Volume 43,Issue 7,2020 Table of Contents

  • Display Type:
  • Text List
  • Abstract List
  • 1  The application of consortium blockchain in health inspection system for special equipments on service security and privacy protection
    ZHAO Hui WEN Junhao HUANG Qiuzi ZHOU Wei YANG Zhengyi
    2020, 43(7):1-5. DOI: 10.11835/j.issn.1000-582X.2020.245
    [Abstract](602) [HTML](481) [PDF 854.89 K](740)
    Abstract:
    The construction of special equipments, health detection and monitoring cloud platform starts the process of "service" of the whole industry, which can achieve a lot in service reuse and service precipitation.However "service" brings advantages as well as some challenges. Since it requires remote service calls and needs to share some industry data, data security and privacy protection during service invocation become a major problem, the solution of which is the focus of this paper. The establishment of the special equipment health detection system based on the consortium blockchain technology was proposed to solves the data security and privacy protection problems in the service invocation process, providing protection for service security and privacy to some extent.
    2  Construction of distributed spatial-temporal correlation service network and its application to IOT service discovery
    YANG Dongju ZHAO Zhuofeng
    2020, 43(7):6-18. DOI: 10.11835/j.issn.1000-582X.2020.233
    [Abstract](574) [HTML](439) [PDF 3.11 M](800)
    Abstract:
    With the rapid increase in the number of IOT (Internet of Things) services, distributed management of IOT services is an inevitable trend. Quick discovery of a set of IOT services based on spatial-temporal properties is the primary issue in the management and use of IOT services. The traditional method of service discovery based on syntactic or semantics usually faces a mass and isolated set of services, and the service discovery time is closely related to the service number. Besides, the result cannot be reused in the service discovery request with multiple iterations. To solve the above problems, this paper proposed a method for distributed spatial-temporal properties related service network building, using the paradigmatic relations of spatial-temporal properties to build service connection relationship between the isolated services. The services were organized and managed by constructing spatial-temporal related service network. The focus of this research was on the construction and evolution of spatial-temporal related service network in distributed environment. Finally, the rapid discovery of services based on service network was discussed in the case of highway emergency handling scenario.
    3  Service composition based on directed bipartite graph in graph database
    FAN Guodong LI Jing ZHU Ming WU Zhiyong YAN Song
    2020, 43(7):19-29. DOI: 10.11835/j.issn.1000-582X.2020.242
    [Abstract](549) [HTML](435) [PDF 1.13 M](577)
    Abstract:
    The advent of cloud computing and big data era has promoted the development of web services. Due to the complexity of user requirements, when a single service cannot meet the requirements, multiple services can be composed to provide solutions. As there are a lot of services in the cloud, it is non-deterministic polynomial hard to find a proper service composition. This paper proposes a method to solve the problem of composition by using the graph database. Through constructing a service composition graph based on a directed bipartite graph, services are pre-composed and stored in a Neo4j graph database,using the least service composition query and Dijkstra search algorithm to find the solution with the least number of services or the best quality of service. In addition, service compositions in the graph database can be added, deleted, and updated according to the availability of services. The experimental results show that the method can find the service composition that meets the user's needs in a short time in the graph database.
    4  A time-improved manufacturing service flow optimization method with QoS assurance
    TAN Wei LIU Xuan CHEN Yi YANG Erfu LI Yun WEI Wenhong
    2020, 43(7):30-41. DOI: 10.11835/j.issn.1000-582X.2020.238
    [Abstract](578) [HTML](1030) [PDF 553.91 K](892)
    Abstract:
    Manufacturing service process is a manufacturing service chain based on business process, which have four basic structures:sequence, selection, loop and parallelism. Since the loop can be transformed into sequential structure, the selection structure and parallel structure are real branch structures. Branch structures often have service capability difference, with the results that the selection branch will delay time due to improper probability allocation, while the parallel branch will be in a waiting state, which will inevitably affect the overall execution efficiency of business process. A time-improved manufacturing service flow optimization method with QoS assurance was proposed in this paper. Firstly, the attribute calculation method of the basic structure of business process was constructed, and then by analyzing the influence relationship between the time of several branch structures and other attribute factors, the layering and blocking linear programming model of branch structure time optimization based on QoS constraint was established, and the hierarchical and block optimization algorithm was designed. An example of the process to be optimized was selected in the experiment, and the execution time of the optimized business process was reduced by 5.4%, which showed that the model and its optimization algorithm are effective and reasonable. This study has positive significance for the application of cloud manufacturing.
    5  Point of interest recommendation based on location category and social network
    TANG Haoran ZENG Jun LI Feng WEN Junhao
    2020, 43(7):42-50. DOI: 10.11835/j.issn.1000-582X.2020.234
    [Abstract](751) [HTML](976) [PDF 558.18 K](874)
    Abstract:
    With the rapid development of internet and global positioning technology, location-based social network (LBSN) is emerging in large numbers which encourages users to share their personal feelings and locations in real time by check-ins. Volumes of check-in data afford an opportunity for mining user preference, which promotes location-based services such as point of interest (POI) recommendation. POI recommendation can not only help users identify favorite locations, but also help POI owner acquire more target customers. A location's category is the accurate abstraction of the context semantics of location. Most of present research only directly considers user preference on a specific location and ignore consideration of location's category. In Yelp, we find the ratio of common visited location is lower than that of common visited location category, which means that considering user preference on location category is more reasonable than that on specified locations. In light of the above, we present a novel POI recommendation method based on location category and social network named CSRS which infers users' preference on category from their check-ins history, and at the same time take the differences of category preferences among friends into consideration. The experimental results on Yelp demonstrate CSRS achieves superior precision and recall compared to other recommendation techniques.
    6  Service recommendation based on user network representation learning
    YANG Yuling WANG Aorong WU Hao DONG Lin HE Peng
    2020, 43(7):51-62. DOI: 10.11835/j.issn.1000-582X.2020.237
    [Abstract](639) [HTML](387) [PDF 917.25 K](608)
    Abstract:
    Network embedding has been a popular branch of deep learning, which represents the network information by mapping network nodes to an extended low-dimensional space. According to user co-tag network and social network, we employed network representation learning to extract the representation vector of tagging relationship and social relationship of users respectively, and proposed a novel service recommendation method, using user's representation vector learned to calculate the similar user set and recommend appropriate services to the target users according to the preferences of top-k similar users. To investigate the feasibility of our approach, experiments were carried out on two open data sets, Delicious and Last.FM. The results show that our method outperforms the four benchmarks, with an average improvement of 13% in precision, 18.6% in recall and 13.1% in F-measure. It is also found that when learning user representation, the co-tag relationship between users is as important as the social relationship. Meanwhile, during the process of collaborative recommendation, the number of similar users returned for a target user is suitable in the range from 25 to 30.
    7  Online service reputation measurement for error minimization
    ZENG Junwei FU Xiaodong YUE Kun LIU Li LIU Lijun FENG Yong
    2020, 43(7):63-74. DOI: 10.11835/j.issn.1000-582X.2020.239
    [Abstract](445) [HTML](1015) [PDF 874.77 K](658)
    Abstract:
    Since each online service can be objectively compared by its own real quality, there is a potential truth ranking of services. In order to provide users with the most authentic and objective online service reputation ranking as a reference for choosing services, service reputation should be as close as possible to the true service ranking. In this paper, an online service reputation measurement method for error minimization was proposed and it regarded user preference ranking as a noisy estimation of real service ranking. Firstly, Kendall tau distance was used to measure the error between service ranking and truth ranking. Then, the possible ranking of truth services was found by setting the upper limit of the average error between the truth and the user's preference ranking set. Finally, the service ranking with minimum average error between itself and the possible sets of service ranking was found as the service reputation. Because all the service ranking could be the truth ranking, causing the computational difficulty of this method, the branch-and-cut algorithm was used to optimize the solution. Based on the real and simulated data sets, experiments were carried out and the result showed that reputation measurement results could be obtained with less error between it and the truth while ensuring the operation efficiency.
    8  View-driven flow data oriented real-time processing and service system
    DI Cheng YANG Zhongguo HAN Yanbo LIU Chen
    2020, 43(7):75-83. DOI: 10.11835/j.issn.1000-582X.2020.241
    [Abstract](584) [HTML](535) [PDF 4.12 M](966)
    Abstract:
    The processing requirements of these data are also complex and changeable. The business personnel need to carry out corresponding algorithm customization, which involves not only relevant programming knowledge, but also cumbersome processing flow and lengthy development cycle. In order to solve the above problems, this paper designed and implemented a stream data processing and service system based on process modeling, which provided real-time access to multi-source stream data, stream data service and stream data processing service. The system encapsulated the stream data processing process into a service provided to the user, allowing the user to drag and drop the combined stream data processing and service module, configure relevant parameters, define the process of stream data processing and service, and implement stream data processing and service-oriented tasks quickly and naturally. The processing results were pushed to other application systems in real time through service routes to meet different business needs. Case studies show that the system is more efficient, flexible, and configurable than traditional streaming data processing systems, and has advantages in terms of usability, availability, and scalability.
    9  Location-oriented ultra-wide-band indoor positioning algorithm
    FU Wentao DONG Xingbo FU Qiang JI Yuanfa SUN Xiyan HE Qian
    2020, 43(7):84-90. DOI: 10.11835/j.issn.1000-582X.2020.243
    [Abstract](549) [HTML](888) [PDF 1.71 M](858)
    Abstract:
    Ultra-wide-band technology has important application value for location services due to its high ranging accuracy and penetration performance. In the actual high-density positioning environment, the traditional positioning algorithm is affected by non-line-of-sight error and multipath effect, and it is difficult to accurately calculate the actual position coordinates in real time. Although increasing the number of base stations can effectively improve the accuracy of positioning, its cost also increases. Aiming at the improvement of the accuracy and robustness of positioning, an ultra-wideband positioning method based on support vector machine was proposed to solve the problem of poor real-time performance and low positioning accuracy of ultra-wideband in high-density indoor positioning. A support vector machine model based on TDOA(TDOA, time difference of arrival) was given, with focus on transformation of the problem of location into the problem of classification. The support vector machine classification model was established by TDOA values and coordinate values. The one-to-one classification model was used to solve the coordinate values and improve the coordinate solution speed. The simulation results show that in the high-density real-time positioning, compared with the traditional Chan algorithm and Taylor algorithm, the method has higher real-time performance when the positioning accuracy is similar, which meets requirements for the actual positioning with its low power consumption, fast and high precision.
    10  Research on data-to-text generation based on transformer model and deep neural network
    XU Xiaohong HE Ting WANG Huazhen CHEN Jian
    2020, 43(7):91-100. DOI: 10.11835/j.issn.1000-582X.2020.244
    [Abstract](1938) [HTML](759) [PDF 952.80 K](1000)
    Abstract:
    Data-to-text generation is a natural language processing method that generates coherent text from structured data. In recent years, data-to-text generation have shown great promise of profit due to the popular neural network architectures which are trained end-to-end. This method can automatically process large amounts of data and generate coherent text and is often used in news writing, report generation, etc. However, there are some defects in the reasoning of information such as the data of specific value and time in the existing researches, which make it unable to make full use of the structural information of data to provide reasonable guidance for the generation. Beyond that the generation process is prone to separate semantic from syntactic when training. In this paper, a data-to-text generation method based on transformer model and deep neural network was proposed, and the algorithm of transformer text planning(TTP) was also introduced so as to effectively control the context information of the generated text and remove the deficiencies of the previous model that resulted in semantics and syntax separation. Experiment results on the Rotowire public dataset show that the method proposed outperforms the existing model and it can be directly applied to the generation task of scattered data to coherent text.
    11  ADMM-based coordinated EV charging scheduling algorithm
    CHAI Zhifu HE Gaoqi LU Xingjian
    2020, 43(7):101-110. DOI: 10.11835/j.issn.1000-582X.2020.201
    [Abstract](790) [HTML](851) [PDF 1.85 M](878)
    Abstract:
    With the increasing number of electric vehicles (EVs), the out-of-order random charging behaviors cause the smart grid overload and the battery depreciation. Despite the fact that a lot of research has focused on EV charging coordination, it remains unexplored how to coordinate the EV charging while maximizing the convenience of EV drivers and minimizing the battery depreciation, which is a vital to the improvement of service quality of the charging station and the users' satisfaction, since the convenience and lifetime of battery are specially concerned by EV drivers. In this paper, we systematically studied the problem and a real-time charging scheme was proposed to coordinate the electric vehicle (EV) charging and decrease the battery depreciation. To prevent private leak and decrease calculation complexity, an ADMM-based distributed method was proposed. Extensive evaluations show that our distributed optimization method brings significant cost savings over existing methods. Simulation results show that the proposed algorithm could reduce the price cost of EV drivers and battery lifetime depreciation by up to 18.3% and 33.0% respectively.
    12  Concept dependency mining method for Wikipedia
    ZHOU Yang XIAO Kui ZENG Cheng
    2020, 43(7):111-120. DOI: 10.11835/j.issn.1000-582X.2020.012
    [Abstract](602) [HTML](1187) [PDF 1.07 M](782)
    Abstract:
    In the era of highly developed Internet technology, the learning resources on the Internet show an exponential growth trend. With the diversification and disorder between various learning objects and concepts, the recognition of the dependencies between them will have a major impact on computer education. Aiming at the solution to this problem, this paper proposed a concept dependency recognition method for Wikipedia. Using the characteristics of the concept in Wikipedia, a set of recognition concept dependency model was designed, and the machine learning based classification algorithm was used to test on the public data set. The experimental results show that with high accuracy and recall rate, the model can effectively discover the dependencies between concepts.
    13  Implementation of multidimensional aggregate query service for time series data
    SHENG Jia FANG Jun GUO Xiaoqian WANG Chengdong
    2020, 43(7):121-128. DOI: 10.11835/j.issn.1000-582X.2020.013
    [Abstract](768) [HTML](893) [PDF 1.60 M](669)
    Abstract:
    With the continuous expansion of power quality monitoring points, a large number of multi-dimensional power quality data with time series characteristics have been generated. The existing data query methods can not meet the need of interactive multi-dimensional aggregation query of power quality monitoring data. This paper presents a method to implement multi-dimensional aggregation service for sequential data. It establishes a hash storage structure for pre-aggregated task results in memory, a bitmap index storage structure for real-time data, and stores pre-aggregated historical data in memory as much as possible thereby improving the performance of random reading and writing, and the efficiency of query, solving the problem of interactive query. At the same time, the optimal aggregation task selection algorithm is used to select as many pre-aggregation tasks as possible to improve the hit rate of interactive queries. Experiments verify the feasibility of the proposed algorithm. Compared with the grouped two-dimensional knapsack algorithm, it has certain advantages in the number of pre-aggregated tasks.

    Current Issue


    Volume , No.

    Table of Contents

    Archive

    Volume

    Issue

    Most Read

    Most Cited

    Most Downloaded