Table of Content

21 July 2016, Volume 251 Issue 07

Previous Issue    Next Issue

Super Resolution-based Astronomical Image Processing System

XIE Hong1，2, LI Zhan1，2, CHEN Hui-qiong1，2, ZHENG Jia-wei1，2, WEN Li1，2

2016, 251(07):  1-5,12.  doi: 10.3969/j.issn.1006-2475.2016.07.001

Asbtract ( 182 )  

References | Related Articles | Metrics

 To provide an approach to obtaining high resolution image and to improve the quality of observations by ground-based telescopes, a Super Resolution-based

Astronomical Image Processing System(SR-AIPS) is designed and implemented， which combines image preprocessing, automatic search positioning, image registration, super

resolution(SR) image reconstruction and image enhancement. SR-AIPS enhances observations using multiple image processing methods, among which SR reconstruction algorithms are

key technologies and the innovation of this system. System tests show that SR-AIPS can automatically search and precisely locate stars in ground-based observations, as well as

improve resolution and visual effect of images effectively.

 An IPSIAST Algorithm and Its Application in Remote Sensing Imagery Segmentation

SUN Xiao-dan

2016, 251(07):  6-12.  doi: 10.3969/j.issn.1006-2475.2016.07.002

Asbtract ( 148 )  

References | Related Articles | Metrics

 Aiming at the defects of the PSI (Pixel Shape Index) algorithm, this algorithm has been modified accordingly, and an improved PSI algorithm of adaptive spectral

threshold (Improved Pixel Shape Index of Adaptive Spectral Threshold, IPSIAST) is proposed in this paper. The main advantages of the new algorithm are following: 1) In order to

enhance the rationality of direction line generation, the differences existed in the spectral feature homogeneity between the bands have been considered adequately. The

direction line on each band layer is extended independently. 2) Length of each direction line is defined as the weighted sum of the lengths about all direction lines along the

same orientation on all band layers. The differences existed in the spectral feature homogeneity between the bands are further reflected by this way, and the accuracy of PSI

about each pixel is improved. 3) Spectral threshold T1 can be adjusted adaptively according to the spectral homogeneity of the local region, and the influence of the

contrast on the edge of the surface feature will be reduced during the computing process of the PSI. Finally, by using visual comparison analysis and five quantitatively

evaluating indexes, the results of experiments showed that compared with the PSI, the imagery segmentation accuracy was further improved through associating with the IPSIAST.

 Self-adaptive Image Encryption Algorithm Based on Improved Logistic Chaotic Map

LIU Rui

2016, 251(07):  13-17,23.  doi:10.3969/j.issn.1006-2475.2016.07.003

Asbtract ( 211 )  

References | Related Articles | Metrics

 In order to solve the problem that the iterative sequences produced by the one-dimension(1D) Logistic chaotic map are uneven distribution and the parameter

space of chaos is smaller, an improved Logistic map was constructed by increasing the control parameter and nonlinear adjustment in the Logistic chaotic map, which has a wider

chaotic range and more uniform distribution than its prototype by analyzing bifurcation diagram and Lyapunov exponent. A self-adaptive image encryption scheme based on improved

Logistic chaotic map was introduced, and the initial value of improved Logistic chaotic map is adaptive change with the plain image, and the scheme is sensitive to all sorts of

subtle change of the plain image. Experiments and security analysis indicate that the algorithm has high security, and can resist statistical analysis and attack operation.

 Beach Foggy Images Haze Removal Based on Dark Channel Prior

HUO Hai-meng, XU Shi-xu, WANG Han-ping

2016, 251(07):  18-23.  doi: 10.3969/j.issn.1006-2475.2016.07.004

Asbtract ( 159 )  

References | Related Articles | Metrics

 In the effects of fog, haze and other bad weather, the beach images acquired from camera have serious distorted and degraded. In order to get better picture

information from restored image, this paper proposed a K-means clustering algorithm combined with dark channel prior theory. Firstly, using K-means clustering algorithm to

divide sky region based on the characteristics of beach scene, the atmospheric light intensity value is obtained by non-sky area luminance values with the sky region luminance

values weighted. Secondly, the transmission is estimated and improved based on atmospheric scattering model. Finally, in order to increase the brightness of the image and

enhance the image contrast, this paper adopted tone remapping on the image. A large number of experiments show that the algorithm can get an excellent performance on image haze

removal for the beach foggy image and particularly do better than traditional defogging algorithm, which is more suitable for processing beach foggy image.

 Slow Feature Learning Discriminant for Ordinal Regression

LI Ya-ke, GAO Hang

2016, 251(07):  24-27,32.  doi: 10.3969/j.issn.1006-2475.2016.07.005

Asbtract ( 114 )  

References | Related Articles | Metrics

 Ordinal regression is an important machine learning paradigm whose purpose is to predict the ordinal outputs or discrete labels by establishing an ordinal

regressor. Many ordinal regression algorithms have been proposed with a better performance by using this prior ordinal information. However, they do not consider the combination

of slowness principle and ordinal regression. This paper first characterizes the slowness within-class scatter matrix with a number of within-class time series, and then

establishes a slow feature learning discriminant for ordinal regression(SFLDOR) by combining the matrix with an ordinal restriction. The experimental results with the eight

standard ordinal regression data sets demonstrate that SFLDOR has a better regression and classification performance than the algorithm with general within-class scatter matrix.

 Collaborative Filtering Recommendation Algorithm Based on User Attributes Clustering

LIN Kang, YANG Yun, QIN Yi, MIN Yu-juan

2016, 251(07):  28-32.  doi: 10.3969/j.issn.1006-2475.2016.07.006

Asbtract ( 168 )  

References | Related Articles | Metrics

 Collaborative filtering algorithm, which can recommend the items appeal to users from mass of data through studying the user’s preferences is widely used in electronic commerce. However, collaborative filtering algorithm suffers from decreasing accuracy and inefficiency in scalability, data sparsity, and cold start. In order to solve there problems, the concept of user attribute similarity is introduced in this paper, and the user can be divided into appropriate user clusters to predict the user’s ratings for a project by using K-means clustering algorithm. Furthermore, through fusing the recommendation algorithm based on user attributes and the collaborative filtering algorithms based on the project by using the method of mixed weights, a collaborative filtering algorithm synthesizing the attributes of user is proposed. Through experiment by using MovieLens data sets, we verify that the proposed algorithm has extensibility. Simultaneously, it can ease cold start problem and improve the prediction accuracy of recommendation algorithm in some degree.

 Short-term Wind Speed Forecasting Based on Phase-space Reconstruction and #br#   Evolutionary Gaussian Process Model

CHANG Chun1, LI De-sheng2

2016, 251(07):  33-36,43.  doi:10.3969/j.issn.1006-2475.2016.07.007

Asbtract ( 234 )  

References | Related Articles | Metrics

 A short-term wind speed forecasting method based on phase-space reconstruction and evolutionary Gaussian process model is proposed in this paper. Firstly, the autocorrelation method and false nearest neighbor method are applied to calculate the delay time and embedding dimension of the wind speed time series, which are used to accomplish the phase-space reconstruction of the chaotic wind speed time series. Secondly, the evolutionary Gaussian process model, which combines Gaussian process with evolutionary algorithm, is used to forcast the wind speed. This model uses Gaussian process model to determine the relationship between the input and output variables， and the improved PSO algorithm to optimize the hyper parameters. The prediction results show that the proposed method can improve the prediction accuracy.

A Discrete Flower Pollination Algorithm for Travelling Salesman Problem

LI Qian1, HE Xing-shi1, YANG Xin-she1,2

2016, 251(07):  37-43.  doi: 10.3969/j.issn.1006-2475.2016.07.008

Asbtract ( 256 )  

References | Related Articles | Metrics

In view of the standard Flower Pollination Algorithm(FPA) can not be used to solve combinatorial optimization problem, a Discrete Flower Pollination Algorithm(DFPA) was proposed and then applied to Traveling Salesman Problem(TSP). By redefining the concept of flowers, global search and local search, etc.， and Levy flight will be segmented by a new method, effectively avoiding premature falling into local optimum and enhancing the global search ability of the algorithm. Finally the performance of the proposed is tested against by some typical instances in the internationally commonly used library of TSP(TSPLIB) and compared with Discrete Particle Swarm Optimization（DPSO）， Hybrid Discrete Particle Swarm Optimization(HDPSO)， Discrete Cuckoo Search(DCS)， Genetic Simulated Annealing Ant Colony System with Particle Swarm Optimisation Technique（GSA-ACS-PSOT）. The results of the tests show that DFPA can quickly, accurately find the optimal solution. Under the same experimental conditions, the algorithm reduces the error rate than any other algorithm. The results show that the proposed algorithm has better solving performance.

 A Fault Tree Analysis Method with Time Constraint

LI Wen, XU Hui

2016, 251(07):  44-48,54.  doi:10.3969/j.issn.1006-2475.2016.07.009

Asbtract ( 191 )  

References | Related Articles | Metrics

 Behavior in the time domain is critical to safety critical systems, if there was a fault, a large number of fault descriptions were related to the time between events. While the traditional fault tree does not have the ability to describe and analyse the time factor. On the basis of original definition of fault tree, semantic description of time constraint fault tree was added, a time constraint fault tree analysis method was put forward based on the extended semantic of the fault tree. The calculation rules of the time constraint logic gate and the event average transfer rate, the input event to the output event propagation rate and the intermediate event arrival rate are given. The propagation rate and arrival rate of the basic event and the minimum cut set of the fault tree were designed, and the algorithm was proposed to obtain the basic event time importance and the minimum cut set arrival rate for each node in the fault tree. The experimental results showed that the proposed timing analysis method can provide theoretical basis for fault diagnosis and prevention.

 Dimension Reduction Method Applying in Three-class ROC Analysis Based on SVM

LIU Hui-he， XU Wei-chao， LIU Shun

2016, 251(07):  49-54.  doi: 10.3969/j.issn.1006-2475.2016.07.010

Asbtract ( 159 )  

References | Related Articles | Metrics

 ROC(Receiver Operating Characteristic) analysis method has been widely used in various fields, but it is mainly applied to two-class task. In the three-class task, it is difficult to show and understand, and the computation complexity is hardly to accept. This paper proposes a new dimension reduction method, which is based on SVM(Support Vector Machine) classifier, to  exploit the ROC analysis method in three-class task, which avoids the above problems and inherits the advantages of ROC analysis method in two-class task.

 Classification Method of Education Text Based on #br#   Hierachical Class Topic Graph Model

LI Quan

2016, 251(07):  55-59,67.  doi: 10.3969/j.issn.1006-2475.2016.07.011

Asbtract ( 168 )  

References | Related Articles | Metrics

 There are more and more education resource of information in the period of big data on the Web. The classification requirement of a great number of education texts of being multi-class, multi-level can be satisfied by hierachical classification. Therefore, the class representation model of traditional hierachical classification has high-dimension and sparse problem, and it’s lack of semantic understanding. To solve the above problems, the classification method of education text based on hierachical class topic graph model was proposed. The text set was modelled by the hierachical class topic graph model. Probability matrices of hierachical class-word of the texts were obtained. In order to further improve correlation between feature words and classes, the combined feature was extracted by the complementarity of the three kinds of way extracting feature. Finally, the texts were classified by the hierachical SVM classifier. The analysis on simulation result indicates that the evaluation values of MacroP, MacroR and MacroF1 etc increase to some extend, comparing to traditional hierachical classification method. Therefore the method has good classification effect of Internet education text, and application prospect.

 A Chinese Address Resolution Model Based on Trie Tree and Finite Automata

WANG Yang1,2, LIU Shi-pei1, WANG Zheng2

2016, 251(07):  60-67.  doi:10.3969/j.issn.1006-2475.2016.07.012

Asbtract ( 291 )  

References | Related Articles | Metrics

 Until now, there is not a relatively mature model in the research of Chinese address resolution no matter in the academic or commercial fields. Elements identification is the main technique for address resolution. Traditional method of address elements identifying basing on the method of feature words and dictionary matching is difficult to solve the problem of the non-canonical address resolution. In this paper, the T-FA model is proposed to solve the problem of address segment and grading, for further, the Trie-tree model is adopted for addressing of administrative regions and the Finite-Automata(FA) model for the elements extraction of non-canonical address corresponding, which are both common technologies in natural language processing field. And fuzzy search and recognition of the address elements could be well resolved using words segmentation method based on the hidden Markov model and the Longest Common Sub-sequence(LCS) algorithm. The T-FA model achieves a better performance in the generalization ability for batch processing the address information than state-of-art, and more effective in solving the problem of non-canonical address resolution.

 A Combined Temperature Sensor Based on Data Fusion

HU Nai-ping, DING Ji-xiang

2016, 251(07):  68-71,76.  doi: 10.3969/j.issn.1006-2475.2016.07.013

Asbtract ( 158 )  

References | Related Articles | Metrics

In this paper, we present a combined temperature sensor based on data fusion. We test the combination of the linearity, stability of the platinum resistance and the sensitivity, dynamic performance of the thermistor, and apply the federated Kalman algorithm to fuse their data realtinely. Our results show that this combined sensor is more excellent than both. The results suggest that this combined temperature sensor could improve the accuracy and dynamic response of the measurement system.

 Design and Simulation of Deflectable Nose Missile Control System #br#   Based on MATLAB-Simulink 

LIANG Yi-chen

2016, 251(07):  72-76.  doi: 10.3969/j.issn.1006-2475.2016.07.014

Asbtract ( 160 )  

References | Related Articles | Metrics

Deflectable nose control is a new control method of missile which has complicated dynamic characteristics. Specific to the deflectable nose missile, the open-loop dynamic model is given and the MATLAB-Simulink is operated to analysis the dynamic characteristic. A vertical control system is designed and the simulation is operated. The result of the simulation indicates that this control system has the strong performance of high precision and fast response.

 Design and Implementation of Electric Drive Typical Load Simulation System

KADYLBEK Zhalyn, SUN Pei-de

2016, 251(07):  77-79,86.  doi: 10.3969/j.issn.1006-2475.2016.07.015

Asbtract ( 154 )  

References | Related Articles | Metrics

 High-quality dynamic load simulator is an important equipment in electric drive experiment. Electric load simulation system is the new direction in the load simulation technology development filed. So researching the design and implementation of electric drive typical load simulation system has very important value. Several types of loads in actual operation are analyzed in this paper, such as constant torque load, constant power load and fan pump load, which are loading as simulation element with magnetic powder brake. Through the experiments, the characteristics of constant torque load, constant power load and fan pump load are realized.

 A Method of Data Center Network Dynamic Traffic Scheduling Based on SDN

ZHUANG Huai-dong, DU Qing-wei

2016, 251(07):  80-86.  doi: 10.3969/j.issn.1006-2475.2016.07.016

Asbtract ( 140 )  

References | Related Articles | Metrics

 In the data center network, multipath is widespread, but the traditional traffic scheduling method based on ECMP is likely to cause flow collision problem, therefore a new dynamic traffic scheduling method based on SDN is proposed. SDN has the advantages of centralized control, and global view of the network, so, it is used to schedule the elephant flow in network. In the scheme, firstly, the sFlow protocols is used to collect network information. Secondly the elephant flow path selection is modelled according to the multi-commodity flow problem. Last, we are trying to solve it by the particle swarm optimization to get the global optimal solution. Finally, the simulation results show that, the proposed algorithm can improve network utilization, achieve higher bisection bandwidth compared with the ECMP algorithm.

 Research and Implementation of a Content Delivery Network

CHEN Ming-ji, HUANG Feng-juan

2016, 251(07):  87-90,94.  doi: 10.3969/j.issn.1006-2475.2016.07.017

Asbtract ( 152 )  

References | Related Articles | Metrics

 The Content Delivery Network(CDN) provides network acceleration services for Internet Content Provider(ICP). The CDN includes central control node, domain name resolution servers and edge cache servers. This paper introduces the concept and base working principles of Content Delivery Network and proposes a solution of CDN. The design is verified on Linux system with Bind and Varnish, the result shows that the CDN is capable of achieving intelligent user routing and efficiently distributing content.

 Time Constrained LDA for Topic Extraction of Public Opinion Texts

WAN Hong-xin1, PENG Yun2, ZHENG Rui-ying1

2016, 251(07):  91-94.  doi: 10.3969/j.issn.1006-2475.2016.07.018

Asbtract ( 144 )  

References | Related Articles | Metrics

 With the development of Internet, a large number of public opinion texts have been produced, and the hot topics and trends can be found by topics extraction from these texts. Because of the huge amount of the texts, and the dynamic changes of topics, a TC-LDA (Time Constrained LDA) model is proposed. TC-LDA can transform the text data into the topic vector and greatly reduce the dimension of public opinion texts, and implements the LDA’s timing conversion by adding the time constraint, which can improve the ability of LDA to capture the dynamic topic words. Experiments show that the accuracy and recall rate of TC-LDA is better than that of the similar topic model.

 Analysis and Research of Malicious URL Recognition Based on SVM and TF-IDF

GAN Hong, PAN Dan

2016, 251(07):  95-97,102.  doi: 10.3969/j.issn.1006-2475.2016.07.019

Asbtract ( 198 )  

References | Related Articles | Metrics

 With the rapid development of the Internet, especially the mobile Internet, there are more and more sites that have been brought out and destroyed in the world. In this paper, we propose a URL detection scheme based on machine learning, through analyzing the features of URL’s text and sites. The URL’s site feature is refined by TF-IDF algorithm, the URL security detection is carried out with SVM kernel based on RBF kernel, and it obtained 96% auuracy and 0.95 F1 sore.

 An Improved AODV Routing Protocol for Urban Vehicular Ad Hoc Networks

CAO Wen-jun, XUE Shan-liang

2016, 251(07):  98-102.  doi: 10.3969/j.issn.1006-2475.2016.07.020

Asbtract ( 165 )  

References | Related Articles | Metrics

 To enhance the link stability of urban vehicular Ad Hoc networks, this paper proposes an enhanced routing protocol on Ad Hoc on-demand distance vector with speed variance (SV_AODV). In SV_AODV, the nodes forward requests to the destination node with their velocities, the destination node collects velocity variance of the path and feedbacks it to the source for selecting the route. The simulation results from the Network Simulator Versi on 2 prove that SV_AODV can reduce the loss of data packets and shorten the end-to-end delay in the case of fast moving of nodes, it can be applied to urban vehicular Ad Hoc networks.

 An Agricultural Environment Monitoring System Based on Sensor

LIU Bo-ping1,2， QIU Feng1,2， FU Kang1,2, WANG Lei1,2, HU Min1,2

2016, 251(07):  103-106.  doi: 10.3969/j.issn.1006-2475.2016.07.021

Asbtract ( 126 )  

References | Related Articles | Metrics

 The development of information technology have brought great convenience to people’s production and life. This article introduces an agricultural environment monitoring system based on sensor from two aspects of design and implementation. The system realizes real-time monitoring and warning on agricultural environment, provides decision support for planting process.

A Population Data Visualization Monitoring System Based on LBS

JIANG Bao-qing1,2, HAO Rui-peng1,2

2016, 251(07):  107-110,114.  doi: 10.3969/j.issn.1006-2475.2016.07.022

Asbtract ( 222 )  

References | Related Articles | Metrics

 This article mainly introduces the design principle and application of population data visualization monitoring system based on LBS. Through statistical population data, using computer image generation technology, the population data is generated when the form of heat to visual images, and for the state of the population flow mapping dynamic migration effect, location-based services(Location-based Service, LBS) is provided. This article describes the design principle, function module and the business process of the system in detail.

 Automatic Recognition of Cough Based on Support Vector Machine

ZHU Chun-mei1,2, LI Ping1

2016, 251(07):  111-114.  doi: 10.3969/j.issn.1006-2475.2016.07.023

Asbtract ( 136 )  

References | Related Articles | Metrics

 To further improve the effect of cough automatic identification, support vector machine is adopted as classification model for cough recognition. The process of sample collection, MFCC feature extraction and support vector machine cough recognition is introduced in detail, and the results are compared with hidden Markov model and dynamic time warping. Experiment results show that, with a big training sample set, recognition rates of support vector machine are similar with hidden Markov model and higher than dynamic time warping, while with a small training sample set, support vector machine achieves the best result. In terms of efficiency of the algorithm, support vector machine significantly outperforms the other two classification models in both training and recognition time.

 Design of a New Intelligent Electronic Door System

WU Shi-yun, WANG Yi-yan

2016, 251(07):  115-117,123.  doi: 10.3969/j.issn.1006-2475.2016.07.024

Asbtract ( 163 )  

References | Related Articles | Metrics

 A new intelligent electronic door system was designed, which is mainly composed of microcontroller STC89C52, LCD12864, pyroelectric infrared sensor, speech synthesis, keyboard module, etc. In normal model, the system can automatically sensing two kinds of action, such as the human body through the door and going out. Then it completed the corresponding speech. The system also expanded the security alarm model, which made the intelligent electronic doorman have automatic alarm function.

  Used-car Recommendation Based on Synthetic Minority Over-sampling Technique Filter

QIU Hai-bo1， QIAN Zhong-min1， QIAN Mo-shu2

2016, 251(07):  118-123.  doi:10.3969/j.issn.1006-2475.2016.07.025

Asbtract ( 210 )  

References | Related Articles | Metrics

 Due to the fact the used-car data have unbalanced characteristics, recommendation of used-cars boils down to unbalanced data classification problem and it can be solved with the unbalanced classification methods. In this paper, with the focus on reconstruction of the trainning data set and by an analysis of characteristics and deficiency of the SMOTE over-sampling method, we propose the Synthetic Minority Over-sampling Technique Filter, or SmoteFilter for short. It works by filtering the data generated by SMOTE over-sampling and reduces the noise in generated data. Based on support vector machine using data generated by SMOTE and SmoteFilter, the experimental study shows that SmoteFilter method has better effect on predicting accuracy of minority class than the SMOTE method, improving the prediction performance of vehicle recommendation.

 Construction and Cost of University Informatization

ZHENG Feng-ni

2016, 251(07):  124-126.  doi: 10.3969/j.issn.1006-2475.2016.07.026

Asbtract ( 121 )  

References | Related Articles | Metrics

 Mobile interconnection, big data, cloud computing and other information technology are causing a new round of social change, universities are promoted from digital campus to wisdom campus. Returning to people-oriented, emphasizing service as the core, the university informatization work has entered a new stage. It also means university informatization needs to spend more cost on university informatization construction. This paper introduces and analyzes the construction current situation, cost and target of university informatization construction, and gives suggestions for it.