Loading...

Table of Content

    25 July 2011, Volume 39 Issue 7
    Electronics, Communication & Automation Technology
    Shi Bu-hai Fang Zhi-xiong
    2011, 39(7):  1-6.  doi:10.3969/j.issn.1000-565X.2011.07.001
    Asbtract ( 499 )   PDF (539KB) ( 1001 )  
    Related Articles | Metrics

    Proposed in this paper is a relative coupling-based multi-motor synchronous control algorithm for the high-power all-electric bending machine applied to the multiaxial synchronous bending of sheet metal. In this algorithm,multiple motors drive according to the position deviation synchronously,and the rapidity of each motor is improved by adopting the equivalent velocity and the acceleration feedforward,thus implementing preferable synchronization and meeting the accuracy requirements of sheet metal bending. Moreover,a modeling simulation and a practical test are performed on a bending-machine experiment platform. The results demonstrate that the proposed synchronous control algorithm is of high synchronization accuracy and strong robustness.

    Liang Jin Luo Fei Xu Yu-ge
    2011, 39(7):  7-12.  doi:10.3969/j.issn.1000-565X.2011.07.002
    Asbtract ( 501 )   PDF (268KB) ( 1086 )  
    Related Articles | Metrics

    In order to reveal the quantity monotone dependence of the output on the input,a fuzzy monotone dependence algorithm based on decision table is proposed by analyzing the data about the quantity dependence in practice and by applying the fuzzy rough set theory. Then,the concepts such as the fuzzy monotone dependence and the fuzzy monotone increasing dependence membership function are defined by interval mapping,and the parameters and characteristics describing the fuzzy monotone increasing dependence are discussed. Moreover,the correlative proposition is proved. The proposed algorithm is finally applied to the wastewater treatment,with its effectiveness in data mining being verified.

    Mo Lei Xu Bu-gong
    2011, 39(7):  13-20.  doi:10.3969/j.issn.1000-565X.2011.07.003
    Asbtract ( 521 )   PDF (435KB) ( 746 )  
    Related Articles | Metrics

    In order to meet the requirements of tracking performance and to balance the node energy consumption in wireless sensor networks ( WSNs),an energy model based on the hardware over wireless sensor node and the time sequence procedure is established. In the process of node communication,a quantization algorithm is employed to compress the transmitted data,on the basis of which a scheduling algorithm with energy optimization strategy is proposed by synthetically taking into consideration the tracking accuracy and the residual energy of nodes. Moreover,a
    double wake-up /sleep mechanism is adopted to prolong the network lifetime. The proposed scheme is easy to implement in resource-limited nodes due to the adoption of distributed computing mode. Experimental results demonstrate that the test platform effectively tracks moving targets in WSNs. Simulated results show that the energy optimization strategy effectively balances the energy consumption among nodes and prevents nodes from depleting prematurely.

    Chu Qing-xin Sun Jing-jing Lin Feng
    2011, 39(7):  21-25,31.  doi:10.3969/j.issn.1000-565X.2011.07.004
    Asbtract ( 507 )   PDF (344KB) ( 1265 )  
    Related Articles | Metrics

    As the conventional 3dB dual-band branch-line coupler is of narrow operation frequency ratio,the method to design a novel dual-band branch-line coupler loaded with stepped impedance stub lines is presented. The adoption of stepped impedance stub lines increases the design degree of freedom and reduces the restriction from the physical realization of impedance range. Thus,a 3 dB dual-band branch-line coupler with wide-range frequency ratio ( 1. 7 ~ 6. 3) can be obtained. Moreover,a 3 dB microstrip branch-line coupler operating at 2. 4 /5. 8 GHz WLAN bands is simulated and fabricated to verify the proposed design method. The results show that,as compared with the conventional Ⅱ-shaped dual-band branch-line coupler,the novel coupler achieves a stub-size reduction up to 25. 1%. The simulated results accord well with the measured ones,which means that the proposed design method is feasible.

    Lin Feng Chu Qing-xin
    2011, 39(7):  26-31.  doi:10.3969/j.issn.1000-565X.2011.07.005
    Asbtract ( 405 )   PDF (443KB) ( 1059 )  
    Related Articles | Metrics

    As the conventional rat race coupler can only operate at the fundamental frequency and may cause odd harmonics,the design method of a novel tri-band rat race coupler is presented. In this method,the quarter-wavelength impedance transformers in the conventional rat race coupler are replaced by the Ⅱ-shaped stepped impedance ones ( ΠSITs) with four circuit topologies,which enables the proposed coupler to operate at two arbitrary frequencies and their center frequency. Then,by taking into consideration the practical realization range of transmission line impedance ( 20 ~150Ω) ,the ratio of the third operating frequency to the first one of the proposed coupler is selected from 1. 70 to 4. 10 and from 6. 60 to 12. 30. Moreover,the corresponding analytic design equations are deduced,and two microstrip 3-dB tri-band rat race couplers based on different ΠSIT circuit topologies,which respectively operate at 2. 0 /3. 9 /5. 8 GHz and 0. 9 /3. 5 /6. 1 GHz,are designed and fabricated. Simulated results accord well with the measured ones,meaning that the proposed design method is feasible.

    Li Bo
    2011, 39(7):  32-37.  doi:10.3969/j.issn.1000-565X.2011.07.006
    Asbtract ( 466 )   PDF (278KB) ( 1084 )  
    Related Articles | Metrics

    When there is more than one tag to simultaneously transmit their data to the reader of radio frequency identification ( RFID) systems,the mixing signals may collide and the reader can not identify what is received,which may significantly reduce the identification rate and the working efficiency of RFID systems. In order to solve this problem,an anti-collision algorithm for RFID systems based on the tag information grouping is proposed,in
    which the tags are divided into several groups according to the information stored in them,the groups are orderly identified according to the grouping sequence,and the colliding probability is reduced by decreasing the number of tags responding to the reader's order. Moreover,the grouping efficiency and the timeslot selection of the proposed algorithm are analyzed,verified and simulated. The results show that the proposed algorithm is superior to the common binary tree algorithm and the ALOHA algorithm because it reduces the collision probability and improves the group identification efficiency.

    Zhang Ying Shen Zhong Chang Yi-lin
    2011, 39(7):  38-44.  doi:10.3969/j.issn.1000-565X.2011.07.007
    Asbtract ( 352 )   PDF (399KB) ( 1046 )  
    Related Articles | Metrics

    Proposed in this paper is a node moving algorithm based on the receiving signal strength,which is used to reduce or eliminate the cut nodes through the node movement without disconnecting the existing links. In this algorithm,according to the receiving signal strength,the moving node,the target node that the moving node tries to connect to,and the moving target position are respectively determined in the presence of cut nodes. Also,the cost
    function of links is defined,by which the movement of node is transformed into a process of minimizing the cost function value. Simulated results show that,with the help of the proposed algorithm,the connectivity of Ad hoc networks can be improved only by moving a single node even when the node information is unavailable,and the network coverage keeps unchanged.

    Xie Wen-hua Xiao Jin-sheng Yi Ben-shun Huang Zheng-xu
    2011, 39(7):  45-49,55.  doi:10.3969/j.issn.1000-565X.2011.07.008
    Asbtract ( 499 )   PDF (282KB) ( 1376 )  
    Related Articles | Metrics

    In the implementation of constant bitrate in advanced audio coding ( AAC) using the ISO standard algorithm,the bitrate is unstable and the computational complexity is high. In order to solve these problems,a novel constant bitrate control algorithm is proposed. By fully considering the use of the bit buffer and the coding complexity during the allocation of bits for the current frame,the buffer plays its important role. Besides,the mask threshold is pre-adjusted before the quantization loop according to the relationship between the number of bits needed for coding and the perceptual entropy. Experimental results show that,as compared with the standard algorithm,the proposed algorithm effectively reduces the iteration number of the quantization loop,significantly decreases the computational complexity,and produces more stable bitrate without decreasing the audio quality.

    An Jin-kun Tian Bin Yi Ke-chu Yu Quan
    2011, 39(7):  50-55.  doi:10.3969/j.issn.1000-565X.2011.07.009
    Asbtract ( 523 )   PDF (333KB) ( 1125 )  
    Related Articles | Metrics

    Proposed in this paper is a blind identification algorithm of orthogonal frequency division multiplexing ( OFDM) signals based on multifractal features,which is applied to the modulation identification in non-cooperative communication. In this algorithm,first,two items,namely the singularity exponent of the maximum multifractal value from communication signals and the span of multifractal from the amplitude of twice Fourier transform of
    squared analytic communication signals,are extracted as signal feature parameters. Then,a multi-layer decision tree separator is constructed to identify OFDM signals and single-carrier signals. The feature parameters extracted by this algorithm are robust to the number of subcarriers,the length of the cyclic prefix of OFDM signals,the raised-cosine shaping roll-off factor of single-carrier signals and the signal-to-noise ratio ( SNR) ,and the signals are processed in intermediate frequency channel. Thus,the synchronization in time and frequency domains is not required. Simulated results show that the proposed algorithm can identify OFDM signals with a high average identification rate in a wide SNR range.

    Li Zhi-jie Fang Xu-ming
    2011, 39(7):  56-62,69.  doi:10.3969/j.issn.1000-565X.2011.07.010
    Asbtract ( 560 )   PDF (448KB) ( 1047 )  
    Related Articles | Metrics

    In order to meet the requirements of the next-generation wireless LAN,an optimization algorithm of frame aggregation is proposed for the multiple-input multiple-output ( MIMO) system. In this algorithm,first,the bit error rates ( BERs) in different spatial streams and modulation /coding schemas are calculated. Next,the frame aggregation throughput under saturated traffic is analyzed by integrating the Markov chain model that describes the
    contention access process of channel. Then,the optimization algorithm which tunes the parameters such as the aggregated size dynamically under current channel and collision conditions is presented. Finally,the algorithm is implemented based on the link quality metric using a simplified method. Analytical and simulated results show that,with the help of the diversity of MIMO technology,the proposed algorithm helps to select optimal control parameters in real time,improves the network throughput,reduces the BER and greatly decreases the complexity of the system to meet the requirements of real-time control.

    Yang Wei Sun Le Xu Chang-long
    2011, 39(7):  63-69.  doi:10.3969/j.issn.1000-565X.2011.07.011
    Asbtract ( 530 )   PDF (996KB) ( 3235 )  
    Related Articles | Metrics

    This paper deals with the channel estimation technology applied to orthogonal frequency division multiplexing ( OFDM) systems and proposes a novel method to design the optimal pilot pattern. In this method,first,the spacing in the time and the frequency domains between two pilot symbols are determined respectively according to the maximum multi-path delay and Doppler frequency shift. Then,all possible pilot patterns are listed by using
    the exhaustive method. Finally,the optimal pilot pattern is obtained according to the mean square error between the estimated and the actual channels. In addition,the proposed method is applied to a long-term evolution ( LTE) system to verify its correctness and effectiveness,and the superiority of the optimal pilot pattern is verified by simulation curves. From the simulated results,it is found that,as compared with the system using the original LTE pilot pattern,the system using the optimal pattern is of higher BER ( Bit Error Rate) performance under the Vehicular Test A channel.

    Meng Fan-yuu Gu Xue-mai Yang Ming-chuan Guo Qing
    2011, 39(7):  70-76,114.  doi:10.3969/j.issn.1000-565X.2011.07.012
    Asbtract ( 456 )   PDF (362KB) ( 985 )  
    Related Articles | Metrics

    Proposed in this paper is a multiple access technology based on bivariate Chirp modulation,which makes use of both the Chirp rate and the initial Chirp phase to furtherest suppress the multiple access interference with small system gain. When the Chirp rate differences are small,this method can ensure the orthogonality of multiple access signals by distinguishing different initial phases. Moreover,the effect of the mutual correlation of multiple access users' Chirp signals on the bit error rate ( BER) is discussed,and the superiority of the initial phase factor in constructing the multiple access signal basis is analyzed, Simulated results show that,as compared with the existing multiple access technologies based on Chirp spread spectrum,the proposed one is more effective because it suppresses the multiple access interference and permits more multiple access users to simultaneously access the system without obviously degrading the BER performance.

    Zhao Jun-hong
    2011, 39(7):  77-82.  doi:10.3969/j.issn.1000-565X.2011.07.013
    Asbtract ( 464 )   PDF (701KB) ( 1202 )  
    Related Articles | Metrics

    Aiming at the edge blurring manipulation in image tampering,a new algorithm for image forensics is presented. In this algorithm,first,the tampered blurring edge is enhanced based on the fuzzy mathematics,while the real clear edge and flat region is weakened,thus obtaining an image. Next,the tampered image is divided into many sub-images,which are then classified to remove flat regions and real clear sharp edges by using the attribute
    reduction of rough set theory,thus obtaining another image. Finally,a fusion of the two above-mentioned images is performed to obtain the resulting image. Experimental results show that the proposed algorithm is an effective passive forensics method that reveals the blurred regions but excludes flat regions and real clear sharp edges.

    Liu Xiao-shan Du Ming-hui Zeng Chun-yan Jin Lian-wen
    2011, 39(7):  83-87.  doi:10.3969/j.issn.1000-565X.2011.07.014
    Asbtract ( 484 )   PDF (343KB) ( 1466 )  
    Related Articles | Metrics

    In order to improve the face recognition rate under varying lighting conditions,a novel face recognition algorithm based on the nonsubsampled Contourlet transform and the pseudo-Zernike moment is proposed. In this algorithm,first,invariant illumination components are extracted via the soft-threshold denoising in the Lambertian illumination model. Then,the corresponding pseudo-Zernike moment vectors are calculated and are used as face classification features. Experimental results on Extended YaleB and CMU PIE face databases show that,as compared with the common face recognition algorithms,the proposed algorithm can eliminate the effect of illumination more effectively and adapt to the variation of scale and pose,so that it significantly improves the accuracy of face recognition.

    Liang Ya-ling Du Ming-hui
    2011, 39(7):  88-94.  doi:10.3969/j.issn.1000-565X.2011.07.015
    Asbtract ( 521 )   PDF (511KB) ( 1415 )  
    Related Articles | Metrics

    In this paper,by taking the visual-only lipreading system as the research objective,a method to extract the visual lip feature based on the lip gray energy image ( LGEI) is proposed. In this method,the image sequences of a word are projected to the 2D lip gray energy image to unify the dimension of input data and maintain most motion information of image sequences. In order to eliminate the dependence of the template matching method on the
    template,the LGEI of the single-training sample is extended to the multi-training sample. Moreover,a lip location method based on the lip center is also proposed. Experimental results show that,as compared with the conventional methods that extract features for each image of the sequence,the proposed method greatly improves the recognition rate and significantly decreases the computation time in the same dimension of features for a single image,that the recognition rate of double-training samples averagely improves by 11.29%,as compared with that of single-training samples,and that,after an accurate lip location,the recognition rate improves by more than 2%,with its maximum being up to 90.63%.

    Zhang Yi Pu Yi-fei Zhou Ji-liu
    2011, 39(7):  95-101.  doi:10.3969/j.issn.1000-565X.2011.07.016
    Asbtract ( 518 )   PDF (641KB) ( 1196 )  
    Related Articles | Metrics

    Both the one-order and the two-order image enhancement masks based on integral-order calculus are insufficient in image processing because the former may cause wide edges and the latter may enhance the texture and the noise. In order to avoid these side effects,the 1 ~2-order fractional derivation masks of digital images are analyzed and deduced according to the Riemann-Liouville definition of fractional calculus,and the corresponding filter is constructed. Simulation results indicate that the constructed filter can not only maintain the low-frequency contour information in the smooth region but also nonlinearly enhance the high-frequency edges and the texture information in images,and that it has unique advantage and excellent visual effect for the treatment of images whose texture information is of great importance.

    Electronics, Communication & Automation Technology
    Zhu Ming Liang Dong Tang Jun Fan Yi-zheng Yan Pu
    2011, 39(7):  102-108.  doi:10.3969/j.issn.1000-565X.2011.07.017
    Asbtract ( 499 )   PDF (1004KB) ( 935 )  
    Related Articles | Metrics

    As most spectrum-based algorithms cannot effectively deal with the matching of size-variable point sets,a point pattern matching algorithm based on the Q-spectrum of line graph is proposed. In this algorithm,first,a weighted complete graph is constructed for each point set,and a line graph is constructed for each point by using the incident first k shortest edges. Then,a spectral decomposition is performed for the signless Laplacian matrix
    constructed with the line graph,and the eigenvalues ( Q-spectrum) obtained from the spectral decomposition are used to represent the features of the point,which make it possible to calculated the matching probability. Finally,the optimal matching of point sets is searched by using the KM algorithm. Experimental results show that the proposed algorithm is of high matching accuracy,and that it can deal with the matching of two point sets with different sizes.

    Luo Hong-yan Li Min Zhang Shao-xiang Zheng Xiao-lin Tan Li-wen Liu Ning
    2011, 39(7):  109-114.  doi:10.3969/j.issn.1000-565X.2011.07.018
    Asbtract ( 348 )   PDF (867KB) ( 570 )  
    Related Articles | Metrics

    In order to reduce the manual intervention involved in the existing segmentation methods of digital human slice images,an algorithm based on the connected component labeling and the K-means clustering is proposed. In this algorithm,first,the initial region of brain tissue is segmented via the connected component labeling and is refined via erosion. Then,a K-means clustering is adopted to extract the white matter,in which the color histogram is used to determine the clustering centers and the Euclidian distance is considered as the judging criterion. The proposed algorithm is finally applied to the segmentation of the sequential brain slice images from the first Chinese female visible human dataset. The qualitative and quantitative analyses of experimental results indicate that the proposed algorithm is of high segmentation accuracy and strong stability,and that it can be used to the automatic separation of skull from the brain tissue and to the automatic extraction of structures in deep brain.

    Computer Science & Technology
    Min Hua-qing Lü Ju-mei Luo Rong-hua Chen Cong
    2011, 39(7):  115-120.  doi:10.3969/j.issn.1000-565X.2011.07.019
    Asbtract ( 591 )   PDF (531KB) ( 1577 )  
    Related Articles | Metrics

    Shadows of moving objects often reduce the accuracy and the effectiveness of tracking and recognition of moving objects. In order to distinguish the objects from their shadows,an adaptive shadow detection method is proposed based on the Gaussian mixture model ( GMM) and the Markov random field ( MRF) . In this method,first,an improved GMM,which adaptively adjusts the parameter learning ratio,is proposed to remove the light shadow of
    an object. Then,a new approach to shadow detection is put forward based on the spatial dependence information about the integrated neighborhood of MRF. Moreover,in order to improve the MRF-based shadow detection accuracy and effectiveness,the information capacity is used to select color features,and the results of a coarse shadow detection obtained from the adaptive threshold-based segmentation are employed to initialize the parameters of MRF. Experimental results indicate that the proposed approach effectively avoids the misclassification existing in the shadow detection and improves the detection accuracy.

    Luo Jian-gao Han Guo-qiang Wo Yan Liang Peng
    2011, 39(7):  121-126,145.  doi:10.3969/j.issn.1000-565X.2011.07.020
    Asbtract ( 433 )   PDF (531KB) ( 1116 )  
    Related Articles | Metrics

    As the existing block-wise lossless image authentication algorithms cannot determine appropriate sizes of image authentication blocks,a novel lossless image authentication algorithm with size-variable authentication blocks is proposed. In this algorithm,an image authentication block is composed of some basic image blocks,and the authentication code is generated by using a digital signature algorithm and is embedded into the authentication block via the lossless watermarking. Moreover,the robust transmission of the image ID is achieved via multiple embedding,which helps to distinguish different images and to resist the vector quantization attack. Theoretical analyses and experimental results demonstrate that the proposed algorithm can not only effectively resist the vector quantization attack but also improve the tamper localization accuracy because it can dynamically adjust the sizes of authentication blocks according to the characteristics of the host image and the fidelity threshold of the watermarked image.

    Liang Ru-bing Liu Qiong
    2011, 39(7):  127-133.  doi:10.3969/j.issn.1000-565X.2011.07.021
    Asbtract ( 438 )   PDF (367KB) ( 903 )  
    Related Articles | Metrics

    The traditional algorithms of semantic cache consistency maintenance are of enormous data communication cost and space complexity of invalidation report. However,most of the current researches mainly focus on the client's algorithms and are unable to solve the above-mentioned problems radically. In this paper,a novel method of semantic cache consistency maintenance with a three-layer cache structure is proposed,which uses the mobile support station ( MSS) to store mobile client's semantic cache items. Then,the corresponding index table is presented and an invalidation report is created based on the bit sequence to further shorten the report length. Finally,the updating sequence is stored in a queue and is used to refine the updated granularity and simplify the consistency maintenance from clients,thus saving the network bandwidth and supporting the cache consistency maintenance in the condition of frequent network disconnection. Simulated results show that the proposed algorithm remarkably reduces the invalidation report size and saves the data communication cost for consistency maintenance.

    Qi Quan Dong Jing
    2011, 39(7):  134-139.  doi:10.3969/j.issn.1000-565X.2011.07.022
    Asbtract ( 378 )   PDF (404KB) ( 888 )  
    Related Articles | Metrics

    Video titles,which are used to describe video content in the text-based video retrieval and recommendation system,are essential sources of information. However,there are no in-depth researches on the description ability of video titles. In this paper,a method is proposed to evaluate the description ability of titles,in which the description ability is divided into three levels that are respectively describable,incomprehensible and comprehensible but undescribable,and the evaluation of the description ability is considered as a classification problem. Moreover,the support vector machine ( SVM) with high recognition accuracy for small samples is used as the classifier. Besides,in order to fill up the shortage of title information,the search results in the search engine are used as the supplements. Finally,the proposed method is applied to the classification of 5000 automotive video titles. that,with the help of the search results,the F scores increase by 3% for both describable and incomprehensible titles.

    Liu Xiao-ming Fan Xiao-zhong Liu Li
    2011, 39(7):  140-145.  doi:10.3969/j.issn.1000-565X.2011.07.023
    Asbtract ( 432 )   PDF (264KB) ( 1351 )  
    Related Articles | Metrics

    The complex questions in the question answering ( QA) system usually involve much more event information. Proper processing of the event content is important for the accuracy improvement of QA system. In this paper,an analysis method of complex questions integrating event information is proposed,in which an event is considered as a complex data object containing multiple arguments,the semantic model of the event is defined,and the
    similarity calculation method of the events is obtained. In the investigation,by using event extraction methods,the event information of a complex question is obtained to form event semantic model instances,and the whole semantic information of a complex question is then represented by a vector consisting of several semantic model instances. Consequently,the similarity of questions is calculated according to the vectors of semantic model instances of the event. Experimental results indicate that the semantic information of an event is helpful to the question analysis,and that the proposed analysis method of complex questions integrating event information improves the overall performance of QA system,with the accuracy being up to 78. 6%.

    Computer Science & Technology
    Liu Li Liu Xiao-ming
    2011, 39(7):  146-149,155.  doi:10.3969/j.issn.1000-565X.2011.07.024
    Asbtract ( 429 )   PDF (229KB) ( 1654 )  
    Related Articles | Metrics

    As domain-specific phenomenal terms are usually compounds that are difficult to extract according to local context features via the traditional machine learning methods,a novel extraction method is proposed. In this method,first,the context-based method is employed to extract the separator set. Then,with the combination of the separator set and context terms,the improved NC-value algorithm is used to extract candidate phenomenal results. Finally,nominal terms are filtered out from the candidate phenomenal terms to obtain the final terms. Experimental results indicate that the proposed extraction method of domain-specific phenomenal terms performs better than the word frequency-based and the separator-based ones.

    Zhao Xiang-kun Li Feng-xia Zhan Shou-yi
    2011, 39(7):  150-155.  doi:10.3969/j.issn.1000-565X.2011.07.025
    Asbtract ( 385 )   PDF (408KB) ( 1316 )  
    Related Articles | Metrics

    In order to improve the fluid simulation speed based on the smoothed particle hydrodynamics ( SPH) ,a new grid-based neighbor search method realizing on the graphics processing unit ( GPU) is proposed. In this method,first,the particle grid map texture is created according to the particle position texture and is sorted according to the grid index of each particle via the CPU sorting method. Then,the particle neighbor index is obtained by searching the sorted grid map texture and is assigned to the pre-computed position of neighbor map texture. The proposed method overcomes the current inability of pixel shaders in terms of scatter operations. With the adoption of this new GPU-based neighbor search technology,SPH fluid simulation can be entirely implemented on GPU and the fluid simulation speed can be doubled.

    2011, 39(7):  156-162.  doi:10.3969/j.issn.1000-565X.2011.07.026
    Asbtract ( 460 )   PDF (489KB) ( 1730 )  
    Related Articles | Metrics

    Proposed in this paper is a novel algorithm based on the spectral clustering and the multiple instance learning,which is applied to the object-based image retrieval. In this algorithm,first,the whole image is regarded as a bag and the visual features of the segmented region are regarded as instances. Next,the spectral clustering of the instance set of positive bags is performed according to the principle of maximum the clustering center number to select the potential center and the representation of positive instance. Then,the radial basis function ( RBF) and the pyramid match kernel ( PMK) are respectively used to measure the similarities of the potential positive instances and other instances in bags. Finally,the support vector machine and the relevance feedback are adopted to retrieve images. Experimental results of the SIVAL image set show that the proposed algorithm is an effective solution to the object-based image retrieval.

    Zhu Wei-jun Zhou Qing-lei Zhang Hai-bin
    2011, 39(7):  163-168.  doi:10.3969/j.issn.1000-565X.2011.07.027
    Asbtract ( 271 )   PDF (276KB) ( 836 )  
    Related Articles | Metrics

    In order to find a unified model checking algorithm for extended interval temporal logic ( EITL) ,the decidable subset of extended Tempura language,which is an executable subset of EITL,is obtained by defining that the constants and the variables in the first-order extended Tempura are all in a finite enumerable type and by combining the constraint version of the first-order extended Tempura with propositional EITL. Then,a novel model checking algorithm of EITL in unified logical framework is proposed. The algorithm is used to decide whether a specification program written in the decidable subset of extended Tempura language satisfies the property described as a propositional EITL formula,and the check includes two steps: to translate the specification program into a propositional EITL formula and to use the existing EITL satisfiability-checking algorithms to automatically check the property. Case study indicates that the proposed algorithm is effective.

News
 
Featured Article
Most Read
Most Download
Most Cited