Vehicle cruise control method and system, electronic equipment and storage medium
Through EEG data processing and classification algorithms, vehicle cruise control is realized, which solves the problems of complex operation and safety hazards in the existing technology, and improves driving comfort and safety.
Patent Information
- Application Number
- CN202411165669.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-12
AI Technical Summary
When a vehicle is cruising at high speed, the existing technology relies on physical buttons or touch screen control, and the operation is complicated, resulting in greater safety risks under high-speed road conditions.
By obtaining preset EEG data, preprocessing and classification, the preset correlation analysis algorithm is used to determine the EEG classification results, and then the vehicle is cruised according to the results to achieve cruise control.
It improves the accuracy and convenience of vehicle cruise control and improves driving comfort and safety.
Smart Images

Figure CN118928393A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a vehicle cruise control method, system, electronic device and storage medium. Background Art
[0002] In the related art, when a vehicle is under cruise control, such as high-speed cruise control, it mainly relies on physical buttons or touch screen control methods, which are relatively complicated to operate. In order to achieve the appropriate speed, it often requires multiple button operations, which can easily lead to safety hazards under high-speed road conditions.
[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the invention
[0004] The main purpose of the embodiments of the present application is to propose a vehicle cruise control method, system, electronic device and storage medium, which can effectively improve the accuracy and convenience of vehicle cruise control and improve driving comfort and safety.
[0005] To achieve the above object, one aspect of an embodiment of the present application provides a vehicle cruise control method, the method comprising the following steps:
[0006] Get preset EEG data;
[0007] Performing data preprocessing on the preset EEG data to obtain EEG signals to be classified;
[0008] Classifying the to-be-classified EEG signal by a preset correlation analysis algorithm to determine an EEG classification result; wherein the EEG classification result corresponds to a vehicle cruise instruction;
[0009] The preset vehicle is cruise controlled according to the vehicle cruise instruction.
[0010] In some embodiments, the obtaining of preset EEG data includes:
[0011] Constructing a preset display interface; wherein the preset display interface includes a plurality of preset stimulation targets, and the flashing frequency of the plurality of preset stimulation targets corresponds to the vehicle cruise instruction;
[0012] The preset EEG data is dynamically acquired through a preset brain-computer interface; wherein the preset EEG data includes steady-state visual evoked potential data, and the steady-state visual evoked potential data is generated by visual stimulation of the preset stimulation target.
[0013] In some embodiments, the preprocessing of the preset EEG data to obtain the EEG signal to be classified includes:
[0014] Performing electrode channel screening on the preset EEG data to obtain first EEG data;
[0015] Performing electrode re-referencing on the first EEG data to obtain second EEG data;
[0016] Performing a preset filtering process on the second EEG data to obtain third EEG data;
[0017] Performing data segmentation processing on the third EEG data to obtain fourth EEG data;
[0018] Baseline correction is performed on the fourth EEG data to obtain the EEG signal to be classified.
[0019] In some embodiments, the classifying the to-be-classified EEG signals by a preset correlation analysis algorithm to determine the EEG classification result includes:
[0020] The EEG signal to be classified is classified by a task-related component analysis algorithm to obtain the EEG classification result.
[0021] In some embodiments, the classifying the to-be-classified EEG signal by a task-related component analysis algorithm to obtain the EEG classification result includes:
[0022] Constructing a plurality of preset template signals through the task-related component analysis algorithm according to the preset training data; wherein the preset template signals correspond to the EEG classification results;
[0023] Calculating the Pearson correlation coefficient between the EEG signal to be classified and each of the preset template signals, so as to select the preset template signal having the greatest correlation with the EEG signal to be classified as the target template signal according to the Pearson correlation coefficient;
[0024] The EEG classification result is determined according to the target template signal.
[0025] In some embodiments, performing cruise control on a preset vehicle according to the vehicle cruise instruction includes:
[0026] Get vehicle speed data;
[0027] When it is determined that the vehicle speed data is greater than a first cruise threshold and less than a second cruise threshold, the preset vehicle is controlled to enter a constant speed cruise mode according to the vehicle cruise instruction; wherein the second cruise threshold is greater than the first cruise threshold.
[0028] In some embodiments, after performing cruise control on a preset vehicle according to the vehicle cruise instruction, the method further includes:
[0029] When it is determined that a preset cruise exit condition is monitored, the preset vehicle is controlled to exit the cruise control mode; wherein the preset cruise exit condition includes the vehicle cruise command being a cruise off command, the vehicle speed data being less than the first cruise threshold, a vehicle fault or power limiting processing being detected, a brake signal being detected, and one of a preset cancel button signal being obtained.
[0030] To achieve the above object, another aspect of the embodiment of the present application provides a vehicle cruise control system, the system comprising:
[0031] The first module is used to obtain preset EEG data;
[0032] The second module is used to perform data preprocessing on the preset EEG data to obtain EEG signals to be classified;
[0033] The third module is used to classify the to-be-classified EEG signal by a preset correlation analysis algorithm to determine an EEG classification result; wherein the EEG classification result corresponds to a vehicle cruise instruction;
[0034] The fourth module is used to perform cruise control on a preset vehicle according to the vehicle cruise instruction.
[0035] To achieve the above objective, another aspect of an embodiment of the present application provides an electronic device, the electronic device comprising:
[0036] at least one processor;
[0037] at least one memory for storing at least one program;
[0038] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.
[0039] To achieve the above objective, another aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.
[0040] The embodiments of the present application include at least the following beneficial effects: The present application provides a vehicle cruise control method, system, electronic device and storage medium, which obtains the preset EEG data and performs data preprocessing on the preset EEG data to obtain the EEG signal to be classified. Then, the embodiment of the present invention classifies the EEG signal to be classified by a preset correlation analysis algorithm to determine the EEG classification result, and the EEG classification result corresponds to the vehicle cruise command, and then the vehicle is cruise controlled according to the determined vehicle cruise command, which effectively improves the accuracy and convenience of the vehicle's cruise control, and improves the driving comfort and safety. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] Figure 1 is a flow chart of a vehicle cruise control method provided by an embodiment of the present invention;
[0042] Figure 2 is a schematic diagram of theoretical brightness change of sinusoidal modulation stimulation provided by an embodiment of the present invention;
[0043] Figure 3 is a schematic diagram of actual brightness change of sinusoidal modulation stimulation provided by an embodiment of the present invention;
[0044] Figure 4 is a schematic diagram of SSVEP response intensity curves under different stimulation frequencies provided by an embodiment of the present invention;
[0045] Figure 5 is a schematic diagram of SSVEP stimulation harmonics provided by an embodiment of the present invention;
[0046] Figure 6 Schematic diagram of the initial interface of the SSVEP stimulation paradigm provided by an embodiment of the present invention;
[0047] Figure 7 It is a functional instruction diagram of the SSVEP stimulation paradigm provided by an embodiment of the present invention;
[0048] Figure 8 It is a frequency diagram corresponding to the SSVEP stimulation paradigm provided by an embodiment of the present invention;
[0049] Fig. 9 It is a schematic diagram of a motor selected by SSVEP classification and a heavy reference motor provided by an embodiment of the present invention;
[0050] Fig.10 is a schematic diagram of the second EEG data before filtering provided by an embodiment of the present invention;
[0051] Fig.11 is a schematic diagram of the second EEG data after filtering provided by an embodiment of the present invention;
[0052] Fig.12 It is a schematic diagram of the arrangement format of EEG data after segmentation provided by an embodiment of the present invention;
[0053] Fig.13 is a classification flow chart of the CCA algorithm provided by an embodiment of the present invention;
[0054] Fig.14 is a schematic diagram of the vehicle cruise control effect provided by an embodiment of the present invention;
[0055] Fig.15 is a schematic structural diagram of a vehicle cruise control system provided by an embodiment of the present invention;
[0056] Fig.16 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present application. They are only examples of devices and methods consistent with some aspects of the embodiments of the present application as detailed in the attached claims.
[0058] It is understood that the terms "first", "second", etc. used in this application can be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another concept. For example, without departing from the scope of the embodiment of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein can be interpreted as "at the time of" or "when" or "in response to determination".
[0059] The terms "at least one", "multiple", "each", "any", etc. used in this application, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.
[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.
[0061] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.
[0062] Steady-State Visual Evoked Potential (SSVEP): It is an EEG signal that is usually triggered by presenting visual stimuli of a specific frequency (such as flashing light sources or patterns) to the subject. Correspondingly, the subject's EEG activity will produce corresponding fluctuations at the frequency of the stimulus, and this potential change at a specific frequency is called a steady-state visual evoked potential.
[0063] Canonical Correlation Analysis (CCA): It is an algorithm that reduces the dimension of two sets of high-dimensional data to one dimension, and then uses the correlation coefficient to analyze the correlation between the data. The purpose of CCA dimensionality reduction is to maximize the correlation coefficient between the two sets of data after the data dimensionality reduction, so it is often used to analyze the correlation between the two sets of data. Among them, CCA can perform multi-channel analysis at the same time, can contain more channel information, and is more effective in extracting the features of visual evoked potentials.
[0064] Task-related Component Analysis (TRCA): is a method used to extract and analyze components related to specific cognitive or sensory tasks from brain signal data such as electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI). Among them, task-related component analysis algorithms are generally designed to identify and enhance signal components related to a specific task, while suppressing noise or other interfering signals that are not related to the task.
[0065] In the related art, when a vehicle is under cruise control, such as high-speed cruise control, it mainly relies on physical buttons or touch screen control methods, which are relatively complicated to operate. In order to achieve the appropriate speed, it often requires multiple button operations, which can easily lead to safety hazards under high-speed road conditions.
[0066] In view of this, a vehicle cruise control method, system, electronic device and storage medium are provided in the embodiments of the present application. The scheme obtains preset EEG data and performs data preprocessing on the preset EEG data to obtain EEG signals to be classified. Then, the embodiments of the present invention classify the EEG signals to be classified by a preset correlation analysis algorithm to determine the EEG classification results. The EEG classification results correspond to the vehicle cruise instructions, and then the vehicle is cruise controlled according to the determined vehicle cruise instructions, which effectively improves the accuracy and convenience of the vehicle's cruise control, and improves the driving comfort and safety.
[0067] The vehicle cruise control method provided in the embodiment of the present application relates to the field of vehicle technology. The vehicle cruise control method provided in the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a vehicle-mounted terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or it can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms and other basic cloud computing services. The server can also be a node server in a blockchain network; the software can be an application that implements the vehicle cruise control method, etc., but is not limited to the above forms.
[0068] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.
[0069] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.
[0070] Figure 1 is an optional flow chart of the vehicle cruise control method provided in the embodiment of the present application, Figure 1The method may include but is not limited to steps S110 to S140.
[0071] Step S110: Obtaining preset EEG data.
[0072] Step S120: preprocessing the preset EEG data to obtain EEG signals to be classified.
[0073] Step S130: Classify the EEG signal to be classified by a preset correlation analysis algorithm to determine the EEG classification result, wherein the EEG classification result corresponds to the vehicle cruise instruction.
[0074] Step S140: performing cruise control on a preset vehicle according to the vehicle cruise instruction.
[0075] During the working process of this specific embodiment, the embodiment of the present invention first obtains preset EEG data to perform data preprocessing on the preset EEG data to obtain the EEG signal to be classified. Specifically, the preset EEG data in the embodiment of the present invention refers to the EEG signal generated by the relevant control personnel, such as the vehicle driver, which contains the control intention information of the relevant control personnel. Accordingly, since the EEG signal is easily interfered by the outside world, and the EEG cap will collect the myoelectric signal generated by body movement, the electrooculogram signal generated by blinking, etc. during the collection process, the embodiment of the present invention preprocesses the preset EEG data after obtaining the preset EEG data to reduce the noise in the preset EEG data, and obtain the EEG signal to be classified, which is convenient for subsequent classification processing. Further, the embodiment of the present invention classifies the EEG signal to be classified by a preset correlation analysis algorithm to determine the EEG classification result. Specifically, the EEG classification result in the embodiment of the present invention corresponds to the vehicle cruise instruction, that is, different EEG classification results correspond to different vehicle cruise instructions, such as the EEG signal frequency obtained by classification corresponds to the vehicle cruise speed. Accordingly, in the embodiment of the present invention, classifying the EEG signals to be classified refers to classifying the stimulation frequencies corresponding to the EEG signals to be classified, wherein each stimulation frequency corresponds to a corresponding vehicle cruise instruction, so that the corresponding vehicle cruise instruction is obtained by matching the EEG classification result. The embodiment of the present invention obtains the EEG signals of the vehicle operator to classify the EEG signals, thereby determining the corresponding vehicle cruise instruction, and can quickly and accurately recognize the driver's intention. Among them, the preset correlation analysis algorithm in the embodiment of the present invention includes a typical correlation analysis algorithm or a task-related component analysis algorithm. Finally, the embodiment of the present invention performs cruise control on the preset vehicle according to the determined vehicle cruise instruction. Specifically, after determining the classification result of the EEG signal to be classified, the embodiment of the present invention controls the vehicle to enter the cruise control mode according to the corresponding vehicle cruise instruction, thereby effectively improving the driving comfort and safety.
[0076] In some embodiments of the present invention, obtaining preset EEG data includes but is not limited to the following steps:
[0077] Constructing a preset display interface, wherein the preset display interface includes a plurality of preset stimulation targets, and the flashing frequencies of the plurality of preset stimulation targets correspond to the vehicle cruise command.
[0078] The preset EEG data is dynamically acquired through a preset brain-computer interface, wherein the preset EEG data includes steady-state visual evoked potential data, and the steady-state visual evoked potential data is generated by visual stimulation of a preset stimulation target.
[0079] In this specific embodiment, the embodiment of the present invention first constructs a preset display interface, and then dynamically obtains preset EEG data through a preset brain-computer interface. Specifically, the preset display interface in the embodiment of the present invention refers to a display interface for visually stimulating the vehicle driver. Among them, the preset display interface includes a number of preset stimulation targets, that is, a number of preset stimulation targets are set on the preset display interface, such as a stimulation target block. Correspondingly, the preset EEG data in the embodiment of the present invention includes steady-state visual evoked potential data (SSVEP), and the vehicle driver is visually stimulated by the preset stimulation targets set on the preset display interface, thereby generating corresponding steady-state visual evoked potential data (SSVEP). Exemplarily, the embodiment of the present invention uses an LCD display as a display for stimulus presentation in combination with hardware conditions. Among them, the LCD display has a fixed refresh rate, and the screen brightness of each frame is fixed. The display refresh rate used in the embodiment of the present invention is 60Hz, and 60 frames are refreshed within 1s, which limits the stimulation frequency. Correspondingly, if a fixed black and white dual-color stimulation is used, the stimulation frequency can only be a divisor of 60Hz. Therefore, the embodiment of the present invention adopts a sinusoidal encoding method to simulate a sinusoidal function waveform to show the change of flicker brightness. At the same time, the embodiment of the present invention combines the stimulation frequency and the sine wave modulation brightness curve to present stimulation of any frequency of 0 to 30 Hz on a 60 Hz display. The sine wave stimulation modulation function in the embodiment of the present invention is shown in the following formula (1):
[0080]
[0081] Where f represents the target flickering frequency, and t represents the time after the stimulus starts (s).
[0082] Accordingly, taking 11 Hz as an example, the theoretical stimulus brightness variation of the sine wave modulation in the embodiment of the present invention is as follows: Figure 2 As shown in the figure, brightness 0 represents black and 1 represents white. Figure 2It can be seen that the screen brightness changes 11 complete cycles within 60 frames (1s), and 11Hz is a frequency that cannot be achieved by traditional fixed black and white flickering. In addition, when the stimulus is actually presented, the brightness of each frame of the display will not change, so the actual brightness change of 11Hz stimulus presentation is as follows Figure 3 As shown in FIG. 1 , sinusoidal modulation stimulation can achieve more stimulation frequencies, the embodiment of the present invention uses a sampled sinusoidal encoding method to generate stimulation.
[0083] In addition, performance is highly correlated with the number of instruction sets, and the number of commonly used instruction sets is between 2 and 9. Accordingly, some high-performance steady-state visual evoked potential technologies use a larger number of instruction sets, but this also brings about limitations on the frequency interval, and the complexity of the classification algorithm and the classification time also increase accordingly. In order to increase the applicability and the length and width ratio of the display interface, the embodiment of the present invention adopts 8 frequencies. Among them, according to the high and low stimulation frequencies, the stimulation frequencies are generally divided into three types: one is a low-frequency band of 4 to 15 Hz, centered on 10 Hz; the second is a medium-frequency band of 15 to 30 Hz, centered on 20 Hz; the third is a high-frequency band of 30 to 60 Hz, centered on 40 Hz. Among them, the EEG response intensity curves stimulated by stimulations of different frequencies are as follows: Figure 4 See Figure 4 , with the highest EEG response intensity in the low frequency band centered at 10 Hz. Since stimulation generates its own frequency stimulation, it also generates weaker harmonic stimulation. For example, 10 Hz stimulation will also generate 20 and 30 Hz harmonic stimulation. Figure 5 As shown. Therefore, there are certain limitations in the selection of stimulation frequency, and stimulation frequencies that are multiples of each other should be avoided. Accordingly, the embodiment of the present invention selects a stimulation frequency band range of 7 to 15 Hz. The adopted paradigm design and timing diagram are shown in Figure 6 , Figure 7 as well as Figure 8 As shown. In the embodiment of the present invention, the interface includes 8 stimulus targets, which are arranged on the screen in a layout of 2 rows and 4 columns, and each white square is assigned a fixed flickering frequency, which is 15Hz, 13Hz, 12Hz, 11Hz, 10Hz, 9Hz, 8hz, and 7hz. The embodiment of the present invention uses eye movement data to identify the submatrix where the target being stared at by the subject is located, and simultaneously combines EEG data to identify the target frequency to lock the target.
[0084] In some embodiments of the present invention, data preprocessing is performed on the preset EEG data to obtain the EEG signal to be classified, including but not limited to the following steps:
[0085] Electrode channel screening is performed on the preset EEG data to obtain first EEG data.
[0086] Electrode re-reference is performed on the first EEG data to obtain second EEG data.
[0087] The second EEG data is subjected to a preset filtering process to obtain third EEG data.
[0088] The third EEG data is processed by segmentation to obtain fourth EEG data.
[0089] The fourth EEG data is baseline corrected to obtain an EEG signal to be classified.
[0090] In this specific embodiment, the embodiment of the present invention first performs electrode channel screening on the preset EEG data to obtain the first EEG data. Specifically, in order to reduce the noise in the EEG data, before the formal classification, the embodiment of the present invention preprocesses the EEG signal, such as preprocessing the EEG signal through the EEGLAB toolbox in the MATLAB software. Accordingly, in the embodiment of the present invention, data is collected by a 64-lead EEG cap, and when classifying, it is not necessary to analyze all the data of the 64 channels, only some of the channels related to the selection are required. Among them, the human brain area includes four areas: the frontal lobe, the parietal lobe, the occipital lobe, and the temporal lobe. The occipital lobe area is responsible for visual signal perception and processing, and it is located in the back of the head. Therefore, the embodiment of the present invention selects some electrodes in the occipital lobe area as electrodes for EEG signal classification: O1, O2, Oz, Pz, POz, PO3, PO4, PO7, PO8. Accordingly, the embodiment of the present invention performs electrode re-reference on the first EEG data to obtain the second EEG data. Specifically, the EEG data collected by the EEG device in the embodiment of the present invention is the difference between the sampling electrode and the selected reference electrode. The embodiment of the present invention selects the bilateral mastoids as the EEG reference electrodes. In the data processing, the embodiment of the present invention re-references the data of each lead, and the re-reference electrodes use TP9 and TP10 electrodes. Fig. 9 , Fig. 9 The green electrode in the middle is the electrode channel position selected for classification, and the yellow electrode is the heavy reference electrode position.
[0091] Furthermore, the embodiment of the present invention performs preset filtering on the second EEG data to obtain third EEG data. Specifically, since external noise interference is difficult to avoid when performing vehicle cruise control, and the EEG acquisition equipment will collect clutter such as electromyography, electrocardiography, and electrooculography, the EEG signal should be filtered before classification. Accordingly, most of the relevant research frequencies are lower than 30 Hz, and the embodiment of the present invention mainly selects low-frequency band frequencies. The embodiment of the present invention uses a bandpass filter of 5 to 30 Hz to eliminate noise. For example, when performing filtering, the embodiment of the present invention first performs a 5 Hz high-pass filter and then a 30 Hz low-pass filter. Among them, the EEG signal quality before and after filtering in the embodiment of the present invention is as follows: Fig.10 and Fig.11As shown, it can be seen that the signal quality is significantly improved after filtering, and there is no obvious clutter. Next, the embodiment of the present invention performs data segmentation processing on the third EEG data to obtain the fourth EEG data. Specifically, the EEG device records all EEG data of the entire control process, including the target stimulation time and the rest time. Therefore, before classification, it is necessary to extract the EEG signal corresponding to the flashing of the stimulus. For example, before collecting data, the embodiment of the present invention writes a program to control the parallel port line to mark the data at the beginning of each trial. Different target stimulation types correspond to different mark types, which are "s1", "s2", ..., "s8" in the embodiment of the present invention, for a total of 8 stimulation types. Among them, when pre-processing data, the embodiment of the present invention extracts the corresponding EEG segment according to the mark position, takes the mark as the starting point, and intercepts the EEG signal of 8s afterwards, so as to complete the extraction of EEG data corresponding to a trial and complete the data segmentation. Among them, after the data is segmented, the EEG signal of the embodiment of the present invention will become more orderly and neat, and its format is channels*times*trials, which lays the foundation for subsequent classification. Among them, the arrangement format of the data after segmentation in the embodiment of the present invention is as follows Fig.12 As shown. Next, the embodiment of the present invention performs baseline correction on the fourth EEG data to obtain the EEG signal to be classified. Specifically, the EEG signal will spontaneously generate noise, causing the EEG signal to be offset. In order to reduce the impact of signal offset, the embodiment of the present invention uses part of the EEG data when the stimulus begins to appear as the baseline and calculates the voltage mean. The EEG data collected when the target stimulus flashes is subtracted from the average value of the baseline data to perform baseline correction and obtain the EEG signal to be classified. Among them, the baseline data length is set to 200ms in the embodiment of the present invention.
[0092] In some embodiments of the present invention, the EEG signals to be classified are classified by a preset correlation analysis algorithm to determine the EEG classification result, including but not limited to the following steps:
[0093] The EEG signals to be classified are classified through the task-related component analysis algorithm to obtain the EEG classification results.
[0094] In this specific embodiment, the embodiment of the present invention classifies the EEG signals to be classified through the task-related component analysis algorithm to obtain the EEG classification results. Specifically, accurate EEG classification is the basis for improving the performance of the brain-computer interface. The embodiment of the present invention conducts a comparative analysis of the canonical correlation analysis algorithm and the task-related component analysis algorithm to determine the classification of the EEG signals to be classified through the task-related component analysis algorithm. For example, in the embodiment of the present invention, the performance of the brain-computer interface is evaluated through corresponding performance evaluation indicators, such as classification accuracy and information transmission rate. Among them, the classification accuracy is the most important performance indicator of the brain-computer interface, and a higher classification accuracy is the basis for the effective operation of the brain-computer interface (Brain-Computer Interface, BCI) system. At the same time, the information transmission rate is a common performance evaluation indicator in the field of brain-computer interface to evaluate the efficiency of the brain-computer interface in transmitting information to the outside world. Its value is determined by the instruction set size N, the target recognition accuracy A c , and the single instruction selection time T are jointly determined, and the calculation formula is shown in the following formula (2):
[0095]
[0096] The instruction set size is the number of optional targets included in the system, which is set as a constant N during calculation; the target recognition accuracy A c The classification accuracy of each subject is taken. Generally, as the number of selectable targets increases, the classification accuracy will decrease accordingly. The single instruction selection time T is the time required for the brain-computer interface system to output a single instruction. When designing the system, T is fixed to the total duration of a single trial (set to 8s in the embodiment of the present invention), but in the dynamic optimization design of the target selection time, T usually changes with the duration of the selected data, which gives rise to the concept of "theoretical information transmission rate". The theoretical ITR refers to the ITR corresponding to the actual classification time window length when T is the actual classification time window length, which has reference value for the selection of the time window length in the actual application of the brain-computer interface.
[0097] Exemplarily, when the classification time window is 2s, the average classification accuracy of the task-related component analysis (TRCA) algorithm used in the embodiment of the present invention is (92.01% ± 9.19%). When the time window length is less than 2s, the classification accuracy of the TRCA algorithm is higher than that of the canonical correlation analysis (CCA) algorithm, and the standard deviation of the accuracy is smaller. When the time window length is greater than 2s, the difference in classification accuracy between the two algorithms gradually decreases. This result shows that in most cases, the classification accuracy of the TRCA algorithm is higher than that of the CCA algorithm, and the sensitivity of the CCA algorithm to the length of the classification time window is higher than that of the TRCA algorithm. When the time window is short, the performance of the TRCA algorithm is significantly higher than that of the CCA algorithm. At the same time, the embodiment of the present invention uses the average classification accuracy to calculate the average theoretical ITR. The results show that the theoretical ITR of the TRCA algorithm classification is higher than that of the CCA algorithm under all time window lengths. In addition, when the embodiment of the present invention uses the TRCA algorithm to classify EEG data, the time window length corresponding to the highest theoretical ITR is 1s. Based on the above classification results, the embodiment of the present invention uses the TRCA algorithm to classify steady-state visual evoked potentials.
[0098] It should be noted that the SSVEP accuracy of each subject in the embodiment of the present invention using the TRCA algorithm for classification under different classification time window lengths is shown in Table 1 below:
[0099] Table 1
[0100]
[0101]
[0102] Among them, most subjects showed good performance when the sampling length was 4s. The classification accuracy of 13 experiments reached 100%, and the lowest classification accuracy was 81.25%. When the time window length was 0.5s, only 7 classification accuracy exceeded 50%, and the lowest classification accuracy was only 16.67%. At this time, unimodal classification has no practical value. The above results show that the classification is greatly affected by the length of the time window, and the classification accuracy is significantly positively correlated with the length of the time window. When the time window length is short, the unimodal classification performance is poor. In addition, the classification accuracy varies greatly among subjects, and the classification accuracy of some subjects is low, which may be related to the subjects' sensitivity to flicker, their concentration, and their experience in using brain-computer interfaces.
[0103] In addition, the theoretical ITR of each subject based on 8-category steady-state visual evoked potential under different time window lengths is shown in Table 2 below. When calculating the theoretical ITR of a single modality, the number of instruction sets is recorded as 8, the target recognition accuracy takes the corresponding value in Table 1 above, and the single instruction selection time takes the corresponding classification time window length. As can be seen from Table 2, when the time window length is greater than 1s, the ITR of most subjects increases as the time window shortens, which is due to the high classification accuracy of this experiment when the time window is long, but most of the data begins to decrease when the time window is 2s or 1s, such as data No. 2-1 and No. 5-2, when the time window length is 2s, the ITR begins to decrease; this is because the influencing factors of ITR include classification accuracy. If the accuracy drops significantly, the ITR will also decrease. Therefore, the time window length is not the only influencing factor of the theoretical ITR, and the optimal time window length should be determined by the change of the average ITR over time. The average ITR of the EEG data in the embodiment of the present invention is the largest at a 1s time window, which is 82.33bpm.
[0104] Table 2
[0105]
[0106]
[0107] From Table 2 above, we can see that the highest value of theoretical ITR appears between 0.5 and 2.5 seconds. When the theoretical ITR is the highest, the average classification accuracy of each subject is 82.29%. Observing the slope change law in each sub-graph, the theoretical ITR will only increase accordingly when the classification accuracy increases significantly with the increase of the time window; when the classification accuracy curve tends to be stable, the ITR curve begins to decline.
[0108] In addition, the embodiment of the present invention statistically analyzes the EEG classification results of each subject, and draws a confusion matrix diagram based on the EEG classification results in the 2s time window. It can be seen that when the frequency is close to 10Hz, the classification accuracy is high, among which 11 and 12Hz have the highest classification accuracy, both of which are 95%; as the frequency increases, the EEG classification accuracy decreases, and the classification accuracy of 16Hz ranks the lowest among all frequencies in the embodiment of the present invention, which is 82%; and among the misclassification results of 10-14Hz frequency stimulation, the probability of misclassification as 16Hz is the highest, which may be due to the influence of harmonics, and 16Hz is misclassified as other low-frequency harmonics. At the same time, the classification performance of each frequency in the embodiment of the present invention is in the low frequency band of 4-15Hz, and the frequency classification accuracy near 10Hz is the highest. Therefore, by optimizing some stimulation frequencies more carefully, EEG classification can achieve better classification effects, and the embodiment of the present invention selects 7-15hz as the selected frequency, which is theoretically feasible.
[0109] In some embodiments of the present invention, the EEG signals to be classified are classified by a task-related component analysis algorithm to obtain EEG classification results, including but not limited to the following steps:
[0110] According to the preset training data, a number of preset template signals are constructed by the task-related component analysis algorithm, wherein the preset template signals correspond to the EEG classification results.
[0111] The Pearson correlation coefficient between the EEG signal to be classified and each preset template signal is calculated, so that the preset template signal with the greatest correlation with the EEG signal to be classified is used as the target template signal according to the Pearson correlation coefficient.
[0112] The EEG classification result is determined based on the target template signal.
[0113] In this specific embodiment, the embodiment of the present invention first constructs a number of preset template signals based on preset training data through a task-related component analysis algorithm to calculate the Pearson correlation coefficient between the EEG signal to be classified and each preset target signal, and then uses the preset template signal with the greatest correlation with the EEG signal to be classified as the target template signal according to the Pearson correlation coefficient, thereby determining the corresponding EEG classification result. Specifically, the task-related component analysis algorithm in the embodiment of the present invention is a trained algorithm that can effectively utilize the relevant information of the stimulus, maximize the reproducibility of the neural impact data in the task, and then obtain task-related components, maximize the reproducibility between multiple trial data in the EEG data, and then improve the signal-to-noise ratio and suppress spontaneous EEG activity. Among them, a multi-channel EEG signal x j (t) can be considered to consist of two parts: the source signal s(t) related to the task and the signal n(t) unrelated to the task (which can be considered as a noise signal). The EEG signal x of each channel j (t) can be decomposed into the linear model shown in the following formula (3):
[0114] x j (t) = a 1,j s(t)+a 2,j n(t),j=1,2,…,N e (3)
[0115] Where j represents the jth lead, N e Indicates the total number of leads, a 1,j and a 2,j is the mixing coefficient, from the EEG signal x j (t), extract the task-related component s(t), perform weighted summation on the multi-channel EEG signals, and combine them into a linear one-dimensional model y(t), as shown in the following formula (4):
[0116]
[0117] Among them, w j is the weight of the corresponding lead. Accordingly, in an ideal situation, When y(t)=s(t), we can make y(t)=s(t), thereby eliminating the noise n(t) in the EEG signal. Maximizing the covariance of the data between trials can solve this problem. The raw data of the hth trial of the EEG signal and the expected task-related components can be described as x (h) (t) and y (h) (t)(h=1,2,…,N t ,t∈[t h ,t h +T]), where t h is the start time of the hth trial, and T is the duration of the trial. The covariance of y(t) between the h1th and h2th trials is shown in the following formula (5):
[0118]
[0119] Accordingly, in order to obtain a finite solution, the variance constraint of y(t) in the embodiment of the present invention is as shown in the following equations (6) and (7):
[0120]
[0121] Among them, S = Cov[x j (t),x j (t)]. Accordingly, the constrained optimization problem can be solved as shown in the following formula (8):
[0122]
[0123] Accordingly, the embodiment of the present invention converts the optimal coefficient vector As the matrix Q -1 The eigenvector of S can be obtained from N e The EEG data of N channels is obtained e Q -1 The eigenvalue λ of the S matrix and its corresponding eigenvector Q is calculated by the concatenated matrix of all training trials. In the process of building the offline model, the training data of the subjects The filter bank is divided into different sub-bands, and then the spatial filters of each frequency are obtained by training the task-related component analysis (TRCA) algorithm. and the mean of the training data As a template signal, that is, a preset template signal. Then, the embodiment of the present invention calculates X (m) and The Pearson correlation coefficient is the Pearson correlation coefficient between the EEG signal to be classified and each preset template signal. Finally, the embodiment of the present invention selects the SSVEP target frequency corresponding to the largest Pearson correlation coefficient to obtain the EEG classification and recognition result.
[0124] It should be noted that, in some embodiments of the present invention, the canonical correlation analysis algorithm can also be used to classify the EEG signals to be classified. Specifically, the goal of the canonical correlation analysis (CCA) algorithm in the embodiment of the present invention is to find a set of linear transformations W for two sets of high-dimensional variables X and Y. X and W Y , so that the one-dimensional dependent variable and The correlation between them is the largest. Where X represents the n-channel EEG data with a data length of N, as shown in the following formula (9):
[0125]
[0126] Among them, channel i represents the EEG signal of channel numbered i. Correspondingly, when there are m stimulation frequencies, f i is the stimulation frequency, then i Correlated reference signal Y i The definition is shown in the following formula (10):
[0127]
[0128] Among them, N h is the harmonic number of the reference signal, N is the number of sampling points, and S is the sampling frequency. In addition, the above formula in the embodiment of the present invention can also be expressed as the following formula (11):
[0129]
[0130] Accordingly, the embodiment of the present invention solves x and y by generalized eigenvalue decomposition method, and the typical correlation analysis algorithm formula is shown in the following formula (12):
[0131]
[0132] Among them, C xx =XX T , C yy =YY T are the intra-class covariance matrices of X and Y, respectively, and C xy =XY T is the covariance matrix between classes X and Y, and ρ is the canonical correlation coefficient.
[0133] Accordingly, the frequencies of the stimulation targets in the embodiment of the present invention are f1, f2, ..., fm (f1 <f2<…<f m ), the correlation coefficient ρ(f) of the EEG data segment is calculated by formula (13), and the corresponding target frequency f(t) is shown in the following formula (13):
[0134] f(t)=argmax f ρ(f),f=f1,f2,…f m (13)
[0135] In this embodiment of the present invention, the obtained f(t) is used as the target stimulation frequency that the subject is looking at. Each stimulation frequency has a corresponding output instruction, so the target block that the subject is looking at can be identified and the corresponding instruction can be output. Accordingly, the principle of the CCA algorithm in the embodiment of the present invention is as follows: Fig.13 shown.
[0136] In some embodiments of the present invention, performing cruise control on a vehicle according to a vehicle cruise instruction includes but is not limited to the following steps:
[0137] Get vehicle speed data.
[0138] When it is determined that the vehicle speed data is greater than the first cruise threshold and less than the second cruise threshold, the preset vehicle is controlled to enter the cruise control mode according to the vehicle cruise command, wherein the second cruise threshold is greater than the first cruise threshold.
[0139] In this specific embodiment, the embodiment of the present invention first obtains the vehicle speed data to determine whether the conditions for entering the cruise control mode are met through the vehicle speed data. Specifically, after the corresponding EEG classification results are obtained through classification, the embodiment of the present invention determines whether the speed of the vehicle is within the preset speed area. When it is determined that the speed of the vehicle is within the preset speed area, that is, the vehicle speed data is greater than the first cruise threshold and less than the second cruise threshold, it means that the vehicle meets the cruise condition. The embodiment of the present invention controls the preset vehicle to enter the corresponding cruise control mode according to the determined vehicle cruise instruction. Exemplarily, there is a reasonable range of cruising speed for electric vehicles in the embodiment of the present invention. For example, for most vehicles, the preset speed range is 90km / h-120km / h, that is, when the current speed is lower than 90km / h and the current speed is greater than 120km / h, the vehicle will not enter the cruise function. Among them, 90km / h in the embodiment of the present invention is the lower limit of the speed, which is the lowest speed generally set for high-speed cruise control. Different models are slightly different, generally 90km / h. When the speed of the electric vehicle is lower than 90km / h, the cruising speed cannot be set and cruising cannot be performed. In addition, the embodiment of the present invention also needs to determine that the power system of the electric vehicle is fault-free when cruising, that is, when the electric vehicle enters cruising, the power system must not have any faults. If the vehicle power system fails during cruising, the cruise function is exited, and the corresponding steady-state visual evoked potential UI interface returns to the style before it is turned on.
[0140] In some embodiments of the present invention, after executing cruise control on the vehicle according to the vehicle cruise instruction, the vehicle cruise control method provided by the embodiment of the present invention further includes but is not limited to the following steps:
[0141] When it is determined that a preset cruise exit condition is detected, the preset vehicle is controlled to exit the cruise control mode. The preset cruise exit condition includes one of the vehicle cruise command being a cruise off command, the vehicle speed data being less than a first cruise threshold, the vehicle fault or power limit processing being detected, the brake signal being detected, and the preset cancel button signal being obtained.
[0142] In this specific embodiment, when the preset cruise exit condition is determined to be monitored, the embodiment of the present invention controls the preset vehicle to exit the cruise control mode. Specifically, within the speed range, when the vehicle driver visually views the UI interface, the cruise control function of the vehicle is turned on, and the vehicle enters the cruise system, and the initial speed is the speed when entering the cruise control system. At the same time, other speed selection blocks on the UI interface (preset display interface) begin to flash for the driver to select a suitable cruise control speed. Accordingly, when the vehicle enters the cruise control mode, the embodiment of the present invention monitors whether the vehicle meets the preset cruise exit condition through the detection module. When it is determined that the preset cruise exit condition is met, the cruise control mode is exited. Among them, the preset cruise exit condition in the embodiment of the present invention includes that the vehicle cruise instruction is a cruise off instruction, the vehicle speed data is less than the first cruise threshold, it is determined that a vehicle fault or power limiting processing is detected, it is determined that a brake signal is detected, and one of the preset cancel button signals is obtained. For example, when the vehicle driver mode turns off the cruise block, the vehicle cruise instruction is determined to be a cruise off instruction according to the corresponding EEG signal, and the vehicle is controlled to exit the cruise control mode. In addition, when the speed of the vehicle is lower than the first cruising threshold, such as 90km / h, it means that the vehicle currently does not meet the cruising conditions, and the embodiment of the present invention controls the vehicle to exit the cruise control mode. At the same time, when the electric vehicle detects that it has a fault or needs to be operated with limited power (such as low battery, motor overheating, etc.), in order to ensure driving safety, the embodiment of the present invention controls the vehicle to exit the cruise control mode to avoid continuing to maintain the cruise state when the vehicle performance is limited. In addition, when the user steps on the brake pedal or has a braking depth, regardless of the braking depth, it means that the driver wants to slow down or stop immediately, so the embodiment of the present invention controls the vehicle to exit the cruise control mode. Accordingly, the embodiment of the present invention is also provided with a preset cancel button, and the vehicle driver can apply to exit the cruise control mode by pressing or touching the preset cancel button. When it is determined that the preset cancel button signal is obtained, the embodiment of the present invention controls the vehicle to exit the cruise control mode.
[0143] It is easy to understand that the embodiment of the present invention captures the driver's response to visual stimulation through steady-state visual evoked potential technology to achieve precise control of the cruise control speed. At the same time, in response to the common speed adjustment needs of drivers during driving, the embodiment of the present invention sets eight different visual stimulation frequencies, each frequency corresponding to a function / speed. The key to the embodiment of the present invention is to induce the driver's EEG signal by presenting flickering visual stimulation of different frequencies, and identify the signal through corresponding signal processing technology (task-related component analysis algorithm). In addition, the embodiment of the present invention analyzes the driver's EEG response in real time, thereby identifying the driver's desired cruise control speed and automatically adjusting the driving speed of the electric vehicle. Accordingly, in order to verify the effectiveness and reliability of the present invention, the embodiment of the present invention designs a driving simulation experiment including a variety of driving scenarios to verify the control effect. Among them, such as Fig.14 As shown, the experimental results of the backup embodiment show that the system can accurately identify the driver's intention and realize the cruise control of the electric vehicle. The embodiment of the present invention realizes the intuitive and rapid recognition of the driver's intention by applying the steady-state visual evoked potential technology to the cruise control system of the electric vehicle. Compared with the traditional physical button or touch screen control method, the embodiment of the present invention has higher convenience and accuracy, and improves the driving comfort and safety. In addition, the vehicle cruise control method provided by the embodiment of the present invention also has a wide range of application prospects, and can be extended to other intelligent driving assistance systems to further enhance the intelligence level of electric vehicles. Accordingly, the embodiment of the present invention realizes the precise control of the cruise speed and the recognition of the steering intention by capturing the steady-state visual evoked potential signal of the driver, which provides strong support for improving the driving experience and safety.
[0144] See also Fig.15 The embodiment of the present application also provides a vehicle cruise control system, which can implement the above vehicle cruise control method, and the system includes:
[0145] The first module 210 is used to obtain preset EEG data.
[0146] The second module 220 is used to perform data preprocessing on the preset EEG data to obtain the EEG signal to be classified.
[0147] The third module 230 is used to classify the EEG signal to be classified by using a preset correlation analysis algorithm to determine an EEG classification result, wherein the EEG classification result corresponds to the vehicle cruise instruction.
[0148] The fourth module 240 is used to perform cruise control on the vehicle according to the vehicle cruise instruction.
[0149] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0150] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above vehicle cruise control method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.
[0151] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0152] See also Fig.16 , Fig.16 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:
[0153] The processor 310 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;
[0154] The memory 320 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 320 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 320, and the processor 310 calls and executes the vehicle cruise control method of the embodiment of the present application;
[0155] Input / output interface 330, used to implement information input and output;
[0156] Communication interface 340, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);
[0157] bus 350 , which transmits information between the various components of the device (e.g., processor 310 , memory 320 , input / output interface 330 , and communication interface 340 );
[0158] The processor 310 , the memory 320 , the input / output interface 330 and the communication interface 340 are connected to each other in communication within the device via the bus 350 .
[0159] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned vehicle cruise control method is implemented.
[0160] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0161] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0162] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
[0163] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.
[0164] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0165] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.
[0166] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0167] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.
[0168] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is 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. Another point is that the mutual coupling or direct coupling or communication connection 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.
[0169] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0170] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0171] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.
[0172] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.
Claims
1. A vehicle cruise control method, It is characterized in that The method comprises the following steps: Get preset EEG data; Performing data preprocessing on the preset EEG data to obtain EEG signals to be classified; Classifying the to-be-classified EEG signal by a preset correlation analysis algorithm to determine an EEG classification result; wherein the EEG classification result corresponds to a vehicle cruise instruction; The preset vehicle is cruise controlled according to the vehicle cruise instruction.
2. The method according to claim 1, It is characterized in that The step of obtaining preset EEG data includes: Constructing a preset display interface; wherein the preset display interface includes a plurality of preset stimulation targets, and the flashing frequency of the plurality of preset stimulation targets corresponds to the vehicle cruise instruction; The preset EEG data is dynamically acquired through a preset brain-computer interface; wherein the preset EEG data includes steady-state visual evoked potential data, and the steady-state visual evoked potential data is generated by visual stimulation of the preset stimulation target.
3. The method according to claim 1, It is characterized in that The step of preprocessing the preset EEG data to obtain an EEG signal to be classified includes: Performing electrode channel screening on the preset EEG data to obtain first EEG data; Performing electrode re-referencing on the first EEG data to obtain second EEG data; Performing a preset filtering process on the second EEG data to obtain third EEG data; Performing data segmentation processing on the third EEG data to obtain fourth EEG data; Baseline correction is performed on the fourth EEG data to obtain the EEG signal to be classified.
4. The method according to claim 1, It is characterized in that The method of classifying the to-be-classified EEG signals by using a preset correlation analysis algorithm to determine the EEG classification result includes: The EEG signal to be classified is classified by a task-related component analysis algorithm to obtain the EEG classification result.
5. The method according to claim 4, It is characterized in that The step of classifying the EEG signal to be classified by using a task-related component analysis algorithm to obtain the EEG classification result includes: Constructing a plurality of preset template signals through the task-related component analysis algorithm according to the preset training data; wherein the preset template signals correspond to the EEG classification results; Calculating the Pearson correlation coefficient between the EEG signal to be classified and each of the preset template signals, so as to select the preset template signal having the greatest correlation with the EEG signal to be classified as the target template signal according to the Pearson correlation coefficient; The EEG classification result is determined according to the target template signal.
6. The method according to claim 1, It is characterized in that The performing cruise control on a preset vehicle according to the vehicle cruise instruction comprises: Get vehicle speed data; When it is determined that the vehicle speed data is greater than a first cruise threshold and less than a second cruise threshold, the preset vehicle is controlled to enter a constant speed cruise mode according to the vehicle cruise instruction; wherein the second cruise threshold is greater than the first cruise threshold.
7. The method according to claim 6, It is characterized in that After executing the cruise control of the preset vehicle according to the vehicle cruise instruction, the method further includes: When it is determined that a preset cruise exit condition is monitored, the preset vehicle is controlled to exit the cruise control mode; wherein the preset cruise exit condition includes the vehicle cruise command being a cruise off command, the vehicle speed data being less than the first cruise threshold, a vehicle fault or power limiting processing being detected, a brake signal being detected, and one of a preset cancel button signal being obtained.
8. A vehicle cruise control system, It is characterized in that The system comprises: The first module is used to obtain preset EEG data; The second module is used to perform data preprocessing on the preset EEG data to obtain EEG signals to be classified; The third module is used to classify the to-be-classified EEG signal by a preset correlation analysis algorithm to determine an EEG classification result; wherein the EEG classification result corresponds to a vehicle cruise instruction; The fourth module is used to perform cruise control on a preset vehicle according to the vehicle cruise instruction.
9. An electronic device, It is characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program. It is characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
Citation Information
Cited By
Instruction output method and device based on brain-computer interface, medium and electronic equipment
CN119336174A
