A Voting-Based Sequential Pattern Recognition Method

Koichi Ogawara, Masahiro Fukutomi, Seiichi Uchida, Yaokai Feng

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We propose a novel method for recognizing sequential patterns such as motion trajectory of biological objects (i.e., cells, organelle, protein molecules, etc.), human behavior motion, and meteorological data. In the proposed method, a local classifier is prepared for every point (or timing or frame) and then the whole pattern is recognized by majority voting of the recognition results of the local classifiers. The voting strategy has a strong benefit that even if an input pattern has a very large deviation from a prototype locally at several points, they do not severely influence the recognition result; they are treated just as several incorrect votes and thus will be neglected successfully through the majority voting. For regularizing the recognition result, we introduce partial-dependency to local classifiers. An important point is that this dependency is introduced to not only local classifiers at neighboring point pairs but also to those at distant point pairs. Although, the dependency makes the problem non-Markovian (i.e., higher-order Markovian), it can still be solved efficiently by using a graph cut algorithm with polynomial-order computations. The experimental results revealed that the proposed method can achieve better recognition accuracy while utilizing the above characteristics of the proposed method.

Original languageEnglish
Article numbere76980
JournalPloS one
Volume8
Issue number10
DOIs
Publication statusPublished - Oct 14 2013

Fingerprint

Politics
Pattern recognition
Classifiers
human behavior
methodology
meteorological data
prototypes
Organelles
trajectories
organelles
Trajectories
Polynomials
Molecules
Dependency (Psychology)
Proteins
proteins
cells

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • General

Cite this

A Voting-Based Sequential Pattern Recognition Method. / Ogawara, Koichi; Fukutomi, Masahiro; Uchida, Seiichi; Feng, Yaokai.

In: PloS one, Vol. 8, No. 10, e76980, 14.10.2013.

Research output: Contribution to journalArticle

Ogawara, Koichi ; Fukutomi, Masahiro ; Uchida, Seiichi ; Feng, Yaokai. / A Voting-Based Sequential Pattern Recognition Method. In: PloS one. 2013 ; Vol. 8, No. 10.
@article{5e5021596dac4aa8ae5baee6696c72e8,
title = "A Voting-Based Sequential Pattern Recognition Method",
abstract = "We propose a novel method for recognizing sequential patterns such as motion trajectory of biological objects (i.e., cells, organelle, protein molecules, etc.), human behavior motion, and meteorological data. In the proposed method, a local classifier is prepared for every point (or timing or frame) and then the whole pattern is recognized by majority voting of the recognition results of the local classifiers. The voting strategy has a strong benefit that even if an input pattern has a very large deviation from a prototype locally at several points, they do not severely influence the recognition result; they are treated just as several incorrect votes and thus will be neglected successfully through the majority voting. For regularizing the recognition result, we introduce partial-dependency to local classifiers. An important point is that this dependency is introduced to not only local classifiers at neighboring point pairs but also to those at distant point pairs. Although, the dependency makes the problem non-Markovian (i.e., higher-order Markovian), it can still be solved efficiently by using a graph cut algorithm with polynomial-order computations. The experimental results revealed that the proposed method can achieve better recognition accuracy while utilizing the above characteristics of the proposed method.",
author = "Koichi Ogawara and Masahiro Fukutomi and Seiichi Uchida and Yaokai Feng",
year = "2013",
month = "10",
day = "14",
doi = "10.1371/journal.pone.0076980",
language = "English",
volume = "8",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

TY - JOUR

T1 - A Voting-Based Sequential Pattern Recognition Method

AU - Ogawara, Koichi

AU - Fukutomi, Masahiro

AU - Uchida, Seiichi

AU - Feng, Yaokai

PY - 2013/10/14

Y1 - 2013/10/14

N2 - We propose a novel method for recognizing sequential patterns such as motion trajectory of biological objects (i.e., cells, organelle, protein molecules, etc.), human behavior motion, and meteorological data. In the proposed method, a local classifier is prepared for every point (or timing or frame) and then the whole pattern is recognized by majority voting of the recognition results of the local classifiers. The voting strategy has a strong benefit that even if an input pattern has a very large deviation from a prototype locally at several points, they do not severely influence the recognition result; they are treated just as several incorrect votes and thus will be neglected successfully through the majority voting. For regularizing the recognition result, we introduce partial-dependency to local classifiers. An important point is that this dependency is introduced to not only local classifiers at neighboring point pairs but also to those at distant point pairs. Although, the dependency makes the problem non-Markovian (i.e., higher-order Markovian), it can still be solved efficiently by using a graph cut algorithm with polynomial-order computations. The experimental results revealed that the proposed method can achieve better recognition accuracy while utilizing the above characteristics of the proposed method.

AB - We propose a novel method for recognizing sequential patterns such as motion trajectory of biological objects (i.e., cells, organelle, protein molecules, etc.), human behavior motion, and meteorological data. In the proposed method, a local classifier is prepared for every point (or timing or frame) and then the whole pattern is recognized by majority voting of the recognition results of the local classifiers. The voting strategy has a strong benefit that even if an input pattern has a very large deviation from a prototype locally at several points, they do not severely influence the recognition result; they are treated just as several incorrect votes and thus will be neglected successfully through the majority voting. For regularizing the recognition result, we introduce partial-dependency to local classifiers. An important point is that this dependency is introduced to not only local classifiers at neighboring point pairs but also to those at distant point pairs. Although, the dependency makes the problem non-Markovian (i.e., higher-order Markovian), it can still be solved efficiently by using a graph cut algorithm with polynomial-order computations. The experimental results revealed that the proposed method can achieve better recognition accuracy while utilizing the above characteristics of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84885397505&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885397505&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0076980

DO - 10.1371/journal.pone.0076980

M3 - Article

C2 - 24155915

AN - SCOPUS:84885397505

VL - 8

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e76980

ER -