Evaluation method and device for electroencephalogram signal quality and electronic equipment
By performing frequency follow-up feature access verification and quality scoring on SSVEP EEG signals, the problem of degradation in the quality evaluation effect of EEG signals in the existing technology is solved, and accurate evaluation of SSVEP EEG signals quality and brain function analysis are achieved. In-depth.
Patent Information
- Application Number
- CN202411365921.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-27
- Publication Date
- 2025-01-10
AI Technical Summary
When evaluating the quality of EEG signal, it is difficult to effectively process the characteristic components in specific scenarios, resulting in a decrease in the evaluation effect of SSVEP EEG signal quality.
By performing frequency follow feature access verification of SSVEP EEG signals, the EEG data characteristics are determined, and their quality scores are calculated, and weighted summing is performed to obtain a total quality score and evaluate the quality of the EEG signal.
Accurate evaluation of the quality of SSVEP EEG signal is achieved, a high-quality data foundation is provided, and the accuracy of evaluation is improved and the in-depth analysis of brain function is improved.
Smart Images
Figure CN119293441A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of electroencephalogram (EEG) signal processing, and for example, to an EEG signal quality evaluation method and device, and electronic equipment. Background Art
[0002] At present, EEG signals are widely used in clinical diagnosis, brain-computer interface, psychological emotion analysis, and sleep research. In the field of brain-computer interface, the quality of EEG signals is directly related to the performance of the system and the user experience. High-quality signals can improve the response speed and accuracy of the system, while low-quality signals may cause the system to respond slowly or inaccurately, affecting user operation and satisfaction. Therefore, the quality assessment of EEG signals is of great significance to the realization of EEG signal applications.
[0003] In order to evaluate the quality of EEG signals, the relevant technology discloses an EEG signal quality evaluation method, including: band-pass filtering the current head electrical signal according to a preset first cutoff frequency and a second cutoff frequency to obtain the filtered current head electrical signal, and evaluating the quality of the current EEG signal according to the filtered current head electrical signal and a preset EEG signal baseline amplitude of the subject.
[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:
[0005] The relevant technology is mainly aimed at the general characteristics of EEG signals, and the quality of EEG signals is evaluated by comparing the head electrical signals with the preset EEG signal baseline amplitude of the test subject. However, when targeting specific scenarios, the effect of quality evaluation will be reduced to a certain extent. For example, the characteristic components of some induced EEG responses may affect the head electrical signals, making it difficult to calculate the SSVEP (steady-state visual evoked potentials) EEG signals.
[0006] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention
[0007] In order to provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. The summary is not an extensive review, nor is it intended to identify key / critical components or delineate the scope of protection of these embodiments, but rather serves as a prelude to the detailed description that follows.
[0008] The embodiments of the present disclosure provide a method and device for evaluating the quality of electroencephalogram (ESVEP) signals, and an electronic device for evaluating the quality of SSVEP EEG signals.
[0009] In some embodiments, the method for evaluating the quality of EEG signals includes: performing access verification on the steady-state visual evoked potential (SSVEP) EEG signal based on its frequency following characteristics; if the access verification is passed, determining the EEG data characteristics of the SSVEP EEG signal; calculating the quality score of the EEG data characteristics; summing the quality scores of the EEG data characteristics to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal based on the total quality score.
[0010] Optionally, based on the frequency following characteristics of the steady-state visual evoked potential (SSVEP) EEG signal, access verification is performed on the SSVEP EEG signal, including: segmenting the SSVEP EEG signal; determining whether the SSVEP EEG signals within different segment window lengths contain evoked response frequency components in the frequency following characteristics; and if the SSVEP EEG signals within different segment window lengths all contain evoked response frequency components, determining that the access verification is passed.
[0011] Optionally, determining the EEG data features of the SSVEP EEG signal includes: determining the signal type of the SSVEP EEG signal; and using the data features corresponding to the signal type of the SSVEP EEG signal as the EEG data features.
[0012] Optionally, data features corresponding to the signal type of the SSVEP EEG signal are used as EEG data features, including one or more of the following methods: when the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio, the broadband signal-to-noise ratio and the spatial projection correlation coefficient are used as EEG data features; when the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal without a frequency mark, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features; when the signal type of the SSVEP EEG signal is an overall SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio, the broadband signal-to-noise ratio, the recognition accuracy, the optimal response time and the optimal information transmission rate are used as EEG data features; when the signal type of the SSVEP EEG signal is an overall SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features.
[0013] Optionally, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are calculated as follows: the power spectrum of the SSVEP EEG signal is calculated using the average periodogram; the narrowband signal-to-noise ratio of the main frequency, the broadband signal-to-noise ratio and the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio of the harmonics in the power spectrum are calculated respectively; and / or, the spatial projection correlation coefficient is calculated as follows: each task stimulation frequency of the SSVEP EEG signal is obtained; a sine-cosine template of each task stimulation frequency of the SSVEP EEG signal and the corresponding frequency multiple is constructed; the spatial projection correlation coefficient of each task stimulation frequency of the SSVEP EEG signal and the corresponding frequency multiple sine-cosine template is calculated; and / or, the recognition accuracy, optimal response time and optimal information transmission rate are calculated as follows: each task stimulation frequency of the SSVEP EEG signal is obtained; each task stimulation frequency is classified and identified using the filter bank canonical correlation analysis FBCCA algorithm to obtain the recognition accuracy, the optimal response time and the optimal information transmission rate.
[0014] Optionally, the quality scores of the EEG data features are summed to obtain a total quality score of the EEG signal, including: weighted summing the quality scores of the EEG data features to obtain a weighted total score; normalizing the calculated weighted total score to obtain a total quality score of the EEG signal.
[0015] Optionally, weighted summation is performed on the quality scores of the EEG data features, including: obtaining the weight of each quality score of the EEG data features; wherein the weight is determined by the feature distribution of the EEG data features; and weighted summation is performed on the quality scores of the EEG data features according to the weight of each quality score.
[0016] In some embodiments, the device for evaluating the quality of EEG signals includes: a data calibration module, configured to perform access verification on the steady-state visual evoked potential (SSVEP) EEG signal based on the frequency following characteristics of the SSVEP EEG signal; a data processing module, connected to the data calibration module, configured to determine the EEG data characteristics of the SSVEP EEG signal when the access verification is passed; a score calculation module, connected to the data processing module, configured to sum the quality scores of the EEG data characteristics to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal based on the total quality score.
[0017] In some embodiments, the device for evaluating the quality of electroencephalogram signals includes a processor and a memory storing program instructions, and the processor is configured to execute the method for evaluating the quality of electroencephalogram signals as described above when running the program instructions.
[0018] In some embodiments, the electronic device includes: an electronic device body; and the device for evaluating the quality of electroencephalogram signals as described above, installed on the electronic device body.
[0019] The method and device for evaluating the quality of electroencephalogram signals and the electronic device provided in the embodiments of the present disclosure can achieve the following technical effects:
[0020] In the embodiment of the present disclosure, while ensuring that the collected EEG signal has a stable frequency following characteristic, the access verification of the SSVEP EEG signal can screen out signals that meet specific frequency characteristics, providing a high-quality data basis for subsequent signal processing and analysis. When the access verification is passed, the determined EEG data features of the SSVEP EEG signal can reflect the quality of the EEG signal, facilitate the quantification of the quality of the EEG signal, and contribute to the in-depth analysis of brain function and state. The quality score of each feature of the EEG signal is calculated, and the EEG signal is quantified to provide an objective standard for evaluating the signal quality, thereby improving the accuracy of the evaluation. By summing the quality scores of the EEG data features, a comprehensive total quality score is obtained, which can comprehensively reflect the overall quality of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score. In this way, the embodiment of the present disclosure realizes the quality evaluation of the SSVEP EEG signal by extracting the EEG data features of the SSVEP EEG signal.
[0021] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:
[0023] Figure 1 is a schematic diagram of an implementation environment of a method for evaluating the quality of an electroencephalogram signal according to an embodiment of the present disclosure;
[0024] Figure 2 is a schematic diagram of a method for evaluating the quality of an electroencephalogram signal provided by an embodiment of the present disclosure;
[0025] Figure 3 is a schematic diagram of another method for evaluating the quality of an electroencephalogram signal provided by an embodiment of the present disclosure;
[0026] Figure 4 is a schematic diagram of another method for evaluating the quality of an electroencephalogram signal provided by an embodiment of the present disclosure;
[0027] Figure 5 is a schematic diagram of another method for evaluating the quality of an electroencephalogram signal provided by an embodiment of the present disclosure;
[0028] Figure 6is a schematic diagram of a device for evaluating the quality of an electroencephalogram signal provided by an embodiment of the present disclosure;
[0029] Figure 7 is a schematic diagram of another device for evaluating the quality of electroencephalogram signals provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0030] In order to be able to understand the features and technical contents of the embodiments of the present disclosure in more detail, the implementation of the embodiments of the present disclosure is described in detail below in conjunction with the accompanying drawings. The attached drawings are for reference only and are not used to limit the embodiments of the present disclosure. In the following technical description, for the convenience of explanation, a full understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, to simplify the drawings, well-known structures and devices can be simplified for display.
[0031] The terms "first", "second", etc. in the technical solutions described in the embodiments of the present disclosure are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged where appropriate, so as to describe the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.
[0032] Unless otherwise stated, the term "plurality" means two or more.
[0033] In the embodiment of the present disclosure, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B indicates: A or B.
[0034] The term "and / or" is a description of the association relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A or B, or, A and B.
[0035] The term "correspondence" may refer to an association relationship or a binding relationship. The correspondence between A and B means that there is an association relationship or a binding relationship between A and B.
[0036] BCI (Brain-Computer Interface) technology is a revolutionary way of communication and control that allows the brain to communicate directly with external devices without relying on traditional nerve and muscle pathways. The core of BCI technology is to capture the brain's electrical signals and control external devices by decoding the brain's signals, thereby providing assistance to people with disabilities or enhancing the cognitive and perceptual abilities of normal people.
[0037] Steady-state visual evoked potential (SSVEP) is one of the current mainstream paradigms in the field of brain-computer interface. It can be widely used in brain-computer active rehabilitation systems, brain-computer interactive typing, brain-computer assisted warning, and brain-computer interface systems that use SSVEP responses as markers. Steady-state visual evoked potential is the potential change related to the stimulation frequency produced by the brain when the visual stimulus flickers at a certain frequency. The SSVEP signal is characterized by an obvious frequency following characteristic, that is, when the visual stimulus flickers at a specific frequency, the brain's potential activity will show an obvious response peak at this frequency or its harmonic frequency. Because SSVEP signals can be used to control external devices. Therefore, the quality of SSVEP signals is particularly important in brain-computer interface technology,
[0038] Figure 1 FIG. 1 is a schematic diagram of an implementation environment of a method for evaluating the quality of an electroencephalogram signal according to an embodiment of the present disclosure. Figure 1 As shown, the implementation environment may include an EEG cap 100 , an EEG amplifier 200 , and a processor 700 .
[0039] Among them, the EEG cap 100 can collect SSVEP responses through different collection methods such as wet electrodes, dry electrodes or semi-dry electrodes. The EEG amplifier 200 can amplify the collected SSVEP response and transmit the amplified signal to the processor 700. The processor 700 performs quality assessment on the SSVEP EEG signal. The processor 700 of the disclosed embodiment calculates the narrowband signal-to-noise ratio, broadband signal-to-noise ratio, frequency template matching correlation, benchmark algorithm recognition accuracy, benchmark algorithm optimal response time, benchmark algorithm optimal information transmission rate and other indicators of the SSEVP EEG signal to achieve quality evaluation of the real-time collected SSVEP EEG signal and overall quality evaluation of the complete SSVEP EEG signal collected throughout the entire segment. This provides a reference for the development of steady-state visual evoked potential brain-computer interface algorithms and the development of future general brain-computer interface recognition algorithms.
[0040] Combination Figure 2 As shown, the present disclosure provides a method for evaluating the quality of an electroencephalogram signal, comprising:
[0041] S201, the processor performs access verification on the steady-state visual evoked potential (SSVEP) EEG signal according to the frequency following characteristics of the SSVEP EEG signal.
[0042] S202: When the access verification is passed, the processor determines the EEG data features of the SSVEP EEG signal.
[0043] S203, the processor calculates the quality score of the EEG data feature.
[0044] S204, the processor sums the quality scores of the EEG data features to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
[0045] By adopting the method for evaluating the quality of EEG signals provided by the embodiment of the present disclosure, while ensuring that the collected EEG signals have stable frequency following characteristics, the access verification of SSVEP EEG signals can screen out signals that meet specific frequency characteristics, providing a high-quality data basis for subsequent signal processing and analysis. Key features in EEG signals, such as amplitude, power spectral density, etc., are essential for understanding brain activity. When the access verification is passed, the determined EEG data features of the SSVEP EEG signals can reflect the quality of the EEG signals, facilitate the quantification of the quality of the EEG signals, and help to deeply analyze the brain function and state. The quality score of each feature of the EEG signal is calculated, and the signal quality is evaluated by quantifying the EEG signals to provide an objective standard, thereby improving the accuracy of the evaluation. By summing the quality scores of the EEG data features, a comprehensive total quality score is obtained, which can comprehensively reflect the overall quality of the EEG signals, so as to evaluate the quality of the EEG signals according to the total quality score. In this way, the embodiment of the present disclosure realizes the quality evaluation of the SSVEP EEG signals by extracting the EEG data features of the SSVEP EEG signals.
[0046] Optionally, based on the frequency following characteristics of the steady-state visual evoked potential (SSVEP) EEG signal, access verification is performed on the SSVEP EEG signal, including: segmenting the SSVEP EEG signal; determining whether the SSVEP EEG signals within different segment window lengths contain evoked response frequency components in the frequency following characteristics; and if the SSVEP EEG signals within different segment window lengths all contain evoked response frequency components, determining that the access verification is passed.
[0047] Combination Figure 3 As shown, the embodiment of the present disclosure provides another method for evaluating the quality of an EEG signal, comprising:
[0048] S301, the processor segments the SSVEP electroencephalogram signal.
[0049] S302, the processor determines whether the SSVEP electroencephalogram signals within different segment window lengths contain the evoked response frequency component in the frequency following feature.
[0050] S303: When the SSVEP electroencephalogram signals in different segmented window lengths all contain evoked response frequency components, the processor determines that the access verification is passed.
[0051] S304: When the access verification is passed, the processor determines the EEG data features of the SSVEP EEG signal.
[0052] S305 , the processor calculates the quality score of the EEG data feature.
[0053] S306: The processor sums the quality scores of the EEG data features to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
[0054] In the disclosed embodiment, the SSVEP EEG signal is segmented according to a fixed time window to divide the continuous SSVEP EEG signal into multiple segments. In this way, long signals can be decomposed into shorter segments, which is easier for EEG signal analysis. In each segment, a frequency analysis method (such as fast Fourier transform) is used to detect whether there is an evoked response frequency component corresponding to the stimulation frequency. It is possible to confirm whether the signal contains the expected frequency components, thereby verifying the validity of the signal. If evoked response frequency components are detected in all segments, it is considered that the access verification has passed. The collected EEG signal has a stable frequency following characteristic and is suitable for subsequent BCI applications.
[0055] Optionally, determining the EEG data features of the SSVEP EEG signal includes: determining the signal type of the SSVEP EEG signal; and using the data features corresponding to the signal type of the SSVEP EEG signal as the EEG data features.
[0056] Combination Figure 4 As shown, the embodiment of the present disclosure provides another method for evaluating the quality of an EEG signal, comprising:
[0057] S401, the processor performs access verification on the steady-state visual evoked potential (SSVEP) EEG signal according to the frequency following characteristics of the SSVEP EEG signal.
[0058] S402: When the access verification is passed, the processor determines the signal type of the SSVEP electroencephalogram signal.
[0059] S403: The processor uses the data feature corresponding to the signal type of the SSVEP electroencephalogram signal as the electroencephalogram data feature.
[0060] S404, the processor calculates the quality score of the EEG data feature.
[0061] S405, the processor sums the quality scores of the EEG data features to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
[0062] In the disclosed embodiment, the collected SSVEP EEG signals include a variety of different types, and each EEG signal type can extract data features corresponding to the type. In this way, the disclosed embodiment adopts different evaluation methods for different types of SSVEP EEG signals to obtain different data features, thereby enabling quality evaluation of different types of SSVEP EEG signals and improving the scope of application of the method.
[0063] Optionally, data features corresponding to the signal type of the SSVEP EEG signal are used as EEG data features, including one or more of the following methods: when the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio, the broadband signal-to-noise ratio and the spatial projection correlation coefficient are used as EEG data features; when the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal without a frequency mark, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features; when the signal type of the SSVEP EEG signal is an overall SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio, the broadband signal-to-noise ratio, the recognition accuracy, the optimal response time and the optimal information transmission rate are used as EEG data features; when the signal type of the SSVEP EEG signal is an overall SSVEP EEG signal with a frequency mark, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features.
[0064] In the disclosed embodiment, when the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal with a frequency marker, the SSVEP task stimulation frequency (i.e., the flickering frequency of the visual stimulation frequency target block that the subject is fixated on when collecting the data in this segment) corresponding to each time period of the data to be analyzed (each time period is usually referred to as a "trial") is confirmed according to the corresponding marker. The power spectrum of the measured data is calculated using methods such as the average periodogram. Then, based on the task stimulation frequency of the corresponding data segment, combined with the multiple frequency principle of the SSVEP response, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio of the corresponding main frequency and 2 to 5 harmonics are calculated in turn. A set of sine and cosine templates of the full task frequency and the corresponding 2-5 multiple frequencies (i.e., the totality of the frequency categories corresponding to all the markers, for example, a total of 12 frequency stimulation tasks, including f1 to f12, 2f1 to 2f12, 3f1 to 3f12, 4f1 to 4f12, 5f1 to 5f12) of the measured SSVEP EEG data are constructed. The canonical correlation analysis algorithm is used to calculate the spatial projection correlation coefficient of the measured data in each task data segment and the sine and cosine templates of the corresponding frequency. Characteristics such as narrowband signal-to-noise ratio, broadband signal-to-noise ratio and spatial projection correlation coefficient are helpful to evaluate the purity and spatial distribution characteristics of SSVEP EEG signals in a specific frequency range, thereby ensuring the real-time processing and recognition accuracy of the signal.
[0065] When the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal without a frequency marker, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features. If the real-time SSVEP EEG signal has no frequency marker, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are mainly calculated. This can effectively reflect the quality of the signal within a specific frequency range.
[0066] When the signal type of the SSVEP EEG signal is an overall SSVEP EEG signal with a frequency marker, first, the SSVEP task stimulation frequency corresponding to each period of the data to be analyzed is confirmed according to the corresponding marker. The power spectrum of the measured data is calculated using methods such as the average periodogram. Secondly, based on the task stimulation frequency of the corresponding data segment, combined with the multiple frequency principle of the SSVEP response, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio of the corresponding main frequency and the 2nd to 5th harmonics are calculated in turn. Finally, the FBCCA algorithm is used as the standard algorithm to perform classification and recognition calculations on all trials of the measured data to obtain the recognition accuracy, optimal response time, and optimal information transmission rate. The above comprehensive indicators can fully reflect the quality of the signal to evaluate the overall SSVEP EEG signal.
[0067] When the signal type of the SSVEP EEG signal is the overall SSVEP EEG signal with frequency marker, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as EEG data features. When there is no clear frequency marker, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are used as the main evaluation features. This helps to evaluate the quality of the overall SSVEP EEG signal in the absence of a clear frequency reference.
[0068] Optionally, the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio are calculated as follows: the power spectrum of the SSVEP EEG signal is calculated using the average periodogram; the narrowband signal-to-noise ratio of the main frequency, the broadband signal-to-noise ratio and the narrowband signal-to-noise ratio and the broadband signal-to-noise ratio of the harmonics in the power spectrum are calculated respectively; and / or, the spatial projection correlation coefficient is calculated as follows: each task stimulation frequency of the SSVEP EEG signal is obtained; a sine-cosine template of each task stimulation frequency of the SSVEP EEG signal and the corresponding frequency multiple is constructed; the spatial projection correlation coefficient of each task stimulation frequency of the SSVEP EEG signal and the corresponding frequency multiple sine-cosine template is calculated; and / or, the recognition accuracy, optimal response time and optimal information transmission rate are calculated as follows: each task stimulation frequency of the SSVEP EEG signal is obtained; each task stimulation frequency is classified and identified using the filter bank canonical correlation analysis FBCCA algorithm to obtain the recognition accuracy, the optimal response time and the optimal information transmission rate.
[0069] In the disclosed embodiment, the narrowband signal-to-noise ratio is the spectrum amplitude ratio of the stimulation frequency to its surrounding frequencies. The narrowband signal-to-noise ratio is calculated as follows:
[0070]
[0071] Where y(f) is the signal amplitude spectrum calculated by fast Fourier transform, and df is the spectrum resolution. During the calculation process, the data of all trials with the same frequency (usually 4-6 trials) are first superimposed and averaged before calculating the narrowband signal-to-noise ratio.
[0072] The broadband signal-to-noise ratio is the ratio of the spectral amplitude of the stimulus frequency and harmonic response to the amplitude of other frequencies within the broadband range. The broadband signal-to-noise ratio is calculated as follows:
[0073]
[0074] Where Nh is the number of harmonics, p(f) is the power spectrum at frequency f, and fs / 2 is the Nyquist frequency.
[0075] The correlation coefficient of spatial domain projection can reflect the strength of the response signal and can therefore be used to evaluate data quality.
[0076] To calculate the spatial domain projection correlation coefficient, you first need to construct a template signal. The template signal is calculated as follows:
[0077]
[0078] Where fk represents different stimulation frequencies (k = 1, 2, ..., N), N h is the harmonic order (N h =1,2,...,10).
[0079] The correlation coefficient between the measured data and is calculated by the canonical correlation analysis algorithm as the correlation coefficient of the spatial projection, where N is the number of stimulation frequencies. The calculation method of the correlation coefficient of the spatial projection is as follows:
[0080]
[0081] Among them, x represents the measured data, y represents Y fk , two multidimensional variables x and y and their linear combination X T W X and Y T W X , the canonical correlation analysis algorithm finds the weight vector W x and W y Maximize the correlation between x and y. In order to identify the stimulation frequency of SSVEP, the canonical correlation analysis algorithm calculates the canonical correlation between the multi-channel EEG data and the reference signal corresponding to each stimulation frequency, where the frequency of the reference signal with the maximum correlation is used as the stimulation frequency of the target.
[0082] The FBCCA (Filter Bank Canonical Correlation Analysis) algorithm is used as the standard recognition algorithm to calculate the data to calculate the recognition accuracy. The data window length used by the FBCCA algorithm is 2 seconds. If the window length of the data set is less than 2 seconds, the maximum window length of the data set is taken.
[0083] Response time is an important indicator of brain-computer interface. For certain paradigms and scenarios, standard algorithms in the field can be matched to calculate and judge the data. Finally, a certain score judgment is given based on the best response time.
[0084] For SSVEP paradigm application, the FBCCA algorithm of the embodiment of the present disclosure is used as the standard recognition algorithm. The data is calculated to calculate the optimal response time of multi-target recognition (the time coordinate of the inflection point when the recognition accuracy is greater than 90%).
[0085] ITR (information transfer rate) is an evaluation index that comprehensively considers recognition accuracy, number of encoding targets and response time. It is calculated as follows:
[0086]
[0087] Among them, T is the calculation response window length, N is the number of system stimulus target types, and P is the recognition accuracy. Time length is an important influencing factor in the calculation of ITR. When calculating data ITR, the window length T used is the recognition window length plus 0.5 seconds. 0.5 seconds is considered to be the time for subjects to switch between gaze targets in actual usage scenarios. The recognition accuracy guarantees whether the system can be used. Therefore, the optimal ITR is defined as the ITR value obtained by the corresponding shortest window length T that can achieve an accuracy rate of more than 90%. The ITR calculated using the FBCCA algorithm is usually distributed between 50 bits / min-250 bits / min.
[0088] Optionally, the quality scores of the EEG data features are summed to obtain a total quality score of the EEG signal, including: weighted summing the quality scores of the EEG data features to obtain a weighted total score; normalizing the calculated weighted total score to obtain a total quality score of the EEG signal.
[0089] Combination Figure 5 As shown, the embodiment of the present disclosure provides another method for evaluating the quality of an EEG signal, comprising:
[0090] S501, the processor performs access verification on the steady-state visual evoked potential (SSVEP) EEG signal according to the frequency following characteristics of the SSVEP EEG signal.
[0091] S502: When the access verification is passed, the processor determines the EEG data features of the SSVEP EEG signal.
[0092] S503: The processor calculates the quality score of the EEG data feature.
[0093] S504: The processor performs weighted summation on the quality scores of the EEG data features to obtain a weighted total score.
[0094] S505: The processor normalizes the calculated weighted total score to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
[0095] In the disclosed embodiment, the data features may include narrowband signal-to-noise ratio, broadband signal-to-noise ratio, spatial projection correlation coefficient, recognition accuracy, optimal response time, and optimal information transmission rate. When scoring the data features of SSVEP EEG signals, different data features may have different effects on the final signal quality. Therefore, the score of each feature will be assigned different weights according to its importance.
[0096] Furthermore, since different SSVEP EEG signals may vary on different scales, the total score after weighted summation needs to be normalized. Normalization usually converts the score to a uniform range, such as 0 to 1, or makes the score follow a standard normal distribution. In this way, the scores of different signals can be compared under the same standard.
[0097] Optionally, weighted summation is performed on the quality scores of the EEG data features, including: obtaining the weight of each quality score of the EEG data features; wherein the weight is determined by the feature distribution of the EEG data features; and weighted summation is performed on the quality scores of the EEG data features according to the weight of each quality score.
[0098] In the disclosed embodiment, the contribution of each feature to the signal quality is determined by analyzing the characteristic distribution of the SSVEP EEG signal. The weight of each quality score of the EEG data feature can be determined by performing a detailed analysis of the signal's spectral characteristics, time-frequency characteristics, waveform characteristics, etc. The quality score of each feature is multiplied by the corresponding weight, and then the weighted scores are added to obtain the total quality score. In this way, the disclosed embodiment achieves quality assessment of the SSVEP EEG signal by integrating multiple EEG data features.
[0099] Combination Figure 6As shown, the embodiment of the present disclosure provides an apparatus 60 for evaluating the quality of an EEG signal, comprising a data calibration module 601, a data processing module 602 and a score calculation module 603. The data calibration module 601 is configured to perform access verification on a steady-state visual evoked potential (SSVEP) EEG signal according to the frequency following characteristics of the SSVEP EEG signal. The data processing module 602 is connected to the data calibration module 601, and is configured to determine the EEG data features of the SSVEP EEG signal when the access verification is passed. The score calculation module 603 is connected to the data processing module 602, and is configured to sum the quality scores of the EEG data features to obtain a total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
[0100] By using the device 60 for evaluating the quality of EEG signals provided by the embodiment of the present disclosure, while ensuring that the collected EEG signals have stable frequency following characteristics, the access verification of the SSVEP EEG signals can screen out signals that meet specific frequency characteristics, providing a high-quality data basis for subsequent signal processing and analysis. When the access verification is passed, the determined EEG data features of the SSVEP EEG signals can reflect the quality of the EEG signals, facilitate the quantification of the quality of the EEG signals, and contribute to the in-depth analysis of brain functions and states. The quality score of each feature of the EEG signal is calculated, and the signal quality is evaluated by quantifying the EEG signals to provide an objective standard, thereby improving the accuracy of the evaluation. By summing the quality scores of the EEG data features, a comprehensive total quality score is obtained, which can comprehensively reflect the overall quality of the EEG signals, so as to evaluate the quality of the EEG signals according to the total quality score. In this way, the embodiment of the present disclosure realizes the quality evaluation of the SSVEP EEG signals by extracting the EEG data features of the SSVEP EEG signals.
[0101] Combination Figure 7 As shown, the embodiment of the present disclosure provides an apparatus 70 for evaluating the quality of an electroencephalogram signal, comprising a processor 700 and a memory 701. Optionally, the apparatus 70 may also include a communication interface 702 and a bus 703. The processor 700, the communication interface 702, and the memory 701 may communicate with each other through the bus 703. The communication interface 702 may be used for information transmission. The processor 700 may call the logic instructions in the memory 701 to execute the method for evaluating the quality of an electroencephalogram signal of the above embodiment.
[0102] In addition, the logic instructions in the memory 701 described above may be implemented in the form of software functional units and when sold or used as independent products, may be stored in a computer-readable storage medium.
[0103] The memory 701 is a computer-readable storage medium that can be used to store software programs and computer executable programs, such as program instructions / modules corresponding to the method in the embodiment of the present disclosure. The processor 700 executes the functional application and data processing by running the program instructions / modules stored in the memory 701, that is, the method for evaluating the quality of the electroencephalogram signal in the above embodiment is implemented.
[0104] The memory 701 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include a high-speed random access memory and may also include a non-volatile memory.
[0105] The disclosed embodiments provide an electronic device, comprising: an electronic device body, and the above-mentioned device 60 (70) for evaluating the quality of electroencephalogram signals. The device 60 (70) for evaluating the quality of electroencephalogram signals is installed on the electronic device body. The installation relationship described here is not limited to placement inside the electronic device body, but also includes installation connections with other components of the electronic device, including but not limited to physical connections, electrical connections, or signal transmission connections. It can be understood by those skilled in the art that the device 60 (70) for evaluating the quality of electroencephalogram signals can be adapted to a feasible electronic device body, thereby realizing other feasible embodiments.
[0106] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product, which is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The aforementioned storage medium may be a non-transient storage medium, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes.
[0107] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure so that those skilled in the art can practice them. Other embodiments may include structural, logical, electrical, process and other changes. The embodiments represent only possible changes. Unless explicitly required, separate components and functions are optional, and the order of operation may vary. The parts and features of some embodiments may be included in or replace the parts and features of other embodiments. Moreover, the words used in this application are only used to describe the embodiments and are not used to limit the claims. As used in the description of the embodiments and the claims, unless the context clearly indicates, the singular forms of "a", "an" and "the" are intended to include plural forms as well. Similarly, the term "and / or" as used in this application refers to any and all possible combinations of listings containing one or more associated ones. In addition, when used in the present application, the term "comprise" and its variants "comprises" and / or comprising refer to the presence of stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof. In the absence of further restrictions, the elements defined by the sentence "comprising a ..." do not exclude the presence of other identical elements in the process, method or device comprising the elements. In this article, each embodiment may focus on the differences from other embodiments, and the same and similar parts between the various embodiments may refer to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method part disclosed in the embodiments, then the relevant parts can refer to the description of the method part.
[0108] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software may depend on the specific application and design constraints of the technical solution. The technicians may use different methods for each specific application to implement the described functions, but such implementations should not be considered to exceed the scope of the embodiments of the present disclosure. The technicians may clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above may refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here.
[0109] In the embodiments disclosed herein, the disclosed methods and products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units can be only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to implement this embodiment. In addition, each functional unit in the embodiment of the present disclosure may be integrated in a processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.
[0110] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
Claims
1. A method for evaluating the quality of an electroencephalogram signal, characterized in that: include: According to the frequency following characteristics of the steady-state visual evoked potential (SSVEP) EEG signal, the SSVEP EEG signal is verified for access; When the access verification is passed, the EEG data characteristics of the SSVEP EEG signal are determined; Calculate quality scores of EEG data features; The quality scores of the EEG data features are summed up to obtain the total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
2. The evaluation method according to claim 1, characterized in that: According to the frequency following characteristics of the steady-state visual evoked potential (SSVEP) EEG signal, the SSVEP EEG signal is verified for access, including: Segment the SSVEP EEG signal; Determine whether the SSVEP EEG signals within different segmented window lengths contain the evoked response frequency components in the frequency following feature; When the SSVEP EEG signals within different segmented window lengths all contain evoked response frequency components, the access verification is determined to be successful.
3. The evaluation method according to claim 1, characterized in that: Determine the EEG data features of the SSVEP EEG signal, including: Determine the signal type of SSVEP EEG signal; The data features corresponding to the signal type of the SSVEP EEG signal are used as EEG data features.
4. The evaluation method according to claim 3, characterized in that: The data feature corresponding to the signal type of the SSVEP electroencephalogram signal is used as the electroencephalogram data feature, including one or more of the following methods: When the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal with a frequency marker, the narrowband signal-to-noise ratio, the wideband signal-to-noise ratio and the spatial domain projection correlation coefficient are used as EEG data features; When the signal type of the SSVEP EEG signal is a real-time SSVEP EEG signal without a frequency marker, a narrowband signal-to-noise ratio and a wideband signal-to-noise ratio are used as EEG data features; In the case where the signal type of the SSVEP EEG signal is the overall SSVEP EEG signal with frequency labeling, the narrowband signal-to-noise ratio, the wideband signal-to-noise ratio, the recognition accuracy, the best response time and the best information transmission rate are used as EEG data features; When the signal type of the SSVEP electroencephalogram signal is an overall SSVEP electroencephalogram signal with a frequency marker, a narrowband signal-to-noise ratio and a wideband signal-to-noise ratio are used as electroencephalogram data features.
5. The evaluation method according to claim 4, characterized in that: The narrowband SNR and wideband SNR are calculated as follows: The power spectrum of the SSVEP EEG signal was calculated using the average periodogram; Calculate the narrowband signal-to-noise ratio, broadband signal-to-noise ratio of the main frequency in the power spectrum and the narrowband signal-to-noise ratio, broadband signal-to-noise ratio of the harmonics; and / or, The spatial projection correlation coefficient is calculated as follows: Obtain the stimulation frequency of each task of the SSVEP EEG signal; Construct the sine and cosine templates of each task stimulation frequency and the corresponding multiple frequency of the SSVEP EEG signal; Calculate the spatial domain projection correlation coefficient of each task stimulation frequency and the corresponding sine and cosine template of the SSVEP EEG signal; and / or, The recognition accuracy, optimal response time and optimal information transmission rate are calculated as follows: Obtain the stimulation frequency of each task of the SSVEP EEG signal; The filter bank canonical correlation analysis (FBCCA) algorithm was used to classify and identify the stimulus frequency of each task to obtain the recognition accuracy, optimal response time and optimal information transmission rate.
6. The evaluation method according to any one of claims 1 to 5, characterized in that: The quality scores of EEG data features are summed to obtain the total quality score of the EEG signal, including: Perform weighted summation on the quality scores of EEG data features to obtain a weighted total score; The calculated weighted total score is normalized to obtain the total quality score of the EEG signal.
7. The evaluation method according to claim 6, characterized in that: The quality scores of EEG data features are weighted and summed, including: Obtaining the weight of each quality score of the EEG data feature; wherein the weight is determined by the feature distribution of the EEG data feature; According to the weight of each quality score, the quality scores of EEG data features are weighted summed.
8. A device for evaluating the quality of electroencephalogram signals, characterized in that: include: A data calibration module is configured to perform access verification on a steady-state visual evoked potential (SSVEP) electroencephalogram (EEG) signal according to a frequency following feature of the SSVEP electroencephalogram (EEG) signal; A data processing module, connected to the data calibration module, configured to determine the EEG data features of the SSVEP EEG signal when the access verification is passed; The scoring calculation module is connected to the data processing module and is configured to sum the quality scores of the EEG data features to obtain the total quality score of the EEG signal, so as to evaluate the quality of the EEG signal according to the total quality score.
9. A device for evaluating the quality of an electroencephalogram signal, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for evaluating the quality of an electroencephalogram signal according to any one of claims 1 to 7 when running the program instructions.
10. An electronic device, characterized in that: include: Electronic device body; The device for evaluating the quality of electroencephalogram signals as described in claim 8 or 9 is installed on the electronic device body.