Functional data analysis method for 3 dimensional movings

2014 Fiscal Year Final Research Report

• Project/Area Number: 24650144
• Research Category: Grant-in-Aid for Challenging Exploratory Research
• Allocation Type: Multi-year Fund
• Research Field: Statistical science
• Research Institution: Hokkaido University
• Principal Investigator: KOMIYA Yuriko 北海道大学, 情報基盤センター, 助教 (40241393)
• Co-Investigator(Kenkyū-buntansha): MIZUTA Masahiro 北海道大学, 情報基盤センター, 教授 (70174026)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 統計学

Outline of Final Research Achievements

With "Functional Data Analysis(FDA)", many data sets have been studied, that with conventional statistical approaches could not answer to. "Symbolic Data Analysis(SDA)" also gives a wider viewpoint for data studies. In SDA, symbolic data have internal variation and structure which must be taken account for when analysing target datasets. We popose methods of FDA and SDA for "Big Data" that has features of big size and variation within it. Our methods are usefully applied to environmental radioactivity data, network delay data and traffic data.

Free Research Field

計算機統計学