Activity recognition with finite state machines

Wesley Kerr, Anh Tran, Paul R Cohen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

This paper shows how to learn general, Finite State Machine representations of activities that function as recognizers of previously unseen instances of activities. The central problem is to tell which differences between instances of activities are unimportant and may be safely ignored for the purpose of learning generalized representations of activities. We develop a novel way to find the "essential parts" of activities by a greedy kind of multiple sequence alignment, and a method to transform the resulting alignments into Finite State Machine that will accept novel instances of activities with high accuracy.

Original languageEnglish (US)
Title of host publicationIJCAI International Joint Conference on Artificial Intelligence
Pages1348-1353
Number of pages6
DOIs
StatePublished - 2011
Event22nd International Joint Conference on Artificial Intelligence, IJCAI 2011 - Barcelona, Catalonia, Spain
Duration: Jul 16 2011Jul 22 2011

Other

Other22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
CountrySpain
CityBarcelona, Catalonia
Period7/16/117/22/11

Fingerprint

Finite automata

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Kerr, W., Tran, A., & Cohen, P. R. (2011). Activity recognition with finite state machines. In IJCAI International Joint Conference on Artificial Intelligence (pp. 1348-1353) https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-228

Activity recognition with finite state machines. / Kerr, Wesley; Tran, Anh; Cohen, Paul R.

IJCAI International Joint Conference on Artificial Intelligence. 2011. p. 1348-1353.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kerr, W, Tran, A & Cohen, PR 2011, Activity recognition with finite state machines. in IJCAI International Joint Conference on Artificial Intelligence. pp. 1348-1353, 22nd International Joint Conference on Artificial Intelligence, IJCAI 2011, Barcelona, Catalonia, Spain, 7/16/11. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-228
Kerr W, Tran A, Cohen PR. Activity recognition with finite state machines. In IJCAI International Joint Conference on Artificial Intelligence. 2011. p. 1348-1353 https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-228
Kerr, Wesley ; Tran, Anh ; Cohen, Paul R. / Activity recognition with finite state machines. IJCAI International Joint Conference on Artificial Intelligence. 2011. pp. 1348-1353
@inproceedings{75e58bf5f8a3400b9babd030018420a8,
title = "Activity recognition with finite state machines",
abstract = "This paper shows how to learn general, Finite State Machine representations of activities that function as recognizers of previously unseen instances of activities. The central problem is to tell which differences between instances of activities are unimportant and may be safely ignored for the purpose of learning generalized representations of activities. We develop a novel way to find the {"}essential parts{"} of activities by a greedy kind of multiple sequence alignment, and a method to transform the resulting alignments into Finite State Machine that will accept novel instances of activities with high accuracy.",
author = "Wesley Kerr and Anh Tran and Cohen, {Paul R}",
year = "2011",
doi = "10.5591/978-1-57735-516-8/IJCAI11-228",
language = "English (US)",
isbn = "9781577355120",
pages = "1348--1353",
booktitle = "IJCAI International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Activity recognition with finite state machines

AU - Kerr, Wesley

AU - Tran, Anh

AU - Cohen, Paul R

PY - 2011

Y1 - 2011

N2 - This paper shows how to learn general, Finite State Machine representations of activities that function as recognizers of previously unseen instances of activities. The central problem is to tell which differences between instances of activities are unimportant and may be safely ignored for the purpose of learning generalized representations of activities. We develop a novel way to find the "essential parts" of activities by a greedy kind of multiple sequence alignment, and a method to transform the resulting alignments into Finite State Machine that will accept novel instances of activities with high accuracy.

AB - This paper shows how to learn general, Finite State Machine representations of activities that function as recognizers of previously unseen instances of activities. The central problem is to tell which differences between instances of activities are unimportant and may be safely ignored for the purpose of learning generalized representations of activities. We develop a novel way to find the "essential parts" of activities by a greedy kind of multiple sequence alignment, and a method to transform the resulting alignments into Finite State Machine that will accept novel instances of activities with high accuracy.

UR - http://www.scopus.com/inward/record.url?scp=84881052291&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881052291&partnerID=8YFLogxK

U2 - 10.5591/978-1-57735-516-8/IJCAI11-228

DO - 10.5591/978-1-57735-516-8/IJCAI11-228

M3 - Conference contribution

AN - SCOPUS:84881052291

SN - 9781577355120

SP - 1348

EP - 1353

BT - IJCAI International Joint Conference on Artificial Intelligence

ER -