CN114081504A - Driving intention identification method and system based on electroencephalogram signals - Google Patents
Driving intention identification method and system based on electroencephalogram signals Download PDFInfo
- Publication number
- CN114081504A CN114081504A CN202111395973.6A CN202111395973A CN114081504A CN 114081504 A CN114081504 A CN 114081504A CN 202111395973 A CN202111395973 A CN 202111395973A CN 114081504 A CN114081504 A CN 114081504A
- Authority
- CN
- China
- Prior art keywords
- wavelet
- driving intention
- electroencephalogram
- electroencephalogram signal
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000008569 process Effects 0.000 claims abstract description 16
- 230000006870 function Effects 0.000 claims description 21
- 230000009466 transformation Effects 0.000 claims description 12
- 238000003860 storage Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000002203 pretreatment Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 14
- 238000012545 processing Methods 0.000 description 14
- 230000009467 reduction Effects 0.000 description 12
- 238000000354 decomposition reaction Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 210000004556 brain Anatomy 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000003044 adaptive effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 210000001061 forehead Anatomy 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 230000002123 temporal effect Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000012880 independent component analysis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000014644 Brain disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000013256 coordination polymer Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004070 electrodeposition Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000003128 head Anatomy 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000001936 parietal effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
- A61B5/372—Analysis of electroencephalograms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Psychiatry (AREA)
- Molecular Biology (AREA)
- Physics & Mathematics (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Psychology (AREA)
- Power Engineering (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention provides a driving intention identification method and system based on electroencephalogram signals, wherein the electroencephalogram signals of a driver in the driving process are acquired, and are preprocessed; obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction; extracting energy characteristics of the wavelet packet coefficients; obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model; the accuracy of the driving intention recognition is improved.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a driving intention identification method and system based on electroencephalogram signals.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The early recognition of the driving intention provides theoretical and practical support for the development of the assisted driving and the automatic driving, and the recognition of the accuracy of the driving intention is one of the key problems in deciding the assisted driving and the automatic driving. More powerful parameters and more accurate identification are required to be acquired for automatic driving, the driving intention is directly identified by electroencephalogram signals, data is not transmitted through any medium for processing, the directness of input parameters is provided, the propagation error of a propagation medium is reduced, the driving intention is identified in advance, powerful guarantee is provided for the safety of auxiliary driving and automatic driving, and important theoretical and practical significance is achieved for traffic safety.
The inventor finds that the key problem of the driving intention based on the electroencephalogram signal lies in noise reduction of the electroencephalogram signal, the electroencephalogram signal is a very weak signal, the electroencephalogram signal can be interfered by various signal noises in the signal acquisition process, the driving intention data of the obtained electroencephalogram signal are relatively mixed, and most of the driving intention data cannot be reflected by the existing support vector machine model, the neural network model or the deep learning model.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a driving intention identification method and system based on electroencephalogram signals, and the identification accuracy of the driving intention is improved.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a driving intention identification method based on electroencephalogram signals.
A driving intention recognition method based on electroencephalogram signals comprises the following processes:
acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
extracting energy characteristics of the wavelet packet coefficients;
and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
The invention provides a driving intention recognition system based on electroencephalogram signals in a second aspect.
A driving intention recognition system based on an electroencephalogram signal, comprising:
a data acquisition module configured to: acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
a wavelet reconstruction module configured to: obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
a feature extraction module configured to: extracting energy characteristics of the wavelet packet coefficients;
a driving intent recognition module configured to: and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
A third aspect of the present invention provides a computer-readable storage medium on which a program is stored, the program implementing the steps in the electroencephalogram signal-based driving intention recognition method according to the first aspect of the present invention when executed by a processor.
A fourth aspect of the present invention provides an electronic device, which includes a memory, a processor and a program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for recognizing driving intention based on electroencephalogram signals according to the first aspect of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the driving intention identification method and system based on the electroencephalogram signals, the driving intention data of the electroencephalogram signals are analyzed and denoised through wavelet transformation, the electroencephalogram signals are divided into five layers, the signals are processed through a soft threshold method, and the accuracy of driving intention identification is improved.
2. According to the method and the system for recognizing the driving intention based on the electroencephalogram signals, the wavelet packet is used for extracting energy characteristics of the electroencephalogram signals after noise reduction, and the energy characteristics are input into the Bayes recognition model of the driving intention, so that the accuracy of driving intention recognition is further improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic flow chart of a driving intention recognition method based on electroencephalogram signals according to embodiment 1 of the present invention.
Fig. 2 is a schematic diagram of partial data of an electroencephalogram signal of a right-turn driving intention provided in embodiment 1 of the present invention.
Fig. 3 is a schematic diagram of partial data of an electroencephalogram signal of a left-turn driving intention according to embodiment 1 of the present invention.
Fig. 4 is a schematic diagram of partial data of an electroencephalogram signal for a straight-driving intention according to embodiment 1 of the present invention.
Fig. 5 is a schematic diagram of wavelet three-layer decomposition provided in embodiment 1 of the present invention.
Fig. 6 is a schematic diagram of an original signal and a noise-reduced signal provided in embodiment 1 of the present invention.
Fig. 7 is a schematic diagram of a wavelet packet decomposition according to embodiment 1 of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example 1:
as shown in fig. 1, an embodiment 1 of the present invention provides a driving intention recognition method based on electroencephalogram signals, including the following processes:
acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
extracting energy characteristics of the wavelet packet coefficients;
and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
Specifically, the method comprises the following steps:
s1: experiment establishment
A driving simulation experiment platform and an electroencephalogram signal acquisition platform are built, electroencephalogram signals are acquired through electroencephalogram equipment g.USBamp, a route is selected, and the driving process of the route comprises driving intention operations such as left turning, right turning, straight going and the like. Selecting 9 drivers, wherein the drivers are 20-23 years old, have driving licenses without any brain diseases, and carry out training work before related experiments on the drivers. The experiment was approved by the ethical committee of the relevant units.
The driving operation is carried out through the driving simulator and simultaneously acquires the information of the electroencephalogram signals, the first 3 seconds of data and the last 3 seconds of data of the electroencephalogram signals of the driving intentions of the driver of turning left, turning right and going straight in the driving process are acquired, and in the acquisition process of the electroencephalogram signals, 50HZ power frequency noise signals are filtered through electroencephalogram equipment. The acquisition frequency is 256HZ, and the time for acquiring the electroencephalogram information is 3 seconds. Collection 16Information of electroencephalogram signals of the channels, 16-channel electrodes mainly comprise areas above a left hemisphere and a right hemisphere of a brain, and the electrodes of 16 channels are respectively as follows: f3,FC3,C3,F1,FC1,C1,Fz,FCz,Cz,CPz,F2,F4,C2,C4,FC2,FC4. Corresponding electroencephalogram data are obtained through testing the electrodes, a basis is provided for electroencephalogram signal analysis, and the positions of the brain partition electrodes are shown in table 1:
table 1: electrode position
Location of a body part | Name (R) | (Code) |
Forehead (head) | Frontal Pole | Fp1、Fp2 |
Forehead (D) | Frontal | F3、F4、Fz |
Center (C) | Central | C3、C4、Cz |
Top roof | Parietal | O1、O2 |
Side forehead | Occipital | F7、F8 |
Temporal region | Inferior Frontal | T3、T4 |
Posterior temporal region | Temporal | T5、T6 |
Ear | Auricular | A1、A2 |
S2: driving intent data analysis
The driving intentions mainly comprise three main driving intentions of left turning, right turning and straight going, electroencephalogram signals of the three driving intentions are collected, time window data of a traditional driving intention object are generally selected from 3 seconds, 6 seconds, 10 seconds and the like for research, and the data of 3 seconds are selected for analysis and research in the embodiment; respectively collecting the left-turn, right-turn and straight-going 3-second electroencephalogram signals of the driver, and processing and analyzing the 3-second electroencephalogram signals.
The sampling frequency is 256HZ, the electroencephalograms corresponding to the left-turn driving intention, the right-turn driving intention and the straight driving intention of 3 seconds respectively account for 768 data points, taking the right-turn driving intention as an example, the right-turn driving intention is determined when a driver turns on a right-turn steering lamp, the electroencephalogram data of the driver in the first 3 seconds of the right-turn moment is collected as research data, and Python software is used for reading the electroencephalograms, as shown in figure 2, the electroencephalogram data are electroencephalogram part data of the right-turn driving intention.
Electroencephalogram signal partial data of left turn driving intention, as shown in fig. 3; the electroencephalogram signal part data of the straight driving intention is shown in fig. 4.
S3: model and method
Decomposing the EEG signal in wavelet domain, selecting wavelet db3, decomposing into three layers, four layers and five layers, wavelet transforming to obtain wavelet coefficient, decomposing part of wavelet coefficient into EEG signal and noise and decomposing part of wavelet coefficient into noise signal, and extracting useful EEG signal by wavelet decomposition transform. And inputting the decomposed signals into an independent component analysis model for continuous filtering, extracting energy as input data of the input model by a wavelet packet processing technology, and training and testing.
S3.1: principle of wavelet transform
Wavelet transformation is an important tool for time-frequency research, frequency can be analyzed locally through the wavelet transformation, the defect of Fourier transformation is overcome, and the method is suitable for processing non-stationary signals. The wavelet transform is a time-frequency analysis method, has the characteristic of multi-resolution, can have good resolution in both time domain and frequency domain, and is more suitable for processing electroencephalogram signals. Wavelet transformation is the local analysis of a time frequency domain, signals are subjected to multi-scale refinement through telescopic translation operation, frequency subdivision is carried out at a low frequency, and time subdivision can be carried out at a high frequency. Various time-varying signals can be effectively decomposed, and signals and noise can be well separated. Commonly used wavelet basis functions include wavelet functions, wavelet function systems, and complex wavelets. The wavelet bases are selected according to which wavelet base obtains the largest wavelet coefficient and the small variance value, and then which wavelet base is selected. The wavelet basis in the wavelet function Daubechies system is represented as dbN, wherein N is the sequence N-1, 2, …, 10.
The basic principle of wavelet transform is to approximate a signal by a wavelet function system, and obtain the signal by translation or expansion through a basic wavelet function.
Wavelet one-dimensional transform decomposition:
in the formula, phi (x) is mother wavelet, a is translation factor, b is expansion factor, W(a,b)Are the wavelet coefficients of signal f (x).
Discretizing the continuous wavelet and wavelet coefficient and taking A discrete wavelet function is obtained:
the wavelet transform is divided into three layers, and only decomposes a low-frequency part, and does not consider a high-frequency part. The signal S ═ CA3+ CD3+ CD2+ CD 1. Where CA is the approximated signal, i.e. the low frequency part, and CD is the detail signal, i.e. the high frequency part, as shown in fig. 5.
The frequency range of beta waves in the electroencephalogram signals is 14-30 Hz; the frequency range of gamma wave is 30-60 Hz. Thus, the brain electrical signal is divided into three layers by the db3 wavelet, which are: a3, D3, D2 and D1. The sampling frequency is 256Hz, according to the sampling theorem, so D1 is the first layer and the frequency range is 64-128 Hz. D2 is the second layer, and the frequency range is 32-64 Hz. D3 is the third layer, and the frequency range is 16-32 Hz. A3 is the third layer, the frequency range is 8-16 Hz. Thus, the beta wave is on the third layer and the gamma wave is on the second layer.
S3.2: wavelet threshold denoising
Wavelet threshold denoising is to reserve wavelet coefficients larger than a threshold value through wavelet transformation, set the wavelet coefficients smaller than the threshold value to be zero, reserve useful signal information and filter out noise signals. And then reconstructing the processed wavelet coefficient to obtain the noise-reduced electroencephalogram signal.
The selection rule of the threshold mainly comprises a minimum maximum threshold, a fixed threshold, an adaptive threshold of an unbiased likelihood estimation principle, a heuristic threshold and the like, and the four threshold selection rules have advantages and disadvantages respectively. The minimum maximum value mainly realizes the minimization of the maximum mean square error and generates a minimum variance extreme value; the fixed threshold is used for selecting a fixed threshold for noise reduction according to the characteristics of the signal during noise reduction; the adaptive threshold is a soft threshold estimator, which estimates the minimization risk to obtain the adaptive threshold; the heuristic threshold is a threshold method proposed on the basis of the idea of adaptive threshold and fixed threshold.
The threshold function is selected mainly from a hard threshold function and a soft threshold function. The hard threshold function compares the wavelet coefficient before wavelet transformation with the threshold, the absolute value of the wavelet coefficient is larger than the threshold and is reserved, and the absolute value smaller than the threshold is set to be zero.
Hard threshold function:
in the formula, wi,jWavelet coefficients of the original signal;wavelet coefficients after threshold quantization; t is a threshold value.
The soft threshold function compares the wavelet coefficient before wavelet transformation with a threshold, the wavelet coefficient with an absolute value greater than or equal to the threshold is set as a constant difference, and the wavelet coefficient smaller than the threshold is set as zero. The hard threshold is prone to lose some useful signal after processing, so the soft threshold is selected for processing and analyzing the brain electrical signal.
Soft threshold function:
in the formula, wi,jWavelet coefficients of the original signal;wavelet coefficients after threshold quantization; t is a threshold value.
The noise reduction effect is evaluated through the signal-to-noise ratio and the minimum mean square error, the smaller the minimum mean square error is, the closer the processed signal is to the original signal is, the larger the signal-to-noise ratio is, the more useful information is represented, and the less noise information is represented.
Maximum minimum threshold method:
the maximum minimum threshold method minimizes the maximum risk, the original noise-containing signal is regarded as similar to the estimation formula of the unknown regression function, the maximum mean error minimization is realized in the function by the extreme value estimation, and the threshold is solved by the maximum minimum threshold method in the embodiment.
And filtering the signals subjected to the wavelet change by an independent component analysis method, and performing wavelet packet transformation processing on the filtered signals.
Wavelet packet transform is a transform that decomposes high frequencies as well on the basis of the wavelet transform theory.
Python simulation:
and (3) carrying out processing analysis on the noise reduction of the wavelet-transformed electroencephalogram signal by utilizing Python, and evaluating the processed effect by comparing the minimum mean square error with the signal to noise ratio.
The signal before noise reduction and the signal after noise reduction are compared, wavelet layering is performed, wavelet transform noise reduction analysis is performed by using a soft threshold, taking the right turn of an F3 channel as an example, as shown in FIG. 6.
The minimum mean square error obtained by utilizing Python simulation noise reduction is 0.001697, which shows that the effect is excellent.
S3.3: wavelet packet theory and its characteristic analysis
The orthogonal wavelet decomposition is to decompose the low-frequency coefficient into two parts, and respectively obtain a low-frequency coefficient vector and a high-frequency coefficient vector. The new low frequency coefficient vector is then decomposed further into a low frequency coefficient vector and a high frequency coefficient vector, but not into a high frequency coefficient vector. Wavelet packet decomposition continues to decompose the high frequency coefficients, and the high frequency coefficient vector is decomposed into two parts, which is different from wavelet decomposition, and the wavelet packet decomposition is more detailed.
In the embodiment, the wavelet packet energy is used as a feature vector and input into a recognition model of a Bayes theory for recognition, and the wavelet packet energy is obtained through a wavelet packet coefficient.
S4: driving intention recognition based on Bayesian theory
S4.1: bayes theory
Assuming that a, B are any two events and p (a) >0, the conditional probability of event B occurring under the condition that event a has occurred is:
p (A) is called prior probability, and P (B/A) is called posterior probability.
Therefore, the multiplication theorem can be obtained:
if there is p (a) >0 and p (B) >0 for any two events a and B, then there is:
P(AB)=P(A)P(B|A)=P(B)P(A|B) (8)
let a1, a 2., An be any n events, n > -2, and P (a1, a 2., An) >0, then there are:
P(A1A2...An)=P(A1)P(A2|A1)P(A3|A1A2)...P(An|A1A2...An-1) (9)
for any event B, there is a total probability formula:
the Bayes theorem can be obtained from the conditional probability and total probability formulas as follows:
s4.2: naive Bayes classifier
The naive bayes classifier is based on the formula (12):
wherein, P (y | x)1,...,xj) To a posterior probability, P (x)1,...,xj| y) is the likelihood probability, P (y) is the prior probability, P (x)1,...,xj) Is the edge probability.
Assuming that the likelihood probability of feature x obeys a normal distribution:
s4.3: driving intention recognition based on Bayesian theory
There are three main categories of recognition of driving intent: turning left, turning right, going straight, assuming that the probability of a certain category is the same, the prior probability is:
when driving intention recognition is performed, the formula is:
wherein j represents left turn, straight line, right turn, i represents the number of channels, k represents the number of drivers, xikA kth characteristic parameter representing the number of ith channels. y isijIndicates the category of the ith number of channels.
In the embodiment, the channel 1 (F3) of the left hemisphere of the brain is selected for research, and analysis results show that the recognition rate is the highest when wavelet decomposition and wavelet packet decomposition are five layers, and the recognition rate of driving intention simulated by Python reaches 71.51% at most.
In the embodiment, the driving intention data of the electroencephalogram signals are analyzed and denoised through wavelet transformation, nonstationary signals can be analyzed and processed by utilizing the wavelet transformation, the characteristics of frequency localization analysis and the like can be carried out, the driving intention data of the electroencephalogram signals are processed and analyzed, the electroencephalogram signals are divided into five layers, then the signals are processed by using a soft threshold method, the minimum mean square error of the denoised signals is 0.001697, and a good denoising effect is obtained; the noise reduction of the wavelet transform theory still has the defects that only low-frequency signals are decomposed, and high-frequency signals cannot be decomposed, so that the electroencephalogram signals subjected to noise reduction are extracted by using wavelet packets, energy characteristics are input into a recognition model of driving intentions, and a good recognition effect is obtained.
Example 2:
the embodiment 2 of the invention provides a driving intention recognition system based on an electroencephalogram signal, which comprises:
a data acquisition module configured to: acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
a wavelet reconstruction module configured to: obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
a feature extraction module configured to: extracting energy characteristics of the wavelet packet coefficients;
a driving intent recognition module configured to: and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
The working method of the system is the same as the driving intention identification method based on the electroencephalogram signals provided in embodiment 1, and is not repeated here.
Example 3:
Example 4:
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A driving intention identification method based on electroencephalogram signals is characterized by comprising the following steps:
the method comprises the following steps:
acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
extracting energy characteristics of the wavelet packet coefficients;
and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
2. The electroencephalogram signal-based driving intention recognition method of claim 1, wherein:
the driving intentions include at least a left turn, a right turn, and a straight line.
3. The electroencephalogram signal-based driving intention recognition method of claim 1, wherein:
pre-treatment, comprising: and denoising by adopting a wavelet threshold denoising method.
4. The electroencephalogram signal-based driving intention recognition method of claim 3, wherein:
dividing the EEG signal into five layers, and then denoising by adopting a wavelet threshold denoising method.
5. The electroencephalogram signal-based driving intention recognition method of claim 3, wherein:
the wavelet threshold denoising method adopts a soft threshold function, compares a wavelet coefficient before wavelet transformation with a threshold, sets the wavelet coefficient with an absolute value larger than or equal to the threshold as a constant difference value, and sets the wavelet coefficient smaller than the threshold as zero.
6. The electroencephalogram signal-based driving intention recognition method of claim 1, wherein:
the electroencephalogram signals include signals acquired by a plurality of channel electrodes.
7. The electroencephalogram signal-based driving intention recognition method of claim 1, wherein:
a Bayesian model comprising:
wherein j represents left turn, straight line or right turn, i represents the number of channels, k represents the number of drivers, xikKth feature representing the number of ith channelsParameter, yijIndicates the category of the ith number of channels.
8. A driving intention recognition system based on electroencephalogram signals is characterized in that:
the method comprises the following steps:
a data acquisition module configured to: acquiring an electroencephalogram signal of a driver in a driving process, and preprocessing the electroencephalogram signal;
a wavelet reconstruction module configured to: obtaining a wavelet packet coefficient of the preprocessed electroencephalogram signal through wavelet packet reconstruction;
a feature extraction module configured to: extracting energy characteristics of the wavelet packet coefficients;
a driving intent recognition module configured to: and obtaining a driving intention recognition result according to the extracted energy characteristics and the Bayesian model.
9. A computer-readable storage medium on which a program is stored, the program realizing the steps in the electroencephalogram signal-based driving intention recognition method according to any one of claims 1 to 7 when executed by a processor.
10. An electronic device comprising a memory, a processor and a program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for recognizing driving intention based on electroencephalogram signal according to any one of claims 1 to 7 when executing the program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111395973.6A CN114081504B (en) | 2021-11-23 | 2021-11-23 | Driving intention recognition method and system based on electroencephalogram signals |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111395973.6A CN114081504B (en) | 2021-11-23 | 2021-11-23 | Driving intention recognition method and system based on electroencephalogram signals |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114081504A true CN114081504A (en) | 2022-02-25 |
CN114081504B CN114081504B (en) | 2024-03-01 |
Family
ID=80303488
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111395973.6A Active CN114081504B (en) | 2021-11-23 | 2021-11-23 | Driving intention recognition method and system based on electroencephalogram signals |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114081504B (en) |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101259015A (en) * | 2007-03-06 | 2008-09-10 | 李小俚 | Electroencephalogram signal analyzing monitoring method and device thereof |
US20110276275A1 (en) * | 2010-05-04 | 2011-11-10 | Nellcor Puritan Bennett Ireland | Systems And Methods For Wavelet Transform Scale-Dependent Multiple-Archetyping |
CN102488516A (en) * | 2011-12-13 | 2012-06-13 | 湖州康普医疗器械科技有限公司 | Nonlinear electroencephalogram signal analysis method and device |
WO2017004880A1 (en) * | 2015-07-08 | 2017-01-12 | 中兴通讯股份有限公司 | Method, device for behavior recognition and computer storage medium |
KR20170014704A (en) * | 2015-07-31 | 2017-02-08 | 전남대학교산학협력단 | Method for recognizing user intention |
CN106618562A (en) * | 2017-01-11 | 2017-05-10 | 南京航空航天大学 | Wearable epilepsy brain-electricity seizure brain area positioning device and method |
CN107095670A (en) * | 2017-05-27 | 2017-08-29 | 西南交通大学 | Time of driver's reaction Forecasting Methodology |
CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
CN107704881A (en) * | 2017-10-12 | 2018-02-16 | 公安部南昌警犬基地 | A kind of data visualization processing method and processing device based on animal electroencephalogramrecognition recognition |
CN108536154A (en) * | 2018-05-14 | 2018-09-14 | 重庆师范大学 | Low speed automatic Pilot intelligent wheel chair construction method based on bioelectrical signals control |
CN109144277A (en) * | 2018-10-19 | 2019-01-04 | 东南大学 | A kind of construction method for realizing brain control intelligent carriage based on machine learning |
CN209258112U (en) * | 2018-07-25 | 2019-08-16 | 北京汽车集团有限公司 | Vehicle DAS (Driver Assistant System) and vehicle |
CN110329248A (en) * | 2019-06-18 | 2019-10-15 | 南京航空航天大学 | A kind of the line traffic control intelligent steering system and its urgent barrier-avoiding method of brain-machine interaction |
CN111680620A (en) * | 2020-06-05 | 2020-09-18 | 中国人民解放军空军工程大学 | Human-computer interaction intention identification method based on D-S evidence theory |
CN112353391A (en) * | 2020-10-22 | 2021-02-12 | 武汉理工大学 | Electroencephalogram signal-based method and device for recognizing sound quality in automobile |
US20210093241A1 (en) * | 2017-08-03 | 2021-04-01 | Toyota Motor Europe | Method and system for determining a driving intention of a user in a vehicle using eeg signals |
CN113501005A (en) * | 2021-08-12 | 2021-10-15 | 戴姆勒股份公司 | Method and device for assisting control of vehicle based on physiological information of driver |
-
2021
- 2021-11-23 CN CN202111395973.6A patent/CN114081504B/en active Active
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101259015A (en) * | 2007-03-06 | 2008-09-10 | 李小俚 | Electroencephalogram signal analyzing monitoring method and device thereof |
US20110276275A1 (en) * | 2010-05-04 | 2011-11-10 | Nellcor Puritan Bennett Ireland | Systems And Methods For Wavelet Transform Scale-Dependent Multiple-Archetyping |
CN102488516A (en) * | 2011-12-13 | 2012-06-13 | 湖州康普医疗器械科技有限公司 | Nonlinear electroencephalogram signal analysis method and device |
WO2017004880A1 (en) * | 2015-07-08 | 2017-01-12 | 中兴通讯股份有限公司 | Method, device for behavior recognition and computer storage medium |
KR20170014704A (en) * | 2015-07-31 | 2017-02-08 | 전남대학교산학협력단 | Method for recognizing user intention |
CN106618562A (en) * | 2017-01-11 | 2017-05-10 | 南京航空航天大学 | Wearable epilepsy brain-electricity seizure brain area positioning device and method |
CN107095670A (en) * | 2017-05-27 | 2017-08-29 | 西南交通大学 | Time of driver's reaction Forecasting Methodology |
US20210093241A1 (en) * | 2017-08-03 | 2021-04-01 | Toyota Motor Europe | Method and system for determining a driving intention of a user in a vehicle using eeg signals |
CN107704881A (en) * | 2017-10-12 | 2018-02-16 | 公安部南昌警犬基地 | A kind of data visualization processing method and processing device based on animal electroencephalogramrecognition recognition |
CN107468260A (en) * | 2017-10-12 | 2017-12-15 | 公安部南昌警犬基地 | A kind of brain electricity analytical device and analysis method for judging ANIMAL PSYCHE state |
CN108536154A (en) * | 2018-05-14 | 2018-09-14 | 重庆师范大学 | Low speed automatic Pilot intelligent wheel chair construction method based on bioelectrical signals control |
CN209258112U (en) * | 2018-07-25 | 2019-08-16 | 北京汽车集团有限公司 | Vehicle DAS (Driver Assistant System) and vehicle |
CN109144277A (en) * | 2018-10-19 | 2019-01-04 | 东南大学 | A kind of construction method for realizing brain control intelligent carriage based on machine learning |
CN110329248A (en) * | 2019-06-18 | 2019-10-15 | 南京航空航天大学 | A kind of the line traffic control intelligent steering system and its urgent barrier-avoiding method of brain-machine interaction |
CN111680620A (en) * | 2020-06-05 | 2020-09-18 | 中国人民解放军空军工程大学 | Human-computer interaction intention identification method based on D-S evidence theory |
CN112353391A (en) * | 2020-10-22 | 2021-02-12 | 武汉理工大学 | Electroencephalogram signal-based method and device for recognizing sound quality in automobile |
CN113501005A (en) * | 2021-08-12 | 2021-10-15 | 戴姆勒股份公司 | Method and device for assisting control of vehicle based on physiological information of driver |
Non-Patent Citations (3)
Title |
---|
宋立国、陆尧胜: "小波分析在脑电信号处理中的应用", 医疗设备信息, vol. 22, no. 7, pages 7 - 10 * |
李敏、曲大义、张西龙、张永亮、潘福全: "基于粒子群算法的神经网络的驾驶意图识别", 科学与技术与工程, 22 December 2018 (2018-12-22) * |
潘鑫: "基于脑机接口的虚拟驾驶系统", 信息科技, 16 June 2018 (2018-06-16) * |
Also Published As
Publication number | Publication date |
---|---|
CN114081504B (en) | 2024-03-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Removal of muscle artifacts from the EEG: A review and recommendations | |
CN109165556B (en) | Identity recognition method based on GRNN | |
Maddirala et al. | Removal of EOG artifacts from single channel EEG signals using combined singular spectrum analysis and adaptive noise canceler | |
Mammone et al. | Automatic artifact rejection from multichannel scalp EEG by wavelet ICA | |
Üstündağ et al. | Denoising of weak ECG signals by using wavelet analysis and fuzzy thresholding | |
CN111046824A (en) | Time series signal efficient denoising and high-precision reconstruction modeling method and system | |
CN103761424B (en) | Based on secondary small echo and independent component analysis electromyographic signal noise reduction with go aliasing method | |
CN109431497B (en) | Electroencephalogram signal processing method and epilepsy detection system | |
Zhao et al. | Classification of epileptic IEEG signals by CNN and data augmentation | |
Walters-Williams et al. | A new approach to denoising EEG signals-merger of translation invariant wavelet and ICA | |
CN108567418A (en) | A kind of pulse signal inferior health detection method and detecting system based on PCANet | |
CN113723557B (en) | Depression brain electricity classifying system based on multiband space-time convolution network | |
CN110543831A (en) | brain print identification method based on convolutional neural network | |
Ranjani et al. | Classifying the autism and epilepsy disorder based on EEG signal using deep convolutional neural network (DCNN) | |
Fattah et al. | An approach for classifying alcoholic and non-alcoholic persons based on time domain features extracted from EEG signals | |
CN114403897A (en) | Human body fatigue detection method and system based on electroencephalogram signals | |
CN113842115A (en) | Improved EEG signal feature extraction method | |
CN110403602B (en) | Improved public spatial mode feature extraction method for electroencephalogram signal emotion analysis | |
Looney et al. | Subspace denoising of EEG artefacts via multivariate EMD | |
CN115017960B (en) | Electroencephalogram signal classification method based on space-time combined MLP network and application | |
CN114081504B (en) | Driving intention recognition method and system based on electroencephalogram signals | |
CN114757236B (en) | Electroencephalogram signal denoising optimization method and system based on TQWT and SVMD | |
AU2021104217A4 (en) | A system and method for optimum wavelet basis function selection for ecg arrhythmia denoising using artificial intelligence | |
Ferdous et al. | Sub-band selection approach to artifact suppression from electroencephalography signal using hybrid wavelet transform | |
Zahan | Removing EOG artifacts from EEG signal using noise-assisted multivariate empirical mode decomposition |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |