mathematical modeling, percolation theory, probability theory, swarm of robots.
In this paper, we propose an incremental learning scheme for the abnormal behavior detection algorithm based on principal component. The results obtained on a UCSD dataset and our experimental videos at a different number of training samples show that error rates are similar to conventional learning...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2020-06-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | http://computeroptics.smr.ru/KO/PDF/KO44-3/440320.pdf |
| _version_ | 1818836809800482816 |
|---|---|
| author | R.A. Shatalin V.R. Fidelman P.E. Ovchinnikov |
| author_facet | R.A. Shatalin V.R. Fidelman P.E. Ovchinnikov |
| author_sort | R.A. Shatalin |
| collection | DOAJ |
| description | In this paper, we propose an incremental learning scheme for the abnormal behavior detection algorithm based on principal component. The results obtained on a UCSD dataset and our experimental videos at a different number of training samples show that error rates are similar to conventional learning. Moreover, the proposed scheme allows the incremental learning time to be significantly reduced in comparison with a method based on matrix eigendecomposition. |
| first_indexed | 2024-12-19T03:12:31Z |
| format | Article |
| id | doaj.art-ad1007e6dd294df5a624c1d816306d48 |
| institution | Directory Open Access Journal |
| issn | 0134-2452 2412-6179 |
| language | English |
| last_indexed | 2024-12-19T03:12:31Z |
| publishDate | 2020-06-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj.art-ad1007e6dd294df5a624c1d816306d482022-12-21T20:37:59ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792020-06-0144347648110.18287/2412-6179-CO-624_1mathematical modeling, percolation theory, probability theory, swarm of robots.R.A. Shatalin0V.R. Fidelman1P.E. Ovchinnikov2Lobachevsky State University of Nizhny Novgorod, Nizny Novgorod, RussiaLobachevsky State University of Nizhny Novgorod, Nizny Novgorod, RussiaLobachevsky State University of Nizhny Novgorod, Nizny Novgorod, RussiaIn this paper, we propose an incremental learning scheme for the abnormal behavior detection algorithm based on principal component. The results obtained on a UCSD dataset and our experimental videos at a different number of training samples show that error rates are similar to conventional learning. Moreover, the proposed scheme allows the incremental learning time to be significantly reduced in comparison with a method based on matrix eigendecomposition.http://computeroptics.smr.ru/KO/PDF/KO44-3/440320.pdfincremental learningvideo analysisanomaly detectionprincipal component analysis |
| spellingShingle | R.A. Shatalin V.R. Fidelman P.E. Ovchinnikov mathematical modeling, percolation theory, probability theory, swarm of robots. Компьютерная оптика incremental learning video analysis anomaly detection principal component analysis |
| title | mathematical modeling, percolation theory, probability theory, swarm of robots. |
| title_full | mathematical modeling, percolation theory, probability theory, swarm of robots. |
| title_fullStr | mathematical modeling, percolation theory, probability theory, swarm of robots. |
| title_full_unstemmed | mathematical modeling, percolation theory, probability theory, swarm of robots. |
| title_short | mathematical modeling, percolation theory, probability theory, swarm of robots. |
| title_sort | mathematical modeling percolation theory probability theory swarm of robots |
| topic | incremental learning video analysis anomaly detection principal component analysis |
| url | http://computeroptics.smr.ru/KO/PDF/KO44-3/440320.pdf |
| work_keys_str_mv | AT rashatalin mathematicalmodelingpercolationtheoryprobabilitytheoryswarmofrobots AT vrfidelman mathematicalmodelingpercolationtheoryprobabilitytheoryswarmofrobots AT peovchinnikov mathematicalmodelingpercolationtheoryprobabilitytheoryswarmofrobots |