Wenxian Yu

Shanghai University, Shanghai, Shanghai Shi, China

Are you Wenxian Yu?

Claim your profile

Publications (23)4.45 Total impact

  • Min Tang, Xia Chen, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: This study considers probabilistic fuzzy systems constructed using Mamdani probabilistic fuzzy rules. As a generalisation of deterministic fuzzy systems, Mamdani probabilistic fuzzy systems better model practical complex systems involving uncertainty because they combine the interpretability of fuzzy systems with the statistical properties of probabilistic systems. Using probabilistic fuzzy rules, both probabilistic uncertainty and linguistic ambiguity are handled simultaneously with a single framework. Considering that the information available often consists of a training set of input–output data pairs, a general method for generating Mamdani probabilistic fuzzy rule bases from numerical data pairs is presented. A fuzzy reasoning method is used on the generated probabilistic fuzzy rule base to derive a map leading from the input space to the output space, and a probabilistic fuzzy system is constructed. We use this probabilistic fuzzy modelling method for nonlinear regression analysis. The effectiveness of the proposed method is demonstrated by a comparison with similar regression techniques.
    Information Sciences. 12/2012; 217:21–30.
  • Min Tang, Xia Chen, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: The design of type-2 fuzzy rule-based classification systems from labeled data is considered in this study. With the aid of interval type-2 fuzzy sets, which can effectively capture uncertainties in the data, a compact and interpretable interval type-2 fuzzy rule base with fewer rules is constructed. Corresponding type-2 fuzzy reasoning method for classification is also presented. The validity of this classification system is shown through experimental results on several data sets.
    Integrated Uncertainty in Knowledge Modelling and Decision Making - International Symposium, IUKM 2011, Hangzhou, China, October 28-30, 2011. Proceedings; 01/2011
  • Weiwei Guo, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: High resolution parameters estimation for Multidimensional Harmonic Retrieval problem is required in a variety of applications including radar, sonar, and communication, etc.. Recent approaches based on deterministic tensor decomposition show promising results. However, these methods raise difficulties to estimate the unknown number of targets. In this paper, we address this problem through reformatting it into a Bayesian framework. Since exact Bayesian estimation of the unknown parameters is intractable, an approximation scheme based on variational principle is developed. The significant features of this approach are that the unknown number of targets are efficiently estimated as a part of Bayesian inference process and moreover, it provides high estimation performance. Experimental results demonstrate the effectiveness of the proposed method.
    01/2011;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents an efficient algorithm combining the stabilized biconjugate gradient fast Fourier transform (BCGS-FFT) method with an improved discrete complex image method (DCIM) for electromagnetic scattering from electrically large objects in both lossless and lossy multilayered media. The required spatial Green's functions obtained by the improved DCIM are accurate both in the near- and far-field regions without any quasi-static and surface-wave extraction. Then, the scattering by buried objects is considered using the BCGS-FFT method combined with the improved DCIM. Numerical results show the improved DCIM can save tremendous CPU time in scattering involving buried objects.
    IEEE Transactions on Geoscience and Remote Sensing 01/2010; 48:1180-1185. · 3.47 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: An efficient particle filter based distributed track-before-detect (PF-DTBD) algorithm is presented in this paper. It key idea is the fusion of multi-sensor local estimated conditional probability density functions (PDFs). Firstly, the PDFs among sensors nodes are estimated by multivariate kernel density estimation (MKDE) technique based on finite particles set and fused to calculate the fused particle's weight at fusion node. Next, according to Bayes rule, we prove that the unnormalized fused particle' weight is actually composed of sensors' local measurement likelihood, which makes the likelihood ratio test feasible at fusion node. Finally we introduce a detection scheme combining sequential probability ratio test (SPRT) and fixed sample size (FSS) likelihood ratio test to definitely realize TBD process for weak targets. Simulation results show our algorithm is efficient, which reduces delay of detection and improves the precision of state estimation simultaneously.
    Radar Conference, 2009 IET International; 05/2009
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, an ensemble of neural networks based incremental learning algorithm with weights updated voting is described. The algorithm defines the class kernel function of the training database of the component neural network in the ensemble. The voting weights are updated based on the distance between the test instance and the kernel function. This method can adaptively update the voting weights according to the classification performance of the component neural network on the test pattern and it is more optimal than the stable weights voting strategy. Experimental results show that the ensemble of neural networks based incremental learning algorithm with weights updated voting is more promising than that with stable weights voting rule.
    Advances in Neural Networks - ISNN 2009, 6th International Symposium on Neural Networks, ISNN 2009, Wuhan, China, May 26-29, 2009, Proceedings, Part I; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Geophysical model function (GMF) is the basis and prerequisite for the ocean surface wind vector retrieval with scatterometers. Among many operational models, the Qscat-1 model was specifically developed for SeaWinds scatterometer and is being applied to its operational wind retrieval. This paper is to validate the accuracy of the Qscat-1 model by using some SeaWinds Level 2 data and corresponding buoy data. First, a comparison between L2B and co-located buoy wind speed was made to analyze the systematic bias between them, and then a new geophysical model function was established using the match-ups of the L2A and buoy data to further valuate the accuracy of the Qscat-1 model. The analytical and modeling results indicate that there may be some systematic error in the Qscat-1 model.
    Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International; 08/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Geophysical model function is the basis for the wind vector retrieval with scatterometer and a number of models have been developed to operationally retrieve the ocean surface wind in the past three decades. However, none of the operational models ever took the water surface temperature into account in its modeling, which is considered to have some effect on the ocean backscattering, and in turn on the model accuracy. Taking Sea Winds as an example, this paper attempts to develop new geophysical model functions with surface temperature to be taken into account by using its level 2A data and corresponding buoy data. For contrast, two independent models are established for the ocean water and fresh water respectively. The modeling results and analysis indicate that some effect of the surface temperature on backscatter were found for both types of water, but with a larger extent of the temperature effect for fresh water.
    Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International; 08/2008
  • [Show abstract] [Hide abstract]
    ABSTRACT: Group targets data association is a key part of group targets analysis through multisensor information fusion. Traditional data association methods using group centroids are no longer applicable when the observation areas of multiple sensors partially overlap. Aiming at the problem a new group targets data association algorithm is proposed in this paper. Firstly, the local structures centered on every point within the point pattern which represents the group target data are constructed based on its Delaunay graph. A pair of reference subsets is found from two point patterns to be associated via local structure matching. Then the two point patterns are aligned by the transformation parameter estimated using the reference subsets. Finally the various group targets data are associated once the aligned data have been matched. Simulation experiments show that the proposed algorithm is an effective solution for the group targets data association problem of multiple sensors with their observation areas partially overlapped.
    Information and Automation, 2008. ICIA 2008. International Conference on; 07/2008
  • Zenghui Zhang, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces the preconditioned methods for Space-Time Adaptive Processing (STAP). Using the Block-Toeplitz-Toeplitz-Block (BTTB) structure of the clutter-plus-noise covariance matrix, a Block-Circulant-Circulant-Block (BCCB) preconditioner is constructed. Based on the preconditioner, a Preconditioned Multistage Wiener Filter (PMWF) which can be implemented by the Preconditioned Conjugate Gradient (PCG) method is proposed. Simulation results show that the PMWF has faster convergence rate and lower processing rank compared with the MWF.
    Journal of Electronics (China) 01/2008; 25(4):465-470.
  • [Show abstract] [Hide abstract]
    ABSTRACT: A method of ship formation recognition is proposed based on the information fusion of spaceborne IMINT (image intelligence) and ELINT (electronic intelligence) in this paper. Firstly, the composition and the battle array of the observed ship formation are derived from the spaceborne IMINT information of each individual ship. The beliefs about the composition and the battle array of the observed formation are calculated separately. A synthetic evaluation method is used to get the BPAF (basic probability assignment function) from IMINT information using the aforementioned two beliefs. Secondly, by computing the matching measure between the observed emitter set and that of the typical formation entity, the BPAF based on ELINT information is obtained. Thirdly, the two BPAFs based on the information of spaceborne IMINT and ELINT are combined with DS (Dempster-Shafer) evidence theory. Finally, a decision is made according to the combined BPAF. The experiment indicates that our proposed methods to obtain the BPAFs are practicable and the formation recognition accuracy is greatly improved compared to the results which use only one of the two sources.
    Proc SPIE 11/2007;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Different from the airborne scenario, space time adaptive processing (STAP) for space based radar (SBR) is a full system design task whose performance is significantly determined by radar system parameters such as array aspect ratio and PRF. To mitigate clutter, the two parameters should be appropriately designed. The suppression of mainbeam clutter is discussed while taking the earth's rotation and high range foldovers into consideration. Clutter rank is derived by modeling it as an equivalent two-dimensional spatially band-limited process and it is shown to be a function of array aspect ratio and radar PRF. Relationships between clutter rank and the two parameters are analyzed. Optimal array aspect ratio and radar PRF are obtained by minimizing clutter rank with the tradeoff of minimum discernable velocity (MDV). A high fidelity modeling of SBR is given to illustrate the effectiveness of the method.
    Proc SPIE 11/2007;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Feature extraction and selection play an important role in radar target recognition. This paper focuses on evaluating feature separability for SAR ATR and selecting the best subset of features. In details, fifteen features extracted from T72, BTR70 and BMP2 in MSTAR standard public dataset are examined, which are divided into seven categories: standard deviation, fractal dimension, weighted-rank fill ratio, size-related features, contrast-based features, count feature, projection feature, and moment features. Since the number of samples is small, a new separability criterion based on the overlap degree of each two class regions is proposed to assess the separability of these features. Here the class region is described by support vector data description (SVDD) method for good generalization. Based on the proposed criterion, a forward feature selection method is adopted to choose the best subset of features. Because of the strong variability of the feature against aspect, the features are analyzed under different aspect sectors within 360°angle range stepped by 15°, 30 °, and 60°, respectively. Experiments using MSTAR dataset validate the criterion, and the best subset of features is determined.
    Proc SPIE 11/2007;
  • [Show abstract] [Hide abstract]
    ABSTRACT: Estimating debris population is of great significance for assessing impact risk to spacecrafts, predicting the long-term growth potential and validating space debris models. A method of estimating the confidence interval for debris population using radar beam fence is proposed. The problem whether a debris object that may cross the beam fence, i.e. has large enough inclination and radar cross section, is actually detected is modeled as a (0-1) distribution. Using orbital altitudes measured, the average probability of crossing the beam fence is obtained. The confidence interval for debris population is estimated by the Central Limitation Theorem. Experimental results show the validity of the method.
    Proc SPIE 11/2007;
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a new method of High Resolution Range (HRR) profile formation based on Linear Frequency Modulation (LFM) signal fusion of multiple radars with multiple frequency bands. The principle of the multiple radars signal fusion improving the range resolution is analyzed. With the analysis of return signals received by two radars, it is derived that the phase difference between the echoes varies almost linearly with respect to the frequency if the distance between two radars is negligible compared with the radar observation distance. To compensate the phase difference, an entropy-minimization principle based compensation algorithm is proposed. During the fusion process, the B-splines interpolation method is applied to resample the signals for Fourier transform imaging. The theoretical analysis and simulations results show the proposed method can effectively increase signal bandwidth and provide a high resolution range profile.
    Journal of Electronics (China) 12/2006; 24(1):75-82.
  • Zhengxin Song, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: Early warning of debris impact makes it necessary to detect and, if possible, catalog all threatening debris. Space debris environment monitoring fence is an attractive option for the requirement. This kind of fence can detect each object passing through its beam with no task planning. It has significant capabilities to detect new launchings, maneuvers and breakups. This paper depicts the necessity of monitoring space debris terrestrial environment and the merits of space debris environment monitoring fence. An overview of the world state of the fence research is present. The techniques of space debris environment monitoring using the fence are discussed, including determination the position and velocity vectors of detected objects from direction cosines, orbit determination by itself and by cooperating with auxiliary sensors, and correlation and cataloging of space objects. Methods of new launching, maneuver validation and detection of breakups are highlighted. The calibration of space debris environment monitoring fence is also described. The future directions of this kind of fence are analyzed in terms of operating frequency, operating concept and system configuration.
    Proc SPIE 11/2005;
  • Hui Tang, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: Shape and size estimation of space debris is an important issue of space debris observation. Generally speaking, space debris is prolate, and follows a simple roll rotation motion around the major axis. In virtue of its own shape and motion features, a two-dimensional radar imaging method of small space debris employing low resolution radar is proposed in this paper. The method recurs to time-frequency analysis technology to obtain the time-instantaneous Doppler distribution of all Scattering centers on the target, and then rearranges the distribution according to aspect angles to acquire target's cross range-aspect angle distribution, and finally reassigns respective points' power in the cross range-aspect angle distribution to gain target image. Furthermore, the paper analyzes the impact of reference center's uniform accelerated motion relative to radar on imaging, and presents corresponding solutions. Simulation results reveal the validity of the method, and target image has a resolution of approximate wave length.
    Proc SPIE 11/2005;
  • Xiaoyong Du, Weidong Hu, Wenxian Yu
    [Show abstract] [Hide abstract]
    ABSTRACT: With the application of regularization, sparse component analysis (SCA) becomes an effective approximate method for finding the sparsest solution of signal decomposition in an overcomplete dictionary. In this paper, the authors present some conditions on a family of regularization functions indexed by a hyperparameter so that these functions are applicable and can be effectively optimized in SCA. For a given signal, with these conditions it is proven that there exists at least one hyperparameter such that the global minimum of the corresponding regularization function can theoretically lead to the sparsest representation of the signal. Based on these propositions, a general principle is presented for the construction of regularization functions, and several kinds of function families are recommended for the purpose of sparse signal representation. The paper gives a numerical example that indicates that, for a synthesized signal, minimizing the regularization function proposed in this paper provides the correct sparse solution, whereas the method of basis pursuit fails.
    Circuits Systems and Signal Processing 01/2005; 24(4):315-325. · 0.98 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper researches on the method of situation assessment for the air combat based on the Bayesian networks technology. It analyzes the events occur in the process of air combat, and presents a hybrid method of fuzzy sets and Bayesian networks to detect these events. Then, it presents a method to construct Bayesian networks using the events and then uses the networks to reason the purpose of enemy fighter pilots. Finally, it shows the method by an illustrative example.
    Proc SPIE 01/2005;
  • [Show abstract] [Hide abstract]
    ABSTRACT: The hierarchical relationship and the objective patterns of subclassifiers is the primary difficulty to construct a hierarchical classifier. In order to solve this problem, firstly, the confusion relationship between patterns has been defined to describe the interweaving effects of patterns in the decision domain. Then a measurement of the relationship has been proposed by utilizing the confusion matrix. Abiding by the Fisher Principle, a multipattern confusion relationship analysis machine (MPCRAM) has been designed to adaptively construct the structure of a hierarchical classifier. Various data scenarios have been used to compare the hierarchical structures generated with the MPCRAM and the conventional ways. The results have testified that MPCRAM was effective, and it could prominently improve the performance of a hierarchical classifier.
    Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on; 01/2004

Publication Stats

10 Citations
4.45 Total Impact Points

Institutions

  • 2011–2012
    • Shanghai University
      • Department of Electronic and Information Engineering
      Shanghai, Shanghai Shi, China
  • 2005–2009
    • National University of Defense Technology
      • College of Electronic Science and Engineering
      Ch’ang-sha-shih, Hunan, China