Table of Content

10 October 2015, Volume 0 Issue 10

Previous Issue    Next Issue

Mixture Recommended Model of Temporal Context-based LDA and Collaborative Filtering

WEI Tong-tong, FENG Jun, TANG Zhi-xian, WANG Chun

2015, 0(10):  1-5+9.  doi:10.3969/j.issn.1006-2475.2015.10.001

Asbtract ( 290 )  

References | Related Articles | Metrics

The existing personalized recommendations often ignore the effect on the users’ behavior caused by the time information, resulting in a lower forecast accuracy. According to the user attribute information and user rating information, this paper sets up a mixture recommendation model (TLDA-CF) based on the temporal context-aware LDA model and collaborative filtering model. It improves the recommendation efficiency through offline and online recommendation; respectively establishes the LDA models based on the user rating information and the project’s access amount in every period of time to solve the problem of data sparsity; sets a dynamic weight to balance the user selection trend to improve the accuracy; and uses user clustering and collaborative filtering algorithm to predict the users’ preferences for those new users with no rating information, so as to solve the cold start problem. The results of the proposed algorithm’s experiment on MovieLens datasets indicate that this algorithm is superior to the traditional LDA model on the recommendation recall rate, accuracy, and F1 values.

Automatic Discovery of Relationship Between Examination Question and Knowledge Points Based on Vector Space Model

DONG Ao-gen, LIU Mao-fu, HUANG Ge-xin, SHU Qi-yun

2015, 0(10):  6-9.  doi:10.3969/j.issn.1006-2475.2015.10.002

Asbtract ( 175 )  

References | Related Articles | Metrics

With the extensive application of examination system based on knowledge points, how to automatically match examination question with knowledge points has become an important direction of current research. In this paper, word2vec is used to get the K-dimensional space vector for each word in the texts of examination question and the knowledge points at first. And then, we calculate the cosine distance between the vectors to represent the semantic similarity of the examination question and the knowledge points. The experimental results show that this method can quickly find the relationship between examination question and knowledge points and improve the work efficiency of the examination system.

Analyzing Information Systems Users’ Access Behavior by Human Dynamics

REN Jia-jia, WANG Nian-xin, GE Shi-lun

2015, 0(10):  10-15.  doi:10.3969/j.issn.1006-2475.2015.10.003

Asbtract ( 192 )  

References | Related Articles | Metrics

Understanding the user's access pattern is a prerequisite for maintenance and upgrade of enterprise information system. In order to investigate the burstiness, memory, and periodicity characteristics of user's access to information systems, human dynamics was used to analyze 360 631 access records of 314 users in a shipbuilding manufacturing enterprise. The results show that the interval time distribution of user's access to enterprise information systems follows a power-law distribution. The exponents of general users, managers, and users are different. The results also indicate that the behaviors of these three types of user's access show strong burstiness and weak memory, and the user's access to information systems has obvious periodicity.

Preferred Learning-based Multiple Individuals Differential Evolution Algorithm for Constrained Optimization Problems

FU Yu-zhen1, ZHOU Jie-wen1, SHAO long-qiu2, ZHANG Hui1

2015, 0(10):  16-20.  doi:10.3969/j.issn.1006-2475.2015.10.004

Asbtract ( 192 )  

References | Related Articles | Metrics

This paper presents a preferred learning-based multiple individuals differential evolution algorithm for solving constrained optimization problems, in order to improve the search ability of difference evolution algorithm. Firstly, a kind of preferred learning strategy is applied to the hybrid mutation operator, which makes it quickly search to the area of feasible solution, then the clone strategies are used to enhance the search intensity in optimal solution area and the ability of local search is greatly improved. Finally the algorithm is tested on the CEC2006 classic Benchmark function, the experimental results show that the algorithm is of better results in solving efficiency and accuracy.

Stock Data Mining Based on C4.5 Decision Tree

WANG Ling, HU Yang

2015, 0(10):  21-24.  doi:10.3969/j.issn.1006-2475.2015.10.005

Asbtract ( 229 )  

References | Related Articles | Metrics

Using data mining algorithms to analyze and forecast the stock still has problems in technical indicators and quantity of data. Based on the analysis of stock market data, this paper selected certain indicators as decision attribute, and used C4.5 decision tree to classify and forecast the stock. This article mainly optimized the indicators of stock, and improved the efficiency of C4.5 algorithm. Optimized algorithm combining with improved indicators not only enhances the efficiency of data mining, also gets better returns in stock forecasting.

Improved Object-based Approaches for Bounds Checking of C Programs

MA Yin-xue, LI Wen-ming, CHEN Zhe

2015, 0(10):  25-30.  doi:10.3969/j.issn.1006-2475.2015.10.006

Asbtract ( 205 )  

References | Related Articles | Metrics

C programs are efficient because it did not check memory bounds safety. However, it also brought a lot of security issues, such as out of bounds of arrays and pointers, illegal operations of C library functions. Object-based runtime verification approaches can monitor program running and find bugs automatically. We improved the traditional approaches by changing address range records of multidimensional arrays and structure variables, querying address two times to detect pointer access, and using AVL tree for storage structure of records. The experiment shows that our approach is better than traditional ones.

Synthetic Vision System Terrain Database Integrity Based on DWL

ZHOU Yan-qing, WANG Li-song

2015, 0(10):  31-35.  doi:10.3969/j.issn.1006-2475.2015.10.007

Asbtract ( 213 )  

References | Related Articles | Metrics

Synthetic vision system (SVS) is an effective solution of controlled flight into terrain (CFIT). In recent years, the national key basic research development plan has brought into the related research on synthetic vision system to study. The study of synthetic vision system terrain database integrity is an important part of the SVS research. Based on the present stage, most aircrafts are equipped with GPS, radar altimeter and other equipment, this paper is about a study of synthetic vision system terrain database integrity based on downward looking (DWL). The real-time monitor of synthetic vision system database based on DWL can effectively guarantee the integrity of the vertical database data, but for aircraft horizontal database data integrity, the assurance ability is also slightly insufficient.

Key Techniques of Multi-agent Workflow Model Based on Time Series

JI Hong-an, MA Ye, LI Xue-hong

2015, 0(10):  36-39+44.  doi:10.3969/j.issn.1006-2475.2015.10.008

Asbtract ( 184 )  

References | Related Articles | Metrics

Aiming at the problem that how to transform the real work program into an automation control problem that a computer can perform and control, some solutions are put forward to establish a multi-agent workflow model based on time series. The workflow is transformed into time series and pushed into multi-process pool to be executed synchronously or asynchronously, that solved the synchronous disorders and deadlock problem caused by workflow branch and aggregation. Based on the multiple Agent model, using Agent unit of process can manage the whole workflow. Finally, a concurrent data processing method based on timestamp makes the system have the function of process optimization and whole-process control. Actual application shows that this method realizes the effective control of the workflow and the desired purpose.

Database Middleware Based on Web Services and Hibernate

CHU Fu-ying, WEI Wen-xue

2015, 0(10):  40-44.  doi:10.3969/j.issn.1006-2475.2015.10.009

Asbtract ( 264 )  

References | Related Articles | Metrics

For the management of some heterogeneous databases in different network is more flexible and convenient, the paper studies and analyzes the common database middleware, Hibernate framework and Web Service technology. Then aiming at the shortcomings of database middleware, the paper puts forward a new database middleware that was designed with Web Service technology and Hibernate framework. This scheme can transparently access databases without changing the original data storage method, ensure data integrity, consistency and security, and has higher development efficiency.

Moving Target Tracking Algorithm Based on Davinci Platform

DONG Yun-fei1, XIE Hong-song1, LUO Bin1,2, TANG Jin1,2

2015, 0(10):  45-49.  doi:10.3969/j.issn.1006-2475.2015.10.010

Asbtract ( 196 )  

References | Related Articles | Metrics

In the process of moving target tracking, considering the data processing ability of Davinci platform, combining the Vibe algorithm with the mean shift algorithm, an improved moving target tracking algorithm is presented. At the same time, in order to solve the problem that it is difficult to eliminate the ghosts left in the foreground image after the moving target becomes stationary state in the Vibe algorithm, we set up foreground counters for each pixel in the video image sequence, and judge the renewal speed of background model according to the value of counter. And the algorithm is optimized based on Davinci platform. At last, the improved moving target tracking algorithm is transplanted into TMS320DM6467T platform. Experiment results show that the improved algorithm is of good tracking performance to moving target.

Texture Illumination Invariant Feature Extraction Algorithm Based on BM3D Pre-processing

ZHAN Jun-jie, SHANG Zhao-wei

2015, 0(10):  50-54.  doi:10.3969/j.issn.1006-2475.2015.10.011

Asbtract ( 235 )  

References | Related Articles | Metrics

In order to eliminate the effects of changing illumination on image structure information, a three dimensional block-matching (BM3D) pre-processing-based texture illumination invariant feature extraction algorithm is proposed. With the excellent denoising feature of BM3D algorithm, this method firstly uses BM3D denoising method to denoise each color channel, and uses wavelet transform to get the low and high frequency component of logarithmic domain of each color channel of image, secondly, uses the wavelet denoising method and Bayes-Shrink denoising method to denoise the low and high frequency components respectively, and thirdly constructs illumination invariant, using the principal component analysis (PCA) to reduce the feature dimension, obtains the feature vector, and lastly uses the K-NFL classifier to classify image. Experimental results based on Outex_TC_00014 texture database show that the proposed method delivers good classification performance.

Evidential Reasoning-based Region Merging for Interactive Medical Image Segmentation

LI Rui

2015, 0(10):  55-59.  doi:10.3969/j.issn.1006-2475.2015.10.012

Asbtract ( 186 )  

References | Related Articles | Metrics

When preoperatively diagnosing the gastric cancer, extracting regions which include lymph nodes in CT images accurately is very important for doctors. Meanwhile, it is better to allow direct intervention of doctors to make necessary corrections when needed. Due to above problems, a novel evidential reasoning based region merging (ERRM) method for interactive image segmentation is proposed. ERRM not only can extract object regions effectively, but also allow direct intervention of doctors. After initial segmentation, the similarity between the target region and its adjacent regions will be calculated by evidential reasoning (ER). Two regions will be merged if they have the highest similarity. The experimental results show that ERRM can obtain better performance than other methods in both qualitative and quantitative analysis.

A Segmentation Method of Strip Defects Image Based on Characteristics Mining of Targets

ZHAO Ting, GUAN Sheng-qi, WANG Peng

2015, 0(10):  60-63.  doi:10.3969/j.issn.1006-2475.2015.10.013

Asbtract ( 185 )  

References | Related Articles | Metrics

Through the analysis of strip image and characteristics mining of defect image, this paper proposes a strip defect image segmentation method based on target characteristic mining. Firstly, this program pretreats strip defect image with median filter algorithm, then segments the strip image with a series of threshold, through characteristics mining of strip defect image and task-driven, finds out the eigenvalue mutation interval. In this mutation interval, the program segments the strip image with above method again to subdivide and finds out the optimal threshold. The program segments the strip image with the threshold and gets characteristic sub graph. Lastly, the program fuses characteristic sub images and gets the segmentation results. Experiments show that applying this method to the strip defect image segmentation process can effectively segment strip defects image. It means that this method provides a possibility for visual detection of strip defects.

Road Lighting Intelligent Management System Based on MVC and Entity Framework

LIU Yu1,2, CAI Jun-tao2, LAI Shun-qiao2, XIAO Yi-lin2

2015, 0(10):  64-68.  doi:10.3969/j.issn.1006-2475.2015.10.014

Asbtract ( 234 )  

References | Related Articles | Metrics

With the development of city construction, the traditional street light control and maintenance methods cannot meet the needs of modern urban development. In this article, based on Microsoft’s ASP.NET MVC4 framework and the entity framework, adopting three-layer architecture mode, we research and design an intelligent road lighting management system. In the system presentation layer, we use jQuery, Ajax, HTML 5, CSS3 and other technologies to achieve page display, the business layer is realized by using the T4 template, and the data layer is realized by adopting the entity framework. We briefly analyze the technical details of system implementation and the realization of intelligent control, fault alarm, and other functions. The system can carry on the real-time detection and control of road lamps, realizing the intellectualized management of urban street lighting.

A Meteorological Service System Based on Android Mobile Terminal

JIANG Jian-hua, ZHANG Guang-yun

2015, 0(10):  69-72.  doi:10.3969/j.issn.1006-2475.2015.10.015

Asbtract ( 200 )  

References | Related Articles | Metrics

Based on actual needs of weather forecasting and disaster warning, a meteorological service system including functions of weather forecasting and warning, special forecast, geological disaster warning was designed for Android intelligent terminal equipment. The key problems of acquainting terminal equipment location, warning messages’ real-time push, graphic display and tagging of meteorological disaster information based on Baidu map were researched. Finally, feasibility and pragmatic value of the system were verified by practical application.

Laboratory Management System Based on Android Smart Phone

GUO Qi-zhi, CHEN Guang, REN Zhuo-jun, LUO Jin-long

2015, 0(10):  73-76.  doi:10.3969/j.issn.1006-2475.2015.10.016

Asbtract ( 195 )  

References | Related Articles | Metrics

Mobile Internet era has been coming to us, and penetrated into every corner of College life and study. The laboratory management system based on B/S mode has been unable to meet the requirements of mobility and portability. The user interface is compiled by Android technology. And function instruction interacts with Tomcat server through GET and POST way. Servlet modular of server completes login authentication and command response. The server interacts with MySQL database through JDBC to save and process data. So the paper has realized an experiment management system based on Android smart phone. By the system, students and teachers could realize experiment booking and obtain course changing notice more quickly. In addition, the system provides individually function modules for teacher and student, in which teacher could look up laboratory situation any time and any place through linking lab’s monitor, student could prepare experiment and check experiment. By this, it increases the portability and timeliness of laboratory management.

Spectrum Allocation for Cognitive Radio Based on NSGA-II

WANG Yin-meng1, WANG Song-qing2, DU Qing-wei1

2015, 0(10):  77-82.  doi:10.3969/j.issn.1006-2475.2015.10.017

Asbtract ( 192 )  

References | Related Articles | Metrics

Spectrum auction is an effective way to solve the dynamic spectrum allocation in cognitive radio networks. The main objective in an auction is to maximize all the primary users’ revenues. However, there are some conflicts among primary users’ gains and this brings difficulties to do the auction. So, a new auction scheme is proposed to solve the winner determination problem (WDP). In the scheme, the dynamic spectrum allocation is regarded as multi-knapsack problem and trying to solve it by non-domination sort genetic algorithm II (NSGA-II). Finally simulation experiments show that NSGA-II does a good job in solving the problem of WDP compared with the greedy algorithm.

Hardware Dynamic Behavior Assessing of WSN and Semi-passive RFID Tags in Temperature Monitoring System

LI Qun

2015, 0(10):  83-87.  doi:10.3969/j.issn.1006-2475.2015.10.018

Asbtract ( 169 )  

References | Related Articles | Metrics

For the issue that traditional low temperature monitoring systems tend to ignore the dynamic behavior characteristics of hardware, a dynamic behavior characteristic assessing method based on wireless sensor networks (WSN) and semi-passive tags of radio frequency identification (RFID) is proposed. Thus, the aim is to evaluate the sensors dynamic behavior. The experimental test temperature is freezer temperature (5 ℃), room temperature (23 ℃) and greenhouse temperature (35 ℃). And three different sensor configurations WSN motes particles and four kinds of RFID tags (packaged or not packaged) were compared. In order to assess the hardware dynamic range of the sensor response, first-order response of the sensor is logarithmically and nonlinearly fitted. Experimental results show that the temperature sensor packages containing wireless and RFID nodes will affect the dynamic response, and its properties can monitor fast temperature changes, ensuring the normal operation of the cold chain system.

Network Management System Based on OpenNMS

YANG He-wen

2015, 0(10):  88-91.  doi:10.3969/j.issn.1006-2475.2015.10.019

Asbtract ( 262 )  

References | Related Articles | Metrics

Some companies specialize in the research and development, production, and sale of wireless broadband access products. The application of these products is mainly for the hot spot coverage projects of operators. The establishment of a unified WLAN hot equipment monitoring network can effectively manage so many wireless access points with the help of professional network management system, so as to ensure the dynamic monitoring and the stable operation of the equipments. According to the functional requirements of a specific WLAN device management system, this paper designed a management system which is suitable for centralized network architecture of WLAN on the basis of OpenNMS, completed and implemented the functions such as data collection, report management, device discovery, MIB file analysis, topology management, scheduling management, alarm management, performance management, user management of the wireless devices. This system basically reached the requirements in the WLAN equipment management through the test.

Performance Analysis of Traffic Anomaly Detection in Cloud-based Software-defined Network

MA Chao1,2, CHENG Li1, KONG Ling-ling3

2015, 0(10):  92-97+102.  doi:10.3969/j.issn.1006-2475.2015.10.020

Asbtract ( 228 )  

References | Related Articles | Metrics

The increasing complexity of hybrid cloud networks becomes a bottleneck of cloud computing. As a potential solution, SDN has gained great attentions from both industry and academia, especially in the network security domain. Research on utilizing SDN in network attack detection is still in its inception phase. Specifically, it has not been evaluated whether SDN can efficiently detect internal network attacks in a cloud environment. In this research we implement both SDN and traditional network infrastructures based on OpenStack platform. We simulate both flood and port-scan attacks and utilize two types of traffic anomaly detection algorithms. Experiment results indicate that the SDN method shows better performance in memory usage without degrading its accuracy, while it also suffers performance bottleneck when directly deployed into SDN controllers.

Pattern Matching-based Wireless Network Security Configuration Verification Tool

TANG Lian, WANG Xiao-long

2015, 0(10):  98-102.  doi:10.3969/j.issn.1006-2475.2015.10.021

Asbtract ( 162 )  

References | Related Articles | Metrics

According to the serious situation of wireless network security, a wireless network security configuration verification tool based on pattern matching is designed and implemented. First of all, according to the relevant provisions of grade protection and through the study of risk assessment of wireless network, the wireless network security configuration verification specification is made; then, on account of the shortcomings of the existing detection methods, an automation configuration verification method based on pattern matching is proposed; finally, the system architecture, module functions and implementation of the tool are provided.

Spatio-temporal Privacy Preservation in Wireless Sensor Networks

PEI Hua-yan1, WANG Huan-min2

2015, 0(10):  103-106.  doi:10.3969/j.issn.1006-2475.2015.10.022

Asbtract ( 162 )  

References | Related Articles | Metrics

To prevent the timing attacks of spatio-temporal in wireless sensor networks, a new privacy preservation mechanism based on MIX idea is proposed. The protection strategies corresponding to three different spatio-temporal relations existed in data transmission are proposed. The realization principle and data processing flow of the protection mechanism are described in detail, thus it provides a new idea for the protection of spatio-temporal privacy in WSN.

Parallel Data Mining Methods in Analysis of Results of Water Census

DING Wei, WAN Ding-sheng, FAN Long

2015, 0(10):  107-111.  doi:10.3969/j.issn.1006-2475.2015.10.023

Asbtract ( 188 )  

References | Related Articles | Metrics

With the end of first nation water census, massive water census data have been generated. To use the cloud computing technology in the area of water census data mining can provide scientific, reasonable supports for the decision of water conservancy in a quick, efficient and economical way. This paper proposes water census data decision tree classified mining algorithm MRC4.5 based on Map/Reduce and water census data of groundwater wells is applied to data mining with the algorithm. The experimental results indicate that compared with the traditional algorithm C4.5, MRC4.5 algorithm has higher efficiency and good speedup when dealing with massive data sets execution.

A Method of Calculating Manipulator Inverse Kinematics Solution Based on ANFIS

LIU Jiang-nan1, XIE Wei1, MA Jia-chen1,2

2015, 0(10):  112-117.  doi:10.3969/j.issn.1006-2475.2015.10.024

Asbtract ( 201 )  

References | Related Articles | Metrics

An adaptive neuro-fuzzy inference system (ANFIS) based inverse kinematics solution of a robotic manipulator is presented. The research object is SCARA type four degrees of freedom manipulator. The corresponding relationship between robot end-effector Cartesian coordinates and manipulator joints space is studied. We select the starting point, intermediate point and end point according to the target trajectory, and use the traditional method to obtain the corresponding joint variable values. Then we get the joints space curve by using cubic splines. Sample points are randomly selected from the curve to train the ANFIS. The results show that ANFIS in calculating precision and computing time of inverse kinematics is superior to the BP neural network.

A Torque Measurement Method of Electric Actuator

SONG Kai-feng1, TIAN Pei1, PAN Lin-xin2, MA Ming-jin2

2015, 0(10):  118-120+126.  doi:10.3969/j.issn.1006-2475.2015.10.025

Asbtract ( 170 )  

References | Related Articles | Metrics

Torque detection is an important part of the electric actuator. There is a certain corresponding relationship between the electric actuator output torque and the motor current, and therefore, this paper puts forward an engineering method of indirectly measuring the output torque, namely indirectly measuring the output torque by measuring the effective value of the electric actuator output current. Computing the current effective value by fast Fourier transform, compared with the current effective value measured by the current detector, experimental results show that the calculation of current effective value of the electric actuator by fast Fourier transform can be used as an effective method of indirectly measuring the output torque.

Congenital Reinforced LCD Monitor Based on Optical Fiber Transmission

DU Cheng-rui, HU Xiao-ji

2015, 0(10):  121-126.  doi:10.3969/j.issn.1006-2475.2015.10.026

Asbtract ( 183 )  

References | Related Articles | Metrics

To solve the problems of low reliability and instability of the display in the process of military operations due to the complexity of the external environment and the strong electromagnetic pulse weapons, a design scheme of LCD which uses congenital reinforcement and optical fiber transmission instead of electrical transmission is proposed. Based on the idea of “modular design”, this paper introduces the circuit framework, hardware design and software design in detail. Finally, the performance and environmental adaptability of the whole machine are tested. The results show that the display performance is good in different input signal sources, and the stress screening and electromagnetic compatibility tests are met the requirements of the test outline. The feasibility and practicality of the design scheme are verified.