An algorithm based on time series similarity measurement for missing data filling

In data mining processing, filling incomplete data is very important in preprocessing of data mining project. An algorithm based on time series similarity measurement for incomplete data is proposed, this approach can fill missing data via following internal rule of data set reasonably. By experiments, we can draw a conclusion that algorithm is effective on condition that incomplete data are no more than half of the whole data in one case.

[1]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[2]  Hui Xiao,et al.  A new segmented time warping distance for data mining in time series database , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[3]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[4]  Wesley W. Chu,et al.  Similarity search of time-warped subsequences via a suffix tree , 2003, Inf. Syst..

[5]  Christos Faloutsos,et al.  Efficient Similarity Search In Sequence Databases , 1993, FODO.