An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics
An abstract model of an artificial immune network (AIS) based on a classifier committee and robust learning algorithms (with and without a teacher) for classification problems, which are characterized by small volumes and low representativeness of training samples, are proposed. Evaluation of the ef...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Samara National Research University
2020-10-01
|
Series: | Компьютерная оптика |
Subjects: | |
Online Access: | http://www.computeroptics.smr.ru/eng/KO/Annot/KO44-5/440518e.html |
id |
doaj-47b3ce15edf0487aaafd5f07eeb304c1 |
---|---|
record_format |
Article |
spelling |
doaj-47b3ce15edf0487aaafd5f07eeb304c12020-11-25T03:59:18ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792020-10-0144583084210.18287/2412-6179-CO-717An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamicsA.E. Sulavko0Omsk State Technical University, Mira, h. 11 Omsk, Russian Federation, 644050An abstract model of an artificial immune network (AIS) based on a classifier committee and robust learning algorithms (with and without a teacher) for classification problems, which are characterized by small volumes and low representativeness of training samples, are proposed. Evaluation of the effectiveness of the model and algorithms is carried out by the example of the authentication task using keyboard handwriting using 3 databases of biometric metrics. The AIS developed possesses emergence, memory, double plasticity, and stability of learning. Experiments have shown that AIS gives a smaller or comparable percentage of errors with a much smaller training sample than neural networks with certain architectures.http://www.computeroptics.smr.ru/eng/KO/Annot/KO44-5/440518e.htmlbiometric authenticationbaggingboostingfeature subspacesmachine learning on small samplesensembles of models |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
A.E. Sulavko |
spellingShingle |
A.E. Sulavko An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics Компьютерная оптика biometric authentication bagging boosting feature subspaces machine learning on small samples ensembles of models |
author_facet |
A.E. Sulavko |
author_sort |
A.E. Sulavko |
title |
An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
title_short |
An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
title_full |
An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
title_fullStr |
An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
title_full_unstemmed |
An abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
title_sort |
abstract model of an artificial immune network based on a classifier committee for biometric pattern recognition by the example of keystroke dynamics |
publisher |
Samara National Research University |
series |
Компьютерная оптика |
issn |
0134-2452 2412-6179 |
publishDate |
2020-10-01 |
description |
An abstract model of an artificial immune network (AIS) based on a classifier committee and robust learning algorithms (with and without a teacher) for classification problems, which are characterized by small volumes and low representativeness of training samples, are proposed. Evaluation of the effectiveness of the model and algorithms is carried out by the example of the authentication task using keyboard handwriting using 3 databases of biometric metrics. The AIS developed possesses emergence, memory, double plasticity, and stability of learning. Experiments have shown that AIS gives a smaller or comparable percentage of errors with a much smaller training sample than neural networks with certain architectures. |
topic |
biometric authentication bagging boosting feature subspaces machine learning on small samples ensembles of models |
url |
http://www.computeroptics.smr.ru/eng/KO/Annot/KO44-5/440518e.html |
work_keys_str_mv |
AT aesulavko anabstractmodelofanartificialimmunenetworkbasedonaclassifiercommitteeforbiometricpatternrecognitionbytheexampleofkeystrokedynamics AT aesulavko abstractmodelofanartificialimmunenetworkbasedonaclassifiercommitteeforbiometricpatternrecognitionbytheexampleofkeystrokedynamics |
_version_ |
1724454675065864192 |