Please wait a minute...

当期目录

    15 May 2018, Volume 4 Issue 3
    TOPIC:BIOMEDICAL BIG DATA
    Quality control of big data analysis for metagenomics
    Guangyong ZHENG, Zhen YANG, Ruifang CAO, Wan LIU, Yixue LI, Guoqing ZHANG
    2018, 4(3):  3-12.  doi:10.11959/j.issn.2096-0271.2018025
    Asbtract ( 596 )   HTML ( 34)   PDF (1136KB) ( 1549 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Metagenomic data has the characteristics of high volume and complexity.As for data type of metagenomics,it covers metadata and sequencing data.Before performing in-depth functional analysis of metagenomic data,strict quality control for these metadata and sequencing data are needed,so as to ensure the validity and correctness of subsequent data analysis.The quality control process of metagenomic data was described in detail,which included information checking of metadata and sequencing data,filtering of low quality fragments,and so on.A pre-processing specification for metagenomic data analysis was presented,and a solid foundation for big data analysis of microbiome was provided.

    Usability research of regional health data for clinical efficacy analysis
    Qi YE, Liang ZHAO, Tong RUAN, DongLei FENG, Ju GAO, Min LIU
    2018, 4(3):  13-23.  doi:10.11959/j.issn.2096-0271.2018026
    Asbtract ( 353 )   HTML ( 6)   PDF (1139KB) ( 788 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The regional electronic health records data are initially collected from several different hospitals and then undergo several rounds of data collection,transformation and integration,so there may exist a variety of quality problems.A new evaluation process for data usability was presented.The evaluation metrics were obtained by firstly gathering research requirements of clinicians,and then designing of requirement templates in the process.An example of obtaining evaluation metrics based on the requirement analysis with heart failure was also given.By using the process,ten metrics related to the data completeness and consistency were obtained and then the data of the provincial regional platform were evaluated for the usability.Finally,that the completeness and the consistency of data related to clinical research needs to be improved was shown.

    Parallel optimization for clustering algorithm of large-scale biological effect evaluation
    Shaoliang PENG, Shunyun YANG, Zhe SUN, Minxia CHENG, Yingbo CUI, Xiaowei WANG, Fei LI, Xiaochen BO, Xiangke LIAO
    2018, 4(3):  24-36.  doi:10.11959/j.issn.2096-0271.2018027
    Asbtract ( 540 )   HTML ( 34)   PDF (1693KB) ( 738 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The biological assessment,including matching algorithm,is realized by measuring and analyzing the human cells’ transcription reaction after stimulated by biological agents,to quickly determine the relevant detection markers and treatment targets.Similarly,the big data strategy was used to estimate the sudden biological effect model.MPI,OpenMP two-level parallel acceleration was considered,transplantation and optimization of the GSEA alignment algorithm and clustering algorithm were used.The potential scalability and the ability of dealing with massive data by testing different scales of data and parallelisms were improved.

    Chronic disease complications clustering based on ICD-10 diagnoses code
    Xiaoxia WANG, Fusong JIANG, Yu WANG, Yun XIONG
    2018, 4(3):  37-45.  doi:10.11959/j.issn.2096-0271.2018028
    Asbtract ( 702 )   HTML ( 29)   PDF (1341KB) ( 928 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Study on the relationship between the chronic disease and the corresponding complications has great theoretical significance and applicable value for patients and clinical medicine.In order to utilize healthcare electronic record more reasonably,preprocessing was needed according to prior medical knowledge for chronic disease complication.The challenge of this work is that medical knowledge should be exploited to label the corresponding complications.To meet these challenges and assist physicians in labeling complications of a target chronic disease,a semi-supervised chronic disease complications clustering algorithm based on ICD-10 code for diagnoses was proposed.Experiments on a real dataset of diabetes electronic healthcare record show that the algorithms are practical and effective.

    Construction and deep application of multi-center clinical big data platform
    Lifeng ZHU, Shujun LIU, Dehua CHEN, Jiajin LE
    2018, 4(3):  46-53.  doi:10.11959/j.issn.2096-0271.2018029
    Asbtract ( 837 )   HTML ( 49)   PDF (1139KB) ( 1644 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Multi-center clinical research is the main approach for multi-center,multi-disciplinary,to develop some collaborative clinical researches on the same clinical issues.The traditional multi-center clinical research mainly has the disadvantages that small sample size and the clinical research is relatively closed and the degree of openness is not high.Therefore,the newly emerging technology,such as big data and cloud computing was combined to integrate clinical centers of physically dispersed hospitals into a logical and unified clinical data.On this basis,a multi-center clinical big data application platform was constructed.First,the overall framework of the multi-center clinical big data platform was designed,and then the subsystems of the platform were elaborated in detail.Finally,the deep application of clinical big data platform was introduced.

    Abnormal detection of hospital admissions based on meteorological factors
    Guangjun YU, Yun XIONG, Sijia PENG, Lu RUAN
    2018, 4(3):  54-60.  doi:10.11959/j.issn.2096-0271.2018030
    Asbtract ( 539 )   HTML ( 16)   PDF (1349KB) ( 951 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The hospital admission data from medicine department and infectious disease department of a hospital was analyzed and a classify model between the number of patients and meteorological factors was built.High accuracy of prediction in abnormal number of patients by utilizing random forest classifier was achieved,and decision support to Public Health Department was provided so that the hospital can make a reasonable allocation of doctors.All experiments were conducted on real data from the hospital and the results show that the final trained model achieve relatively high accuracy and recall.

    STUDY
    Analysis on hybrid memory architecture for big data application
    Xin LI, Xuan CHEN, Zhiqiu HUANG
    2018, 4(3):  61-80.  doi:10.11959/j.issn.2096-0271.2018031
    Asbtract ( 510 )   HTML ( 20)   PDF (1303KB) ( 1002 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Due to the limited scalability of DRAM,it is hard to optimize the performance of big data analysis and the big data applications.The new non-volatile memory (NVM) brings the opportunity to improve the performance and efficiency for big data applications,which benefits by the advantages of NVM,including its non-volatile,high storage density,and low power consumption.The PCM/DRAM hybrid memory architecture based on the non-volatile memory was analyzed.The feasibility and advantages of hybrid memory for big data applications through the analysis on the optimization of performance,energy consumption and memory management strategies for hybrid memory architecture were demonstrated.The defects in existing work were summarized and the potential research field in PCM/DRAM hybrid memory architecture was discussed.

    APPLICATION
    Visualization analysis of shipping recruitment information based on Gephi
    Yang WANG, Ye TIAN, Tieshan LI, HENC.L.Philip C, Dongcheng PENG, Yihua ZHOU
    2018, 4(3):  81-91.  doi:10.11959/j.issn.2096-0271.2018032
    Asbtract ( 731 )   HTML ( 18)   PDF (3700KB) ( 1292 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The Gephi-based social network visualization analysis method was introduced into the field of association analysis of crew recruitment data.By constructing the attribute co-occurrence network of crew recruitment data,the relationship between various attributes in the crew recruitment information was analyzed.Through interactive analysis,the correlations such as positions and routes,routes and certificates,can be obtained.What’s more,the degree of correlation between various attributes in the crew data and the core attributes of the shipping recruitment information network were explored,which in order to provide reference and basis for the relevant enterprises and crews to deal with changes in the crew market.

    COLUMN:NATIONAL ENGINEERING LABORATORY FOR BIG DATA
    Big data driven security collaborative ecological construction
    Xuhua BAO, Xiaodong QU, Xinhua ZHENG
    2018, 4(3):  93-100.  doi:10.11959/j.issn.2096-0271.2018033
    Asbtract ( 577 )   HTML ( 28)   PDF (1150KB) ( 692 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    Big data technology in network security field has brought challenges and opportunities at the same time.New technology and new model spring up with data breaches of privacy risks,cross-border data flows,data misuse and a series of security risks.The idea of big data security to deal with these risks was introduced.At the same time,the development of big data technology has brought great opportunities to the improvement of security industry capacity.Big data technology,intelligent security mode and security industry synergy will be developed.

    COLUMN:2017 TOP 10 PRACTICES OF BIG DATA APPLICATION
    Practices of hybrid heterogeneous marketing data platform
    Yilei LU
    2018, 4(3):  104-110.  doi:10.11959/j.issn.2096-0271.2018034
    Asbtract ( 407 )   HTML ( 14)   PDF (1001KB) ( 654 )   Knowledge map   
    Figures and Tables | References | Related Articles | Metrics

    The problem of business requirements solved by the Hybrid Heterogeneous Marketing Data Platform in the process of implementation was elaborated,and the corresponding technical solutions were selected.The inventions and innovations in the construction of the entire platform,the problems and solutions encountered,as well as the lessons learned were depicted from a technical point of view.

    TREND
Most Download
Most Read
Most Cited