Absentminded state determination apparatus

• US 9,332,910 B2
• Filed: 10/03/2012
• Issued: 05/10/2016
• Est. Priority Date: 03/21/2012
• Status: Active Grant

• Current Assignee: DENSO Corporation, Koji Oguri
• Original Assignee: DENSO Corporation, Koji Oguri
• Inventors: Matsunaga, Shinya, Oguri, Koji
• Primary Examiner(s): MULLEN, THOMAS J
• Application Number:
  US13/633,982
• Publication Number:
  US 20130253841A1
• Time in Patent Office: 1,315 Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/02 Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/18 for vehicle drivers or machine operators
• CPC Class Codes: A61B 5/319 Circuits for simulating ECG signals
• CPC Class Codes: A61B 5/6893 Cars
• CPC Class Codes: B60W 2040/0818 Inactivity or incapacity of driver
• CPC Class Codes: B60W 2540/221 Physiology, e.g. weight, heartbeat, health or special needs

Abstract

An absentminded state determination apparatus includes: a data obtaining element for obtaining a time series data of a physiological characteristic value of a participant, wherein a fluctuation component is overlapped on the time series data, and depends on a state of the participant including normal and absentminded states; a detection element for detecting reflecting portions of the time series data, which reflect on the fluctuation component; a counting element for counting the number of the reflecting portions of the time series data in a determination time period between a determination time and a certain past time; and a determination element for determining according to the number of the reflecting portions at the determination time whether the participant is in the absentminded state. The determination time period has a predetermined time width from the certain past time to the determination time.

Claims

1. An absentminded state determination apparatus comprising:

a data obtaining element for obtaining time series data, wherein at least portions of data points in the time series data are time intervals between adjacent pulse beats or heart beats of a participant;

a detection element for detecting a plurality of peaks and troughs of the time series data;

a counting element for counting the number of the peaks and troughs detected by the detection element in a determination time period; and

a determination element for determining, without using a Fourier transform, according to the number of the peaks and troughs counted by the counting element whether the participant is in an absentminded state,

wherein each peak is a data point, which is larger than each adjacent data point,

wherein each trough is a data point, which is smaller than each adjacent data point,

wherein each peak represents the largest time interval in a region of the time series data,

wherein each trough represents the smallest time interval in a region of the time series data.

2. The absentminded state determination apparatus according to claim 1, further comprising:

a threshold setting element for setting a threshold for the number of the peaks and troughs,

wherein the determination element determines that the participant is in the absentminded state when the number of peaks and troughs is smaller than the threshold.

3. The absentminded state determination apparatus according to claim 2, further comprising:

a standard time period determination element for determining a standard time period, which has a same time length as the determination time period, wherein the standard time period is defined in such a manner that the participant is deemed to be in a normal state in the standard time period; and

a standard number counting element for counting the number of peaks and troughs in the standard time period, which is defined as a standard number,

wherein the threshold setting element sets the threshold according to the standard number.

4. The absentminded state determination apparatus according to claim 3,

wherein the participant is a driver of a vehicle,

the absentminded state determination apparatus further comprising:

an information obtaining element for obtaining at least one of vehicle acceleration information and vehicle speed information,

wherein the standard time period determination element includes a standard time period judgment element for judging a time period, in which the vehicle runs stably, according to the at least one of vehicle acceleration information and vehicle speed information, and

wherein the standard time period determination element selects one of time periods, which are judged as stable running periods by the standard time period judgment element, as the standard time period.

5. The absentminded state determination apparatus of claim 1,

the peaks and troughs of the time series data, in which the counting element counts the number of peaks and troughs, include noise of the time series data obtained by the data obtaining element without removal by the Fourier transform, and

the determining by the determination element as to whether the participant is in the absentminded state uses the peaks and troughs counted by the counting element in the time series data which include the noise as obtained by the data obtaining element without removal by the Fourier transform.

6. An absentminded state determination apparatus comprising:

a data obtaining element for obtaining time series data, wherein at least portions of data points in the time series data are time intervals between adjacent pulse beats or heart beats of a participant;

a detection element for detecting a plurality of peaks and troughs of the time series data;

a counting element for counting the number of the peaks and troughs detected by the detection element in a determination time period; and

a determination element for determining, without using a Fourier transform, according to the number of the peaks and troughs counted by the counting element whether the participant is in an absentminded state,

wherein a standard time period is defined, without using a Fourier transform, in such a manner that the participant is deemed to be in a normal state in the standard time period,

wherein the standard time period has a same time length as the determination time period,

wherein the time series data in the standard time period is defined as standard time series data,

wherein each peak is a data point, which is larger than each adjacent data point and larger than corresponding standard time series data,

wherein each trough is a data point, which is smaller than each adjacent data point and smaller than corresponding standard time series data,

wherein each peak represents the largest time interval in a region of the time series data,

wherein each trough represents the smallest time interval in a region of the time series data.

7. The absentminded state determination apparatus according to claim 6, further comprising:

a first calculation element for dividing the standard time series data with a predetermined time width into a plurality of partial data items, and for calculating a standard change amount of each partial data item, wherein the standard change amount is a variation of the heart rate or the pulse beat of the participant in a corresponding partial data item;

a second calculation element for calculating a variation threshold according to the standard change amount;

a second detection element for detecting a large fluctuation portion in the time series data as the peaks and troughs, wherein the large fluctuation portion is defined in such a manner that a fluctuation component larger than a fluctuation component overlapped on the standard time series data is overlapped on the time series data in the large fluctuation portion, and wherein the time series data in the large fluctuation portion is different from the time series data in the standard time period;

a second counting element for counting the number of large fluctuation portions in the time series data in the determination time period;

a second determination element determines that the participant is in the absentminded state when the number of large fluctuation portions is larger than a predetermined second threshold,

wherein the variation threshold is a threshold of the variation of the heart rate or the pulse beat of the participant for detecting the large fluctuation portion, and

wherein the second detection element detects the large fluctuation portion having the variation of the heart rate or the pulse beat of the participant in the time series data, which is larger than the variation threshold.

8. The absentminded state determination apparatus according to claim 7, further comprising:

a removing element for removing a high frequency fluctuation component from the time series data,

wherein a low frequency fluctuation component is overlapped on the time series data when a sympathetic is superior to a parasympathetic,

wherein the high frequency fluctuation component has a frequency higher than the low frequency fluctuation component,

wherein the first calculation element calculates the standard change amount according to the standard time series data, from which the high frequency fluctuation component is removed, and

wherein the second detection element detects the large fluctuation portion in the time series data, from which the high frequency fluctuation component is removed.

9. The absentminded state determination apparatus according to claim 8,

wherein the second detection element detects an upper convexity or a lower convexity as the large fluctuation portion,

wherein the upper convexity is overlapped on the time series data so that the upper convexity protrudes toward a direction, in which the heart rate or the pulse beat of the participant increases,

wherein the lower convexity is overlapped on the time series data so that the lower convexity protrudes toward a direction, in which the heart rate or the pulse beat of the participant decreases,

wherein each of the upper convexity and the lower convexity has a predetermined first time width, which is larger than a cycle of the high frequency fluctuation component, and

wherein each of the upper convexity and the lower convexity has the variation of the heart rate or the pulse beat of the participant, which is larger than the variation threshold.

10. The absentminded state determination apparatus according to claim 9,

wherein the first calculation element divides the standard time series data with a second time width into the plurality of partial data items,

wherein the second time width is a half of the first time width, and corresponds to the predetermined time width,

wherein the second calculation element calculates the variation threshold according to the standard change amount with respect to the second time width,

wherein the second detection element includes an upper convexity determination element and a lower convexity determination element,

wherein the time series data in the determination time period is divided with the first time width into a plurality of first time width partial data items,

wherein each first time width partial data item includes a first half item and a last half item, each of which has the second time width,

wherein the heart rate or the pulse beat of the participant in the first half item is defined as a first half physiological characteristic value, and the heart rate or the pulse beat of the participant in the last half item is defined as a last half physiological characteristic value,

wherein the upper convexity determination element determines that the first time width partial data item provides the upper convexity when the first half physiological characteristic value monotonically increases with time, the last half physiological characteristic value monotonically decreases with time, and each of the variation of the first half physiological characteristic value and the variation of the last half physiological characteristic value is larger than the variation threshold, and

wherein the lower convexity determination element determines that the first time width partial data item provides the lower convexity when the first half physiological characteristic value monotonically decreases with time, the last half physiological characteristic value monotonically increases with time, and each of the variation of the first half physiological characteristic value and the variation of the last half physiological characteristic value is larger than the variation threshold.

11. The absentminded state determination apparatus according to claim 10,

wherein the second calculation element calculates the variation threshold, which is a standard deviation of the standard change amount.

12. The absentminded state determination apparatus of claim 6,

the peaks and troughs of the time series data, in which the counting element counts the number of peaks and troughs, include noise of the time series data as obtained by the data obtaining element without removal by the Fourier transform, and

the determining by the determination element as to whether the participant is in the absentminded state uses the peaks and troughs counted by the counting element in the time series data which include the noise obtained by the data obtaining element without removal by the Fourier transform.