EEG Analysis in Biometric Identification and Authentication (original) (raw)
Related papers
Use of EEG as a Unique Human Biometric Trait for Authentication of an Individual
2020
With the advancement of biomedical technology, human brain signals are easy to measure and which are known as electroencephalogram (EEG) signals. These signals are used in different applications. One of the applications for brain waves is biometric authentication. For any signal to use as biometric parameter, it must possess some biometric characteristics such as universality, uniqueness, permanence, collectability, performance, acceptance, and circumvention. EEG has several characteristic to use as biometric parameter. This paper shows the uniqueness of EEG signal using some statistical parameters that support the uniqueness property of EEG.
A Review on Development of an EEG-based Biometric Authentication System
2018
The authentication system is the system that provides security and ensures confidentiality of information. Biometric systems provide the best security among other authentication systems. There are some classical approaches of biometric systems for authentication such as fingerprints, eyeballs and voices. However, the threat of fake fingerprints, eyeballs and recorded voices still compromise security walls. Electroencephalogram (EEG) signal is the electrical activity of the brain which may contain much useful information. It can possibly be used for building a robust biometric recognition because of its uniqueness. EEG signal is required to undergo advanced signal processing in order to get the useful information. There are three main stages included in advanced signal processing namely preprocessing, feature extraction and classification. The techniques of signal processing are categorized into two groups which are linear and non-linear. Although many different research activities h...
A Generic Framework for EEG-Based Biometric Authentication
2015 12th International Conference on Information Technology - New Generations, 2015
Biometric systems are a part and parcel of everyone's lives these days. However, with the increase in their use, the security risks associated with them have equally increased. Hence, there is an increased need to develop systems which use biometrics efficiently and ensure the authentication is integral and effective. This paper aims to introduce the concept of using Electro Encephalogram (EEG), commonly known as brain waves, as a biometric. A wavelet based feature extraction method is proposed, that uses visual and auditory evoked potentials. The future scope, pros and cons of this biometric are analyzed next.
Biometric Authentication System Using EEG Brain Signature
This paper proposes an algorithm to recognize EEG signals of individuals using a biometric authentication. Research on brain signals shows that each individual has unique brain wave pattern. Electroencephalography signals generated by mental tasks are acquired to extract the distinctive brain signature of an individual. Electroencephalography signals recorded during four biometric tasks, such as relax, read, spell and math activity were acquired from twenty five healthy subjects.We propose an algorithm for recognition of individuals using power spectral density using Recurrent Neural Network and Feed forward Neural Network. The performance of the Recurrent Neural Network is appreciable with an accuracy of 98% for the spell task and 95% for the read task.
Analysis of factors that influence the performance of biometric systems based on EEG signals
Expert Systems with Applications, 2021
Searching for new biometric traits is currently a necessity because traditional ones such as fingerprint, voice, or face are highly prone to forgery. For this reason, the study of bioelectric signals has the potential to develop new biometric systems. A motivation for using electroencephalogram signals is that they are unique to each person and are much more difficult to replicate than conventional biometrics. The objective of this study is to analyze the factors that influence the performance of a biometric system based on electroencephalogram signals. This work uses six different classifiers to compare several decomposition levels of the discrete wavelet transform as a preprocessing technique and also explores the importance of the recording time. These classifiers are Gaussian Naïve Bayes Classifier, K-Nearest Neighbors, Random Forest, AdaBoost, Support Vector Machine, and Multilayer Perceptron. This work proves that the decomposition level does not have a high impact on the overall result of the system. On the other hand, the recording time of electroencephalograms has a significant impact on the performance of the classifiers. It is worth mentioning that this study used two different datasets to validate the results. Finally, our experiments show that Support Vector Machine and AdaBoost are the best classifiers for this particular problem since they achieved a sensitivity, specificity, and accuracy of 85.94 ± 1.8, 99.55 ± 0.06, 99.12 ± 0.11 and 95.54 ± 0.53, 99.91 ± 0.01, and 99.83 ± 0.02 respectively.
Akademia Baru Biometric Authentication of Individuals using Electroencephalography ( EEG )
2017
In this research we proposed a novel authentication method based on electroencephalogram (EEG) responses of individuals while writing their own signature and other ́s signature. Two healthy male subjects (average years 27) participated in the experiments. In one task of the experiments, we asked them to sign their personal signatures on a paper within 2 seconds just after hearing a beep sound. This was repeated 24 times with an interval of 5 seconds. In addition, the same experiment was done but subjects were asked to sign a new unfamiliar signature, that is, other person ́s signature. During these two tasks, EEG was recorded at 14 locations by using Emotiv EPOC neuro-headset. Comparison of the averages of the frequency powers after fast Fourier transformation of EEG data revealed the similarities and differences at different frequencies between two tasks. Average comparison was done for each individual channel in 10 frequency ranges within 4 to 43.5 Hz showed the significant differ...
Survey of EEG-based biometric authentication Conference
2018
User authentication systems based on EEG (electroencephalography) is currently popular, marking an inflection point in the field. Recently, the scientific community has been making tremendous attempts towards perceiving uniqueness of brain signal patterns. Several types of methodical approaches have been proposed and prototyped to analyze EEG data with various signal-processing methods and pattern-recognition algorithms. Even though there are many stimulation methods to produce reasonable distinctiveness between subjects, optimization and lowering task complexity are still desirable from technoeconomic points of view. With recent technological advancement of EEG signal capturing devices, the process is getting comparatively simpler as devices are capable of providing better portability with reduced calibration time. However, most detailed analysis suggests that a minimal number of most appropriate channels should be selected for better results, even if a system is equipped with the ...
BRAIN COMPUTER INTERFACE FOR BIOMETRIC AUTHENTICATION BY RECORDING SIGNAL
Computer Science & Information Technology (CS & IT), 2019
Electroencephalogram(EEG) is done in several ways, which are referred to as brainwaves, which scientists interpret as an electromagnetic phenomenon that reflects the activity in the human brain, this study is used to diagnose brain diseases such as schizophrenia, epilepsy, Parkinson's, Alzheimer's, etc. It is also used in brain machine interfaces and in brain computers. In these applications wireless recording is necessary for these waves. What we need today is Authentication? Authentication is obtained from several techniques, in this paper we will check the efficiency of these techniques such as password and pin. There are also biometrics techniques used to obtain authentication such as heart rate, fingerprint, eye mesh and sound, these techniques give acceptable authentication. If we want to get a technology that gives us integrated and efficient authentication, we use brain wave recording. The aim of the technique in our proposed paper is to improve the efficiency of the reception of radio waves in the brain and to provide authentication. Keyword Related work, EEG brain signal, Brain wave, Overall projcet outline, System requirements. 1. INTRODCTION The evolution of life technology has many requirements. The application of this technology on the ground includes obtaining permission for the person authorized to enter (all these methods depend on the pin technique or password to obtain permission from the system) as in banks, experimental laboratories, nuclear reactor, confidential data in computerized systems ... Houses Smart.As a result of the development of piracy in return for the weakness in the development of authentication techniques, the main purpose of which is to avoid the imbalance that occurs in this aspect.The best solution to avoid these problems is to follow a new approach as in our paper of these biometrics, As a result of the unique efficiency of this road for each user is more effective than others and less prone to the problems mentioned. EEG is one way to measure brain waves of different-frequencies in human brain, By placing the electrodes in specific-places of the scalp (head) in order to identify and record brain waves. These recordings are a collection of the amount of waves produced by neurons, which are estimated in millions of interconnected and adjacent neurons. Here, it should be noted that the EEG is
2020
In this study, we propose the authentication of individuals using electroencephalograms (EEGs) evoked by the application of invisible visual stimuli. In our previous study, we introduced a wavelet transform, which is a time-frequency analysis method, and applied it to extract features, including time information, to enable more accurate discrimination between individuals. An equal error rate (EER) of 9.4 % was achieved using Euclidean distance matching. In this paper, we introduce a machine learning-based approach in order to further improve the verification performance. An EER of 8.1 % is achieved by the proposed method after training the constituent neural networks using ensemble learning with 30 networks.