EEG-Based Biometric Close-Set Identification Using CNN-ECOC-SVM

Lai, Chi Qin; Ibrahim, Haidi; Abdullah, Mohd Zaid; Suandi, Shahrel Azmin

doi:10.1007/978-3-030-97610-1_57

Cited by 6 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models have been analyzed with features extracted from the time domain [ 25 ] and the frequency domain [ 26 ]. Comparable results have been recently reported in [ 27 , 28 ]. Other suitable models include Hidden Markov Model (HMM) and Gaussian Mixture Models (GMM) [ 15 ].…”

Section: Related Worksupporting

confidence: 91%

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

Hernández–Álvarez

Barbierato

Caputo

et al. 2022

Sensors

View full text Add to dashboard Cite

In the current Information Age, it is usual to access our personal and professional information, such as bank account data or private documents, in a telematic manner. To ensure the privacy of this information, user authentication systems should be accurately developed. In this work, we focus on biometric authentication, as it depends on the user’s inherent characteristics and, therefore, offers personalized authentication systems. Specifically, we propose an electrocardiogram (EEG)-based user authentication system by employing One-Class and Multi-Class Machine Learning classifiers. In this sense, the main novelty of this article is the introduction of Isolation Forest and Local Outlier Factor classifiers as new tools for user authentication and the investigation of their suitability with EEG data. Additionally, we identify the EEG channels and brainwaves with greater contribution to the authentication and compare them with the traditional dimensionality reduction techniques, Principal Component Analysis, and χ2 statistical test. In our final proposal, we elaborate on a hybrid system resistant to random forgery attacks using an Isolation Forest and a Random Forest classifiers, obtaining a final accuracy of 82.3%, a precision of 91.1% and a recall of 75.3%.

show abstract

Section: Related Worksupporting

confidence: 91%

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

Hernández–Álvarez

Barbierato

Caputo

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…[21, 34, 58] and similar results to those using REC and REO in Refs. [23, 59–61]. Moreover, the proposed model provided the same quality of results in the population of the own‐made dataset I by using a more suitable headset for biometric applications, as it is wireless and more affordable, despite of having a significantly lower number of channels (14) and a lower sampling rate (128 Hz) than the BCI2000 system (64 channels and 160 Hz).…”

Section: Experiments Results and Discussionmentioning

confidence: 82%

Brainprint based on functional connectivity and asymmetry indices of brain regions: A case study of biometric person identification with non‐expensive electroencephalogram headsets

et al. 2023

View full text Add to dashboard Cite

Brain-computer interface applications for biometric person identification have increased their interest in recent years since they are potentially more secure and more difficult to counterfeit than traditional biometric techniques. However, it is necessary to consider how brain waves are acquired for this purpose, not only in terms of efficiency but also of practical comfort for the user and the affordability degree of the biosignal acquisition device so that their everyday application can become a realistic possibility. In this context, this paper presents the capabilities of using a non-expensive wireless electroencephalogram (EEG) device to extract spectral-related and functional connectivity information of brain activity. The proposed method achieved a sufficient biometric identification with two datasets of 13 and 109 subjects when comparing the performance of a sizeable classification algorithm set. In addition, a novel feature in EEG biometric identification, called asymmetry index, is introduced here. Furthermore, this is the first study in this field to consider the effect of the time-lapse between different recording sessions on the system's behaviour when using a low-cost EEG device with identification accuracy rates of up to 100%. K E Y W O R D S biometrics brain-computer interface (BCI), classification, electroencephalogram (EEG) | INTRODUCTIONThe extraction of information from human brain electrical biosignals has been the subject of much attention in recent years. The electroencephalogram, encephalogram, or EEG is a non-invasive measure used to study the central nervous system's functioning, specifically the cerebral cortex's electrical activity [1]. EEG analysis has been widely used during the last century in medicine and as a basis for interfaces between brain and machine (BMI) [2,3]. In this context, the application of feature extraction techniques and automatic classification algorithms to the EEG signals has served as support tools in various utilities such as diagnosing neurological disorder diseases [4,5], since BMIs provide their users with an alternativeThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…See Section 7.1.2 to see an evaluation of what could happen if an EKM was obtained for every heartbeat. 9 The creation of the EKM segments has been discussed in Section 7.1.1 and detailed in Appendix A.1. the peak x and α i is a free hyperparameter indicating the percentage of samples that are taken before p x .…”

Section: Ekmmentioning

confidence: 99%

“…Still, in the current state-of-the-art regarding the use of the EKG as the base for a biometric system, some drawbacks can be found. Through time, identification systems with different biometric traits have moved to use different Deep Learning (DL) techniques such as Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and others [7,8,9,10]. But, unfortunately, many of the existing works base their study on very complex DL architectures making it difficult to reproduce those systems in a real-life situation.…”

Section: Introductionmentioning

confidence: 99%

ELEKTRA: ELEKTRokardiomatrix application to biometric identification with convolutional neural networks

Fuster-Barceló

Peris-López²,

Cámara³

2022

Neurocomputing

View full text Add to dashboard Cite

EEG-Based Biometric Close-Set Identification Using CNN-ECOC-SVM

Cited by 6 publications

References 26 publications

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

EEG Authentication System Based on One- and Multi-Class Machine Learning Classifiers

Brainprint based on functional connectivity and asymmetry indices of brain regions: A case study of biometric person identification with non‐expensive electroencephalogram headsets

ELEKTRA: ELEKTRokardiomatrix application to biometric identification with convolutional neural networks

Contact Info

Product

Resources

About