KR101740983B1 - Apparatus and method for determining validity of sensing data related with vehicle driver - Google Patents

Abstract

The present invention relates to a technology for determining the usefulness of sensing data that can be associated with a driver of a vehicle, and includes a body data collection unit for collecting sensing data relating to a subject, and a pre-processing unit for performing efficiency analysis on at least a part of the collected sensing data A data availability determination unit for determining availability of the sensing data, and a state determination unit for determining a state of the subject by determining statistical significance with respect to sensing data having utility in the sensing data.

Description

[0001] APPARATUS AND METHOD FOR DETERMINING VALIDITY OF SENSING DATA [0002] RELATED WITH VEHICLE DRIVER [0003]

The present invention relates to a technique for determining the effectiveness of sensing data, and more particularly, it relates to a technique for determining the efficiency of sensing data by analyzing the effectiveness of sensing data according to a situation, To an apparatus and method for determining the effectiveness of sensing data that can be associated with a vehicle driver that can be improved.

One of the reasons for the high proportion of traffic accidents is human error. Problems of attention required for safe driving lead to driver's judgment error, information processing delay, etc., and the possibility of a traffic accident increases. As a result, various research institutes and commercial vehicle companies are developing a system to determine the driver's condition.

Many sensing data such as vehicle, image, voice, and driver's biometric information are used in the driver's condition determination system. However, it takes a lot of time in the process of judging by considering a lot of sensing data, and the efficiency is lowered accordingly.

Korean Patent Laid-Open Publication No. 10-2014-0113153 (2014.09.24) relates to a method of determining the identity, comprising a first determination step of comparing the statistical values of the process data with the reference statistics to determine the same / non-identical / improvement; A correction step of correcting the reference statistics by considering a statistical tolerance on the non-identical / improved process data; And a second determination step of comparing the statistical values of the non-identical / improved process data determined by the corrected reference statistics to determine acceptance / non-uniformity.

Korean Patent No. 10-1305841 (2013.09.02) relates to an automatic search for a variable association and a dynamic result report calculation method using the same, and it is an object of the present invention to provide a dynamic result report calculation method in which, And categorizing them as categorical variables and continuous variables; The statistical algorithm automatic application module applying statistical analysis to the variables automatically classified by the variable type automatic classification module applying different statistical algorithms according to the combination of the types; Creating a dynamic variable association diagram showing the association between all the variables statistically analyzed by the module for automatically applying the statistical algorithm association module; And creating a dynamic result report showing the association between all variables statistically analyzed by the statistical algorithm automatic application module of the dynamic result report creation module.

1. Korean Patent Laid-Open Publication No. 10-2014-0113153 (2014.09.24) 2. Korean Patent No. 10-1305841 (2013.09.02)

An embodiment of the present invention can be applied to a vehicle driver that can improve the speed and efficiency of information processing by analyzing the effectiveness of sensing data according to a situation and reflecting only statistically verified sensors to the state determination of the subject An apparatus and method for determining the effectiveness of sensing data.

One embodiment of the present invention relates to a method and apparatus for sensing a subject through sensors that are useful according to the current situation of the subject and activating only useful sensors according to the changed situation when the current situation is changed to improve the efficiency And to provide an apparatus and method for determining the usefulness of sensing data.

In an embodiment, the apparatus for determining the effectiveness of sensing data generates a sensing data population related to a simulated subject in a specific situation predefined through a plurality of sensors, analyzes the sensing data population, And a subject sensing unit for determining a current state of the subject with respect to the subject and sensing the subject through the current efficiency sensor according to the current situation.

The predetermined specific situation may include a steady state or an abnormal state with respect to the simulated subject, and may further include an operation state by the simulated subject.

The subject sensing unit can continuously detect the current state of the subject.

The subject sensing unit may detect a change of the current situation of the subject and determine the next situation, and may activate only the next benefit sensor according to the next situation.

The subject sensing unit may determine the current state of the subject through the sensor among the plurality of sensors.

The current state may include a current operation state by the subject.

The efficiency sensor determination unit may collect sensing data including vehicle information, image information, audio information, and biometric information on the simulated subject to generate the sensing data population.

The utility sensor determination unit may generate processing data about at least a part of the sensing data population.

The utility sensor determination unit may generate the processing data related to the face direction if at least a part of the sensing data population includes the face coordinate information.

The utility sensor determination unit may generate the processing data related to the degree of dialogue if at least a portion of the sensing data population includes the speech amplitude information.

The utility sensor determiner may perform preprocessing for utility analysis on preprocessable data corresponding to at least one of the processing data and at least a portion of the sensing data population not associated with the processing data.

The pre-processing for the utility analysis applies the pre-processable data having various characteristics and a wide range of values to at least one pre-processing analysis model to generate at least one pre-processing data And the like.

The at least one pre-processing analytical model may include at least one of a root mean square error (RMSE) analysis model, a principal frequency analysis model, an average size analysis model, an average frequency analysis model, an average duration analysis model, And a ratio analysis model.

The efficiency sensor determination unit may perform an efficiency analysis based on the pre-processing data to determine a meaningful efficiency sensor in the specific situation.

Wherein the utility sensor determination unit compares the case where the abnormality is likely to occur with the case where the abnormality is likely to occur for each of the predefined specific situations and analyzes the utility of at least one specific sensor associated with the at least one pre- The utility analysis can be performed through a statistical significance test.

The utility sensor determination unit may perform the utility analysis by selecting one of the parameter and non-parametric test methods included in the statistical significance test method based on the number of samples of the sensing data population.

The apparatus for determining the effectiveness of the sensing data may further include a state determination unit for determining a state of the subject based on a result of sensing the subject through the current efficiency sensor.

The apparatus for determining the effectiveness of the sensing data may further include a sensing data population adding unit for adding the sensing data and the status determination result about the inspected object to the sensing data population when the status determination for the inspected object is completed to support the updating of the sensing data population specific to the inspected object And a population update unit.

In one embodiment, a method for determining the effectiveness of sensing data performed by an apparatus for determining the effectiveness of sensing data includes generating a sensing data population for a simulated subject in a specific situation that is predefined through a plurality of sensors, A method of determining a utility sensor that determines a meaningful sensor in the specific situation and a method of sensing a subject by sensing a current state of the inspected object using the current utility sensor according to the current situation can do.

Among the embodiments, an apparatus for determining the effectiveness of sensing data, which may be associated with a vehicle driver, generates a sensing data population for a simulated driver in a predefined specific situation through a plurality of sensors, analyzes the sensing data population, And a driver sensing unit for determining a current state of the utility sensor determining unit and the driver determining a meaningful efficiency sensor in a specific situation and sensing the driver through the current utility sensor according to the current situation.

The disclosed technique may have the following effects. It is to be understood, however, that the scope of the disclosed technology is not to be construed as limited thereby, as it is not meant to imply that a particular embodiment should include all of the following effects or only the following effects.

An apparatus and method for determining the effectiveness of sensing data that can be associated with a vehicle driver according to an embodiment of the present invention includes analyzing effectiveness of sensing data according to a situation and reflecting only statistically verified sensors to the determination of the state of the subject, The speed and efficiency of the processing can be improved.

An apparatus and method for determining the effectiveness of sensing data that can be associated with a vehicle driver according to an embodiment of the present invention includes sensing a subject through sensors that are operative according to the current status of the subject, Only efficient sensors can be activated to improve efficiency.

1 is a block diagram illustrating an apparatus for determining the effectiveness of sensing data according to an embodiment of the present invention.
2 is a flowchart illustrating an embodiment of a method for determining the effectiveness of sensing data performed by the apparatus for determining effectiveness of sensing data shown in FIG.
FIG. 3 is a flowchart for explaining another embodiment of a method for determining the effectiveness of sensing data performed by the apparatus for determining effectiveness of sensing data shown in FIG.

The description of the present invention is merely an example for structural or functional explanation, and the scope of the present invention should not be construed as being limited by the embodiments described in the text. That is, the embodiments are to be construed as being variously embodied and having various forms, so that the scope of the present invention should be understood to include equivalents capable of realizing technical ideas. Also, the purpose or effect of the present invention should not be construed as limiting the scope of the present invention, since it does not mean that a specific embodiment should include all or only such effect.

Meanwhile, the meaning of the terms described in the present application should be understood as follows.

The terms "first "," second ", and the like are intended to distinguish one element from another, and the scope of the right should not be limited by these terms. For example, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

It is to be understood that when an element is referred to as being "connected" to another element, it may be directly connected to the other element, but there may be other elements in between. On the other hand, when an element is referred to as being "directly connected" to another element, it should be understood that there are no other elements in between. On the other hand, other expressions that describe the relationship between components, such as "between" and "between" or "neighboring to" and "directly adjacent to" should be interpreted as well.

It is to be understood that the singular " include " or "have" are to be construed as including the stated feature, number, step, operation, It is to be understood that the combination is intended to specify that it does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

In each step, the identification code (e.g., a, b, c, etc.) is used for convenience of explanation, the identification code does not describe the order of each step, Unless otherwise stated, it may occur differently from the stated order. That is, each step may occur in the same order as described, may be performed substantially concurrently, or may be performed in reverse order.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Commonly used predefined terms should be interpreted to be consistent with the meanings in the context of the related art and can not be interpreted as having ideal or overly formal meaning unless explicitly defined in the present application.

1 is a block diagram illustrating an apparatus for determining the effectiveness of sensing data according to an embodiment of the present invention.

1, an apparatus 100 for determining the effectiveness of sensing data includes a utility sensor determination unit 110, a body sensing unit 120, a control unit 130, a body state determination unit 140, and a population update unit 150).

The apparatus 100 for determining the effectiveness of the sensing data may correspond to a computing apparatus that can analyze the effectiveness of the sensing data for each situation and reflect only the sensors having the statistical significance in the determination of the state of the subject. In one embodiment, the sensing data availability determination device 100 may be implemented as a desktop, notebook, tablet PC, or smart phone. In another embodiment, the apparatus 100 for determining the effectiveness of sensing data may be electrically connected to the vehicle or connected via a network, and may be implemented as a control unit of a vehicle included in the vehicle.

The apparatus 100 for determining the effectiveness of sensing data may include a utility sensor determination unit 110, a body sensing unit 120, a controller 130, a body state determination unit 140, and a population update unit 150 And can be designed to transmit and receive electrical signals between them.

The utility sensor determination unit 110 can generate a sensing data population related to a simulated subject in a specific situation defined in advance through a plurality of sensors. Here, the subject refers to an object to be measured, which is a source of specific information included in the sensing data, and a simulation subject is a sensor that is statistically comparable to determine a meaningful efficiency sensor to be activated when sensing a particular subject Means at least one simulated object to be measured forming a data population. In one embodiment, the mock subject is in a predefined specific situation, and the predefined specific situation may include a steady state or abnormal state with respect to the mock subject, and may further include an operation state by the mock subject. For example, the simulated subject may be in a steady state or an abnormal state corresponding to a predefined driver's state, and at the same time, may be in a specific operating state corresponding to the driving state of the vehicle.

In one embodiment, the plurality of sensors include a vehicle sensor 112 that receives the vehicle's running status, a camera sensor 114 that senses the driver and generates a driver image, a voice sensor 116 that receives the driver's voice, And a biosensor 118 capable of sensing driver's biometric information, and may further include various other sensors. Here, the vehicle sensor 112 may be a sensor capable of sensing information in the vehicle, and may correspond to a sensor capable of sensing the driving of the actuators in the vehicle. The vehicle sensor 112 may be operated from an electronic control unit (ECU) The camera sensor 114 may correspond to an image sensor having a structure in which a shape of a subject comes in through a lens and the light is converted into an electric signal and stored in a memory when the image sensor is contacted with the image sensor. And the voice sensor 116 may correspond to an acoustic sensor capable of recognizing the voice of a voice size and a specific frequency. The bio sensor 118 may be a heart rate sensor capable of sensing biometric information such as a person's heart rate or body temperature, It may correspond to a body temperature sensor.

In one embodiment, the utility sensor determination unit 110 may generate a sensing data population for a model subject based on the sensing data collected through the plurality of sensors. In another embodiment, the utility sensor determination unit 110 may include at least one sensor (not shown) electrically connected to the sensing data effectiveness determination apparatus 100 or connected through a network, or a device A sensing data population related to the simulated subject can be generated based on the data collected from the sensor (not shown). According to the above embodiments, the utility sensor determination unit 110 may generate sensing data populations by collecting sensing data including vehicle information, image information, audio information, and biometric information on a simulated subject.

The utility sensor determination unit 110 may analyze the sensing data population to determine a meaningful efficiency sensor in a specific situation. In one embodiment, the data contained in the generated sensing data population is raw data that has not been processed, i.e., the original data collected through a plurality of sensors, It may correspond to data with the original form of the former. In one embodiment, the utility sensor determination unit 110 processes the data of the sensing data population, preprocessing process for utility analysis, and utility analysis process, , And thus can determine meaningful sensory sensors for each situation.

The utility sensor determination unit 110 can generate processing data about at least a part of the sensing data population. In one embodiment, the sensing data population may include raw data data that can be directly applied to analysis and raw data data that requires processing, and the efficiency sensor determination unit 110 may include two types of raw data data The processing data can be generated through at least a part of the sensing data population and used for the subsequent analysis process.

The utility sensor determination unit 110 may generate the processing data related to the face direction if at least a part of the sensing data population includes the face coordinate information. In one embodiment, the utility sensor determination unit 110 can divide the face direction into the front, top, bottom, left, and right directions through the x-axis coordinate and y-axis coordinate of the face coordinate information included in the specific data of the sensing data population And the reference threshold value for discrimination can be preset based on the heuristic method. In this embodiment, the utility sensor determination unit 110 can generate the processing data on the face direction by processing the data of the sensing data population including the face coordinate information based on Equation (1). (For example, the processing data on the face direction generated based on the face coordinate information is one of the values 0 (front), 1 (upper), 2 (lower), 3 (left) and 4 Lt; / RTI >

[Equation 1]

The utility sensor determination unit 110 can generate the processing data on the degree of dialogue if at least a part of the sensing data population includes the voice amplitude information. In one embodiment, the utility sensor determination unit 110 determines the degree of dialogue by using the maximum speech amplitude to noise (intentional input (no speech) -free signal) of the speech amplitude information included in the specific data of the sensing data population, It can be divided into 7 steps. In this embodiment, the efficiency sensor determination unit 110 can generate the processing data on the degree of conversation by processing the data of the sensing data population including the voice amplitude information based on Equation (2).

&Quot; (2) "

The utility sensor determination unit 110 may perform preprocessing for utility analysis on preprocessable data corresponding to at least one of the processing data and at least one portion of the sensing data population not associated with the processing data. In one embodiment, the utility sensor determination unit 110 determines whether or not the data of the sensed data population is raw data that needs to be processed, and for the pre-processable data corresponding to the processed data generated through the processing, If the source data that does not need to be processed in the data of the sensing data population can be subjected to the pre - processing, the pre - processing can be performed on the pre - processable data corresponding to the source data, Processing can be performed.

In one embodiment, the pre-processing for utility analysis comprises applying pre-processable data having various characteristics and a wide range of values to at least one pre-processing analytical model, so that at least one pre- And generating processing data. In one embodiment, the at least one pre-processing analytical model comprises at least one of a root-mean square error (RMSE) analysis model, a principal frequency analysis model, an average size analysis model, , A maximum change amount analysis model, and a ratio analysis model. Here, the mean square error analysis model is related to the ideal size, and the main frequency analysis model is a method of analyzing the main frequency of the information of the changing time dimension, and the average size analysis model is used to analyze the average size of the input signal The average time analysis is a method of analyzing the number of times a meaningful value of an input signal is inputted. The average duration analysis is a method of analyzing a time duration in which a significant value of a signal is inputted and a maximum variation analysis is a method of analyzing an input signal And the ratio analysis is a method of analyzing the ratio of the significant values of the signals among the whole signals. For example, when the pre-processable data corresponds to one of 'longitudinal speed', 'longitudinal acceleration', 'steering angle', and 'lateral acceleration', the utility sensor determination unit 110 may calculate a mean square root mean square error Based on the average size analysis model, the pre-processing data can be generated by calculating the relationship between the ideal value and the observed value based on the average acceleration model, and if the acceleration pedal, the heart rate, The average size can be calculated to generate preprocessing data.

The utility sensor determination unit 110 may perform utility analysis based on the pre-processing data to determine a meaningful utility sensor in a specific situation. In one embodiment, the purpose of such utility analysis is to determine whether the vehicle, video, audio, and / or video signals are in an abnormal state (e.g., the driver is sleeping, distracted or overloaded) Analyzing the statistical utility of which information among a large number of information including voice and biometric information and determining a specific sensor among a plurality of sensors associated with specific information that has been found to be useful for a particular situation. In one embodiment, the utility sensor determination unit 110 determines whether or not an abnormal state (e.g., an operating state) of a plurality of operating states (e.g., vehicle driving states) by a predefined simulated subject, The utility sensor can be determined to detect the abnormal state in a specific operation state by analyzing the utility by comparing the normal state with the case where the abnormal state is detected.

The utility sensor determination unit 110 analyzes the utility of at least one specific sensor associated with at least one pre-processing data by comparing the case where the probability of occurrence of the abnormal state is high and the case of low occurrence, The statistical significance test method can be used to perform the utility analysis. In one embodiment, the utility sensor determiner 110 may perform the utility analysis by selecting one of the parameter and non-parametric test methods included in the statistical significance test method based on the number of samples of the sensing data population. For example, if the number of samples in the sensed data population is 30 or more, it is assumed that normality is assumed. Therefore, a Paired t-test is used as a parameter test method. If the number of samples is less than 30, (Paired t-test), which is a parameter test method, is used only when there is a normality, and the Wilcoxon signed-rank test, which is a nonparametric test method, is used when there is no normality .

The subject sensing unit 120 can determine the current state of the subject. In one embodiment, the subject sensing unit 120 may determine the current status of the subject through the sensor, among the plurality of sensors. In one embodiment, the always sensor means a sensor that is always operated regardless of the situation, and the current situation may include the current operating state by the subject. In one embodiment, the subject sensing unit 120 can determine that the current status of the subject corresponds to a specific operation state based on the vehicle sensor 112 set to the normal sensor. For example, the subject sensing unit 120 collects data on the driving state of the vehicle from the vehicle sensor 112 set as the always-on sensor, and calculates the driving direction and the descending direction of the vehicle including leftward, It is possible to determine one of the first to ninth operating states according to the combination of the running gradient of the vehicle including the uphill road as the current state of the subject.

The subject sensing unit 120 can sense the subject through the current performance sensor according to the current situation. In one embodiment, the subject sensing unit 120 senses the current state of the subject through one of the first to ninth operating states (e.g., the third operating state) through the vehicle sensor 112, (For example, the camera sensor 114 and the voice sensor 116 in the case of the third operation state) in a specific situation determined by the efficiency sensor determination unit 110, Only the sensors can be activated.

The subject sensing unit 120 can continuously detect the current state of the subject. In one embodiment, the subject sensing unit 120 can continuously detect the current status of the subject at a specific period and can detect a specific event (for example, when the vehicle is turned on or the gear position of the vehicle is changed Event), the present situation can be detected.

The subject sensing unit 120 may detect a change in the current state of the subject, determine the next situation, and activate only the next effective sensor according to the next situation. In one embodiment, the subject sensing unit 120 can detect a change in the current status of the subject by continuously detecting the current status of the subject, activate only the effectiveness sensor according to the changed status, . ≪ / RTI > For example, the subject sensing unit 120 determines that the current state of the subject is determined as the third operation state and the camera sensor 114, which is a meaningful utility sensor in the third operation state determined by the efficiency sensor determination unit 110, Only the camera sensor 114 and the biosensor 118, which are sensible effect sensors, are activated in the fourth operation state to detect that the subject has been changed to the fourth operation state, Sensing can be performed.

In the above description, the plurality of sensors are included in the utility sensor determination unit 110. However, in another embodiment, the plurality of sensors may be included in the subject sensing unit 120, May be included in a separate sensor device (not shown) electrically connected to the data determination device 100 or connected via a network.

The control unit 130 controls the overall operation of the sensing data effectiveness determination apparatus 100 and includes a function determination unit 110, a body sensing unit 120, a body state determination unit 140, and a population updating unit 150 to control the flow of control or data between them.

The subject state determination unit 140 can determine the state of the subject based on the result of sensing the subject through the current utility sensor. In one embodiment, the object state determination unit 140 may process a plurality of sensing data obtained by sensing a subject through a current efficiency sensor, and analyze the sensing data based on a specific determination criterion and a conditional probability on a normal distribution. It is possible to determine the current state of the subject by confirming that the condition of the specific state set in advance is satisfied based on the analysis result of each of the plurality of sensed data processed.

The population updating unit 150 may update the sensing data population specific to the subject by adding the sensing data and the status determination result about the subject to the sensing data population when the status determination of the subject is completed. In one embodiment, the population update unit 150 transmits the sensed data and the status determination result to the effect sensor determination unit 110 when the status of the subject based on the meaningful sensory sensor is determined in the current situation It is possible to add the sensing data to the sensing data population and re-determine the meaningful sensory sensors in a specific situation based on the sensed data population updated at specific time intervals, so that the efficiency of sensing data specific to the subject can be determined.

2 is a flowchart illustrating an embodiment of a method for determining the effectiveness of sensing data performed by the apparatus for determining effectiveness of sensing data shown in FIG.

In Fig. 2, the method for determining the effectiveness of the sensing data largely includes the following steps.

First, a method for determining the effectiveness of sensing data may include generating a sensing data population related to a simulated subject in a specific situation predefined through a plurality of sensors (step S210).

Second, the method of determining the effectiveness of the sensing data may include analyzing the sensing data population to determine a meaningful efficiency sensor in the specific situation (step S220).

Third, the method of determining the effectiveness of the sensing data may include determining the current state of the subject (step S230).

Finally, the method of determining the effectiveness of sensing data may include sensing the subject through a current utility sensor according to the current situation (step S240).

FIG. 3 is a flowchart for explaining another embodiment of a method for determining the effectiveness of sensing data performed by the apparatus for determining effectiveness of sensing data shown in FIG.

In FIGS. 3A and 3B, the method for determining the effectiveness of sensing data may include the following steps.

First, a method of determining the usefulness of the sensing data may include generating a sensing data population related to a simulated subject in a specific situation predefined through a plurality of sensors (step S310).

Second, the method of determining the effectiveness of the sensing data may include generating processing data about at least a portion of the sensing data population (step S320).

Thirdly, a method for determining the usefulness of sensing data comprises performing preprocessing for utility analysis on pre-processable data corresponding to at least one of at least one of the machining data and at least a portion of the sensing data population not associated with the machining data, And generating processing data (step S330).

Fourth, a method for determining the effectiveness of the sensing data may include a step of determining a meaningful efficiency sensor in a specific situation by performing efficiency analysis based on the pre-processed data (step S340).

Fifth, the method of determining the effectiveness of the sensing data may include determining the current state of the subject including the current operation state of the subject through the sensor among the plurality of sensors (S350).

Sixth, a method of determining the effectiveness of the sensing data may include activating only the subject through the current efficiency sensor according to the current situation (step S360).

Seventhly, a method of determining the effectiveness of the sensing data may include determining a state of the subject based on a result of sensing the subject by means of a current efficiency sensor (step S370).

Eighth, the method of determining the effectiveness of the sensing data includes adding the sensing data and the status determination result about the subject to the sensing data population when the status determination of the subject is completed, and based on the sensing data population updated at specific time intervals (Step S380). ≪ RTI ID = 0.0 > [0037] < / RTI >

Finally, the method of determining the effectiveness of the sensing data may include detecting a change in the current state of the subject, determining the next situation, and activating only the next benefit sensor according to the next situation (step S390).

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims It can be understood that

100: Apparatus for determining the effectiveness of sensing data
110:
112: vehicle sensor 114: camera sensor
116: voice sensor 118: biosensor
120:
130:
140:
150:

Claims (20)

A utility sensor determination unit for generating a sensing data population related to a simulated subject in a specific situation predetermined through a plurality of sensors and analyzing the sensing data population to determine a meaningful efficiency sensor in the specific situation; And
And a subject sensing unit for determining a current state of the subject and sensing the subject through a current efficiency sensor according to the current situation.
The method of claim 1, wherein the predetermined predefined situation is
Further comprising a steady state or an abnormal state with respect to the simulated subject and an operation state of the simulated subject.
The apparatus of claim 1, wherein the body sensing unit
And continuously detects the current state of the object to be inspected.
The apparatus of claim 3, wherein the body sensing unit
Detecting the change of the current state of the subject to determine the next situation, and activating only the next effective sensor according to the next situation.
The apparatus of claim 1, wherein the body sensing unit
Wherein the current state of the subject is determined through the constant sensor among the plurality of sensors.
2. The method of claim 1,
And a current operation state of the inspected object.
The apparatus according to claim 1, wherein the utility sensor determination unit
Wherein the sensed data population is generated by collecting sensing data including vehicle information, image information, audio information, and biometric information on the simulated subject.
8. The apparatus according to claim 7, wherein the utility sensor determination unit
And generating processed data about at least a part of the sensing data population.
9. The apparatus according to claim 8, wherein the utility sensor determination unit
And generating the processed data regarding the face direction if at least a part of the sensing data population includes face coordinate information.
9. The apparatus according to claim 8, wherein the utility sensor determination unit
And generating the processed data on the degree of dialogue if at least a portion of the sensing data population includes speech amplitude information.
9. The apparatus according to claim 8, wherein the utility sensor determination unit
Processable data for at least one of the processing data and at least one of the sensing data population that is not associated with the processing data. Device.
12. The method of claim 11, wherein the pre-treatment for efficacy analysis comprises:
Processing data that has various characteristics and a wide range of values to at least one pre-processing analysis model to generate at least one pre-processing data that is comparable between data of similar data characteristics A device for determining the effectiveness of sensing data.
13. The method of claim 12, wherein the at least one pre-
(RMSE), a major frequency analysis model, an average size analysis model, an average frequency analysis model, an average duration analysis model, a maximum variation analysis model, and a ratio analysis model Wherein the sensing data comprises a plurality of sensing data.
13. The apparatus according to claim 12, wherein the utility sensor determination unit
And the efficiency analysis is performed based on the pre-processing data to determine a meaningful efficiency sensor in the specific situation.
15. The apparatus of claim 14, wherein the utility sensor determination unit
A statistical significance test method for analyzing the effectiveness of at least one specific sensor associated with the at least one pre-processed data by comparing the case where the abnormality is likely to occur with the case where the abnormality is likely to occur for each of the predefined specific situations And the efficiency analysis is performed through the use of the sensing data.
16. The apparatus of claim 15, wherein the utility sensor determination unit
Wherein the efficiency analysis is performed by selecting one of a parameter and a nonparametric test method included in the statistical significance test method based on the number of samples of the sensing data population.
The method according to claim 1,
And a state determination unit for determining a state of the subject based on a result of sensing the subject through the current efficiency sensor.
18. The method of claim 17,
And a population updating unit for adding the sensing data and the status determination result about the subject to the sensing data population when the status determination for the subject is completed to support the updating of the sensing data population specified for the subject, Apparatus for determining the effectiveness of data.
A method for determining the effectiveness of sensing data performed by an apparatus for determining effectiveness of sensing data,
A utility sensor determination method of generating a sensing data population related to a simulated subject in a specific situation predetermined through a plurality of sensors and analyzing the sensing data population to determine a meaningful efficiency sensor in the specific situation; And
A method for determining the effectiveness of sensing data comprising the steps of: determining a current state of a subject and sensing the subject through a current efficiency sensor according to the current situation.
A utility sensor determination unit for generating a sensing data population related to a simulated driver in a specific situation predefined through a plurality of sensors and analyzing the sensing data population to determine a meaningful efficiency sensor in the specific situation; And
And a driver sensing unit for determining a current state of the driver and sensing the driver through a current efficiency sensor according to the current situation.

Images