Table of Content

01 March 2008, Volume 28 Issue 3

Previous Issue    Next Issue

Network and communications

Divisional searching strategy based on degree in unstructured P2P networks

Xi－Guang Dong

2008, 28(3):  549-552. 

Asbtract ( )   PDF (1047KB) ( )  

Related Articles | Metrics

Flooding is widely used in current unstructured P2P systems because of its simplicity. Although it is effective in content search, flooding is very inefficient because it results in a great number of redundant messages. This greatly restricts the scalability of the networks. The existing improved search mechanism can reduce the redundant messages but also usually significantly shrink the query coverage range. DSearch, a divisional search strategy based on degree was proposed, with the objective of minimizing the number of redundant messages and retaining the same message propagating scope as that of standard flooding. DSearch divided the searching into two stages. At each stage DSearch controlled the number of messages to forward by a function, and then it chose objects to send according to its neighbors’degree. Analysis and simulation results show that the DSearch provides a low overhead broadcasting facility that can be effectively used in P2P searching.

Adaptive Web prediction model based on popularity

2008, 28(3):  553-557. 

Asbtract ( )   PDF (921KB) ( )  

Related Articles | Metrics

The current research of Prediction by Partial Match （PPM） model generally focuses on the reduction of space complexity of the model under the condition of guaranteeing the prediction accuracy. But most of the studies lack the adaptive mechanism, which is requisite in online systems. In terms of Web access characteristics, popularity based adaptive PPM prediction model (PA PPM) was proposed, whose core was prefetching algorithm based on Web objects’popularity. PA PPM actualized dynamic adaptive Web prefetching by three parts: model construction, model prediction and model update. The mechanisms of deterministic context prediction, optimal order estimation and LRU based discarding policy to support adaptation were discussed and realized. Under the condition of integrated Web caching and prefetching, experimental results have shown that PA PPM model can achieve a good performance and can be used to realize on-line Web prefetching.

Adaptive data scheduling algorithm for P2P media streaming

Ming-song Sun Hong-Min Zhou Liang Tang

2008, 28(3):  558-559. 

Asbtract ( )   PDF (598KB) ( )  

Related Articles | Metrics

In order to solve the problem of losing data block under the limited bandwidth in existed algorithms, a novel scheduling algorithm was proposed for P2P network, named Least-First Scheduling Algorithm (LFSA), which was simple to implement. Furthermore, it can adjust itself automatically to adapt to network heterogeneity, bandwidth fluctuation, and overlay dynamics. Experimental results show that LFSA can shorten the start delay time and achieve better performance than conventional strategies without any knowledge of the bandwidth of its partners or any special mechanism for the load balance.

Topology discovery for IPv6 networks based on traceroute6

Yuan-Chen LI Wei-Qun LIU Guo-Fang KUANG Lei XUE

2008, 28(3):  560-563. 

Asbtract ( )   PDF (854KB) ( )  

Related Articles | Metrics

With the development of IPv6 networks， it is challenging to measure its topology for network management. By analyzing the difference between IPv6 and IPv4 protocols and researching the concepts of IPv6, the key problems that must be resolved were presented. Based on the above mentioned analysis， a topology discovery method for IPv6 network was proposed， the test experiment circumstance and result were given and a network topology automatic discovery system for IPv6 based on traceroute6 was accomplished too. Simulation results show that the system is correct and has better performance.

Extension to DCF for wireless local area networks — ExDCF

2008, 28(3):  564-567. 

Asbtract ( )   PDF (783KB) ( )  

Related Articles | Metrics

In typical installation of an 802.11 based Wireless Local Area Network (WLAN), mobile hosts would access the network through Access Points （AP）. Since the communication link between two mobile stations in the same WLAN effectively becomes a two-hop path, even if they can hear each other, the throughput degrades significantly. In this paper, ExDCF protocol as an extension to standard Distributed Coordination Function （DCF） protocol in WLAN was proposed, which could improve the throughput between two mobile stations more than twice. In ExDCF, when two mobile nodes are in the same transmission range, the data packets will be sent directly by the source to the destination without AP. Reversely, the data packets need forwarding by AP. However, AP can relay them without contention of the channel. Theoretical analysis and simulation results show that our ExDCF works better in WLAN than the standard DCF while remaining compatible to the standard DCF.

Multiple ant colony algorithm load balancing for network sessions

Jun LU

2008, 28(3):  572-574. 

Asbtract ( )   PDF (585KB) ( )  

Related Articles | Metrics

A multiple Ant Colony Algorithm （ACA） path load balancing optimization algorithm for the resources allocation within network sessions was proposed. Combining bio-inspired ant colony algorithm with dynamic load balancing in the network traffic engineering, the algorithm further extended the basic ant colony to multiple ones with dynamic pheromone release design. By fully considering ACA's parallel-computing characteristic, the scheme tried to allocate the traffic load of network sessions to the different paths equally to avoid traffic congestion. Besides analyzing the effective control of the pheromone, compared with basic ant algorithm, simulation experiments illustrate that the proposed scheme achieves better resources allocation in terms of path bandwidth utilization, session delay and session packet loss.

Using uncertainty DHT to solve non-transitive connectivity problems in overlay network

WANG Xiang-Hui 王向辉 Guo-Yin ZHANG

2008, 28(3):  575-578. 

Asbtract ( )   PDF (768KB) ( )  

Related Articles | Metrics

In order to resolve the widely existing problem of Non-Transitive Connectivity (NTC) in networks, a uncertainty Distributed Hash Tables （DHT） method to resolve the NTC problem in overlay network was proposed. The relationship of bottom node ID and logical space location was lifted to avoid infection of network structure by NTC nodes, and redirection route mechanism was used to implement the message routing of network. Simulation shows that uncertainty DHT could effectively resolve the NTC problem in overlay network.

Ordering-based enhanced sphere decoding algorithm of space-time code

Rong-Bo ZHU

2008, 28(3):  579-581. 

Asbtract ( )   PDF (729KB) ( )  

Related Articles | Metrics

With spatial multiplexing, sphere decoder can markedly improve the spectrum efficiency. However, the existing sphere decoders can only tackle the real constellation and some special complex constellations. In order to process the constellation with any shape, an enhanced sphere detector called Ordered Sphere Decoding （OSD） was proposed. By ordering candidate Channel State Information （CSI） and adding heuristic rules, the proposed algorithm can obtain near Maximum Likelihood (ML) performance. Detailed simulation results show that the proposed algorithm greatly decreases computation complexity and decoding time. Compared with other known methods to solve complex constellation, the proposed algorithm OSD is both faster and more accurate.

Traffic matrix estimation based on generalized linear inversion

Ke ZHANG Jia XIE Guang-min HU Zheng-hong DENG

2008, 28(3):  582-585. 

Asbtract ( )   PDF (768KB) ( )  

Related Articles | Metrics

To reduce the estimation's complexity, an algorithm for traffic matrix estimation based on generalized linear inversion theory was proposed. For the purpose of improving the algorithm stability, a Singular Value Decomposition （SVD） decomposition method was used to find an optimum damping coefficient. Moreover, the historical average and link data were used to get the prior information so that the number of solutions can be reduced. Simulation results using Abilene network's actual data show that the proposed algorithm can guarantee good real-time capability while the computational accuracy can also be improved significantly.

Reconstruction model of different network traffic based on multi-fractal

Jun Hu Xian-hai Tan Yu-qing Hu Xue Yang

2008, 28(3):  586-587. 

Asbtract ( )   PDF (597KB) ( )  

Related Articles | Metrics

Fractal is a ubiquitous property of real-traffic, and the multi-fractal of traffic has great impact on network performances. Therefore, it is important to build the reconstructed model based on multi-fractal for the real network traffic. In this paper, a new reconstruction model based on wavelet transform that could release the correlation of traffic was build in combination with the conclusion that different traffic had different fractal characteristics in the past research, and more accuracy was got. Then, through depicting the new traffic and performance evaluation, the correctness of the new model is certificated.

Research of optimizing frame size and group division in Aloha-based algorithms

Yuan-Yuan XU Jun-Fang Zeng Yu Liu

2008, 28(3):  588-590. 

Asbtract ( )   PDF (596KB) ( )  

Related Articles | Metrics

Comprehensive review of the research of one kind of anti-collision algorithms and analysis of their disadvantages were provided. Based on the analysis of the frame size adjusting method of the most in common use branch dynamic framed slotted Aloha algorithm, this paper brought forward an improved resolution by dynamically adjusting the frame size and group division, which can consumedly enhance the system efficiency and its stability.

Approach for multiple constrained QoS multicast routing based on immune genetic algorithm

Xiu-Ping ZHAO

2008, 28(3):  591-595. 

Asbtract ( )   PDF (910KB) ( )  

Related Articles | Metrics

Based on the Immune Genetic Algorithm with Elitism (IGAE), a new routing selection approach to solve QoS multicast routing problem with minimum cost and constrains of bandwidth, delay and delay jitter was proposed. Firstly, it used the preprocessing mechanism to get rid of the links that did not satisfy bandwidth constraint in network structure. And the k shortest paths' Dijkstra algorithm was utilized to establish the alternative path set of the algorithm coding space. Secondly, it generated the initial population of IGAE, using the tree structure coding based on the path. Thereby, each individual of the population represented a candidate solution to the multicast routing problem. Finally, IGAE algorithm was used to optimize the population. It ultimately obtained the multicast routing meeting QoS requirements. The simulation results show that this proposed algorithm is highly efficient and it can find a multicast tree at the lowest cost and at fast convergence speed.

New active queue management algorithm

Wu-Man LUO

2008, 28(3):  596-598. 

Asbtract ( )   PDF (559KB) ( )  

Related Articles | Metrics

A new Active Queue Management （AQM） algorithm based on the Misra's TCP windows stochastic differential equation was proposed. With the restriction on the bound sizes of TCP windows, the transfer function of the new AQM model was obtained by using local linearization technique, and then this transfer function was taken as the controlled object, the differences between the output of the transfer function and the ideal queue were controlled by a Proportional Integral Differential （PID） controller. The experimental simulation results show that the overall performance of the new algorithm is better than RED and ARED algorithm.

New SIP compression mechanism in IMS

2008, 28(3):  599-600. 

Asbtract ( )   PDF (573KB) ( )  

Related Articles | Metrics

Session Initiation Protocol （SIP） was used in 3G cellular IP Multimedia Subsystems （IMS） to perform multimedia session setup and maintenance. However, it is text-based and has large messages with size frequently exceeding several hundred bytes during the setup session; consequently, it causes more setup session delay. In this paper, a new algorithm combining LZW with HUFFMAN and static dictionary was proposed, which was named as S-LZW-HUFFMAN. Simulation results prove that the new algorithm can effectively reduce the message size and shorten the session setup delay in IMS.

Information security

Robust adaptive information hiding algorithm based on image spatial domain

2008, 28(3):  601-604. 

Asbtract ( )   PDF (926KB) ( )  

Related Articles | Metrics

A robust information hiding algorithm of image spatial domain blind watermarking was presented. Embedding place of every bit of Binary sequences that will be hidden was scrambled randomly to the pixel space of entire image by making use of general Arnold mapping, and then a bit will be embedded a place of the pixel point which has no effect apparently on vision feeling result through applying adaptive policies of combining Logistic chaotic mapping with the position of the highest non-zero bit of a pixel. Withdrawing watermark needs only key and there is huge key space. Error-correcting codes were adopted against noise attacks, and still optimal policies of the minimal pixel change degree were applied to decrease vision feeling changes. Experimental result shows that this algorithm can have large amounts of hidden information, good invisible characters and robustness against attacks, such as cut, and salt and pepper noise.

Digital watermark-based authentication of queries in outsourced database

Qin ZHU

2008, 28(3):  605-608. 

Asbtract ( )   PDF (1038KB) ( )  

Related Articles | Metrics

Query authentication in outsourced database refers to the client users' verifying the authenticity of data resource, correctness of query operation and consistency of query results in outsourced database. In this paper, a query-verifying scheme of outsourced database based on fragile watermark was proposed. In the scheme, the randomized ordered binary pairs, which were generated by chaotic equation, was utilized as the watermark signal and control signal for watermark embedding, the watermark was embedded into numeric data in the database by changing the parity of their low order digits under the control of the secret key, and the query was verified by detecting the watermarks in the query result set. The scheme has little redundant storage size and low flow load of network, and the tamper with the database can be located at fine grain.

Supervisal algorithm design of IDS using support vector regression

Jia-chao ZHANG

2008, 28(3):  609-611. 

Asbtract ( )   PDF (564KB) ( )  

Related Articles | Metrics

To improve classific precision of network intrusion detection model and reduce the number of training data set and learning time, a new supervisal algorithm based on ε Support Vector Regression machines (ε-SVR) machine was proposed. Firstly, normalization was used on training data set, and then a new coefficience of sparse penalty function was adjusted. Finally, the experimental results using KDD CUP 1999 data set show that this approach can detect intrusion behavior, increase its veracity and validity, and reduce its distortion.

Model for access control system based on RBAC and GFAC

2008, 28(3):  612-614. 

Asbtract ( )   PDF (927KB) ( )  

Related Articles | Metrics

On study of Role-Based Access Control （RBAC） model and Generalized Framework for Access Control （GFAC）, the generalized model for access control based on RBAC and GFAC was presented. The characteristics of this model and the control policy were described, in which the group permission, constraint elements and special permission were introduced. Combining techniques of layered authorization, minimizing privileges and role inherited authorization, the RBAC was optimized by enforcing access control on the request. It can figure out the complex access control in the system, and decrease the complexity of the authorization and management of users. The system is configurable and can be maintained easily. Finally, the case of a generalized access control system was given.

Blind watermarking algorithm based on lifting scheme wavelet and encrypted watermark

2008, 28(3):  615-619. 

Asbtract ( )   PDF (1155KB) ( )  

Related Articles | Metrics

The watermark algorithm based on pyramid decomposition of lifting scheme wavelet and a new watermark scrambling encryption methods were proposed. Spread spectrum was conducted first，and then it was embedded into watermark by means of integer modulo. The simulation results show that the algorithm enhances the security of watermark and has very strong robustness and transparency.

Study on the realization of differentiated services in network isolation system

2008, 28(3):  620-622. 

Asbtract ( )   PDF (765KB) ( )  

Related Articles | Metrics

Implementing Differentiated Services (DS) in network isolation system can further improve its QoS. Firstly, application proxy model in network isolation system was researched, and fundamental requirements for the DS implementation were described. Under these requirements, it proposed a feasible architecture for DS realization in inner unit. And then, with the constructed architecture, it described the realization methods of application data classification, data queuing and other related technologies. Finally, it researched the organization of configuration information and the configuring process.

Computation model for trustworthiness in P2P network service environment

Feng-Ming Liu Xingjia Lu Yong-Sheng Ding

2008, 28(3):  623-625. 

Asbtract ( )   PDF (632KB) ( )  

Related Articles | Metrics

An algorithm to compute an initial trust value for the new entities based on its capability was presented, and then the computation algorithms of direct trustworthiness based on the degree of interaction satisfaction were designed. The recommendation trustworthiness based on the recommendation opinions came from trusted entities. Finally, the integrated trustworthiness computation model was given. Based on this model, the trust relationships can be built among entities in P2P network service environment and the decision of trust can be made based on the trustworthiness, and the risk can be reduced and the stability of network can be promoted.

Payload analysis of N-path rerouting-based anonymous communication system

Ting Tao Le-Chang Sun

2008, 28(3):  626-628. 

Asbtract ( )   PDF (587KB) ( )  

Related Articles | Metrics

The theoretical calculation of the participant payload was given, the relationship between the participant payload and the rerouting road's dependency was investigated，and the factors that decided the system payload performance were analyzed. The result shows that the determinants are the mathematical expectations of the road's length and the requested dependency. The system administrator can balance the payload and the dependencies to fit the different usages by configuring these two parameters.

Research of normalization towards instruction substitution metamorphism

2008, 28(3):  629-632. 

Asbtract ( )   PDF (973KB) ( )  

Related Articles | Metrics

A new normalization method towards instruction substitution that was a commonly used metamorphism approach was proposed. The method mainly involved two steps. Firstly, the input code was rewritten with standard instructions. Secondly, the order of standard instructions was adjusted based on the data dependence graph of each basic block. Based on the method, a synthetic normalization scheme was also introduced. The aim of the scheme is to provide an ability of effective normalizing metamorphic malware in true-life, which uses more than one common metamorphic technique. A case study of normalizing Win32.Evol, Win32.Zperm and Win32.Bistro was carried out. The results demonstrate the feasibility of the scheme.

Research of access control model in multi-domain

2008, 28(3):  633-636. 

Asbtract ( )   PDF (854KB) ( )  

Related Articles | Metrics

Mutil Domain-Role Based Access Control （MD-RBAC） model was proposed. MD-RBAC was based on Role-Based Access Control （RBAC） model, building relations between access control elements of different domains. Besides, the model introduced validation constrains and border policy, which was based on validation constrains, in order to identify and defense the risks that were brought in by inter-domain access. Finally, we briefly compared MD-RBAC model to another access control model I-RBAC 2000 which also aimed to solve access control problem in multi-domain environment.

Dynamic authentication scheme using smart card

2008, 28(3):  637-639. 

Asbtract ( )   PDF (551KB) ( )  

Related Articles | Metrics

This article discussed an authentication scheme recently advanced by Yuan Ding et al, and indicated that the scheme was vulnerable to dictionary attack, man-in-the-middle attack and denial-of-service attack to the server. And then a dynamic authentication scheme using smart card was proposed and analyzed. The analysis shows that the proposed new scheme, which provides mutual authentication, has the properties of high security and low computational cost, and that it supplies secure, friendly and convenient password-change phase and the server of the scheme does not need to maintain the verification tables used to help authentication.

Research of automatic worm signature generation based on vulnerability

2008, 28(3):  640-642. 

Asbtract ( )   PDF (609KB) ( )  

Related Articles | Metrics

A new worm signature based on vulnerability was proposed, which was different from traditional methods based on syntactic or semantic. It focused on vulnerability signature that did not change in worm attack. Finally, we applied this method to a detection system and it proved this system can efficiently detect various kinds of worms.

Graphics and image processing

Facial expression recognition based on hybrid features fused by CCA

Jian-ming Zhang Li-Rui YANG Liang-min Wang

2008, 28(3):  643-646. 

Asbtract ( )   PDF (1109KB) ( )  

Related Articles | Metrics

To overcome the disadvantage of traditional facial expression recognition methods that generally use single feature extraction methods, which can not extract effective features currently, a new method based on fused hybrid features and discrete Hidden Markov Model （HMM） for facial expression recognition from image sequences was presented. For the same image sequence, we used Discrete Wavelet Transformation （DWT） and Orthonormal Non-Negative Matrix Factorization （ONMF） to extract texture information toward pure faces and used Active Appearance Model （AAM） to extract geometrical shaped information. In order to reduce the redundancy, Canonical Correlation Analysis （CCA） was used to fuse the two features for observation vectors of discrete HMM. Experiments show that the method can get high recognition rate after fused with fewer feature vectors.

Fabric defect detection method based on texture structure analysis

2008, 28(3):  647-649. 

Asbtract ( )   PDF (748KB) ( )  

Related Articles | Metrics

A new fabric defect segmentation was proposed based on texture structure analysis in this paper. Firstly in accordance with the characteristics of the well-regulated texture, texture primitive template was calculated using auto-correlation function and defect image was enhanced using difference between each texture primitive and primitive template. Secondly local roughness of texture image was calculated to locate defect, and defect image was segmented using threshold value gained according to Otsu's approach to detect fabric defect. Lastly validity and robustness of this approach is proved by different fabric defect image segmentation in our experiment.

Study on adaptive segmentation of irregular image based on improved PCNN

Deng-Chao Feng Zhao-Xuan Yang Zhe Wang Pereira Jose Miguel

2008, 28(3):  650-652. 

Asbtract ( )   PDF (857KB) ( )  

Related Articles | Metrics

Concerning the characteristics of complex components of irregular images and random alignment of irregular spot without proper fitting mathematics model, an adaptive segmentation algorithm with improved Pulse Coupled Neural Network （PCNN） was proposed in the paper. On the basis of basic PCNN model, the neurons feedback input function and dynamic threshold function were modified and multi-level output model for the neuron output was designed to implement the segmentation process as well. Simulation experiment shows that the improved PCNN has better robustness and can realize the adaptive segmentation of irregular image.

Image retrieval method combining integer and blocks' color distribution

Jun YANG JiCheng WANG Dan-Jun XIN

2008, 28(3):  653-655. 

Asbtract ( )   PDF (830KB) ( )  

Related Articles | Metrics

In order to overcome the defect that the conventional color histogram retrieval method is prone to lose the spatial information of colors, an image retrieval method based on the largest color-connected regions was presented, and its rim roughness to capture the regional traits and reduce the absolute dependence on color. Then the similarity of the images is defined as the combination of the similarity of an integer and the similarity of the blocks to reflect the recognition process by people. The experimental result on real-world image collections indicates that the proposed approach significantly improves image retrieval accuracy.

Ray tracing algorithm based on octree space partition method

2008, 28(3):  656-658. 

Asbtract ( )   PDF (628KB) ( )  

Related Articles | Metrics

Ray tracing algorithm is one of the main algorithms of creating the real graphic. To improve the speed, accelerating algorithm for ray tracing was studied and compared and a ray tracing algorithm based on octree data structure was presented. The intersecting algorithm based on barycentric coordinate can advance the intersection efficiency. Using barycentric coordinate to express triangular parameter surfaces does not need long-term storage as the planar triangle does, and can quickly tell whether the triangular intersects with the light and calculate the intersection. Experiments show that the algorithm can guarantee image quality and improving the rendering speed.

Classification and extraction of image affective features

Kun Huang Maosheng Lai

2008, 28(3):  659-661. 

Asbtract ( )   PDF (912KB) ( )  

Related Articles | Metrics

The characteristics of image affective features were analyzed and a method was provided to divide affective features into 3 levels. Typical affective features for colorful natural scenes were chosen and an investigation was carried out to collect users' impressions on images. Then, based on color features and users' evaluations, the mapping between color and subjective impressions was established by multiple linear regressions, which could be used to extract affective features automatically. Finally, the validity of 3 levels was verified. Besides, the mapping is also testified effective to forecast and index the affective features correctly.

Contrast enhancement algorithm for fog-degraded image based on fuzzy logic

2008, 28(3):  662-664. 

Asbtract ( )   PDF (713KB) ( )  

Related Articles | Metrics

Based on the analysis for the fuzzy nature of fog-degraded images, a novel contrast enhancement algorithm based on fuzzy logic was presented. By normalizing the degraded image, the algorithm allayed the impact of different fog conditions on gray levels distribution range. According to the attenuation law of atmospheric contrast in fog weather, the algorithm enhanced the contrast of normalized image in fuzzy region. Experimental results demonstrate that the proposed algorithm can more flexibly and effectively improve the contrast of fog-degraded images.

Morphological color image filter based on fuzzy combination and soft-multi-structural elements

Shi-Tong WANG

2008, 28(3):  665-668. 

Asbtract ( )  

Related Articles | Metrics

A new filter on color morphology based on fuzzy combination and soft-multi-structural elements was presented. Color image pixels were sorted by the value of fuzzy combination. Morphological filter based on the ranking of fuzzy combination can get better results than based on the ranking of HSV. Experimental results demonstrate that the ability of color processing based on the new morphology is superior to the classical one, and that the algorithm possesses excellent performance on the noise restrained.

Curve detection and its application in mainstream line of Yellow River

Zhi-Yin WANG Yan-Ning ZHANG Hui-Min CAI Feng DUAN

2008, 28(3):  669-670. 

Asbtract ( )   PDF (766KB) ( )  

Related Articles | Metrics

An approach to detecting continuous curves from uniformly distributed random background was presented. A dynamic programming algorithm was employed to detect the most notable curve from the points according to curve continuity. And an application to detect the Yellow River's mainstream line was demonstrated with multispectral image. The mainstream points extracted by feature extraction methods were scattered on the river because of the spectral similarity of mainstream and non-mainstream. The spatial continuity between mainstream points makes this approach feasible. And experimental results indicate that this approach is valid and superior to curve fitting.

Effective implementation of image region segmentation based on Gomory-Hu algorithm

Qiang-Feng ZHOU Zheng Tian Xiao-bin LI Bing-Tao LIU

2008, 28(3):  671-673. 

Asbtract ( )   PDF (733KB) ( )  

Related Articles | Metrics

A graph-based image segmentation method was presented. Firstly, use region growing technique to find initial over-segmentation. Secondly, use these regions as nodes to create the graph. Finally, use minimum cut method to merge these regions. The proposed method has two advantages: one is using minimum cut criterion to merge regions, which can contain global information; the other is using regions as nodes to create the graph, which can greatly reduce nodes of the graph. The experimental results show the effectiveness of the approach.

Improved fast iris localization algorithm

2008, 28(3):  674-676. 

Asbtract ( )   PDF (723KB) ( )  

Related Articles | Metrics

For the purpose of detecting iris precisely and quickly, an ellipse pupil based detection algorithm was proposed based on some prevailing localization algorithms. After determining the threshold by OTSU algorithm, the longest-chord based method detected the boundary of pupil more effectively than the prevailing algorithms based on circular template. The outer boundary of iris based on circular template was searched in less range as the pupil and iris were approximately concentric. Compared with the usual algorithms based on circular template, this algorithm detects pupil as ellipse, reduces the blindness of the search process, and improves the speed and accuracy.

Novel approach for generating binary chaotic sequences and its application to image encryption based on 4-D chaotic system

Chen Dong-Sheng YE Rui-Song

2008, 28(3):  677-679. 

Asbtract ( )   PDF (983KB) ( )  

Related Articles | Metrics

A novel approach for generating binary chaotic sequences based on 4-D chaotic systems was proposed, and the performances of these binary sequences were analyzed. The proposed algorithm was compared with others as well. The results show that the generating binary sequences have good pseudo-randomness and correlation. The binary sequences were also applied to image encryption and good results were achieved.

Estimating mutual information of image by fast Gaussian transform

2008, 28(3):  680-682. 

Asbtract ( )   PDF (590KB) ( )  

Related Articles | Metrics

A new fast algorithm was presented to accelerate the computation of mutual information of images based on kernel density estimate. This algorithm adopted gauss function as kernel function, and then used fast Gaussian transform to reduce time complexity and improved the fast Gaussian transform by k-center clustering. The new algorithm can evaluate the mutual information in linear time complexity and experiments show it is very efficient.

Research of collision detection in skinned mesh

2008, 28(3):  683-687. 

Asbtract ( )   PDF (632KB) ( )  

Related Articles | Metrics

A collision detection using the trait of skinned mesh was proposed, which was based on the hierarchical bounding volume and ameliorated the building and refitting of OBB tree. The experiment demonstrates that the algorithm enhances the efficiency and could fit the demand for the collision detection of complex 3D characters.

Image segmentation algorithm based on grey model MRF

Jie Liu

2008, 28(3):  686-687. 

Asbtract ( )   PDF (676KB) ( )  

Related Articles | Metrics

The traditional Markov Random Field （MRF） used in image segmentation have several disadvantages, such as too much time and no convergence. Aiming at this disadvantage, a developed algorithm was presented. Firstly, establish the label field update model according to the image grey distribution, then update the label field so that the convergence speed has been accelerated. It is shown that satisfactory segmentation is achieved.

Artificial intelligence

Genetic/Tabu hybrid optimization algorithm for location-routing problems

Hai-Jun Yang

2008, 28(3):  688-691. 

Asbtract ( )   PDF (881KB) ( )  

Related Articles | Metrics

A Genetic/Tabu hybrid optimization algorithm for Location-Routing Problems （LRP） with the soft time windows was researched, which can tackle both location-allocation problem and vehicle-routing problem. Hybrid strategy for Genetic Algorithm （GA）and Tabu Search algorithm （TS）, genetic coding and corresponding genetic operations were used in this proposed algorithm, so that the quality of the solution and the efficiency of the algorithm have been improved at the same time. And the results show the proposed algorithm is feasible and efficient.

Mamdani fuzzy system structure identification based on LSSVR

QianFeng Cai

2008, 28(3):  692-694. 

Asbtract ( )   PDF (466KB) ( )  

Related Articles | Metrics

To design a Mamdani fuzzy system with good generalization ability in high dimensional feature space, a novel learning algorithm based on Least Squares Support Vector Regression (LSSVR) was presented in this paper. The structural risk was considered in the goal function to avoid overfitting in traditional algorithms and then the parameter estimation of a Mamdani fuzzy system was converted to a quadratic optimization problem. In the proposed algorithm, the fuzzy kernel generated by premise membership functions is proved to be a mercer kernel. Numerical experiments show that the presented algorithm improves the approximation ability and the generalization ability of Mamdani fuzzy systems.

CPU time slice allocation algorithm considering Agent deadline

Ai-zhen LIU

2008, 28(3):  695-698. 

Asbtract ( )   PDF (729KB) ( )  

Related Articles | Metrics

A chaos-based genetic algorithm was proposed to solve CPU time slice combinational auction problem in which both agent time slice demand and execution deadline demand were considered. First, the problem model was defined. Then the pre-selecting method was designed to decrease computing complexity of genetic algorithm; and variable chromosome coding, two kinds of chaos-optimal-technology-based crossover operator （one for the same parent chromosome and one for the different parent chromosome）, chaos-optimal-technology-based adjusting bid order operator and replacing bid operator were designed to solve it in genetic algorithm. Finally, the experimental results show this algorithm can obtain good optimal solution.

Application of genetic algorithm combined with fuzzy clustering in information filtering system

Hong-Ju LU Pei-Yu LIU Jia CUI

2008, 28(3):  703-705. 

Asbtract ( )   PDF (928KB) ( )  

Related Articles | Metrics

The Fuzzy Clustering （FC） theory into information filtering system based on Genetic Algorithm （GA） was introduced, to cluster the training texts by using the fuzzy similar matrix depending on each individual of GA's species, and the species according to the results of clustering with the proposed fitness function was evaluated. Doing GA operators using this evaluation method iteratively, we got a template which expressed user's interest better, to improve the precision of information filtering. Then, we did experiment to test the efficiency by applying this method to a designed information filtering system.

Application of a hybrid distributed multi-agent task allocation mechanism to soccer robot systems

Xiu-Cai JI Lian-Hu CUI Zhi-Qiang ZHENG

2008, 28(3):  706-709. 

Asbtract ( )   PDF (1014KB) ( )  

Related Articles | Metrics

The advantages and disadvantages of primary multi-agent task allocation mechanisms were analyzed. A hybrid distributed task allocation algorithm for the role allocation of soccer robots was presented, which combined the market-based task allocation mechanism with the regulation-based mechanism. This algorithm can dynamically allocate roles for robots, and at the same time unexpected oscillations of roles were avoided. Simulations and actual matches validate the presented algorithm.

Innovative method for emotion recognition of speech based on pulse coupled neural network

2008, 28(3):  710-713. 

Asbtract ( )   PDF (1143KB) ( )  

Related Articles | Metrics

An innovative method for classifying emotional states of neutral or happy of Chinese phonetics by using Pulse Coupled Neural Network (PCNN) was proposed. The entropy series and neurons firing series of the image obtained by feeding the spectrogram into PCNN were used as the characteristics of emotion speech for emotion recognition. The experimental result show that this method can distinguish speaker's emotions（normal & happy） in speech effectively. The application of PCNN in emotion recognition of speech expands the combination of two important parts of signal processing-speech and image processing and it is significant for theoretical research and application of PCNN.

Spam message self-adaptive filtering system based on Naive Bayes and support vector machine

Jin Zhan Fan Jing Chen Feng Xu congfu

2008, 28(3):  714-718. 

Asbtract ( )   PDF (1129KB) ( )  

Related Articles | Metrics

With the development of the short message services, the characteristics and contents of the spam short Message are also changing constantly, the main problems that exist in the traditional short message filtering systems are that the characteristics and contents fail to be updated in time, which reduced the filter capability. This paper mainly utilized Na ve Bays advantage of rapid statistics classification and Support Vector Machine （SVM） incremental training characteristic in Spam Short Message filtering, and provided feedbacks to the online filtering sub-system in time in order to enhance the system-s self-adaptability. The experimental results show that this new method effectively deals with the above problems in the traditional spam short Message filtering systems．

Application study on a novel differential evolution algorithm

2008, 28(3):  719-722. 

Asbtract ( )   PDF (920KB) ( )  

Related Articles | Metrics

A novel algorithm based on simple diversity rules and Simple Improved Differential Evolution (SIDE) algorithm was proposed in this paper. It is characterized with the following new features: 1) introducing a hybrid self-adaptive crossover-mutation operator, which can enhance the search ability and exploit the optimum offspring; 2) using a new constraint-handling technique to maintain the diversity of the population; 3) simplifying the scaling factor F of the Original Differential Evolution (ODE) algorithm, which can reduce the parameters of the algorithm and make it easy to use for engineers. Our algorithm was tested on 13 benchmark optimization problems with linear or/and nonlinear constraints and compared with other state-of-the-art evolutionary algorithms. The experimental results demonstrate that the performance of SIDE outperforms other evolutionary algorithms in terms of the quality of the final solution and the stability; and its computational cost (measured by the average number of fitness function evaluations) is lower than the cost required by the other techniques compared.

Automated software test data generation based on immune genetic algorithm

2008, 28(3):  723-725. 

Asbtract ( )   PDF (584KB) ( )  

Related Articles | Metrics

A kind of software test data automated generation method based on Immune Genetic Algorithms （IGA） was proposed. Immune operators including vaccine extraction, vaccination and immune selection were introduced into the traditional genetic algorithm. The experimental results show that this algorithm is more effective than the traditional one.

Articles

Sequence concept lattice model with interest measure and its construction

2008, 28(3):  726-728. 

Asbtract ( )   PDF (782KB) ( )  

Related Articles | Metrics

In order to mine efficiently the sequential patterns according to user's requirements, the interest measure for every item was introduced to reveal the different importance in the sequence database. And on the basis of extending the concept lattice model, the sequence concept lattice model with interest measure and its construction algorithm were presented. The instance shows that the algorithm can reduce the redundant sequences and mine the sequential patterns that satisfy user's requirements.

Extracting symbolic rules from support vector machines based on the heuristic information

2008, 28(3):  729-731. 

Asbtract ( )   PDF (577KB) ( )  

Related Articles | Metrics

A new approach for symbolic rules extraction from support vector machines based on heuristic information was proposed, which solved the attribute selection and the division of attribute space. The position and shape characteristics of the classification hypersurface of Support Vector Regression （SVR） were used as heuristic information to direct the attribute selection and the division of attribute space. Then, the algorithm was given. Experiment results show that the proposed approach can improve the validity of the extracted rules remarkably compared to other rule extracting approaches, especially for complicated classification problems.

Grid-entropy-based boundary points detecting algorithm

Bao-Zhi QIU Yang LIU

2008, 28(3):  732-734. 

Asbtract ( )   PDF (671KB) ( )  

Related Articles | Metrics

In order to detect the boundary points of clusters effectively, the concept of grid-entropy and a grid-entropy-based boundary points detecting algorithm Greb were proposed, which detected boundary points by the value of grid-entropy and only needed to scan the datasets twice. As shown in the experimental results, Greb can detect boundary points effectively and efficiently on various datasets.

New frequent pattern tree structure

2008, 28(3):  735-737. 

Asbtract ( )   PDF (488KB) ( )  

Related Articles | Metrics

FP_tree is an efficient algorithm for mining frequent itemsets. Many algorithms proposed recently are based on FP_tree. But the FP_tree construction may cost much time, moreover, it needs to scan database twice. In order to improve the efficiency of constructing the FP_tree, a new fast algorithm called Inprove Hierarchy FP_tree (IHFP_tree) was proposed. The algorithm contained two main parts. The first was to scan the database only once for generating equivalence classes of each item. The second was to delete the non-frequent items and rewrite the equivalence classes of the frequent items, and then construct the IH FP_tree.

Application of data mining in traffic state quantification and recognition

2008, 28(3):  738-741. 

Asbtract ( )   PDF (931KB) ( )  

Related Articles | Metrics

In the Intelligent Transportation System (ITS) environment, the magnanimous flow information of traffic detector was targeted, using data mining technology which included data collection, data preprocessing, data mining, result analysis and appraisal and pattern application to carry on new information extraction. Various stages request as well as the clustering analysis and the pattern recognition algorithm were proposed. Finally the new useful information traffic state was obtained from the magnanimous data. Simultaneously the real-time gathering traffic data was used to distinguish the traffic state, which finally indicated the recognition state could accurately reflect the actual traffic state.

Design of the persistent redundancy storage scheme in P2P environment

2008, 28(3):  742-744. 

Asbtract ( )   PDF (741KB) ( )  

Related Articles | Metrics

The scheme of the P2P persistent redundancy storage is an important issue in current research areas. The paper focused on two main points: the storage organizational structure and data maintenance mechanism. First the paper deeply compared the characteristics of the complete, coded and hybrid data storage modes. Second based on the analysis of the data maintenance mechanism, the paper proposed one kind of data time-delay maintenance strategy with failure confidence. At last the paper discussed the validity and related indicators of the maintenance mechanism in different storage modes through simulation.

Adapted DBSCAN with multi-threshold

2008, 28(3):  745-748. 

Asbtract ( )   PDF (952KB) ( )  

Related Articles | Metrics

After analyzing the features of Density-Based Spatial Clustering of Application with Noise （DBSCAN） and other adapted clustering algorithms, an adapted clustering algorithm based on DBSCAN was presented. Through the construction of grid-density-matrix, a graph of data density distribution was protracted, which helped users to identify density arrangement. Each threshold, ε, was calculated according to equivalent rule of grid and density. By clustering on multi-density-levels, the clustering result was refined. The disadvantage of DBSCAN — parameter-selection and density-disagreement — was solved. This algorithm has significance in application.

Multi-relational spatial data mining method based on S-CART decision tree

Xiang-Qun Zheng Zheng Zhao

2008, 28(3):  749-752. 

Asbtract ( )   PDF (773KB) ( )  

Related Articles | Metrics

Regarding the complicated relationship existing in the spatial data, a kind of improved arithmetic based on the S-CART was presented. In this arithmetic, firstly, the relational atoms propositions from different thematic layers were drawn by the Spatial Jion Index Table （SJIT）. And then, based on the predicates, a multi-relational binary decision tree was established and the spatial association rules were drawn out. The efficiency of this arithmetic is validated based on the soil pollution data of some areas of Daye, Hubei.

Efficient algorithm for XML query based sequence matching — SCALER+

2008, 28(3):  753-756. 

Asbtract ( )   PDF (939KB) ( )  

Related Articles | Metrics

The problems of SequenCe bAsed XML QuEry AlgoRithm （SCALER） were solved. The first was definitely supporting wildcard * and descendant axis //, and the second was supporting queries of pattern trees with out-of-order brother nodes. The extended algorithm was named SCALER+. Experimental results prove that it is efficient as SCALER and stronger for twig query evaluation.

Text clustering method based on genetic algorithm and SOM network

Xiao QIN

2008, 28(3):  757-760. 

Asbtract ( )   PDF (758KB) ( )  

Related Articles | Metrics

As a cluster of high-dimensional visualization and unsupervised learning algorithm, Self-Organizing Map (SOM) provided a favorable means for Chinese Web clustering. However, the SOM algorithm has a natural flaw of being sensitive to the network initial power value so as that the accuracy of the cluster made by the SOM has been influenced. To solve the problem, this paper applied genetic algorithm to optimize SOM. This paper made the following contributions. 1) Propose a text clustering method based on GA-SOM-based Text Clustering Algorithms (GSTCA); 2) Make comparison experiment. The result of the experiment shows that the GSTCA has higher accuracy rate than SOM algorithm in the Web Chinese Document Clustering, and the average value of F measure is improved by 14.5% than traditional method. The experiments also show that GSTCA is not sensitive to initial weights of the network, thereby enhancing the stability of the algorithm.

Approach for finding optimized rules based on strength of necessity and sufficiency

2008, 28(3):  761-763. 

Asbtract ( )   PDF (716KB) ( )  

Related Articles | Metrics

A new method extracting optimization rules based on information system was put forward. And this method aimed to extract certain optimization rules of necessity and sufficiency in information system. Firstly, strength of necessity and sufficiency and its feature were put forward and discussed. Secondly, for the massive characteristic of searching space and overall optimization of genetic algorithms, optimization rule searching method using genetic algorithms was designed. Lastly, the effectiveness of this method was verified through experiment.

Web document representation method based on new-word discovery

Chun-Ying WU Shi-Tong WANG Chong-Chao CAI

2008, 28(3):  764-767. 

Asbtract ( )   PDF (783KB) ( )  

Related Articles | Metrics

Web document representation is important foundation of Web page feature selection and categorization. At present, the commonly used method is word-based vector space model. Because the model does not consider the latent concept construction of text, and a Web document is in semi-structural form where many new-words perhaps occur, a new Web document representation method based on new-word discovery was presented in this paper. This method first preprocessed the Web page, and segmented words for the converted documents; then tried to discover new-words by using bi-gram and mutual information, added new-words into its original dictionary, and segmented words for text again, finally represented the Web document using words and new-words. The experimental results show that it can help us to identify unknown words and extend the current dictionary, strengthen the representation of Web documents, improve the quality of the adopted vector, and increase the effect of Web document categorization.

Typical applications

Solution for Complicated CARP of Route Planning of Sprinklers

2008, 28(3):  768-772. 

Asbtract ( )   PDF (970KB) ( )  

Related Articles | Metrics

As a kind of CARP(Capacitated Arc Routing Problem) application, route planning of sprinklers involves many factors such as multi-type vehicle, multi-type road, turn prohibition, and so on, which belong to complicated CARP. As for this, the paper presents a algorithm called HEGA(High Efficient Genetic Algorithm)，which is based on traditional genetic algorithm. HEGA improves the population mechanism, structure of chromosome and crossover operation, and then introduces a kind of operation called Local Search to enhance the ability of searching optimal value. An experiment adopting real data, shows that HEGA gains a better plan than manual assignment originally. At last, another comparing experiment between two algorithms proves that HEGA can get quite excellent accuracy of solution.

Object detection module based on implementation of Java and OpenCV

Lu HAN Zushu Li Dongyi CHEN

2008, 28(3):  773-775. 

Asbtract ( )   PDF (768KB) ( )  

Related Articles | Metrics

A module of object detection based on Java and OpenCV was presented, every implementation step of the module's block diagram was explained in detail, the specifies of using Java Native Interface （JNI） to implement the function of object detection via OpenCV were mentioned. This module could simply integrate most academia and industry video based application systems. The experimental results show that the Java video system which integrated this module has a high detection rate and realizes real-time processing.

Two level core test compression based on partial test vector reuse and VRL coding

2008, 28(3):  776-778. 

Asbtract ( )   PDF (547KB) ( )  

Related Articles | Metrics

This paper presents a novel scheme for core based SoC test compression. All the test vectors belonging to distinct test sets are partially overlapped to form shorter overlapped vectors. Variable-Run-Length coding is utilized to further compress the result overlapped test vectors. Due to the fact that test application time is proportional to the length of the overlapped vector, except that the length of the overlapped vector is far less than the sum of the length of the original individual test vectors, minimal test application time can be obtained. Maximized compression ratio is realized through variable-Run-length coding. Experimental results indicate that the proposed method achieves reduced test application time and significant compression rate.

Integration of navigation simulation system based on Eclipse platform

Nian-le SU Xiao-shuang WANG Qun LI Wein-ping WANG

2008, 28(3):  779-781. 

Asbtract ( )   PDF (914KB) ( )  

Related Articles | Metrics

In order to satisfy the software integration requirements of navigation simulation system, an Eclipse based solution of integrating different experiment tasks was proposed. By developing Eclipse plugins of new wizards，experiment configures and experiment analyses, all the modules were well integrated, providing analysts with a system software of universal and consistent operation style. Depending on the ascendency of the Eclipse, this method has the advantages of shorter developing cycle and lower developing cost. Besides, this system software has an open framework, that is, the tasks modules developed in the future can also be integrated into this software.

Recovery of callback function for static binary translation

Song-Yang DING

2008, 28(3):  782-784. 

Asbtract ( )   PDF (594KB) ( )  

Related Articles | Metrics

The recovery of callback function is a difficult problem in static binary translation. For the static binary translation of using C language as backend, this paper put forward a technique of analyzing the gap code and plugging codes into the target programs which searched the callback function address based on the source function address. This method can be implemented effectively. The speed of translated code running exceeds the speed of using interpreter.

Approach of extracting RBC image based on regional growing with boundary contour

2008, 28(3):  785-786. 

Asbtract ( )   PDF (658KB) ( )  

Related Articles | Metrics

A cell extraction algorithm implemented by regional growing based on boundary contour was proposed. Furthermore the 3D height field of each cell can be obtained resorting to Shape from Shading technique, which would be used to calculate surface curvature of cell. The whole algorithm was divided three main sections: tracing contour, regional growing and 3D shape reconstruction with Scanned Electronic Microscope （SEM） imaging system as well. Regarding the statistics feature of overlapped cell, it is reasonable to extract the top-level cell only. The results show that this approach is really practicable and promising.

Parameterization of non-convex surface and its application in game engine

Yu-Jing ZHANG Lei-Ting CHEN Ming-Yun HE

2008, 28(3):  787-789. 

Asbtract ( )   PDF (654KB) ( )  

Related Articles | Metrics

Parameterization is the basic principle of 3D games modeling and the crucial technique in surface fitting. A new algorithm for mesh parameterization was proposed. Attach a convex boundary for non-convex mesh and then parameterize the interior vertices based on mean value coordinate method. This algorithm was applied to the modeling module of game engine, and the experimental results demonstrate the feasibility and efficiency of the method.

Study on classification of micrograph based on SVM

Xian Zhang

2008, 28(3):  790-791. 

Asbtract ( )   PDF (618KB) ( )  

Related Articles | Metrics

Because bacterium in microbe image has different shapes, is apt to overlap, and gray levels are very close, a new method of micrograph identification was proposed in this paper, which was based on pattern recognition theory of Support Vector Machine (SVM) and used texture feature extracted by Variation. The classification results were then compared with the results obtained by NN theory. The results of study have proved that the method based on pattern recognition theory of support vector machine to the classification of bacterium micrograph may improve the accuracy of image classification.

Mandarin-Sichuan dialect bilingual text-independent speaker verification using GMM

Jing Zhao

2008, 28(3):  792-794. 

Asbtract ( )   PDF (609KB) ( )  

Related Articles | Metrics

Due to the mismatch between mandarin and Sichuan dialect in training and test stages, the performance of speaker verification system degrades dramatically. To solve this problem, a combined Gaussian Mixture Model （GMM）, which is trained by proportional pooling mandarin and Sichuan dialect, was presented in this paper. Compared with the Gaussian mixture model trained solely using mandarin/Sichuan dialect, the combined Gaussian mixture model described the characteristic of speaker from both mandarin and Sichuan dialect. Experiments on a self-built mandarin-Sichuan dialect speech database demonstrate that the introduced combined Gaussian mixture model is more robust for speech mismatching between mandarin and Sichuan dialect. A proper proportion between pooling mandarin and Sichuan dialect speech was also provided.

Design and implementation of enterprise service bus

Xiao-Ming Bao Xiao Wu Hai-Hui Zhang Guang-Liang Cheng

2008, 28(3):  795-798. 

Asbtract ( )   PDF (890KB) ( )  

Related Articles | Metrics

The existing Enterprise Service Bus （ESB） products can hardly fulfill enterprises' changeable requirements of business processes due to their absence or inadequacy of manageability, flexibility and openness. Importing work flow technology, an innovative ESB design scheme was proposed with component model as its basis, service chain as the design, deployment and management unit of ESB applications, and event-driven asynchronous messaging as the communication mechanism. Our work has been applied in the NPUESB system. Results prove that the design can not only effectively realize enterprise application integration, but also efficiently implement and manage ESB applications and deal with changeable enterprise business processes, meanwhile possessing good openness and scalability properties.

Realtime feature points matching method in game engine

Liu Yang Lei-Ting Chen He Mingyun

2008, 28(3):  799-800. 

Asbtract ( )   PDF (698KB) ( )  

Related Articles | Metrics

A new method for matching feature points of images from two cameras of a stereo vision system in the game engine was presented. The main issue is how to meet the request of real-time processing and accuracy of the system. Our method is to calibrate the epipolar constrains and calculate the offset of two image along with the constraints of homography. Then we used a fast method to match the feature points in a local area. This method is proved to be real-time and accurate enough to fulfill the request of our game engine.

Robust classifier based two-layer Adaboost for precise eye location

Yi LIU Wei-guo GONG Wei-hong LI

2008, 28(3):  801-803. 

Asbtract ( )   PDF (712KB) ( )  

Related Articles | Metrics

A two-layer eye classifier for eye detection was proposed. Two layers, double-eye layer and single-eye layer, had been trained and cascaded into a strong one for eye detection. Two-layer classifier was more robust in illumination invariance eye detection compared with YCbCr space eye map algorithm. Also, it kept the same detection rate as the commonly trained Adaboost eye classifier with a much lower error detection rate. Relationship among stages, training sample number and error detection rate had been analyzed to facilitate the training procedure.

Fast detection of vehicles based on the moving region

2008, 28(3):  804-807. 

Asbtract ( )   PDF (945KB) ( )  

Related Articles | Metrics

A method for detecting vehicles was presented, which can remove the shadows fast. The main process is composed of three steps: moving region detection, shadow detection and edge detection. Firstly, achieve the moving region quickly using the self-adaptive background updating method. Then get the coarse shadow area where the shadow detection based on the HSV color space is only applied in. Finally, impose edge detection on both the moving regions and shadow areas. Subtraction of these two areas led to the detection of real vehicle. Experimental results show that this method can improve the efficiency of the moving vehicles detection greatly.

Decomposition and recovery on MA superposition process using ICA

Rui Qi Yu-Jie Zhang Hong-Wei LI

2008, 28(3):  808-810. 

Asbtract ( )   PDF (540KB) ( )  

Related Articles | Metrics

Decomposition and recovery on Moving Average （MA） superposition process contained in multivariable time series were researched in this paper. Firstly, because of the independence of the high-order statistical information, the mixtures were separated by searching a reversible matrix with the Independent Component Analysis （ICA） algorithm-fixed point algorithm. Then an adaptive method was designed to identify MA model based on higher-order cumulant. In every iteration, it estimated the order and the parameters of MA. Finally, the effectiveness of the algorithm was verified by the computer simulation.

Using IP factor to customize Intranet search engine

2008, 28(3):  811-812. 

Asbtract ( )   PDF (600KB) ( )  

Related Articles | Metrics

There is a lot of information available in intranet for search engine to improve its performance. The difference between internet and intranet search was compared. Then an algorithm which used IP factor to customize intranet search engine was proposed. The algorithm was implemented on Lucene and an experiment was designed to prove the feasibility and effectiveness of this algorithm.

Sealed-bid electronic auction scheme based on new group signature

Xu Qiu-liang Xu

2008, 28(3):  813-815. 

Asbtract ( )   PDF (577KB) ( )  

Related Articles | Metrics

With the help of a group signature based on Hierarchical Identity-Based Signature (HIBS) and bilinear map， a new secure and efficient sealed-bid electronic auction scheme was presented. The scheme not only fulfilled the common security requirements, such as the anonymity of bidders, robustness, non-repudiation of the winner and public verifiability, but also had some other characteristics: compendiary steps, convenient construction, low cost of communications and computation, etc. Meanwhile, the scheme realized simple revocation, one-registration, and many times bidding.

Integration of OA and ERP based on service-oriented architectures

Jian Wu

2008, 28(3):  816-818. 

Asbtract ( )   PDF (636KB) ( )  

Related Articles | Metrics

Through reconstructing business process, reinforcing business supervising and controlling and so on, the necessity of integrating Office Automation （OA） and Enterprise Resource Planning （ERP） was pointed out. On the basis of the analysis of Service-Oriented Architecture （SOA）, OA and ERP integration scheme based on SOA was proposed. Through constructing workflow platform and SOA, integration of OA and ERP could be realized with low cost and high efficiency, which can provide the business process restructuring platform for the enterprise and improve the enterprise's competitive ability.

Research and implement of SOA-oriented enterprise services bus

2008, 28(3):  819-822. 

Asbtract ( )   PDF (772KB) ( )  

Related Articles | Metrics

For the quickly growing requirements of information sharing and business integration in enterprise, it tends to use SOA architecture to integrate enterprise applications because enterprise service bus can shield the heterogeneous enterprise applications. Current products of SOA-oriented Enterprise Service Bus (s-ESB) can mainly offer Web services container but unified adapter mechanism to integrate some kinds of enterprise applications. It restricts the availability and scalability of s-ESB. In this paper, it firstly brought forward a new SOA-based enterprise application integration environment which clarified the status and function of s-ESB in constructing Web services-based application supporting platform. Then, it presented an architecture for s-ESB, and then analyzed some key technologies including protocols adaptation, service adaptation and common services etc. At last, s-ESB is proved to be feasible and effective by prototype system.

Statistical buffering for streaming media in mobile networks

Xin-Chen CUI

2008, 28(3):  823-825. 

Asbtract ( )   PDF (772KB) ( )  

Related Articles | Metrics

To investigate streaming media access in mobile networks, a new mechanism that made use of prior knowledge to predict the trend of user movement among cells was proposed, which included cache block scheduling and SAA* search algorithm. Experimental studies show that, this algorithm can obtain good performance on buffering streaming media data.

Design and implementation of a distributed parallel system based on streaming media distributing system

2008, 28(3):  826-828. 

Asbtract ( )   PDF (677KB) ( )  

Related Articles | Metrics

The data scheduling policy in the present Peer to Peer streaming media system is a big pressure for the network.To reduce the data schedule in the backbone network, a new scheduling policy was proposed. It based on distributed system and with the main characteristic of scheduling the nearest node, scheduling the client node in a station, the automatic server node scheduling inter-stations. a multicast streaming media system was described to introduce the data distribution technology on this scheduling olicy. The test results present that the system has stable data buffer and with a good performance of node updating.