Concentration index extraction method and device, electronic equipment and medium

Abstract

The invention discloses a concentration index extraction method and device, electronic equipment and a medium. The method comprises the following steps: acquiring af7 and af8 dual-channel electroencephalogram signals in front of a forehead; calculating the fuzzy entropy of the dual-channel electroencephalogram signal by adopting a preset sliding window method to obtain a dual-channel electroencephalogram signal fuzzy entropy value; smoothing the dual-channel electroencephalogram signal fuzzy entropy value to obtain a target dual-channel electroencephalogram signal fuzzy entropy value; and performing weighted calculation on the fuzzy entropy value of the target dual-channel electroencephalogram signal to obtain a concentration index. According to the concentration degree extraction method, only af7 and af8 double-channel data need to be collected, channel data are simplified, and the possibility and convenience of electroencephalogram signal collection are improved; and meanwhile, the method adopted by the invention does not need to perform frequency division processing on the data, so that the anti-interference capability of the data is further improved, and the accuracy of obtaining the concentration index is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of nonlinear physiological signal processing, and in particular to a concentration index extraction method, device, electronic equipment and medium. Background Art

[0002] The brain can receive external signal stimulation and generate corresponding electrical activities in various areas. These activities can be recorded through scalp electrodes to obtain electroencephalogram (EEG) signals. EEG signals contain various information. The current concentration index can be detected by analyzing EEG data. There are three main EEG-based concentration extraction schemes: First, the concentration is obtained by calculating the energy spectrum characteristics of different bands of EEG signals. This method first removes noise from EEG data and eliminates useless signal interference, then divides the EEG signals by wavelet decomposition, extracts α, β, δ, θ, γ band signals, and finally obtains the concentration by using the energy or power characteristics of different bands; second, the sample entropy is used for analysis. The size of the self-similarity of the EEG signal in time series and mode is calculated by sample entropy, and it is used as the attention feature in the EEG signal. The support vector machine is used for classification to extract the concentration information; third, the deep learning algorithm is used to obtain the power spectrum density through the short-time Fourier transform (STFT) as a feature, which is input into the personalized classifier based on the convolutional neural network (CNN) to extract the concentration.

[0003] Traditionally, the energy spectrum characteristics of the five bands of EEG signals, α, β, δ, θ, and γ, are used to extract the concentration index. First, the signal needs to be divided. The final extraction result is greatly affected by the signal division effect. Especially in wearable, low-power real-time EEG acquisition systems, the environment is complex and greatly affected by external signals, and the effect of signal division is difficult to guarantee. By using sample entropy for analysis, the results are highly mutated and the entropy value lacks continuity. The accuracy of the results of the deep learning method to extract the concentration is closely related to the number of channels of EEG signal acquisition. The more signal channels, the better the effect. It is not suitable for wearable forehead EEG signals with fewer signal channels. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned technical deficiencies and provide a concentration index extraction method, device, electronic device and medium to solve the technical problem that the concentration calculation method in the prior art requires frequency division processing of multi-channel EEG signals, resulting in low concentration extraction accuracy.

[0005] In order to solve the above problems, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a method for extracting a concentration index, comprising:

[0007] Obtain dual-channel EEG signals of af7 and af8 in front of the forehead;

[0008] Calculating the fuzzy entropy of the dual-channel EEG signal using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal;

[0009] Smoothing the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value;

[0010] The fuzzy entropy value of the target dual-channel EEG signal is weightedly calculated to obtain a concentration index.

[0011] In some embodiments, after acquiring the dual-channel EEG signal, the dual-channel EEG signal is further preprocessed, and the preprocessing includes:

[0012] Performing bandpass filtering on the dual-channel EEG signal to obtain an initial dual-channel EEG signal;

[0013] Performing median filtering on the initial dual-channel EEG signal to obtain a clean dual-channel EEG signal;

[0014] The fuzzy entropy of the clean dual-channel EEG signal is calculated using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal.

[0015] In some embodiments, the method of calculating the fuzzy entropy of the clean dual-channel EEG signal using a preset sliding window method to obtain the fuzzy entropy value of the dual-channel EEG signal includes:

[0016] Determining the window length of the preset sliding window according to the time scale of the clean dual-channel EEG signal;

[0017] Adding the clean dual-channel EEG signals collected in real time into a preset sliding window in time series;

[0018] Determine whether the length of the dual-channel EEG signal added to the preset sliding window is consistent with the window length;

[0019] If they are consistent, the fuzzy entropy value of the dual-channel EEG signal with the preset sliding window added is calculated to obtain the fuzzy entropy value of the dual-channel EEG signal in the current time period.

[0020] In some embodiments, the step of calculating the fuzzy entropy value of the dual-channel EEG signal with a preset sliding window added thereto to obtain the fuzzy entropy value of the dual-channel EEG signal includes:

[0021] Constructing a vector sequence of a set initial length based on the dual-channel EEG signal, and determining the endpoint distance of the vector sequence of the initial length;

[0022] Determining the similarity of the vector sequence according to the endpoint distance, and determining the similarity mean of the vector sequence of the initial length;

[0023] Based on the initial length, a preset step length is used to change the length of the vector sequence, a vector sequence of a target length is determined, and a similarity mean of the vector sequence of the target length is determined;

[0024] The fuzzy entropy value of the dual-channel electroencephalogram signal is determined according to the difference relationship between the similarity mean of the vector sequence of the initial length and the similarity mean of the vector sequence of the target length.

[0025] In some embodiments, the step of smoothing the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value includes:

[0026] The preset exponential smoothing method is used to smooth the fuzzy entropy values ​​of the dual-channel EEG signals respectively to obtain the fuzzy entropy values ​​of the target dual-channel EEG signals of af7 and af8.

[0027] In some embodiments, the preset exponential smoothing method can be expressed by the following formula:

[0028] S t =α*y t +(1-α)S t-1

[0029] Among them, S t is the exponential smoothing value at time t; y t is the fuzzy entropy value of the target dual-channel EEG signal at the tth moment; S t-1 is the exponential smoothing value at the t-1th moment; α is the smoothing constant.

[0030] In some embodiments, the fuzzy entropy value of the target dual-channel EEG signal is weightedly calculated to obtain a concentration index, which can be expressed by the following formula:

[0031] F t =0.5*S 1 t +0.5*S 2 t

[0032] where F t is the concentration index at time t, S 1 t is the fuzzy entropy value of the target EEG signal of channel af7 at time t, S 2 is the fuzzy entropy value of the target EEG signal of channel af8 at time t.

[0033] In a second aspect, the present invention further provides a concentration index extraction device, comprising:

[0034] An acquisition module is used to acquire dual-channel EEG signals of af7 and af8 in front of the forehead;

[0035] A fuzzy entropy value determination module is used to calculate the fuzzy entropy of the dual-channel EEG signal by using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal;

[0036] A smoothing processing module is used to perform smoothing on the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value;

[0037] The concentration index determination module is used to perform weighted calculation on the fuzzy entropy value of the target dual-channel EEG signal to obtain a concentration index.

[0038] In a third aspect, the present invention further provides an electronic device, comprising: a processor and a memory;

[0039] The memory stores a computer-readable program executable by the processor;

[0040] When the processor executes the computer-readable program, the steps in the concentration index extraction method described above are implemented.

[0041] In a fourth aspect, the present invention further provides a computer-readable storage medium storing one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the concentration index extraction method as described above.

[0042] Compared with the prior art, the concentration index extraction method, device, electronic device and medium provided by the present invention first obtain the dual-channel EEG signals of af7 and af8 in front of the forehead; then use the preset sliding window method to calculate the fuzzy entropy of the dual-channel EEG signals to obtain the fuzzy entropy value of the dual-channel EEG signals; and smooth the fuzzy entropy value of the dual-channel EEG signals to obtain the fuzzy entropy value of the target dual-channel EEG signals; finally, weighted calculation is performed on the fuzzy entropy value of the target dual-channel EEG signals to obtain the concentration index. The concentration extraction method adopted by the present invention only needs to collect dual-channel data of af7 and af8, simplifies the channel data, and improves the possibility and convenience of collecting EEG signals; at the same time, the method adopted by the present invention does not need to perform frequency division processing on the data, further improves its anti-interference ability, thereby improving the accuracy of obtaining the concentration index. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is an EEG electrode position reference map in the concentration index extraction method provided by the present invention;

[0044] Figure 2is a flow chart of an embodiment of a method for extracting a concentration index provided by the present invention;

[0045] Figure 3 It is a schematic diagram of an embodiment of dual-channel EEG signal preprocessing in the concentration index extraction method provided by the present invention;

[0046] Figure 4 is a schematic diagram of an embodiment of step S202 in the concentration index extraction method provided by the present invention;

[0047] Figure 5 is a schematic diagram of an embodiment of step S404 in the concentration index extraction method provided by the present invention;

[0048] Figure 6 It is a schematic diagram of an embodiment of extracting a concentration index in the concentration index extraction method provided by the present invention;

[0049] Figure 7 It is a schematic diagram of another embodiment of extracting the concentration index in the concentration index extraction method provided by the present invention;

[0050] Figure 8 is a schematic diagram of an embodiment of a concentration index extraction device provided by the present invention;

[0051] Fig. 9 It is a schematic diagram of the operating environment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0053] The present invention provides a method for extracting concentration, which is a method in cognitive research used to evaluate and quantify human attention and its regulatory mechanism. Concentration extraction can study the concentration level and changes of an individual through electroencephalogram (EEG).

[0054] EEG is a physiological signal that records brain activity. It captures the electrical activity of brain neurons by placing multiple electrodes on the scalp. Figure 1AF7 and AF8 are specific scalp locations defined under the International 10-20 system, located at the left and right frontal lobes on the scalp, respectively. Collecting AF7 and AF8 dual-channel EEG signals in front of the forehead can be used to study the electrical activity of the brain under different cognitive tasks, such as attention, memory, emotion, etc. By analyzing the spectrum, time domain, and spatial characteristics of EEG signals, we can understand the electrical activity patterns of the brain during various cognitive activities.

[0055] EEG signal acquisition usually requires the use of professional EEG equipment, which transmits electrical signals from the scalp to an amplifier through electrodes, and then digitizes the signals for further analysis. When collecting EEG signals, it is usually necessary to keep the subject still to reduce motion artifacts and to ensure the accuracy and consistency of the signal.

[0056] Therefore, the difficulty of collecting the EEG signals of the two channels is low and the structure of the collection device is simple, which is suitable for a wearable, low-power real-time EEG collection system.

[0057] The present invention provides a method for extracting a concentration index. Figure 2 ,include:

[0058] S201, obtaining dual-channel EEG signals of af7 and af8 in front of the forehead;

[0059] S202, calculating the fuzzy entropy of the dual-channel EEG signal using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal;

[0060] S203, performing smoothing processing on the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value;

[0061] S204, performing weighted calculation on the fuzzy entropy value of the target dual-channel EEG signal to obtain a concentration index.

[0062] In this embodiment, firstly, the dual-channel EEG signals of af7 and af8 in front of the forehead are obtained; then, the fuzzy entropy of the dual-channel EEG signals is calculated by a preset sliding window method to obtain the fuzzy entropy value of the dual-channel EEG signals; and the fuzzy entropy value of the dual-channel EEG signals is smoothed to obtain the fuzzy entropy value of the target dual-channel EEG signals; finally, the fuzzy entropy value of the target dual-channel EEG signals is weightedly calculated to obtain the concentration index. The concentration extraction method adopted by the present invention only needs to collect dual-channel data of af7 and af8, simplifies the channel data, and improves the possibility and convenience of collecting EEG signals; at the same time, the method adopted by the present invention does not need to perform frequency division processing on the data, further improves its anti-interference ability, thereby improving the accuracy of obtaining the concentration index.

[0063] It should be noted that in practical applications, the specific steps of extracting the concentration index can be fine-tuned according to the hardware equipment and software tools used. It is understandable that different models of EEG devices can be used when collecting AF7 and AF8 dual-channel data. Different sliding windows and algorithms can also be used when calculating fuzzy entropy. In addition, in order to improve the accuracy of the concentration index, the concentration index can be comprehensively analyzed with other biological signals (such as electrocardiogram, eye movement, etc.).

[0064] It should be noted that by using wearable devices to extract EEG signals with a small number of channels, it has the characteristics of fast response speed and strong anti-interference ability, and by processing the dual-channel EEG signals through a sliding window, a real-time concentration index can be obtained.

[0065] Furthermore, when performing patent degree extraction and detection, in addition to the AF7 and AF8 channels, it is possible to consider using data from more EEG channels, such as channels related to the frontal lobe area, to improve the credibility of the concentration index. In this embodiment, concentration extraction and detection are performed by collecting AF7 and AF8 dual-channel data to be suitable for wearable detection equipment, while reducing the error caused by signal frequency division, improving the signal's anti-interference ability, and the accuracy of concentration detection.

[0066] Furthermore, since the EEG signals on the human scalp are very weak electrical signals, they are often interfered by the environment and physiological noise, which will not only affect the signal quality, but also cause certain errors in the analysis and interpretation of the EEG data. Biological signals such as electrooculography and electromyography, as well as 50Hz power frequency interference, may affect the EEG signals. Therefore, the original EEG signals directly collected from the scalp contain a lot of noise and artifacts. Therefore, before analyzing the EEG data, the collected raw EEG data needs to be preprocessed to reduce the impact of artifacts. In some embodiments, after obtaining the dual-channel EEG signal, the dual-channel EEG signal is also preprocessed. Please refer to Figure 3 , the preprocessing comprises:

[0067] S301, performing bandpass filtering on the dual-channel EEG signal to obtain an initial dual-channel EEG signal;

[0068] S302, performing median filtering on the initial dual-channel EEG signal to obtain a clean dual-channel EEG signal;

[0069] S303, using a preset sliding window method to calculate the fuzzy entropy of the clean dual-channel EEG signal to obtain a fuzzy entropy value of the dual-channel EEG signal.

[0070] In this embodiment, the received EEG data is first passed through a 0.5-48 Hz bandpass filter to remove 50 Hz power frequency noise and retain effective frequency band information, and a median filter is used to remove baseline drift.

[0071] It is understandable that bandpass filtering is a filter that limits the frequency of a signal. It can remove low-frequency and high-frequency noise in the signal and retain effective frequency band information of about 50Hz. In the present embodiment, a bandpass filter of 0.5-48Hz is used. In other embodiments, the purpose of filtering out noise signals outside the frequency band can also be achieved by setting other filter passband and stopband frequency ranges. The median filter is a nonlinear filter that can remove outliers and baseline drift in the signal by calculating the median of the data in the signal window. In the present embodiment, the use of a median filter can remove the baseline drift in the EEG signal, making the signal clearer, more stable and easier to analyze.

[0072] It should be noted that the preprocessing method varies according to the requirements of different experiments. In other embodiments, when preprocessing the EEG signal, the following method may also be used:

[0073] Removing DC drift: DC drift is a low-frequency shift caused by unstable electrode position on the scalp or poor electrode contact. A common method is to use a high-pass filter, usually with a cutoff frequency set to 0.1Hz or higher, to remove DC drift.

[0074] Motion artifact removal: Movement causes artifacts in EEG signals, affecting the analysis and interpretation of the signals. By additionally collecting head position information or using accelerometer sensors, head movement information can be detected and recorded, and motion artifact correction algorithms can be used to remove artifact signals related to head movement from EEG signals.

[0075] Artifact removal: Artifacts may be introduced during EEG signal acquisition, such as poor electrode contact, large isolation between electrodes, etc. Using the reference electrode configuration, artifact signals can be removed by subtracting the average reference, monopolar reference, or other reference electrode methods.

[0076] Independent Component Analysis (ICA): ICA is a data-driven method for decomposing mixed signals into independent components. In EEG signal processing, ICA can be used to separate EEG signals from other interfering components, such as eye movement signals or electromyographic signals. Through ICA, components from different sources can be identified and separated based on the statistical characteristics and mutual independence of the signals.

[0077] Signal-to-noise ratio enhancement: The signal-to-noise ratio of EEG signals can be improved by increasing the amplitude of the signal, reducing the amplitude of the noise, or removing interfering signals. Common methods include signal smoothing, noise estimation and correction, and adaptive filtering.

[0078] In some embodiments, the fuzzy entropy of the clean dual-channel EEG signal is calculated by using a preset sliding window method to obtain the fuzzy entropy value of the dual-channel EEG signal. Figure 4 ,include:

[0079] S401, determining a window length of a preset sliding window according to the time scale of the cleaned dual-channel EEG signal;

[0080] S402, adding the clean dual-channel EEG signals collected in real time into a preset sliding window according to a time series;

[0081] S403, determining whether the length of the dual-channel EEG signal added to the preset sliding window is consistent with the window length;

[0082] S404: If they are consistent, then the fuzzy entropy value of the dual-channel EEG signal with the preset sliding window added is calculated to obtain the fuzzy entropy value of the dual-channel EEG signal in the current time period.

[0083] It should be noted that the sliding window is a time window. In this method, the window moves along the time series with a preset size and sliding step. In each window, the fuzzy entropy of the EEG signal is calculated. Fuzzy entropy is a metric used to quantify the complexity and uncertainty of a signal. It is based on the concept of information entropy and describes the randomness and irregularity of the signal. By calculating the fuzzy entropy of EEG signals, information about the complexity and dynamic changes of the signal can be obtained. Specifically, the more focused people are, the more active and excited their brains are, the greater the complexity of the EEG and the higher the fuzziness.

[0084] Furthermore, by setting a preset sliding window size and sliding step, the EEG signal is divided into window signal segments in real time. When the length of the EEG signal meets a window length, the fuzzy entropy of the EEG signal under the length is solved in real time, so that the concentration index of the previous period can be obtained in real time. It is understandable that the window length of the sliding window can be set as required according to the time scale of the signal, the purpose of analysis and the availability of data.

[0085] Specifically, the window length should match the time scale of the signal. If the signal has a fast time-varying characteristic, the window length should be relatively short to capture the fast changes of the signal. If the signal has a slow time-varying characteristic, the window length can be selected to be relatively long to fully capture the changing trend of the signal.

[0086] Furthermore, the acquisition in the previous period can be calculated by the following formula:

[0087]

[0088] Among them, T is the time period length, L is the window length, and Fs is the sampling frequency.

[0089] In some embodiments, see Figure 5 , the calculation of the fuzzy entropy value of the dual-channel EEG signal with a preset sliding window added thereto to obtain the fuzzy entropy value of the dual-channel EEG signal includes:

[0090] S501, constructing a vector sequence of a set initial length based on the dual-channel EEG signal, and determining the endpoint distance of the vector sequence of the initial length;

[0091] S502: Determine the similarity of the vector sequence according to the endpoint distance, and determine the similarity mean of the vector sequence of the initial length;

[0092] S503: Based on the initial length, change the length of the vector sequence by using a preset step length to determine a vector sequence of a target length, and determine a similarity mean of the vector sequence of the target length;

[0093] S504: Determine the fuzzy entropy value of the dual-channel EEG signal according to the difference relationship between the similarity mean of the vector sequence of the initial length and the similarity mean of the vector sequence of the target length.

[0094] In this embodiment, the similarity of adjacent window data sequences is calculated by using a similarity-based fuzzy entropy algorithm, and the length is gradually increased to evaluate the complexity and irregularity of the signal. The algorithm has the advantages of being simple and easy to use, not requiring prior assumptions such as linear or Gaussian distribution, and having certain robustness to noise and uncertainty, and has been widely used in practical research.

[0095] Specifically, the similarity-based fuzzy entropy algorithm defines the window data sequence of N points as {u(i):1≤i≤N}, and given a vector length m, constructs a new vector sequence The formula is as follows (1):

[0096]

[0097] in That is, vector The average value of .

[0098] Then the distance of the vector sequence is calculated, that is, and The maximum value of the difference between the corresponding endpoints. This value is recorded as The calculation formula is as follows (2):

[0099]

[0100] Calculate the similarity of vectors

[0101] Calculate the average of all similarities except itself, the calculation formula is as follows (3):

[0102]

[0103] Change the vector length m to , repeat the above steps, and get the average value of m+1 similarity of m+1:

[0104]

[0105] Finally, we can get the fuzzy entropy FE = lnφ m (n,r)-lnφ m+1 (n,r);

[0106] Where n is the exponential coefficient, r is the similarity tolerance, and the general value is r = 0.15*sd. sd is the standard deviation of the window data sequence {u(i): 1≤i≤N}.

[0107] In some embodiments, the step of smoothing the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value includes:

[0108] The preset exponential smoothing method is used to smooth the fuzzy entropy values ​​of the dual-channel EEG signals respectively to obtain the fuzzy entropy values ​​of the target dual-channel EEG signals of af7 and af8.

[0109] In this embodiment, by using a preset exponential smoothing method to smooth the fuzzy entropy values ​​of af7 and af8, the influence of noise and mutation on the fuzzy entropy evaluation can be reduced, and a more stable and reliable fuzzy entropy value of the target dual-channel EEG signal can be obtained. The smoothed fuzzy entropy value can be used for further analysis, research and application, such as judging the dynamic changes of EEG signals and extracting EEG signal features.

[0110] Specifically, the preset exponential smoothing method can be expressed by the following formula:

[0111] S t =α*y t +(1-α)S t-1

[0112] Among them, S t is the exponential smoothing value at time t; y t is the fuzzy entropy value of the target dual-channel EEG signal at the tth moment; S t-1 is the exponential smoothing value at the t-1th moment; α is the smoothing constant, and its value range is [0, 1].

[0113] Furthermore, data smoothing can be performed by sliding average, and the calculation method is as follows:

[0114]

[0115] where y t-i is the observation value at time ti, and n represents the window length.

[0116] In some embodiments, the fuzzy entropy value of the target dual-channel EEG signal is weightedly calculated to obtain a concentration index, which can be expressed by the following formula:

[0117] F t =0.5*S 1 t +0.5*S 2 t

[0118] where F t is the concentration index at time t, S 1 t is the fuzzy entropy value of the target EEG signal of channel af7 at time t, S 2 is the fuzzy entropy value of the target EEG signal of channel af8 at time t.

[0119] In this embodiment, by weighted calculation of the fuzzy entropy value of the smoothed target dual-channel EEG signal, the importance of each signal feature can be comprehensively considered to obtain a more accurate and effective concentration index, thereby further improving the accuracy of concentration extraction.

[0120] In a specific embodiment, see Figure 6 , the relaxation task and the attention task were performed alternately, and the preliminary calculation results showed large fluctuations in the data, and the effect was poor. The final effect of the concentration index obtained by combining data smoothing and weighted calculation is as follows Figure 7 As shown, the results have obvious differentiation and good effect. The high attention focus index is about 0.004, and the low attention focus index is about 0.001.

[0121] Based on the above-mentioned concentration index extraction method, the embodiment of the present invention also provides a concentration index extraction device 800. Figure 8 The concentration index extraction device 800 includes an acquisition module 810, a fuzzy entropy value determination module 820, a smoothing processing module 830 and a concentration index determination module 840.

[0122] An acquisition module 810 is used to acquire dual-channel EEG signals of af7 and af8 in front of the forehead;

[0123] A fuzzy entropy value determination module 820 is used to calculate the fuzzy entropy of the dual-channel EEG signal by using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal;

[0124] A smoothing processing module 830 is used to perform smoothing processing on the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value;

[0125] The concentration index determination module 840 is used to perform weighted calculation on the fuzzy entropy value of the target dual-channel EEG signal to obtain a concentration index.

[0126] like Fig. 9 As shown, based on the above concentration index extraction method, the present invention also provides an electronic device, which can be a computing electronic device such as a mobile terminal, a desktop computer, a notebook, a palm computer, and a server. The electronic device includes a processor 910, a memory 920, and a display 930. Fig. 9 Only some components of the electronic device are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0127] In some embodiments, the memory 920 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. In other embodiments, the memory 920 may also be an external storage electronic device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the memory 920 may also include both an internal storage unit of the electronic device and an external storage electronic device. The memory 920 is used to store application software and various types of data installed in the electronic device, such as program codes for installing the electronic device. The memory 920 can also be used to temporarily store data that has been output or is to be output. In one embodiment, a concentration index extraction program 940 is stored on the memory 920, and the concentration index extraction program 940 can be executed by the processor 910, thereby realizing the concentration index extraction method of each embodiment of the present application.

[0128] In some embodiments, the processor 910 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes stored in the memory 920 or process data, such as executing a concentration index extraction method.

[0129] In some embodiments, the display 930 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 930 is used to display information of the electronic device for extracting the concentration index and to display a visual user interface. The components 910-930 of the electronic device communicate with each other via a system bus.

[0130] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium, and the program can include the processes of the above-mentioned method embodiments when executed. The storage medium can be a memory, a disk, an optical disk, etc.

[0131] The specific implementation of the present invention described above does not constitute a limitation on the protection scope of the present invention. Any other corresponding changes and modifications made based on the technical concept of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A concentration index extraction method, characterized in that: include: Obtain dual-channel EEG signals of af7 and af8 in front of the forehead; Calculating the fuzzy entropy of the dual-channel EEG signal using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal; Smoothing the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value; The fuzzy entropy value of the target dual-channel EEG signal is weightedly calculated to obtain a concentration index.

2. The concentration index extraction method according to claim 1, characterized in that: After acquiring the dual-channel EEG signal, the method further includes preprocessing the dual-channel EEG signal, wherein the preprocessing includes: Performing bandpass filtering on the dual-channel EEG signal to obtain an initial dual-channel EEG signal; Performing median filtering on the initial dual-channel EEG signal to obtain a clean dual-channel EEG signal; The fuzzy entropy of the clean dual-channel EEG signal is calculated using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal.

3. The concentration index extraction method according to claim 2, characterized in that: The method of calculating the fuzzy entropy of the clean dual-channel EEG signal by using a preset sliding window method to obtain the fuzzy entropy value of the dual-channel EEG signal includes: Determining the window length of the preset sliding window according to the time scale of the clean dual-channel EEG signal; Adding the clean dual-channel EEG signals collected in real time into a preset sliding window in time series; Determine whether the length of the dual-channel EEG signal added to the preset sliding window is consistent with the window length; If they are consistent, the fuzzy entropy value of the dual-channel EEG signal with the preset sliding window added is calculated to obtain the fuzzy entropy value of the dual-channel EEG signal in the current time period.

4. The concentration index extraction method according to claim 3, characterized in that: The step of calculating the fuzzy entropy value of the dual-channel EEG signal with the preset sliding window added thereto to obtain the fuzzy entropy value of the dual-channel EEG signal includes: Constructing a vector sequence of a set initial length based on the dual-channel EEG signal, and determining the endpoint distance of the vector sequence of the initial length; Determining the similarity of the vector sequence according to the endpoint distance, and determining the similarity mean of the vector sequence of the initial length; Based on the initial length, a preset step length is used to change the length of the vector sequence, a vector sequence of a target length is determined, and a similarity mean of the vector sequence of the target length is determined; The fuzzy entropy value of the dual-channel electroencephalogram signal is determined according to the difference relationship between the similarity mean of the vector sequence of the initial length and the similarity mean of the vector sequence of the target length.

5. The concentration index extraction method according to claim 1, characterized in that: The step of smoothing the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value includes: The preset exponential smoothing method is used to smooth the fuzzy entropy values ​​of the dual-channel EEG signals respectively to obtain the fuzzy entropy values ​​of the target dual-channel EEG signals of af7 and af8.

6. The concentration index extraction method according to claim 5, characterized in that: The preset exponential smoothing method can be expressed by the following formula: S t =α*y t +(1-α)S t-1 Among them, S t is the exponential smoothing value at time t; y t is the fuzzy entropy value of the target dual-channel EEG signal at the tth moment; S t-1 is the exponential smoothing value at the t-1th moment; α is the smoothing constant.

7. The concentration index extraction method according to claim 1, characterized in that: The fuzzy entropy value of the target dual-channel EEG signal is weightedly calculated to obtain the concentration index, which can be expressed by the following formula: F t =0.5*S 1 t +0.5*S 2 t where F t is the concentration index at time t, S 1 t is the fuzzy entropy value of the target EEG signal of the af7 channel at time t, and S2 is the fuzzy entropy value of the target EEG signal of the af8 channel at time t.

8. A concentration index extraction device, characterized in that: include: An acquisition module is used to acquire dual-channel EEG signals of af7 and af8 in front of the forehead; A fuzzy entropy value determination module is used to calculate the fuzzy entropy of the dual-channel EEG signal by using a preset sliding window method to obtain a fuzzy entropy value of the dual-channel EEG signal; A smoothing processing module is used to perform smoothing on the dual-channel EEG signal fuzzy entropy value to obtain a target dual-channel EEG signal fuzzy entropy value; The concentration index determination module is used to perform weighted calculation on the fuzzy entropy value of the target dual-channel EEG signal to obtain a concentration index.

9. An electronic device, characterized in that: include: Processor and memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the concentration index extraction method according to claims 1-7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the concentration index extraction method according to claims 1-7.

Images