MC

Current Trends in Science and Technology

an Open Access Publication ISSN: 0976-9730 | 0976-9498

Engineering and Technology

Hoeffding’s-Bound Based Data Stream Prediction Using HMI Algorithm

Priya.S, Dr.Antony Selvadoss Thanamani
1Research Scholar, Bharathiar University and Assistant Professor, Department of Computer Science, Government First Grade, College, KGF, priyapunith@yahoo.com 2Professor and Head, Research Department of Computer Science, NGM College, 90, Palghat Road, Pollachi - 642 001 Coimbatore District, Tamilnadu, India
Online First: November 22, 2017
| Google Scholar

Abstract

Dynamic Data Stream Multiple Imputation  is divided into m equal-sized segments of s trans­actions, and processes the Imputation/update of data stream incrementally in a segment-based manner. HMI uses the simplified Hoeffding’s bound concepts to calculate the appropriate data stream size for the mining of Missing Data. It then uses the comparison of the two data stream sub-range observations and the Data counts when a segment occurs within the data stream and then adjusts the data stream size appropriately. In this paper implications of HMI algorithm is analysed with  Segment time comparison between HMI and FIDS using statlog data set

Keyword : HMI Algorithm,Multiple Imputation,Data Stream,Missing Data

  Submitted
Nov 22, 2017
Published
Nov 22, 2017
Abstract Views
50
PDF Downloads
55
Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

Downloads

Downloads

Download data is not yet available.
No Supplimentary Material available for this article.

Statistics from Altmetric.com

Statistics from Dimensions.ai

Statistics from PlumX


Related Articles

Related Authors

 



In Google Scholar

In International Journal of Current Trends in Science and Technology

In Google Scholar

 
  • Priya.S, Dr.Antony Selvadoss Thanamani

  • INDEXING AND ABSTRACTING