Table of Content

20 April 2017, Volume 0 Issue 4

Previous Issue    Next Issue

Smoke Detection Algorithm About Video Image with Multiple Features Based on Serial and Parallel Processing Model

CHEN Kang, LI Yao-hua, YOU Feng, CHEN Run-feng

2017, 0(4):  1-6,22.  doi:10.3969/j.issn.1006-2475.2017.04.001

Asbtract ( 243 )  

References | Related Articles | Metrics

This paper presents a smoke detection algorithm characterized by combination of serial and parallel processing model. This algorithm analyzes multiple features of video sequence by extracting the motion foreground of Gaussian mixture background modeling, and circling interested regions. When analyzing color feature, the information of each channel is normalized in RGB space, and the threshold value is judged according to the color characteristics of the smoke. When analyzing the shape feature, the statistical method is adopted to monitor the irregular degree of the video image with the measurement standard of irregular degree of break variable. Taken change rate of wavelet coefficient as check standard, the wavelet transform method is adopted to detect the high frequency information in the image with the combination of the characteristics of smoke diffusion. Based on the weighted analysis of multiple features, a comprehensive criterion is established for the detection and alarm of smoke detection in video image.

Underwater Image Super-resolution Reconstruction Based on Optical Imaging Model

ZHANG Hao1,2, FAN Xin-nan1,2,3, LI Min1,3, ZHANG Xue-wu1,3

2017, 0(4):  7-13.  doi: 10.3969/j.issn.1006-2475.2017.04.002

Asbtract ( 223 )  

References | Related Articles | Metrics

Now most super-resolution reconstruction algorithms are applied to atmospheric picture restoration. Taking the complexity of underwater optical environment into consideration, it is hard to perform direct processes towards scattering and attenuation caused by water simply by transplanting those super-resolution reconstruction algorithms to underwater images. In such condition, an underwater image super-resolution reconstruction algorithm based on optical imaging model is proposed by integrating different imaging models. Firstly, aiming at the severe degradation in image quality caused by light scattering in water, dark channel prior is used, based on underwater optical imaging model, to estimate scattered light and transmission in observed data to produce the result of noise estimation. Secondly, super-resolution reconstruction of projection onto convex sets is performed on the low-resolution image sequence from which scattered light is removed in order to produce a high-resolution image. At last, aiming at overcoming the decrease in intensity and blur caused by water so as to produce the restored image, light compensation is conducted on the high-resolution image using transmission. By comparing the reconstructed images produced by the proposed algorithm with those produced by classical super-resolution algorithms, quality improvement in restored images by our algorithm is proved in algorithm simulation.


A Video Watermarking Algorithm Based on Chebyshev Chaotic Neural Network

LIANG Jia-dong, YANG Shu-guo

2017, 0(4):  14-17,43.  doi:10.3969/j.issn.1006-2475.2017.04.003

Asbtract ( 181 )  

References | Related Articles | Metrics

For the copyright protection of digital video, this paper proposes a video watermarking algorithm based on Chebyshev chaotic neural network. First, to enhance the watermarking images safety, we process it using Chebyshev chaotic neural network, then decompose the host video into the frames, extract key frames from the chaotic sequences generated by Henon mapping, and extract the low frequence coefficient of the key frames luminance component. The processed image watermark is adaptively embedded into the low frequency coefficients of the luminance component after the wavelet transform. The experimental results show that this algorithm has a good invisibility, and has good robustness for the attacks such as noise, Gauss filtering, rotation, frame shear, etc.


Actuators Tasks Assignment Algorithm Based on Improved Distributed Auction for WSAN

QI Ben-sheng, MIAO Xue-jiao, MIAO Hong-xia, DENG Zhi-xiang

2017, 0(4):  18-22.  doi: 10.3969/j.issn.1006-2475.2017.04.004

Asbtract ( 128 )  

References | Related Articles | Metrics

In order to solve the tasks assignment of actuators in wireless sensor and actuator network (WSAN), an improved distributed auction algorithm (IDAA) is proposed. Utility of each task and cost of each actuator are taken into account to obtain the optimal assignment. The construction method of the response tree is improved, and the matching degree is introduced in the calculation of utility. Simulation results show that the energy consumption has been more balanced, and the numbers of data packets and time of tasks assignment have been reduced.


Collaborative Filtering Algorithm Based on Item Attribute Preference

ZHU Ming, WEI Hui-qin

2017, 0(4):  23-26.  doi: 10.3969/j.issn.1006-2475.2017.04.005

Asbtract ( 174 )  

References | Related Articles | Metrics

To tackle the data sparse problem of the traditional collaborative filtering algorithm, this paper proposes a collaborative filtering algorithm based on item attribute preference (CFBIAP). This algorithm calculates user similarity based on item attribute preference by using the item attributes and scores. Meanwhile it makes linear fitting with the similarity based on score matrix to get the user similarity. Up to a point, it decreases the error merely by score matrix partly. Experiments on MovieLens dataset show that the recommendation is better than traditional collaborative filtering algorithm both in quality and effect. The algorithm solves the data sparse problem effectively.


A Dynamic Adaptive Bit-rate Switching Algorithm for HTTP Streaming

WANG Cang-ling, LI Ze-ping

2017, 0(4):  27-31,37.  doi: 10.3969/j.issn.1006-2475.2017.04.006

Asbtract ( 180 )  

References | Related Articles | Metrics

Adaptive video streaming is an important mechanism for improving the performance of video delivery over mobile networks. By dynamically switching between different bit-rate versions of the same video, the mechanism can compensate for and adapt to the ever-changing network conditions. With limited client buffer and varying network， this paper proposes a new dynamic bit-rate switching algorithm. The proposed algorithm considers the following metrics in order to select different bit-rate versions of the video segment to improve the quality of video playback, which are: client buffer, excess video frames dropped per second, and available network bandwidth. It has been evaluated in dynamic real-time Internet environment by using the wired and wireless network. Experiment results show that the proposed algorithm can provide a good user experience in the dynamic network environment.


Vertical Search Engine for MOOC

LI Quan， LIN Song， TIAN Jun， LIU Xing-hong

2017, 0(4):  32-37.  doi: 10.3969/j.issn.1006-2475.2017.04.007

Asbtract ( 162 )  

References | Related Articles | Metrics

Learners need spend a lot of time in searching the satisfying courses of themselves in different platforms, as the large network open platform MOOC appears in recent years. A vertical search engine for MOOC is designed and implemented in order to improve the utilization efficiency of education resource in MOOC. This paper proposes a kind of optimization scheme of tightly coupled crawling and index of multithreading parallel. It can download the relative information of courses according to three kinds of methods of loading course list, and customize the extraction rules of relative information according to the feature of course Web page being analyzed. This paper also proposes a kind of prioritization method of similarity score in search ranking. The analysis on experiment result indicates that the evaluation values of average time of crawling and index, sorting effect and average mean value of correct rate etc increase to some extend by the vertical search engine for MOOC. Therefore, it achieves the integration, storage, and retrieval functions of education resource in MOOC, and satisfies the requirements of development of educational information.


Hyper-heuristic Genetic Cluster Algorithm Based on Self-organizing Map

XU Cong, HUANG Wen-zhun, HUANG Shi-qi

2017, 0(4):  38-43.  doi:10.3969/j.issn.1006-2475.2017.04.008

Asbtract ( 249 )  

References | Related Articles | Metrics

 Genetic clustering algorithm can obtain the optimal solution on the condition of the larger population, however, which leads to a slow convergence speed. In order to tackle the challenge problem, this paper proposes a novel hyper-heuristic genetic cluster algorithm based on self-organizing map. Firstly, the data space is converted to feature space by exploiting self-organizing map method. Secondly, one solution can be found by employing genetic algorithm in the feature space to diminish the computational load of the presented algorithm. Then， the one solution can be reflected to the data space. Moreover, another solution can be found by the K-means algorithm in the data space. The optimal solution is obtained according to the optimal method, which the same cluster results maintained and the different ones are clustered again to further ensure optimal solution. The extensive simulation results demonstrate the proposed algorithm has much higher accurate rate in the case of small population in comparison with genetic clustering algorithm.

SysML-based Avionics System Architecture Safety Evaluation

DENG Jia-jia1, CHEN Hai-yan1, ZHANG Yu-ping1, HE Yi-zheng2

2017, 0(4):  44-47,126.  doi:10.3969/j.issn.1006-2475.2017.04.009

Asbtract ( 227 )  

References | Related Articles | Metrics

Aiming at the problem that existing analysis methods for system safety separate the processes of system design and safety assessment, a SysML-based avionics system architecture safety evaluation method is proposed. At first, the physical architecture of the system is modeled based on SysML with Enterprise Architect. Then critical information about the system is refined from the XML document of the SysML model, based on which fault trees are established. Finally, after analyzing fault trees, system failure probability and zone safety are obtained. This process is conducted in an automatic safety assessment tool. A display system in IMA architecture is introduced as an example for conducting this method, which verifies the effectiveness of the proposed system architecture safety assessment tool.


Design of Rollback Recovery Fault Tolerance Simulation for Distributed System

DONG Qi1, HUANG Bin1, YAN Yao1, LI Wei-wei2, ZENG Wei-ni2, ZHANG Heng1,3

2017, 0(4):  48-51.  doi:10.3969/j.issn.1006-2475.2017.04.010

Asbtract ( 200 )  

References | Related Articles | Metrics

In order to solve the evaluation problem of the rollback recovery fault tolerance in the distributed computing system, a rollback recovery fault tolerance simulation was designed. According to the structure of the rollback recovery fault tolerance scheme, the nodes task process of the distributed computing system was simulated by the discrete events. The simulation function of the rollback recovery fault tolerance was added in the application layer based on the network simulation software. The related structure, function modules and system parameters were introduced in the proposed simulation. Finally, the proposal was evaluated that the proposed simulation method is capable of the evaluation of the different rollback recovery fault tolerance scheme, and can be utilized to compare, improve and optimize the related fault tolerant algorithms.


Analysis on Construction of American Naval Ordnance Deficiency Reporting System

FENG Yu-guang, TANG Jin-guo, TANG Jia-yu

2017, 0(4):  52-55,72.  doi:10.3969/j.issn.1006-2475.2017.04.011

Asbtract ( 244 )  

References | Related Articles | Metrics

 Based on the introduction of American Ordnance Deficiency Reporting Code, the category of American Naval Ordnance Deficiency Report, its management information system and the procedure and time limits of Deficiency Report are analyzed with emphasis, which may be an illumination of our naval ordnance equipment quality construction.


Research and Design of Smart Battery System Based on Reinforcement Computer

ZHEN Yun-qing, HU Xiao-ji

2017, 0(4):  56-61.  doi:10.3969/j.issn.1006-2475.2017.04.012

Asbtract ( 210 )  

References | Related Articles | Metrics

In order to improve the performence of battery system of rugged notebook, aiming at the power supply requirements of various embedded computers, this paper studies the power supply of the rugged notebook and designs a general Smart Battery System (SBS). The system takes battery as the host serial devices to implement management and generalization, making use of the character of the embedded computers having serial ports. Finally this paper supplies the battery charging and discharging performance graphs, the results show that the system works well in different equipments and systems, can provide high security and efficiency for reinforcement computers, and has wide universality.


Distributed Architecture for 3D Graphics Rendering in Collaborative System

ZHUANG Tian-long, LIANG Zheng-he, WANG Huai-ting

2017, 0(4):  62-66.  doi:10.3969/j.issn.1006-2475.2017.04.013

Asbtract ( 195 )  

References | Related Articles | Metrics

In the 3D collaborative systems, 3D graphics rendering efficiency and transmission rate affect the overall efficiency of the system. In this paper, a distributed architecture is designed to ensure that the 3D graphics rendering and transmission efficiency in the collaborative system. The rendered 3D graphics are in the form of photographs to generate an image transporting on the network, breaking the limitations of traditional 3D graphics rendering on browsers as well as mobile terminals that consume enormous resources limitations. In addition, through the establishment of multi-threaded. TCP communications on the server, it not only ensures the reliability of user interaction, but also avoids the operations ambiguity of multiple users simultaneous operation of 3D graphics. Finally it achieves users real-time interaction with 3D graphics, thereby improves the users experience.


Construction and Analysis of Uighur Emotional Corpus

TUERGONG, Wushouer SILAMU, Rexidan TUSERHONGTAI, YU Qing

2017, 0(4):  67-72.  doi:10.3969/j.issn.1006-2475.2017.04.014

Asbtract ( 301 )  

References | Related Articles | Metrics

For the problems of lacking standardization on criterion of Uighur sentiment corpus, small scale corpus， and no suitable tagging system, we built a tagging criterion for Uighur sentiment corpus by analyzing the advantages of famous sentiment corpuses in English and Chinese and combining the characteristics of Uighur text. We also developed a tagging system which can collect data from the Internet using Python language and built a Uighur sentiment corpus. The corpus can be used in the analysis of public opinion. Experimental results show that the tagging criterion is of expandability and practicability, the tagging system can effectively reduce the workload and improve the quality of sentiment corpus, and the sentiment corpus can be used for the public opinion analysis task.


Sentiment Classification of Short Texts on Internet Based on Convolutional Neural Networks Model

LIU Xiao-ming1,2, ZHANG Ying1,2, ZHENG Qiu-sheng1,2

2017, 0(4):  73-77.  doi: 10.3969/j.issn.1006-2475.2017.04.015

Asbtract ( 169 )  

References | Related Articles | Metrics

Sentiment classification aims to find the users views on hot issues, but now the format of the short texts on the Internet is not normative, the effect of traditional sentiment classification method is not ideal. Facing the information of the short texts on the Internet of big data, this paper puts forward a deep convolution neural network (CNNs) model of the short text on the Internet. First it uses the Skip-gram in the Word2vec training model as the feature vector, then further extracts feature vector into CNNs, finally trains the classification model of the depth convolution neural network. The experimental results show that, compared with classification methods of traditional machine learning, this method not only can effectively handle emotion classification of the short texts on the Internet, but also improves the accuracy of emotion classification significantly, the average increased by about 5%。


Internet Short-text Classification Method Based on CNNs

GUO Dong-liang, LIU Xiao-ming, ZHENG Qiu-sheng

2017, 0(4):  78-81.  doi: 10.3969/j.issn.1006-2475.2017.04.016

Asbtract ( 170 )  

References | Related Articles | Metrics

The Internet short-text classification is a hot research topic in natural language processing. This paper presents a short text classification method based on deep learning’s convolutional neural networks. First short-text features are achieved by the Skip-gram model of Word2vec, then it is sent into the CNNs to extract high-level features, after the K-max pooling, it is put into the Softmax classifier to get a classification model. In the Internet short-text classification experiments, compared to machine learning and DBN’s method, the results show that the proposed method not only solves the problems of the curse of dimensionality of text vector and the local optimal solution, but also effectively improves the accuracy of Internet short-text classification, and confirms the validity of the Internet short-text classification method based on CNNs.


Overview on Big Data Query

ZHANG Yu-jie, YU Shuang-yuan

2017, 0(4):  82-88.  doi:10.3969/j.issn.1006-2475.2017.04.017

Asbtract ( 254 )  

References | Related Articles | Metrics

Big data has the characteristics such as summed up to volume, variety, velocity and veracity while traditional data doesnt have. As traditional technology doesnt meet the big data query, big data query technology has arose at the historic moment and was maturing rapidly. From the perspective of big data query, this paper analyzed the big data storage technology, big data processing platform and big data query engine, etc. This paper introduced traditional relational database, NoSQL, NewSQL and their application on big data query processing. Also, the current popular big data processing platforms and the big data query engines running on them were introduced, and an overview about their advantages and disadvantages was made.


Big Data Analytics Technology Based on MOOC

SUN Xiao-yin, ZHOU Wei

2017, 0(4):  89-93,108.  doi:10.3969/j.issn.1006-2475.2017.04.018

Asbtract ( 288 )  

References | Related Articles | Metrics

In recent years, MOOC developed well and accumulated massive behavior data in the process of using vast teaching resources. Therefore, big data analytics technology based on MOOC is a new research trend and its frame can be involved in four stages: where to get big data (Where), what are data types of MOOC (What), how to deal with big data (How) and do with applications (Do). The paper arranges research status and describes characteristics and classifications of MOOC, then puts forward a framework of Where-What-How-Do for big data analytics. At last, it designs and displays an experiment with multiple regression analysis and cluster analysis on Canvas Network dataset, and makes conclusions on MOOC data of some insight and applications.


Design of Multiple-flow Timing Channel in Software-defined

YIN Su-kai1, LIU Guang-jie1, LIU Wei-wei1, ZHAI Jiang-tao2, DAI Yue-wei1,2

2017, 0(4):  94-98,104.  doi:10.3969/j.issn.1006-2475.2017.04.019

Asbtract ( 224 )  

References | Related Articles | Metrics

Software-defined networks (SDN), different from traditional network, is a new network architecture with the separation of application layer, control layer and data layer. In this paper, covert communication in SDN is studied, a multiple-flow timing channel scheme is proposed based on the interaction characteristic between OpenFlow controllers and switches, which utilizes the arriving time of reply packets in link layer discovery protocol to transmit secret messages. Simulation results show that the proposed scheme can achieve well covertness and robustness.


Formal Verification Method of Secure Operating System Based on Isabelle/HOL

GUO Yi, YANG Wei-yong, LIU Wei

2017, 0(4):  99-104.  doi:10.3969/j.issn.1006-2475.2017.04.0020

Asbtract ( 468 )  

References | Related Articles | Metrics

As the cornerstone of the information age, the importance of operating system security is self-evident. Conventional methods of software testing are not enough to guarantee the safety of the operating system, so we need to use more rigorous formal verification methods based on mathematical logic. This paper puts forward a new idea of formal verification of software: constructing a simulation running environment in Isabelle, and running the assembly code in it, recording the changes of the system state, and finally according to the changes of system state before and after run of the program, determining the correctness and safety of the program. It emphatically introduces the prove method of sequential, conditional and iterative structure, uses them on to a sample program, and gets the state  changes under any preconditions.


An Identity-based Blind Signature Scheme and Its Security Proof

MAO Yu-fang, DENG Lun-zhi

2017, 0(4):  105-108.  doi:10.3969/j.issn.1006-2475.2017.04.021

Asbtract ( 259 )  

References | Related Articles | Metrics

Blind signature is a special digital signature which can protect the user’s privacy. At present, most of the blind signature schemes use the bilinear pairings, so the cost of computing is relatively high, and a part of the schemes do not give the proof on security. To deal with these problems, a new blind signature scheme based on identity is proposed, it is proved to be security based on n-CDH problem in the random oracle model. The scheme does not use bilinear pairing in signing and uses only once bilinear pairing in verification, compared with other blind signature schemes, the cost of computing is lower.


Android Malware Application Detection Method Based on BPSO-NB

HAN Jing-dan, SUN Lei, WANG Shuai-li, WANG Ze-wu

2017, 0(4):  109-113.  doi:10.3969/j.issn.1006-2475.2017.04.022

Asbtract ( 227 )  

References | Related Articles | Metrics

 In order to improve the efficiency of Android malware application detection, the binary particle swarm optimization (BPSO) is used for optimal selection of complete ensemble of original features, combined with the Nave Bayesian (NB) classification algorithm，an Android malware detection method based on BPSO-NB algorithm is proposed. First, this method uses static analysis for unknown applications to extract the permission information in an AndroidManifest.XML file as a feature. Then, it uses the BPSO algorithm to optimize selected classification feature,  and uses the classification accuracy of  NB algorithm as the evaluation function. Finally, NB classification algorithm is used to construct classifier for Android malicious applications. Through cross experiment, BPSO-NB classification equipment has higher classification accuracy, and the optimal selection of BPSO algorithm classification characteristics under the condition of the security classification accuracy can effectively improve the efficiency of detection.

Attribute-based Encryption Scheme of Efficient Full-verifiable Outsourced Decryption

WANG Yao, LI Fei-fei, WANG Gang

2017, 0(4):  114-117.  doi:10.3969/j.issn.1006-2475.2017.04.023

Asbtract ( 212 )  

References | Related Articles | Metrics

Attribute-based encryption can protect the security of users data, but the decryption cost grows linearly with the complexity of access policy. Outsourced decryption technology makes the users only need a little overhead to decrypt and obtain the plaintext. However, a large number of decryption operations of outsourced decryption technology are dealt with  by cloud service providers. But the cloud service providers are regarded as semi-trusted (honest but curious). So it is necessary to verify the correctness of outsourced decryption to ensure security for users data. This paper proposes an efficient ABE scheme with full-verifiable outsourced decryption, it makes both the authorized users and unauthorized users can verify the correctness of the transformed ciphertext.


Designated Server Identity-based Encryption with Conjunctive Keyword Search Scheme

WANG Gang, LI Fei-fei, WANG Yao

2017, 0(4):  118-121.  doi:10.3969/j.issn.1006-2475.2017.04.024

Asbtract ( 249 )  

References | Related Articles | Metrics

Public key encryption with keyword search (PKES) allows a user to send a trapdoor of some searched keywords to a server, which will enable the server locate all encrypted data containing the searched keywords. To remove the secure channel between the server and the receivers in the previous identity-based encryption with keyword search (IBEKS) schemes, Wu et al. proposed a designated server identity-based encryption with keyword search (dIBEKS) scheme. However, Wu et al.’s dIBEKS scheme can not satisfy the ciphertext indistinguishability. To overcome the security weakness in Wu et al.’s scheme and provide the functionality of multiple keywords searching, we put forward a designated server identity-based encryption with conjunctive keywords search scheme. The security analysis shows that the proposed scheme simultaneously satisfies the security of ciphertext indistinguishability, trapdoor indistinguishability and off-line keyword-guessing attack. Comparison analysis shows that the proposed scheme is more efficient and practical.

Simulation of Web Crawler Detection Algorithm Based on Hidden Markov Model

JU Xing-kong

2017, 0(4):  122-126.  doi:10.3969/j.issn.1006-2475.2017.04.025

Asbtract ( 252 )  

References | Related Articles | Metrics

In the construction and maintenance process of the website, in order to improve server efficiency, strengthen security and confidentiality, developers need to distinguish between human users and Web crawlers. However, some inappropriate or malicious designs make it difficult to detect crawlers. These crawlers not only increase the burden on the site, but also endanger the security of network. In order to solve the problem that it is difficult to detect crawlers, a detection algorithm based on behavior pattern is proposed, which uses hidden Markov model to describe the behavior patterns of different clients and uses Matlab simulation to achieve a highly accurate detection result. The simulation results show that the detection technology of hidden Markov model can detect Web crawler with high accuracy and low error rate.
