a BP neural network was utilized for the fusion of the user interest degree. The training samples of the BP neural network were feed by collected user's browsing behaviors. The rationality and feasibility of the algorithm for the user interest degree was verified in the research.
Keywords:	User’s Browsing Behaviors, Degree of the user interest, Browsing Speed, Web Interest Degree
Source:	Journal of Theoretical and Applied Information Technology pp 587 - 592 Vol. 45. No. 2 -- 2012
Full Text

Title:	FACIAL FEATURE LOCATING USING ACTIVE APPEARANCE MODELS WITH CONTOUR CONSTRAINTS FROM CONSUMER DEPTH CAMERAS
Author:	QINGXIANG WANG, XIAOQIANG REN
Abstract:	Active appearance model (AAM) is a powerful method for objects feature localization and successfully used in computer vision. Although widely employed, AAMs suffer from a few drawbacks, such as accuracy on the contour of face. We present an Active Appearance Models with contour constraints method from depth data acquired by consumer depth cameras, which could capture video data in 3D, include depth data and color image, under any ambient light conditions based on invisible infrared projection. The facial contour points are acquired from depth data that can be used to restrain the fitting result of AAM and improve the accuracy of the contour part of the result shape by minimize the Euclidean distance in parameter space from the previous state to the solution. Experimental results show the improvement on the facial feature locating.
Keywords:	Facial Feature, Active Appearance Models, Consumer Depth Cameras
Source:	Journal of Theoretical and Applied Information Technology pp 593 - 597 Vol. 45. No. 2 -- 2012
Full Text

Title:	ANALYSIS ON THE NEW CHARACTERISTICS OF WIND WAVES AT SEA SURFACE
Author:	QIANZHAO LEI
Abstract:	In order to comprehend the characteristics of sea waves, starting from the features of fluid dynamics, the relationship between wave height and sea surface wind speed was found, the wind speeds over sea surface were calculated with SMB formula, so got the corresponding relationship between the peak frequency of wave height and the wind speed. Sea wave spectrum was introduced, the simulation results suggested when the wave number is smaller, changing of wave velocity has greater impact on sea wave spectrum, but when the wave number is larger, no significant effect do velocities have on wave spectrums. By using the resonance condition between radar working frequency and that of sea wave, sea surface wave number model was set up. Simulation results revealed that although the cutoff wave number changes with wind speeds and radar frequencies, but in the range of normal working frequencies of HF radar and general sea wind speeds, the cutoff wave number basically stabilizes as a constant quantity. Research conclusions can provide theoretical basis for quantitative research of the sea waves characteristics; it also is an important basis for the simulation of radar sea echoes.
Keywords:	Wind Waves, Sea Wave Spectrum, Wave Height, Resonance Condition, Cutoff Wave Number
Source:	Journal of Theoretical and Applied Information Technology pp 598 - 602 Vol. 45. No. 2 -- 2012
Full Text

Title:	CLUTTER MODELING AND ANALYSIS BASED ON ZMNL METHOD
Author:	BIN WANG, JINKUAN WANG, DONG WANG, JIE ZHANG
Abstract:	With the development of space technology and continuous exploration of outer space, more extensive use of electromagnetic spectrum and high speed of target will make electromagnetic environment become more and more complex. So the influence of clutter can not be ignored. How to model and analyze clutter is very important in the research field of radar. In this paper, we research on the principle of ZMNL (Zero Memory Nonlinearity) method and the basic way of clutter modeling. Then based on the characteristics of Rayleigh distribution, we use ZMNL method to generate Rayleigh distribution clutter. Simulation results show that the generated clutter approaches the theoretical value and the method is effective. Finally, the whole paper is summarized.
Keywords:	Clutter Modeling, Clutter Analysis, ZMNL, Rayleigh Distribution
Source:	Journal of Theoretical and Applied Information Technology pp 603 - 608 Vol. 45. No. 2 -- 2012
Full Text

Title:	ANALYSIS ON MECHANISM OF HUMAN FACTORS AND COMPLEXITY IN SHIP TRANSPORTATION MANAGEMENT
Author:	HONGZHI WANG, YANG ZHAO
Abstract:	This paper elaborates the human factors in ship management, and analyzes Liveware-Liveware interface and Liveware- Environment interface based upon the SHEL model. And the measures to reduce human error in marine transport has also been proposed. This paper also has made systematic analysis on the complexity of Shipping Transportation System, construct system model, and analyzes Synergy Mechanism of Shipping Transportation System .
Keywords:	Human Factor, Shel Model, Ship Management, Shipping Transportation System
Source:	Journal of Theoretical and Applied Information Technology pp 609 - 614 Vol. 45. No. 2 -- 2012
Full Text

Title:	FEATURE EXTRACTION FROM SERIES LOW-VOLTAGE ARC FAULT
Author:	SHUIRONG LIAO, RENCHENG ZHANG, XIAHE LI
Abstract:	220V/50Hz residential circuit was taken as application object. Series arc fault experiment platform was built with reference to the domestic existing research results and the United States UL1699 standards. Arc current and arc voltage were collected. High order harmonic ratio analysis method for wire’s current was proposed. Through the variation condition analysis for high order harmonic ratio of wire’s current data in parallel multi-load circuit, the variation characteristics, for high order harmonic ratio caused by arc fault, was summed up. Research results show that: if a non-linear load was connected to the circuit’s load in parallel, when this two loads were in stable operation at the same time, high order harmonic ratio of wire’s current increased. If a linear load was connected to the circuit’s load in parallel, high order harmonic ratio of wire’s current did not significantly change. When arc fault occurred in parallel load circuit, high order harmonic ratio of wire’s current appeared to rise sharply, and it is not stable, in fierce fluctuation.
Keywords:	Electrical Fire, Arc Fault, High Order Harmonic Ratio, Harmonic Analysis, Feature Extraction
Source:	Journal of Theoretical and Applied Information Technology pp 615 - 620 Vol. 45. No. 2 -- 2012
Full Text

Title:	THREE-DIMENSIONAL NUMERICAL ANALYSIS ON EXCAVATION AND SUPPORT OF DEEP PIT NEAR THE SUBWAY TUNNEL BY COMPUTER SIMULATION TECHNIQUE
Author:	DAPENG ZHU, YUNDIAN LIN, ECHUAN YAN
Abstract:	Computer simulation technique was an effective method to analyze the influence of pit excavation on the stress-strain of soil around pit. Based on ANSYS and FLAC simulation software, in order to ensure the safety of building and subway tunnel nearby the pit excavation, the processes of excavation and support of deep foundation pit were simulated by the finite difference method, this paper obtained stress and deformation characteristics of the soil around pit and underground structures such as subway tunnel. The results showed that the method reflected interaction effects of retaining structure and soil in excavation process, and it could predict stress-strain and stability accurately when the pit was excavated to the designed depth. The study provided a scientific basis for pit design and safety assessment of pit excavation near the subway tunnel.
Keywords:	Excavation, 3-D Simulation Analysis, Subway, Pit Deformation, Support Structure
Source:	Journal of Theoretical and Applied Information Technology pp 621 - 626 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN ENERGY-EFFICIENT MAXIMIZATION BASED PATH SELECTION AND RESOURCE ALLOCATION SCHEME IN OFDMA-BASED TWO-HOP RELAY CELLULAR NETWORKS
Author:	GAOYONG HUANG, XUMING FANG, BO XIAO
Abstract:	In this paper, we investigate the energy efficiency problem in downlink transmission of the OFDMA-based two-hop relay cellular networks. Most of the researches on energy efficiency focus on the transmission in traditional cellular system, especially for the uplink transmission. Our objective is to maximize the system energy efficiency for the downlink transmission of the two-hop relay cellular system. We consider both the circuit power and transmission power consumption, and propose a two-step suboptimal path selection and subchannel allocation scheme to maximize the system energy efficiency. The simulation results show that our proposed scheme have good performance in energy efficiency.
Keywords:	OFDMA, Multi-hop Relay Network, Path Selection, Resource Allocation, Scheduling
Source:	Journal of Theoretical and Applied Information Technology pp 627 - 633 Vol. 45. No. 2 -- 2012
Full Text

Title:	A MULTI-CHANNEL SIGNAL SOURCES BASED ON FPGA AND DDS
Author:	QIULIN TAN, XIANGDONG PEI, JIJUN XIONG, WENYI LIU, SIMIN ZHU, MINGSI QI, CHAO LI
Abstract:	In the field of Test & Control Instrument , multi-channel signal sources are needed as the excitation in the electrical parameters measurement. This paper presents a realization method of multiplexed signal source which combined the advantages of DDS principle with high speed programmable logic device FPGA, fully reflect the characteristics of fast switching frequency, high precision with DDS technology, and abundant FPGA logic resources. This design realized the optimization of DDS resources primarily through FPGA, made use of timing multi-threaded design ROM shared access, innovated an adjustable amplitude method, namely, applied FPGA internal procedures to modulate the normalized waveform sampling digital.
Keywords:	Multi-Channel, DDS, FPGA, ROM Shared Access
Source:	Journal of Theoretical and Applied Information Technology pp 634 - 639 Vol. 45. No. 2 -- 2012
Full Text

Title:	ECONOMIC OPERATION STATISTICS AND ANALYSIS OF SUPPLY CHAIN MANAGEMENT SYSTEM FOR BAMBOO INDUSTRY
Author:	DEYUN WEI, HONGTAO ZHANG, JUN LU, YUXIA HU
Abstract:	The bamboo industry is facing good opportunities for development in China, but it faces enormous challenges, too. From the level of bamboo industrial development, mainly in the following aspects: the level of bamboo resources management is low, cultivate direction is not clear, operating methods are backward, production is not high, processing or utilization of bamboo products is small-scale and scattered, low cost-effectiveness. China’s bamboo industry is still mainly need for in the domestic market, supplemented by foreign markets. The bamboo industry exigently needs the information managing tools to congregate the customer information, in order to improve their working power. Supply Chain Management (SCM) is effectively idea and tool which used to manage the information flowing in the enterprise. This paper based on the bamboo industry economic operation statistics and analysis of SCM which has been in use, analyzes the requirement, management flow and the idea of customer relationship management, designs and implements a SCM system for bamboo industry.
Keywords:	Bamboo Industry, Supply Chain Management, Economic Operation Statistics
Source:	Journal of Theoretical and Applied Information Technology pp 640 - 645 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN EFFECTIVE DENOISING METHOD FOR MEDICAL ULTRASOUND IMAGE
Author:	HUADONG WANG
Abstract:	In the present work, the denoising problem of medical ultrasound images is researched to ensure the denoising effectiveness. In the ultrasound imaging process, as the organ and tissue will scattering echo signal when the ultrasonic wave arrived, multiplicative speckle noise will form in ultrasound images, and causing damage on image quality. The traditional wiener filtering method can't effectively remove multiplicative noise and reserve image detail information, and then cause ultrasound image denoising efficiency is not high. In order to solve this problem, this paper put forward the alpha ultrasound image denoising method. Though analysis and wavelet decomposition of ultrasound image, it is found that the ultrasound image signal has significant non-Gaussianity, and two-dimensional wavelet coefficients obey the alpha distribution, according to alpha distribution characteristics, adopt estimator using minimum average absolute error criterion to remove multiplicative noise in ultrasound images. Simulation experiments results show that the present method can remove multiplicative noise in ultrasound images on the basis of maximize the retention of the image detail characteristics, and can ensure the higher effectiveness of the ultrasound image denoising.
Keywords:	Ultrasound Images; Multiplicative Noise Spots, Wavelet Decomposition
Source:	Journal of Theoretical and Applied Information Technology pp 646 - 650 Vol. 45. No. 2 -- 2012
Full Text

Title:	MULTI-AGENT SIMULATION IN INTEGRATED PASSENGER TRANSPORTATION SYSTEM UNDER UNCERTAIN ENVIRONMENT
Author:	RONGJIE LV, JIASHUN ZHANG
Abstract:	With the rapid development of transportation technology, public passenger traffic system construction investment is getting more and more expensive. Determining the development trend and make the optimal allocation of transportation investment becomes more and more important to the government. To describe the relationship and development trends of the integrated passenger transportation system under uncertain environment, an uncertain multi-agent model is proposed. Then, uncertain variable simulation technique is introduced to estimate the uncertainties in the model. A simulation program based on swarm platform is developed to implement the proposed model. Finally, a numerical experiment is conducted to illustrate that this technique is effective and can be used in decision support.
Keywords:	Multi-agent Simulation, Uncertain Variable, Transportation System
Source:	Journal of Theoretical and Applied Information Technology pp 651 - 655 Vol. 45. No. 2 -- 2012
Full Text

Title:	AN ITERATIVE LEARNING ALGORITHM BASED ON LEAST SQUARES SUPPORT VECTOR REGRESSION MACHINES
Author:	YUPING YUAN, ZENGLONG AN
Abstract:	Aiming at the problem of the large training data set leading to amounts of calculation a sparse approximation algorithm of least squares support vector machine are proposed. Firstly using the thought of matrix block, convert the optimization problem of a Least Squares support vector machine into low - order symmetric positive definite linear systems. Furthermore, use conjugate gradient algorithm which has the number of smaller conditions ,reduce the number of iterations about least squares support vector machine learning process At the same time, we also proved theoretically that the new algorithm is of faster convergence rate. Dramatically improve the speed of the algorithm for learning and prediction. Finally, experimental results show that the algorithm has a very good performance in terms of the accuracy of forecast and speed of training.
Keywords:	Nonlinear Modeling, Least Squares Support Vector Machine, Support Vector Pruning, Conjugate Gradient Method
Source:	Journal of Theoretical and Applied Information Technology pp 656 - 660 Vol. 45. No. 2 -- 2012
Full Text

Title:	APPLICATION OF FUZZY CLUSTERING IN MULTI-SENSOR INFORMATION FUSION
Author:	AIHONG TANG, YOUMEI ZHANG
Abstract:	In this article, we describe two kinds of Fuzzy clustering algorithm based on partition, use multiple sensors to collect valid data and classifies them. Fuzzy C-means algorithms are on the basis of the Hard C-means algorithm, and get a big improvement, making large data similarity as far as possible together. As a result of Simulation, FCM algorithm has more reasonable than HCM method on convergence, data fusion, and so on.
Keywords:	Fuzzy Clustering, HCM, FCM
Source:	Journal of Theoretical and Applied Information Technology pp 661 - 667 Vol. 45. No. 2 -- 2012
Full Text

Title:	DYNAMIC TOPOLOGY ALGORITHM FOR P2P NETWORKS
Author:	YUNXIA PEI, JUANJUAN LUO
Abstract:	In order to improve the Peer-to-Peer network resource allocation efficiency, and to isolate the malicious nodes, this paper has presented a new method named dynamic topology algorithm (DTA), suitable for unstructured P2P network. As the neighbor node sets variable time-to-live (TTL) values, and in the interaction according to the neighbor node forwarding on the TTL value is adjusted; records of the query path directly on a forwarding node connection; given the forwarding information placing method and topological adjustment algorithm. The simulation experiments and analysis show that, the DTA topology construction method can be malicious nodes isolated to the network edge, improves the efficiency of resource locating, effectively improve the quality of service in P2P network.
Keywords:	Peer-to-Peer, Unstructured, Topology, Resource Locating
Source:	Journal of Theoretical and Applied Information Technology pp 668 - 674 Vol. 45. No. 2 -- 2012
Full Text

Title:	DIE SURFACE COMPENSATION BASED ON THE SPRINGBACK
Author:	XIAODA LI, XIANGHUI ZHAN, XIANGYANG LIU, BAOQING DENG
Abstract:	To solve the problem about the difference between the design shape and the actual after the sheet metal forming because of the springback, the stamping simulation software can be used to predict the springback values, and according the values, the shape of the die surface can be compensated in the opposite direction to make the forming part fit the design requirement. In the paper, according to the springback valves predicted by KMAS, the R、S and the triangular element coordinate mapping methods are put forward to amend the element node movement. And the amending nodes are used to build the CAD model, which can be the reference of the die surface. In the end, an example was shown to test the validity of the method.
Keywords:	Springback, Die Surface Compensation Method, Coordinate Mapping Method, KMAS, Stamping Simulation
Source:	Journal of Theoretical and Applied Information Technology pp 675 - 680 Vol. 45. No. 2 -- 2012
Full Text

Title:	SEMANTICS BASED ON DISTRIBUTED INTERPRETATION FOR ONTOLOGY INTEGRATION
Author:	KUN LIU, SHENGQUN TANG, WEIFENG PAN
Abstract:	Under the background of information integration, the semantics of ontology integration is still an open issue. In this paper, we propose a revised distributed interpretation which is adapted from distributed description logics. In our proposal, ontology integration is taken as global ontology and local ontologies connected by ontology mapping. They are respectively interpreted with description logic semantics and semantic import semantics. Due to the latter, consistency checking can be focused on global ontology and the mapped relations from local ontologies to global ontology. In this way, our method can facilitate understanding and maintenance of ontology integration.
Keywords:	Ontology Integration, Distributed Interpretation, Description Logic, Ontology Mapping
Source:	Journal of Theoretical and Applied Information Technology pp 681 - 687 Vol. 45. No. 2 -- 2012
Full Text

Title:	CALIBRATION ALGORITHM FOR FREEHAND ULTRASOUND
Author:	YAO RAO, YAO PENG
Abstract:	Ultrasound (US) image 3-D calibration for freehand probe is an extremely important technique in computerize 3-D ultrasonic (US image model reconstruction). Calibration is a procedure to calculate the spatial relationship between the US image and the tracker attached to the US probe. In this research, a different cross-string phantom and the corresponding algorithm are presented. The phantom with a set of crosses accelerates interactive operation speed through the strings and crosses out of the scanning plane guiding the operator quickly to find the scanning plane. The other, the ten crosses in the scanning plane provide the coordinates and spatial vectors for the calibration algorithm, thus the calibration algorithm can be optimized based on the least-squares fitting method of the homologous points matching. The results show that the scanning plane positioning time is no more than 5s. The precision and the accuracy demonstrate that the algorithm calculates more accurate matrix than that is obtained through other ways in the same operation time.
Keywords:	Image Processing, Ultrasound Image Calibration, Homologous Points Matching
Source:	Journal of Theoretical and Applied Information Technology pp 688 - 693 Vol. 45. No. 2 -- 2012
Full Text

Title:	MULTI-CLASSIFICATION OF BALL MILL LOAD STATUS USING VIBRATION FREQUENCY SPECTRUM
Author:	LIJIE ZHAO, DECHENG YUAN
Abstract:	On-line monitoring and recognition of mill load status has significant effect on the operating efficiency, product quality and energy consumption for the milling circuit. Due to low reliability to recognize the operating states near the boundary region, a multi- classification model is built to identify the operating status of ball mill load. Spectrum features of shell vibration signals are extracted using kernel principal component analysis as input of the multi-classification model. Partial least square-based extreme learning machine model predicts the output coding of ball mill load status. Bayesian decision theory further enhances the reliability and accuracy of the classification model. The proposed method is compared with one-against-one multi-classification strategy and verified with the experimental ball mill. Experimental results show the accuracy and stability of the proposed multi-classification model of ball mill load status outperforms multi-classification with one-against-one strategy.
Keywords:	Ball Mill, Mill Load State, Multi-class Classification, Vibration Spectrum
Source:	Journal of Theoretical and Applied Information Technology pp 694 - 701 Vol. 45. No. 2 -- 2012
Full Text

Title:	E-TOURISM SUPPLY CHAIN EVALUATION BASED ON AHP AND FCE METHOD
Author:	LIJUAN HUANG, PENG YU, QIAOQIAO LUO, CHUNFANG ZOU
Abstract:	Since 21st century, developing E-commerce has overthrown the traditional tour operation. Tourism supply chain is an alliance established on confidence between each tour operator. And it also changes the traditional business mode. In this paper, the authors make the E-commerce as the breakthrough point, and analyze the traditional tourism supply chain mode, and then propose an evaluation index system of e-tourism supply chain. This research is based on AHP and Fuzzy Comprehensive Evaluation (abbr. FCE). The authors believe that the application of this mode may greatly enhance the coordination capacity and flexibility of tourism supply chain, and can also raise the tourists’ satisfaction and meet visitors’ personalized demand. Evaluation model of e-tourism supply chain has been applied to scenic spots in Jiangxi.
Keywords:	E-Tourism Supply Chain, Evaluation Model, Network Intermediary, AHP, FCE
Source:	Journal of Theoretical and Applied Information Technology pp 702 - 709 Vol. 45. No. 2 -- 2012
Full Text

Title:	A HVS MODEL FOR REPRESENTATION OF DOMAIN-ORIENTED WEB PAGE TOPIC FEATURES
Author:	XIANGHUA WU, QIAO GUO, LEI LA, QIMIN CAO
Abstract:	Domain-oriented web page extraction is a new and practical direction in the field of information extraction. The paper focuses on the representation of domain-oriented web page topic features, and hierarchical vector space (HVS) model is put forward. Considering the hierarchical characteristics of the web page itself, topic features of the web page are expressed more effectively by HVS model from the facets of the page structure and the content. Then the topic-related page identification problem is discussed by the similarity calculation. Experimental results show good accuracy and applicability for our system to domain-oriented web extraction.
Keywords:	Domain-Oriented, Hierarchical Vector Space Model, Information Extraction
Source:	Journal of Theoretical and Applied Information Technology pp 710 - 715 Vol. 45. No. 2 -- 2012
Full Text

Title:	INTELLIGENT LOGISTICS SYSTEM BASED ON THREE-TIER ARCHITECTURE AND RFID
Author:	DONG HUANG, HE WEI
Abstract:	Radio frequency identification technology (RFID) is a non-contact intelligent identification system, its main advantage lies in the wide range of recognition, information capacity, security, excellent resistance to abrasion, reusable. It can take place of the traditional bar code recognition technology, and be applied to the area of modern intelligence logistics management. This thesis introduces the working principle of the net three-tier system and RFID technology, and proposes the setting-up of the intelligent logistics system based on three-tier system and RFID technology. The thesis also studies the design and realization of the data access layer, logic layer and presentation layer for providing technical backing to the Logistics management of enterprise monitoring and decision. The experiment shows that the system can greatly improve the intelligence level of the logistics management, improve the competitiveness and economic benefits of logistics enterprises.
Keywords:	Three–tier Architecture, RFID Technology, Intelligent logistics, Technical Support
Source:	Journal of Theoretical and Applied Information Technology pp 716 - 722 Vol. 45. No. 2 -- 2012
Full Text

Title:	CASCADE-CORRELATION NEURAL NETWORK FOR VIBRATION FITTING OF HYDRAULIC TURBINE UNITS
Author:	CHUNLIU LI, LIYING WANG
Abstract:	Cascade-Correlation (CC) network is a new architecture and supervised learning algorithm for artificial neural networks. The learning algorithm of CC network and its network structure are described in this paper, the CC network with an excellent fitting ability is applied to fitting vibration characteristics of hydraulic turbine units according to different parts under three water heads. Compared with the BP network, the simulation experiments demonstrates that the CC network has a faster convergence speed and a higher accuracy, it is much closer to true to describe the vibration characteristics of hydraulic turbine units under different working conditions for their parts than its counterpart.
Keywords:	Cascade-Correlation Neural Network, Vibration Fitting, Turbine Units
Source:	Journal of Theoretical and Applied Information Technology pp 723 - 727 Vol. 45. No. 2 -- 2012
Full Text