WO2004082479A1 - 心身状態判定システム - Google Patents
心身状態判定システム Download PDFInfo
- Publication number
- WO2004082479A1 WO2004082479A1 PCT/JP2004/002054 JP2004002054W WO2004082479A1 WO 2004082479 A1 WO2004082479 A1 WO 2004082479A1 JP 2004002054 W JP2004002054 W JP 2004002054W WO 2004082479 A1 WO2004082479 A1 WO 2004082479A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- state
- mental
- subject
- psychosomatic
- determination system
- Prior art date
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
Definitions
- the present invention measures a human's load value or a time-series signal of the position of the center of gravity without making the subject aware, and predicts or determines a mind-body state such as awakening or non-wakening of the subject based on chaos theory.
- the present invention relates to a psychosomatic state determination system. Background art
- Patent Document 1
- Patent Document 2
- Patent Document 1 Japanese Patent Application Laid-Open No. 9-1109273 (Page 5, paragraph 50)
- the devices disclosed in Patent Document 1 and Patent Document 2 are capable of determining the head tilt and the number of blinks to be judged. It is subjective whether you fall asleep because of individual differences It is often left to judgment, and it is difficult to make an accurate judgment, and it is not possible to distinguish between a state before falling asleep and a state of being fully awake, and it is not possible to completely prevent accidents before they happen was there.
- the present inventor calculates a psychosomatic state index such as a Lyapunov exponent from a time series signal of a human load value or a center of gravity position showing chaotic behavior, and compares it with a known psychosomatic state index. Predict or judge the mental and physical condition of the person to be measured unconsciously and without any subjective judgment without burdening the person to be measured, and prevent accidents before falling asleep, etc. Invented a mental and physical condition judgment system that can do it.
- a psychosomatic state index such as a Lyapunov exponent from a time series signal of a human load value or a center of gravity position showing chaotic behavior
- the “mental and physical condition” in the present invention refers to a physical health condition and a psychological condition.
- health states include “wake” awake state and “sleeping” non-awake state, and non-awake state can range from light sleep (REM sleep) to deep sleep (non-REM sleep). It is divided into each stage.
- the psychological state includes states expressed by fatigue, tension, anxiety, and the like.
- Physical health and psychology The states are all caused by the work of the brain and are closely related, so these are collectively referred to as “mental and physical states”.
- the mental and physical state is caused by the function of the brain, in the present invention, the “mental and mental state” is synonymous with the “brain function state”.
- the chaos theory is "The e s s se en c e o f c ha o s (E.
- N. Lorenz refers to "theory of finding dependence on initial conditions from stochastic vibration phenomena occurring in nonlinear systems, etc.” and "Lyapunov exponent
- the psychological and physical condition index refers to a numerical value for quantitatively determining whether or not it is chaos in the chaos theory.
- the human load value shall include a value that can be converted to a load value or a value (acceleration value, etc.) obtained in response to the load value.
- a psychosomatic state determination system for predicting a psychosomatic state such as an awake state or a non-awake state of a human, and a data processing means for calculating a psychosomatic state index such as a Lyapunov exponent from a time series signal of a load value or a center of gravity of a subject. And comparing the temporal trend of the psychosomatic state index calculated by the data processing means with the temporal trend of the known psychosomatic state index corresponding to the psychosomatic state to predict the psychosomatic state of the subject.
- This is a psychosomatic state determination system having evaluation means for performing the evaluation.
- a psychosomatic state determination system that determines a psychosomatic state such as an awake state or a non-awake state of a person, and a data processing means for calculating a psychosomatic state index such as a Lyapunov exponent from a time-series signal of a load value or a center of gravity position of a subject. Evaluation means for comparing the numerical value of the physical and mental state index calculated by the data processing means with the numerical value of the known physical and physical state index corresponding to the physical and mental state to determine the physical and physical state of the person to be measured.
- a psychosomatic state determination system having
- Claims 1 and 2 does not make the person In addition, it is possible to predict or judge the mental and physical condition of the subject without relying on subjective judgment.
- the invention of claim 3 is:
- a psychosomatic state determination system including a sensor that outputs a load value of the subject.
- the third aspect of the present invention by using a sensor that outputs a load value, it is possible to predict or judge a mental and physical state without making a person to be measured conscious.
- the one sensor is a mental and physical condition determination system.
- the fourth aspect of the invention it is not necessary to take into account synchronization between a plurality of sensors and an individual difference due to an output delay generated between the sensors, and it is possible to reduce the cost of parts.
- the invention of claim 5 is:
- the sensor is a psychosomatic state determination system that is one of a pressure sensor such as a piezo element, a pressure-sensitive resistor element, a potentiometer, or an acceleration sensor.
- a pressure sensor such as a piezo element, a pressure-sensitive resistor element, a potentiometer, or an acceleration sensor.
- the invention of claim 6 is:
- the sensor is a psychosomatic state determination system attached to a chair or a bed on which the load of the subject is applied.
- the invention of claim 7 is:
- the chair or bed is a psychosomatic state determination system having an elastic material such as a spring therein.
- the subject can be made to feel less uncomfortable, and the sensor can be directly inserted into the inside, and there is no need to provide the sensor under the floor.
- unnecessary frequency components are removed from the time series signal of the load value or the position of the center of gravity, and the accuracy of prediction or judgment of the mental and physical condition is improved.
- the invention of claim 9 is:
- a psychosomatic state determination system for sampling a time series signal of the load value or the position of the center of gravity of the subject at a frequency of 100 Hz to 100 Hz.
- a time-series signal of a frequency necessary for chaos analysis can be extracted, and the same effect as monitoring the physical and mental state continuously with a small number of samples can be obtained.
- a time-series signal having periodicity it becomes possible to perform signal processing and calculate a psychosomatic state index at high speed.
- This is a psychosomatic state determination system including an amplifying means for amplifying a time series signal of the load value or the position of the center of gravity of the subject.
- the signal when the time series signal of the load value or the position of the center of gravity is small, the signal is amplified to facilitate data processing.
- This is a psychosomatic state determination system including a calculating unit that calculates a center of gravity of the subject from respective load values output from the plurality of sensors.
- the position of the center of gravity is calculated from two or more sensors. Rukoto can.
- a warning is issued to the measured person using a display device and a Z or a speaker based on the predicted or determined mental and physical state of the measured person, or the measured person is managed.
- This is a psychosomatic state determination system that has a warning means to notify the management station.
- the result of prediction or judgment of the mental and physical condition of the person to be measured is transmitted to the place where the person under measurement is managed or controlled, or the person to be measured is prevented beforehand and surely. I can do it.
- the invention of Claim 13 is:
- It has operation detecting means for detecting an operation state and a driving state of the person to be measured in chronological order
- the evaluation means comprises a known mind and body corresponding to the state detected by the operation detection means and the mind and body state. Comparing the temporal tendency and z or the numerical value of the state index with the calculated temporal tendency and Z or the numerical value of the mental and physical state index to predict or judge the mental and physical state for each of the states of the subject. It is a state determination system.
- the psychosomatic state index varies depending on the state of the person to be measured, it is possible to predict or judge the mental and physical state sequentially according to the state.
- the invention of Claim 14 is:
- a stimulus output unit that applies a stimulus such as a physical stimulus or an audio-visual stimulus to the subject; and the evaluation unit includes a temporal output of a known psychosomatic state index when the stimulus is output from the stimulus output unit.
- a psychosomatic state determination system for predicting or judging the psychosomatic state of the subject by comparing a tendency and Z or a numerical value with a temporal tendency and / or a numerical value of the calculated psychosomatic state index.
- the stimulus output unit outputs the stimulus having an effect of preventing an abnormal mind and body state from being abnormally based on the predicted or determined mental and physical condition of the person to be measured. It is a mental and physical condition judgment system that promotes changes in the behavior of the elderly.
- FIG. 1 is a diagram showing an example of a system configuration of a psychosomatic state determination system of the present invention.
- FIG. 2 is a diagram showing another example of the system configuration of the psychosomatic state determination system of the present invention.
- FIG. 3 is a diagram showing another example of the system configuration of the psychosomatic state determination system of the present invention.
- FIG. 4 is a diagram showing an example of a chair to which a sensor is attached.
- FIG. 5 is a diagram showing another example of a chair to which a sensor is attached.
- FIG. 6 is a diagram showing another example of a chair to which a sensor is attached.
- Fig. 7 is a graph showing the time change of the output signal of the acceleration sensor attached to the chair. It is rough.
- FIG. 1 is a diagram showing an example of a system configuration of a psychosomatic state determination system of the present invention.
- FIG. 2 is a diagram showing another example of the system configuration of the psychosomatic state determination system of the present invention
- FIG. 8 is another graph showing the time change of the output signal of the acceleration sensor attached to the chair.
- Figure 9 is a graph showing the temporal change of the psychosomatic index.
- FIG. 10 is a diagram showing an embodiment of a restructuring of an attractor. BEST MODE FOR CARRYING OUT THE INVENTION
- FIG. 1 is an example of a system configuration of a psychosomatic state determination system 1 of the present invention.
- the psychosomatic condition determination system 1 includes a psychosomatic condition evaluation means 2, a sensor 3, a noise removing means 4, and a warning means 5.
- the psychosomatic state evaluation means 2 is means for predicting or judging the psychosomatic state of the subject 6 from the load value of the subject 6 or a time-series signal of the position of the center of gravity.
- a sufficiently awake human brain processes innumerable information from the outside world efficiently, and the movement of the center of gravity draws a stable trajectory in chaos theory.
- the general term for a stable solution that has the property of attracting its trajectory that is, the set in which the trajectory asymptotically is called an attractor, and an attractor that exhibits chaos has a geometrically complex structure. Therefore, it is generally called strange tractor.
- the load value of the subject 6 required in the psychosomatic state evaluation means 2 includes a load value applied to a pressure sensor or the like, a value that can be converted to a load value, or a value obtained corresponding to the load value ( Acceleration data, etc.), and the data may be one-dimensional or multi-dimensional. Similarly, the number of dimensions does not matter for the position of the center of gravity.
- the mental and physical condition evaluation means 2 has data processing means 20, evaluation means 22, and index database 24.
- the data processing means 20 is a means for calculating a psychosomatic state index from a load value of the subject 6 or a time-series signal of the position of the center of gravity.
- the mental and physical condition index is a numerical value that is the basis for predicting or judging mental and physical condition. Specifically, it refers to a Lyapunov exponent used for the chaos index, and a numerical value that can quantitatively determine whether or not it is chaos in chaos theory or a time average value of the numerical value.
- This psychosomatic condition index is an index calculated for each psychosomatic condition, which has few individual differences, such as pulse rate and blood pressure, unlike an index that has individual differences of several hundred percent or more, such as steroids in blood and saliva. is there.
- the psychosomatic index is not limited to the conventional Lyapunov index, but may be a brain function index as described in detail later.
- the brain function index is an index for evaluating chaos, like the conventional Lyapunov index, but the calculation target is the time series signal of the weight value or the position of the center of gravity of the subject 6 and the time series signal of the continuous speech sound. This is a value calculated after specifying a time-series signal that has strong periodicity or periodic characteristics (a spectrum in which a clear peak appears on the frequency axis due to frequency analysis). .
- the brain function index is calculated more stably and faster than the conventional index because in the calculation process, a neighborhood point set is generated by previously extracting processing units based on the periodicity of the time series signal. Is a possible psychosomatic index is there. Therefore, it is possible to more quickly and accurately predict or judge the state of mind and body, and it is particularly effective in a situation where it is necessary to reliably prevent human error due to falling asleep.
- the evaluation means 22 is based on the result of comparing the psychosomatic state index calculated by the data processing means 20 with the known psychosomatic state index stored in the index database 24, and is based on the result of the comparison. This is a means for predicting or judging the state.
- the index database 24 stores the temporal trend and Z or numerical value of the psychosomatic state index corresponding to a certain psychosomatic state. For example, the values and tendency of the mental and physical condition index when a standing person is awake, and the numerical value and tendency of the mental and physical condition index when a sitting person is tired are stored. Temporal tendency is also the temporal change (gradient) of the psychosomatic state index, and can be represented by numerical values, positive / negative signs, ratios, and the like. Since the psychosomatic state index is calculated from the load value of the subject 6 or a time-series signal of the position of the center of gravity, the subject is measured without being conscious of the subject 6 and consciously and without any subjective judgment.
- the subject 6 is objectively predicted, rather than subjective, that he or she is likely to sleep, and when settled at a certain value, it is judged objectively, not subjectively, that he or she slept. You can do it.
- the sensor 3 may be any sensor that outputs a load value of the person 6 to be measured, a value that can be converted to the load value, or a value obtained in accordance with the load value.
- weight A sensor that measures weight like a gauge, a potentiometer that changes the resistance value in proportion to the magnitude of pressure by a pressure-sensitive resistor element, a sensor that generates electromotive force by a combination of a coil and a magnet
- the sensor 3 includes various sensors such as a sensor that outputs an electric signal proportional to the magnitude of pressure, such as a piezo element, a capacitance-type sensor, and an acceleration sensor that outputs an acceleration value. That is, any sensors such as a pressure sensor, a strain sensor, a displacement sensor, and an acceleration sensor may be used.
- the sensor 3 include an FSR series pressure-sensitive resistor element manufactured by Interlink Electronics.
- the position of the center of gravity may be specified by comparing output values of two or more sensors 13 such as pressure sensors.
- trims and volumes for adjusting the levels of these output signals are provided.
- sensors 3 are compact, have improved pressure resistance, and are easily available, so they can be easily built into chair seats, backrests, beds, etc., without making the subject 6 aware. It is possible to measure the load value and the position of the center of gravity.
- the signal obtained from the sensor 3 may be one-dimensional as described above, that is, in the case where the mental and physical condition is predicted or determined from the time series signal of the load value. All you need is one sensor.
- FIGS. 4 to 6 show specific examples in which a sensor is attached to a chair and the body or body condition is predicted or judged from the load value of the subject on the chair.
- Figure 4 shows It is a front view (a) and a side view (b) of a chair 7a with four pressure sensors installed as feet 3a as sensors 3a. The sensor 3a is hidden under the floor A.
- the center of gravity of the person to be measured is calculated from the output values of the four sensors 13a, and this center of gravity is calculated. It is also possible to predict or judge the mental and physical condition of the subject by performing chaos analysis on the time series signal of the position.
- Fig. 5 and Fig. 6 show that the elastic material 8 such as a spring is sandwiched under the seating surface of the chair 7, and the resistance change due to expansion and contraction and distortion of the elastic material 8 is measured with a sensor 3 such as a potentiometer This is an example of what is done.
- FIG. 6 (a) which shows the chair 7c in FIG. 6 (b) from above, the elastic material 8c is sandwiched between the four corners of the chair 7 and the sensor 13c is located at the center of the chair 7c. It can be seen that they are arranged.
- the use of the conductive material 8 makes the chair 7 less uncomfortable when the person to be measured sits down, and the sensor 3 can be directly inserted into the interior of the chair 7, such as under the floor or the feet of the chair 7. There is no need to provide sensor 3.
- the elastic material 8 may be any material such as metal, rubber, silicone, and polyurethane as long as it can be deformed according to the magnitude of the load. Also, the shape does not matter.
- Figs. 4 to 6 show examples of chairs. However, even if the sensor 13 is attached to a bed, floor, backrest of a chair, etc., which is subject to the load of the person to be measured, the force is similarly reduced. Analysis is possible. As a result, the subject is sitting on a chair, lying on a bed, or standing, for example, driving a patient at a hospital or a vehicle such as an automobile or an aircraft. Or judgment of the mental and physical condition of the elderly Can be performed without the subject's consciousness.
- the required sampling frequency of the data is preferably about 100 Hz to 100 H 2. This is because the fluctuation of the chaos at the load value or the position of the center of gravity has a low frequency of about 10 1 ⁇ 2 to about 100 112, and the frequency components higher than that can be regarded as noise. Therefore, even when the state of mind and body is continuously monitored, a relatively small number of samples is required, and the capacity of the television is not enormous.
- chaos theory is a theory in which data is sampled at the next time, the behavior of the sampled data is observed at the next time, and the behavior of the sampled data is observed at the next time, and the dependence is obtained. Depending on the amount of superimposed noise, the prediction of chaos itself changes greatly, so the required resolution of the load value or the data of the position of the center of gravity is
- the noise removing unit 4 is a unit that removes a noise component that is unnecessary when the data processing unit 20 calculates the psychosomatic condition index from the signal of the load value or the position of the center of gravity of the subject 6.
- the noise removing means 4 usually removes unnecessary frequency components using an analog or digital low-pass filter or a high-pass filter. By removing frequency bands that are impossible in the theory of chaos theory, noise components generated by the subject 6 sneezing, noise components superimposed on the power supply, etc. The accuracy of the judgment can be improved.
- the warning means 5 is a management station 9 that manages the subject 6 or the subject 6 when the subject 6 is between the awake state and the non-awake state, or in an abnormal state of mind and body. And the like.
- the person to be measured 6 It is possible to warn the person to be measured 6 by displaying the contents of the warning on the display device 11 or outputting a warning sound or a threatening sound from the speaker 110 through the warning means 5.
- the condition of the subject 6 is reported to the management station 9 which manages and controls the person 6 to be measured. For example, a warning or a command can be issued to the person 6 to be measured.
- the warning means 5 can prevent accidents due to human errors, such as the subject 6 falling asleep, before and reliably.
- the operation of the psychosomatic state determination system 1 will be described using the system configuration of FIG.
- a case will be described in which the mental and physical state of the subject 6 sitting on a chair 7 having a built-in sensor 13 as shown in FIG. 6 is predicted or determined.
- the sensor 3 is an acceleration sensor.
- FIGS. 7 and 8 show time series data of the output value of the acceleration sensor 1 in a certain time range.
- FIG. 8 is an enlarged view of the time axis of a certain time range in FIG.
- FIG. 9 shows the calculated psychosomatic state index versus time data.
- the psychosomatic index shown in FIG. 9 is a brain function index, and a detailed calculation method will be described later.
- the calculated psychosomatic state index is compared with the psychosomatic state index stored in the index database 24.
- the mental and physical condition index does not increase as described above just because the subject is tired in any state.
- the person sitting in front of the radar scope in the air traffic control room, or the chair in front of the instrument panel in the plant monitoring room Tired when sitting in
- the movement of the center of gravity becomes firm and mechanical, so the psychosomatic state index calculated from the time-series signal of the load value gradually decreases compared to when in the awake state, and then completely sleeps After that, it calms down to a certain low value.
- the index database 24 in the present embodiment shows that when the subject 6 is sitting on the chair 7, the mental and physical condition index gradually shifts from higher to lower. If the tendency is shown, it is predicted to fall asleep, and if a certain value is shown, it is judged to be dozing, so that the temporal tendency of the psychosomatic state and the psychosomatic state index and Z or numerical value are stored in association with each other. .
- the mental and physical condition index is initially high during the period (1) in the figure, and the subject 6 monitors the display while awake.
- the psychosomatic state index gradually decreased, it is possible to predict that the subject 6 is in a semi-awake state before sleeping.
- the psychosomatic state index is generally stable at a lower value than at the time of awakening in (1), the subject 6 is falling asleep. It is determined that the user is in the awake state.
- the psychosomatic state index should rise further and return to the awake state. Since the noise level was low and had only a small effect on the subject 6, the psychosomatic state index settled to a low value again, and it was determined that the subject 6 returned to a completely non-awake state .
- the prediction or judgment of the physical and mental state was made from the output value of one acceleration sensor.However, any number of sensors 3 that output the load value or the position of the center of gravity were used. The prediction or judgment of the mental and physical condition does not change, and uniform results can be obtained. As described above, according to the present embodiment, it can be understood that the mental and physical condition of the subject can be predicted or determined without making the subject 6 conscious and without any subjective judgment.
- the conventional calculation of the Lyapunov index is based on the system (system, in this embodiment, the subject
- the time series signal of the load value or the position of the center of gravity has a short duration or repetition time of a certain dynamics, so even if the conventional Lyapunov exponent is calculated for each dynamic, the number of convergence calculations is limited, and the number of convergence calculations is not necessarily limited.
- the value is not considered to be valid, and the value obtained in about 5 minutes is averaged to increase its validity.
- the conventional calculation of the Lyapunov exponent assumes not only periodic time-series signals but also general time-series signals including non-periodic time-series signals.
- it takes time to search for a nearby point in a processing unit and conversely, if the processing unit is set short, the convergence calculation tends to be unstable.
- it is difficult to optimize parameters such as processing units and neighborhood conditions as it takes time to search for neighboring points if the number of samples is simply increased to improve the accuracy of the convergence calculation.
- the conventional calculation of the Lyapunov index was time consuming.
- a method for calculating a brain function index has been invented. That is, instead of searching for a neighboring point from processing units at a predetermined fixed interval, a set of points that can be a candidate for a neighboring point is generated by using a range in which the period of the time-series signal is stable as a processing unit. By doing so, a set of neighboring points with high convergence can be generated from the beginning, even if the processing unit and neighboring conditions are not specified. Therefore, not only is the processing speeded up, but also a local psychosomatic state index can be calculated stably and immediately even for a time-series signal with a short duration of dynamics.
- (B) in the figure on the right shows how a time-delay vector is plotted into a time-delayed coordinate system to reconstruct an attractor.
- this dimension m is a dimension that can correctly represent the information of the system from which the original time-series signal was obtained, m is called an embedding dimension. If the attractor is reconstructed with the correct embedding dimensions, it will be possible to evaluate the chaos of the system. The condition under which the conversion to the reconstructed state space using the time-delayed coordinates becomes embedded is proved by the embedding theorem of Takens, and is publicly known.
- s (t) is a time-series signal obtained by sampling the output signal of the sensor 3 at a constant sampling frequency f (HZ). Note that the time interval between adjacent time-series signals (for example, s (1) and s (2)) is It is based on the sampling period (lZf) (s).
- the size N of the neighborhood point set needs to be equal to or greater than the embedding dimension number D + 1, and is set according to the properties of the time-series signal. It is desirable to set D + 2 and D + 3 or more in order to stably perform the calculations described below without causing division by zero, etc., but even if D + 1, the sampled time series By dithering the signal, it is possible to prevent the division by zero.
- dithering is to intentionally add noise to a signal, and is common in digital processing of audio signals. The accuracy of restoring the digital signal to the original analog signal may be increased by performing the dither processing.
- the size N of the set of neighboring points is set to prevent the points with different dynamics from entering into the set of neighboring points or the set of points that are candidates for neighboring points. It is preferable to set as small as possible as long as stable calculation is possible. For example, if the embedding dimension is 4, the size N of the set of neighboring points is preferably about 6 or 7.
- the embedding delay time d and the evolving delay time e can be formed only from the point where the time-series signal is sampled, a value that is an integral multiple of the sampling period is selected.
- a set x x (i) of time series signals having a period T satisfying T m ⁇ T ⁇ T M is cut out from the time series signal s (t) as a processing unit for brain function index calculation.
- the cycle T may differ depending on the processing unit cut out.
- the prediction of the period T and whether the processing unit X (i) is a set that satisfies the period T is performed by frequency analysis such as discrete Fourier transform (DFT), linear prediction analysis (LPC), and wavelet analysis. This is done using a technique.
- DFT discrete Fourier transform
- LPC linear prediction analysis
- wavelet analysis wavelet analysis.
- not only the periodicity condition of having the period ⁇ but also a condition according to the level (amplitude) of the sampled signal may be added to the extraction of the processing unit. For example, the fact that the dynamic range of the signal is greater than or equal to a certain value may be added as a processing unit cutout condition.
- the period T is not naturally defined as described above, for example, every 10 ms.
- a processing unit is sequentially cut out in a predetermined fixed time unit. Therefore, in the case of the conventional calculation of the Lyapunov exponent, a set of neighboring points has not yet been generated at this point, and a predetermined processing unit Since a set of neighboring points that satisfies a predetermined neighborhood condition is searched from all the sampled time-series signals, processing takes time. Next, the radius of the hypersphere containing the above-mentioned neighborhood point set P is set as the neighborhood distance ⁇ s and given by the following equation.
- this neighborhood distance ⁇ s is a parameter that is indispensable as a neighborhood condition when searching for a neighborhood point set. Or, since a set of points that are candidates for neighboring points has been generated, it is not always necessary to use them as neighborhood conditions.
- the neighborhood distance £ s is used as a neighborhood condition as a meaning of sifting the extracted processing unit.
- This condition (convergence calculation continuation condition) shall be used.
- the extracted processing unit contains strong white noise that should not have the original periodicity.
- a signal whose dynamic range is a certain value or more is regarded as non-white noise, and a processing unit is cut out. You may.
- the processing unit X (i ) Is rejected. Then, a new processing unit X () is generated starting from a point in time series with respect to the processing unit X (i), and a set of neighboring points P 'generated from X (i') is used as a neighborhood condition. To determine if you are satisfied. However, if sieving of processing units is not performed, skip this process and A processing unit starting from all sample points or an arbitrary sample point in the column signal s (t) may be generated, a set of neighboring points may be generated for each processing unit, and the following calculation may be performed.
- the development delay time e is applied to generate a development point set s of the neighborhood point set P as follows.
- S i is a development point for P i.
- the evolution set S ⁇ S shown in Equation 4. , S..., S (N _ 1 ⁇ ⁇ is composed of a set of elements that are sequentially delayed by e from each component of the neighboring point set P.
- the above-mentioned neighboring point set P is a reference.
- the displacement between the neighboring point P Q and the other neighboring points Pj is defined as follows: Further, the displacement is similarly defined for the development point set s.
- Equation 7 is matrix A. Is described by the least squares method.
- the cerebral function index is a local X value because a set of neighboring points is generated in synchronization with the periodicity of the time series signal. And its numerical value have a high correlation.
- the following convergence calculation is performed to improve the temporal and local reliability of the brain function index.
- the convergence calculation in the conventional Lyapunov exponent is indispensable as a means to confirm the validity of the correlation between the previously searched near-point set and its evolved point set. Since the validity of the point set and its development point set is extremely high, the purpose of the calculation differs from the conventional convergence calculation using the Lyapunov exponent. In the convergence calculation, first, the period T starting from the earliest point in time series (that is, the first point of S.
- x Q + ie among the time series signals constituting the advanced point set S is first calculated.
- a new processing unit X l (i) is cut out.
- the number of components of X l (i) is (n Q + l) like X (i) above.
- a neighboring point set P (1) is generated from this X l (i) in the same manner as above, and the same as the previous neighboring point set P, If the neighborhood condition and Z or the convergence calculation continuation condition are satisfied, the development point set S is derived from P (1).
- the convergence calculation means that the brain function index is calculated for each dynamic. As a result, even if a plurality of different dynamics are simultaneously overlapped, the brain function index is calculated for each dynamic, that is, by the number of dynamics.
- the earliest point in time series among the time-series signals constituting the (n ⁇ 1) th development point set S (n ⁇ 1) Generate a processing unit x n (i) that satisfies the periodicity condition. If this processing unit satisfies the periodicity condition, generate a neighboring point set P (n) . The neighboring point set P (n) satisfies the previous neighborhood condition. Only when this occurs, the evolution point set S (n) is generated, that is, the convergence calculation is continued.
- the convergence calculation times are calculated as in the conventional Lyapunov exponents.
- the calculation of the brain function index also contributes to speeding up the processing without repeating the number of times without knowing the significance.
- the neighborhood condition and the convergence calculation continuation condition need not be uniform, and may be changed according to the number of times of convergence. For example, for the nth convergence calculation Is that the calculated neighborhood distance ⁇ s is less than or equal to the neighborhood distance ⁇ s X (n ⁇ 1) of the neighborhood point set P (n ⁇ 1) in the (n ⁇ 1) th convergence calculation. Or .. ⁇ S X (n-1) X a (a is a constant .. For example, a ⁇ l. 1)
- the brain function index in the present embodiment indicates the largest numerical value of the celebral spectrum c. That is, x.
- the brain function index corresponding to is
- R k s indicates the s-th one of the diagonal components of the matrix R k in the order of increasing numerical value.
- Conventional Lyapunov exponent A m is equivalent to c s, in R k m to A m refers to m-th diagonal element of the matrix R k.
- another processing unit X (i ') is cut out and the starting point x in it.
- the convergence calculation corresponding to, and the calculation of the cerebral spectrum and brain function index are performed in the same manner as above. Theoretically, if a processing unit that satisfies a certain periodicity condition can be extracted from all the sample points starting from the sample point, a celebral spectrum for that sample point is obtained. It is not necessary to perform calculations for every sample point. Here, basically, the same operation continues, such as when the subject is sitting in a chair and standing still, and the measurement is compared with the case using the conventional Lyapunov exponent. If you do not require a particularly high temporal resolution,
- the results can be displayed in a time-series graph to visually grasp changes in the physical and mental state.
- the brain function index is calculated with higher accuracy at a higher temporal resolution than the conventional Lyapunov index, and in order to make it easier to visually grasp more detailed changes in physical and mental states, the The method of processing the brain function index will be described below.
- c m (t) is time t (excised time the starting point of the processing units) in the brain function index
- s s (t) is near distance gave the brain function index
- T (t ) Is the cycle obtained by frequency analysis at the time of processing unit extraction.
- t is, of course, a time based on the sampling period.
- CEm (t I to ⁇ tt a period in which the dynamics are almost constant, that is, a period in which the dynamics are almost constant, for example, a period in which a straight road is driven at a constant acceleration in Example 2 described later,
- the period of sleeping in the same posture, etc. is equivalent to a certain duration of operation
- the duration of a phoneme composed of a certain vowel in the speech voice signal In the case of Japanese, the period is characterized by each vowel Because there is.
- CEm (i I 1 ⁇ i ⁇ n) is obtained by sorting the elements in CEm (t I t 0 ⁇ t ⁇ t l ) in ascending order according to the size of ⁇ s (t). And From this CEm (iI l ⁇ i ⁇ n), the brain function index C M for each operating state is Given by the formula.
- p is a numerical value indicating the percentage of the 100th fraction
- cm ( i ⁇ )) represents the nXp-th element.
- p 10%
- CEm (i I 1 ⁇ i ⁇ n) from the smallest ⁇ s to 10% of the total number of elements
- mean values of these extracted elements c m (i) is a brain function index C M corresponding to each operation state.
- the brain function index C M obtained here is subjected to temporal moving average processing, and a graph is shown in FIG. 9 used in the previous embodiment.
- the mental and physical state changes within the period even if the dynamics do not change much. T, which would impede immediate mental or physical condition prediction or judgment.
- ⁇ a period T ⁇ ti subdividing extent coming out track changes in mental and physical conditions may be calculated brain function index C M in the (number of samples of the order of thousands) divided period each.
- the change time or the change time of the dynamics is the extraction timing of CEm (tI to ⁇ t ⁇ ti).
- p may be varied according to the measurement accuracy of the time-series signal obtained from the sensor 3 and the conversion performance when converting an analog time-series signal into a digital signal.
- p is 10 to About 20% Is good.
- the performance of either the sensor 3 or the AD converter is poor, and P is preferably set to 30% or more for a signal having a large noise level due to this performance.
- the brain function index C M psychosomatic state determination system of the present invention Upon using the brain function index C M psychosomatic state determination system of the present invention, its temporal tendency, if not requiring high resolution on a relatively time axis, that is, if it is not a high precision, it is also possible to calculate the cerebral function exponent C M as follows. First, the following equation is obtained based on the elements (c m (t), ⁇ s (t), and T (t)) constituting CEm (t It. ⁇ t ⁇ t), based on the magnitude of ⁇ s .
- the brain function index C M (t I t. ⁇ t ⁇ t for C Em (t I t. ⁇ t ⁇ t is given by the following equation for the magnitude of the near-Chiseca distance £ s (t). 1 3 ⁇ )
- ⁇ s is the number of elements of cm that satisfies that it is 10% or less of the diameter of the strange attractor at the time when cm is given.
- ⁇ ° (t I t. ⁇ t ⁇ t from elements in C Em (t I t. ⁇ t ⁇ t , ⁇ s is 1 in the diameter of Strange ⁇ tractor at the time gave c m 0 % to extract elements such that follows, given as average values of these extracted elements c m.
- CM 1 "is, epsilon s is strange ⁇ tractor since obtained as the average value of c m 1 is less than 0% of the diameter, the extraction main prime not determined by r, varies depending times seeking C M.
- Cj can be mechanically calculated for any r where 0% ⁇ r ⁇ 100%.
- the processed time-series signal has strong chaos, such as the weight value, the position of the center of gravity, and the time-series signal of the uttered voice, the rate of change rapidly decreases at r> 10%. In order to judge or predict the mental and physical condition more correctly, it is necessary to set r ⁇ 10%.
- r needs to be set from 2% to 3% or more.
- the variables, formulas, and values required for calculating the brain function index are stored, and these variables, formulas, values are added, subtracted, multiplied and divided, calculus, functions, arrays, pointers, branch processing,
- a storage medium further storing a statement for use in arithmetic processing such as iterative processing and recursive processing constitutes a brain function index calculation program.
- the brain function index calculation program is executed by a general computer including hardware such as a memory, a processor, and a storage unit, and can be a component of the data processing unit 20.
- FIG. 2 shows an example of the configuration of the psychosomatic state determination system in this case.
- the psychosomatic condition judging system 1 a includes a psychosomatic condition evaluation means 2, a sensor 3, a differential amplification means 32, an analog / digital conversion means 34, a noise removal means 4, a warning means 5, and an operation detection means 12.
- the mental and physical condition evaluation means 2, the sensor 1, and the warning means 5 are the same as those described above, and a description thereof will be omitted.
- the noise removing means 4 is a means for removing unnecessary noise components as described in the first embodiment, but when the subject 6 is riding on a vehicle as in the present embodiment.
- the noise caused by these vibrations and the like is superimposed on the data of the signal obtained from the sensor 3 because the vibration components and the like of the vehicle temporarily generated by running on an unpaved road or starting the engine are superimposed as noise on the signal data obtained from the sensor 3. Removal is essential.
- the band elimination is performed.
- a sensor other than the sensor 3 that removes or attenuates a specific band at the time of measurement, or measures the biological signal of the person 6 to be measured is prepared, and a pure noise component obtained from the sensor 3 is provided at the subsequent differential amplification means 3. It is possible to remove noise components by subtracting by 2 etc.
- the differential amplifying unit 32 amplifies the output signal of the sensor 3. For example, if a pressure-sensitive resistor element is used as the sensor 3, an electric signal corresponding to the magnitude of the pressure can be obtained by inserting the output resistance of the pressure-sensitive resistor element into the input stage of the differential amplifier 32. Can be done. As a result, even when the load value and the time-series signal of the position of the center of gravity are small, the signal can be amplified to facilitate data processing.
- the differential amplifying means 32 is a means for specifying the position of the center of gravity from the measured load value which is the signal output of each sensor 3. But also.
- the position of the center of gravity is calculated by the differential amplifying means 32 by calculating the potential difference between the electric signals output from the respective sensors 3 at the same time. Can be obtained by comparing the locations of high
- the position and number of the sensors 3 for obtaining the position of the center of gravity are not particularly limited. Regardless of the position or number of sensors 3, the calculated time-series signal of the center of gravity is Therefore, it is not always necessary to arrange a large number of sensors 13 in a matrix, and at least two sensors 3 are required to calculate the position of the center of gravity. Since it is not necessary to arrange the sensors 13 in a matrix form, it is easy to introduce the apparatus of the psychosomatic state determination system 1 and there is a cost advantage. Conversely, if the number of sensors 3 is large, the output delay specific to each sensor 13 will be different, and unless this delay is constant between sensors 13, it will greatly affect chaos analysis. It is preferable that the number is small.
- the analog-to-digital conversion means 34 converts the signal amplified by the differential amplifying means 32 into a digital signal for processing by the data processing means 20 when the signal is an analog signal, and converts the time-series signal. It is a means to obtain.
- the above-described sampling and quantization may be performed in the analog-to-digital conversion means 34.
- the motion detection means 12 is a means for detecting the motion state and the driving state of the person 6 to be measured in a time-series manner. For example, the load value and the position of the center of gravity differ depending on whether the user is sitting in a chair, standing still, standing still, or driving a vehicle. Even so, the time trends and figures of the psychosomatic state index are different.
- the acceleration state depends on the direction change and acceleration such as turning a curve or turning right or left. And the state of the position of the center of gravity changes, it is necessary to detect the operation state of an acceleration sensor such as an accelerator or the like, a brake or a steering wheel by the operation detecting means 12 to grasp the driving state.
- an acceleration sensor such as an accelerator or the like, a brake or a steering wheel
- the time lag of the dimension greatly affects the prediction of chaos.
- the obtained time-series data and the time-series data of the position of the center of gravity obtained from the sensor 3 are synchronized with each other so that there is no delay. It is desirable.
- the mental and physical condition determination system 1a removes an unnecessary frequency component from a signal obtained by converting the pressure signal indicating the load state of the subject 6 received by the sensor 3 into an electric signal, and removing the unnecessary frequency component in the noise removing means 4. Then, the center-of-gravity position of the subject 6 is calculated by processing in the differential amplifier means 32, and the time-series signal of the center-of-gravity position is converted into a digital time-series signal in the analog-to-digital conversion means 34. Then, the data processing unit 20 calculates the psychosomatic state index.
- the index database 24 stores the temporal trends and Z or numerical values of the known psychosomatic state indices corresponding to the mental and physical states for each operating state and driving state of the person 6 to be measured.
- the known psychosomatic state index in the state of the subject 6 detected in the above is compared with the psychosomatic state index calculated in advance. This makes it possible to sequentially predict or judge the mental and physical state according to the state where the subject 6 is placed.
- the driver of the vehicle receives various information from the outside world with his eyes and ears, and receives information on the road surface from the chair as a bodily sensation.
- the trajectory of the position of the center of gravity of the body also corresponds to the required change in posture, and even in the case where acceleration works, it is possible to foresee the occurrence of acceleration from the view information in advance, It is possible to cope with less stable movement of the center of gravity.
- the brain does not accept information from the outside world, and the trajectory of the center of gravity becomes simple in flat running such as running on a straight road.
- the value of the psychosomatic condition index decreases, but conversely, acceleration works. If the person goes wrong or turns a curve, the body's response will be delayed, and wasteful movement will increase. The position of the center of gravity will become unstable, and the value of the psychosomatic state index will increase.
- the temporal tendency and the numerical value of the physical and mental state index differ depending on the operation state and the driving state of the person 6 to be measured.
- a database is prepared for each state detected by the motion detection means 12 and the calculated psychosomatic state index and the known psychosomatic state index for each operating state and driving state at that time are used. Predict or judge mental and physical condition by comparing
- the processing unit extraction and convergence calculation will be performed at the time the periodicity changes.
- the brain function index can be calculated for each dynamic, that is, the dynamic state.
- the processing unit is cut out based on the periodicity of the time-series signal, even if multiple different dynamics overlap at one time, the brain function index is calculated for each dynamic, that is, as many as the number of dynamics Is done.
- the method of calculating the brain function index is as described in Example 1, but t is selected from the C Em (t) obtained earlier. ⁇ t ⁇ t ⁇ , and let it be C Em (t I t. ⁇ t ⁇ t.
- the period of ⁇ ! ⁇ is a period in which the constant motion detected by the motion detecting means 12 is continued, for example, a period in which the vehicle is traveling on a straight road at a constant acceleration, and a period in which the vehicle is stopped. It is divided into periods, such as the period during which a curve is being bent.
- the period of tc ⁇ tti that is, the certain operation period is a long period as in the first embodiment, the mental and physical state naturally changes during that period, and on the contrary, T because it hinders immediate mental or physical condition prediction or judgment.
- the period of ⁇ t ⁇ t is subdivided to the extent that changes in physical and mental states can be tracked, For each divided period may be calculated cerebral function exponent C M.
- a description will be given of a case of a psychosomatic state determination system for predicting or judging a mental and physical state of a measured person by intentionally applying a stimulus to the measured person.
- Fig. 3 shows the system configuration of the psychosomatic state determination system in this case.
- the psychosomatic state determination system 1b in FIG. 3 includes a stimulus output means 13 and a stimulus database 15 in addition to the system configuration of the psychosomatic state determination system 1a shown in FIG.
- the stimulus output means 13 is means for giving a stimulus to the subject 6. For example, vibration is generated in a chair or a bed provided with the sensor 3 or a stimulus that appeals to visual and auditory senses is given.
- a specific example of the stimulus output means 13 is a pressure sensor such as a piezo element.
- This pressure sensor can not only convert pressure into an electric signal, but also convert an electric signal into pressure, that is, vibration or fluctuation.
- the stimulus output means 13 may be any means other than the piezo element as long as it can control and output the vibration with a computer or the like.
- music or voice is played from the speaker 10
- a visual stimulus a still image or a moving image is displayed on the display device 11.
- the stimulus database 15 is a database that stores the vibration, sound, image, and the like output by the stimulus output unit 13.
- the index database 24 contains, for example, the stimulus database 15 When a vibration of A is given to a non-awakened subject, it shows the temporal trend and numerical value of the psychosomatic state index of B, and when given to an awake subject, C The known data indicating the temporal trends and numerical values of the psychosomatic state index is stored. In addition to vibration, the correspondence between the psychosomatic state index and the psychosomatic state should be clarified in advance for music and images for each type of stimulus. For example, when a certain minute vibration is given to the person 6 to be measured, the brain of the person 6 to be measured in an awake state has the information processing ability enough to cope with the minute vibration, so that the brain follows the minute vibration with almost no delay.
- the subject 6 who is in a fatigue state slows down the response to the micro-vibration, so that the change in the position of the centroid is delayed with respect to the micro-vibration. If you are more tired, the response will be further delayed, and furthermore, you will exhibit an excessive response to micro-vibration, and the position of the center of gravity will become unstable.
- the subject 6 listens to the rhythmic and crisp music, the subject 6 shakes in response to the rhythm if it feels good, but does not respond to the rhythm when the user does not feel comfortable.
- the difference appears as a difference between the numerical value of the psychosomatic state index and the temporal tendency.
- a psychosomatic state determination system that provides a physical stimulus or an audio-visual stimulus to recover from the abnormal psychosomatic state to a normal psychosomatic state.
- the psychosomatic state index returns to the value of the awake state. 22 Based on the mental and physical condition of the subject 6 predicted or judged in 2 It can be output at the time when the state before the subject 6 falls asleep from 1 to 3 can be prevented, so that the subject 6 can be prevented from being in an abnormal mental and physical state and the behavior of the subject 6 can be changed. To help promote.
- the psychosomatic state determination system of the present embodiment can be used to avoid a warning or intimidation of the person 6 It is also suitable for conducting psychological tests.
- the respective means and devices in the present invention are only logically distinguished in their functions, and may have the same physical or practical area. Needless to say, a data file may be used instead of a database, and the description “data base” includes a data file.
- a storage medium storing a software program for realizing the functions of the present embodiment is supplied to the system, and the computer of the system reads and executes the program stored in the storage medium. It is also realized.
- the program itself read from the storage medium implements the functions of the above-described embodiments, and the storage medium storing the program constitutes the present invention.
- Examples of storage media for supplying the program include a magnetic disk and a hard disk.
- Hard disk, optical disk, magneto-optical disk, magnetic tape, nonvolatile memory card, etc. can be used.
- the present invention it is possible to predict or judge the mental and physical condition of the measured person without putting a burden on the measured person, without being conscious, and without depending on subjective judgment, and that the subject fell asleep. It is possible to predict not only that you are going to sleep, but also to warn you before you fall asleep, so that accidents caused by human error can be prevented beforehand and reliably.
- At least one sensor that can be mounted on the seat surface, backrest, etc. of a chair, it is possible to unknowingly predict or judge the physical and mental state of patients treated at hospitals and those who are driving cars, aircraft, etc. It is possible to do. Since only one sensor may be used, it is necessary to take into account synchronization between sensors, such as when measuring the position of the center of gravity from multiple sensors, and individual differences due to output delays that occur between sensors. And the number of parts is small.
- the subject's mental and physical condition at that time can be predicted or judged, and conversely, an abnormal mental and physical condition can be achieved.
- an abnormal mental and physical condition can be achieved.
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Educational Technology (AREA)
- Developmental Disabilities (AREA)
- Social Psychology (AREA)
- Child & Adolescent Psychology (AREA)
- Psychology (AREA)
- Psychiatry (AREA)
- Hospice & Palliative Care (AREA)
- Dentistry (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/546,475 US7737859B2 (en) | 2003-02-24 | 2004-02-23 | Psychosomatic state determination system |
EP04713642A EP1607043B1 (en) | 2003-02-24 | 2004-02-23 | Psychosomatic state determination system |
JP2005503639A JP4505619B2 (ja) | 2003-02-24 | 2004-02-23 | 心身状態判定システム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2003046428 | 2003-02-24 | ||
JP2003-046428 | 2003-02-24 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2004082479A1 true WO2004082479A1 (ja) | 2004-09-30 |
Family
ID=33027656
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2004/002054 WO2004082479A1 (ja) | 2003-02-24 | 2004-02-23 | 心身状態判定システム |
Country Status (4)
Country | Link |
---|---|
US (1) | US7737859B2 (ja) |
EP (1) | EP1607043B1 (ja) |
JP (1) | JP4505619B2 (ja) |
WO (1) | WO2004082479A1 (ja) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010038497A1 (ja) * | 2008-09-30 | 2010-04-08 | ブラザー工業株式会社 | 姿勢判定装置、姿勢判定機能付座席装置 |
JP2011019552A (ja) * | 2009-07-13 | 2011-02-03 | Gov Co Ltd | 疲労検出装置 |
JP2013153924A (ja) * | 2012-01-30 | 2013-08-15 | Aisin Seiki Co Ltd | 運動機能判定装置 |
WO2013172173A1 (ja) * | 2012-05-18 | 2013-11-21 | 日産自動車株式会社 | 運転支援装置および道路地図情報構築方法 |
JP2016039842A (ja) * | 2014-08-12 | 2016-03-24 | 国立大学法人大阪大学 | 会話評価装置、会話評価システム、及び、会話評価方法 |
JP2018032338A (ja) * | 2016-08-26 | 2018-03-01 | マツダ株式会社 | 運転者体調検知装置及び方法 |
JP2018032339A (ja) * | 2016-08-26 | 2018-03-01 | マツダ株式会社 | 運転者体調検知装置及び方法 |
WO2018180331A1 (ja) * | 2017-03-28 | 2018-10-04 | 国立大学法人九州工業大学 | 運転者状態検知装置 |
JP2020006074A (ja) * | 2018-07-12 | 2020-01-16 | 国立大学法人電気通信大学 | 心身的負担測定システム、心身的負担測定方法及びプログラム |
Families Citing this family (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2004043259A1 (ja) * | 2002-11-11 | 2004-05-27 | Electronic Navigation Research Institute, An Independent Administrative Institution | 心身診断システム |
JP4247055B2 (ja) * | 2003-05-21 | 2009-04-02 | 株式会社デルタツーリング | 運転席用座席システム |
CA2560529C (en) * | 2004-04-28 | 2012-06-26 | Electronic Navigation Research Institute, An Independent Administrative Institution | Cerebrum evaluation device |
JP4284538B2 (ja) * | 2004-10-19 | 2009-06-24 | ソニー株式会社 | 再生装置および再生方法 |
US20060259206A1 (en) * | 2005-05-16 | 2006-11-16 | Smith Matthew R | Vehicle operator monitoring system and method |
US7839293B2 (en) * | 2005-12-02 | 2010-11-23 | Farah Jubran | Sound generating device for use by people with disabilities |
US20090043586A1 (en) * | 2007-08-08 | 2009-02-12 | Macauslan Joel | Detecting a Physiological State Based on Speech |
CN102612279A (zh) * | 2011-01-19 | 2012-07-25 | 鸿富锦精密工业(深圳)有限公司 | 服务器机柜 |
US9116838B2 (en) * | 2011-04-08 | 2015-08-25 | The United States Of America As Represented By The Secretary Of The Army | Determining lyapunov exponents of a chaotic system |
JP5666383B2 (ja) * | 2011-05-26 | 2015-02-12 | パナソニック株式会社 | 眠気推定装置及び眠気推定方法 |
US8876535B2 (en) | 2013-03-15 | 2014-11-04 | State Farm Mutual Automobile Insurance Company | Real-time driver observation and scoring for driver's education |
US9734685B2 (en) | 2014-03-07 | 2017-08-15 | State Farm Mutual Automobile Insurance Company | Vehicle operator emotion management system and method |
US9135803B1 (en) | 2014-04-17 | 2015-09-15 | State Farm Mutual Automobile Insurance Company | Advanced vehicle operator intelligence system |
US9283847B2 (en) | 2014-05-05 | 2016-03-15 | State Farm Mutual Automobile Insurance Company | System and method to monitor and alert vehicle operator of impairment |
US9972054B1 (en) | 2014-05-20 | 2018-05-15 | State Farm Mutual Automobile Insurance Company | Accident fault determination for autonomous vehicles |
US10319039B1 (en) | 2014-05-20 | 2019-06-11 | State Farm Mutual Automobile Insurance Company | Accident fault determination for autonomous vehicles |
US9715711B1 (en) | 2014-05-20 | 2017-07-25 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle insurance pricing and offering based upon accident risk |
US10185999B1 (en) | 2014-05-20 | 2019-01-22 | State Farm Mutual Automobile Insurance Company | Autonomous feature use monitoring and telematics |
US10599155B1 (en) | 2014-05-20 | 2020-03-24 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle operation feature monitoring and evaluation of effectiveness |
US10373259B1 (en) | 2014-05-20 | 2019-08-06 | State Farm Mutual Automobile Insurance Company | Fully autonomous vehicle insurance pricing |
US11669090B2 (en) | 2014-05-20 | 2023-06-06 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle operation feature monitoring and evaluation of effectiveness |
US10475127B1 (en) | 2014-07-21 | 2019-11-12 | State Farm Mutual Automobile Insurance Company | Methods of providing insurance savings based upon telematics and insurance incentives |
US10831204B1 (en) | 2014-11-13 | 2020-11-10 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle automatic parking |
US20210258486A1 (en) | 2015-08-28 | 2021-08-19 | State Farm Mutual Automobile Insurance Company | Electric vehicle battery conservation |
US10324463B1 (en) | 2016-01-22 | 2019-06-18 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle operation adjustment based upon route |
US11242051B1 (en) | 2016-01-22 | 2022-02-08 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle action communications |
US10134278B1 (en) | 2016-01-22 | 2018-11-20 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle application |
US10395332B1 (en) | 2016-01-22 | 2019-08-27 | State Farm Mutual Automobile Insurance Company | Coordinated autonomous vehicle automatic area scanning |
US11719545B2 (en) | 2016-01-22 | 2023-08-08 | Hyundai Motor Company | Autonomous vehicle component damage and salvage assessment |
US10503168B1 (en) | 2016-01-22 | 2019-12-10 | State Farm Mutual Automotive Insurance Company | Autonomous vehicle retrieval |
US9940834B1 (en) | 2016-01-22 | 2018-04-10 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle application |
US11441916B1 (en) | 2016-01-22 | 2022-09-13 | State Farm Mutual Automobile Insurance Company | Autonomous vehicle trip routing |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0428353A (ja) * | 1990-03-02 | 1992-01-30 | Anima Kk | 重心動揺判定装置 |
JPH08586A (ja) * | 1994-06-27 | 1996-01-09 | Nippon Telegr & Teleph Corp <Ntt> | 信号分析装置 |
JPH10146321A (ja) * | 1996-11-20 | 1998-06-02 | Matsushita Electric Ind Co Ltd | 運転者監視装置 |
JPH11332856A (ja) * | 1998-02-05 | 1999-12-07 | Mini Mitter Co Inc | 覚醒状態モニタ |
JP2001283134A (ja) * | 2000-03-28 | 2001-10-12 | Sharp Corp | 状態の判定・予測方法 |
JP2001344341A (ja) * | 2000-03-31 | 2001-12-14 | Sharp Corp | 生活活動度評価システムおよび体調判定方法 |
JP2002165799A (ja) * | 2000-12-01 | 2002-06-11 | Sharp Corp | 健康状態診断方法およびその方法を用いた健康状態診断装置 |
JP2003144438A (ja) * | 2001-11-13 | 2003-05-20 | Electronic Navigation Research Institute | カオス論的脳機能診断装置 |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01207036A (ja) | 1988-02-15 | 1989-08-21 | Matsushita Electric Works Ltd | 体動検出装置 |
US5422479A (en) * | 1991-01-25 | 1995-06-06 | Canon Kabushiki Kaisha | Optical type encoder for position detection |
US5458137A (en) * | 1991-06-14 | 1995-10-17 | Respironics, Inc. | Method and apparatus for controlling sleep disorder breathing |
JP3369201B2 (ja) * | 1991-10-02 | 2003-01-20 | マツダ株式会社 | 覚醒度維持装置 |
JPH09109723A (ja) | 1995-10-17 | 1997-04-28 | Yazaki Corp | 居眠り運転防止装置 |
US6070098A (en) * | 1997-01-11 | 2000-05-30 | Circadian Technologies, Inc. | Method of and apparatus for evaluation and mitigation of microsleep events |
JPH11161798A (ja) | 1997-12-01 | 1999-06-18 | Toyota Motor Corp | 車両運転者監視装置 |
AU5900299A (en) * | 1998-08-24 | 2000-03-14 | Emory University | Method and apparatus for predicting the onset of seizures based on features derived from signals indicative of brain activity |
US6134731A (en) * | 1999-04-01 | 2000-10-24 | Bel-Art Products, Inc. | Adjustable support apparatus |
US6524239B1 (en) * | 1999-11-05 | 2003-02-25 | Wcr Company | Apparatus for non-instrusively measuring health parameters of a subject and method of use thereof |
US20020156392A1 (en) * | 2001-03-06 | 2002-10-24 | Mitsubishi Chemical Corporation | Method and apparatus for inspecting biological rhythms |
WO2002080762A1 (en) * | 2001-04-06 | 2002-10-17 | Medic4All Inc. | A physiological monitoring system for a computational device of a human subject |
WO2004043259A1 (ja) * | 2002-11-11 | 2004-05-27 | Electronic Navigation Research Institute, An Independent Administrative Institution | 心身診断システム |
ATE425499T1 (de) * | 2003-02-24 | 2009-03-15 | Electronic Navigation Res Inst | System zur kalkulierung von chaologen indexwerten |
CA2560529C (en) * | 2004-04-28 | 2012-06-26 | Electronic Navigation Research Institute, An Independent Administrative Institution | Cerebrum evaluation device |
-
2004
- 2004-02-23 EP EP04713642A patent/EP1607043B1/en not_active Expired - Lifetime
- 2004-02-23 WO PCT/JP2004/002054 patent/WO2004082479A1/ja active Application Filing
- 2004-02-23 US US10/546,475 patent/US7737859B2/en not_active Expired - Fee Related
- 2004-02-23 JP JP2005503639A patent/JP4505619B2/ja not_active Expired - Fee Related
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0428353A (ja) * | 1990-03-02 | 1992-01-30 | Anima Kk | 重心動揺判定装置 |
JPH08586A (ja) * | 1994-06-27 | 1996-01-09 | Nippon Telegr & Teleph Corp <Ntt> | 信号分析装置 |
JPH10146321A (ja) * | 1996-11-20 | 1998-06-02 | Matsushita Electric Ind Co Ltd | 運転者監視装置 |
JPH11332856A (ja) * | 1998-02-05 | 1999-12-07 | Mini Mitter Co Inc | 覚醒状態モニタ |
JP2001283134A (ja) * | 2000-03-28 | 2001-10-12 | Sharp Corp | 状態の判定・予測方法 |
JP2001344341A (ja) * | 2000-03-31 | 2001-12-14 | Sharp Corp | 生活活動度評価システムおよび体調判定方法 |
JP2002165799A (ja) * | 2000-12-01 | 2002-06-11 | Sharp Corp | 健康状態診断方法およびその方法を用いた健康状態診断装置 |
JP2003144438A (ja) * | 2001-11-13 | 2003-05-20 | Electronic Navigation Research Institute | カオス論的脳機能診断装置 |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010038497A1 (ja) * | 2008-09-30 | 2010-04-08 | ブラザー工業株式会社 | 姿勢判定装置、姿勢判定機能付座席装置 |
JP2011019552A (ja) * | 2009-07-13 | 2011-02-03 | Gov Co Ltd | 疲労検出装置 |
JP2013153924A (ja) * | 2012-01-30 | 2013-08-15 | Aisin Seiki Co Ltd | 運動機能判定装置 |
WO2013172173A1 (ja) * | 2012-05-18 | 2013-11-21 | 日産自動車株式会社 | 運転支援装置および道路地図情報構築方法 |
JP2016039842A (ja) * | 2014-08-12 | 2016-03-24 | 国立大学法人大阪大学 | 会話評価装置、会話評価システム、及び、会話評価方法 |
JP2018032338A (ja) * | 2016-08-26 | 2018-03-01 | マツダ株式会社 | 運転者体調検知装置及び方法 |
JP2018032339A (ja) * | 2016-08-26 | 2018-03-01 | マツダ株式会社 | 運転者体調検知装置及び方法 |
US10561356B2 (en) | 2016-08-26 | 2020-02-18 | Mazda Motor Corporation | Driver's physical condition detection device and method |
WO2018180331A1 (ja) * | 2017-03-28 | 2018-10-04 | 国立大学法人九州工業大学 | 運転者状態検知装置 |
CN110476194A (zh) * | 2017-03-28 | 2019-11-19 | 国立大学法人九州工业大学 | 驾驶员状态探测装置 |
JPWO2018180331A1 (ja) * | 2017-03-28 | 2020-02-06 | 国立大学法人九州工業大学 | 運転者状態検知装置 |
JP2020006074A (ja) * | 2018-07-12 | 2020-01-16 | 国立大学法人電気通信大学 | 心身的負担測定システム、心身的負担測定方法及びプログラム |
Also Published As
Publication number | Publication date |
---|---|
EP1607043B1 (en) | 2012-09-26 |
JP4505619B2 (ja) | 2010-07-21 |
EP1607043A4 (en) | 2008-03-19 |
US20060232430A1 (en) | 2006-10-19 |
JPWO2004082479A1 (ja) | 2006-06-15 |
EP1607043A1 (en) | 2005-12-21 |
US7737859B2 (en) | 2010-06-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP4505619B2 (ja) | 心身状態判定システム | |
CN108366732B (zh) | 困倦起始检测 | |
EP2618733B1 (en) | Method and apparatus for monitoring the respiration activity of a subject | |
JP5383200B2 (ja) | 覚醒度判定方法および覚醒度判定プログラム | |
US7250029B2 (en) | Human condition evaluation system, computer program, and computer-readable record medium | |
CN107554528B (zh) | 驾乘人员的疲劳等级检测方法及装置、存储介质、终端 | |
WO2010107092A1 (ja) | 生物学的パラメータを監視する方法、コンピュータプログラム、および生物学的パラメータの監視装置 | |
WO2010107093A1 (ja) | 生物学的パラメータを監視する方法、コンピュータプログラム、および生物学的パラメータの監視装置 | |
JP4867215B2 (ja) | 生理・心理状態判定装置、生理・心理状態判定方法、リファレンスデータ生成装置、及びリファレンスデータ生成方法。 | |
US20190117144A1 (en) | Heart rate variability and drowsiness detection | |
JP3151489B2 (ja) | 音声による疲労・居眠り検知装置及び記録媒体 | |
KR100956406B1 (ko) | 긴장도를 조절하는 드라이빙 시뮬레이션 시스템 및 방법과이에 사용되는 기록매체 | |
WO2015060267A1 (ja) | 覚醒装置、シート及び覚醒度判定方法 | |
JP2007130454A (ja) | 移動体搭乗者の心身状態調整装置及び心身状態調整装置の制御方法 | |
WO2018180330A1 (ja) | 感情推定装置 | |
JP6518056B2 (ja) | 睡眠状態判定装置、睡眠状態判定方法及びプログラム | |
JP6666705B2 (ja) | 生体状態推定装置、生体状態推定方法及びコンピュータプログラム | |
CN113598773A (zh) | 数据处理装置以及用于评估用户不适的方法 | |
JP6750229B2 (ja) | 眠気検知プログラム、眠気検知方法および眠気検知装置 | |
KR100209610B1 (ko) | 뇌파계신호를 이용한 졸음방지장치 및 그 제어방법 | |
WO2017057022A1 (ja) | 生体状態推定装置、生体状態推定方法及びコンピュータプログラム | |
JP2008049067A (ja) | 人の状態検出装置及び人の状態検出方法 | |
JP2021037033A (ja) | ドライバーの状態推定方法及びシステム | |
WO2020157988A1 (ja) | 状態推定装置、状態推定方法、及びコンピュータ読み取り可能な記録媒体 | |
JP5962751B2 (ja) | 覚醒度判定装置、覚醒度判定プログラムおよび覚醒度判定方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): BW GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LU MC NL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2004713642 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 2004713642 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2006232430 Country of ref document: US Ref document number: 10546475 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 10546475 Country of ref document: US |