CN107273856B - A kind of EEG power spectrum mean value compression method for driver workload comparative study - Google Patents
A kind of EEG power spectrum mean value compression method for driver workload comparative study Download PDFInfo
- Publication number
- CN107273856B CN107273856B CN201710462934.0A CN201710462934A CN107273856B CN 107273856 B CN107273856 B CN 107273856B CN 201710462934 A CN201710462934 A CN 201710462934A CN 107273856 B CN107273856 B CN 107273856B
- Authority
- CN
- China
- Prior art keywords
- driver workload
- simulator
- test
- power spectrum
- mean value
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- 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]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Abstract
The present invention relates to a kind of EEG power spectrum mean value compression methods for driver workload comparative study, belong to traffic engineering technical field, this method is tested by tissue contrast and obtains driver workload actual road test and driver workload simulator test drive person's EEG power spectrum mean value;Intend device test drive person EEG power spectrum mean value duration according to obtained driver workload actual road test and driver workload, obtains compression ratio;According to the compression ratio of acquisition, that longer group of duration in driver workload actual road test and driver workload simulator test drive person's EEG power spectrum mean value is compressed using integral recombination compression method, keep compressed power spectrum mean value duration identical with another group of power spectrum mean value, compared with prior art, this method compares research with actual road test driver workload to simulator test and provides reliable ensure, through overcompression, relationship numerically between them can be easily found, and then obtains the relationship between simulator test and actual road test.
Description
Technical field
The invention belongs to traffic engineering technical field, the driver workload research being related in driving behavior research, main needle
Analysis to EEG power spectrum mean value in driver workload research, more particularly to a kind of brain applied to driver workload comparative study
Electrical power composes mean value compression method.
Background technique
Driver workload research is the important component of driving behavior research, and by being carried out to driver's heart physical signs
Analysis is the important channel for studying driver workload, and existing research is most of to be tested based on simulator or based on road road test
Verification certificate is solely unfolded, and the driver workload comparative study based on simulator test and both actual road tests, still belongs to blank rank at present
Section.
The same driver carries out actual road test and simulator test respectively, strict control various variables when test, such as
Actual road test is identical with the scene that simulator is tested, and the initial physical state of driver is identical, at the beginning of two groups of tests are selected
Between put it is identical etc..When reaching same state by test acquisition driver, the electroencephalogram power of simulator test and actual road test
Mean value is composed, but due to various differences such as two groups of experimental enviroments, can be affected to driver's heart physiology, Jin Erhui
The having differences property of EEG power spectrum mean value for causing driver, i.e., when driver reaches same state, time span experienced
It is not identical.In order to compare research with actual road test driver workload to simulator test, both unified time span is needed.
This application provides a kind of EEG power spectrum mean value compression methods, and requirements above may be implemented.
Summary of the invention
The purpose of the present invention is to propose to a kind of EEG power spectrum mean value compression method for driver workload comparative study,
Actual road test and simulator test drive people's EEG power spectrum mean value are obtained by comparative test, according to two groups of obtained data
Duration obtains compression ratio, according to the compression ratio of acquisition, using integral recombination compression method to actual road test and simulator test drive
That longer group of duration is compressed in people's EEG power spectrum mean value, keeps compressed duration identical with another group, to simulator
Test compares research with actual road test driver workload and provides reliable ensure.
In order to achieve the above object, the present invention adopts the following technical scheme that:
A kind of EEG power spectrum mean value compression method for driver workload comparative study, which is characterized in that including following
Step:
Step 1: obtaining driver workload actual road test and driver workload simulator test drive person's EEG power spectrum mean value;
Prefixed time interval is T, and is consistent in driver workload actual road test and the test of driver workload simulator, is driven
Sail load actual road test duration tRoad=nT, n are the total strong point of driver workload actual road test driver EEG power spectrum mean value
Number, n are the natural number greater than 3, obtain n driver workload actual road test driver's EEG power spectrum mean value a, aiIt indicates i-th
Driver workload actual road test driver EEG power spectrum mean value in prefixed time interval T, i value are 1 natural number for arriving n;It drives
Load simulation device tests duration tSimulator=sT, s are the total data of driver workload simulator test drive person EEG power spectrum mean value
Point number, s are the natural number greater than 3, obtain s driver workload simulator test drive person EEG power spectrum mean value b, bjIt indicates
Driver workload simulator test drive person's EEG power spectrum mean value in j-th of prefixed time interval T, j value are 1 nature for arriving s
Number;
Step 2: the driver workload actual road test duration t obtained according to step 1RoadWhen with the test of driver workload simulator
Long tSimulator, obtain driver workload actual road test duration tRoadDuration t is tested with driver workload simulatorSimulatorCompression ratio, uniformly drive
Load actual road test and driver workload simulator test duration are sailed, specific as follows:
tSimulator> tRoad, then compression ratio beAccording to t in step 1Simulator=sT and tRoad=nT, compression ratio arePass through compression processing driver workload simulator test drive person's EEG power spectrum mean value
Total strong point number isDriver workload simulator tests duration t ' after compressionSimulator=nT=tRoad;
tSimulator< tRoad, then compression ratio beAccording to t in step 1Simulator=sT and tRoad=nT, compression ratio arePass through the total of compression processing driver workload actual road test driver's EEG power spectrum mean value
Data point number isDriver workload actual road test duration t ' after compressionRoad=sT=tSimulator;
Step 3: carrying out unified driver workload actual road test and the test duration processing of driver workload simulator through step 2
Afterwards,
In t 'Simulator=tRoadUnder the conditions of, using integral recombination compression method to s driver workload simulator of acquisition in step 1
Test drive person's EEG power spectrum mean value b is compressed, the specific steps are as follows:
I, presetting f (x)=b, x are the time point in time coordinate in prefixed time interval T, and b is prefixed time interval T
Interior driver workload simulator test drive person EEG power spectrum mean value, when x takes 0, f (0)=b0, b0For the examination of driver workload simulator
Test driver's EEG signals original state, f (xj)=bj, i.e. f (xj) it is driver workload simulator test in j-th of time interval T
Driver's EEG power spectrum mean value, xjValue is natural number;
II, according to compression ratioBy following formula to s driver workload simulator test drive person's EEG power spectrum
Mean value b is compressed, and compressed n driver workload simulator test drive person's EEG power spectrum mean value c, c are obtainedkIndicate pressure
Driver workload simulator test drive person's EEG power spectrum mean value in k-th of time interval T after contracting, k value are 1 nature for arriving n
Number, the total strong point number and the total strong point number phase of driver workload actual road test of compressed driver workload simulator test
Together,
[] is to be rounded symbol in formula;
In t 'Road=tSimulatorUnder the conditions of, using integral recombination compression method to n driver workload road road test of acquisition in step 1
Driver's EEG power spectrum mean value a is tested to compress, the specific steps are as follows:
I, presetting f (x)=a, x are the time point in time coordinate in prefixed time interval T, and a is prefixed time interval T
Interior driver workload actual road test driver EEG power spectrum mean value, when x takes 0, f (0)=a0, a0It is driven for driver workload actual road test
The person's of sailing EEG signals original state, f (xi)=ai, i.e. f (xi) it is driver workload actual road test driver in i-th of time interval T
EEG power spectrum mean value, xiValue is natural number;
II, according to compression ratioIt is equal to n driver workload actual road test driver's EEG power spectrum by following formula
Value is compressed, and compressed s driver workload actual road test driver's EEG power spectrum mean value d, d are obtainedlAfter indicating compression
Driver workload simulator test drive person's EEG power spectrum mean value in first of time interval T, l value are 1 natural number for arriving s, pressure
The total strong point number of driver workload actual road test after contracting is identical as the total strong point number that driver workload simulator is tested,
[] is to be rounded symbol in formula.
The prefixed time interval is that T value is 30 seconds.
Compared with prior art, through the above design, the present invention can be brought the following benefits:
The invention proposes a kind of EEG power spectrum mean value compression methods for driver workload comparative study, pass through comparison
Test obtains actual road test and simulator test drive people's EEG power spectrum mean value is obtained according to the duration of two groups of obtained data
Compression ratio is taken, according to the compression ratio of acquisition, using integral recombination compression method to actual road test and simulator test drive human brain electricity
That longer group of duration is compressed in power spectrum mean value, keeps compressed duration identical with another group, through overcompression, can be easy
Ground finds the relationship between them numerically, and then obtains the relationship between simulator test and actual road test, i.e., to simulation
Device test compares research with actual road test driver workload and provides reliable ensure.
Detailed description of the invention
The invention will be further described with specific embodiment for explanation with reference to the accompanying drawing:
Fig. 1 is a kind of schematic diagram of the EEG power spectrum mean value compression method for driver workload comparative study of the present invention.
Fig. 2 is EEG power spectrum mean value compression method schematic diagram of the present invention.
Fig. 3 is driver workload actual road test EEG power spectrum mean value figure of the present invention.
Fig. 4 is driver workload simulation test EEG power spectrum mean value figure of the present invention.
Fig. 5 is to simulate after a kind of EEG power spectrum mean value compression method for driver workload comparative study of the present invention compresses
Device test and actual road test EEG power spectrum mean value comparison diagram.
Specific embodiment
As shown in Figure 1, Figure 2, shown in Fig. 3, Fig. 4 and Fig. 5, the invention proposes a kind of brains applied to driver workload comparative study
Electrical power composes mean value compression method, specifically includes the following steps:
Step 1: it is as follows to obtain driver's EEG power spectrum mean value by the test of driver workload simulator and actual road test:
If time interval is T, and is consistent in driver workload actual road test and the test of driver workload simulator, this reality
It applies T in example to take 30 seconds, driver workload actual road test duration tRoad=nT, n are driver workload actual road test driver's EEG power spectrum
The total strong point number of mean value, n=90 obtain 90 driver workload actual road test driver's EEG power spectrum mean values a, aiIt indicates
Driver workload actual road test driver's EEG power spectrum mean value in i-th prefixed time interval 30 seconds, i value are 1 to 90;It drives
Load simulation device tests duration tSimulator=sT, s are the total data of driver workload simulator test drive person EEG power spectrum mean value
Point number, s=150 obtain 150 driver workload simulator test drive person EEG power spectrum mean value b, bjJ-th of expression pre-
If driver workload simulator test drive person's EEG power spectrum mean value in time interval 30 seconds, j value is 1 to 150, from the above, it can be seen that
tSimulator> tRoad,
Step 2: be 90 according to the total strong point number of actual road test EEG power spectrum mean value in step 1, simulator examination
Testing EEG power spectrum mean value sum strong point number is 150 and tSimulator> tRoadCondition determines that compression ratio isPass through pressure
The total strong point number of contracting, the EEG power spectrum mean value of simulator test can be changed to,Compression
Driver workload simulator tests duration t ' afterwardsSimulator=nT=tRoad, and then achieve the purpose that unified two groups of test durations;
Step 3: carrying out unified driver workload actual road test and the test duration processing of driver workload simulator through step 2
Afterwards, equal to 150 driver workload simulator test drive person's EEG power spectrums are obtained in step 1 using integral recombination compression method
Value is compressed, the specific steps are as follows:
I, presetting f (x)=b, x are time point in prefixed time interval 30 seconds in time coordinate, unit be " time/
30 seconds ".B is driver workload simulator test drive person's EEG power spectrum mean value in prefixed time interval 30 seconds, when x takes 0, f (0)
=b0, b0For driver workload simulator test drive person's EEG signals original state, f (xj)=bj, i.e. f (xj) it is j-th of time
Driver workload simulator test drive person's EEG power spectrum mean value in interval 30 seconds, xjValue is natural number;
II, according to compression ratioBy following formula to 150 driver workload simulator test drive person's brain electric works
Rate spectrum mean value is compressed, and compressed 90 driver workloads simulator test drive person's EEG power spectrum mean value c, c are obtainedkTable
Show that driver workload simulator test drive person's EEG power spectrum mean value, k value are 1 to 90 in k-th of time interval T after compressing
Natural number, the total strong point number of compressed driver workload simulator test and the total strong point of driver workload actual road test
Number is identical,
[] is to be rounded symbol in formula.
If Fig. 3 and Fig. 4 is driver's electroencephalogram power that original driver workload actual road test and driver workload simulator are tested
Compose mean value figure, it is easy to see that driver's EEG power spectrum mean data length of the two is different, but be difficult with the naked eye to find out two
Person has any relationship, after compression method proposed by the present invention, obtains compressed driver workload simulator test brain electric work
Rate spectrum mean value figure is compared with driver workload actual road test EEG power spectrum mean value figure again, as shown in figure 5, from Fig. 5 not only
Compressed driver workload simulator test EEG power spectrum mean data and driver workload actual road test brain can be clearly seen
Electrical power spectrum mean data has similar lifting trend, can also be easier the relationship sought Er Zhe quantitatively, obtain two
The functional relation of person obtains driver workload simulator test EEG power spectrum mean data and the road test of driver workload road in turn
The functional relation between EEG power spectrum mean data is tested, simulator test is compared with actual road test driver workload and is ground
The reliable guarantee of offer is provided.
Claims (2)
1. a kind of EEG power spectrum mean value compression method for driver workload comparative study, which is characterized in that including following step
It is rapid:
Step 1: obtaining driver workload actual road test and driver workload simulator test drive person's EEG power spectrum mean value;
Prefixed time interval is T, and is consistent in driver workload actual road test and the test of driver workload simulator, is driven negative
Lotus actual road test duration tRoad=nT, n are the total strong point number of driver workload actual road test driver EEG power spectrum mean value, n
For the natural number greater than 3, n driver workload actual road test driver's EEG power spectrum mean value a, a are obtainediIt indicates to preset for i-th
Driver workload actual road test driver EEG power spectrum mean value in time interval T, i value are 1 natural number for arriving n;Driver workload
Simulator tests duration tSimulator=sT, s are the total strong point of driver workload simulator test drive person EEG power spectrum mean value
Number, s are the natural number greater than 3, obtain s driver workload simulator test drive person's EEG power spectrum mean value b, bjIndicate jth
Driver workload simulator test drive person's EEG power spectrum mean value in a prefixed time interval T, j value are 1 natural number for arriving s;
Step 2: the driver workload actual road test duration t obtained according to step 1RoadDuration is tested with driver workload simulator
tSimulator, obtain driver workload actual road test duration tRoadDuration t is tested with driver workload simulatorSimulatorCompression ratio, it is unified to drive
Load actual road test and driver workload simulator test duration, specific as follows:
tSimulator> tRoad, then compression ratio beAccording to t in step 1Simulator=sT and tRoad=nT, compression ratio arePass through compression processing driver workload simulator test drive person's EEG power spectrum mean value
Total strong point number isDriver workload simulator tests duration t ' after compressionSimulator=nT=tRoad;
tSimulator< tRoad, then compression ratio beAccording to t in step 1Simulator=sT and tRoad=nT, compression ratio arePass through the total of compression processing driver workload actual road test driver's EEG power spectrum mean value
Data point number isDriver workload actual road test duration t ' after compressionRoad=sT=tSimulator;
Step 3: after step 2 carries out unified driver workload actual road test and the test duration processing of driver workload simulator,
In t 'Simulator=tRoadUnder the conditions of, s driver workload simulator of acquisition in step 1 is tested using integral recombination compression method
Driver's EEG power spectrum mean value b compresses, the specific steps are as follows:
I, presetting f (x)=b, x are the time point in time coordinate in prefixed time interval T, and b is to drive in prefixed time interval T
Sail load simulation device test drive person's EEG power spectrum mean value, when x takes 0, f (0)=b0, b0It is driven for the test of driver workload simulator
The person's of sailing EEG signals original state, f (xj)=bj, i.e. f (xj) it is driver workload simulator test drive in j-th of time interval T
Member's EEG power spectrum mean value, xjValue is natural number;
II, according to compression ratioBy following formula to s driver workload simulator test drive person's EEG power spectrum mean value b
It is compressed, obtains compressed n driver workload simulator test drive person's EEG power spectrum mean value c, ckAfter indicating compression
Driver workload simulator test drive person's EEG power spectrum mean value in k-th of time interval T, k value are 1 natural number for arriving n, pressure
The total strong point number of driver workload simulator test after contracting is identical as the total strong point number of driver workload actual road test,
[] is to be rounded symbol in formula;
In t 'Road=tSimulatorUnder the conditions of, n driver workload actual road test of acquisition in step 1 is driven using integral recombination compression method
The person's of sailing EEG power spectrum mean value a is compressed, the specific steps are as follows:
I, presetting f (x)=a, x are the time point in time coordinate in prefixed time interval T, and a is to drive in prefixed time interval T
Sail load actual road test driver's EEG power spectrum mean value, when x takes 0, f (0)=a0, a0For driver workload actual road test driver
EEG signals original state, f (xi)=ai, i.e. f (xi) it is driver workload actual road test driver brain electricity in i-th of time interval T
Power spectrum mean value, xiValue is natural number;
II, according to compression ratioBy following formula to n driver workload actual road test driver's EEG power spectrum mean value into
Row compression, obtains compressed s driver workload actual road test driver's EEG power spectrum mean value d, dlIt indicates after compressing first
Driver workload simulator test drive person EEG power spectrum mean value in time interval T, l value is 1 natural number for arriving s, after compression
Driver workload actual road test total strong point number it is identical as the total strong point number that driver workload simulator is tested,
[] is to be rounded symbol in formula.
2. a kind of EEG power spectrum mean value compression method for driver workload comparative study according to claim 1,
Be characterized in that: the prefixed time interval is that T value is 30 seconds.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710462934.0A CN107273856B (en) | 2017-06-19 | 2017-06-19 | A kind of EEG power spectrum mean value compression method for driver workload comparative study |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710462934.0A CN107273856B (en) | 2017-06-19 | 2017-06-19 | A kind of EEG power spectrum mean value compression method for driver workload comparative study |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107273856A CN107273856A (en) | 2017-10-20 |
CN107273856B true CN107273856B (en) | 2019-08-20 |
Family
ID=60069019
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710462934.0A Expired - Fee Related CN107273856B (en) | 2017-06-19 | 2017-06-19 | A kind of EEG power spectrum mean value compression method for driver workload comparative study |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107273856B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102133100A (en) * | 2011-03-04 | 2011-07-27 | 上海交通大学 | Sparse representation-based electroencephalogram signal detection method |
US8690748B1 (en) * | 2010-08-02 | 2014-04-08 | Chi Yung Fu | Apparatus for measurement and treatment of a patient |
CN205144580U (en) * | 2015-11-05 | 2016-04-13 | 西南交通大学 | Wearable driver EEG signal mining head area |
-
2017
- 2017-06-19 CN CN201710462934.0A patent/CN107273856B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8690748B1 (en) * | 2010-08-02 | 2014-04-08 | Chi Yung Fu | Apparatus for measurement and treatment of a patient |
CN102133100A (en) * | 2011-03-04 | 2011-07-27 | 上海交通大学 | Sparse representation-based electroencephalogram signal detection method |
CN205144580U (en) * | 2015-11-05 | 2016-04-13 | 西南交通大学 | Wearable driver EEG signal mining head area |
Non-Patent Citations (1)
Title |
---|
疲劳驾驶识别中的脑电信号特征选择算法和支持向量机模型研究;谢宏等;《中国生物医学工程学报》;20140831;第33卷(第4期);482-486 |
Also Published As
Publication number | Publication date |
---|---|
CN107273856A (en) | 2017-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105956624B (en) | Mental imagery brain electricity classification method based on empty time-frequency optimization feature rarefaction representation | |
CN109299751B (en) | EMD data enhancement-based SSVEP electroencephalogram classification method of convolutional neural model | |
CN104706349B (en) | Electrocardiosignal construction method based on pulse wave signals | |
CN107007278A (en) | Sleep mode automatically based on multi-parameter Fusion Features method by stages | |
CN107157477A (en) | EEG signals Feature Recognition System and method | |
CN109657642A (en) | A kind of Mental imagery Method of EEG signals classification and system based on Riemann's distance | |
CN103472922A (en) | Destination selecting system based on P300 and SSVEP (Steady State Visual Evoked Potential) hybrid brain-computer interface | |
CN103955270B (en) | Character high-speed input method of brain-computer interface system based on P300 | |
CN104571504B (en) | A kind of online brain-machine interface method based on Imaginary Movement | |
CN1803122A (en) | Method for producing rehabilitation exerciser controlling order using imagination movement brain wave | |
CN103750844A (en) | Identification method based on EEG phase synchronization | |
CN113205074A (en) | Gesture recognition method fusing multi-mode signals of myoelectricity and micro-inertia measurement unit | |
CN106175754A (en) | During sleep state is analyzed, waking state detects device | |
CN105942975A (en) | Stable state visual sense induced EEG signal processing method | |
CN113158964A (en) | Sleep staging method based on residual learning and multi-granularity feature fusion | |
CN105843377A (en) | Hybrid brain-computer interface based on asynchronous parallel induction strategy | |
CN107273856B (en) | A kind of EEG power spectrum mean value compression method for driver workload comparative study | |
CN104536572A (en) | Cross-individual universal type brain-computer interface method based on event related potential | |
CN113080900B (en) | Human body stress response testing method and system in sudden noise environment | |
Huang et al. | Empirical mode decomposition improves detection of SSVEP | |
CN106843509A (en) | A kind of brain machine interface system | |
CN103399627A (en) | Brain-machine interface paradigm based on frequency conversion flickering stimulation | |
CN109814720A (en) | A kind of brain control method and system of equipment | |
CN111973184B (en) | Model training data optimization method for nonideal sEMG signals | |
CN109002798A (en) | It is a kind of singly to lead visual evoked potential extracting method based on convolutional neural networks |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190820 Termination date: 20200619 |