Intelligent driving fatigue evaluation system and method

Abstract

The invention discloses an intelligent driving fatigue evaluation method and system, and relates to the technical field of automobile safety, and the method comprises the steps: obtaining the physiological data of a driver in a driving scene; the physiological data comprises myoelectricity data, heart rate data and respiratory rate data; calculating a driving fatigue evaluation index according to the physiological data; the driving fatigue evaluation indexes comprise physical load, alertness and cognitive load; and according to the driving fatigue evaluation index, calculating a fatigue driving comprehensive evaluation index by adopting a weight method. According to the method, psychological fatigue and physiological fatigue are comprehensively considered, and from three dimensions of physical load, alertness and cognitive load, indexes such as an electromyographic signal root-mean-square value, an electromyographic signal integral value, a heart rate mean value, a root-mean-square value of a whole-course adjacent NN interval difference, a ratio of heart rate variability low-frequency power to heart rate variability high-frequency power and heart rate breathing cross consistency are synthesized; the driving fatigue evaluation is carried out by adopting a weight method, so that the accuracy and objectivity of the driving fatigue evaluation can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of automobile safety technology, and in particular to an intelligent driving fatigue evaluation method and system. Background Art

[0002] Road traffic accidents are a major threat to life safety, resulting in a large number of casualties and huge property losses. Driving fatigue is an important factor inducing road traffic accidents. While intelligent driving is being realized, due to the lack of attention paid to smart cockpits, there is no standardized evaluation system and assessment method for fatigue driving during driving. Fatigue during driving can be divided into two categories: (1) Psychological fatigue: mental fatigue caused by long-term monotonous, repetitive work or continuous high-intensity cognitive load. (2) Physiological fatigue: decreased work ability, manifested as muscle soreness, fatigue, and weakness. Driving fatigue is usually a mixed fatigue caused by the combined effects of psychological and physiological fatigue.

[0003] At present, some existing driving fatigue detection or evaluation technologies are based on external behavioral characteristics of people, such as blinking, bowing, hand grip, etc.; some are based on vehicle driving status, such as speed, lateral deviation, etc., but these methods are difficult to directly and accurately understand the psychological and physiological characteristics of drivers, resulting in low accuracy of driving fatigue detection results; some are based on human physiological signals, such as EEG signals and heart rate, but most of them are based on individual human physiological signals, which is not comprehensive enough, and driving fatigue evaluation still has the problem of low accuracy. Therefore, there is an urgent need for a complete and scientific evaluation index system and an effective evaluation method to evaluate intelligent cockpit fatigue driving. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent driving fatigue evaluation method and system, which evaluates driving fatigue from two dimensions: psychological fatigue and physiological fatigue, so as to achieve the purpose of accurate and objective evaluation.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] In a first aspect, the present invention provides an intelligent driving fatigue evaluation method, the method comprising:

[0007] Acquiring physiological data of a driver in a driving scenario; the physiological data includes electromyography data, heart rate data, and respiratory rate data;

[0008] A driving fatigue evaluation index is calculated according to the physiological data; the driving fatigue evaluation index includes a driving fatigue evaluation index representing physiology and a driving fatigue evaluation index representing psychology; wherein the driving fatigue evaluation index representing physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index representing psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of the difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents the interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency;

[0009] According to the driving fatigue evaluation indicators, the weighted method is used to calculate the comprehensive evaluation index of fatigue driving.

[0010] Optionally, the calculation formula of the electromyographic signal integral value iEMG is:

[0011]

[0012] Where Fs is the sampling frequency, EMG i represents the amplitude of the i-th electromyographic signal, and N is the number of electromyographic signal amplitude data.

[0013] Optionally, the ratio of low frequency power to high frequency power of heart rate variability LF / HF is calculated using the following formula:

[0014] LF=Sum(FFT(RR))| 0.04～0.15Hz ,

[0015] HF=Sum(FFT(RR))| 0.15～0.4Hz ,

[0016] Wherein, LF is the low frequency power of heart rate variability, HF is the high frequency power of heart rate variability, Sum() represents a summation operation, FFT() represents a fast Fourier transform operation, and RR represents the heartbeat interval.

[0017] Optionally, the heart rate-breathing cross-consistency coefficient CPC is calculated using the following formula:

[0018]

[0019] Among them, HR is heart rate, Resp is respiratory rate, Cross() means calculating the cross correlation between signals, and Coherence() means calculating the coherence between signals.

[0020] Optionally, a weighting method is used to calculate a comprehensive evaluation index of fatigue driving based on the driving fatigue evaluation index, specifically including:

[0021] The fatigue driving comprehensive evaluation index A is calculated using the following formula:

[0022] A=μ1A1+μ2A2+μ3A3+μ4A4+μ5A5+μ6A6,

[0023] Among them, A1 is the root mean square value of the electromyographic signal, A2 is the integral value of the electromyographic signal, A3 is the root mean square value of the difference between adjacent NN intervals throughout the whole process, A4 is the ratio of low-frequency power to high-frequency power of heart rate variability, A5 is the mean heart rate, and A6 is the cross-consistency coefficient of heart rate and breathing; μ1, μ 12 ,…,μ6 are the weight coefficients of A1,A2,…,A6 respectively.

[0024] Optionally, the weight coefficients μ1-μ6 are calculated as follows:

[0025]

[0026] Among them, μ i is the i-th driving fatigue evaluation index A i The weight coefficient of i is the weight of the i-th driving fatigue evaluation index determined by the hierarchical analysis method; w i is the weight of the i-th driving fatigue evaluation index determined by the entropy weight method; N is the total number of driving fatigue evaluation indicators.

[0027] Optionally, the process of using the analytic hierarchy process to determine the weight coefficient of the i-th driving fatigue evaluation index is as follows:

[0028] The priority relationship quantity scaling method is used to score the relative importance of each driving fatigue evaluation index and obtain the judgment matrix;

[0029] Normalize the judgment matrix by column, and add the normalized judgment matrix by row to obtain the sum vector M i , i represents the i-th driving fatigue evaluation index;

[0030] The weight coefficient W of the i-th driving fatigue evaluation index is calculated according to the following formula: i :

[0031]

[0032] Optionally, before executing the step of normalizing the judgment matrix by columns, the method further includes:

[0033] If the number of the driving fatigue evaluation indicators is greater than 2, a consistency check is performed on the judgment matrix; if the judgment matrix fails the consistency check, the judgment matrix is ​​modified and the consistency check is performed again until the judgment matrix passes the consistency check;

[0034] If the number of the driving fatigue evaluation indicators is less than or equal to 2, jump to the step of normalizing the judgment matrix by column.

[0035] Optionally, the process of determining the weight coefficient of the i-th driving fatigue evaluation index by using the entropy weight method is:

[0036] The original data of each driving fatigue evaluation index is standardized to obtain the unit data of each driving fatigue evaluation index, and the information entropy value and information utility value of each driving fatigue evaluation index are calculated according to the following formula:

[0037]

[0038] d i =1-e i ,

[0039] Among them, e i is the information entropy value of the i-th driving fatigue evaluation index, d i is the information utility value of the i-th driving fatigue evaluation index, m* is the number of original data of a single driving fatigue evaluation index, Y ti is the tth unit data of the i-th driving fatigue evaluation index;

[0040] The weight coefficient wi of the i-th driving fatigue evaluation index determined by the entropy weight method is calculated according to the following formula:

[0041]

[0042] In a second aspect, the present invention provides an intelligent driving fatigue evaluation system, comprising:

[0043] A physiological data acquisition module, used to acquire the physiological data of the driver; the physiological data includes electromyography data, heart rate data and respiratory rate data;

[0044] A driving fatigue evaluation index calculation module, used for calculating a driving fatigue evaluation index according to the physiological data; the driving fatigue evaluation index includes a driving fatigue evaluation index representing physiology and a driving fatigue evaluation index representing psychology; wherein the driving fatigue evaluation index representing physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index representing psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of the difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents an interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency;

[0045] The fatigue driving comprehensive evaluation module is used to calculate the fatigue driving comprehensive evaluation index based on the driving fatigue evaluation indicators using a weighting method.

[0046] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0047] Compared with the prior art, when evaluating driving fatigue, the indirect method based on people's external behavioral characteristics or vehicle driving status, or the method based on individual human physiological signals, has the defect of low accuracy. The present invention comprehensively considers psychological fatigue and physiological fatigue, starting from the three dimensions of physical load, alertness and cognitive load, and comprehensively considers indicators such as the root mean square value of electromyographic signals, the integral value of electromyographic signals, the mean heart rate, the root mean square value of the difference between adjacent NN intervals throughout the whole process, the ratio of low-frequency power to high-frequency power of heart rate variability, and heart rate-breathing cross-consistency, and adopts a weighted method to evaluate driving fatigue, which can effectively improve the accuracy and objectivity of driving fatigue evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 A flow chart of an intelligent driving fatigue evaluation method provided by an embodiment of the present invention;

[0050] Figure 2 An evaluation index system diagram provided for an embodiment of the present invention;

[0051] Figure 3 An intelligent driving fatigue evaluation model diagram based on the driver's physiological and psychological reactions is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] The purpose of the present invention is to provide an intelligent driving fatigue evaluation method and system.

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] Embodiment 1

[0056] See also Figure 1 and Figure 2 , this embodiment provides an intelligent driving fatigue evaluation method, the method comprising:

[0057] Step 100: Acquire physiological data of a driver in a driving scenario; the physiological data includes electromyography data, heart rate data, and respiratory rate data;

[0058] Step 200: Calculating a driving fatigue evaluation index according to the physiological data; the driving fatigue evaluation index includes a driving fatigue evaluation index representing physiology and a driving fatigue evaluation index representing psychology; wherein the driving fatigue evaluation index representing physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index representing psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of a difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents an interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency;

[0059] Step 300: Calculate the fatigue driving comprehensive evaluation index using a weighting method based on the driving fatigue evaluation index.

[0060] In this embodiment, the design of the intelligent cockpit fatigue driving evaluation index is based on physiology and psychology, and characterizes the driver's overall fatigue condition from three dimensions: physical load, alertness, and cognitive load. By fusion of multiple indicators, an intelligent cockpit fatigue driving evaluation model based on the driver's physiological and psychological reactions is constructed.

[0061] In the process of selecting various evaluation indicators, the physiological data indicators of the driving process are compared with various indicators under natural conditions, and screened according to the principles of significance, specificity and effectiveness.

[0062] Figure 2 In the table, the symbols “+” and “-” below each indicator indicate positive correlation and negative correlation.

[0063] In some embodiments, in step 200, the calculation formula of the electromyographic signal integral value iEMG is:

[0064]

[0065] Where Fs is the sampling frequency, EMG irepresents the amplitude of the i-th electromyographic signal, and N is the number of electromyographic signal amplitude data.

[0066] In some embodiments, in step 200, the calculation formula of the root mean square value RMS of the electromyographic signal is:

[0067]

[0068] Physical load is measured by the root mean square value (RMS) and the integrated electromyographic value (IEMGM) of the electromyographic signal. The electromyographic signal (EMG) is the superposition of the action potentials of the motor units in many muscle fibers in time and space. The surface electromyographic signal (sEMG) is the combined effect of the superficial muscle EMG and the electrical activity on the nerve trunk on the skin surface, which can reflect the neuromuscular activity to a certain extent. As a non-destructive real-time measurement method, surface electromyography technology can objectively reflect the muscle activity level and functional state, and also has important practical value in driving physiological fatigue. Among them, RMS and iEMG can effectively characterize the dynamic changes of physiological fatigue.

[0069] The root mean square value (RMS) of the electromyographic signal refers to the effective value of muscle discharge. Its size changes depend on the change of the electromyographic amplitude, reflecting the average level of muscle discharge within a certain period of time. From the initial state to the fatigue state, the amplitude of the surface electromyographic signal will increase, that is, as fatigue increases, the RMS increases, which is positively correlated with physical load.

[0070] The integrated value of electromyographic signal (iEMG) refers to the total discharge of motor units involved in muscle activity within a certain period of time. Generally, the larger the amplitude, the greater the degree of fatigue. It is an important indicator for evaluating muscle fatigue and is positively correlated with physical load.

[0071] In some embodiments, the ratio of low frequency power to high frequency power of heart rate variability LF / HF is calculated using the following formula:

[0072] LF=Sum(FFT(RR))| 0.04～0.15Hz , (3);

[0073] HF=Sum(FFT(RR))| 0.15～0.4Hz , (4);

[0074] Among them, LF is the low-frequency power of heart rate variability, HF is the high-frequency power of heart rate variability, Sum() represents the summation operation, FFT() represents the fast Fourier transform operation, RR is the heartbeat interval, and the RR interval represents the time interval between two adjacent heart beats (R waves), usually in milliseconds (ms).

[0075] FFT(RR) refers to analyzing heart beat time interval data by fast Fourier transform in order to convert it into a frequency spectrum to study the frequency domain characteristics of heart rate variability.

[0076] Sum()|0.04~0.15 indicates that the frequency range of LF is not fixed, and usually includes a frequency range between 0.04 Hz and 0.15 Hz.

[0077] In some embodiments, in step 200, the calculation formula of the heart rate mean HR is:

[0078]

[0079] Among them, HR i is the heart rate of the ith minute, N is the number of heart rate data groups, and each minute of heart rate data is a group.

[0080] In some embodiments, in step 200, the root mean square value RMSSD of the difference between adjacent NN intervals throughout the process is calculated as:

[0081]

[0082] Among them, RR i , RR i+1 They are the i-th and i+1-th heartbeat intervals respectively; N is the number of heartbeat interval data.

[0083] The alertness is measured by heart rate mean, RMSSD, and LF / HF. Since the autonomic activity of the heart is controlled by the autonomous regulation of its sympathetic and parasympathetic nerves, heart rate variability (HRV) contains rich information about the human body's cardiovascular autonomic balance regulation. Characteristic indicators that can characterize the physiological information of the person being tested are extracted from this regulation information. The change in heart rate is closely related to the physiological fatigue and arousal level of the human body. Heart rate (HR) and heart rate variability (HRV) are the two most commonly used indicators in current fatigue detection research.

[0084] Mean heart rate (MeanHR) refers to the number of heart beats per minute and is positively correlated with alertness.

[0085] RMSSD is a time domain indicator of heart rate variability (HRV), which refers to the root mean square value of the difference between adjacent NN intervals throughout the entire process. It reflects the fast-changing component of HRV, characterizes the parasympathetic nerve activity, and is negatively correlated with alertness.

[0086] LF / HF is a frequency domain indicator of heart rate variability (HRV), which refers to the ratio of low-frequency power to high-frequency power of HRV. It is an indicator of the balance between the sympathetic nerves and the vagus nerves. It is positively correlated with sympathetic nerve activity, positively correlated with alertness, and negatively correlated with cognitive load.

[0087] In some embodiments, in step 200, the calculation formula of the heart rate breathing cross consistency coefficient CPC is:

[0088]

[0089] Among them, HR is heart rate, Resp is respiratory rate, Cross() means calculating the cross correlation between signals, and Coherence() means calculating the coherence between signals.

[0090] Cognitive load is measured using LF / HF and heart rate-breathing cross consistency (CPC). Heart rate-breathing cross consistency represents the driver's relaxation state during driving. The more relaxed the driver is, the lower the psychological load.

[0091] The heart rate-respiration cross-consistency coefficient (CPC) refers to the consistency of the heart rate and respiratory rate rhythm in the awake state, which represents the psychological load of the driver. The higher the cardiorespiratory consistency value, the higher the user's attention level, which means that the user occupies more attention resources and is more focused on something, which means that the cognitive load is higher. This indicator is positively correlated with cognitive load.

[0092] In some embodiments, step 300 calculates the fatigue driving comprehensive evaluation index using a weighting method according to the driving fatigue evaluation index, specifically including:

[0093] The fatigue driving comprehensive evaluation index A is calculated using the following formula:

[0094] A=μ1A1+μ2A2+μ3A3+μ4A4+μ5A5+μ6A6, (8);

[0095] Among them, A1 is the root mean square value of the electromyographic signal, A2 is the integral value of the electromyographic signal, A3 is the root mean square value of the difference between adjacent NN intervals throughout the whole process, A4 is the ratio of low-frequency power to high-frequency power of heart rate variability, A5 is the mean heart rate, and A6 is the cross-consistency coefficient of heart rate and breathing; μ1, μ 12 ,…,μ6 are the weight coefficients of A1,A2,…,A6 respectively.

[0096] In some embodiments, the weight coefficients μ1-μ6 are calculated as follows:

[0097]

[0098] Among them, μ i is the i-th driving fatigue evaluation index A i The weight coefficient of i is the weight of the i-th driving fatigue evaluation index determined by the hierarchical analysis method; w i is the weight of the i-th driving fatigue evaluation index determined by the entropy weight method; N is the total number of driving fatigue evaluation indicators.

[0099] This embodiment adopts the AHP entropy method for comprehensive weighting (combining the weighting of the analytic hierarchy process with the entropy method for combined weighting) to evaluate and form a fatigue driving safety risk for the smart cockpit based on physiological and psychological factors. The higher the index value, the higher the degree of physiological and psychological fatigue of the driver and the lower the safety level.

[0100] In some embodiments, the process of determining the weight coefficient of the i-th driving fatigue evaluation index by using the hierarchical analysis method is as follows:

[0101] The priority relationship quantity scaling method is used to score the relative importance of each driving fatigue evaluation index and obtain the judgment matrix;

[0102] Normalize the judgment matrix by column, and add the normalized judgment matrix by row to obtain the sum vector M i , i represents the i-th driving fatigue evaluation index;

[0103] The weight coefficient W of the i-th driving fatigue evaluation index is calculated according to the following formula: i :

[0104]

[0105] Wherein, N is the total number of driving fatigue evaluation indicators.

[0106] In some embodiments, the process of determining the weight coefficient of the i-th driving fatigue evaluation index by using the hierarchical analysis method further includes:

[0107] The priority relationship quantitative scaling method is used to score the relative importance of each driving fatigue evaluation index. The quantitative scale is given by 0.1 to 0.9 as shown in Table 2. The expert scoring method is used to assign importance to the six indicators of F1-root mean square electromyography value, F2-integral electromyography value, F3-RMSSD, F4-LF / HF, F5-heart rate mean and F6-heart rate breathing cross consistency coefficient. The matrix is ​​assigned values ​​to obtain the judgment matrix A described in Table 1:

[0108] Table 1 Judgment Matrix A

[0109] <![CDATA[F1]]> <![CDATA[F2]]> <![CDATA[F3]]> <![CDATA[F4]]> <![CDATA[F5]]> <![CDATA[F6]]> <![CDATA[F1]]> <![CDATA[A 11 ]]> <![CDATA[A 12 ]]> <![CDATA[A 13 ]]> <![CDATA[A 14 ]]> <![CDATA[A 15 ]]> <![CDATA[A 16 ]]> <![CDATA[F2]]> <![CDATA[A 21 ]]> <![CDATA[A 22 ]]> <![CDATA[A 23 ]]> <![CDATA[A 24 ]]> <![CDATA[A 25 ]]> <![CDATA[A 26 ]]> <![CDATA[F3]]> <![CDATA[A 31 ]]> <![CDATA[A 32 ]]> <![CDATA[A 33 ]]> <![CDATA[A 34 ]]> <![CDATA[A 35 ]]> <![CDATA[A 36 ]]> <![CDATA[F4]]> <![CDATA[A 41 ]]> <![CDATA[A 42 ]]> <![CDATA[A 43 ]]> <![CDATA[A 44 ]]> <![CDATA[A 45 ]]> <![CDATA[A 46 ]]> <![CDATA[F5]]> <![CDATA[A 51 ]]> <![CDATA[A 52 ]]> <![CDATA[A 53 ]]> <![CDATA[A 54 ]]> <![CDATA[A 55 ]]> <![CDATA[A 56 ]]> <![CDATA[F6]]> <![CDATA[A 61 ]]> <![CDATA[A 62 ]]> <![CDATA[A 63 ]]> <![CDATA[A 64 ]]> <![CDATA[A 65 ]]> <![CDATA[A 66 ]]>

[0110] Table 2 Judgment matrix scale and meaning

[0111]

[0112]

[0113] After the judgment matrix A is obtained through the above method, the matrix A is normalized by columns, and then the rows are averaged to obtain the weight coefficients.

[0114] For example, the matrix A = [a ij ] N×N , where N is the number of driving fatigue evaluation indicators (number of elements, the same below). The matrix A is normalized as follows:

[0115]

[0116] Add the normalized judgment matrix row by row to get the sum vector M i , as shown below,

[0117]

[0118] Then, perform row averaging according to formula (10) to obtain the weight coefficient W i .

[0119] In some embodiments, before executing the step of normalizing the judgment matrix by columns, the method further includes:

[0120] If the number of the driving fatigue evaluation indicators is greater than 2, a consistency check is performed on the judgment matrix; if the judgment matrix fails the consistency check, the judgment matrix is ​​modified and the consistency check is performed again until the judgment matrix passes the consistency check;

[0121] If the number of the driving fatigue evaluation indicators is less than or equal to 2, jump to the step of normalizing the judgment matrix by column.

[0122] The purpose of performing consistency check on the judgment matrix is ​​to ensure logical consistency.

[0123] In some embodiments, performing consistency check on the judgment matrix further includes:

[0124] The square root method is used to calculate the maximum characteristic root γ of the judgment matrix A max , as shown below:

[0125]

[0126] Among them, A*W i is the characteristic root of the judgment matrix, W i is the weight coefficient of the ith driving fatigue evaluation index, N is the number of driving fatigue evaluation indicators, n is the number of dimensions (same meaning as n in Table 3), and N=n.

[0127] The consistency index CI is calculated according to the following formula, and the average random consistency index CR is obtained according to Table 3:

[0128]

[0129] Table 3 Average random consistency index CR value

[0130] n 3 4 5 6 7 8 9 10 11 CR 0.58 0.9 1.12 1.24 1.32 1.41 1.45 1.49 1.51

[0131] If the following inequality is satisfied, the consistency check is passed. Otherwise, the judgment matrix needs to be modified and the consistency check is repeated until it passes.

[0132]

[0133] In some embodiments, modifying the judgment matrix includes: 1. Modifying the judgment matrix data. For the accumulation of small errors in multiple data items of the judgment matrix: minimize the modification of expert data and fine-tune each element of the matrix; for the judgment error of a certain data item in the judgment matrix: find the element with the highest degree of deviation in the judgment matrix process and make corrections.

[0134] 2. Reduce the order of the judgment matrix.

[0135] In some embodiments, the process of determining the weight coefficient of the i-th driving fatigue evaluation index using the entropy weight method is as follows:

[0136] The original data of each driving fatigue evaluation index is standardized to obtain the unit data of each driving fatigue evaluation index, and the information entropy value and information utility value of each driving fatigue evaluation index are calculated according to the following formula:

[0137]

[0138] d i =1-e i , (17);

[0139] Among them, e i is the information entropy value of the i-th driving fatigue evaluation index, d i is the information utility value of the i-th driving fatigue evaluation index, m * is the number of original data of a single driving fatigue evaluation index, Y ti is the tth unit data of the i-th driving fatigue evaluation index;

[0140] The weight coefficient wi of the i-th driving fatigue evaluation index determined by the entropy weight method is calculated according to the following formula:

[0141]

[0142] The basic idea of ​​the entropy weight method is: if the value of an indicator changes more, the greater the degree of variation of the indicator value, the more information it provides, the smaller the information entropy value, the greater the weight, and vice versa.

[0143] In some embodiments, the tth unit data Y of the i-th driving fatigue evaluation indexti Calculated as follows:

[0144] First, the original driving fatigue evaluation index data is standardized as follows:

[0145]

[0146] where x ti is the original value of the t-th unit data of the i-th driving fatigue evaluation index, x imax is the maximum unit data original value of the i-th driving fatigue evaluation index, x imin is the minimum unit data original value of the i-th driving fatigue evaluation index, Y ti is the t-th unit data of the i-th driving fatigue evaluation index after dimensionless processing, and the definition is standardized as shown in the following formula:

[0147]

[0148] In the formula, m * is the number of original data of a single driving fatigue evaluation index.

[0149] See also Figure 3 In some embodiments, an intelligent driving fatigue evaluation method further includes:

[0150] Design an intelligent cockpit driving simulation experiment based on physiological psychology.

[0151] Construct an intelligent cockpit fatigue driving evaluation index system based on the driver's physiological and psychological reactions.

[0152] Establish an intelligent driving fatigue evaluation method based on the driver's physiological and psychological reactions.

[0153] In some embodiments, the intelligent cockpit driving simulation experiment based on physiological psychology includes:

[0154] (1) The experimental sample consists of 40 drivers with more than 2 years of driving experience and a driver's license level of C2 or above. They are evenly distributed in four age groups: 18-25 years old, 25-35 years old, 35-45 years old, and over 45 years old. The male-to-female ratio is 1:1.

[0155] (2) The experimental equipment consists of a driving simulator and a data acquisition system. The data acquisition system includes an electromyography / electrocardiography device. The electromyography measurement sites are the left and right trapezius muscles and calf muscles, and the electrocardiography measurement sites are the left and right sides of the sternum.

[0156] (3) Drivers participated in two 90-min driving simulation experiments. They got 8 hours of adequate sleep the night before the first experiment and 4 hours of sleep the night before the second experiment, from 03:00 to 07:00. Volunteers wore a bracelet to monitor their sleep time before going to bed. Both experiments started at 9:00 a.m., and chewing gum and making phone calls were not allowed during the experiments. The experimental environment was kept quiet to prevent external stimuli from affecting the driver's state.

[0157] (4) The road environment in the simulator is a closed circular composite road, including urban, rural, highway and mountain roads, with a small number of vehicles on the road. The driver can drive freely without exceeding the speed limit or causing an accident. The experiment was carried out indoors, with air circulation, a constant room temperature of 23°C, and stable and sufficient light.

[0158] Embodiment 2

[0159] This embodiment provides an intelligent driving fatigue evaluation system, including:

[0160] A physiological data acquisition module, used to acquire the physiological data of the driver; the physiological data includes electromyography data, heart rate data and respiratory rate data;

[0161] A driving fatigue evaluation index calculation module, used for calculating a driving fatigue evaluation index according to the physiological data; the driving fatigue evaluation index includes a driving fatigue evaluation index representing physiology and a driving fatigue evaluation index representing psychology; wherein the driving fatigue evaluation index representing physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index representing psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of the difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents an interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency;

[0162] The fatigue driving comprehensive evaluation module is used to calculate the fatigue driving comprehensive evaluation index based on the driving fatigue evaluation indicators using a weighting method.

[0163] In summary, the present invention has the following advantages:

[0164] The intelligent driving fatigue evaluation method based on the physiological and psychological reactions of the driver proposed in this invention achieves the purpose of simultaneously detecting psychological and physiological fatigue during driving. Refined evaluation indicators are selected to form an evaluation system, and the hierarchical analysis method and entropy weight evaluation method are used to form an evaluation method, which largely gets rid of the dependence on indicator data and brings certain reference value to the safety evaluation of fatigue driving in my country's intelligent cockpit of automobiles.

[0165] The present invention is based on an intelligent driving fatigue evaluation based on the driver's physiological and psychological reactions. It characterizes the driver's physiological and psychological behavior characteristics from three dimensions: physical load, alertness, and cognitive load, and constructs an intelligent cockpit fatigue driving evaluation index system, which overcomes the shortcoming of low accuracy of single parameter identification.

[0166] The technical solution provided by the present invention realizes the accurate evaluation of intelligent cockpit fatigue driving, which is beneficial to the promotion and application. It can greatly reduce the incidence of serious traffic accidents caused by intelligent cockpit fatigue driving during driving, and also provides a reference basis for driving safety status monitoring and intelligent cockpit safety design.

[0167] Aiming at the behavior of fatigue driving in the intelligent cockpit, the present invention adopts a method combining subjective and objective factors, and applies the analytic hierarchy process and the entropy weight method to determine the index weights, which is both subjective and reasonable, and objective and accurate.

[0168] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0169] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. An intelligent driving fatigue evaluation method, characterized in that: The method comprises: Acquiring physiological data of a driver in a driving scenario; the physiological data includes electromyography data, heart rate data, and respiratory rate data; A driving fatigue evaluation index is calculated according to the physiological data; the driving fatigue evaluation index includes a driving fatigue evaluation index representing physiology and a driving fatigue evaluation index representing psychology; wherein the driving fatigue evaluation index representing physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index representing psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of the difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents the interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency; According to the driving fatigue evaluation indicators, the weighted method is used to calculate the comprehensive evaluation index of fatigue driving.

2. According to claim 1, the intelligent driving fatigue evaluation method is characterized in that: The calculation formula of the electromyographic signal integral value iEMG is: Where Fs is the sampling frequency, EMG i represents the amplitude of the i-th electromyographic signal, and N is the number of electromyographic signal amplitude data.

3. According to claim 1, the intelligent driving fatigue evaluation method is characterized in that: The ratio of low-frequency power to high-frequency power of heart rate variability (LF / HF) was calculated using the following formula: LF=Sum(FFT(RR))| 0.04～0.15Hz , HF=Sum(FFT(RR))| 0.15～0.4Hz , Wherein, LF is the low frequency power of heart rate variability, HF is the high frequency power of heart rate variability, Sum() represents a summation operation, FFT() represents a fast Fourier transform operation, and RR represents the heartbeat interval.

4. According to claim 1, the intelligent driving fatigue evaluation method is characterized in that: The calculation formula of heart rate breathing cross consistency coefficient CPC is: Among them, HR is heart rate, Resp is respiratory rate, Cross() means calculating the cross correlation between signals, and Coherence() means calculating the coherence between signals.

5. The intelligent driving fatigue evaluation method according to claim 1, characterized in that: According to the driving fatigue evaluation index, the weight method is used to calculate the comprehensive evaluation index of fatigue driving, which includes: The fatigue driving comprehensive evaluation index A is calculated using the following formula: A=μ1A1+μ2A2+μ3A3+μ4A4+μ5A5+μ6A6, Among them, A1 is the root mean square value of the electromyographic signal, A2 is the integral value of the electromyographic signal, A3 is the root mean square value of the difference between adjacent NN intervals throughout the whole process, A4 is the ratio of low-frequency power to high-frequency power of heart rate variability, A5 is the mean heart rate, and A6 is the cross-consistency coefficient of heart rate and breathing; μ1, μ 12 ,…,μ6 are the weight coefficients of A1,A2,…,A6 respectively.

6. The intelligent driving fatigue evaluation method according to claim 5, characterized in that: The calculation formula of weight coefficient μ1-μ6 is: Among them, μ i is the i-th driving fatigue evaluation index A i The weight coefficient of i is the weight of the i-th driving fatigue evaluation index determined by the hierarchical analysis method; w i is the weight of the i-th driving fatigue evaluation index determined by the entropy weight method; N is the total number of driving fatigue evaluation indicators.

7. The intelligent driving fatigue evaluation method according to claim 6, characterized in that: The process of determining the weight coefficient of the i-th driving fatigue evaluation index using the hierarchical analysis method is as follows: The priority relationship quantity scaling method is used to score the relative importance of each driving fatigue evaluation index and obtain the judgment matrix; Normalize the judgment matrix by column, and add the normalized judgment matrix by row to obtain the sum vector M i , i represents the i-th driving fatigue evaluation index; The weight coefficient W of the i-th driving fatigue evaluation index is calculated according to the following formula: i :

8. The intelligent driving fatigue evaluation method according to claim 7, characterized in that: Before executing the step of normalizing the judgment matrix by columns, the method further includes: If the number of the driving fatigue evaluation indicators is greater than 2, a consistency check is performed on the judgment matrix; if the judgment matrix fails the consistency check, the judgment matrix is ​​modified and the consistency check is performed again until the judgment matrix passes the consistency check; If the number of the driving fatigue evaluation indicators is less than or equal to 2, jump to the step of normalizing the judgment matrix by column.

9. The intelligent driving fatigue evaluation method according to claim 6, characterized in that: The process of determining the weight coefficient of the i-th driving fatigue evaluation index using the entropy weight method is as follows: The original data of each driving fatigue evaluation index is standardized to obtain the unit data of each driving fatigue evaluation index, and the information entropy value and information utility value of each driving fatigue evaluation index are calculated according to the following formula: d i =1-e i , Among them, e i is the information entropy value of the i-th driving fatigue evaluation index, d i is the information utility value of the i-th driving fatigue evaluation index, m * is the number of original data of a single driving fatigue evaluation index, Y ti is the tth unit data of the i-th driving fatigue evaluation index; The weight coefficient w of the i-th driving fatigue evaluation index determined by the entropy weight method is calculated according to the following formula: i :

10. An intelligent driving fatigue evaluation system, characterized in that: include: A physiological data acquisition module, used to acquire the physiological data of the driver; The physiological data includes electromyographic data, heart rate data and respiratory rate data; A driving fatigue evaluation index calculation module, used to calculate the driving fatigue evaluation index according to the physiological data; The driving fatigue evaluation index includes a driving fatigue evaluation index that characterizes physiology and a driving fatigue evaluation index that characterizes psychology; wherein the driving fatigue evaluation index that characterizes physiology includes a physical load index; the physical load index includes a root mean square value of an electromyographic signal and an integral value of an electromyographic signal; the driving fatigue evaluation index that characterizes psychology includes an alertness index and a cognitive load index; the alertness index includes a heart rate mean, a root mean square value of the difference between adjacent NN intervals throughout the entire process, and a ratio of low-frequency power to high-frequency power of heart rate variability, wherein the NN interval represents the interval between two adjacent heartbeat fluctuations; the cognitive load index includes a ratio of low-frequency power to high-frequency power of heart rate variability and heart rate-breathing cross-consistency; The fatigue driving comprehensive evaluation module is used to calculate the fatigue driving comprehensive evaluation index based on the driving fatigue evaluation indicators using a weighting method.

Images