Table of Content

01 December 2008, Volume 28 Issue 12

Previous Issue    Next Issue

Digital media technology

Survey of physical-based deformable modeling

Hong-Bin CAI Zi-Chun ZHONG Lei-Ting CHEN Jing-Wu ZHOU

2008, 28(12):  2991-2993. 

Asbtract ( )   PDF (642KB) ( )  

Related Articles | Metrics

Physical-based deformable models have been popular in the field of computer graphics. The most significant contributions were presented including Euler method, mass-spring system, finite element, boundary element, smoothed particle hydrodynamics and meshfree method. The connection to the simulation of other continua was also discussed, such as fluid, fire, gas, lava flow and melting objects for completeness. Finally, the areas of application were summarized, such as elastoplastic deformation and fracture, cloth and thin shell simulation, sand and mud animation, interactive entertainment. Future research areas were also described.

GPU-based meshless fluids interactive rendering

Lei-Ting CHEN Zi-Chun ZHONG Hong-Bin CAI

2008, 28(12):  2994-2997. 

Asbtract ( )   PDF (643KB) ( )  

Related Articles | Metrics

An approach based on smoothed particle hydrodynamics to simulate fluids with free surfaces was proposed, while surface tension was modeled by using Van der Waals equation of state with a combination of short-range repulsive and longer-range attractive interactions between fluid particles, finally a GPU-based particle splatting algorithm was designed for rendering. This approach completely avoids the temporal discretization artifacts, which results in the interactive rendering effects with high quality. In contrast to traditional Lagrangian approaches, this method uses the simplified surface tension model with fast rendering algorithm, reduces the complexity of the simulation and efficiently advances the run-time speed.

Domain based fast feature modeling: Design and implementation

Hong-Xin ZHANG Wei-Feng Chen Hua Liu

2008, 28(12):  2998-3002. 

Asbtract ( )   PDF (892KB) ( )  

Related Articles | Metrics

A domain-based fast feature modeling approach was proposed. Inspired by the approach of Domain Engineering in software engineering, for a particular field of feature modeling design, this approach is on how to use the knowledge of such field to improve geometric modeling system. As a result, the entire efficiency of the geometric modeling system was improved by optimizing software architecture and algorithm design. Base on this novel method, the demand of geometric modeling in Computer-Aided Architectural Design (CAAD) was discussed, and a system framework for domain-based geometric modeling was created. Several examples of this method in industry modeling design and digital entertainment fields prove the effective.

MPEG video encryption algorithm based on Lorenz chaotic system

Zhi-liang ZHU Wei ZHANG Hai YU

2008, 28(12):  3003-3006. 

Asbtract ( )   PDF (659KB) ( )  

Related Articles | Metrics

An encryption algorithm which combined the process of MPEG video compressing with video encryption based on Lorenz chaotic system was put forward to deal with the security problem of video information. Three dimensional chaotic sequences of Lorenz system were used to encrypt DC, AC and motion vector coefficients during the compressing of I frame, B frame and P frame. The luminance information of I frame was encrypted among blocks by the chaotic sequence. The algorithm is secure and real-time because the encryption is done during the process of video compressing.

Real-time meshless deformation based on particle system and shape matching

Ji-Cheng LIN Huan DING Xiao-Hui TAN

2008, 28(12):  3007-3009. 

Asbtract ( )   PDF (453KB) ( )  

Related Articles | Metrics

An algorithm for simulating deformable objects was presented based on particle system and shape matching. In this method, each vertex of a model was considered as a particle, so a model was represented by a particle system, which controlled the shape of the deformable object. And each particle had a corresponding goal position. Since there were forces among particles and their corresponding goal positions to pull the particles back, the deformable object would finally return to its original shape. The goal position could be computed via a generalized shape matching of a non-deformed rest state with the current deformed state of the particle system. The algorithm did not require complex data structure and it was simple to implement. Experimental results show that the presented algorithm provides unconditional stability in real-time simulation, and can be effectively used in 3D games.

Network and communications

Research of reliable routing in wireless Ad Hoc network

2008, 28(12):  3010-3013. 

Asbtract ( )   PDF (720KB) ( )  

Related Articles | Metrics

First, the Expected Transmission Count (ETX) algorithm was improved, and the new link status monitoring algorithm of combining the dynamic ACK algorithm and the improved ETX algorithm was presented, which could ignore the bad link in routing path. Then a new backup routing mechanism was proposed to replace the previously mentioned backup routing mechanism of QDSR. Route recovering could be initiated from middle nodes on the disjoined path, therefore, the route recovery could be done fast. NS2 simulation results demonstrate that the improved algorithm significantly reduce the routing error, and greatly reduce the average time to find a new path after the disjoined path in a large scale MANET of the node while at smaller moving speed.

Assisted interest-based method for searching shared files in P2P network

LI Tao Shi-ping CHEN

2008, 28(12):  3014-3016. 

Asbtract ( )   PDF (600KB) ( )  

Related Articles | Metrics

Having studied the advantages and disadvantages of some traditional searching methods in structured and unstructured P2P networks, an assisted interest-based searching method was proposed to enhance the search in unstructured P2P overlay networks by registering interests of nodes in structured P2P overlay networks. Experimental results show that this method achieves good performance in success rate and search latency.

Web service selection based on genetic algorithm with tree dual-structure code

2008, 28(12):  3017-3020. 

Asbtract ( )   PDF (594KB) ( )  

Related Articles | Metrics

A concept of syntactic business process tree for Web service was proposed. And considering the characteristics of service global selection based on QoS, a genetic algorithm with tree dual-structure code for Web service global selection named GATD was studied. This algorithm was established on syntactic business process tree for Web service (SBPT4WS) and dealt with restriction conditions with dual-structure code. And it can not only effectively select service resource meeting users' QoS requirements, but also preferably support rapid replanning on service executione.

Algorithm for choosing ARQ feedback types based on IEEE 802.16

CAI Cang-Fu Yan YANG

2008, 28(12):  3021-3023. 

Asbtract ( )   PDF (583KB) ( )  

Related Articles | Metrics

ARQ mechanism in IEEE 802.16 can resolve the problems for data transmission on wireless link, but there is no appropriate solution for choosing the ARQ feedback types. The key to the algorithm is to choose an appropriate feedback type to send feedback messages for high resource utilization according to wireless link. Therefore, a new algorithm for choosing proper feedback types in real time was proposed. The simulation results show that the new algorithm can increase resource utilization.

Fuzzy-logic-based call admission control scheme for multimedia multicast application

Kan-Min YU

2008, 28(12):  3024-3028. 

Asbtract ( )   PDF (715KB) ( )  

Related Articles | Metrics

Multicast Call Admission Control (CAC) is the key issue of NGN QoS. Based on the analysis of existing CAC mechanisms, a fuzzy-logic-controlled multicast call admission control mechanism was proposed, termed FMAC. FMAC considered four parameters, including quality of service, network congestion status parameters, available capacity and equivalent bandwidth, as fuzzy input for CAC. with fuzzy inference, the decision of acceptance of new multicast call was obtained. FMAC was proved to be scalable, easy to implement, and suitable for both unicast and multicast. Simulations with multicast services show that, FMAC can reach high network exploitation while statistically meet the needs of users on QoS, and can keep low values of blocking frequency when the network is correctly dimensioned.

Virtual-timing-based policing algorithm in AFDX network

Lei Shen Shaohui Yang Zhiliang Qiu

2008, 28(12):  3029-3031. 

Asbtract ( )   PDF (593KB) ( )  

Related Articles | Metrics

To implement policing algorithm in specific device (e.g. FPGA), designers should not only consider the correctness and efficiency of the algorithm, but also take account of the feasibility. A virtual-time-based policing algorithm used in Avionics Full Duplex Switched Ethernet (AFDX) network, of high efficiency and low logic resources consumption, was introduced in detail. The consumption of resource and several important problems were danalyzed. This algorithm had been implemented in ALTERA's FPGA, and could be applied to other networks.

Resource allocation scheme based on dynamic policy and mobile prediction

Xue-Jie LIU Hu-ying LIU Qi LI

2008, 28(12):  3032-3036. 

Asbtract ( )   PDF (818KB) ( )  

Related Articles | Metrics

A dynamic resource allocation scheme based on dynamic policies and mobile predicted information was presented for the problem that traditional policies cannot preferably get adapted to the change of network state. Policy Decision Point （PDP） made decisions before the mobile users' arriving and worked out parameter values of the action according to the predicted information of the users,guidance policies and universal policies when it made decisions, which decreased the amount of stored policies and improved the adaptability of policies to network state. By experiments and analysis, it is shown that this scheme insures new call blocking probability, reduces handoff call dropping probability and increases network resource utilizing rate.

Energy efficiency analysis of DCF-based MAC protocol in Ad Hoc network

HUANG Jing-Lian

2008, 28(12):  3037-3040. 

Asbtract ( )   PDF (736KB) ( )  

Related Articles | Metrics

IEEE 802.11 Medium Access Control (MAC) protocol provides a competition-based distributed channel access mechanism for mobile stations to share the wireless medium in wireless Ad Hoc networks. Under the precondition of variable packet length, an energy analytical method was proposed, which calculated the energy efficiency of the basic, the RTS/CTS (Request To Send/Clear To Send) and the hybrid access mechanisms of the IEEE 802.11 Distributed Coordination Function (DCF). Furthermore, the effects of the network size, the average packet length, maximum backoff time, and the initial contention window on the energy efficiency of IEEE 802.11 DCF were explored in detail. Correctness and effectiveness of the proposed analytical method were verified through detailed simulation results.

Time synchronization protocol for Ad Hoc network based on delay-probing

2008, 28(12):  3041-3044. 

Asbtract ( )   PDF (637KB) ( )  

Related Articles | Metrics

The MAC protocol based on reservation and dynamic-slot distribution can offer fine QoS guarantee for real-time traffic. One of its key technologies is how to realize the synchronism among the nodes. Therefore, a new time synchronization protocol for Ad Hoc network by means of delay-probing was put forward, which combined the merits of DMTS protocol and TPSN protocol. Through transmitting and relaying a little probing code, the protocol could complete the retardation measuring. Owing to the separation between delay-probing course and time-correcting course, the conflict and burden of the network could be lightened. Analysis and simulation indicate that DMC-TS protocol is simple to realize, and possesses a precision which can be compared with TPSN protocol.

Solution to stalemate situation of mobile home Agent

Song-Hua Huang HUANG Hao

2008, 28(12):  3045-3047. 

Asbtract ( )   PDF (605KB) ( )  

Related Articles | Metrics

Based on the tree model of access routers of nested mobile network, a solution to crack the stalemate situation of mobile home Agent was proposed. In comparison with its counterparts, the proposed scheme could decrease network handover delay and save more overhead in traffic from and to mobile network with deeper nesting while guaranteeing the session continuity between the mobile network nodes and any correspondent from the Internet and among nodes from floating nested mobile networks as well.

Design and implementation of header compression prototype system in TinyOS

Jian-Jun ZHANG Si-Wang ZHOU

2008, 28(12):  3048-3051. 

Asbtract ( )   PDF (629KB) ( )  

Related Articles | Metrics

Wireless Sensor Networks (WSNs) are resource constraint, and header compression can significantly reduce the amount of data transferred and improve channel utilization efficiency. The header characteristics and compressibility of the active message layer and communication layer in the protocol stack of the TinyOS were analyzed, then a header compression scheme for TinyOS was proposed, which could reduce the length of header significantly. First, communication components of TinyOS were modified and a new compression layer was inserted in the protocol stack to make the TinyOS support header compression. Then, based on a network composed of Micaz nodes, a header compression prototype system was designed and developed to implement the header compression scheme. The results of comparison experiments show that the prototype system can effectively reduce energy consumption and packet loss rate of the network.

Artificial intelligence

Evolutionary ensemble of neural network based on niche technology

Shi-cai YU Juan CHEN

2008, 28(12):  3052-3054. 

Asbtract ( )   PDF (596KB) ( )  

Related Articles | Metrics

In view of the current problems that neural network ensemble generates individual networks with low difference degree and its poor generalization ability, a method of evolutionary ensemble of neural network based on niche technique was proposed. Niche technique's good performance was used in increasing population diversity and improving local search capability of evolution, and the similarity degree's sharing function among individuals was adopted to adjust individual network's fitness. Then the individuals were selected according to the new adjusted fitness to get individual network with diversity. Theoretical analysis and experimental results show that this method can generate individual network with great difference degree and can improve the generalization ability and calculation accuracy of neural network ensemble system.

Improved PSO algorithm with adaptive neighborhood

Wan-Bo Xing Sheng-Qi Yang Shu-Ping Wang Wen-jie Chen

2008, 28(12):  3055-3057. 

Asbtract ( )   PDF (569KB) ( )  

Related Articles | Metrics

Based on thorough analysis on the existing PSO algorithms, an improved PSO algorithm with adaptive neighborhood was proposed, which included two special improvements: the mechanism of scheduled neighborhood adaptation, and a modified mechanism of scheduled interia weight adaptation. The proposed PSO algorithm is proved to be high-performing and high accurate by 7 standard banchmark functions.

Adaptive particle swarm optimization algorithm based on Sigmoid inertia weight

Dong-Ping TIAN

2008, 28(12):  3058-3061. 

Asbtract ( )   PDF (594KB) ( )  

Related Articles | Metrics

Due to the disadvantages of the canonical Particle Swarm Optimization (PSO), a new adaptive particle swarm optimization algorithm based on Sigmoid inertia weight was proposed. On the one hand, the premature computing formula of the particles was introduced so as to conduct the evolution process and enhance the convergent speed. On the other hand, the decision threshold of particles' focusing degree was employed in order to make the PSO adaptively adopt the inertia weight between linear decrease and nonlinear decrease based on Sigmoid function, which could effectively prevent the PSO from plunging into local minimum. The experimental results show that the proposed algorithm is feasible and effective.

Hybrid artificial fish swarm algorithm for global optimization problems

HUANG Hua-Juan Yong-quan ZHOU

2008, 28(12):  3062-3064. 

Asbtract ( )   PDF (625KB) ( )  

Related Articles | Metrics

Based on the Powell algorithm and Adaptive Artificial Fish Swarm Algorithm (AAFSA), a hybrid artificial fish swarm algorithm (AAFSA-Powell) for global optimization problems was presented by inserting Powell algorithm into AAFSA. As a local search operator, Powell algorithm has strong local search ability, whereas artificial fish swarm algorithm has global convergence. Therefore, the hybrid algorithm is capable of improving the global search ability of the algorithm, as well as reducing the computational burden. The numerical experimental results show that the algorithm can converge quickly with high adjustment.

Optimize method of minimizing fuzzy finite automata

Charine Zhang

2008, 28(12):  3065-3067. 

Asbtract ( )   PDF (397KB) ( )  

Related Articles | Metrics

The existing methods of minimizing fuzzy finite automata do not discuss the transfer and change of the grade of fuzzy automata, but the problem is solved in the optimized method. Firstly, the method transferred from fuzzy finite automata to normal fuzzy automata of a single initial state, and then transferred the normal fuzzy automata into the minimum fuzzy finite automata. Moreover, how the grades of fuzzy states transferred was discussed independently in the transferring methods. Optimizing the method is to make the algorithm simpler and more precise.

Adaptive genetic algorithm of cloud based on double bee population evolutionary

2008, 28(12):  3068-3071. 

Asbtract ( )   PDF (582KB) ( )  

Related Articles | Metrics

Traditional adaptive genetic algorithm still easily gets stuck at a local optimum. To solve the problem, a novel adaptive genetic algorithm of cloud based on double bee population evolutionary was introduced, which was based on stable tendency of a normal cloud model and the evolutionary mechanism of double bee population. In this algorithm, a Y-conditional normal cloud generator and the queen were used as the cross operator of genetic algorithm, and a basic normal cloud generator was used as the mutation operator. From the simulation results of function optimization and the optimization of heavy rain intensity formula's parameter, it is believed that the improved algorithm is effective and will become a promising candidate of evolutionary algorithms.

Improved genetic algorithm for maximum clique problem

Dong-Hui WU

2008, 28(12):  3072-3073. 

Asbtract ( )   PDF (286KB) ( )  

Related Articles | Metrics

Maximum Clique Problem (MCP) is a classic NP Complete problem in combinatorial optimization. Its enumeration algorithm is only suitable for graphs with small scale. A new method based on genetic algorithm for MCP was proposed. Probability model was introduced to guide mutation when generating offspring, and heuristic local search was combined to find clique. The experimental results show that its performance is satisfying.

Diploid code genetic algorithm used to solve UTP

2008, 28(12):  3074-3076. 

Asbtract ( )   PDF (624KB) ( )  

Related Articles | Metrics

The University Timetable Problem (UTP) is a typical NP-hard problem. Using the layered method, the common combined programming model of five dimensions was decompounded into two three-dimensional combinations, cutting down the problem scale. Then in view of the disadvantages of the traditional genetic algorithm for UTP, the diploid code was put forward and alternate evolution was used to optimize multi-targets one by one. Experimental results show that the method realizes the pattern theorem and quickens the evolving velocity.

Adaptive genetic strategy with continuous mutation

Si-Yan WANG Guo-Li ZHANG

2008, 28(12):  3077-3079. 

Asbtract ( )   PDF (577KB) ( )  

Related Articles | Metrics

A new algorithm based on continuous mutation was proposed. The mixed selection was used for choosing individuals. Through the combination of the phased crossover and the cosine adaptive crossover, the double adaptive crossover got the crossover probability. The continuous mutation strategy used continuous process from crude search to precise search. Numerical experiments show that the new algorithm is more effective in realizing the high convergence speed, convergence precision, reducing the convergence algebra and good at keeping the stability of the adaptive genetic algorithm.

Pattern recognition and Software

Influence of feature weight on text categorization performance of Bayesian classifier

2008, 28(12):  3080-3083. 

Asbtract ( )   PDF (548KB) ( )  

Related Articles | Metrics

In the field of text categorization, researchers tend to use feature weights to promote the performance of text classifiers. Taking the optimal classifier - Bayesian classifier, as the benchmark, theoretical analysis was performed about the possible influence of feature weight on text categorization performance. Theoretical deduction proves that feature weight can not effectively improve the performance of text categorization if the text classifier is a Bayesian one.

Key frame extraction based on curvature detection of multi-feature similarity curve

YU WU Xue-Peng JIA Hong-Bo LI

2008, 28(12):  3084-3088. 

Asbtract ( )   PDF (868KB) ( )  

Related Articles | Metrics

With the development of network multimedia, quick and low-cost management of the massive video information is urgently needed. Key frames can decrease data quantity in video indexing and provide a framework for video retrieval and indexing. A key frame extraction method based on high-curvature points detection was proposed. First, three descriptors of color histogram, edge direction histogram and wavelet statistics were used to describe visual content, and combined to form a frame difference measure. Then the key frames were got by detecting high curvature points. Experimental results show that the proposed algorithm is rapid and efficient. It can capture precise changes dynamically in the content of video sequences, and can extract the key frames on the fly. Finally, a fidelity evaluation proves the effectiveness of the algorithm.

Application of HHT to different mental tasks in EEG analysis

2008, 28(12):  3089-3091. 

Asbtract ( )   PDF (561KB) ( )  

Related Articles | Metrics

The non-linear, non-stationary signal processing method named Hilbert-Huang Transformation (HHT) and its characteristics were introduced, and it was applied to the different mental tasks in EEG analysis. The results indicate that different mental tasks in EEG have different Hilbert-Huang spectrums and Hilbert marginal spectrums, which proves HHT to be a feasible method on EEG analysis.

Research of combined forecasting model for software reliability

2008, 28(12):  3092-3094. 

Asbtract ( )   PDF (438KB) ( )  

Related Articles | Metrics

Based on grey model, harmonic analysis and time series analysis theory, the fault data sets obtained from software reliability testing phase were analyzed, and then a combined forecasting model for software reliability was proposed. Referring to practical data, the realization method was presented. The experimental result indicates that the combined model has higher precision of prediction and better adaptability, compared with other single time series prediction models.

Skin detection based on maximal class separability in new color space

Xiao-Hua LI

2008, 28(12):  3095-3097. 

Asbtract ( )   PDF (654KB) ( )  

Related Articles | Metrics

Four new color space models were constructed based on Bhattacharyya distance aiming at skin detection. Meanwhile, according to Bhattacharyya distance measurements of each feature in the new color spaces, some most discernible features were selected to form an assembled model for skin detection. Then, in traditional color spaces and four new spaces，Bhattacharyya distance and positive detection rate were compared on skin and non-skin samples. The experimental results indicate that the new color spaces based on maximal class separability performs better. Eventually, the illustration of skin segmentation in color images also verifies the effectivenesses of both new color space model and assembled model.

Improvement of full function point for Web-based applications

Xun-Mei GU Hui-Qun YU

2008, 28(12):  3098-3101. 

Asbtract ( )   PDF (663KB) ( )  

Related Articles | Metrics

Full Function Point (FFP) is a widely and expediently used method of software Functional Size Measurement (FSM), but it can only measure the static aspects of systems and can not take the interactions and behaviors of objects into consideration. On the foundation of measurement elements of COSMIC-FFP and the structure of Web applications, an improved COSMIC-FFP software model was proposed and measurement rules were also supplied especially for Web applications. An example was also given to explain these rules.

Social network matching model using dynamic Bayesian network

WU Jun-Wei Yu Fang

2008, 28(12):  3102-3104. 

Asbtract ( )   PDF (443KB) ( )  

Related Articles | Metrics

In order to help a new client in the social network finding the best matching circle of social communication for itself, the Dynamic Bayesian Network (DBN) theory was introduced. The group set up by several hobbies' degrees was described as the eigenvector of the circle's property and DBNs with auxiliary information were set up for each circle using this eigenvector. The best matching result is the DBNs maximal output. Objective and subjective experiments show that this model can achieve satisfactory result for the matching task.

Graphics and image processing

Blind detection of image splicing based on image quality metrics and moment features

Zhen ZHANG Jiquan Kang Xijian Ping Yuan Ren

2008, 28(12):  3108-3111. 

Asbtract ( )   PDF (759KB) ( )  

Related Articles | Metrics

Image splicing is a technique commonly used in image tampering. To implement image splicing blind detection，a new splicing detection scheme was proposed. Image splicing detection could be regarded as a two-class pattern recognition problem and the model was established based on moment features and some Image Quality Metrics (IQMs) extracted from the given test image. This model could measure statistical differences between original image and spliced image. Kernel-based Support Vector Machine (SVM) was chosen as a classifier to train and test the given images. Experimental results demonstrate that this new splicing detection scheme has some advantages of high-accuracy and wide-application.

Fuzzy segmentation of urban areas in panchromatic remote sensing images

2008, 28(12):  3112-3115. 

Asbtract ( )   PDF (638KB) ( )  

Related Articles | Metrics

A fast fuzzy algorithm for the segmentation of urban areas especially in panchromatic remote sensing images was proposed. The algorithm was supposed to be an image previous process for the small targets recognition in immense remote sensing images. Based on the fuzzy set theory, a membership function was introduced according to Bayesian criteria. The process of segmentation was achieved gradually by using appropriate features of urban areas. The experiment was implemented on SPOT-5 PAN images and a reliability analysis of the fuzzy membership function was made after the segmentation. Compared with the region growing segmentation method and the algorithm based on multi-scale wavelet geometry information, the experimental results show that this algorithm has good performance with low complexity and high accuracy, and it is an efficient preprocessing technique for some important remote sensing applications.

Real-time correcting algorithm of extracted contour based on graph cuts

XU Qiu-ping GUO Min WANG Ya-rong

2008, 28(12):  3116-3119. 

Asbtract ( )   PDF (807KB) ( )  

Related Articles | Metrics

Post correcting of the extracted contour is an important measure to further improve extraction accuracy. Aiming at the difficulty and limitation of correcting implementation and generalization within the corresponding extracting algorithm framework, an independent correcting algorithm based on graph cuts was proposed. At first, the region to be corrected was obtained by human-computer interaction. Then the region was mapped into an s-t network. Finally a corrected object contour was obtained using the max-flow/min-cut algorithm. The experimental results show that the simplification, real-time responding, and strong anti-noise ability of the proposed approach are suitable for general contour-based object extraction.

Improved target tracking algorithm based on Mean-shift

Da-Yong JIANG Yang ZHOU

2008, 28(12):  3120-3122. 

Asbtract ( )   PDF (415KB) ( )  

Related Articles | Metrics

Traditional Mean-shift target tracking algorithm is rather sensitive to background environment. The use of kernel weighted histogram for target template and target candidates can not always get exact center of the target. Therefore, an improved feature selection mechanism was proposed, in which background weighted histogram was chosen for target template and kernel weighted histogram for target candidates. The simulation results show that the method achieves more accurate target tracking in complex environments.

C1-continuous triangular Coons patches with shape parameter

Xiao-Qin WU HAN Xuli Shan-Ming LUO

2008, 28(12):  3123-3125. 

Asbtract ( )   PDF (616KB) ( )  

Related Articles | Metrics

In order to improve the transfinte interpolation surfaces, two kinds of C1-continuity Coons patches with shape parameter were constructed by two classes of λ-Hermite polynomial functions on triangles. Triangular Coons patches with shape parameter were the extensions of side-side scheme and side-vertex scheme. These shapes depended on shape parameter λ and degenerated the triangular Coons patches under λ＝0.With changing the value of λ,the interior shape of the patches could be adjusted, but the boundary shape of the patches was not influenced. At last,examples illustrate that the scheme of constructing surface is very useful for surface design.

Gray projection image stabilizing algorithm based on log-polar image transform

Bo YU Lei Guo Tian-yun ZHAO

2008, 28(12):  3126-3128. 

Asbtract ( )   PDF (501KB) ( )  

Related Articles | Metrics

Traditional gray projection image stabilizing algorithm just works under horizontal and vertical movement; but it is unable to deal with either scaling or rotation of the matched images. Due to the limitation, a gray projection image stabilizing algorithm based on log-polar image transform was introduced. When log-polar image transform was used in scaling or rotation image, the scaling or rotation movement in Descartes reference frame was represented by horizontal and vertical movement in log-polar reference frame. Accordingly, gray projection algorithm could be used in scaling or rotation image.

Edge extraction method with multi-scale gradient

Liang CHEN Lei GUO

2008, 28(12):  3129-3131. 

Asbtract ( )   PDF (497KB) ( )  

Related Articles | Metrics

To extend the application of traditional edge extraction methods based on gradient, a new method combined with multi-scale idea was proposed. According to the response of the gradient on the edge, the integration of different scale gradients was used to define the edge feature with a new view, which was self-adaptive to the image. Next, non-maxima suppression was employed to obtain the maximal response of the integrative edge feature, which made the method adapted to strong or weak edge based on the local extremum instead of the global one. Experimental results prove that the method is much better than traditional ones and it is not sensitive to the noise.

Fairing and approximation algorithm of C-Bezier curves

Xin-qiang QIN Gang HU Fei LIU

2008, 28(12):  3132-3134. 

Asbtract ( )   PDF (359KB) ( )  

Related Articles | Metrics

Based on the fairing requirements of the strain energy and jerk energy of a thin elastic beam, a new method of fairing C-Bezier curves was given. This method considered the strain, the strain energy and jerking energy of the curves, and set up a new fairing rule of C-Bezier curves firstly. Secondly, according to this rule, fairing of curves was fulfilled by adjusting the value of parameter α and controling points to reduce the implied energy. By using least square approximation and non-linear functional minimization, the data points of plane could be faired approximately. Finally, examples of C-Bezier curve fairing show the efficiency of the method.

Panorama real-time unrolling of catadioptric omni-directional images with look-up table based on FPGA

Bin Wang

2008, 28(12):  3135-3137. 

Asbtract ( )   PDF (619KB) ( )  

Related Articles | Metrics

In order to design a real-time embedded system for catadioptric omni-directional images, a look-up table approach for omni-directional images was used on FPGA. Combined with FPGA features, some methods were used to improve the speed of panorama unrolling, including dividing image into blocks and unrolling the image blocks, time-hidden data access technology and FPGA pipeline technology, etc. Experiments indicate that the methods make the unrolling achieve a level of 100 frames per second, when dealing with 1024×768 YUV 4∶2∶2 source image to 1280×256 YUV 4∶2∶2 target image. It is 12 times faster than a look-up table panorama unrolling based on single pixel.

Image denoising based on fast discrete curvelet transform

Gao-Qiu Fang Zheng-yong Wang Xiao-hong Wu

2008, 28(12):  3138-3140. 

Asbtract ( )   PDF (468KB) ( )  

Related Articles | Metrics

Curvelet can reflect anisotropy of singular function and image edges; therefore it is better suitable for multiscale image denoising. According to the defects of the traditional thresholding methods, the diamond-shaped pieces thresholding algorithm combined with cycle spinning algorithm was proposed after analyzing the fast discrete curvelet transform based on wrapping algorithm, and the curvelet transform coefficients in different subbands were filtered with adaptive thresholds. The method can avoid image distortion due to the lack of translation invariance of curvelet transform, and can make use of correlation of curvelet coefficients better. Experimental results show that the proposed method yields denoised images with higher PSNR and better visual effects compared with the traditional wavelet denoising algorithm, the hard-threshold denoising method, the soft-threshold denoising method and the method between soft and hard thresholding based on curvelet transform.

Moving shadow removal based on invariant texture feature

yuanyuan hu rangding wang

2008, 28(12):  3141-3143. 

Asbtract ( )   PDF (581KB) ( )  

Related Articles | Metrics

Moving shadows cause serious problem while segmenting and extracting foreground from video sequences, due to the misclassification of moving shadow as foreground. In order to detect the moving objects accurately, a method based on the similarity between little textured patches was proposed to remove the moving shadows. Firstly, the potential shadows were detected by analyzing the intensity and color properties. Secondly, the shadow detection approach was improved by evaluating the textural similarity between the current frame and the corresponding background model. Finally, the geometric heuristics were imposed to further improve the performance. Experimental results on both indoor and outdoor scenes exhibit that the proposed method succeeds in removing shadows robustly and achieves real-time performance.

Fast geometry deformable insect's color image segmentation algorithm

Mingquan Zhou

2008, 28(12):  3144-3146. 

Asbtract ( )   PDF (410KB) ( )  

Related Articles | Metrics

Most of the existing geometric deformable model methods can not be directly used for color image segmentation. Therefore, fast geometry deformable color image segmentation algorithm was proposed to solve the problem and be applied to insect color image. The experimental results show that the algorithm can segment target insect in the image successfully. However, the results with channel by channel fast geometry deformable algorithm are different edges of the same insect in different channels.

Novel image contour grouping algorithm based on competitive layer neural network

2008, 28(12):  3147-3149. 

Asbtract ( )   PDF (641KB) ( )  

Related Articles | Metrics

An image contour grouping algorithm based on Competitive Layer Neural Network (CLNN) was proposed. The presented algorithm, which is inspired from the lateral interactions and WTA interaction within the biological visual cortex, performs the grouping perception on the image by using the visual signal processing mechanisms similar to the biological neurons. The results of experiments show that the proposed algorithm exhibits stronger grouping capability and promising anti-noise capability.

Optimization and application of connected component labeling algorithm based on run-length encoding

Shi-Jie CAI Qiang YU

2008, 28(12):  3150-3153. 

Asbtract ( )   PDF (582KB) ( )  

Related Articles | Metrics

To improve the robustness of image real-time feedback control system, connected component labeling algorithm was applied to droplet contour extraction in space droplet evaporation experiment. The algorithm was optimized in two aspects to realize a faster processing speed and smaller memory occupation in real-time image processing. First, it introduced run-length encoding into DSP real-time image processing to reduce memory occupation and the quantity of objects. Second, it optimized Suzuki's labeling algorithm by solving the problem that it could lose some label equivalences in assignment operation in one scan process. By changing the assignment of label connection table, it can memorize all label equivalences in one scanning. The result of experiments demonstrates that the optimized algorithm is superior to conventional algorithms in terms of processing speed and memory occupation.

Moving objects extraction in video sequence based on moving point accumulation

Meng Yuan 孟苑

2008, 28(12):  3154-3156. 

Asbtract ( )   PDF (519KB) ( )  

Related Articles | Metrics

Through the analysis on the characteristics of the moving objects in video sequence, a method to acquire background was proposed. Moving point accumulation was applied to extract the background, and then background subtraction was employed to detect moving objects. Because of visual comparability, the result included shadow. Shadow filter function was used to remove the shadow to get the completely moving objects. Experimental results show that the algorithm is efficient, adaptive, and establishes a foundation for advanced image processing.

Fast inter mode decision algorithm for H.264/AVC

Feng XIN

2008, 28(12):  3157-3159. 

Asbtract ( )   PDF (453KB) ( )  

Related Articles | Metrics

In order to resolve the high computation complexity in inter-mode decision, a novel fast algorithm was proposed. The proposed algorithm utilized the adoption information of coding mode and spatio-temporal correlation to judge maximum possible mode of current macroblock beforehand, so it consequently accelerated the process of mode decision greatly. The proposed algorithm reduced the range of candidate modes and used thresholds to heighten precision of prediction. Simulation results demonstrate that the proposed algorithm can reduce encoder complexity significantly while coding quality is only slightly decreased.

Algorithm to generate progressive meshes based on quadric error metric

Hua SONG Jiang LIU

2008, 28(12):  3160-3162. 

Asbtract ( )   PDF (489KB) ( )  

Related Articles | Metrics

A kind of progressive three-dimensional mesh generation algorithm was studied. Under the premise of a fixed resolution and to obtain a higher quality of three-dimensional model, an improved algorithm for the progressive meshes based on quadric error metric was presented. The algorithm used a contour protection and produced a 2-adjacent filed index. Experimental results indicate that the model produced by the algorithm is better than others in literature.

Information security

Proxy signcryption scheme with public verifiability and controllable authority

Shu-Hai WANG ZhiYong FENG Zhao-Hui QI

2008, 28(12):  3163-3164. 

Asbtract ( )   PDF (489KB) ( )  

Related Articles | Metrics

The Shin's signcryption scheme with public verifiability of Shin et al.and the proxy signcryption scheme of Jung et al. were cryptoanalyzed and improved. By studying the confidentiality of Shin's scheme and Jung's scheme, and the proxy authority of Jung's scheme, the fact is that the confidentiality of Shin's scheme and Jung's scheme was lost, and the proxy authority of Jung's scheme was not controlled. Then a modification based on Shin's scheme was presented. The modification was a security proxy signcryption scheme with public verifiability and controllable authority. Based on some cryptographic assumptions, the security of the scheme was also proved.

Authenticated certificateless key agreement protocol

2008, 28(12):  3165-3167. 

Asbtract ( )   PDF (471KB) ( )  

Related Articles | Metrics

Certificateless public key cryptography was introduced to overcome the key escrow limitation of the identity-based cryptography. Combining the advantages of the identity-based cryptography and authenticated key agreement protocol， a new ID-based authenticated certificateless key agreement protocol that made use of bilinear pairings was proposed. The analysis shows that the protocol not only possesses the security properties that common key agreement protocols have, but also needs less pairing operation compared to the existing key agreement protocols.

P2P information flow model based on trust and security grade

2008, 28(12):  3168-3170. 

Asbtract ( )   PDF (412KB) ( )  

Related Articles | Metrics

Introducing the reputation grade, classifications and access control grade, a new information flow model on P2P based on trust and security grade was described, with the security classification achieved by access control grade, and with the information flow role described by access control grade of two objects. This information flow model satisfies the characteristics of finite lattice and least upper bound operator in existing literature. It is reasonable and safe, and it is an expansion of information flow model based on BLP model.

Bisynchronous approach in audio watermarking based on quantization discrete wavelet transform

2008, 28(12):  3171-3174. 

Asbtract ( )   PDF (573KB) ( )  

Related Articles | Metrics

A bisynchronous approach was proposed for audio watermarking. The bisynchronous process consisted of self-synchronization and additive synchronization. A kind of synchronous valley was created for watermark location through five features drawn from audio carrier. Following the synchronous valleys, the additive synchronous approach was adopted to locate the usable watermarks. Meanwhile, an adaptive matching approach was stated to obtain the final watermark from several candidates. The bisynchronous algorithm was robust against most common signal processing and attacks, such as re-sampling, re-quantization, MP3 compression, echo delay, Gaussian noise corruption and cropping. It also can be against some of low pass filtering attacks.

Watermarking of text images using character step edge adjustment

2008, 28(12):  3175-3178. 

Asbtract ( )   PDF (749KB) ( )  

Related Articles | Metrics

A novel feature calibration watermarking for binary text document images was proposed. Good imperceptibility could be achieved by adjusting the character step edge stroke instead of horizontal and vertical stroke. With this principle, the adjustment method could be applied to change the summation ratio of black pixels between the upper half part and the lower half part of each line text image. Higher and lower ratio express watermark bit 0 and bit 1 separately. Extracting watermark from the watermarked text images just depended on the result of the detected ratio compared to the given thresholds. The experiments were performed with Chinese and English binary text document images. It reveals that this text watermarking has good imperceptibility and robustness against various operations and attacks, such as scaling, nosing, cropping, multi-times printing and scanning.

New method for secure steganography in color images

Du Chang He

2008, 28(12):  3179-3182. 

Asbtract ( )   PDF (685KB) ( )  

Related Articles | Metrics

A new method for hiding secret information in color images was proposed, in which bit planes were treated as binary images. A set of rules was used to check boundary pixels in the bit planes for data embedding eligibility. These rules can ensure correct extraction of the secret data from the stego-image without any other additional information. A key was introduced in identifying the eligible embedding positions to enhance security. Experiments show that, at an embedding rate of 1.5 bits per color pixel, the stego-images have no perceptual and histogram abnormality with PSNR values greater than 40 dB, and can resist several effective methods for steganalytical detection, achieving a good trade-off between security and embedding capacity. It also can solve the difficult problem that format change, data embedding, information extraction of the image containing secret may happen when being processed or compressed, and can resist several effective methods for steganalytical detection.

Vulnerabilities analysis of RTS/CTS mechanism in 802.11 protocols

CHEN Wei Lei YU Ying-Zhou ZHANG

2008, 28(12):  3183-3186. 

Asbtract ( )   PDF (653KB) ( )  

Related Articles | Metrics

RTS/CTS mechanism in 802.11 protocol can solve the hidden nodes problem in wireless networks. The vulnerabilities in RTS/CTS mechanism were analyzed. Due to the lack of authentication in RTS/CTS handshakes, attackers can launch denial of service attacks by continuously sending spurious RTS/CTS frames with large enough NAV values. Based on theoretical analysis, experiment was implemented in practical wireless networks using aircrack-ng developing toolkit. The experimental results show that it is feasible to launch denial of service attacks against RTS/CTS mechanism. This vulnerability can be utilized by attacker at any time and should be paid more attention.

New chaotic pseudo-random sequence and its performance analysis

罗松江 LUO Song-Jiang

2008, 28(12):  3187-3189. 

Asbtract ( )   PDF (486KB) ( )  

Related Articles | Metrics

A new pseudo-random sequence based on chaotic map was proposed, which can avoid the accumulated effect of round-off errors caused by iterating the map. With the difference of step size in simulation (time interval) or slightly variation of the parameter value, the sequence is very different. The analysis shows that the sequence possesses very good cryptographic properties, such as the ratio of 0-1 is close to 1, large linear complexity, δ-like auto-correlation and close-to-zero cross-correlation. Applying the new sequence in image encryption algorithm, the simulation results show that it is a class of effective pseudo-random in practical applications.

Measuring anonymity in P2P anonymous communication system

Kun Xie Deng Lin Renfa Li Jigang Wen

2008, 28(12):  3190-3193. 

Asbtract ( )   PDF (616KB) ( )  

Related Articles | Metrics

The model of P2P anonymous system and attack model were analyzed. And then based on information entropy and aiming at collusion attack, receiver anonymity of several kinds of typical systems were measured. Finally, mathematic analysis was provided for the relationship among anonymity, the size of system, the proportion of malicious node, the length of rerouting path and forwarding probability. Calculations show that nested encryption causes the system to obtain strong anonymity, and the degree of receiver anonymity increases while the system scale increases and decreases while the proportion of malicious node increases. The degree of receiver anonymity is affected by the proportion of malicious node and the system scale obviously, and is affected by the length of path slightly.

A credible access control model in P2P networks

YAN Ying 晏樱

2008, 28(12):  3194-3196. 

Asbtract ( )   PDF (450KB) ( )  

Related Articles | Metrics

Trust model emphasizes credibility of member and data. By proclaiming and restricting the misconduct of networks, it can provide guarantee for users to use the Internet more reasonably. A global trust model (GSTrust) was proposed based on similarity weighting recommendation. In this model, the trust value's requester weighted recommendation by using similarity behavior of the presenter and himself, and calculated the global trust value by using the similarity score to weight its recommendation. An incentive mechanism also was proposed based on group as the effective complement for trust model. Simulation experiment shows the good performance of GSTrust model.

Designated verifier signature scheme based on braid group

Shi-min WEI

2008, 28(12):  3197-3198. 

Asbtract ( )   PDF (446KB) ( )  

Related Articles | Metrics

The braid group is infinite non-commutative group，and it has many hard problems that can be utilized to design cryptographic primitives, such as the word problem, conjugacy problem and root problem. The designated verifier signature scheme was proposed using the root problem and conjugacy search problem in the braid group. Analysis shows that it is a simple, fast and efficient scheme with security features.

New authentication encryption scheme based on AES and Three-Prime RPrime RSA

Chen Zuo-xin 陈作新

2008, 28(12):  3199-3201. 

Asbtract ( )   PDF (423KB) ( )  

Related Articles | Metrics

RPrime RSA private key operations was speeded up based on Chinese Remainder Theorem, and a bran-new authentication encryption scheme was proposed based on three-prime RPrime RSA and AES algorithm. Due to its high-efficiency and security, it is very suitable for the identification and exchange of information between smart cards, and between smart card and terminal.

Routing policy management method for multi-ISP collaboration

Jing-hu Xu Ning Hu Pei-dong Zhu

2008, 28(12):  3202-3204. 

Asbtract ( )   PDF (615KB) ( )  

Related Articles | Metrics

Inter-domain routing system consists of several Autonomous Systems (AS), and they are connected to each other and configure their own routing policy. Currently, due to the privacy of policy of Internet Service Providers (ISP) and flaws of design and realization of Boarder Gateway Protocol (BGP), there are a lot of flaws in collaborative configuration and security, along with apparent deficiency to deal with the problems just like conflict in routing policy and routing cheating. To handle the problems mentioned above, a distributed system for collaborative configuration and policy check between multi ISPs was put forward, in which privacy protection technology was applied in the information sharing process, so that multi ISPs could work collaboratively to check policy consistence violation faults that could not be found out by themselves alone.

Improvement of authentication test based on strand spaces model

2008, 28(12):  3205-3207. 

Asbtract ( )   PDF (550KB) ( )  

Related Articles | Metrics

Authentication test is a formal method of verifying the security protocols based on strand space model. However, it hardly analyzes some complex security protocols on account of its poor cryptographic primitives. Theory of strand spaces model and corresponding authentication test were extended by extending the message term, the in-term relation and penetrator's model. SSL3.0 handshaking protocols were analyzed with the proposed approach, and the properties of authentication were verified.

Improvement of ID-based proxy signature scheme without trusted PKG

2008, 28(12):  3208-3210. 

Asbtract ( )   PDF (445KB) ( )  

Related Articles | Metrics

A security defect was detected in ZUO Wei-ping's ID-based designated verifier proxy signature scheme without trusted PKG. The proxy signer can compute the original signer's private key after receiving his authorization. An improved scheme was presented to overcome the above defect. Analysis indicates that it is secure against the proxy signer's forgery attack, and even against the malice attack of the ally of the proxy signer and the PKG.

Research of tri-unit-equivalence phenomenon and improved scheme on XTR

Yong LI

2008, 28(12):  3211-3213. 

Asbtract ( )   PDF (575KB) ( )  

Related Articles | Metrics

Tri-unit-equivalence phenomenon was discussed and proved by the property of cyclic group and transposition. The effect of the phenomenon on XTR security was analyzed. A new improved scheme was proposed, and its security, computational complexity and communications cost were analyzed. The improved scheme is more effective than the others to improve the scale of XTR security.

G-R_TRBAC access control model in grid environment

2008, 28(12):  3214-3216. 

Asbtract ( )   PDF (629KB) ( )  

Related Articles | Metrics

Aiming at the complex demand of grid access control, the current task-role -based access control model for grid was improved and a new model based on role-task & role-based access control (G-R_TRBAC) was built. In G-R_TRBAC model, Role-Based Access Control (RBAC) combined with certification management system was applied in the virtual organizational domains of the grid environment. The virtual organizational domain of the grid environment was an improved model from the task-role-based access control model, which could meet the requirements of multi-domain and dynamic characteristics in the grid access control.

Building a hybrid trust model for P2P systems

2008, 28(12):  3217-3219. 

Asbtract ( )   PDF (594KB) ( )  

Related Articles | Metrics

In order to resolve the problems of P2P network, such as security, bad management and complex computation of trust worthiness in current trust model, a hybrid trust model in P2P system was proposed. This model adopted the hybrid P2P network structure, and time section mechanism for computation trust level, which could efficiently prevent malicious actions amongst peers, such as "exaggeration" and "slander", etc. In addition, the building method and the way of evaluation feedback of the model were proposed. The simulation proves that this model has little computation workload, and can isolate and identify the malicious peers efficiently, with high performance of security.

Blood examination-based network traffic analysis framework

2008, 28(12):  3220-3223. 

Asbtract ( )   PDF (677KB) ( )  

Related Articles | Metrics

Network information stream, similar to the blood in human being, can function as the indicator of security and health status. Fluctuations of the ingredients probably implicate the changes or potential threats to the security and stability of the whole system. The mechanism of blood-examination used in medical diagnosis was employed to help analyze the security status of network. A blood-examination-based network traffic analysis framework (BETA) was presented. Firstly, the target system for traffic analysis was set up based on Hurst exponent and typical traffic packets. Secondly, the design of the knowledge base for BETA was given, and the knowledge representation was described. After that, the implementation of traffic analysis engine was expounded, and the steps of Prerequisite-Generation Algorithm (PGA) and Diagnosis Algorithm (DA) were given out in detail to realize the diagnosis of network security. At the end, the architecture of BETA and some implementation details were described.

Database Technology

Incremental updating algorithm for association rule based on sliding-window

LIU Wan-Rong 刘婉蓉

2008, 28(12):  3224-3226. 

Asbtract ( )   PDF (485KB) ( )  

Related Articles | Metrics

Most of the present association rule algorithms are devoted to the problem of incremental updating, and need to scan the database several times. It is difficult to deal with the large data effectively. The incremental updating algorithm for association rule based on sliding-window (SWIUA) was proposed. This algorithm updates the data by sliding-window, deals with the large new data effectively, and gets the interested and new association rules. It scans the original database and updates data only once, reduces the time of I/O and improves the mining performance of association rules.

Text classifier based on fuzzy support vector machine and decision tree

ZHANG Qiu-yu Jie Yang

2008, 28(12):  3227-3230. 

Asbtract ( )   PDF (630KB) ( )  

Related Articles | Metrics

For determining the membership function in text classification with fuzzy support vector machine, a construction approach of text classifier based on fuzzy support vector machine and decision tree was proposed. The relationship between the sample and its cluster center was considered and the tangent sphere was constructed by the hyperplane that contained the support vectors and paralleled the classification hyperplane in traditional support vector machine, so to further determine the relation of all samples in the class. The membership of one sample to a class could be computed by the location of the sample in the sphere, so the efficient samples, noises and outliers could be distinguished rationally. Integrating the decision tree method, the classification of multi-classes was realized. The experimental results demonstrate the method has preferable classification effect.

Multi-query join algorithm based on sharing for XML publish/subscribe data stream systems

2008, 28(12):  3231-3234. 

Asbtract ( )   PDF (611KB) ( )  

Related Articles | Metrics

In XML publish/subscribe system, multi-query join involves the processing of subscriptions of several XML documents, including XPath evaluation, comparison computation and time management. XML join algorithm based on sharing observes that much join computation can be shared by several subscriptions to save the computation time of join. Experimental results demonstrate that the algorithm is efficient and suitable for the system of millions of subscriptions.

Process mining algorithm based on synchronized-manager

Hong-Mei Huang Yun ZHANG

2008, 28(12):  3235-3239. 

Asbtract ( )   PDF (748KB) ( )  

Related Articles | Metrics

Strong-loop, weak-loop, jump and invisible tasks are ubiquitous between tasks in the business process, and mining them from the event logs is a problem to be solved. The features of strong-loop, weak-loop, jump and invisible tasks were analyzed, and the determinant theorems were offered, on the basis of which the γ+ algorithm was proposed with synchronized-manager models. The γ+algorithm overcomes the limitation of the converntional mining algorithms, executes the mining of management actions along with the mining of process structure，and manages to solve problems such as strong-loop, weak-loop, jump and invisible tasks. Experimental results indicate the effectiveness and applicability.

New clustering algorithm based on watershed transform

Ru-Zhen Bai Qing Tian Hai-Jiang Xu

2008, 28(12):  3240-3243. 

Asbtract ( )   PDF (666KB) ( )  

Related Articles | Metrics

Based on watershed transform, a new clustering analysis algorithm was proposed. In this algorithm, the 2-dimension data set was converted to digital grey image according to its density at first. And watershed transform was performed on the grey image, and then the clustering results were got. The result indicates that the accuracy is slightly worse than that of K-means algorithm, but it has the capability of recognizing the number of clusters automatically.

Modified K-means algorithm based on new cluster validity index

2008, 28(12):  3244-3247. 

Asbtract ( )   PDF (630KB) ( )  

Related Articles | Metrics

The class number k is one of the key factors to influence cluster quality in K-means algorithm. Several cluster validity measures have been proposed for confirming the optimal k value. However, the existing methods may not work well for the following two kinds of data sets: the data set containing cluster groups with different densities and the data set in which the cluster groups are extremely close to each other. Therefore, a new cluster validity index was proposed. The index was defined as the ratio value between the squared total length of the data eigen-axes and the between-cluster separation (the data set containing merged cluster group). If the value reaches the minimum, the clustering number is the optimal one. At the same time, in order to reduce the sensitivity of K-means algorithm to isolation point and noise, a K-wmeans clustering algorithm based on weights was put forward to calculate clustering centers. Experimental results show that the proposed algorithm gives more accurate results than the other algorithm. A modified K-means algorithm based on a new cluster validity index not only reduces the impact of isolation point and noise but also effectively deals with the two kinds of data sets mentioned above, improving the quality of data clustering.

E-mail classification based on concept vector space model

Jun-zhong GU

2008, 28(12):  3248-3250. 

Asbtract ( )   PDF (480KB) ( )  

Related Articles | Metrics

A new approach of e-mail classification based on the concept vector space model was proposed. In this approach, the eigenvector of the e-mail was extracted during training process by replacing terms with synonymy sets in WordNet and considering hypernymy-hyponymy relation between synonymy sets. Then, TF * IWF * IWF method was used to revise the weight of the concept vector. In the end, the type of e-mail was determined using the simple vector classification method. Compared with the term-based VSM approach, the results show that this approach can improve the accuracy of e-mail classification especially when the size of training set is small.

Dynamic compound indexing method for moving objects based on road distribution

Qian ZENG Ming Jin

2008, 28(12):  3251-3253. 

Asbtract ( )   PDF (534KB) ( )  

Related Articles | Metrics

Traffic management information service requires an efficient indexing method to manage moving objects. Aiming at such requirement，a dynamic compound indexing structure for moving objects based on road distribution was proposed. It adopted bottom-up updating algorithm and road segments connecting method to improve updating and accessing efficiency. Experimental results prove that such compound index has better performance in updating and inquiring．

Typical applications

Application of sentence similarity measurement in automated assessment of subjective tests

2008, 28(12):  3254-3256. 

Asbtract ( )   PDF (635KB) ( )  

Related Articles | Metrics

Trying to use the natural language in the automated assessment of network examination system has become a research hotpot in computer area. Referring to Chinese word segmentation, the sentence similarity calculation model was established by using the model of words semantic similarity based on HowNet and sentence semantic similarity model based on Hungary algorithm. In accordance with the sentence similarity, the correct value was evaluation scores for automated assessment.

Research and realization of RIA WebGIS based on Flex

2008, 28(12):  3257-3260. 

Asbtract ( )   PDF (673KB) ( )  

Related Articles | Metrics

According to the characteristics of Flex and RIA, the architecture of RIA WebGIS based on Flex was analyzed. In order to improve the efficiency of the system, the tile and double cache technology was introduced with vector and raster integrated map service. At last, a solution was given and a certain company WebGIS system was developed. The results demonstrate that developing WebGIS by using Flex technology is an ideal method.

Multi-protocols instant messaging system based on SOA

LIN Hao-Ran Yao-Wen YAO

2008, 28(12):  3261-3263. 

Asbtract ( )   PDF (627KB) ( )  

Related Articles | Metrics

Gateway strategy and multi-protocols client strategy are the two main solutions to implement the interconnection among IM systems at present. The multi-protocols-based Pidgin realizes IM interconnection to some extent. But Pidgin's practical functions are limited by its disadvantages that lie in weak modifiability, poor scalability and inconvenient deployment. Based on SOA, an open-source multi-protocols IM system was established via reconstructing and reusing the Pidgin. This IM system is easy to modify, extend and deploy.

Performance evaluation of air traffic control system based on analytic hierarchy process

Zheng-Hong XIA Yu-Nong HU Song-Hao BAI Jun-Feng WANG

2008, 28(12):  3264-3267. 

Asbtract ( )   PDF (659KB) ( )  

Related Articles | Metrics

The performance of air traffic control system was evaluated by using Analytic Hierarchy Process (AHP). Firstly, the factors that can affect the performance of air traffic control system were analyzed and air traffic control system's performance guidelines and metrics suitable for the characteristics of China's military and civil aviation were established. Then the relative weight of these guidelines could be obtained by computing the judgment matrix that was constructed by experts. At last, the relative weight to the system performance could be got by recursively using probability multiplication methods. Finally the value of air traffic control system's performance equaled the liner weighted value of product between weights and their corresponding indicators of membership. According to the statistics conducted by the simulation, it is basically the same as the conclusions of experts, which shows it is reasonable to use AHP in the performance evaluation of air traffic control system.

Application of improved Q learning algorithm to job shop problem

2008, 28(12):  3268-3270. 

Asbtract ( )   PDF (417KB) ( )  

Related Articles | Metrics

The Job Shop Problem (JSP) is a key technology in manufacturing system, and the Q learning was used to realize it. The improved Q learning algorithm was suggested because of the traditional algorithm has limitations of slow and partial constringency. In this algorithm, a complex action group was suggested. And uniformity degrees of action choices were weighed by cohesion, and then the two limitations could be overcome effectively. It could be adapted to the complicated manufacturing environment. Experimental results show its good effect in the JSP.

Research and improvement of EPC Gen2 anti-collision protocol

Yuan-Yuan Xu Jun-Fang Zeng Chen Lin Yu Liu

2008, 28(12):  3271-3273. 

Asbtract ( )   PDF (493KB) ( )  

Related Articles | Metrics

Anti-collision protocol in EPC Gen2 protocol is flexible, so reasonable algorithm can evidently improve the system performance. Based on the research of its Q value adjusting method and the process of this important protocol, a new Q value adjusting method and an improved slotted random Aloha method were proposed. The simulation results show that the improved algorithms can increase the system throughput and lower the delay of tag identification, showing a good performance.

Subject-related information collection method based on domain Ontology

Guo-Liang ZHENG Fei-yue Ye Guo-Jun LIN Dong Geng

2008, 28(12):  3274-3277. 

Asbtract ( )   PDF (586KB) ( )  

Related Articles | Metrics

Vector Space Model (VSM) based on the keywords is a traditional related information collection method, which is commonly used in the professional search engine. It takes account of the weight of keywords and keywords' frequency in the web page to collect the subject-related pages. The method of ontology-based information collection no longer reflects the frequency of the term in a simple way, and it strengthens the page of the semantic relationships between terms, thereby it overcomes polysemy, synonyms and dependence on the word existing in the traditional vector space model. The result of the experiment, compared with the method based on keyword, further demonstrates the feasibility of the method based on Ontology.