Point process models for novelty detection on spatial point patterns and their extremes
Novelty detection is a particular example of pattern recognition identifying patterns that departure from some model of “normal behaviour”. The classification of point patterns is considered that are defined as sets of N observations of a multivariate random variable X and where the value N follows...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Published: |
Elsevier
2018
|
| _version_ | 1797067357468753920 |
|---|---|
| author | Luca, SE Pimentel, MAF Watkinson, PJ Clifton, DA |
| author_facet | Luca, SE Pimentel, MAF Watkinson, PJ Clifton, DA |
| author_sort | Luca, SE |
| collection | OXFORD |
| description | Novelty detection is a particular example of pattern recognition identifying patterns that departure from some model of “normal behaviour”. The classification of point patterns is considered that are defined as sets of N observations of a multivariate random variable X and where the value N follows a discrete stochastic distribution. The use of point process models is introduced that allow us to describe the length N as well as the geometrical configuration in data space of such patterns. It is shown that such infinite dimensional study can be translated into a one-dimensional study that is analytically tractable for a multivariate Gaussian distribution. Moreover, for other multivariate distributions, an analytic approximation is obtained, by the use of extreme value theory, to model point patterns that occur in low-density regions as defined by X. The proposed models are demonstrated on synthetic and real-world data sets. |
| first_indexed | 2024-03-06T21:55:08Z |
| format | Journal article |
| id | oxford-uuid:4ca6f459-e0fd-4a70-b44c-984d3d89fe10 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T21:55:08Z |
| publishDate | 2018 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oxford-uuid:4ca6f459-e0fd-4a70-b44c-984d3d89fe102022-03-26T15:50:48ZPoint process models for novelty detection on spatial point patterns and their extremesJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:4ca6f459-e0fd-4a70-b44c-984d3d89fe10Symplectic Elements at OxfordElsevier2018Luca, SEPimentel, MAFWatkinson, PJClifton, DANovelty detection is a particular example of pattern recognition identifying patterns that departure from some model of “normal behaviour”. The classification of point patterns is considered that are defined as sets of N observations of a multivariate random variable X and where the value N follows a discrete stochastic distribution. The use of point process models is introduced that allow us to describe the length N as well as the geometrical configuration in data space of such patterns. It is shown that such infinite dimensional study can be translated into a one-dimensional study that is analytically tractable for a multivariate Gaussian distribution. Moreover, for other multivariate distributions, an analytic approximation is obtained, by the use of extreme value theory, to model point patterns that occur in low-density regions as defined by X. The proposed models are demonstrated on synthetic and real-world data sets. |
| spellingShingle | Luca, SE Pimentel, MAF Watkinson, PJ Clifton, DA Point process models for novelty detection on spatial point patterns and their extremes |
| title | Point process models for novelty detection on spatial point patterns and their extremes |
| title_full | Point process models for novelty detection on spatial point patterns and their extremes |
| title_fullStr | Point process models for novelty detection on spatial point patterns and their extremes |
| title_full_unstemmed | Point process models for novelty detection on spatial point patterns and their extremes |
| title_short | Point process models for novelty detection on spatial point patterns and their extremes |
| title_sort | point process models for novelty detection on spatial point patterns and their extremes |
| work_keys_str_mv | AT lucase pointprocessmodelsfornoveltydetectiononspatialpointpatternsandtheirextremes AT pimentelmaf pointprocessmodelsfornoveltydetectiononspatialpointpatternsandtheirextremes AT watkinsonpj pointprocessmodelsfornoveltydetectiononspatialpointpatternsandtheirextremes AT cliftonda pointprocessmodelsfornoveltydetectiononspatialpointpatternsandtheirextremes |