Please wait a minute...

当期目录

    15 November 2023, Volume 9 Issue 6
    Previous Issue   
    TOPIC: BIG DATA SECURITY AND PRIVACY COMPUTING
    Application of big data technology in data security governance
    Wei CHENG, Cheng MA, Jie LING
    2023, 9(6):  3-14.  doi:10.11959/j.issn.2096-0271.2023074
    Asbtract ( 316 )   HTML ( 108)   PDF (2444KB) ( 336 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Facing the challenges of data security governance in the new situation and following the technological development trends in the field of data security, in response to the prominent issue of identifying key authorized personnel in the practical application of data security governance in large state-owned enterprises, this article proposes a key authorized personnel identification technology based on graph algorithm, which can discover potential authorization influencing factors in the system and measure the weight influence of different meanings from multiple perspectives, The recognition results have strong interpretability.Aiming at the problems of user and entity behavior anomaly detection in data security governance, this paper proposes a user and entity behavior anomaly detection method based on the generative adversarial network.The experimental results show that the accuracy, recall rate and average F1-score of the proposed method are better than the comparison baseline model method.A data security platform has been designed and developed.The platform has played an important role in reducing data security risks, assisting enterprise compliance construction, promoting data development and utilization, and has been applied in multiple data centralized management projects.It can meet the needs of big data processing in security scenarios, and has good application and promotion value.

    Research and application of innovative models for public data integration based on secure multi-party computation
    Jiahe JIN, Chengyao ZHAO, Haoze QIU, Peng LIU
    2023, 9(6):  15-27.  doi:10.11959/j.issn.2096-0271.2023073
    Asbtract ( 139 )   HTML ( 26)   PDF (2302KB) ( 286 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Secure multi-party computation is widely used in finance, the Internet, and other fields to solve the problem of ＆quot;data silos＆quot;, but its application in the field of public data is not yet mature.An innovative model for public data integration based on secure multi-party computation was proposed, and a technical architecture for joint computing using public data from different parties while protecting their private information was presented.The model breaks through institutional constraints through technological innovation, achieving a balance between improving data value and ensuring data security.Three sub-layers of the core system of secure multi-party computation in the proposed model, including the joint computation substructure layer, the secure relational algebra layer, and the basic operator layer of secure multi-party computation were mainly analyzed.Additionally, a general process for implementing the innovative model was presented, and the practical application of the innovative model was also discussed.The results of this study provide a new reference for promoting digital China construction and facilitating the flow of data resources.

    Design and implementation of trusted gateway for privacy-preserving interconnection
    Jian YE, Wen LI
    2023, 9(6):  28-38.  doi:10.11959/j.issn.2096-0271.2023072
    Asbtract ( 104 )   HTML ( 27)   PDF (1995KB) ( 217 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Based on the current development status of privacy computing both domestically and internationally, this paper summarizes the research progress in the field of privacy computing interconnectivity.Utilizing a systemic architecture perspective, it elaborates on the implementation pathways of interconnectivity technology across three levels: the＆quot;application layer, protocol layer, and communication layer＆quot;.Considering the complexities arising from the current characteristics of interconnectivity platforms, including intricate computational principles and diverse architectures, an innovative Adaptation mechanism is proposed as an interconnectivity framework.Through the design and implementation of key technologies, this framework not only ensures the realization of existing functionalities but also addresses the compatibility issues posed by different architectures.By means of experiments conducted in various scenarios encompassing traditional machine learning, horizontal federated learning, and vertical federated learning, and considering dimensions such as data volume and feature distribution, the effectiveness and viability of the trustworthy interconnectivity gateway under the Adaptation framework have been demonstrated.

    A blockchain-based privacy protection scheme for sensing data trading
    Yunhui LI, Jiahui CHEN
    2023, 9(6):  39-52.  doi:10.11959/j.issn.2096-0271.2023071
    Asbtract ( 139 )   HTML ( 34)   PDF (2393KB) ( 215 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Sensing data trading is to transform sensory data into economic value and promote the utility and sharing of data.To ensure the reliability and privacy of data transaction, a blockchain sensing data transaction scheme based on shuffle differential privacy was proposed.In our scheme, we set an audit node to supervise users and perform tasks, a shuffle node to deal with disputes and reward distribution.We used the differential privacy technology under the shuffle model to add noise to the user's data.In addition, we supplied additive secret sharing divide the data into r shufflers to prevent the mapping relationship between users and data.Our scheme does not require a trusted third party, while data consumers could publish tasks and broadcast data through the blockchain trading platform for secure and private transactions.According to the privacy amplification theorem, the proposed scheme could obtain similar privacy protection with the centralized differential privacy.Finally, we gave experiments to verify the feasibility of the scheme.Compared with related algorithms, the data accuracy obtained by our scheme was better.

    STUDY
    A survey of expressive speech synthesis
    Haobin TANG, Xulong ZHANG, Jianzong WANG, Ning CHENG, Jing XIAO
    2023, 9(6):  53-71.  doi:10.11959/j.issn.2096-0271.2022082
    Asbtract ( 273 )   HTML ( 102)   PDF (3524KB) ( 285 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Speech synthesis is a hot research topic in the field of speech, language and machine learning, which aims to synthesize understandable and natural speech for a given text.It has a wide range of applications in industry.One of the goals of speech synthesis is to make the synthesized speech natural, and there is still a lot of room for improvement in emotion, prosody and other aspects of speech synthesis.A comprehensive survey of expressive speech synthesis was conducted with the aim of better understanding current research status and future trends.A comprehensive summary, comparison and analysis of emotion-based and prosodic speech synthesis in recent years were given.Firstly the traditional way and bottleneck of common speech synthesis were introduced, then expressive speech synthesis was introduced and the benefits of expressive speech synthesis in the aspects of emotion and prosody were described.Finally, the prospect and summary of expressive speech synthesis were presented.

    Semi-supervised classification algorithm for hyperspectral remote sensing images fusing spectral measure-based label transfer and tri-training
    Feng CAO, Wentao LI, Jiancheng LUO, Deyu LI, Yuhua QIAN, Hexiang BAI, Chao ZHANG
    2023, 9(6):  72-89.  doi:10.11959/j.issn.2096-0271.2022084
    Asbtract ( 73 )   HTML ( 12)   PDF (16102KB) ( 210 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Aimed at the problem that a large number of hyperspectral remote sensing images were rich in spectral and spatial information, and the labeled samples available for image classification were far less than unlabeled samples, a semisupervised spectral-spatial classification algorithm was proposed by fusing spectral measure-based label transfer and Tri-training.A spectral measure-based label transfer method was proposed for our algorithm.The transferred labels and predicted labels for Tri-training algorithm were used to predict the labels of expanded unlabeled samples, which can promoted the prediction accuracies of labels for expanded unlabeled samples.Meanwhile, our algorithm selectel expanded samples based on spatial correlation, and used spectral and spatial features to improve the accuracy of image classification.Experimental study was executed on two public hyperspectral remote sensing image datasets, and the results showed that the proposed algorithm outperform tri-training algorithm.

    A brand digital communication evaluation model based on interactive experience
    Yingxin LIU
    2023, 9(6):  90-99.  doi:10.11959/j.issn.2096-0271.2022087
    Asbtract ( 80 )   HTML ( 16)   PDF (1939KB) ( 98 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Along with the rapid development of the digital economy, brand communication is conducive to enhancing digital brand influence and contributing to the digital transformation of enterprises.Evaluating the brand communication effect of landmark products based on interactive emotions can help county governments to better brand landmark products.First of all, a brand digital communication evaluation model based on interactive emotions was proposed, which was conducive to discovering and solving the lack of digital communication of existing landmark product brands, and promoting digital brand influence with a systematic dynamic mechanism.Then the usability of the hierarchical model of the brand communication effects of landmark products in Zhejiang Province was analyzed empirically, using data from Weibo.The actual results show that the brand digital communication evaluation model based on interactive emotion proposed has the universality of guiding the digital construction of landmark products.

    Research on the development path and countermeasures of data element value
    Yunlong YANG, Liang ZHANG, Xulei YANG
    2023, 9(6):  100-109.  doi:10.11959/j.issn.2096-0271.2022080
    Asbtract ( 682 )   HTML ( 107)   PDF (2022KB) ( 890 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Based on the development of data element marketization at home and abroad, the development path and characteristics of data element value in foreign countries were expounded.The current situation of China's data element market in terms of transaction market and application scenarios was summarized.In view of the current development of China's data element market, combined with China's data element market environment and development characteristics, through the construction of a data element market model with Chinese characteristics, we can speed up the release of data element value.

    Visual analytics of urban epidemic situation development and dynamic regulation
    Song WANG, Shijie CHEN, Hanglin LI, Xiaohui LI, Qiongfang FENG, Huijie WANG
    2023, 9(6):  110-123.  doi:10.11959/j.issn.2096-0271.2023027
    Asbtract ( 69 )   HTML ( 17)   PDF (20696KB) ( 153 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    In order to solve the reasonable allocation of limited medical resources for patients, a visual platform for dynamic control of cabin hospital was built based on the dataset of the COVID-19 epidemic in Wuhan cabin hospital, which integrates multi-source data such as public opinion, space-time trajectory and science popularization.The droppingwater diagram was introduced to dynamically monitor the overall situation of the cabin hospital.The theme model and sentiment dictionary were used to extract the emotional features of the masses, the WordStream were used to visually present the trend of urban public opinion.The path planning algorithm based on hospital load capacity were built for treatment route, the population-oriented science information of access to cabin hospital and the urban recovery model can enhance anti-epidemic confidence.The system is helpful to realize the reasonable allocation of human and material resources, timely guide the emotional trend of the masses, pay attention to the change of public opinion after the release of new polices/decisions, and slow down the phenomenon of patients gathering.The function and effectiveness of the system was verified by the analysis of several cases.

    Intelligent recommendation system for rectification of construction safety hazards based on deep learning
    Zhen LIU, Song ZHAO, Tao YANG, Taiwei CAI
    2023, 9(6):  124-136.  doi:10.11959/j.issn.2096-0271.2023076
    Asbtract ( 95 )   HTML ( 31)   PDF (3923KB) ( 229 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The management of safety hazards in water conservancy engineering construction is transitioning towards informatization and intelligence.In order to efficiently mine valuable potential information from a large amount of unstructured construction safety hazard data, an intelligent recommendation system for construction safety hazard rectification based on deep learning is proposed.This paper is based on the TF-IDF algorithm to extract feature words of hidden danger, construct a safety hazard association Sankey diagram and display the information flow characteristics among construction sections, hazard features and hazard types.Then, this paper mines association rules in historical data based on the FP-Growth algorithm.In addition, the process of case retrieval recommendation is optimized by combining the sequence similarity matching algorithm and the Doc2Vec model.This paper uses 80 953 construction safety hazard information as the data source, which is recorded in the water resources allocation project of Pearl River Delta from 2019 to 2023.Example verification shows that the proposed method can match accurate rectification measures for current construction safety hazards, effectively assisting construction safety managers to identify and address hidden danger.

    APPLICATION
    Data central-platform: architecture and practice
    Xindong WU, Zeyu YING, Shaojing SHENG, Tingting JIANG, Chenyang BU, Zan ZHANG
    2023, 9(6):  137-159.  doi:10.11959/j.issn.2096-0271.2023034
    Asbtract ( 250 )   HTML ( 83)   PDF (4476KB) ( 301 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    A data central platform positions the data of an entity-be it a corporate entity, institutional body, or governmental department-as a pivotal strategic asset.It's a management mechanism that spans from data collection to processing and application, aiming to improve data quality, achieve extensive data sharing, and ultimately maximize the value of the data.A definition for data central-platforms was provided, and a generic architecture was presented along with the core technologies and functions of physical management, logical management, data asset management, data services and information security management.Finally, taking the construction of Huapu system as an example, a realization of the data central platform, which is geared towards genealogical big data and integrated with the HAO intelligence model, was introduced-Huapu Central-Platform.

    Application of long short-term memory networks in virtual power plant data centers
    Jun CHEN, Siheng NING
    2023, 9(6):  160-173.  doi:10.11959/j.issn.2096-0271.2023077
    Asbtract ( 77 )   HTML ( 13)   PDF (5610KB) ( 212 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The intermittent, random and uncontrollable power generation characteristics of renewable energy pose challenges for the full utilization of green energy.The high energy consumption feature of the virtual power plant data center makes it an efficient absorption and regulation strategy for the intermittent (non-dispatchable) power in renewable energy.This paper proposes a method to predict the ＆quot;source-load＆quot; dual-state of the virtual power plant using a long short-term memory network that incorporates time-embedded encoding.The results indicate that using the model presented in this paper can achieve proactive alerts for ＆quot;power shortages＆quot; at 15-minute intervals, creating ample buffer time windows for container suspension and backup.Combined with container technology, it realizes dynamic energy consumption management in data centers, thereby enhancing the robustness of the virtual power plant data center against power supply-demand imbalances.This technology is of great significance for stabilizing grid operations, accelerating the application of green clean energy, constructing a service pattern for the energy ecosystem and speeding up the digital transformation of the grid.

    Construction of industry knowledge graph based on graph theory
    Zhenjun LI, Zujun LIU, Peng WANG, Bin YANG, Dazhong LI, Yu GUO, Hua ZHAO
    2023, 9(6):  174-183.  doi:10.11959/j.issn.2096-0271.2023078
    Asbtract ( 126 )   HTML ( 41)   PDF (2456KB) ( 248 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    China has the largest industrial scale and the most abundant industry type among the world.However, due to the influence of many factors, it is necessary to discover the blocking and breakpoints of the industrial chain, identify the stuck points, find alternative channels, and comprehensively optimize the industry.Then, this article explained the construction process of the industry knowledge graph from three aspects: data base construction, core knowledge graph mining, and compatibility with traditional industry chain knowledge.Finally the application scenarios and advantages of industry knowledge graph was analyzed, and an application case was given in the integrated circuit industry.

    EXPERT VIEW
Most Download
More...
Most Read
More...
Most Cited
More...
Links
More...