Enhancing eye-movement-based biometric identification method by using voting classifiers

2005 ◽  
Author(s):  
Pawel Kasprowski ◽  
Jozef Ober
Keyword(s):  
Eye Movement ◽  
Biometric Identification ◽  
Identification Method

scholarly journals Biometric Identification Based on Eye Movement Dynamic Features

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6020
Author(s):  
Katarzyna Harezlak ◽  
Michal Blasiak ◽  
Pawel Kasprowski
Keyword(s):  
Random Forest ◽  
Decision Tree ◽  
Eye Movement ◽  
Classification Performance ◽  
Biometric Identification ◽  
Largest Lyapunov Exponent ◽  
Dynamic Features ◽  
Signal Features ◽  
Good Classification Performance ◽  
Test Sets

The paper presents studies on biometric identification methods based on the eye movement signal. New signal features were investigated for this purpose. They included its representation in the frequency domain and the largest Lyapunov exponent, which characterizes the dynamics of the eye movement signal seen as a nonlinear time series. These features, along with the velocities and accelerations used in the previously conducted works, were determined for 100-ms eye movement segments. 24 participants took part in the experiment, composed of two sessions. The users’ task was to observe a point appearing on the screen in 29 locations. The eye movement recordings for each point were used to create a feature vector in two variants: one vector for one point and one vector including signal for three consecutive locations. Two approaches for defining the training and test sets were applied. In the first one, 75% of randomly selected vectors were used as the training set, under a condition of equal proportions for each participant in both sets and the disjointness of the training and test sets. Among four classifiers: kNN (k = 5), decision tree, naïve Bayes, and random forest, good classification performance was obtained for decision tree and random forest. The efficiency of the last method reached 100%. The outcomes were much worse in the second scenario when the training and testing sets when defined based on recordings from different sessions; the possible reasons are discussed in the paper.

scholarly journals Multi-banking automatic teller machine transaction system by utilizing GSM and biometric identification with one single touch

2020 ◽  
Author(s):  
Muhammad Yasir Imam ◽  
Nabila Jannat ◽  
Gul Sher Khan
Keyword(s):  
Current System ◽  
Biometric Identification ◽  
User Identification ◽  
Identification Scheme ◽  
Secure Systems ◽  
Machine System ◽  
Identification Method ◽  
Automatic Teller Machine ◽  
Verification Methods ◽  
High Level

Everyone in many banks has many types of bank accounts, people need to bring a lot of ATM cards for their transaction, many types of PINs for each account. In the current system, ATM machine user identification systems depend only on bank ATM cards, safety secret pin code, and also such kind of user ID verification methods which measures are not optimal and sometimes there are incidents where we dismiss our secret security PIN code, lose ATM cards, rob ATM cards, stolen secret PIN code.Weare presenting a fresh concept or idea for the ATM machine user identification scheme, "Multi-banking Automatic Teller Machine Transaction System by Utilizing GSM and Biometric Identification with One Single Touch" to get control of the issues in the current ATM machine system. On the base of the fingerprint identification method which is also one of the most secure systems, unofficial accesses are blocked, as it makes the fingerprint technique a unique recognition for every user. Our introduced system also assures a very secure GSM and OTP based transaction deals. The presented scheme has no hazard in managing many account transaction deals and performs high-level security, compared to the current ATM machine scheme.

scholarly journals Multi-banking automatic teller machine transaction system by utilizing GSM and biometric identification with one single touch

2020 ◽  
Author(s):  
Muhammad Yasir Imam ◽  
Nabila Jannat ◽  
Gul Sher Khan
Keyword(s):  
Current System ◽  
Fingerprint Identification ◽  
Biometric Identification ◽  
User Identification ◽  
Identification Scheme ◽  
Machine System ◽  
Identification Method ◽  
Automatic Teller Machine ◽  
Verification Methods ◽  
High Level

Everyone in many banks has many types of bank accounts, people need to bring a lot of ATM cards for their transaction, manytypes of PINs for each account.In the current system, ATM machine user identification systems depend only on bank ATM cards, safety secret pin code, and also such kind of user ID verification methods which measures are not optimal and sometimes there are incidents where we dismiss our secret security PIN code, lose ATM cards, rob ATM cards, stolen secret PIN code.Weare presenting a fresh concept or idea for the ATM machine user identification scheme, "Multi-banking Automatic TellerMachine Transaction System by Utilizing GSM and Biometric Identification with One Single Touch" to get control of theissues in the current ATM machine system. On the base of fingerprint identification method which is also one of most securesystems, unofficial accesses are blocked, as it makes fingerprint technique a unique recognition for every user. Our introducedsystem also assures a very secure GSM and OTP based transaction deals. The presented scheme has no hazard in managingmany account transaction deals and performs high-level security, compared to the current ATM machine scheme.

Sign in / Sign up

Export Citation Format

Share Document