Artificial immune systems based novelty detection with CNN-UM

György Cserey, T. Roska

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

1 Citation (Scopus)

Abstract

In this paper, we show that our earlier presented immune response inspired algorithmic framework [1], [3] for spatial-temporal target detection applications using CNN technology [9], [17], [10] can be implemented on the latest CNN-UM chip (Ace16k) [16] and Bi-i system [15]. The implementation of the algorithm is real-time and able to detect novelty events in image flows reliably, running 10000 templates/s with video-frame (25 frame/s) speed and on image size of 128×128. Besides that some results of the implementation of this AIS model and its application for natural image flows are shown, the realized adaptation and mutation methods are also introduced.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007
Pages156-161
Number of pages6
DOIs
Publication statusPublished - 2007
Event2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007 - Honolulu, HI, United States
Duration: Apr 1 2007Apr 5 2007

Other

Other2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007
CountryUnited States
CityHonolulu, HI
Period4/1/074/5/07

Fingerprint

Novelty Detection
Artificial Immune System
Immune system
Target tracking
Immune Response
Target Detection
Template
Mutation
Chip
Real-time
Model

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Mathematics(all)

Cite this

Cserey, G., & Roska, T. (2007). Artificial immune systems based novelty detection with CNN-UM. In Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007 (pp. 156-161). [4233900] https://doi.org/10.1109/FOCI.2007.372162

Artificial immune systems based novelty detection with CNN-UM. / Cserey, György; Roska, T.

Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007. 2007. p. 156-161 4233900.

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

Cserey, G & Roska, T 2007, Artificial immune systems based novelty detection with CNN-UM. in Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007., 4233900, pp. 156-161, 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007, Honolulu, HI, United States, 4/1/07. https://doi.org/10.1109/FOCI.2007.372162
Cserey G, Roska T. Artificial immune systems based novelty detection with CNN-UM. In Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007. 2007. p. 156-161. 4233900 https://doi.org/10.1109/FOCI.2007.372162
Cserey, György ; Roska, T. / Artificial immune systems based novelty detection with CNN-UM. Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007. 2007. pp. 156-161
@inproceedings{28f36648d9aa47668820f78117f13474,
title = "Artificial immune systems based novelty detection with CNN-UM",
abstract = "In this paper, we show that our earlier presented immune response inspired algorithmic framework [1], [3] for spatial-temporal target detection applications using CNN technology [9], [17], [10] can be implemented on the latest CNN-UM chip (Ace16k) [16] and Bi-i system [15]. The implementation of the algorithm is real-time and able to detect novelty events in image flows reliably, running 10000 templates/s with video-frame (25 frame/s) speed and on image size of 128×128. Besides that some results of the implementation of this AIS model and its application for natural image flows are shown, the realized adaptation and mutation methods are also introduced.",
author = "Gy{\"o}rgy Cserey and T. Roska",
year = "2007",
doi = "10.1109/FOCI.2007.372162",
language = "English",
isbn = "1424407036",
pages = "156--161",
booktitle = "Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007",

}

TY - GEN

T1 - Artificial immune systems based novelty detection with CNN-UM

AU - Cserey, György

AU - Roska, T.

PY - 2007

Y1 - 2007

N2 - In this paper, we show that our earlier presented immune response inspired algorithmic framework [1], [3] for spatial-temporal target detection applications using CNN technology [9], [17], [10] can be implemented on the latest CNN-UM chip (Ace16k) [16] and Bi-i system [15]. The implementation of the algorithm is real-time and able to detect novelty events in image flows reliably, running 10000 templates/s with video-frame (25 frame/s) speed and on image size of 128×128. Besides that some results of the implementation of this AIS model and its application for natural image flows are shown, the realized adaptation and mutation methods are also introduced.

AB - In this paper, we show that our earlier presented immune response inspired algorithmic framework [1], [3] for spatial-temporal target detection applications using CNN technology [9], [17], [10] can be implemented on the latest CNN-UM chip (Ace16k) [16] and Bi-i system [15]. The implementation of the algorithm is real-time and able to detect novelty events in image flows reliably, running 10000 templates/s with video-frame (25 frame/s) speed and on image size of 128×128. Besides that some results of the implementation of this AIS model and its application for natural image flows are shown, the realized adaptation and mutation methods are also introduced.

UR - http://www.scopus.com/inward/record.url?scp=34548834977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548834977&partnerID=8YFLogxK

U2 - 10.1109/FOCI.2007.372162

DO - 10.1109/FOCI.2007.372162

M3 - Conference contribution

AN - SCOPUS:34548834977

SN - 1424407036

SN - 9781424407033

SP - 156

EP - 161

BT - Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence, FOCI 2007

ER -