Table of Content

12 November 2015, Volume 0 Issue 11

Previous Issue    Next Issue

A Novel Fuzzy C-Means Algorithm Based on k-d Tree

WU Fei, MAO Yu-guang

2015, 0(11):  1-5+11.  doi:10.3969/j.issn.1006-2475.2015.11.001

Asbtract ( 295 )  

References | Related Articles | Metrics

Abstract: The performance of the Fuzzy C-Means(FCM) algorithm largely depends on the selection of the initial cluster center. A set of good initial cluster centers which are close to the actual final cluster center will not only speed up the rate of convergence but also reduce the overall processing time of the FCM dramatically. In this paper, we propose a novel FCM algorithm based on k-d tree which is a kind of multidimensional binary tree. The original data sets are split into several grids by using k-d tree. Then we form a new simplified data set by using the weighted centers of the grids, and based on which we find a good initial cluster center that is close to actual final cluster center so that reduce the iterations of FCM signally. The experiments on sixteen artificial datasets and real-life image data show that comparing with original FCM algorithm, the convergence rate of the proposed algorithm is advanced nearly twice as FCM algorithm, and the overall processing time reduce to less than half of the FCM.

Application of Nearest Base Station Suggestion Method in Base-station Position's Correction#br#

FENG Li-rong1,2, PENG Yan-bing2, YANG Mei-zhen3

2015, 0(11):  6-11.  doi:10.3969/j.issn.1006-2475.2015.11.002

Asbtract ( 226 )  

References | Related Articles | Metrics

Abstract: With the rapid development of the mobile networks and intelligent terminals, locationbased service has become one of hot topics on the internet, therefore the accuracy of the base station's position becomes a critical factor. For the wrong base stations or the unknown base stations, a new corrected algorithm-NBSS(Nearest Base Station Suggestion Method) is proposed. Firstly, it mainly does a filter on the data preprocessing and timestamp. Secondly, according to the continuity feature of time, combining with the location information uploaded by the users' mobile terminals' App, the track of the base stations in a short dynamic time is gotten. Finally, referring to the position characteristics of the base stations, it could give the suggested value of the wrong base stations or the unknown ones, and obtain the true latitude and longitude of stations though field trips. After field tripping base stations, compared the true value with NBSS corrected one, the results show that the NBSS algorithm has low complexity and its positional accuracy meets the requirements of most wireless applications.

Research and Application of Data Warehouse Based on Pentaho

FAN Xin1， HE Zhong-wei1， ZHANG Su-wei2

2015, 0(11):  12-16+112.  doi:10.3969/j.issn.1006-2475.2015.11.003

Asbtract ( 287 )  

References | Related Articles | Metrics

The hidden value of data not only determines the fate of the enterprise itself, but also carries the future direction of the whole industry. Under the background of big data era, whether the development of the company or government management, building a data warehouse to themselves is particularly important. Based on the Zhongguancun data fusion center platform, the paper expounds the key technology points of building the Pentaho management system which mainly includes the design of the data warehouse, ETL design of data collection process, OLAP design of data analysis process and report design in the data display process.

Method of Predicting Water Level Based on Similarity Search

HUANG Zheng, XIAO Yan

2015, 0(11):  17-21.  doi:10.3969/j.issn.1006-2475.2015.11.004

Asbtract ( 276 )  

References | Related Articles | Metrics

Abstract: Combining similarity search with neural network, a method of predicting water level was proposed. We calculate similarity distance of water level series between fifteen days before predicting day and months of forty-nine years before predicting year whose hydrological characteristics was similar to predicting months, then seek the most similar water level series of each year. Lastly, the most similar series of forty-nine years and the water level after the last day of them were used as training set of BP neural network. The experimental results show that predictions of the method combining similarity search with BP neural network are more accurate and their fluctuations are within the scope permitted by state.

Research on Discourse Partition of Fuzzy Time Series Models

WANG Yang1,2, CHEN Hai-yan1,2, PENG Yan-bing1,2

2015, 0(11):  22-26+121.  doi:10.3969/j.issn.1006-2475.2015.11.005

Asbtract ( 284 )  

References | Related Articles | Metrics

There are two research directions on it, one is discourse partition, and the other is fuzzy relations. Firstly, aiming at the problem of fuzzy time series model of multi-scale ratio existing in the theory of discourse partition method, the paper puts forward a method that uses relative error of the geometric average adjacent data instead of the arithmetic mean, in order to improve the precision of fuzzy intervals and the accuracy of prediction. Secondly, if the periodic time sequence using observations of continuous time to represent the fuzzy logic relation will exist a lot of prediction error, the paper comes up with using cycle as the interval of time series observation value indicates the fuzzy logic relationship. This method not only simplifies the fuzzy relationship matrix, but also reduces the algorithm complexity. Finally, the effectiveness of this method through Chongqing Net Bars traffic forecast is demonstrated in the paper.


Software Fault Localization Based on Genetic Neural Network

LYU Qiong-shuai, SHAN Dong-hong, SHEN Yuan

2015, 0(11):  27-31.  doi:10.3969/j.issn.1006-2475.2015.11.006

Asbtract ( 239 )  

References | Related Articles | Metrics

Software fault localization accuracy helps to improve software debugging efficiency. According to the analysis of software runtime information, a method is proposed to improve the accuracy of software error locating by using genetic neural network. First, the information is collected and encoded while the program is running. The encoding is considered as a genetic neural network training data set. Then, building a virtual test set, the program statement suspicious degree is calculated according to the virtual test set and the software error is positioned according to the size of the suspicious. Finally, this paper conducts on the Siemens Suite of 132 programs with injected bugs. The experimental results show that the genetic neural network can improve the accuracy of locating software faults to some extent and is helpful for software debugging.


Target Allocation Method of Multi-UAV Cooperative Task Based on PSO

WEI Cheng-wei, PEI Yi, LIU Dong-sheng, WANG Wei-ping

2015, 0(11):  32-35.  doi:10.3969/j.issn.1006-2475.2015.11.007

Asbtract ( 270 )  

References | Related Articles | Metrics

Based on analysis of UAV collaborative features and a variety of task allocation algorithm, using discrete PSO, the multi-UAV task allocation problem is solved. This article analyzes the principle of PSO method and gives the solving process. Computer simulation of a simple multi-UAV collaborative problem verifies the validity of PSO.

Automatic Meter Reading Task Scheduling Algorithm Based on Site Applicability Strategy

HUANG Guo-bing1, LIN Yuan2, JIN Yong1

2015, 0(11):  36-39+46.  doi:10.3969/j.issn.1006-2475.2015.11.008

Asbtract ( 249 )  

References | Related Articles | Metrics

Aiming at the question about billing information reading being out of sync which was caused by the unreliable communication connection between automatic meter reading system and energy remote terminal unit, and the problem on applicability of the products caused by various users’ requirements, an automatic meter reading task scheduling algorithm was developed based on site applicability strategy. Through analyzing users’ requirements, the meter reading strategy man-machine interface was designed to set and submit themselves strategy according to actual ones. A task  cheduling algorithm with priority was developed which can adapt users’ demand. This algorithm could schedule task table with priority to achieve the goal of meter reading which was generated by distinguishing meter reading strategy submitted by users automatically and retrieving calling progress of history information and accepting manual call commands. The engineering application shows that various users’ requirements could be met by this algorithm, integrity and traceability of billing information could be protected by supplementing to call the lost information automatically and manually.

Design and Implementation of M Template’s Software of Graphical Remote Terminal Unit in Electric Power Dispatching System#br#

HUANG Xia, HUANG Guo-bin

2015, 0(11):  40-46.  doi:10.3969/j.issn.1006-2475.2015.11.009

Asbtract ( 225 )  

References | Related Articles | Metrics

Meeting nation grid company formulation’s claim about smart grid construction, distributed open system architecture is adopted. Substation monitoring system gradually puts monitoring center with remote terminal unit together, which uses embedded system to sample electrical parameters and concludes data acquisition, remote function, selfdiagnosis, selfhealing, independent communication and other functions. This graphical remote terminal unit entirely meets abovementioned claim designing. This equipment adopts software and hardware’s configuration according to the actual industrial site, adding in conditions figure display and monitoring function of the master dispatch center, having the event monitoring alarm function. The M template software adopts C language as the development tool, includes two modules real time mutitask software and graphic production software.

WLANs Optimization Algorithm Based on Channel Assignment and Power Control

WANG Hao, LYU Yun-fei, CHEN Yuanbao, PENG Yun-fei

2015, 0(11):  47-52.  doi:10.3969/j.issn.1006-2475.2015.11.010

Asbtract ( 191 )  

References | Related Articles | Metrics

Without modifying the current IEEE 802.11 protocol, a novel heuristic algorithm based on proportional fairness optimization of Channel Assignment and Power Control is proposed to improve the performance of largescale wireless local area networks (WLANs), maximizing the effective bandwidth, while ensuring the fairness for each user to access the WLAN. Based on the traffic characteristic analysis from real network, we take both uplink and downlink traffic into account in the process of network modeling. The analysis towards network utility shows that it has a controllable upper bound. This characteristic helps us develop a strategy to improve network utility by maximizing the upper bound, and then forcing network utility approximate to the enhanced upper limit. In particular, both channel assignment (CA) and power control (PC) are performed in each iteration of the proposed algorithm. Extensive simulations show that the proposed algorithm outperforms current popular onedimensional optimization algorithms LCCS/PCAP, and compared the results in the aspect of increasing throughput, it reduces network delay.

Responsive Web Design for Small and Medium Enterprises Website

LUO Yu-dong, CHEN Wei-jun, LIU Xiu-zhan, LIU Hong-wei

2015, 0(11):  53-55+59.  doi:10.3969/j.issn.1006-2475.2015.11.011

Asbtract ( 198 )  

References | Related Articles | Metrics

An emergent architecture called “Responsive Web Design” has spawned by the high-speed growth of mobile Internet. First the principles of Responsive Web Design using in some mainstream Web portal were introduced. And then to enhance the user experience of “the new starting cram school” website, some of Responsive Web Designs have been applied in this website selectively. Compared to the traditional APP development, Responsive Web Design technique can be applied in the original MVC system seamlessly, which reduces the requirements for developers, improves the efficiency of Web development, and reduces the cost of maintenance.


Gesture Recognition in Multiple Scenarios Based on Kinect

MENG Xian-wei, HUANG Wen-pei

2015, 0(11):  56-59.  doi:10.3969/j.issn.1006-2475.2015.11.012

Asbtract ( 343 )  

References | Related Articles | Metrics

 Aiming at the gesture recognition problem in mutiplayer scene, this paper introduces a method combining a key bone pivot position, the human body gestures divide into segments of coherent actions for timely capturing and releasing mobile user scenario, and the experiment proves that the method can improve the recognition rate of gestures.

Visual Inspection Based on Intelligent Feedback Coupling PLC

LI Hua-chang

2015, 0(11):  60-64.  doi:10.3969/j.issn.1006-2475.2015.11.013

Asbtract ( 247 )  

References | Related Articles | Metrics

Visual inspection has widely existed in manufacturing demand. And there exist two problems, one is that the light environment of instability will affect the accuracy of image processing algorithm and the other is that interaction of hardware organization and visual software is often difficult, thus affecting the visual detection function implantation. Therefore, this paper presents a vision detection system based on intelligent feedback coupling PLC, which is implemented in software and hardware integration. Firstly the images of great light and shade change and the traditional method based on gray level are analyzed; and then an algorithm of real-time feedback and threshold intelligent adjustment is put forward, and programming based on the multi-thread is achieved. In the interaction of mechanism with the software, ModBus protocol is analyzed firstly, and then based on VC, the communication of visual software with PLC is realized. Finally, the performance of mechanism is tested, the results show that the mechanism is of high precision compared with the traditional image processing method, and realizes the interaction of hardware and software at the same time.

Application of Visual-Label in Detection of Plant Leaves'Wilt

YU Kai1, LI Qing-wu1,2, QIU Chun-chun1, CAO Mei1, ZHU Jian-chun3

2015, 0(11):  65-68+73.  doi:10.3969/j.issn.1006-2475.2015.11.014

Asbtract ( 229 )  

References | Related Articles | Metrics

Visual-Label is a novel concept of Intelligent Vision Internet of Things, which is widely used in areas such as face recognition as well as license plate recognition. However, application of plant's visual-label is hot and difficult in intelligence research area. So, a method for extracting feature vectors of the neighborhood of corner points, combined with value of local binary patterns used to establish the visual-label for plant leaves is proposed. Firstly, we detect the corners of different states of plant leaves, extract the value of local binary patterns as the center of the corners and calculate its neighborhood gradient vector, and then assign gradient direction and right weight to get an eighteen-dimensional feature vector. Finally, we calculate the angle of feature points feature vectors between the different leaves which have the equal values of local binary patterns. Matching plant leaves by the value of angle, which judges the state of plant leaves. This feature works well for the plant visual-label and is of good robustness for the blight caused by plant diseases and insect pests and the rotation of the blade.

Face and Speech Recognition Fusion Method Based on Penalty Coefficient

WEN Miao-i1,2

2015, 0(11):  69-73.  doi:10.3969/j.issn.1006-2475.2015.11.015

Asbtract ( 265 )  

References | Related Articles | Metrics

The quality of biometric sample acquired from different acquisition devices is higher, then the reliability of recognition is higher. For the same biometric sample, recognition method is better, then the reliability of recognition is higher. So this paper proposes a multi-biometric recognition algorithm using biometric sample quality and recognition expert reliability (QSVM). First, the method obtains the sample penalty coefficient and reliability penalty coefficients from the sample quality and the expert reliability, then deduces the overall penalty coefficient, finally, uses the overall penalty coefficient to modify SVM fusion recognition algorithm. The experiment uses the XM2VTS database. We compares the Half Total Error Rate (HTER) of QSVM, Bayesian, Fisher linear discriminant, multi-layer perceptron, mean methods and SVM, the experimental results show that the HTER of QSVM fusion algorithm is lower.


Images Registration of Breast DCE-MRI by Markov Random Field

YU Li-ling1，XU Bin-feng1，JIN Hao-yu1，YANG Wei2

2015, 0(11):  74-78+83.  doi:10.3969/j.issn.1006-2475.2015.11.016

Asbtract ( 192 )  

References | Related Articles | Metrics

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) suffers artifact by patient motion during the imaging procedure. It is necessary to correct patient motion effect by deformation registration for DCE-MRI. To make use of the prior knowledge of enhancement in space-time, we present the deformation field which is described by free deformation model based on B-spline and the displacement field of free-form deformation control points, and model by the Markov random field (MRF) model. We adopt the residual complexity (RC) based on the Gaussian kernel as the image similarity measure. The optimization of discrete MRF energy is quickly completed by Fast-PD algorithm, which can achieve the solution of deformation field. Finally, the solution of deformation field is used to correct the motion of time sequence images. The experimental results on synthetic and real images demonstrated the proposed method could provide high registration accuracy.


A Conflict Alert Algorithm Based on ADS-B Information

ZHANG Zhong-guang, SHI Hong-wei

2015, 0(11):  79-83.  doi:10.3969/j.issn.1006-2475.2015.11.017

Asbtract ( 233 )  

References | Related Articles | Metrics

Abstract: To solve the problem of flight safety that the sustained and rapid growth of air traffic flow leads to, the paper gives a conflict alert algorithm based on ADSB information. The purpose of the algorithm is to find the flight collision which may occur in terminal area or near the airport, and then to provide sufficient time for pilots to take avoiding action. The algorithm is mainly constituted by two models. The first model is flying conflict zoning model which contains the two regions of protected airspace (PAZ) and conflict airspace (CAZ). The second model is the flight conflict detection model which firstly primaries the conflict goal, then detects the possible conflict from both vertical and horizontal directions and issues the appropriate warning information based on the detection result. The large number of MonteCarlo simulation results show that the algorithm is of good performance, the flight conflicts can be effectively found in time, which is of great significance to ensure the security of terminal area or near the airport.

Keyframe Extraction System Based on Underwater Video Defogging

PENG Hai-qiang, LIAO Hua-li

2015, 0(11):  84-88.  doi:10.3969/j.issn.1006-2475.2015.11.018

Asbtract ( 207 )  

References | Related Articles | Metrics

Abstract: In order to overcome the video data redundancy and image haze in the video capture process during the underwater detection, this paper designs a keyframe extraction system taking into account the video frame content and extract amount. The original detective image is enhanced by using the Image Dehazing Algorithm based on Dark Channel Prior. The improved key frame extraction algorithm based on sampling interval and image similarity is used for keyframe extraction after the original image enhancement. The image stitching method is used to test the reliability of extracted key frames. Experimental results show that the amount of key frames is significantly reduced comparing to the original data, and effectively reflects the main information for the entire detective process.

3D Visualization Information Management System of Channel and Ship Based on OSG

HE Kun-jin1, ZHANG Li-jun1, LI Qiang1, LIU Jian-xin2

2015, 0(11):  89-92.  doi:10.3969/j.issn.1006-2475.2015.11.019

Asbtract ( 273 )  

References | Related Articles | Metrics

Abstract: In view of the problem that 3D visualization interaction pattern is difficult to support the channel and ship information management at present, this paper researches a 3D visualization information management system, which combines with the realtime presentation of dynamic 3D scene, the information management of scene object as a whole oriented channel and ship management. Firstly, based on the existing 3D scene which contains static channel and moving ships, 3D visualization scene is constructed. Secondly, this paper establishes a static information database describing waterway and ship objects, and a dynamic database expressing ship's motion and water level's changes. Finally, it also shows us some functions on 3D platform, such as supporting information bidirectional query of scene’s objects and their attributions, data update. Examples show that the constructed system of this paper effectively makes the management of channel gate section with visualization and informazation.


Lightweight Heterogeneous Data Integration Method Based on XML Schema

LI Zong-hua, ZHANG Lei

2015, 0(11):  93-98.  doi:10.3969/j.issn.1006-2475.2015.11.020

Asbtract ( 254 )  

References | Related Articles | Metrics

 Data integration method such as data warehousing and federate database is of typical complexity and excessive cost. A lightweight data integration method based on XML Schema is designed, which consists of application service layer, data service interface layer, data integration layer and database system layer. The design process of data sources object description model, global data object description model, semantic representation and reception of data query model, and data services interface model are introduced. Finally, achievement of data integration method is illustrated.


An Enhanced Method of Color Image Based on NSCT and PCNN

DUAN Qun, HAN Li-na

2015, 0(11):  99-102+108.  doi:10.3969/j.issn.1006-2475.2015.11.021

Asbtract ( 286 )  

References | Related Articles | Metrics

Abstract: This paper presents a new enhanced method of color image based on Nonsubsampled Contourlet Transform (NSCT) and Pulse Coupled Neural Networks (PCNN), according to the porceptual character of human visual system in HSV space. First, luminance V is decomposed to low frequency coefficients and high frequency coefficients by NSCT, the low frequency coefficients are enhanced by PCNN and corrected, the high frequency coefficients are linear transformed and inverse NSCT is performed to reconstruct the enhanced luminance V. Then, the saturation S is slightly enhanced by power to increase image contrast. Last, the color image is transformed from HSV color space to RGB color space. Experiments illustrate that the proposed method can retain a visual quality and objective evaluation index, this algorithm can not only correct nonuniform illumination in images, but also maintain a good image color and the local details.

Analysis and Comparison of Mainstream Code Generation Method

ZHANG Yan-wei, CHEN Zheng-ming, LYU Jia, ZHANG Xia

2015, 0(11):  103-108.  doi:10.3969/j.issn.1006-2475.2015.11.022

Asbtract ( 233 )  

References | Related Articles | Metrics

 For the problems, such as the long cycle of software development, the gradual increasement of software cost and rewriting code, code generation technology is a feasible approach. This paper not only exposited the basic principle and characteristics of code generation, but also analyzed and summarized domestic and foreign code generation methods. Taking a game scene as an example, three mainstream methods were implemented respectively, their advantages and disadvantages were analyzed sequentially. The future trends of the code generation technology were prospected at the end of the paper. All of these would provide some reference for the future work.

Application of Virtualization Technology in Experiment Teaching

CAI Dong-jiao

2015, 0(11):  109-112.  doi:10.3969/j.issn.1006-2475.2015.11.023

Asbtract ( 247 )  

References | Related Articles | Metrics

The advantages of virtualization technology are introduced. Taking the application of VMware Workstation as an example, several kinds of patterns of building virtualization network are expounded. Through the typical cases in experiment teaching, it is pointed out that constructing a virtual teaching environment for experiments by using virtualization technology can increase students’ practice opportunities, facilitate teacher to demonstrate the experiment teaching contents, greatly enhance the teaching effects and improve the utilization of experimental computer room.

Application of Improved Ant Colony Optimization Algorithm in Equipment Support Route Selection

CHEN Man-qing1, WU Zi-rong1, CUI Wei-ning1, CHANG Ting-ting2

2015, 0(11):  113-117.  doi:10.3969/j.issn.1006-2475.2015.11.024

Asbtract ( 221 )  

References | Related Articles | Metrics

At present, many of supporting units are based on artificial decision when they deployed resources of equipment support. Using the experience, route is chosen and a security scheme is formed. But artificial decision-making is not scientific, the path is not optimal and the scheme is unreasonable. According to the above conditions, this paper uses ant colony algorithm to experiment with different parameter values, and puts forward the best solution, optimizes route selection in the allocation of resources, then improves the basic ant colony algorithm. The experimental comparison results show that the improved ant colony algorithm can reduce the delay and improve the efficiency of the route optimization.

A Comprehensive Evaluation Method for Network Courses Learning    ——A Case Study on College English Network Course Teaching

WEI Bin1, ZENG Qing-song2

2015, 0(11):  118-121.  doi:10.3969/j.issn.1006-2475.2015.11.025

Asbtract ( 268 )  

References | Related Articles | Metrics

Abstract: Evaluation of network study result is the fundamental job in network course teaching. In this paper, a mathematical model of evaluation of network course learning effect was proposed based on fuzzy entropy theory. Each evaluation index is weighted by its entropy. Combined with the subjective weighting, we obtain the comprehensive weighting. This paper establishes the evaluation index system of college English online course learning. It improved the disadvantages of traditional evaluation methods. It is easy to extend the application to other courses by defining additional evaluation index system. The experimental results verified the feasibility of this method.


Design and Implementation of Smart Home Based on Android Platform

WU Zhi-hua1, WANG Xiao-long2

2015, 0(11):  122-126.  doi:10.3969/j.issn.1006-2475.2015.11.026

Asbtract ( 237 )  

References | Related Articles | Metrics

 In view of the complicated operation and  lack of a good user experience of smart home control system, this paper proposes a low-cost, easy to operate and suitable system for home appliances control. A set of intelligent household mobile client-system is designed and implemented based on Android platform, which uses Socket communication technology to realize data communication and XML file to store the results of data operation and home appliance equipment information. The Smart Home system realizes the control of household equipment and the real-time monitoring of family environment, which can be used in residential home, hotels and other places. Results show that the system hardware is of low cost, and strong extensibility, stability and reliability.