Neurotechnology is safe
Fragment of the report "Neurotechnologies in security" at the ZeroNights'16 conference on the use of data on brain activity in biometric control systems.
When using data on brain activity as a biometric parameter, the overall architecture of the verification system is preserved.
An authorized user has an identifier and a biometric sample. For verification, data from the database and from the user are compared. But in working with the data of brain activity there are subtleties.
We obtain data on brain activity by means of electroencephalography .
EEG captures the total electrical activity of the brain according to the potential difference on the surface of the scalp. Potentials remove special electrodes.
')
The EEG signal is non-linear, noisy and non-stationary.
Removal of the EEG - contact procedure: you need to install the electrodes on the user's head. And long, because the electrical activity of the brain is extended in time. We need to collect some amount of data, while they can not be removed for a long time. Over long periods of time manifest non-linear distortion of the EEG signal.
We cope with nonlinearity by a series of short measurements during which the signal can be considered linear.
EEG may contain signals not related to brain activity. These are artifacts .
Artifacts may be of a physical or physiological nature.
EEG affects muscle contraction, and the guidance from electrical devices, and the quality of the electrodes.
To increase the purity of the signal can be procedurally, hardware, software.
It is best to shoot eeg in a relaxed atmosphere, when the user is not moving, relaxed and concentrated. You can add external incentives that are repeated from procedure to procedure. For example, the same music, pictures.
Artifacts can be recognized in person. It is necessary to remove the EEG when a person blinks, nods, clenches his jaws, smiles, speaks. Artifacts will appear on the electroencephalogram. You can supplement the EEG with myo-sensors and accelerometers that register muscle contraction and head movement. Then cut out the sections with extraneous signals from the electroencephalogram.
The quality of the EEG signal directly depends on the quality of the contact of the electrodes with the surface of the scalp. It is important to properly position the electrodes and reduce the resistance between them and the skin, for this you can use conductive gels or saline solution.
The removed signal needs to be cleared of noise. For example, using band-pass filtering systems. You can increase the purity of the signal by fine selection of the filter bandwidth. The bandwidth depends on the specific neural interface.
After cleaning the signal, you need to highlight its significant features. This process is called feature extraction .
Feature extraction is the acquisition of the characteristics of the most informative fragments of a signal. The characteristics obtained can be used in classification problems.
For EEG processing, you can use the Fast Fourier Transform , as a result we get the frequency characteristics of the signal.
However, the FFT is a linear method, and the EEG signal is non-stationary.
For processing a non-stationary signal, time-frequency analysis methods are more suitable. For example, wavelet transform .
The wavelet transform represents the EEG signal as a sequence of wavelets . This allows us to consider the frequency component of the EEG in the time perspective and provides a clear binding of the spectrum of significant features of the signal to time.
The last stage of work with EEG in the verification system is a biometric matcher.
With all its limitations, EEG has the potential to be used in biometric systems.
EEG can be used as a biometric parameter , because the brain activity is individual . Its unique makes synchronized activity of groups of neurons.
Neurons that process the same signals form metastable groups.
Signals that correspond to a single external stimulus or cognitive event, cause synchronized activity of the neurons united in groups. A certain level of such synchronization is maintained at rest.
Synchronized activity of neurons is observed on electroencephalograms.
The EEG as a biometric parameter has advantages :
When using data on brain activity as a biometric parameter, the overall architecture of the verification system is preserved.
An authorized user has an identifier and a biometric sample. For verification, data from the database and from the user are compared. But in working with the data of brain activity there are subtleties.
We obtain data on brain activity by means of electroencephalography .
EEG captures the total electrical activity of the brain according to the potential difference on the surface of the scalp. Potentials remove special electrodes.
')
The EEG signal is non-linear, noisy and non-stationary.
Removal of the EEG - contact procedure: you need to install the electrodes on the user's head. And long, because the electrical activity of the brain is extended in time. We need to collect some amount of data, while they can not be removed for a long time. Over long periods of time manifest non-linear distortion of the EEG signal.
We cope with nonlinearity by a series of short measurements during which the signal can be considered linear.
EEG may contain signals not related to brain activity. These are artifacts .
Artifacts may be of a physical or physiological nature.
EEG affects muscle contraction, and the guidance from electrical devices, and the quality of the electrodes.
To increase the purity of the signal can be procedurally, hardware, software.
It is best to shoot eeg in a relaxed atmosphere, when the user is not moving, relaxed and concentrated. You can add external incentives that are repeated from procedure to procedure. For example, the same music, pictures.
Artifacts can be recognized in person. It is necessary to remove the EEG when a person blinks, nods, clenches his jaws, smiles, speaks. Artifacts will appear on the electroencephalogram. You can supplement the EEG with myo-sensors and accelerometers that register muscle contraction and head movement. Then cut out the sections with extraneous signals from the electroencephalogram.
The quality of the EEG signal directly depends on the quality of the contact of the electrodes with the surface of the scalp. It is important to properly position the electrodes and reduce the resistance between them and the skin, for this you can use conductive gels or saline solution.
The removed signal needs to be cleared of noise. For example, using band-pass filtering systems. You can increase the purity of the signal by fine selection of the filter bandwidth. The bandwidth depends on the specific neural interface.
After cleaning the signal, you need to highlight its significant features. This process is called feature extraction .
Feature extraction is the acquisition of the characteristics of the most informative fragments of a signal. The characteristics obtained can be used in classification problems.
For EEG processing, you can use the Fast Fourier Transform , as a result we get the frequency characteristics of the signal.
However, the FFT is a linear method, and the EEG signal is non-stationary.
For processing a non-stationary signal, time-frequency analysis methods are more suitable. For example, wavelet transform .
The wavelet transform represents the EEG signal as a sequence of wavelets . This allows us to consider the frequency component of the EEG in the time perspective and provides a clear binding of the spectrum of significant features of the signal to time.
The last stage of work with EEG in the verification system is a biometric matcher.
With all its limitations, EEG has the potential to be used in biometric systems.
EEG can be used as a biometric parameter , because the brain activity is individual . Its unique makes synchronized activity of groups of neurons.
Neurons that process the same signals form metastable groups.
Signals that correspond to a single external stimulus or cognitive event, cause synchronized activity of the neurons united in groups. A certain level of such synchronization is maintained at rest.
Synchronized activity of neurons is observed on electroencephalograms.
The EEG as a biometric parameter has advantages :
- It can only be removed explicitly with the knowledge and consent of the user, because the procedure is contact and requires concentration.
- EEG can be used to authenticate an individual. If someone replaces an authorized user at work in the system, then this can be tracked by changing the nature of brain activity.
- Electroencephalogram is variable. To create a new biometric sample, it’s enough to concentrate on something else. Theoretically, we can create an unlimited number of biometric samples on a single physiological property.
- EEG reflects the user's psycho-emotional state. EEG is a physiological manifestation of behavioral characteristics.
Source: https://habr.com/ru/post/372951/
All Articles