Yong Zhang

HuaiHai Institute of Technology, Wu-hsien, Jiangsu Sheng, China

Are you Yong Zhang?

Claim your profile

Publications (12)2.76 Total impact

  • Yihua Lan · Yong Zhang · Haozheng Ren ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduced an even data distribution strategy in SAN. Even data distribution is always the target of distributed storage design. Many articles dedicate the purpose. We use size-based data placement here to guarantee the data distributed evenly at furthest. Size-based data distribution separates the SAN into zones, and each zone has some storage devices (SD), different sized data will fill into different zones. Two kind of allocating algorithms are used to keep the data distribute evenly: orderly and best fit first. Our design will achieve 1) the data will even distributed on each storage devices at furthest; 2) read and write requests will even access the SDs, and 3) bandwidth can be improved at our system. Experimental results showed our design can optimize data distribution.
    02/2013; 8(2). DOI:10.4304/jsw.8.2.426-434
  • Yihua Lan · Haozheng Ren · Yong Zhang · Chih-cheng Hung ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Multi-focus image fusion is one of the important embranchments of image fusion. It has been widely used in target identification, remote sensing image processing and so on. In this paper, a new multi-focus image fusion method based on multi-band vector wavelet is presented. Furthermore, some post processing is done in this paper, in which anisotropic diffusion arithmetic based on partial differential equations is used. As for the fusion image, the blocking effects which usually existed in the results are eliminated by using wavelet based image fusion method. To test and evaluate the proposed method, it is applied to a case study to demonstrate its performance in image fusion. Comparisons of experimental results by using several methods demonstrated the effectiveness of our proposed methods.
    01/2013; 8(1). DOI:10.4304/jsw.8.1.208-217
  • Yihua Lan · Yong Zhang · Haozheng Ren · Ming Li ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer is considered one of the most common diseases among the female population, and early detection and diagnosis is the only way to reduce the death rate. For the time being, mammography is recognized as the most effective means for detection of early breast cancer. However, reading mammograms is a different and time-consuming task. To improve the accuracy and efficiency of the radiologists in reading mammograms, a number of computer-aided detection and diagnosis (CAD) systems have been proposed and developed to assist radiologists to classify suspicious lesions. Decision making is an important step in almost all of the CAD systems. Most of CAD systems use single classifier for calculating the decision value to identify those suspicious lesions into mass or calcification, or normal tissue. There is not enough potential to improve the performance of CAD systems by using one single classifier. For complex classification task in mammography CAD, using multi-classifiers systems is an available approach to calculate more accurate decision value. In this paper, we proposed a decision making optimization method to improve the classification performance of CAD. To test and evaluate the proposed method, a number of experiments were conducted by using a large scale of image database which can be available publicly. Receiver operating characteristic (ROC) scheme was employed to analyze those different methods mentioned in this study. The proposed method achieved an Az value of 0.883 ± 0.009, which is higher than the two other methods. Statistical analysis was also performed. Experimental results demonstrate the efficacy of the proposed method.
    International Journal of Digital Content Technology and its Applications 11/2012; 6(20):343-351. DOI:10.4156/jdcta.vol6.issue20.37
  • Yong Zhang · Yihua Lan · Haozheng Ren · Ming Li ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Detection of visually salient image regions has been of great research interest in recent years. It is useful for a wide range of applications such as object detection, video summarization and object segmentation. In this paper, we propose a modified method based on frequency-tuned (FT) model for salient region detection that outputs full resolution saliency maps with well-defined boundaries of salient objects. For FT model, saliency is considered as a distance to the mean spatial frequency content that is too simple for complex scenes and inconsistent with our usual sense. Our modified model, which called as Robust FT, following the assumptions of salient region, can get better saliency maps. We consider the mean spatial frequency content as background and formulate a much more robust model to descript it. By practical experiments, it is verified that our model obtains better results than original methods.
    International Journal of Digital Content Technology and its Applications 11/2012; 6(20):361-369. DOI:10.4156/jdcta.vol6.issue20.39
  • Yihua Lan · Xiaopu Ma · Yong Zhang · Haozheng Ren · Chao Yin · Huaifei Hu ·

    International Journal of Digital Content Technology and its Applications 11/2012; 6(20):465-474. DOI:10.4156/jdcta.vol6.issue20.50
  • Yong Zhang · Yihua Lan · Haozheng Ren ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Breast cancer is a major health problem and continues to be the primary cause of death among women all over the world. Screening mammography is recognized the most effective method for its early detection. since reading mammograms is an error-prone and time-consume task, a number of computer-aided detection and diagnosis (CAD) systems have been developed to aid the radiologists in the complex work of discriminating types of breast lesions. in almost all of the CAD systems, segmentation of lesions is a very crucial step. Image enhancement which is as a pre-process can largely improve performance of segmentation algorithms. However, the effectiveness of improvements has not been quantized evaluated and compared in previous studies. in this study, we conducted a set of experiments to evaluated two methods, namely 2D segmentation method based on dynamic programming (DPA) and DPA with image enhancement method. the detailed description of our image dataset, experimental procedures and results are presented. the study demonstrates that due to the using of image enhancement, DPA has an obvious improvement in segmenting suspicious regions of interest (ROIs) in mammogrphic lesions.
    Proceedings of the 2012 Fifth International Symposium on Computational Intelligence and Design - Volume 01; 10/2012
  • Yihua Lan · Cunhua Li · Haozheng Ren · Yong Zhang · Zhifang Min ·
    [Show abstract] [Hide abstract]
    ABSTRACT: A new heuristic algorithm based on the so-called geometric distance sorting technique is proposed for solving the fluence map optimization with dose-volume constraints which is one of the most essential tasks for inverse planning in IMRT. The framework of the proposed method is basically an iterative process which begins with a simple linear constrained quadratic optimization model without considering any dose-volume constraints, and then the dose constraints for the voxels violating the dose-volume constraints are gradually added into the quadratic optimization model step by step until all the dose-volume constraints are satisfied. In each iteration step, an interior point method is adopted to solve each new linear constrained quadratic programming. For choosing the proper candidate voxels for the current dose constraint adding, a so-called geometric distance defined in the transformed standard quadratic form of the fluence map optimization model was used to guide the selection of the voxels. The new geometric distance sorting technique can mostly reduce the unexpected increase of the objective function value caused inevitably by the constraint adding. It can be regarded as an upgrading to the traditional dose sorting technique. The geometry explanation for the proposed method is also given and a proposition is proved to support our heuristic idea. In addition, a smart constraint adding/deleting strategy is designed to ensure a stable iteration convergence. The new algorithm is tested on four cases including head-neck, a prostate, a lung and an oropharyngeal, and compared with the algorithm based on the traditional dose sorting technique. Experimental results showed that the proposed method is more suitable for guiding the selection of new constraints than the traditional dose sorting method, especially for the cases whose target regions are in non-convex shapes. It is a more efficient optimization technique to some extent for choosing constraints than the dose sorting method. By integrating a smart constraint adding/deleting scheme within the iteration framework, the new technique builds up an improved algorithm for solving the fluence map optimization with dose-volume constraints.
    Physics in Medicine and Biology 09/2012; 57(20):6407-28. DOI:10.1088/0031-9155/57/20/6407 · 2.76 Impact Factor
  • Yihua Lan · Haozheng Ren · Yong Zhang · Hongbo Yu ·
    [Show abstract] [Hide abstract]
    ABSTRACT: To provide assistance for radiologists in mammographic screening, many computer-aided detection and diagnosis systems (CAD) have been developed. However, there are a lot of problems which should be addressed in conventional mammographic CAD system, such as the relatively lower performance in detecting malignant masses, especially those subtle masses. The reasons which caused those errors may be the black-box type approach, which only cuing those suspicious masses but it is different to explain the reasoning of the CAD decision-making. Mammographic CAD using content-based image retrieval is another new type of CAD which can provide visual assistance instead of the type of black box method in conventional CAD for radiologists. Unlike those conventional CAD, in content-based image retrieval (CBIR) CAD, several most similar regions of interest (ROIs) are provided to radiologists as well as the decision index (DI) of one ROI which being a positive region. It has been proved that this visual aid tool could improve radiologists' performance. At present, there are two common types of CBIR CAD based on the calculation of similarity between testing ROI and reference ROI, one is the multi-feature based methods, and the other one is pixel-value-based template matching methods. The typical techniques used in these two types of CBIR CAD are multi-feature-based K-nearest neighbor (KNN) and template matching based system using mutual information (MI). The objective of this paper is to evaluate the performance of those methods commonly used in CBIR and discuss the approaches to improve CAD performance.
    Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2012 4th International Conference on; 01/2012
  • Yihua Lan · Haozheng Ren · Yong Zhang · Hongbo Yu · Guangwei Wang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a non-symmetry and anti-packing object pattern representation model (NAM). The NAM model codes the geometry of generic object categories as a hierarchy of sub-patterns and each sub-pattern is represented by a rich set of image cues. The sub-pattern-based NAM model is designed to decouple variations due to affine warps and other forms of shape deformations. The combination of multi-feature is to deal with the local variation of object. We then train part classifiers. Based on this model, we apply a generalized Hough voting scheme to generate object locations and scales. The experimental results on a variety of categories demonstrate that our method provides successful detection of the object within the image.
  • Haozheng Ren · Yihua Lan · Yong Zhang · Xuefeng Zhao ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This article mainly study the application of the digital image process based on PDE. We present the concept and property of scale space, and give the relationship between continuous scale space and the PDE model, for example, the heat exchange equation ascertain the gauss scale space. Following with the simple linear diffusion equation, it introduces the nonlinear isotropic diffusion and the nonlinear an isotropic diffusion. It not only presents corresponding idiographic diffusion equation models, but also compares the different effects of them in image processing. This application begins with the method of energy analysis, then constructs variation problem, gets the original model at last. Besides, it improves the original model for the goal of noise-removing, edge enhancement, remaining the original image's information. The difficulty of image processing -- edge's noise-removing and blur-removing, will be answered preferably by this article. As the result indicates, the image processed by this method is quite notable in the aspect of SNR enhancement. This article analyses the function of each PDE's items in image processing from the mathematical view, by which we constructs the diffusion model which not only generates the new arithmetic in the article, but also paves the way for people's further research in this field.
  • Haozheng Ren · Yihua Lan · Yong Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Image fusion is one of the important embranchments of data fusion. Its purpose is to synthesis multi-image information in one scene to one image which is more suitable to human vision and computer vision or more adapt to further image processing, such as target identification. This paper mainly discusses the image fusion method based on wavelet transformation. Firstly, the article gives the basic concept of multi-focus image fusion. On top of this, the paper gives the theory of wavelet analyses and its fast arithmetic, hereon gives the image fusion method based on singe wavelet. Getting on with the single wavelet, the paper presents some improved wavelet as multi-wavelet, multi-band multi-wavelet, including their theories and their arithmetic of decomposition and reconstruction. At the same time, the article applies the multi-band multi wavelet in the image fusion with the wavelet fusion thought. In the side of selecting fusion arithmetic operators, the paper compares the methods based on pictures, windows and regions, and adopts the fusion norm based on grads and characteristic measurement of regional energy. Besides it compares images which is based on different fusion norms and different wavelets in the aspects of entropy, peak value Signal-to-Noise, square root error and standard error in the experimentation. By using Matlab as experimental platform, we approved the feasibility and validity of the method mentioned in the article through a lot of experiments. The result indicates that multi-band multi-wavelet is very effective in image fusion. Furthermore, the article does some post processing to the fusion image. The method is based on anisotropic diffusion arithmetic based on partial differential equations. The experiments show that the brim diffusion enhanced the PSNR of image with the selective brim diffusion to the fusion image and depressed the image block domino effects caused by wavelet fusion method.
  • Yihua Lan · Haozheng Ren · Yong Zhang · Hongbo Yu · Xuefeng Zhao ·
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature selection methods are critical in mammography computer-aided diagnosis and clinical decision support systems. However, searching for an optimal or near optimal feature subset is still a difficult task. After examining the problems with both filter and wrapper methods in feature selection, we propose a hybrid feature selection method using both Filter and Wrapper by taking advantage of both approaches in a content-based image retrieval computer-aided diagnosis. At first, we used step-by-step linear discriminative analysis (SLDA) algorithm, which belongs to filter approach, to remove irrelevant features, and then we used genetic algorithm (GA, wrapper approach) to remove useless features and achieve the ultimate feature subset. To test and evaluate the proposed method, we compared our method with using either GA or SLDA algorithm singly; the result is encouraging.
  • Jian Zhang · Xianyun Fei · Yong Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper is focused on the problem of selecting optimum discrimination eigenvectors of PCA and improving the recognition accuracy. A new method for face recognition based on PCA optimize strategy is presented, in which the PSO algorithm is embedded, which select the recognition accuracy as the fitness value of particle swarm, to find out the optimum discrimination eigenvectors of PCA and obtain the optimal recognition accuracy simultaneously. We validate the effectiveness of this method with the ORL database and the Yale database. The experimental results indicate that the method can obtain the optimum discrimination eigenvector of PCA and a major improvement on recognition accuracy compared with the eigenvector selection approach based on the energy accumulative contribution rate.
    2010 International Conference on Computer Application and System Modeling (ICCASM 2010); 10/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: A novel nanocrystal formulation of hydrophobic drugs has been developed for cancer therapy. The new method, called a three-phase nanoparticle engineering technology (3PNET), includes three phases: phase 1, amorphous precipitate; phase 2, hydrated amorphous aggregate; and phase 3, stabilized nanocrystal. The 3PNET has been applied to two anticancer drugs, paclitaxel (PTX) and camptothecin (CPT), using Pluronic F127 (F127) polymer as a single excipient. The nanocrystals encapsulated over 99% of the drug with a high ratio of drug to excipient. The nanocrystal formulation of PTX did not induce hemolysis at pharmacologically relevant concentrations. Antitumor activity in two tumor models, human lung cancer and murine breast cancer, demonstrated that intravenously injected nanocrystals significantly inhibited the tumor growth. The nanocrystals also showed significant therapeutic effects via oral administration. In addition, the nanocrystals could be further modified for targeted delivery of PTX by conjugating a folate ligand to F127. The new nanomedicine formulations show clear potential for clinical development because of the excellent antitumor activity, low toxicity, and the ease of scale-up manufacture. The formulation method may apply to other hydrophobic drugs.
    Journal of Pharmaceutical Sciences 08/2010; 99(8):3542-51. DOI:10.1002/jps.22112 · 2.59 Impact Factor
  • Mingliang Hou · Yong Zhang · Feng Liu · Jian Zhang · Liyun Su ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In order to overcome the deficiencies of poor adaptive capacity, lack of inspiration and narrow domain knowledge of expert system and fundamentally improve the diagnostic efficiency, an intelligent fault diagnosis expert system for photoelectric tracking devices, based on BP neural network, is put forward. Firstly, in this paper, some key basic concepts and principles of intelligent fault diagnosis technology are proposed. Secondly, according to the difficulty of multiple and coupling fault diagnosis, after making a comparative analysis of the related BP neural network algorithms, such as the quasi-Newton method, the stretch BP method and the conjugate gradient method, a neural network fault diagnosis reasoning method based on the Levenberg-Marquardt is designed, which combined the implementation of the diagnosis expert system. Finally, several interrelated essential implementation issues, such as the architecture of the system and the VR technology based on OpenGL, are also discussed. Practical experiments and applications demonstrate that the proposed approach is effective, robust and universal.
    Proceedings of SPIE - The International Society for Optical Engineering 05/2010; 7658. DOI:10.1117/12.865714 · 0.20 Impact Factor
  • Source
    Mingliang Hou · Cunhua Li · Yong Zhang · Liyun Su ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In view of the crucial deficiency of the traditional diagnosis approaches for photoelectric tracking devices and the output of more sufficient diagnosis information, in this paper, an virtual fault diagnosis system based on open graphic library(OpenGL) is proposed. Firstly, some interrelated key principles and technology of virtual reality, visualization and intelligent fault diagnosis technology are put forward. Then, the demand analysis and architecture of the system are elaborated. Next, details of interrelated essential implementation issues are also discussed, including the the 3D modeling of the related diagnosis equipments, key development process and design via OpenGL. Practical applications and experiments illuminate that the proposed approach is feasible and effective.
    Proceedings of SPIE - The International Society for Optical Engineering 10/2009; DOI:10.1117/12.834086 · 0.20 Impact Factor
  • Mingliang Hou · CunHua Li · Yong Zhang ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, a method for texture retrieval based on scale and rotation invariant directional empirical mode decomposition (SRIDEMD) is presented. Different from other filtering based techniques such as wavelet and Gabor decomposition, EMD uses the nonlinear filtering process called 'sifting' which attains its scalead aptivity and obtained intrinsic mode functions (IMFs) which has approximate orthogonality. We extend DEMD which is a fast technique of extending 1D EMD to 2D case by introducing scale and rotation invariance. Features including frequency and envelopes of IMFs are extracted after 2D Hilbert transform. Decomposition in several directions is made for rotation invariance and main direction is used. Scale-invariant features are attained by further processing the results and using fractal dimensions of the residues and IMFs. We validate the effectiveness of this method by experiments for textures from public texture database.
    8th IEEE/ACIS International Conference on Computer and Information Science, IEEE/ACIS ICIS 2009, June 1-3, 2009, Shanghai, China; 01/2009