On Biometrics With Eye Movements

Abstract

Eye movements are a relatively novel data source for biometric identification. When video cameras applied to eye tracking become smaller and more efficient, this data source could offer interesting opportunities for the development of eye movement biometrics. In the present article, we study primarily biometric identification as seen as a classification task of multiple classes, and secondarily biometric verification considered as binary classification. Our research is based on the saccadic eye movement signal measurements from 109 young subjects. In order to te s t the dat a m e as ur e d, w e us e a pr o c e dur e o f biom e tri c identification according to the one-versus-one (subject) principle. In a development from our previous research, which also involved biometric verification based on saccadic eye movements, we now apply another eye movement tracker device with a higher sampling frequency of 250 Hz. The results obtained are good, with correct identification rates at 80-90% at their best.

Detection of genetic cardiac diseases by Ca2+ transient profiles using machine learning methods

“…In fact, these three machine learning algorithm types yielded the best results for the current data as presented in Tables 2 and 3 . Frequently, we have drawn similar conclusions from our other recent machine learning studies, for example, for eye movement signal data 26 and socio-economic crime data 27 . Although these machine learning methods were developed several years or even decades ago, they have in recent years become highly useful with the innumerable data sources that have arisen and along with global digitalization and the development of various measurement and data collecting technologies.…”

“…No doubt, there are now key computational algorithms to solve in machine learning: among other things, classification problems for use in almost any areas in which data can be collected efficiently. Eye movements could be used for verification and identification of subjects, for example, as users of computers 26 (to replace passwords); country crime data can be used to study crime rates and types 27 for comparison with different countries on the basis of databases from the United Nations and national statistical organizations; or freshwater benthic macroinvertebrates 28 (small aquatic animals) could be classified for water quality research in inland waterways. One of the most interesting fields to utilize machine learning is medicine.…”

Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics

“…If a service provider responds to requests indiscriminately, it may be exploited for crime, so it should be limited to the authorized person, and the required technology is authentication. Authentication methods of security-dependent services, such as access to private clouds and payments using smartphone banking, are moving toward applying convenient biometrics [1,2,3,4,5,6].…”

Pre-Configured Deep Convolutional Neural Networks with Various Time-Frequency Representations for Biometrics from ECG Signals

“…Considering the security requirements of any company/organization, biometrics automatically permit access only to those whose identities have been verified. It also allows the automatic authorization of cash settlements or remittances even on online platforms [1][2][3][4][5][6][7].…”