期刊名称：International Journal of Database Management Systems
印刷版ISSN：0975-5985
电子版ISSN：0975-5705
出版年度：2014
卷号：6
期号：4
页码：1
DOI：10.5121/ijdms.2014.6401
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：The development of sensor data repositories will aid the researchers to create benchmark dataset. Thesebenchmark dataset will provide a platform for all the researchers to access the data, test and compare theaccuracy of their algorithms. However, the storage and management of sensor data itself is a challengingtask due to various reasons such as noisy, redundant, missing, and faulty data. Therefore it is veryimportant to create a data repository which contains the precise and accurate data and also storage andmanagement of data is effective. Hence, in this paper we are proposing to use the combination ofquantitative association rules and decision tree for classification of faulty data and normal data. Usage ofmultiple linear regression models for the estimation of missing data. A symbolic table approach for storageand management of sensor data. And development of a graphical user interface for visualization of sensordata.
关键词：Data Mining; Association Rules; Decision Tree; Sensor Network; Faulty data; Missing Data; Multiple;Linear Regression; Sensor Data Repository.
