December 24, 2022Open Access

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

Q: What is the clinical evidence from this study?

Study design: Other. Population: User authentication. Intervention: EEG-based user authentication system using Isolation Forest and Random Forest classifiers vs. Traditional dimensionality reduction techniques (PCA, χ2). Primary outcome: Authentication accuracy, precision, and recall.

Q: What does this research mean for the field?

A hybrid EEG-based user authentication system utilizing Isolation Forest and Random Forest classifiers achieves an accuracy of 82.3%, a precision of 91.1%, and a recall of 75.3% against random forgery attacks. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

Key Result

A hybrid EEG-based user authentication system using Isolation Forest and Random Forest classifiers achieved a final accuracy of 82.3%, a precision of 91.1%, and a recall of 75.3%.

Structured PICO

Intervention

EEG-based user authentication system employing One-Class (Isolation Forest, Local Outlier Factor) and Multi-Class (Random Forest) Machine Learning classifiers

Comparator

Traditional dimensionality reduction techniques (Principal Component Analysis and χ2 statistical test)

Outcome

Authentication accuracy, precision, and recall

A hybrid machine learning system using Isolation Forest and Random Forest classifiers can achieve 82.3% accuracy for EEG-based biometric user authentication.

Abstract

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%.

Mark Helpful

Bookmark

Relay

View Full Paper

Mark Helpful

Bookmark

Relay

View Full Paper

Cite This Study

Hernández–Álvarez et al. (Sat,) conducted a other in User authentication. EEG-based user authentication system using Isolation Forest and Random Forest classifiers vs. Traditional dimensionality reduction techniques (PCA, χ2) was evaluated on Authentication accuracy, precision, and recall. A hybrid EEG-based user authentication system using Isolation Forest and Random Forest classifiers achieved a final accuracy of 82.3%, a precision of 91.1%, and a recall of 75.3%.

synapsesocial.com/papers/6a1d62251e7099f691055848 https://doi.org/https://doi.org/10.3390/s23010186

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: