Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Intelligent Computer and Applications》 2019-04
Add to Favorite Get Latest Update

Uncertain time series data cleaning based on energy filter

SUN Jizhou;LI Jianzhong;School of Computer Science and Technology,Harbin Institute of Technology;  
Large scale time series data are generated and processed in many applications,such as data collected by sensors. Due to environmental interferences and lowprecision of the sensors,the collected data are not usually accurate. Accuracy is an important aspect of data science area,which plays a key role in the subsequent data processing tasks. To improve data quality,multiple sensors are often deployed to collect data at the same location. The time series samples returned by the sensors are called uncertain time series data. Existing research often designs newalgorithm for old problems on uncertain time series,the drawbacks are lowefficiencies. Cleaning the uncertain data to get a single series close to the truth as much as possible is of great significance.Traditional algorithms designed for certain time series can be applied directly. A power filter based method to clean uncertain time series is proposed in this paper,experimental results showthat the proposed method is better in both effectiveness and efficiency.
【Fund】: 国家自然科学基金(61190115 61033015);; 国家重点基础研究发展计划(973)(2012CB316200)
【CateGory Index】: TP311.13;O211.61
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved