Loading...

Table of Content

      
    20 March 2019
    Volume 54 Issue 3
     
    Security domain-based data isolation protection framework for Hive
    Tian-tian CHANG,Xing-shu CHEN,Yong-gang LUO,Xiao LAN
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  1-9.  doi:10.6040/j.issn.1671-9352.2.2018.073
    Abstract ( 678 )   HTML ( 139 )   PDF (1780KB) ( 208 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Aiming at the problem of sensitive information leakage caused by data sharing in Hive database, a data isolation and protection framework (SD-DIPF) based on security domain is proposed, which is combined with data classification and tag-based access control technology. Firstly, the tag level is divided by the hierarchy security tag tree which is used to identify the subject and object in the system. Then, the design idea of security domain (SD) is illustrated with hierarchical tags, the definition of SD and its subdomains and formal proof of security are given. Finally, the platform data is logically partitioned by security domain to ensure the effective isolation of different sensitive levels data. The applicability of SD-DIPF to Hive database is illustrated, and its implementation in Hive database is given based on the existing authentication mechanism. The experimental results show that SD-DIPF can protect sensitive data from being illegally accessed, which proves the feasibility and security of the framework.

    Sensitive attribute iterative inference method for social network users
    Xiao-jie XIE,Ying LIANG,Xiang-xiang DONG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  10-17, 27.  doi:10.6040/j.issn.1671-9352.2.2018.084
    Abstract ( 374 )   HTML ( 9 )   PDF (949KB) ( 167 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Analyzing and inferring sensitive information of social network users is conducive to technically quantifying the degree of privacy leakage and protecting privacy. Aiming at the problem that existing user attribute inference methods needs to make strong assumptions on the value of user attributes, an iterative method for user sensitive attributes in social network is proposed by combining the RL iterative classification framework and extending the wvRN relation inference method. Extracting probabilities of user sensitive attributes based on user text and convolution neural network and iteratively updating inference results with neighboring nodes, not only weakens the assumption of user attributes, but also improves the degree of application. The experimental results show that by obtaining a small amount of labeled data in social networks and setting reasonable parameter values for iterative inference methods, better user sensitive attribute inference results can be obtained.

    Security analysis model of behavior based on cryptographic protocols implement at source code level
    Fu-sheng WU,Huan-guo ZHANG,Ming-tao NI,Jun WANG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  18-27.  doi:10.6040/j.issn.1671-9352.2.2018.053
    Abstract ( 299 )   HTML ( 4 )   PDF (692KB) ( 104 )   Save
    Figures and Tables | References | Related Articles | Metrics

    An analytical model of the behavior based on the cryptographic protocols implement at source code level is proposed. The cryptographic protocol implementations can be divided into two parts by the model that is proposed. One is an external behavior (the behavior of opening the interactive communications in cyberspace); the other is an internal behavior (the behavior of cryptographic protocol implements at the source code level). Though the behavior controllability, it is possible to find, control, or correct the security of the cryptographic protocol implementations at the source code level. Based on the analysis model method, a simulation experiment using classic cryptographic protocol as an example was given. The results show that the behavioral security of the cryptographic protocol implementations is controllable.

    A survey of visual saliency and salient object detection methods
    Jia XU,Peng JIANG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  28-37.  doi:10.6040/j.issn.1671-9352.0.2018.601
    Abstract ( 919 )   HTML ( 17 )   PDF (7152KB) ( 138 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Saliency detection aims to locate the most attractive areas in image or video data, as the basic task of computer vision field, has receive intensive attentions. Many methods have been proposed recently, these methods usually can be classified into two branches: visual saliency detection and salient object detection. Tough the methods of two branches usually share the similar features and even the frameworks, their performances on datasets of different branch have large gap, seldom works have compared and analyzed them. In this work, we will provide a detailed review and analysis of main works in two branches, including their mechanism, metrics and datasets. Besides, in this work, we summarized approaches to boost visual saliency detection methods for the task of salient object detection. With these approaches, visual saliency detection methods can be applied to detect the salient object and show superior performance that even outperform some specialized state-of-the-art salient object detection methods, thus reduce the performance inconsistence in different specialized datasets.

    A modeling method of user growth profile
    Zhe-jin DONG,Jian WANG,Ling-fei QIAN,Hong-fei LIN
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  38-45.  doi:10.6040/j.issn.1671-9352.1.2018.149
    Abstract ( 448 )   HTML ( 9 )   PDF (1933KB) ( 105 )   Save
    Figures and Tables | References | Related Articles | Metrics

    User growth value reflects users stickiness, and growth value prediction is important to accurate marketing. This paper focuses on the study of users growth portraits. For problems, disorganized raw data and unpredictable user features, this paper applies scatter diagram analysis to extract behavior features and stable time features influencing the users growth value, and compares two feature selection theories, Tree-based and L1 norm to recognize key features. For the issue of insufficient labeled training dataset, this paper improved the COREG algorithm, enriching labeled dataset through semi-supervised regression, promoting the prediction accuracy, and reducing the algorithms time complexity. Finally, this paper utilizes Stacking method to integrate different models advantages. Experiments based on the data from SMP CUP 2017, provided by the CSDN blog platform, show that the methods proposed in this paper effectively enhances models generalization ability and prediction accuracy.

    User sentiment tendency aware based Micro-blog sentiment analysis method
    Jie WU,Xiao-fei ZHU,Yi-hao ZHANG,Jian-wu LONG,Xian-ying HUANG,Wu YANG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  46-55.  doi:10.6040/j.issn.1671-9352.1.2018.159
    Abstract ( 724 )   HTML ( 12 )   PDF (1385KB) ( 145 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Micro-blog's speech often has strong sentimental color, and the sentiment analysis of Micro-blog's speech is an important way to get users' opinions and attitudes. Many researchers conduct research via focusing on the parts of speech (POS), emotion symbol and emotion corpus. This paper proposes a novel method for Micro-blog sentiment analysis, which aims to identify the sentiment features of a text by modeling user sentiment tendency. Specifically, we construct a sentiment information embedded word embedding sequence, and input it into a long short term memory (LSTM) model to get a sentiment embedded output representation. Then we merge both the user sentiment tendency score and the output representation of LSTM, and use it as the input of a fully connected layer which is followed by a softmax layer to get the final sentiment classification result. The experiment shows that the performance of our proposed method UA-LSTM is better than all the baseline methods on the sentimental classification task, and it achieves the F1-score up to 0.91, with an improvement of 3.4% over the best baseline method MF-CNN.

    Tag recommendation with multi-source heterogeneous networked information
    Heng-ze BAO,Dong ZHOU,Tan WU
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  56-66.  doi:10.6040/j.issn.1671-9352.1.2018.100
    Abstract ( 429 )   HTML ( 3 )   PDF (6680KB) ( 138 )   Save
    Figures and Tables | References | Related Articles | Metrics

    Tags have been utilized extensively to associate various online resources, such as articles, images and movies, aiming at helping users understand and facilitate the process of managing and indexing huge web resources. Since it is time-consuming and prone for errors to create manual tags for these resources, automatic tag recommendation techniques have attracted widespread attention. At present, most tag recommendation methods mainly recommend tags by mining content information of resources. However, Most data information in the real world do not exist independently. For example, science articles have a complex network structure by referencing each other. The research show that the topology information and text content information of resources describe the similar semantic features of re-sources from two different perspectives, and the information from two aspects can complement and explain for each other. Based on this, we propose a probabilistic topic model and a tag recommendation method for simultaneously modeling content information and topology structure information of resource. This method uses multi-source heterogeneous information, such as tagging relationship between tag and resource content and link relationship between resources to mine potential semantic information of the resources to recommend several tags with similar functional semantics for the new resources. The experimental results on two real data sets prove the effectiveness of our proposed method.

    Automatic extraction of key information for news web pages based on tag and block features
    Xue-mei WANG,Xing-shu CHEN,Hai-zhou WANG,Wen-xian WANG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  67-74.  doi:10.6040/j.issn.1671-9352.2.2018.212
    Abstract ( 578 )   HTML ( 7 )   PDF (649KB) ( 141 )   Save
    Figures and Tables | References | Related Articles | Metrics

    In view of that issue of news key information extraction require manual construction template or training generation template, provide news key information automatic extraction method based on label and block characteristics. The method first locates the news body block by calculating the relevant characteristics of the text block, then position the news title block by editing distance, and finally locates the press release time and source label block according to the text block and title block, and finally obtains the target news key information by extracting the text of each block. On the basis of this method, propose an automatic news extraction framework for news sites, and uses this framework to extract news from 30 news columns of 10 news sites. A total of 1597 news data are collected, and 1000 of them are randomly selected for the experiment. The experimental results show that this method has a good extraction effect on news title, publish time, source and text, and is superior to the comparison objects.

    Input-output finite time stability for event-triggered control of switched singular systems
    FENG Na-na, WU Bao-wei
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  75-84.  doi:10.6040/j.issn.1671-9352.0.2018.297
    Abstract ( 366 )   PDF (545KB) ( 435 )   Save
    References | Related Articles | Metrics
    The input-output finite-time stability for event-triggered-based switched singular systems is investigated. Concept of input-output finite-time stability for switched singular systems is given, and an event-triggered condition is proposed. The dynamic output feedback controller based on event-triggered mechanism is designed, by applying the Lyapunov function technique and average dwell time approach, some sufficient conditions for input-output finite-time stability of the switched singular closed-loop systems are derived, furthermore, dynamic output feedback controller parameters are obtained. Lastly, a numerical example is employed to illustrate the validity of the theoretical results.
     
    Identification of large intergenic non-coding RNAs using random forest
    Wei-na XU,Guang-le ZHANG,Shi-hong LI,Yuan-yuan CHEN,Qiang LI,Tao YANG,Ming-min XU,Ning QIAO,Liang-yun ZHANG
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  85-92, 101.  doi:10.6040/j.issn.1671-9352.0.2018.261
    Abstract ( 254 )   HTML ( 5 )   PDF (2464KB) ( 172 )   Save
    Figures and Tables | References | Related Articles | Metrics

    A data source for understanding lincRNAs′ regulatory mechanisms by accurate identification is provided. With the features of minimum free energy and signal-noise ratio, we remove the redundant features by feature contribution. Thus, we develop a machine learning model (random forest) based on random forest algorithm to identify lincRNAs. After inspecting with the same experimental dataset, we prove that the sensitivity, specificity and accuracy of this new method have reached 94.1%, 93.2% and 93.7%, which are higher than the current identification index of the methods of PhyloCSF, LncRNA-ID and CPC. The method proposed in this paper shows better robustness and effective classification.

    A chunk increment partial least square algorithm
    ZENG Xue-qiang, YE Zhen-lin, ZUO Jia-li, WAN Zhong-ying, WU Shui-xiu
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  93-101.  doi:10.6040/j.issn.1671-9352.1.2018.051
    Abstract ( 337 )   PDF (550KB) ( 117 )   Save
    References | Related Articles | Metrics
    For the data mining of large-scale data, incremental learning is an effective and efficient technique. As an improved partial least square(PLS)method based on incremental learning, incremental partial least square(IPLS)has a competitive dimension reduction performance. However, there is a drawback in this approach that training samples must be learned one by one, which consumes a lot of time on the issue of on-line learning. To overcome this problem, we propose an extension of IPLS called chunk incremental partial least square(CIPLS)in which a chunk of training samples is processed at a time. Comparative experiments on k8 cancer rescue mutants data set and Reuter-21578 text classification corpus show the proposed CIPLS algorithm is much more efficient than IPLS without sacrifice dimension reduction performance.
    Fixed-radius nearest neighbor progressive competition algorithm for imbalanced classification
    ZHOU Peng, YI Jing, ZHU Zhen-fang, LIU Pei-yu
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  102-109.  doi:10.6040/j.issn.1671-9352.1.2018.107
    Abstract ( 400 )   PDF (609KB) ( 126 )   Save
    References | Related Articles | Metrics
    There is a problem called class imbalance in many real-world datasets. When traditional classification algorithms classifying imbalanced data, it is easy to misclassify the minority class. In order to improve the classification accuracy of the samples from the minority class, this paper proposes a fixed-radius nearest neighbor progressive competition algorithm(FRNNPC). As a preconditioning, FRNNPC eliminates ineligible samples globally through the fixed-radius nearest neighbor rule, and use the NPC in the obtained candidate data to gradually calculate the score of the nearest neighbor sample of the query sample until the sum of the scores of the one class is higher than another class. In short, this method can effectively deal with the imbalance problem, and does not require any manually set parameters. The experimental results compare the proposed method with four representative algorithms applied to 10 imbalanced data sets, and illustrate the effectiveness of the algorithm.
    Channel pricing strategy of supply chain considering vertical E-commerce
    XIAO Min, YU Min, HE Xin-hua
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  110-118.  doi:10.6040/j.issn.1671-9352.0.2018.159
    Abstract ( 280 )   PDF (648KB) ( 151 )   Save
    References | Related Articles | Metrics
    With the development of network, the introduction of vertical E-commerce has become an inevitable choice for manufacturers. Manufacturers need to weigh the direct selling price after introducing vertical E-commerce and the wholesale price to retailers. In the case of symmetric information, two kinds of channel supply chain systems were studied, which were composed of manufacturer, traditional retailer and whether introduced into a vertical E-commerce. Considered the influence of price and service sensitivity on the pricing decision of manufacturers, and the comparison of two supply chain systems pricing strategies. It is a better choice that manufacturers choosing to introduce vertical E-commerce for their own and the consumers. The price of manufacturer direct channel has been reduced by the vertical E-commerce is introduced, the wholesale price to the traditional retailer has been increased, but slightly lower than the wholesale price of vertical E-commerce, the specific price of the market influenced by the price and service sensitivity.
    Study on the way to improve the satisfaction of logistics outsourcing——A fuzzy set qualitative comparative analysis of 102 cases
    ZHANG Ke-yong, LYU Mei-lin, YAO Jian-ming, WANG Hao
    JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE). 2019, 54(3):  119-126.  doi:10.6040/j.issn.1671-9352.0.2018.280
    Abstract ( 244 )   PDF (756KB) ( 144 )   Save
    References | Related Articles | Metrics
    The theoretical model of “service quality perception-satisfaction” of logistics outsourcing is constructed. Using 102 questionnaires from 42 manufacturing enterprises in Chengdu Hi-tech West District and Pidu District as samples, the model hypothesis is validated by partial least squares structural equation. Based on the perception of service quality, the structure of realizing high satisfaction of logistics outsourcing is analyzed; the asymmetric causal relationship between configuration and satisfaction is found. It is found that the most important way to achieve high customer satisfaction is to enhance the professionalism of staff and provide one-stop integrated service for customers in logistics enterprises, quick response to customer service is the core condition to achieve customer satisfaction, providing reliable, accurate and punctual service is an auxiliary condition to achieve customer satisfaction. The low customer satisfaction is analyzed and the specific suggestions on how to achieve high customer satisfaction and how to avoid minefields that lead to low customer satisfaction for logistics enterprises are given.