Most Down Articles

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

A segmentation method for wheat leaf images with disease in complex background   ZHANG Wu,HUANG Shuai,WANG Jingjing,LIU Lianzhong J4    2015, 37 (07): 1349-1354.   Abstract （584）      PDF （762KB）（189706）       Knowledge map    According to the properties of wheat disease (wheat stripe rust and wheat leaf rust) images in complex background, we propose a segmentation method based on the Kmeans clustering segmentation method and the Otsu threshold algorithm. The proposed method is comprised of three main steps. Firstly, by utilizing the difference between the background and the a*b* of leaves, the k-means clustering segmentation method deletes the irrelevant background. Secondly, we use the Otsu dynamic threshold segmentation method to perform binarization and combine the mathematical morphological method with the area threshold method to separate the wheat leaf image with disease from the complex background. Finally, the Kmeans segmentation method is used again and eventually the disease spot of the image is divided. Experimental results show that the correct extraction rate can reach 95%, and it can segment the diseased regions from the whole color image  with good robustness and good accuracy, thus offering an effective method for wheat disease detection and diagnosis. Reference | Related Articles | Metrics

Select

Chinese textual contradiction recognition based on semantic rules  LIU Maofu，WANG Yue，GU Jinguang J4    2015, 37 (04): 806-812.   Abstract （321）      PDF （4072KB）（100183）       Knowledge map    Text entailment is foundational for text understanding and semantic inference,and recently it has attracted considerable attention in the computational linguistics community.Text contradiction is a negation of text entailment and both of them are the key aspects of semantics.In this paper,we aim to address the problem of textual contradiction detection on the basis of textual entailment,and a textual contradiction recognition approach based on semantic rules is proposed to tackle this problem.Experimental results demonstrate the effectiveness and feasibility of the textual contradiction recognition approach,which can also significantly improve the performance of textual entailment recognition. Reference | Related Articles | Metrics

Select

An improved simulated annealing algorithm for program optimization parameters search    LU Pingjing,LI Bao,YI RenJiao,ZHANG Ying,Wang Shaogang,PANG Zhengbin J4    2015, 37 (07): 1227-1232.   Abstract （384）      PDF （751KB）（98336）       Knowledge map    High level program transformations are critical to improve applications’ performance,many of which mainly concern the determination of optimal transformation parameters, such as loop blocking.Since optimization parameter search problem is featured NP-hard,to date,no one can find any deterministic algorithms to efficiently solve this problem.Considering it as a nonlinear global optimization problem,we introduce an improved simulated annealing algorithm to find the optimal parameters.Several comparative experiments demonstrate the performance and effectiveness of the new method. Reference | Related Articles | Metrics

Select

Risk assessment selection based on static Bayesian game         YU Dingkun，WANG Jindong，ZHANG Hengwei，WANG Na，CHEN Yu J4    2015, 37 (06): 1079-1086.   Abstract （275）      PDF （769KB）（89158）       Knowledge map    Nowadays,most studies of risk assessment methods based on game theory use complete information game model.These models cannot deal with the situation in which the attacker and the defender do not know each other’s actions.In this paper we establish an attackdefense model based on static Bayesian game theory to categorize the attacker and the defender into different types.Then,we analyze the Bayesian equilibrium of the game comprehensively,and improve the taxonomy and cost quantitative method of the classical strategies with consideration of the strike back acts of the defender and the success rate of attacks.Under the premise that the actions of the attacker are predicted based on game equilibrium,we use the risk calculating algorithm to calculate the risk in the information system. Simulation results  prove the effectiveness of the proposed model and the algorithm. Reference | Related Articles | Metrics

Select

Design and implementation of a new user recommendation algorithm based on Mahout   GAO Xianwei,SHI Zhibin J4    2015, 37 (08): 1444-1449.   Abstract （214）      PDF （747KB）（87194）       Knowledge map    Recommendation for new users in big data era is difficult and the efficiency is very low due to the lack of historical data. In order to solve these problems, we propose a new user recommendation algorithm, which combines the collaborative filtering algorithm based on the Mahout and the Top N algorithm based on the MapReduce. We build a new user recommendation system architecture, design and implement the Hadoop Top N algorithm and the collaborative filtering algorithm in the Mahout. Theoretical analysis and experimental results show that the proposed recommendation algorithm for big data processing has better recommended efficiency, scalability and quality than  the collaborative filtering algorithm. Reference | Related Articles | Metrics

Select

Survey on topic-focused crawlers  YU Juan，LIU Qiang J4    2015, 37 (02): 231-237.   Abstract （383）      PDF （487KB）（53289）       Knowledge map    With the exponential growth of network information resources and the growing personalized demands of customers, topicfocused crawler emerges as the times require. Topicfocused crawlers are programs designed to download web pages which are relevant to specific topics. Using information gathered at running time, topicfocused crawlers explore the webs which follow promissory hyperlinks, and fetch only pages which appear to be relevant. The searching engine and corpus building based on topicfocused crawling have been widely used. We first define the goals and operating principles of focused crawling, comprehensively analyze the recent advances at home and abroad, and then compare the crawling strategies of various topicfocused crawlers as well as the advantages and disadvantages of related algorithms. Finally, we point out the future direction of topicfocused crawling. Reference | Related Articles | Metrics

Select

Application research of neural network ensemble method based on improved clustering analysis  YANG Hongbo1,ZHENG Jian2 J4    2015, 37 (05): 974-978.   Abstract （208）      PDF （517KB）（48276）       Knowledge map    With the expansion of industrial production scale and the increasing complexity of production process,demands  for process simulation are increasing. In the paper, we propose an improved clustering analysisbased neural network ensemble method.Firstly,according to the density distribution of data,an improvement in Kmeans method is made to overcome the disadvantage in the selection of the original central point，and then the samples are classified and the differences among the samples are enlarged.Secondly,aiming to the different samples, the general regression neural network (GRNN) with fast learning ability is used to construct and train individual neural networks.Thirdly,a compensation network is constructed for all the samples by GRNN so as to eliminate the output errors due to false selection.Finally,the obtained clustering center is utilized to make numerical analysis for the input samples and to select the individual neural network.The output of the selected individual neural network is compared with the output of the compensation network,and the neural network ensemble is realized.The verification on artificial data Sinc illustrates that the model accuracy is enhanced by the proposed method.Thus,it provides a new way for increasing the accuracy of process simulation. Reference | Related Articles | Metrics

Select

An ear recognition algorithm based on Gabor features and improved LDA    HU Chunan，CHEN Yuling J4    2015, 37 (07): 1355-1359.   Abstract （192）      PDF （478KB）（46670）       Knowledge map    We propose a novel ear recognition algorithm based on Gabor features and improved LDA to deal with the inevitable problem of small sample size.We firstly extract ear features by the local Gabor filter,and redefine the new Fisher criteria and the intra class scatter matrix.Then we seek the optimal projection direction by mapping from a higherdimensional space to a lowerdimensional space,Finally we make a comparison of the Euclidean distance of projecting feature vectors  between the training samples and the testing samples,and classify them accordingly. Experimental results show that, compared with the traditional methods, the proposed algorithm can effectively solve the small sample size problem in ear recognition with a higher recognition accuracy. Reference | Related Articles | Metrics

Select

A survey of the parallel solutions to convection-diffusion equation   GONG Chunye,BAO Weimin,LIU Haidong,YU Caihui,FANG Hong,ZHENG Zhaohu,WANG Li J4    2015, 37 (04): 628-633.   Abstract （451）      PDF （528KB）（37526）       Knowledge map    The convection-diffusion equation is a typical partial differential equation. Its parallel solutions have reference significance for the parallel solutions to other equations. In this paper we conduct a survey on the parallel solutions to convection-diffusion equation. These parallel solutions are classified as four kinds of parallelism: explicit direct, implicit iterative, alternating group explicit and Monte Carlo. Computational principles and several examples are described. Finally, the prospects of future development in this field are presented. Reference | Related Articles | Metrics

Select

Scheduling DAG-based tasks in distributed system：a survey          TIAN Guozhong1,2,XIAO Chuangbai1 J4    2015, 37 (05): 882-894.   Abstract （515）      PDF （889KB）（30781）       Knowledge map    In recent years, along with the development of the technologies for distributed computing, such as grid and clouds workflow systems, the problem of scheduling DAG-based tasks in distributed system environment has attracted intensive attention of researchers recently. According to the latest research progress,we explore the problem of scheduling DAG-based tasks in distributed system environment and related technologies.It includes the following four parts:(1) describing the related concepts on distributed systems and on heterogeneous distributed systems and demonstrating the problem of scheduling DAG-based tasks in heterogeneous distributed system environment,its model and its typical applications;(2) classifying the researches on scheduling DAGbased tasks according to different perspectives;(3) reviewing the previous researches on scheduling the shared heterogeneous distributed resources based on multiple DAGs;(4) discussing problems to be resolved regarding scheduling multiple DAG.Finally,we summarize the key points of this paper.   Reference | Related Articles | Metrics

Select

Improved dynamic loadbalancing strategy of web servers in virtual environment   LIU Shengnan1,WANG Shilin2 J4    2015, 37 (09): 1607-1613.   Abstract （422）      PDF （760KB）（27286）       Knowledge map    In order to improve the scalability and automation of web cluster servers, we study many cluster systems from the aspects of virtualization and load balancing, propose a load information collection algorithm based on the Xen server virtualization platform, design and implement a modeling system called XCluster which can automatically control the cluster scale according to the load status. A monitoring service in the new model collects and quantifies the loads of the hosts and active nodes in real time. VM controllers will be notified to deploy more VMs from an optimumload host when lightload nodes are in short supply; however, when there are too many lightload nodes, a number of VMs will be shutdown to release more hardware resources. Theoretical analysis and experimental results show that the XCluster can make full use of the unique capabilities of the virtualization platform which can manage all backend nodes in an economical way. By scheduling VMs, the clusters can avoid resource waste, yet maintaining the applications quality of service within an acceptable size. Reference | Related Articles | Metrics

Select

J4    2006, 28 (6): 71-72.   Abstract （543）      PDF （190KB）（4322）       Knowledge map    To guarantee the normal development of network application and crack down on network crimes, one ot the most important aspects is monitoring and restoring the bad real-time video information. A process and procedure of manipu lating the H. 264 coding is introduced,which can capture, restore and store the real-time video information, and convert the video frames captured into image files for special use. The results of the experiments show that both e fficiency and effect of the process are achieved. This paper is significant to distinguish the ill media information from the Internet. Related Articles | Metrics

Select

J4    2005, 27 (12): 68-71.   Abstract （645）      PDF （265KB）（4070）       Knowledge map    This paper analyzes and summarizes the previous definition of feature selection,and then introduces a self-contained definition. It divides feature se lection into three classes according to the selecting strategy, and categorizes the methods into five styles by the evaluation function. Through analyzi ng the infection factors in the feature selection technology,this paper introduces some principles to pave the way for practitioners who search for suit able features to solve real-world applications. Related Articles | Metrics

Select

J4    2006, 28 (2): 54-56.   Abstract （775）      PDF （213KB）（3998）       Knowledge map    Image enhancement which is also called image pre-processing plays an indispensable role m signal Image processing. This article introduces two kinds of algorithm-hlstogram equalization and histogram specifications, gives an experimental result based on MATLAB. From the relevant images and histograms of realization, it is clear that histogram enhancement can improve the contrast details and equalize the dynamic range of image gray level. Related Articles | Metrics

Select

J4    2008, 30 (2): 72-74.   Abstract （842）      PDF （229KB）（3715）       Knowledge map    The traveling salesman problem （TSP） is a typical combination optimization problem, and possesses a practical application value. However, there is no effective corresponding solution to it today. So, in this paper, the traditionally affirmative methods and popular meta-heuristic methods are discussed. The advantages and disadvantages of each method are discussed. The future research direction of the TSP problem is also given. Related Articles | Metrics

Select

J4    1991, 13 (2): 26-31.   Abstract （451）      PDF （198KB）（3602）       Knowledge map    Related Articles | Metrics

Select

J4    2006, 28 (2): 41-44.   Abstract （597）      PDF （313KB）（3161）       Knowledge map    Starting from the observation and research results of oceanography, combining wttta the 3D Gerstner waves model, we present a Gerstner waves model under wind force based on spectrum. First, on the basis of analyzing all parameters of the Gerstner model, all parameters at a fixed speed can be obtained  from the spectrum, thus the basic ocean waves shape is constructed. Then, a wind model based on the spectrum is established to simulate ocean waves unde achieved. This method not only simulates ocean  waves more truly, but also has better interaction. Related Articles | Metrics

Select

J4    2008, 30 (8): 139-143.   Abstract （750）      PDF （357KB）（2823）       Knowledge map    With the SERDES data rate approaching 10 Gbps, the transmission technology of PCB, especially the multiboard transmission, has become more and more di fficult. Understanding, designing and simulating the PCB and its features as precisely as possible is essential for optimizing the complete signal path, and the very high-speed serial links can be achieved. This paper firstly analyzes the framework of SERDES, and then studies and models the key features of the high- speed PCB design. As a result , the multi-board transmission model is built by using the experimental PCBs, and the key SERDES network tra   nsmission on multi-PCBs are simulated and analyzed. Related Articles | Metrics

Select

Research on LargeScale Network  Topology Generation LI Jin, HUANG Min-Huan, KUANG Xiao-Hui, HU Fei, TANG Hong J4    2010, 32 (3): 11-13.   doi: 10.3969/j.issn.1007130X.2010. Abstract （693）      PDF （686KB）（2772）       Knowledge map    Network test environment is of great importance to the development of protocols and applications. Largescale network topology generation is one of the key technologies to construct a test environment. In this paper, we present a new generation framework VLTGF which divides the network topology into three hierarchies and contains the bandwidth assignment mechanism. The topologies generated by VLTGF are more complete and accurate. Related Articles | Metrics

Select

J4    2008, 30 (7): 40-46.   Abstract （612）      PDF （607KB）（2753）       Knowledge map    With the development of the synthetic aperture radar （SAR） technology, how to extract and interpret the SAR information is more and more important. The SAR target characteristics analysis for target recognition is studied in detail in the paper. Firstly, the factors which have effect on the SAR target characteristics are analyzed. Secondly, the SAR target characteristics analysis and feature extraction of small targets, line targets, and region tar   gets from SAR images are systematically summarized. Finally, the outlook of SAR target recognition is put forward. Related Articles | Metrics