Impact of censoring on estimation of flow duration distribution and its mitigation using kaplan-meier-based method

Yuki Sakai, Masato Uchida, Masato Tsuru, Yuji Oie

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A basic and inevitable problem in estimating flow duration distribution arises from "censoring" (i.e., cutting off) the observed flow duration because of a finite measurement period. We extended the Kaplan-Meier method, which is used in the survival analysis field, and applied it to recover information on the flow duration distribution that was lost due to censoring. We show that the flow duration distribution from a short period of actual traffic data with censoring that was estimated using a Kaplan-Meier-based method can approximate well the flow duration distribution calculated from a sufficiently long period of actual traffic data.

Original languageEnglish
Pages (from-to)1949-1952
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE92-D
Issue number10
DOIs
Publication statusPublished - 2009
Externally publishedYes

Keywords

  • Censoring
  • Flow duration distribution
  • Kaplan-Meier method

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

Impact of censoring on estimation of flow duration distribution and its mitigation using kaplan-meier-based method. / Sakai, Yuki; Uchida, Masato; Tsuru, Masato; Oie, Yuji.

In: IEICE Transactions on Information and Systems, Vol. E92-D, No. 10, 2009, p. 1949-1952.

Research output: Contribution to journalArticle

@article{8bbce20928c04ce4b209d62f7e1d6f7b,
title = "Impact of censoring on estimation of flow duration distribution and its mitigation using kaplan-meier-based method",
abstract = "A basic and inevitable problem in estimating flow duration distribution arises from {"}censoring{"} (i.e., cutting off) the observed flow duration because of a finite measurement period. We extended the Kaplan-Meier method, which is used in the survival analysis field, and applied it to recover information on the flow duration distribution that was lost due to censoring. We show that the flow duration distribution from a short period of actual traffic data with censoring that was estimated using a Kaplan-Meier-based method can approximate well the flow duration distribution calculated from a sufficiently long period of actual traffic data.",
keywords = "Censoring, Flow duration distribution, Kaplan-Meier method",
author = "Yuki Sakai and Masato Uchida and Masato Tsuru and Yuji Oie",
year = "2009",
doi = "10.1587/transinf.E92.D.1949",
language = "English",
volume = "E92-D",
pages = "1949--1952",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "10",

}

TY - JOUR

T1 - Impact of censoring on estimation of flow duration distribution and its mitigation using kaplan-meier-based method

AU - Sakai, Yuki

AU - Uchida, Masato

AU - Tsuru, Masato

AU - Oie, Yuji

PY - 2009

Y1 - 2009

N2 - A basic and inevitable problem in estimating flow duration distribution arises from "censoring" (i.e., cutting off) the observed flow duration because of a finite measurement period. We extended the Kaplan-Meier method, which is used in the survival analysis field, and applied it to recover information on the flow duration distribution that was lost due to censoring. We show that the flow duration distribution from a short period of actual traffic data with censoring that was estimated using a Kaplan-Meier-based method can approximate well the flow duration distribution calculated from a sufficiently long period of actual traffic data.

AB - A basic and inevitable problem in estimating flow duration distribution arises from "censoring" (i.e., cutting off) the observed flow duration because of a finite measurement period. We extended the Kaplan-Meier method, which is used in the survival analysis field, and applied it to recover information on the flow duration distribution that was lost due to censoring. We show that the flow duration distribution from a short period of actual traffic data with censoring that was estimated using a Kaplan-Meier-based method can approximate well the flow duration distribution calculated from a sufficiently long period of actual traffic data.

KW - Censoring

KW - Flow duration distribution

KW - Kaplan-Meier method

UR - http://www.scopus.com/inward/record.url?scp=77950295135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950295135&partnerID=8YFLogxK

U2 - 10.1587/transinf.E92.D.1949

DO - 10.1587/transinf.E92.D.1949

M3 - Article

AN - SCOPUS:77950295135

VL - E92-D

SP - 1949

EP - 1952

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 10

ER -