Model-based classification and novelty detection for point pattern data

© 2016 IEEE. Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper propos...

Full description

Bibliographic Details
Main Authors: Vo, Ba Tuong, Tran, N., Phung, D., Vo, Ba-Ngu
Format: Conference Paper
Published: 2017
Online Access:http://hdl.handle.net/20.500.11937/56163
_version_ 1848759802088390656
author Vo, Ba Tuong
Tran, N.
Phung, D.
Vo, Ba-Ngu
author_facet Vo, Ba Tuong
Tran, N.
Phung, D.
Vo, Ba-Ngu
author_sort Vo, Ba Tuong
building Curtin Institutional Repository
collection Online Access
description © 2016 IEEE. Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper proposes the modelling of point pattern data via random finite sets (RFS). In particular, we propose appropriate likelihood functions, and a maximum likelihood estimator for learning a tractable family of RFS models. In novelty detection, we propose novel ranking functions based on RFS models, which substantially improve performance.
first_indexed 2025-11-14T10:05:40Z
format Conference Paper
id curtin-20.500.11937-56163
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:05:40Z
publishDate 2017
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-561632018-03-29T09:09:01Z Model-based classification and novelty detection for point pattern data Vo, Ba Tuong Tran, N. Phung, D. Vo, Ba-Ngu © 2016 IEEE. Point patterns are sets or multi-sets of unordered elements that can be found in numerous data sources. However, in data analysis tasks such as classification and novelty detection, appropriate statistical models for point pattern data have not received much attention. This paper proposes the modelling of point pattern data via random finite sets (RFS). In particular, we propose appropriate likelihood functions, and a maximum likelihood estimator for learning a tractable family of RFS models. In novelty detection, we propose novel ranking functions based on RFS models, which substantially improve performance. 2017 Conference Paper http://hdl.handle.net/20.500.11937/56163 10.1109/ICPR.2016.7900030 restricted
spellingShingle Vo, Ba Tuong
Tran, N.
Phung, D.
Vo, Ba-Ngu
Model-based classification and novelty detection for point pattern data
title Model-based classification and novelty detection for point pattern data
title_full Model-based classification and novelty detection for point pattern data
title_fullStr Model-based classification and novelty detection for point pattern data
title_full_unstemmed Model-based classification and novelty detection for point pattern data
title_short Model-based classification and novelty detection for point pattern data
title_sort model-based classification and novelty detection for point pattern data
url http://hdl.handle.net/20.500.11937/56163