An analysis and evaluation method for static driving adaptability of old drivers

Abstract

The application relates to an analysis and evaluation method for static driving adaptability of old drivers, which comprises the following steps: obtaining evaluation indexes of a target driver, normalizing and converging the evaluation indexes to obtain index data; inputting the index data into a driving adaptability evaluation model to obtain a comprehensive evaluation score index output by the driving adaptability evaluation model; and determining an evaluation grade corresponding to the comprehensive evaluation score index in a target preset score interval. The method comprehensively considers multiple driving adaptability indexes, can systematically analyze and evaluate the driving adaptability of the old driver, comprehensively understands the driving adaptability level of the old driver, early discovers potential driving adaptability problems, reduces the risk of driving accidents, promotes safe driving of the old driver, improves driving safety and comfort of the old driver, provides a scientific basis and reference for relevant decisions, and helps management departments and individuals to formulate reasonable driving training and support measures.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driving evaluation analysis, in particular to an analysis and evaluation method for static driving adaptability of old drivers. BACKGROUND

[0002] Driving adaptability detection aims to assess whether an individual has the ability to continue safe driving, which usually includes the assessment of the driver's visual ability, cognitive function, operation skill and other basic abilities related to driving. Through comprehensive assessment, the reaction ability and risk handling ability of the driver in the face of complex traffic environment are determined.

[0003] Currently, different strategies and measures have been taken by countries in the detection of driving adaptability of old drivers, including establishing standardized assessment procedures, popularizing self-assessment tools and providing targeted retraining courses, to help old drivers maintain their driving ability and reduce safety hazards caused by potential cognitive or physiological defects. However, there is a lack of an evaluation method that combines multiple detection indicators for adaptability analysis of old drivers. Because a single driving adaptability detection indicator only reflects the advantages and disadvantages of a driver's driving adaptability in one aspect, there may be large differences in single detection indicators of different drivers. A comprehensive evaluation method is needed to evaluate the driving adaptability of middle-aged and old drivers by combining multiple indicators and considering the influence and degree of each indicator on driving adaptability. SUMMARY

[0004] To solve or partially solve the problems in the related art, the present application provides an analysis and evaluation method for static driving adaptability of old drivers, which provides ideas and solutions for driving adaptability analysis and evaluation of old people, and helps to realize driving adaptability evaluation of old drivers.

[0005] The first aspect of the present application provides an analysis and evaluation method for static driving adaptability of old drivers, comprising the following steps:

[0006] Obtaining evaluation indicators of the target driver, normalizing and converging the evaluation indicators to obtain index data, and the evaluation indicators including night vision, dynamic vision, depth vision, complex reaction and precise operation indicators of the target driver;

[0007] Inputting the index data into a driving adaptability evaluation model to obtain a comprehensive evaluation score index output by the driving adaptability evaluation model, wherein the driving adaptability evaluation model includes a factor analysis method based on a double-base point method and a weighted geometric mean model used as a synthesis model for driving adaptability evaluation;

[0008] Determine the corresponding evaluation level of the comprehensive evaluation score index in the target preset score interval, wherein the driving adaptability comprehensive evaluation standard in the preset score interval is obtained based on the improved K-means clustering algorithm.

[0009] wherein the expression of the driving adaptability evaluation model is:

[0010]

[0011] wherein, represents the first common factor, represents the normalized value of night vision, represents the normalized value of dynamic vision, represents the normalized value of deep vision, represents the normalized value of complex reaction, represents the normalized value of precise operation.

[0012] wherein, the normalized and homogenized processing evaluation index obtains index data including:

[0013] Based on the minimum-maximum standardization method, the evaluation index is normalized to obtain normalized data;

[0014] The normalized data of night vision, complex reaction and precise operation index are obtained as index data;

[0015] and, the normalized data of deep vision and dynamic vision are homogenized as index data.

[0016] wherein, based on the minimum-maximum standardization method, the improved logistic value function is based on the improved logistic value function, and the expression of the improved logistic value function is:

[0017]

[0018] wherein, is the normalized criterion score, and are the mean and standard deviation thereof, and are the mean and standard deviation of the initial value, is a determined parameter.

[0019] wherein, the homogenization processing of deep vision and dynamic vision includes:

[0020] Obtain the normalized data of deep vision and dynamic vision;

[0021] Subtract the normalized data of deep vision from 1 to obtain the deep vision index data of deep vision;

[0022] And, the dynamic visual acuity index data is obtained by subtracting the dynamic visual acuity normalization data from 1.

[0023] The factor analysis method improved based on the double-base point method comprises the following steps:

[0024] Correlation coefficients between the indexes are calculated to construct a correlation coefficient matrix;

[0025] Eigenvalues and eigenvectors of the correlation coefficient matrix are solved, and principal components with eigenvalues greater than 1 are selected as common factors, wherein the number of the highest loading variables is reduced by calculating a loading matrix and a rotated loading matrix;

[0026] The common factor scores of each index are calculated based on the Thomson factor regression method;

[0027] The comprehensive factor scores are calculated, and the comprehensive factor scores are normalized;

[0028] The closeness of each evaluation object to the optimal factor scheme is calculated according to the optimal vector and the worst vector.

[0029] The evaluation grades include a good grade, a general grade and a level-need-to-notice grade, the score interval of the good grade is a first interval, the score interval of the general grade is a second interval, and the score interval of the level-need-to-notice grade is a third interval.

[0030] The technical scheme provided by the present application can include the following beneficial effects:

[0031] The present application provides an analysis and evaluation method for static driving adaptability of old drivers, which comprehensively considers multiple driving adaptability indexes, and can systematically analyze and evaluate the driving adaptability of old drivers by establishing an evaluation system and an evaluation model, so as to comprehensively understand the driving adaptability level of old drivers, discover potential driving adaptability problems as early as possible, reduce the risk of driving accidents, and promote the safe driving of old drivers. The method provides a systematic and comprehensive approach, which can assist in evaluating the driving adaptability of old drivers, help improve the driving safety and comfort of old drivers, provide scientific basis and reference for related decision-making, and help management departments and individuals to develop reasonable driving training and support measures.

[0032] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0033] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings, in which like reference characters refer to like parts throughout the several views, and in which:

[0034] Figure 1 is a flowchart of the analysis and evaluation method shown in the embodiments of the present application;

[0035] Figure 2 is a correlation coefficient diagram of each driving adaptability index of the analysis and evaluation method shown in the embodiments of the present application;

[0036] Figure 3 is a normal P-P diagram of the driving adaptability comprehensive evaluation score index of the analysis and evaluation method shown in the embodiments of the present application;

[0037] Figure 4 is a relationship between the three types of model driving adaptability evaluation scores and the number of accidents of the analysis and evaluation method shown in the embodiments of the present application. DETAILED DESCRIPTION

[0038] Embodiments of the present application will be described in more detail by referring to the attached drawings. Although the embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0039] It should be understood that although the terms "first", "second", "third", etc. can be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information without departing from the scope of the present application. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, the meaning of "a plurality of" is two or more, unless otherwise specifically limited.

[0040] In the description of the present application, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only used to facilitate the description of the present application and simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be understood as limiting the present application.

[0041] Unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0042] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.

[0043] like Figure 1 The method for analyzing and evaluating the static driving adaptability of elderly drivers, as shown, includes the following steps:

[0044] S1. Obtain the evaluation indicators of the target driver, and normalize and converge the evaluation indicators to obtain indicator data.

[0045] Evaluation indicators include the target driver's night vision, dynamic visual acuity, depth vision, complex reaction time, and precision operation. In the field of road traffic safety, statistical analysis of driving adaptability indicators plays an important role in assessing and improving drivers' driving abilities. Night vision, dynamic visual acuity, depth vision, complex reaction time, and precision operation are key elements constituting driving adaptability, directly related to drivers' driving performance and safety risks in different environments and situations.

[0046] Night vision, also known as dark adaptation vision, refers to the ability of the human eye to distinguish details of objects in dark environments. Night vision can be affected by a variety of factors, including environmental factors, eye diseases, or refractive problems

[199] . Night vision usually declines with age, possibly due to factors such as the degeneration of retinal photoreceptor cells and slower pupillary response. According to national standards, the standard for night vision of motor vehicle drivers is less than or equal to 5 seconds. Dark adaptation time is used as an indicator to evaluate night vision, and night vision is tested using a night vision testing instrument.

[0047] Dynamic visual acuity, also known as kinematic visual acuity, refers to the visual acuity tested when one or both the person and the visual target are in motion. It involves the eye's ability to capture moving targets, decompose images, and perceive details. Dynamic visual acuity primarily reflects a driver's sensitivity to identifying external objects while driving. It is tested using a dynamic visual acuity testing instrument, and the standard for night vision for motor vehicle drivers is set at ≥0.2s. Drivers with lower dynamic visual acuity test values ​​also have lower sensitivity to identifying external objects while driving.

[0048] Depth perception, also known as stereoscopic vision or depth awareness, refers to the ability of individuals to perceive the relative distances of objects in three-dimensional space. It is crucial for judging distances and speeds between vehicles. As people age, depth perception may decline, which can lead to problems in activities that require accurate distance judgment, such as driving, walking, or other activities. The national standard specifies the normal value of depth perception for motor vehicle drivers, with -25mm~+25mm for initial examination drivers and -22mm~22mm for in-service drivers. Depth perception is detected using a depth perception detector, with continuous repeated measurements of 5 times, and the average judgment error is taken as the evaluation result. If the measured value of the tested driver is larger, it indicates that his perception ability of space distance is poor, and he is prone to inaccurate position and distance judgment during driving.

[0049] Complex reaction ability, also known as selective reaction ability, involves the ability of individuals to quickly and accurately identify each stimulus when receiving multiple stimuli, and to make different responses according to each stimulus. It requires individuals to have the ability of fast information processing, decision-making, and action execution. In the fields of psychology and physiology, complex reaction ability is usually evaluated through a selective reaction time experiment, in which two or more stimuli are presented, and the subject is required to make different responses to each stimulus, and the required time is recorded. When the test begins, the tested driver sees a yellow pattern and immediately presses the left-hand button, sees a green pattern and immediately presses the right-hand button, sees a red pattern and immediately steps on the right foot pedal, and when he hears a buzzing sound in the earphone, he should not operate regardless of the color of the pattern. The test is practiced 3 times and tested 10 times. The national standard specifies the normal value of complex reaction for motor vehicle drivers, with less than or equal to 8 times for initial examination drivers and less than or equal to 5 times for in-service drivers. If the tested driver makes many mistakes in selective reaction, it indicates that the driver's reaction accuracy is poor when facing complex situations.

[0050] Precise operation ability detection is an important parameter for evaluating whether the tested person can accurately and quickly perform tasks in complex or emergency situations. This indicator usually involves multiple dimensions, including but not limited to reaction time, action accuracy, coordination, and decision-making ability in specific situations. The tested person clicks the start button to control the movement of the ball on the screen, and moves the ball through the narrow channel set by the system. If the ball falls, the test ends. The higher the level the tester passes, the more time-limited the system will be to move the ball to the end within the specified time. If the red dot falls off the channel, the test ends. The national standard specifies the normal value range of operation function for motor vehicle drivers, with less than or equal to 130 times for initial examination drivers and less than or equal to 150 times for in-service drivers. If the tested driver makes many mistakes in operation, in areas with heavy traffic such as urban areas, such drivers are prone to uneven distribution of left and right attention, rapid attention shift, and uncoordinated movements, which can lead to traffic accidents.

[0051] Driving adaptability indicators are directly related to the performance of drivers in complex traffic environment. There is also correlation between each driving adaptability indicator. By analyzing the correlation between driving adaptability indicators including night vision, dynamic vision, depth vision, complex reaction ability and precise operation ability, the interaction between different indicators and their comprehensive influence on driving safety can be revealed.

[0052] Single driving adaptability detection indicators only reflect the advantages and disadvantages of a certain aspect of driving adaptability of drivers. There may be large differences in single detection indicators of different drivers. In order to more comprehensively evaluate the driving adaptability of middle-aged and elderly drivers, the influence of night vision, dynamic vision, depth vision, complex reaction and precise operation indicators should be combined, and the influence and degree of each indicator on driving adaptability should be considered comprehensively.

[0053] 1) Single indicator value range determination

[0054] The standard of night vision of motor vehicle drivers in the People's Republic of China National Standard GB18463-2001 Motor Vehicle Driver Physical Condition and Evaluation Requirements is <=5s.

[0055] The normal value of dynamic vision of motor vehicle drivers in the People's Republic of China National Standard GB18463-2001 Motor Vehicle Driver Physical Condition and Evaluation Requirements is >=0.2s.

[0056] The normal value of depth vision of motor vehicle drivers in the People's Republic of China National Standard GB18463-2001 Motor Vehicle Driver Physical Condition and Evaluation Requirements is -25mm~+25mm for new drivers and -22mm~+22mm for in-service drivers.

[0057] The normal value of complex reaction of motor vehicle drivers in the People's Republic of China National Standard GB18463-2001 Motor Vehicle Driver Physical Condition and Evaluation Requirements is <=8 times for new drivers and <=5 times for in-service drivers.

[0058] The normal value range of operation function of motor vehicle drivers in the People's Republic of China National Standard GB18463-2001 Motor Vehicle Driver Physical Condition and Evaluation Requirements is <=130 times for new drivers and <=110 times for in-service drivers.

[0059] The People's Republic of China National Standard GB18463-2001 Motor Vehicle Drivers Physical Condition and Evaluation Requirements stipulates the normal value range of each indicator of motor vehicle drivers. However, due to the introduction of retirement policy and the adjustment of the upper limit of driving license age, the number of elderly drivers is on the rise, and the physical and cognitive functions of this group of drivers may have declined to varying degrees with age. The applicability of the previous indicator standards to this driving group needs to be verified. Therefore, according to the test data of this driving adaptability test, the normal value range of each indicator is analyzed to determine the normal value range of unilateral and bilateral fraction of middle-aged and elderly drivers, to obtain the value range of night vision, dynamic vision, depth vision, complex reaction and precise operation, as shown in the following table.

[0060] Table 1 Value range of each driving adaptability indicator

[0061] Tab. 1 The value range of each driving adaptability indicators

[0062]

[0063] According to the numerical value of the percentile in the above table, combined with the characteristics of the middle-aged and elderly driver group, the normal value range of each indicator is determined. Night vision reflects the night vision function of the tested driver, and the faster the reaction time of night vision is, the better it is. This paper selects the 80% percentile as the normal value range, and the normal value range of night vision is 9s.

[0064] Dynamic vision can reflect the ability of the tested driver to identify moving objects, and middle-aged and elderly drivers may have difficulty identifying moving objects. This paper selects unilateral 75% percentile or below as the normal value range of dynamic vision, and the normal value range of dynamic vision is 0.3s. Depth vision reflects the longitudinal depth discrimination ability of the tested driver, and this paper selects 90% percentile as the normal value range of depth vision, and the normal value range of depth vision is -42mm~42mm. The number of error reactions in complex reaction can reflect the reaction ability of the tested driver to changes in the external environment, and the fewer the number of error reactions, the shorter the reaction time, and the higher the safety guarantee for driving. This paper selects unilateral 95% percentile of the number of error reactions in complex reaction as the normal value range, and the normal value range of complex reaction is 6 times. Precise operation can reflect the coordination ability and accuracy of the tested driver, and the stronger the operation ability, the more conducive to safe driving. This paper selects 80% percentile as the normal value range, and the normal value range of precise operation is 124 times.

[0065] In order to construct a reasonable driving adaptability evaluation system, the driving adaptability testing indicators formulated in the "Automobile Driver Suitability Testing and Evaluation"

[214] are used as references. These indicators are night vision, dynamic vision, depth vision, complex reaction and precise operation tested in this experiment. At the same time, data processing is carried out according to the "Automobile Driver Suitability Testing and Evaluation"

[215] to construct a driver adaptability evaluation system. The proposed evaluation system includes night vision (Y1), dynamic vision (Y2), depth vision (Y3), complex reaction (Y4) and precise operation (Y5). Except for the dynamic vision indicator, the smaller the value of the other indicators, the better. The mean value of each indicator is taken as the sub-indicator, which is represented as the mean value of night vision (X1), the mean value of dynamic vision (X2), the mean value of depth perception judgment error (X3), the number of false reactions (X4) and the number of false operations (X5).

[0066] The evaluation indicators are based on an improved logistic linear function. To effectively control the magnitude of each normalization criterion score, normalization should consider keeping the standardized scores within a limited range, and the mean of the standardized scores for each indicator should be a constant. Therefore, an improved logistic value function, as shown in equation (1), is introduced to normalize the standard scores, letting... Indicates the first The indicator in the first One standard The criteria are divided to achieve the goal of... arrive Dimensionless mapping.

[0067] (1)

[0068] In the formula, The normalized criterion score, and These are its mean and standard deviation, respectively. and These are the mean and standard deviation of the initial values, respectively. The parameters are defined. The selected metrics have two attributes: larger is better (LB) and smaller is better (SB).

[0069] Assuming the weight vector is known, take the initial weight vector... , The calculation formula is as shown in equation (2):

[0070] (2)

[0071] In the formula, As the indicator weight. Fixed. According to the equation Perform calculations to obtain the parameters. The value of . When approximate When the approximation is linear, and not equal to 0 or 1, the transformation of the same size as formula (1) is satisfied, at this time The mean of the above formula is approximately equal to 1.

[0072] To reasonably construct the driving adaptability evaluation model, the test data needs to be pre-processed first. The units of each driving adaptability indicator in the test are not unified, and the numerical values differ greatly. In order to perform reasonable calculations, standardization processing is required. In addition, there may be some correlation between night vision, dynamic vision, depth vision, complex reaction, and precise operation indicators. In order to avoid the influence of some indicators not being in line with the actual situation, it is necessary to analyze the independence of individual indicators. First, the minimum-maximum standardization method is used to normalize the data. In particular, considering that the smaller the values of night vision, dynamic vision, complex reaction, and precise operation indicators are, the better, and the smaller the absolute value of depth vision is, the better, and the larger the value of dynamic vision is, the better, in order to ensure that the trend changes of the aforementioned five indicators are consistent with the trend of driving adaptability, the absolute value of depth vision is taken as the indicator value, and the dynamic vision indicator value is processed to be consistent, that is, after completing the standardization processing of the dynamic vision indicator value, the value obtained by subtracting 1 from the value is taken as the corresponding indicator value. The processed part of the data is shown in the following table. After the normalization and convergence of the indicators are completed, there is no order of magnitude difference in the values of the indicators, so there is no need for order of magnitude unification processing.

[0073] Tab. 2 Partial data of processed driving adaptability indicators

[0074] Tab. 2 Partial data of processed driving adaptability indicators

[0075]

[0076] S2, input the indicator data into the driving adaptability evaluation model to obtain the comprehensive evaluation score indicator output by the driving adaptability evaluation model.

[0077] Among them, the driving adaptability evaluation model includes an improved factor analysis method based on the double-base point method for driving adaptability evaluation and a weighted geometric mean model used as a synthesis model.

[0078] Factor analysis is a multivariate statistical analysis method that identifies latent factors by studying the correlation between variables to reduce data dimensionality and structure detection. The TOPSIS double-base point method is a multi-criteria decision analysis method for evaluating and selecting the optimal solution, which is based on the concept of ideal solution, calculates the distance from each solution to the positive ideal solution and the negative ideal solution to sort and select. In this paper, the improved factor analysis method based on the double-base point method is used to evaluate driving adaptability, and the specific steps are as follows:

[0079] a. There are n indexes, each with m observations. On the basis of data standardization, the original data are converted into the form of matrix.

[0080] b. The correlation coefficient between indexes is calculated, the correlation coefficient matrix R is constructed, and principal component analysis is performed.

[0081] c. The eigenvalue and eigenvector of the correlation coefficient matrix R are solved, and the eigenvalue greater than 1.

[0082] d. The loading matrix C of each common factor is solved. To reflect the meaning of the common factor variable, the loading matrix is rotated to minimize the number of the highest loading variables.

[0083] e. After the factor variable is determined, the common factor score of each index is calculated by using Thompson's factor regression method.

[0084] f. The comprehensive factor score y is calculated by formula (3).

[0085] (3)

[0086] In the formula, is the variance contribution rate, is the common factor score.

[0087] g. The index system is established, the research object set is , the index set is , and t is the test point.

[0088] h. Factor analysis is performed on to obtain the factor of the object set and the factor score matrix of each object set.

[0089] i. The factor score is used as the evaluation index to form a new index system with indexes, n evaluation objects, and data, and the uniformization processing is performed by formula (4).

[0090] (4)

[0091] In the formula, is the uniformization processing matrix, is the factor score set.

[0092] j. The maximum value and the minimum value of each column in the matrix are found, and the optimal vector is calculated by formula (5) and the worst vector .

[0093] (5)

[0094] k. The closeness of the ith evaluation object to the optimal solution and the worst solution is calculated by formula (6).

[0095] (6)

[0096] l. The closeness of the ith evaluation object to the optimal factor solution is calculated by formula (7), and the larger Ci indicates the better effect of the ith evaluation object.

[0097] (7)

[0098] Further, to avoid exaggerating or reducing the impact of part of the driving adaptability indicators, the correlation of each indicator is analyzed. Normality test found that the data of each indicator does not conform to the normal distribution, so non-parametric test method is needed. Considering the sample size, Kendall rank correlation coefficient is selected for correlation analysis of night vision, dynamic vision, depth vision, complex reaction and precise operation five indicators, and the results are shown in Figure 2 .

[0099] As can be seen from Figure 2 , the correlation coefficient values between each driving adaptability indicator are mostly > 0.1, indicating that each indicator has a certain correlation with each other. Therefore, it is feasible to use factor analysis in this paper. The results of KMO test and Bartlett sphericity test in correlation analysis are shown in Table 3, the KMO test result is 0.606> 0.6, which meets the prerequisite requirement of factor analysis, and the data passes the Bartlett sphericity test (p = 0.002 < 0.05), indicating that the research data is suitable for factor analysis.

[0100] Table 3 KMO and Bartlett sphericity test results

[0101] Tab. 3 Results of KMO and Bartlett sphericity test

[0102]

[0103] ​The new independent index is extracted by the method of factor analysis, that is, the new index variance contribution rate generated after independent test is used to obtain the new index, and then the maximum variance method is used for rotation transformation. The variance contribution rate result is shown in Table 4. According to the factor extraction and the amount of information extracted by the factor, it is found that four factors are extracted by the factor analysis, and the variance explanation rates of the four factors after rotation are 27.323%, 22.148%, 20.432% and 20.037% respectively, and the cumulative variance explanation rate after rotation is 89.940%.

[0104] Tab. 4 Variance contribution rate

[0105] Tab. 4 Variance contribution rate

[0106]

[0107] According to the results in Table 4, the cumulative variance contribution rate of the first four independent factors reaches 89.940%, which is more than 80%. According to the related knowledge of statistics and the significance of cumulative variance contribution rate, it can be known that the first four independent factors can fully reflect the driving adaptability level of the driver. Therefore, the first four factors are extracted as new indexes in this paper. The maximum variance rotation method (varimax) is used to further rotate the new factors to determine the correspondence between the factors and the research items. The factor loading matrix is shown in Table 5.

[0108] Tab. 5 The factor load matrix of the new factor

[0109] Tab. 5 The factor load matrix of the new factor

[0110]

[0111] Table 5 shows the information extraction of each factor on the research items and the correspondence between the factors and the research items. It can be found that the common degree value corresponding to all research items is higher than 0.4, which means that there is a strong correlation between the research items and the factors, and the factors can effectively extract the information. After ensuring that the factors can extract most of the information of the research items, the correspondence between the factors and the research items is analyzed. The absolute value of the factor loading coefficient is greater than 0.4, which means that the item has a corresponding relationship with the factor.

[0112] If factor analysis is used for weight calculation, the "component score coefficient matrix" table is needed to establish the relationship between the factors and the research items, i.e. to establish a relationship expression based on the standardized data, as shown in equation (8). Each common factor is a coefficient of the linear expression form of the initial index variable, and after analysis, independent new indexes are obtained.

[0113] (8)

[0114] In the formula, represents the th common factor, represents the night vision standardized value, represents the motion vision standardized value, represents the depth perception standardized value, represents the complex reaction standardized value, represents the fine operation standardized value.

[0115] For evaluation problems, commonly used synthetic models include the weighted sum model, the weighted product model, and the weighted geometric mean model. The first two models have a large compensation, while the weighted geometric mean model first takes the logarithm of each index value, then calculates the arithmetic mean, converts it to an exponential form to obtain the geometric mean, and finally multiplies it by the weight and sums it to obtain the weighted geometric mean. This data processing method makes the weighted geometric mean model less affected by extreme values and more robust. Therefore, this paper adopts the weighted geometric mean model as the synthetic model, and the calculation is as shown in equation (9).

[0116] (9)

[0117] Based on the weighted geometric mean model, the variance contribution rate of the common factor is used as the weight, and the sum of the variance contribution rates is used as the basis for weight normalization processing. Considering the calculation in percentage, the comprehensive score is expanded by 100 times, and since all current index values are better the smaller, 100 is subtracted from the current score to meet the conventional scoring standard. The final driver driving adaptability evaluation model is shown in equation (10).

[0118] (10)

[0119] Based on the P-P plot, the comprehensive score index is verified. By comparing the cumulative distribution function of continuous data with the cumulative distribution function of a specified theoretical distribution, it is evaluated whether the data conforms to a certain theoretical distribution. The P-P plot is used to analyze the driving adaptability comprehensive evaluation score index Whether it is normal distribution, the actual data cumulative proportion as X axis, the corresponding normal distribution cumulative proportion as Y axis, scatter plot, its normal P-P chart as shown in Figure 3 , if the scatter plot is approximately a diagonal straight line, it means that the data is normally distributed, otherwise it is not normal. From Figure 3 , it can be seen that the driving adaptability comprehensive evaluation score index is basically in line with the normal distribution as a whole.

[0120] In order to evaluate the effectiveness of the driving adaptability evaluation model constructed based on the improved logistic linear function combined with Topsis and factor analysis and linear weighted model , the evaluation results of the other two models are compared and analyzed. That is, the driving adaptability model constructed by Topsis method , and the driving adaptability evaluation model constructed based on the maximum and minimum standardization combined with Topsis and factor analysis and linear weighted model , the model formula is shown in equation (11). Draw the correlation scatter plot of driving adaptability comprehensive score and accident frequency in the above three methods, as shown in Figure 4 , the higher the score, the fewer the number of accidents, and the better the driving adaptability.

[0121] (11)

[0122] From Figure 4 , it can be seen that the score of each driving adaptability evaluation model is in line with the rule that the higher the score, the fewer the number of accidents, and the better the driving adaptability. Individual points with high accident frequency are distributed at high scores or points with fewer accidents are scattered at low scores, which may be due to the difference in the state of the test driver.

[0123] Further, the correlation coefficient between driving adaptability comprehensive score and accident frequency is calculated. The larger the correlation coefficient, the more effective the model evaluation result. First, the Shapiro-Wilk test is used to test the normality of the data. The data is in line with the normal distribution, so the Pearson correlation coefficient is used for data analysis, and the results are shown in Table 6.

[0124] Table 6 Variance analysis results of different driving adaptability evaluation scores and accident frequency

[0125] Tab. 6 Results of variance analysis of different driving adaptabilityevaluation scores and accident frequency

[0126]

[0127] According to Table 6, the scores of the three types of driving adaptability evaluation models and the number of accidents all present significance at the 1% level, while the correlation coefficient of the model constructed in this study is significantly higher than that of the comparative models and , indicating that the correlation between the model constructed in this study and the number of accidents is higher, and the new model is superior to the comparative models.

[0128] In order to evaluate the effectiveness of the constructed model in driving adaptability evaluation, the samples are divided into four groups, i.e. no accident group, one accident group, two accidents group, and three or more accidents group, and single factor variance analysis is used to test the differences between groups. First, the homogeneity of variance test is performed, and the results are shown in Table 7. The driving adaptability evaluation score is the largest in the no accident group and the smallest in the accident-prone group, and it presents a trend of gradually decreasing with the increase of the number of accidents. In addition, the significance P value of DAE is 0.011 , the data do not meet the homogeneity of variance, the significance P value of DAE1 is 0.236, the data meet the homogeneity of variance, and the significance P value of DAE2 is 0.152, the data meet the homogeneity of variance. Since DAE does not meet the homogeneity of variance, Welch's variance test is used, and the variance analysis result P value is 0.000 ≤0.05, so the statistical result is significant, indicating that there is a significant difference in DAE between different accident frequencies. DAE1 and DAE2 meet the homogeneity of variance, and single sample variance test is used, and the variance analysis result P values are 0.015 ≤0.05 and 0.011 ≤0.05, respectively, so the statistical result is significant, indicating that there is a significant difference in DAE1 and DEA2 between different accident frequencies. It can be seen that the driving adaptability evaluation scores of the three types of models and the number of accidents all present significant differences at the 1% level, but the differences between the accident groups of the new model are significantly higher than those of the two types of comparative models.

[0129] Table 7 Results of variance analysis of different driving adaptabilityevaluation scores and accident frequency

[0130] Tab. 7 Results of variance analysis of different driving adaptabilityevaluation scores and accident frequency

[0131]

[0132] By comparing the effects of different methods, the optimal strategy is selected, and the difference amplitude is compared by effect quantification analysis method, and the results are shown in Table 8. The results of effect quantification analysis show that based on DAE, =0.288, which shows that the difference of 28.8% of the data is from the difference between different groups, Cohen's f=0.637, which reflects the difference degree of the data effect quantification is large. Based on DAE1, =0.201, which shows that the difference of 20.1% of the data is from the difference between different groups, Cohen's f=0.501, which reflects the difference degree of the data effect quantification is large. Based on DAE2, =0.212, which shows that the difference of 21.2% of the data is from the difference between different groups, Cohen's f=0.519, which reflects the difference degree of the data effect quantification is large. It can be seen that the group difference of DAE is the largest (2182.152), and the value is the highest (0.288), which shows that DAE has the highest explanation degree for the variability of dependent variable, and has stronger effect than DAE1 (0.201) and DAE2 (0.212). It shows that the evaluation results of the new model constructed in this paper have higher correlation with the number of accidents, and are obviously better than other two comparison models in distinguishing the group difference between different accident groups. =0.288), indicating that DAE has the highest explanation degree for the variability of dependent variable, and has stronger effect than DAE1 (0.201) and DAE2 (0.212). It shows that the evaluation results of the new model constructed in this paper have higher correlation with the number of accidents, and are obviously better than other two comparison models in distinguishing the group difference between different accident groups. Tab. 8 Effect quantification analysis results

[0133] Tab. 8 Effect quantification analysis results

[0134] Tab. 8 Effect quantification analysis results

[0135]

[0136] In summary, the improved logistic nonlinear value function used to build the driving adaptability evaluation model controls the difference of mean value to a certain extent compared with the linear normalization data processing method. The new model uses the method of combining factor analysis and Topsis. Factor analysis converts multiple related variables into a few unrelated latent factors through dimension reduction technology, so as to eliminate the multicollinearity problem in original data and more objectively determine the weight of each index. Further combining Topsis method takes into account the characteristics of multi-attribute decision making. Further using the weighted geometric mean model with smaller compensation than linear weighted model, more effective driving adaptability evaluation is realized.

[0137] S3, determine the evaluation grade corresponding to the target preset score interval of the comprehensive evaluation score index. ​​

[0138] The driving adaptability comprehensive evaluation standard in the preset score interval is obtained based on an improved K-means clustering algorithm.

[0139] The driving adaptability comprehensive evaluation score index is clustered to obtain the driving adaptability comprehensive evaluation standard of the middle-aged and old drivers. The K-means clustering algorithm is a classic unsupervised clustering algorithm which minimizes the variance of data points in clusters through an iterative process, thereby increasing the difference between different clusters as much as possible. However, the K-means clustering algorithm needs to specify the number of clusters K in advance, and is sensitive to the selection of initial centroids, and different initial values can lead to different clustering results. The initial clustering center points of the traditional K-means clustering algorithm are selected in a random way, and improper selection of the initial center points can lead the algorithm to fall into a local optimal solution. In this paper, the improved Kmeans++ clustering algorithm is used to optimize the selection method of the initial center points, so as to improve the convergence speed and accuracy of the clustering algorithm.

[0140] The improved Kmeans++ clustering algorithm and the original K-means clustering algorithm are used to cluster the comprehensive evaluation score index, the clustering effects of the two methods are compared, and the driving adaptability comprehensive evaluation standard of the middle-aged and old drivers is further obtained according to the better clustering effect, and the results are shown in Table 9. It can be found that the clustering effect of Kmeans++ is obviously better than that of K-means clustering in the contour coefficient, DBI index and CH index, so the clustering result of the former is selected for further analysis.

[0141] Tab. 9 Comparison between Improved K-means Clustering Results andOriginal K-means Clustering Results

[0142] Tab. 9 Comparison between Improved K-means Clustering Results andOriginal K-means Clustering Results

[0143]

[0144] According to the comprehensive score index, the original data is analyzed, and the test drivers are classified according to the comprehensive evaluation index, and the results are shown in Table 10. According to the clustering result of Kmeans++, the test drivers are divided into three categories of good, general and attention, and it can be seen that the score interval of the driving adaptability of good level is [80.23, 95.90], the score interval of the driving adaptability of general level is [70.16, 80.22], and the score interval of the driving adaptability of attention level is [44.43, 67.77], among which the proportion of the test drivers with driving adaptability of attention level is relatively large, and it may be necessary to further pay attention to whether the current state is suitable for continuing driving.

[0145] Table 10 Driving adaptability scores of drivers

[0146] Tab. 10 Driving adaptability scores of drivers

[0147]

[0148] Finally, it should be noted that the terms "first" and "second", and the like, are used herein merely to distinguish one element from another, and are not necessarily intended to indicate physical or chronological order. Also, the terms "including", "comprising", or any other variation thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements is not necessarily limited to those elements, but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0149] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, i.e. may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0150] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles, practical application or improvement of technology in the market of the embodiments, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for analyzing and evaluating the static driving adaptability of elderly drivers, characterized in that, Includes the following steps: The evaluation indicators of the target driver are obtained, and the evaluation indicators are normalized and homogenized to obtain indicator data. The evaluation indicators include the target driver's night vision, dynamic vision, depth vision, complex reaction and precision operation indicators. The index data is input into the driving adaptability evaluation model to obtain the comprehensive evaluation score index output by the driving adaptability evaluation model. The driving adaptability evaluation model includes a factor analysis method based on the two-base-point method improved for driving adaptability evaluation and a weighted geometric mean model used as a composite model. The expression for the driving adaptability evaluation model is as follows: ； In the formula, Representing the One common factor, This represents the standardized value of night vision. This represents the standardized value of dynamic visual acuity. This represents the standardized value of deep visual acuity. This represents the standardized value of a complex reaction. This represents the standardized value after precise operation; The factor analysis method based on the two-point method includes the following steps: Calculate the correlation coefficients between the indicators and construct a correlation coefficient matrix; The eigenvalues ​​and eigenvectors of the correlation coefficient matrix are solved, and the principal components with eigenvalues ​​greater than 1 are selected as common factors. The number of the highest loaded variables is reduced by calculating the loading matrix and the rotation loading matrix. The common factor score for each indicator was calculated using Thomson factor regression. Calculate the comprehensive factor score and perform a consistency processing on the comprehensive factor score; Based on the optimal and worst vectors, calculate the degree of closeness between each evaluation object and the optimal factor scheme; The evaluation level corresponding to the comprehensive evaluation score index in the target preset score range is determined. The comprehensive evaluation standard for driving adaptability in the preset score range is obtained based on the improved K-means clustering algorithm. The K-means clustering algorithm is used to optimize the selection method of the initial center point in order to improve the convergence speed and accuracy of the clustering algorithm.

2. The method for analyzing and evaluating the static driving adaptability of elderly drivers according to claim 1, characterized in that, The normalization and convergence processing of the evaluation indicators yields the following indicator data: The evaluation indicators were normalized using the min-max standardization method to obtain normalized data. Normalized data of the night vision, complex reaction and precision operation indicators are obtained as the indicator data; Furthermore, the normalized data of the depth vision and the motion vision are processed to be used as indicator data.

3. The method for analyzing and evaluating the static driving adaptability of elderly drivers according to claim 2, characterized in that, The min-max normalization method is based on an improved logistic value function, the expression of which is: ； In the formula, The normalized criterion score, and These are its mean and standard deviation, respectively. and These are the mean and standard deviation of the initial values, respectively. These are definite parameters.

4. The method for analyzing and evaluating the static driving adaptability of elderly drivers according to claim 2, characterized in that, The assimilation process for the depth vision and the motion vision includes: Obtain normalized depth vision data and normalized motion vision data; The depth vision index data is obtained by subtracting the depth vision normalized data from 1. Furthermore, the dynamic visual acuity index data is obtained by subtracting the normalized dynamic visual acuity data from 1.

5. The method for analyzing and evaluating the static driving adaptability of elderly drivers according to claim 1, characterized in that, The evaluation levels include a good level, a fair level, and a level requiring attention. The score range for the good level is the first range, the score range for the fair level is the second range, and the score range for the level requiring attention is the third range.

Images