JP6919415B2 - Drowsiness detection device and drowsiness detection program - Google Patents

Description

The present invention relates to a drowsiness detection device and a drowsiness detection program.

One of the causes of relatively serious traffic accidents based on human error is, for example, drowsiness of a car driver. On the other hand, when the driver's breathing cycle varies greatly due to mental stress when the driver drives with drowsiness, the driver's breathing cycle tends to vary widely. There is a technique for determining that the driver is drowsy.

As a prior art, for example, when the average value of RI immediately after is higher than the average value of RI (Respiration Interval), which is the interval of one breath, and RrMSSD (Respiration root Mean Square Successive) indicating the variation of RI. When the RrMSSDn immediately after is higher than the constant multiple of Difference), it is determined that the person is in a low arousal state. Further, for example, there is a technique for acquiring the breathing interval of a subject and determining the presence or absence of drowsiness of the subject by using the degree of the fluctuation as a parameter for determining drowsiness when a fluctuation that increases the acquired breathing interval occurs. Further, for example, the detection value of the pressure sensor provided at the portion where the belt portion of the seatbelt is fixed and detecting the breathing of the occupant who is seated with the seatbelt is compared with the reference value indicating the awakening state of the occupant. , There is a technique to judge the awakening state of the occupant based on the result of comparison. In addition, for example, there is a technique for extracting respiratory rate, heart rate, waveforms due to respiratory activity and cardiac activity, abnormal breathing, or strange breathing as information related to the cardiopulmonary movement of the subject.

Japanese Unexamined Patent Publication No. 2015-80521 International Publication No. 2010/143535 Japanese Unexamined Patent Publication No. 2004-290324 Japanese Patent Application Laid-Open No. 2011-591288

However, with the prior art, it may be difficult to accurately detect whether or not the driver has become drowsy. For example, even if the driver is actually drowsy, the variation in the driver's breathing cycle may be relatively small, and it may not be possible to determine that the driver is drowsy. ..

In one aspect, it is an object of the present invention to provide a drowsiness detection device and a drowsiness detection program capable of improving the accuracy of detecting that a subject is drowsy.

According to one embodiment, the subject becomes drowsy when it is determined that the subject's breathing cycle or amplitude satisfies the first condition based on the subject's breathing cycle or amplitude information. When it is determined that the subject is drowsy, and then it is determined that the subject's breathing cycle or amplitude no longer satisfies the first condition, the subject It is determined whether or not the index value indicating the variation in the exhalation time or amplitude for each breath of the subject satisfies the second condition, or the variation in the inhalation time or amplitude for each breath of the subject is determined. It is determined whether or not the indicated index value satisfies the third condition, and when it is determined that the second condition is satisfied or when it is determined that the third condition is satisfied, the subject is drowsy. A drowsiness detection device that determines that the subject does not have drowsiness when it is determined that the second condition is not satisfied or the third condition is not satisfied, and drowsiness detection. The program is proposed.

According to one aspect of the present invention, it is possible to improve the accuracy of detecting that the subject is drowsy.

FIG. 1 is an explanatory diagram showing an embodiment of a drowsiness detection method according to an embodiment. FIG. 2 is an explanatory diagram showing an example of the drowsiness detection system 200. FIG. 3 is a block diagram showing a hardware configuration example of the drowsiness detection device 100. FIG. 4 is an explanatory diagram showing an example of the stored contents of the analysis information table 400. FIG. 5 is an explanatory diagram showing an example of the stored contents of the respiratory information table 500. FIG. 6 is an explanatory diagram showing an example of the stored contents of the breath / breath information table 600. FIG. 7 is a block diagram showing a functional configuration example of the drowsiness detection device 100. FIG. 8 is a block diagram showing a specific example of the functional configuration of the drowsiness detection device 100. FIG. 9 is an explanatory diagram (No. 1) showing the flow of drowsiness detection. FIG. 10 is an explanatory diagram (No. 2) showing the flow of drowsiness detection. FIG. 11 is an explanatory diagram (No. 1) showing an embodiment of drowsiness detection. FIG. 12 is an explanatory diagram (No. 2) showing an embodiment of drowsiness detection. FIG. 13 is an explanatory diagram (No. 3) showing an embodiment of drowsiness detection. FIG. 14 is an explanatory diagram (No. 4) showing an embodiment of drowsiness detection. FIG. 15 is a flowchart showing an example of the drowsiness detection processing procedure. FIG. 16 is a flowchart showing an example of the respiratory frequency calculation processing procedure. FIG. 17 is a flowchart showing an example of the respiratory drowsiness determination processing procedure. FIG. 18 is a flowchart showing an example of the respiratory drowsiness value calculation processing procedure. FIG. 19 is a flowchart showing an example of the respiratory drowsiness threshold setting processing procedure. FIG. 20 is a flowchart showing an example of the procedure for determining the necessity of awakening effort determination. FIG. 21 is a flowchart (No. 1) showing an example of the awakening effort value calculation processing procedure. FIG. 22 is a flowchart (No. 2) showing an example of the awakening effort value calculation processing procedure. FIG. 23 is a flowchart showing an example of the awakening effort threshold setting processing procedure.

Hereinafter, embodiments of the drowsiness detection device and the drowsiness detection program according to the present invention will be described in detail with reference to the drawings.

(Example of drowsiness detection method according to the embodiment)
FIG. 1 is an explanatory diagram showing an embodiment of a drowsiness detection method according to an embodiment. In FIG. 1, the drowsiness detection device 100 is a computer that determines whether or not the subject 110 is drowsy. The subject 110 is a target for determining whether or not the subject 110 is drowsy. The subject 110 is, for example, a driver of a car. The target person 110 may be, for example, a driver of a train, an airplane, or the like. The target person 110 may be, for example, a student in class.

One of the causes of relatively serious traffic accidents based on human error is the drowsiness of car drivers. For this reason, it is determined whether or not the driver is drowsy, and if it is determined that the driver is drowsy, the driver's drowsiness should be eliminated by using sound, vibration, or smell. Therefore, it is desired to prevent traffic accidents and ensure traffic safety.

Here, if the driver becomes tired or monotonous while driving, the driver's concentration on the driver tends to decrease, and eventually the driver's brain awakening decreases. The driver may become drowsy. In this case, the driver becomes drowsy, and as the driver's physical activity decreases, the driver's breathing cycle tends to become longer. In other words, the driver's breathing cycle tends to correlate with the driver's drowsiness. However, even if the driver becomes drowsy, the driver will continue to drive while enduring the drowsiness. For this reason, mental stress tends to increase the variation in the driver's breathing cycle, and the correlation between the driver's breathing cycle and the driver's drowsiness may be difficult to understand.

Therefore, based on these tendencies, when the driver's breathing cycle becomes long and the driver's breathing cycle varies widely, it is determined that the driver is drowsy and traffic is present. It is conceivable to prevent accidents and ensure traffic safety. However, it may be difficult to accurately determine whether or not the driver has become drowsy.

For example, even if the driver is actually drowsy, the variation in the driver's breathing cycle may be relatively small, and it may not be possible to determine that the driver is drowsy. .. Specifically, as a result of the driver's awakening efforts such as yawning, sighing, and swallowing the brim, during the awakening effort, even if drowsiness continues, the driver's breathing cycle variation awakens. It may be similar to the condition, and it is difficult to determine that the driver is drowsy. Awakening effort is a state of conflict that tries to wake up against drowsiness. The wakefulness state is a state in which the person is awake and is judged not to be drowsy.

In addition to the driver's breathing, determine whether the driver is drowsy based on features such as the driver's heartbeat, prevent traffic accidents, and ensure traffic safety. It is conceivable to do. However, since the driver is required to wear the heart rate sensor, the mechanism for determining whether or not the driver is drowsy tends to be complicated, which may increase the burden on the driver. .. In addition, it may lead to an increase in financial costs.

Therefore, in the present embodiment, the accuracy of detecting that the subject 110 is drowsy is based on the index value indicating the variation in the feature amount related to the exhalation or inhalation of the subject 110 for each breath. A drowsiness detection method that can be improved will be described.

For example, as a result of the awakening effort of the subject 110, even if the variation of the driver's breathing cycle becomes similar to the awakening state during the awakening effort, the breathing or inhalation is related to the awakening effort. The feature quantity tends to change. Specifically, since the subject 110 holds his breath when swallowing the brim, the time of exhalation or inspiration tends to change. Specifically, since the subject 110 holds his / her breath when swallowing the brim, the amplitude of exhalation or inspiration also tends to change.

By utilizing these tendencies, in the present embodiment, the subject 110 becomes drowsy based on the index value indicating the variation in the feature amount regarding exhalation or inspiration for each breath of the subject 110. It becomes possible to improve the accuracy of detecting the presence.

In FIG. 1, the drowsiness detection device 100 causes drowsiness in the subject 110 when it is determined that the breathing cycle of the subject 110 satisfies the first condition based on the information of the breathing cycle of the subject 110. Judge that it is. The first condition is a condition indicating that the variation in the respiratory cycle is relatively large.

In the example of FIG. 1, the drowsiness detection device 100 determines that the first condition is not satisfied because the variation in the respiratory cycle of the subject 110 is relatively small between the times t1 to t2, and the subject 110 is drowsy. Is not generated. On the other hand, the drowsiness detection device 100 determines that the first condition is satisfied because the variation in the respiratory cycle of the subject 110 is relatively large between the times t2 to t3, and the subject 110 becomes drowsy. Judge that there is.

In FIG. 1, the drowsiness detection device 100 determines that the subject 110 does not satisfy the first condition after it is determined that the subject 110 is drowsy. It is determined whether or not the index value indicating the time variation satisfies the second condition. Exhalation is exhalation. The second condition is a condition indicating that the variation in exhalation time is relatively large. The second condition is, for example, that the index value indicating the variation in exhalation time is equal to or greater than the threshold value. The index value indicating the variation in exhalation time is the variance or standard deviation of exhalation time. The index value indicating the variation in the time of exhalation may be the variance or standard deviation of the ratio of the time between exhalation and inspiration in one breath. Inhalation is to inhale. The drowsiness detection device 100 determines that the subject 110 is drowsy when it is determined that the second condition is satisfied, and the drowsiness is generated in the subject 110 when it is determined that the second condition is not satisfied. Judge that it is not done.

In the example of FIG. 1, the drowsiness detection device 100 determines that the subject 110 is drowsy during the time t2 to t3, and then determines that the first condition is no longer satisfied at the time t3. In this case, the drowsiness detection device 100 determines whether or not the index value indicating the variation in the exhalation time for each breath of the subject 110 satisfies the second condition. Here, the drowsiness detection device 100 determines that the index value indicating the variation in the exhalation time for each breath of the subject 110 satisfies the second condition between the times t3 and t4, and the subject 110 is drowsy. Is determined to have occurred. On the other hand, the drowsiness detection device 100 determines that the index value indicating the variation in the exhalation time for each breath of the subject 110 does not satisfy the second condition between the times t4 and t5, and determines that the subject 110 does not. It is determined that drowsiness has not occurred.

As a result, the drowsiness detection device 100 can use the breathing cycle, the exhalation time, and the like as an index value based on breathing for determining whether or not the subject 110 is drowsy. It is possible to improve the accuracy of detecting that drowsiness is occurring in 110. Then, if the subject 110 is drowsy, the drowsiness detection device 100 prevents the traffic accident by using sound, vibration, odor, or the like to eliminate the drowsiness of the subject 110, thereby preventing traffic safety. It can be secured.

In the drowsiness detection device 100, for example, even if the subject 110 makes an awakening effort and the variation in the respiratory cycle of the subject 110 becomes similar to the awake state, the exhalation time changed due to the awakening effort. Based on the above, it can be determined whether or not the subject 110 is drowsy. Therefore, the drowsiness detection device 100 erroneously determines that the subject 110 is not drowsy when the subject 110 is making an awakening effort and the subject 110 is still drowsy. Can be prevented. Then, the drowsiness detection device 100 stops trying to eliminate the drowsiness of the subject 110 by using sound, vibration, odor, etc., even though the drowsiness of the subject 110 is still continuing, thereby ensuring traffic safety. It is possible to prevent the inability to achieve the above.

In addition, the drowsiness detection device 100 can continue to determine that the subject 110 is drowsy while the subject 110 continues to be drowsy. Therefore, the drowsiness detection device 100 can prevent the determination result from being easily switched by mistake and the determination result from being switched frequently. Then, the drowsiness detection device 100 can efficiently eliminate the drowsiness of the subject 110 by using sound, vibration, odor, or the like, and the target by erroneously trying to eliminate the drowsiness of the subject 110. It is possible to suppress an increase in the burden on the person 110.

Further, since the drowsiness detection device 100 does not have to use the feature amount such as the heartbeat of the subject 110 in addition to the breathing of the subject 110, if the subject 110 is equipped with the breathing sensor, the heartbeat sensor is attached. You don't have to. Therefore, the drowsiness detection device 100 can suppress the complexity of the mechanism for determining whether or not the subject 110 is drowsy, and can suppress the increase in the burden on the subject 110.

Here, the case where the drowsiness detection device 100 determines whether or not the respiratory cycle satisfies the first condition has been described, but the present invention is not limited to this. For example, the drowsiness detection device 100 may determine whether or not the respiratory amplitude satisfies the first condition. Further, for example, the drowsiness detection device 100 may determine whether or not the respiratory cycle and amplitude satisfy the first condition.

Here, the case where the first condition is a condition indicating that the variation in the respiratory cycle is relatively large has been described, but the present invention is not limited to this. For example, the first condition may be a condition indicating that the respiratory cycle is larger than the threshold value. Further, for example, the first condition may be a condition indicating that the respiratory cycle is larger than the threshold value and the variation in the respiratory cycle is relatively large.

Here, the case where the drowsiness detection device 100 determines whether or not the index value indicating the variation in the exhalation time satisfies the second condition is described, but the present invention is not limited to this. For example, the drowsiness detection device 100 may determine whether or not the index value indicating the variation in the amplitude of exhalation satisfies the second condition. Further, for example, the drowsiness detection device 100 determines whether or not the index value indicating the variation of the exhalation cycle satisfies the second condition α, and the index value indicating the variation of the exhalation amplitude satisfies the second condition β. It may be determined whether or not.

Further, for example, the drowsiness detection device 100 may determine whether or not the index value indicating the variation in the inhalation time satisfies the third condition. Further, for example, the drowsiness detection device 100 may determine whether or not the index value indicating the variation in the inspiration amplitude satisfies the third condition. Further, for example, the drowsiness detection device 100 determines whether or not the index value indicating the variation in the inspiration cycle satisfies the third condition α, and the index value indicating the variation in the inspiration amplitude satisfies the third condition β. It may be determined whether or not.

Further, for example, the drowsiness detection device 100 determines whether or not the index value indicating the variation in the exhalation time satisfies the second condition and the index value indicating the variation in the inspiration time satisfies the third condition. There may be cases. Further, for example, the drowsiness detection device 100 determines whether or not the index value indicating the variation in the inspiration amplitude satisfies the second condition and the index value indicating the variation in the inspiration amplitude satisfies the third condition. There may be cases.

Here, the case where the drowsiness detection device 100 determines whether or not the subject 110 is drowsy has been described, but the present invention is not limited to this. For example, the drowsiness detection device 100 may determine whether or not the subject 110 is drowsy, and also determine the intensity of the drowsiness of the subject 110 when the subject 110 is drowsy.

Further, since the reciprocal of the breathing cycle is the breathing frequency, the drowsiness detection device 100 determines whether or not the breathing frequency, which is the reciprocal of the breathing cycle, satisfies the first condition. May be realized to determine whether or not the first condition is satisfied.

(Example of drowsiness detection system 200)
Next, an example of the drowsiness detection system 200 to which the drowsiness detection device 100 shown in FIG. 1 is applied will be described with reference to FIG.

FIG. 2 is an explanatory diagram showing an example of the drowsiness detection system 200. In FIG. 2, the drowsiness detection system 200 includes a subject 110, a sensor device 211, and a drowsiness detection device 100. In the drowsiness detection system 200, the sensor device 211 and the drowsiness detection device 100 are connected by, for example, by wire or wirelessly.

The subject 110 is a target for determining whether or not drowsiness is occurring. The subject 110 is, for example, a driver of a car. The drowsiness detection system 200 is used, for example, to determine whether or not the subject 110 while driving is drowsy, prevent a traffic accident, and ensure traffic safety.

The sensor device 211 is a computer that acquires time-series data indicating the magnitude of respiration of the subject 110 as a respiration signal of the subject 110 and outputs the time-series data to the drowsiness detection device 100. For example, the sensor device 211 detects the expansion / contraction 220 of the thorax and chest of the subject 110 linked to the respiration of the subject 110 by using the pressure sensor, and acquires the time-series data of the detected value of the pressure sensor as a respiration signal. ..

The sensor device 211 is attached to the subject 110. The sensor device 211 is, for example, a chest band type device. Specifically, the sensor device 211 is built in the seat belt 210 worn by the subject 110 during driving. Further, the sensor device 211 may be, for example, a smartphone or a wearable terminal. Further, the sensor device 211 may be in non-contact with the target person 110. The sensor device 211 may be, for example, an in-vehicle camera, and may acquire a breathing signal of the subject 110 based on an image of the subject 110.

The drowsiness detection device 100 is a computer that can communicate with the sensor device 211, acquires a respiration signal from the sensor device 211, and determines whether or not the subject 110 is drowsy based on the respiration signal. When the drowsiness detection device 100 determines that the subject 110 is drowsy, the drowsiness detection device 100 prevents the traffic accident and prevents traffic safety by eliminating the drowsiness of the subject 110 by using sound, vibration, odor, or the like. To secure. If the drowsiness detection device 100 determines that the target person 110 is drowsy if the automobile has an automatic driving function, the drowsiness detection device 100 activates the automatic driving function in the automobile to prevent a traffic accident and traffic safety. You may try to secure.

The drowsiness detection device 100 exists, for example, in a car driven by the subject 110. Specifically, the drowsiness detection device 100 is an in-vehicle device such as a car navigation device. Further, the drowsiness detection device 100 may be specifically a tablet terminal, a smartphone, a wearable terminal, or the like possessed by the subject 110. The drowsiness detection device 100 may exist outside the vehicle driven by the subject 110, for example. Specifically, the drowsiness detection device 100 may be a server, a PC (Personal Computer), a notebook PC, or the like.

Here, the case where the drowsiness detection device 100 and the sensor device 211 are different devices has been described, but the present invention is not limited to this. For example, the drowsiness detection device 100 and the sensor device 211 may be integrated.

(Hardware configuration example of drowsiness detection device 100)
Next, a hardware configuration example of the drowsiness detection device 100 will be described with reference to FIG.

FIG. 3 is a block diagram showing a hardware configuration example of the drowsiness detection device 100. In FIG. 3, the drowsiness detection device 100 includes a CPU (Central Processing Unit) 301, a memory 302, a network I / F (Interface) 303, a recording medium I / F 304, a recording medium 305, an alarm device 306, and the like. It has a sensor I / F 307. Further, each component is connected by a bus 300.

Here, the CPU 301 controls the entire drowsiness detection device 100. The memory 302 includes, for example, a ROM (Read Only Memory), a RAM (Random Access Memory), a flash ROM, and the like. Specifically, for example, a flash ROM or ROM stores various programs, and RAM is used as a work area of CPU 301. The various programs include, for example, a drowsiness detection program. The program stored in the memory 302 is loaded into the CPU 301 to cause the CPU 301 to execute the coded process. The memory 302 may store, for example, the analysis information table 400 described later in FIG. 4, the breathing information table 500 described later in FIG. 5, the breathing information table 600 described later in FIG. 6, and the like.

The network I / F 303 is connected to the network 310 through a communication line, and is connected to another computer via the network 310. Other computers are, for example, external servers. The other computer may be, for example, a control device provided in an automobile. Then, the network I / F 303 controls the internal interface with the network 310 and controls the input / output of data from another computer. For the network I / F 303, for example, a modem, a LAN (Local Area Network) adapter, or the like can be adopted.

The recording medium I / F 304 controls read / write of data to the recording medium 305 according to the control of the CPU 301. The recording medium I / F 304 is, for example, a disk drive, an SSD (Solid State Drive), a USB (Universal Bus) port, or the like. The recording medium 305 is a non-volatile memory that stores data written under the control of the recording medium I / F 304. The recording medium 305 may store the drowsiness detection program. The recording medium 305 is, for example, a disk, a semiconductor memory, a USB memory, or the like. The recording medium 305 may be detachable from the drowsiness detection device 100.

The alarm 306 aims to eliminate the drowsiness of the subject 110 when the subject 110 is drowsy. For example, when the subject 110 is drowsy, the alarm 306 attempts to eliminate the drowsiness of the subject 110 by using sound, vibration, odor, or the like. The sensor I / F 307 controls data read / write to the sensor device 211 according to the control of the CPU 301. The sensor I / F307 is, for example, a communication circuit corresponding to Wi-Fi (registered trademark) or Bluetooth (registered trademark).

The drowsiness detection device 100 may include, for example, a keyboard, a mouse, a display, a printer, a scanner, a microphone, a speaker, and the like, in addition to the above-described components. Further, the drowsiness detection device 100 does not have to have the recording medium I / F 304 or the recording medium 305. The drowsiness detection device 100 does not have to have the network I / F 303. The drowsiness detection device 100 does not have to have the sensor I / F 307 as long as it is integrated with the sensor device 211. Further, the network I / F 303 and the sensor I / F 307 may be integrated.

(Stored contents of analysis information table 400)
Next, the stored contents of the analysis information table 400 will be described with reference to FIG. The analysis information table 400 is realized, for example, by a storage area such as the memory 302 or the recording medium 305 of the drowsiness detection device 100 shown in FIG.

FIG. 4 is an explanatory diagram showing an example of the stored contents of the analysis information table 400. As shown in FIG. 4, the analysis information table 400 has a field of an exhalation start point and an inspiration start point. In the analysis information table 400, analysis information is stored as a record by setting information in each field for each breath.

In the field of the exhalation start point, the exhalation start point indicating the time when the exhalation starts is set. The exhalation start point is, for example, the time when the respiratory differential signal obtained by differentiating the respiratory signal changes from positive to negative. The exhalation start point may be, for example, a time when the respiratory signal is below the threshold value and the respiratory differential signal obtained by differentiating the respiratory signal changes from positive to negative.

In the field of the inhalation start point, the inspiration start point indicating the time when the inspiration starts is set. The inhalation start point is, for example, the time when the respiratory differential signal obtained by differentiating the respiratory signal changes from negative to positive. The inhalation start point may be, for example, a time when the respiratory signal is equal to or higher than the threshold value and the respiratory differential signal obtained by differentiating the respiratory signal changes from negative to positive.

(Memory contents of breathing information table 500)
Next, the stored contents of the respiratory information table 500 will be described with reference to FIG. The respiration information table 500 is realized, for example, by a storage area such as the memory 302 or the recording medium 305 of the drowsiness detection device 100 shown in FIG.

FIG. 5 is an explanatory diagram showing an example of the stored contents of the respiratory information table 500. As shown in FIG. 5, the respiration information table 500 has fields for a respiration interval, a respiration cycle, a respiration frequency, a respiration drowsiness value, a respiration drowsiness threshold, and a determination result.

In the respiration information table 500, the respiration information is stored as a record by setting information in each field for each respiration. Each column of the respiration information table 500 is stored as an array that collects information on each field.

In the breathing interval field, the breathing interval, which is the interval between the inhalation start point and the inspiration start point, is set. In the respiratory cycle field, the respiratory cycle, which is the result of dividing the respiratory interval by the sampling frequency, is set. In the respiratory frequency field, the respiratory frequency, which is the result of reciprocalizing the respiratory cycle, is set.

The field of respiratory drowsiness value is an index value indicating the magnitude of drowsiness occurring in the subject 110 based on the cycle or amplitude of breathing, and determines whether or not the subject 110 is drowsy. The respiratory drowsiness value used when doing so is set. The respiratory drowsiness value is specifically the average value of the respiratory frequencies for a predetermined time.

In the field of respiratory drowsiness threshold, the respiratory drowsiness threshold used for determining whether or not the subject 110 is drowsy based on the average value of the respiratory drowsiness value and the standard deviation value of the respiratory drowsiness value is set. Set. In the determination result field, the result of determining whether or not the subject 110 is drowsy by comparing the respiratory drowsiness value and the respiratory drowsiness threshold value is set.

(Memory contents of the exhalation and inspiration information table 600)
Next, the stored contents of the exhalation and inspiration information table 600 will be described with reference to FIG. The exhalation-breath information table 600 is realized, for example, by a storage area such as the memory 302 or the recording medium 305 of the drowsiness detection device 100 shown in FIG.

FIG. 6 is an explanatory diagram showing an example of the stored contents of the breath / breath information table 600. As shown in FIG. 6, the exhalation and inspiration information table 600 includes an exhalation interval, an inspiration interval, an exhalation time, an inspiration time, an exhalation power, an inspiration power, and an exhalation amplitude. , The inspiration amplitude, the exhalation-inspiration ratio, the awakening effort value, the awakening effort threshold, and the determination result.

In the exhalation and inspiration information table 600, the exhalation and inspiration information is stored as a record by setting information in each field for each breath. Each column of the exhalation-breath information table 600 is stored as an array that collects information on each field.

In the breath interval field, the exhalation interval, which is the interval between the exhalation start point and the inspiration start point, is set. In the inspiration interval field, the inspiration interval, which is the interval between the inspiration start point and the exhalation start point, is set. In the exhalation time field, the exhalation time, which is the result of dividing the exhalation interval by the sampling frequency, is set. In the inspiration time field, the inspiration time, which is the result of dividing the inspiration interval by the sampling frequency, is set.

In the field of exhalation power, exhalation power, which is an integral value of the exhalation start point to the inspiration start point, is set. In the field of inspiration power, the inspiration power which is an integral value of the inspiration start point to the exhalation start point is set. In the field of exhalation amplitude, the exhalation amplitude which is the result of dividing the exhalation power by the sampling frequency is set. In the field of inspiration amplitude, the inspiration amplitude which is the result of dividing the inspiration power by the sampling frequency is set. In the field of the exhalation-breath ratio, the exhalation-breath ratio, which is the ratio of the exhalation time to the inhalation time, is set. In the field of exhalation-breath ratio, the ratio of the exhalation amplitude to the inspiration amplitude may be set as the exhalation-inspiration ratio.

The field of awakening effort value is an index value indicating the magnitude of drowsiness occurring in the subject 110 based on the cycle or amplitude of exhalation or the cycle or amplitude of inspiration, and is indicated in the subject 110. The awakening effort value used to determine whether or not drowsiness is occurring is set. The arousal effort value is, for example, the standard deviation of the exhalation-breath ratio.

In the field of the awakening effort threshold value, the awakening effort threshold value used for determining whether or not the subject 110 is drowsy based on the average value of the awakening effort value and the standard deviation value of the awakening effort value is set. Set. In the determination result field, the result of determining whether or not the subject 110 is drowsy by comparing the awakening effort value and the awakening effort threshold value is set.

(Hardware configuration example of sensor device 211)
The hardware configuration example of the sensor device 211 includes sensors in addition to the same parts as the hardware configuration example of the drowsiness detection device 100 shown in FIG. The sensors acquire the respiratory signal of the subject 110. The sensors include, for example, a pressure sensor, detect expansion and contraction of the thorax and chest of the subject 110 linked to the respiration of the subject 110, and acquire time-series data of the detected value of the pressure sensor as a respiration signal. The sensors may include a heart rate sensor that acquires the heart rate of the subject 110.

(Example of functional configuration of drowsiness detection device 100)
Next, a functional configuration example of the drowsiness detection device 100 will be described with reference to FIG. 7.

FIG. 7 is a block diagram showing a functional configuration example of the drowsiness detection device 100. The drowsiness detection device 100 includes a storage unit 700, an acquisition unit 701, a first determination unit 702, a second determination unit 703, and an output unit 704.

The storage unit 700 is realized by, for example, a storage area such as the memory 302 or the recording medium 305 shown in FIG. The acquisition unit 701 to the output unit 704 are functions that serve as control units. Specifically, the acquisition unit 701 to the output unit 704 may, for example, cause the CPU 301 to execute a program stored in a storage area such as the memory 302 or the recording medium 305 shown in FIG. 3, or the sensor I / F 307. To realize the function. The processing result of each functional unit is stored in a storage area such as the memory 302 or the recording medium 305 shown in FIG. 3, for example.

The storage unit 700 stores the respiratory signal. The storage unit 700 stores the analysis result based on the respiratory signal. The storage unit 700 stores, for example, the analysis information table 400 shown in FIG. 4, the breathing information table 500 shown in FIG. 5, the exhalation-breathing information table 600 shown in FIG. 6, and the like. As a result, the storage unit 700 can refer to the respiratory signal, the analysis result based on the respiratory signal, and the like by each functional unit.

The acquisition unit 701 acquires the respiratory signal of the subject 110 and stores it in the storage unit 700. The acquisition unit 701 receives, for example, the respiration signal of the subject 110 from the sensor device 211 and stores it in the storage unit 700. As a result, the acquisition unit 701 can acquire the information used when determining whether or not the subject 110 is drowsy, and can refer to it to the first determination unit 702 and the second determination unit 703. can.

The first determination unit 702 determines whether or not the respiratory cycle or amplitude of the subject 110 satisfies the first condition based on the information of the respiratory cycle or amplitude of the subject 110. The first determination unit 702 determines that the subject 110 is drowsy when it is determined that the first condition is satisfied, and when it is determined that the first condition is not satisfied, the first determination unit 110 determines that the subject 110 is drowsy. It is determined that drowsiness has not occurred.

The first determination unit 702 determines whether or not the first condition is satisfied based on the comparison result between the respiratory cycle or amplitude statistical value of the subject 110 and the predetermined threshold value in a time zone of a predetermined length, for example. judge. The statistical value is, for example, an average value. The statistics may be variance, standard deviation, maximum, median, mode, and so on. The statistical value is specifically a respiratory drowsiness value.

The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like. The predetermined threshold value is set by, for example, the user of the drowsiness detection device 100. The predetermined threshold is specifically the respiratory drowsiness threshold.

Specifically, the first determination unit 702 calculates the average value of the respiratory cycle or amplitude of the subject 110 in a time zone of a predetermined length as a respiratory drowsiness value. The first determination unit 702 determines that the first condition is satisfied when the respiratory drowsiness value is equal to or higher than the respiratory drowsiness threshold. On the other hand, the first determination unit 702 determines that the first condition is not satisfied when the respiratory drowsiness value is smaller than the respiratory drowsiness threshold value.

As a result, the first determination unit 702 causes drowsiness in the subject 110 based on the statistical value of the respiratory cycle or amplitude of the subject 110 in the time zone in which the respiratory tendency of the subject 110 appears. It is possible to improve the accuracy of detecting the fact.

The first determination unit 702 sets a predetermined threshold value based on an index value indicating a variation in the respiratory cycle or amplitude of the subject 110 in a time zone of a predetermined length. The index value is, for example, the variance or standard deviation of the respiratory drowsiness value. The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like.

Specifically, the first determination unit 702 calculates the respiratory drowsiness threshold = the average value of the respiratory drowsiness value A-weighting coefficient K × the standard deviation value B of the respiratory drowsiness value. The weighting coefficient K is set by the user of the drowsiness detection device 100. As a result, the first determination unit 702 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy. The first determination unit 702 is realized by, for example, the respiratory drowsiness determination unit described later in FIG.

The second determination unit 703 determines that the subject 110 is drowsy, and then determines that the first condition is no longer satisfied, and then the time or amplitude of the exhalation of the subject 110 for each breath. It is determined whether or not the index value indicating the variation of is satisfied with the second condition. The second determination unit 703 determines that the subject 110 is drowsy when it is determined that the second condition is satisfied, and when it is determined that the second condition is not satisfied, the subject 110 is drowsy. It is determined that it has not occurred. The index value is, for example, the standard deviation value or the variance of the exhalation time. The index value may be a standard deviation value or variance of the ratio of the time of inspiration to the time of exhalation. Specifically, the index value is the awakening effort value. As a result, the second determination unit 703 can improve the accuracy of detecting that the subject 110 is drowsy.

The second determination unit 703 is based on, for example, a comparison result between an index value indicating a variation in the time or amplitude of the exhalation of the subject 110 for each breath in a time zone of a predetermined length and a predetermined threshold value. 2 Determine whether or not the conditions are met. The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like. The predetermined threshold is specifically the arousal effort threshold. As a result, the second determination unit 703 can easily reflect the respiratory tendency of the subject 110 in the index value, and can improve the accuracy of detecting that the subject 110 is drowsy. can.

The second determination unit 703 sets a predetermined threshold value based on, for example, an index value indicating a variation in the time or amplitude of the exhalation of the subject 110 for each breath in a time zone of a predetermined length. The index value is, for example, the variance of the awakening effort value or the standard deviation. The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like.

Specifically, the second determination unit 703 calculates the awakening effort threshold value = the average value of the awakening effort values A-the weighting coefficient K × the standard deviation value B of the awakening effort value. The weighting coefficient K is set by the user of the drowsiness detection device 100. As a result, the second determination unit 703 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy.

Whether the second determination unit 703 satisfies the second condition after it is determined that the subject 110 is drowsy and before the predetermined time elapses after it is determined that the first condition is no longer satisfied. It may be determined whether or not. As a result, the second determination unit 703 does not determine whether or not drowsiness is occurring based on the second condition after the elapse of the predetermined time, and after the drowsiness is resolved, drowsiness is erroneously generated. It is possible to suppress the determination that the item is being used.

The second determination unit 703 determines that the subject 110 is drowsy, and then determines that the first condition is no longer satisfied, and then the time or amplitude of inspiration for each breath of the subject 110. It is determined whether or not the index value indicating the variation of is satisfied with the third condition. The second determination unit 703 determines that the subject 110 is drowsy when it is determined that the third condition is satisfied, and when it is determined that the third condition is not satisfied, the subject 110 is drowsy. It is determined that it has not occurred. The index value is, for example, the standard deviation value or the variance of the inhalation time. The index value may be a standard deviation value or variance of the ratio of the time of exhalation to the time of inspiration. Specifically, the index value is the awakening effort value. As a result, the second determination unit 703 can improve the accuracy of detecting that the subject 110 is drowsy.

The second determination unit 703 is, for example, based on a comparison result between an index value indicating a variation in the inhalation time or amplitude for each breath of the subject 110 in a time zone of a predetermined length and a predetermined threshold value. It is determined whether or not the three conditions are satisfied. The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like. The predetermined threshold is specifically the arousal effort threshold. As a result, the second determination unit 703 can easily reflect the respiratory tendency of the subject 110 in the index value, and can improve the accuracy of detecting that the subject 110 is drowsy. can.

The second determination unit 703 sets a predetermined threshold value based on, for example, an index value indicating a variation in the inhalation time or amplitude for each breath of the subject 110 in a time zone of a predetermined length. The index value is, for example, the variance of the awakening effort value or the standard deviation. The predetermined length is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined length is preferably a length equal to or longer than the time required for the subject 110 to take several breaths, and a length at which the subject 110's tendency to breathe appears. The unit of the predetermined length is hours, minutes, seconds, and the like.

Specifically, the second determination unit 703 calculates the awakening effort threshold value = the average value of the awakening effort values A-the weighting coefficient K × the standard deviation value B of the awakening effort value. The weighting coefficient K is set by the user of the drowsiness detection device 100. As a result, the second determination unit 703 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy.

Whether the second determination unit 703 satisfies the third condition between the time when the subject 110 is determined to be drowsy and the time when the predetermined time elapses after the determination that the first condition is no longer satisfied. Judge whether or not. As a result, the second determination unit 703 does not determine whether or not drowsiness is occurring based on the third condition after the elapse of the predetermined time, and after the drowsiness is resolved, drowsiness is erroneously generated. It is possible to suppress the determination that the item is being used. Specifically, the second determination unit 703 is realized by the awakening effort determination unit described later in FIG.

The output unit 704 outputs an instruction to the alarm device 306 to eliminate the drowsiness of the subject 110 by using sound, vibration, odor, or the like according to the determination result of the second determination unit 703. The output unit 704 may output the processing result of each functional unit. The output format is, for example, display on a display, print output to a printer, transmission to an external device by the network I / F 303, or storage in a storage area such as a memory 302 or a recording medium 305.

(Specific example of the functional configuration of the drowsiness detection device 100)
Next, a specific example of the functional configuration of the drowsiness detection device 100 will be described with reference to FIG.

FIG. 8 is a block diagram showing a specific example of the functional configuration of the drowsiness detection device 100. The drowsiness detection device 100 includes a first determination processing unit 801 and a second determination processing unit 802. For example, the first determination processing unit 801 realizes the first determination unit 702 shown in FIG. 7. For example, the second determination processing unit 802 realizes the second determination unit 703 shown in FIG. 7.

The first determination processing unit 801 includes a respiratory frequency calculation unit 803, a respiratory drowsiness value calculation unit 804, a respiratory drowsiness threshold calculation unit 805, and a respiratory drowsiness determination unit 806. The first determination processing unit 801 calculates the drowsiness value of the subject 110 based on the cycle or amplitude of respiration, and determines whether or not the subject 110 is drowsy based on the drowsiness value of the subject 110. ..

The respiration frequency calculation unit 803 calculates the respiration frequency based on the respiration signal 800 received from the sensor device 211. The respiration frequency calculation unit 803 calculates the exhalation start point and the inspiration start point based on, for example, the respiration signal 800 received from the sensor device 211. The breathing frequency calculation unit 803 calculates the breathing interval from the exhalation start point to the exhalation start point. The breathing frequency calculation unit 803 may calculate the breathing interval from the breathing start point to the breathing start point. The respiration frequency calculation unit 803 divides the calculated respiration interval by the sampling frequency to calculate the respiration cycle. Then, the respiratory frequency calculation unit 803 reciprocals the respiratory cycle and calculates the respiratory frequency.

The respiratory drowsiness value calculation unit 804 calculates the statistical value of the respiratory frequency at a predetermined time based on the respiratory frequency, and calculates the respiratory drowsiness value using the statistical value of the respiratory frequency. The predetermined time is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined time is preferably a time longer than the time required for the subject 110 to take several breaths, and is a length of time during which the subject 110's tendency to breathe appears. The unit of the predetermined time is hours, minutes, seconds, and the like. The statistical value is, for example, an average value. The statistics may be variance, standard deviation, maximum, median, mode, and so on.

The respiratory drowsiness threshold calculation unit 805 calculates the statistical value of the respiratory frequency within a predetermined time based on the respiratory frequency, and calculates the respiratory drowsiness threshold using the statistical value of the respiratory frequency. The predetermined time is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined time is preferably a time longer than the time required for the subject 110 to take several breaths, and is a length of time during which the subject 110's tendency to breathe appears. The unit of the predetermined time is hours, minutes, seconds, and the like. The statistical value is, for example, an average value. The statistics may be variance, standard deviation, maximum, median, mode, and so on.

The respiratory drowsiness determination unit 806 compares the respiratory drowsiness value with the respiratory drowsiness threshold, and when the respiratory drowsiness value is lower than the respiratory drowsiness threshold, the subject 110 is in a "sleepy" state in which drowsiness is occurring. judge. When the respiratory drowsiness value is equal to or higher than the respiratory drowsiness threshold value, it is determined that the subject 110 is in a “wake” state in which drowsiness does not occur.

The second determination processing unit 802 includes an exhalation-breath ratio calculation unit 807, an awakening effort value calculation unit 808, an awakening effort threshold value calculation unit 809, an awakening effort determination necessity determination unit 810, and an awakening effort determination unit 811. including. The second determination processing unit 802 calculates the awakening effort value of the subject 110 based on the cycle or amplitude of exhalation or the time or amplitude of inspiration, and the subject 110 is based on the awakening effort value of the subject 110. Determine if you are drowsy.

The breath-in-breath ratio calculation unit 807 calculates the exhalation-breath ratio based on the breathing signal 800. The exhalation-inspiration ratio calculation unit 807 calculates an exhalation start point and an inspiration start point based on, for example, the breathing signal 800 received from the sensor device 211. The exhalation-inspiration ratio calculation unit 807 calculates the exhalation interval, which is the interval between the exhalation start point and the inspiration start point, and the inspiration interval, which is the interval between the inspiration start point and the exhalation start point. The exhalation-breath ratio calculation unit 807 divides the exhalation interval by the sampling frequency to calculate the exhalation time, and divides the inspiration interval by the sampling frequency to calculate the inspiration time. The exhalation-breath ratio calculation unit 807 calculates the ratio between the exhalation time and the inspiration time as the exhalation-inspiration ratio.

Further, the exhalation-breath ratio calculation unit 807 calculates, for example, the integrated value of the breath signal 800 from the exhalation start point to the inspiration start point as the exhalation power, and breathes from the inspiration start point to the exhalation start point. The integrated value of the signal 800 may be calculated as the inspiratory power. The exhalation-inspiration ratio calculation unit 807 may divide the exhalation power by the sampling frequency to calculate the exhalation amplitude, and divide the inspiration power by the sampling frequency to calculate the inspiration amplitude. The exhalation-breath ratio calculation unit 807 may calculate the ratio of the exhalation amplitude and the inspiration amplitude as the exhalation-inspiration ratio.

The awakening effort value calculation unit 808 calculates the awakening effort value using the statistical value of the exhalation / inhalation ratio at a predetermined time based on the exhalation / inhalation ratio. The arousal effort value is, for example, the standard deviation of the exhalation-breath ratio. The predetermined time is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined time is preferably a time longer than the time required for the subject 110 to take several breaths, and is a length of time during which the subject 110's tendency to breathe appears. The unit of the predetermined time is hours, minutes, seconds, and the like. The statistical value is, for example, an average value. The statistics may be variance, standard deviation, maximum, median, mode, and so on.

The awakening effort threshold calculation unit 809 calculates the awakening effort threshold using the statistical value of the exhalation / inhalation ratio at a predetermined time based on the exhalation / inhalation ratio. The awakening effort threshold is calculated based on the average value of the awakening effort value obtained from the exhalation-breathing ratio and the standard deviation value of the awakening effort value obtained from the exhalation-breathing ratio. The predetermined time is set by, for example, the user of the drowsiness detection device 100. Specifically, the predetermined time is preferably a time longer than the time required for the subject 110 to take several breaths, and is a length of time during which the subject 110's tendency to breathe appears. The unit of the predetermined time is hours, minutes, seconds, and the like. The statistical value is, for example, an average value. The statistics may be variance, standard deviation, maximum, median, mode, and so on.

If the respiratory drowsiness determination unit 806 determines that the respiratory drowsiness determination unit 806 is in the "sleepy" state in the past t seconds, the awakening effort determination necessity determination unit 810 causes drowsiness in the subject 110 based on the awakening effort value. Whether or not it is determined to be "judgment required". On the other hand, if the awakening effort determination necessity determination unit 810 has not determined that the respiratory drowsiness determination unit 806 is in the "sleepy" state in the past t seconds, the subject 110 becomes drowsy based on the awakening effort value. It is determined that "no determination is required" whether or not it has occurred. The t seconds are set by, for example, the user of the drowsiness detection device 100. The awakening effort determination necessity determination unit 810 may use t time, t minutes, etc. instead of t seconds.

The awakening effort determination unit 811 compares the awakening effort value with the awakening effort threshold value, and if the awakening effort value is equal to or greater than the awakening effort threshold value, determines that the subject 110 is “awakening effort in progress”. The awakening effort determination unit 811 compares the awakening effort value with the awakening effort threshold value, and if the awakening effort value is lower than the awakening effort threshold value, determines that the subject 110 is not “awakening effort in progress”. When the awakening effort determination unit 811 determines that the awakening effort determination necessity determination unit 810 is "determination required" and the awakening effort determination unit 811 is "awakening effort in progress", the respiratory drowsiness determination unit 806 Correct the judgment result to "sleepy".

(Flow of drowsiness detection)
Next, the flow of drowsiness detection will be described with reference to FIGS. 9 and 10.

9 and 10 are explanatory views showing the flow of drowsiness detection. In FIG. 9, the drowsiness detection device 100 calculates the respiratory cycle based on the interval between the maximum values of the received respiratory signals. The respiratory signal becomes, for example, the waveform shown in Graph 900 of FIG. The vertical axis of the graph 900 in FIG. 9 indicates the pressure. The horizontal axis of the graph 900 in FIG. 9 indicates time. The drowsiness detection device 100 calculates the respiratory drowsiness value based on the calculated respiratory cycle and compares it with the respiratory drowsiness threshold value to determine whether or not the subject 110 is drowsy. Next, the description shifts to FIG.

In FIG. 10, after the drowsiness detection device 100 determines that the subject 110 is drowsy, it is determined that the subject 110 is not drowsy by comparing the respiratory cycle with the respiratory drowsiness threshold. In the case, the exhalation time and the inspiration time are calculated based on the breathing signal. Here, the respiratory signal is, for example, the waveform of graph 1000 in FIG. The vertical axis of the graph 1000 in FIG. 10 indicates the pressure. The horizontal axis of the graph 1000 in FIG. 10 indicates time. In the example of FIG. 10, the respiration signals of the respiration pattern 1 and the respiration pattern 2 are shown as an example. The drowsiness detection device 100 distinguishes the respiration patterns in which the ratios of the exhalation time and the inspiration time are different even if the respiration cycle is the same, such as the respiration pattern 1 and the respiration pattern 2, and the subject 110 is drowsy. Further determines whether or not is occurring.

In the drowsiness detection device 100, for example, when the variation in the respiratory cycle is relatively small and the variation in the ratio between the exhalation time and the inspiration time is also relatively small as in the breathing pattern 1, the subject 110 becomes drowsy. It is determined that it has not occurred. On the other hand, when the drowsiness detection device 100 has a relatively small variation in the respiratory cycle but a relatively large variation in the ratio between the exhalation time and the inspiration time, as in the breathing pattern 2, the subject 110 Determine that drowsiness is occurring.

(Example of drowsiness detection)
Next, an example of drowsiness detection will be described with reference to FIGS. 11 to 14.

11 to 14 are explanatory views showing an embodiment of drowsiness detection. In FIG. 11, the drowsiness detection device 100 differentiates the respiratory signal received from the sensor device 211 to generate a respiratory differential signal. The respiratory signal becomes, for example, the waveform of graph 1100 of FIG. The vertical axis of the graph 1100 in FIG. 11 indicates the pressure. The horizontal axis of graph 1100 in FIG. 11 indicates time. The respiratory differential signal becomes, for example, the waveform of graph 1110 in FIG. The vertical axis of the graph 1110 in FIG. 11 shows the differential value. The horizontal axis of graph 1110 in FIG. 11 indicates time. The drowsiness detection device 100 calculates the time point at which the respiratory differential signal changes from positive to negative as the exhalation start point. On the other hand, the drowsiness detection device 100 calculates the time point at which the respiratory differential signal changes from negative to positive as the inspiration start point. The drowsiness detection device 100 stores the calculated exhalation start point array including the exhalation start point and the inspiration start point array including the calculated inspiration start point by using the analysis information table 400.

The drowsiness detection device 100 calculates the breathing interval from the exhalation start point to the exhalation start point. The drowsiness detection device 100 may calculate the breathing interval from the inhalation start point to the inspiration start point. The drowsiness detection device 100 stores the respiration interval sequence including the calculated respiration interval using the respiration information table 500. The drowsiness detection device 100 divides the calculated respiration interval by the sampling frequency to calculate the respiration cycle. The drowsiness detection device 100 stores the respiratory cycle sequence including the calculated respiratory cycle by using the respiratory information table 500.

Here, the drowsiness detection device 100 sets the first appearance point as the exhalation start point when the respiratory signal vibrates relatively finely and the time points in which the respiratory differential signal changes from positive to negative appear continuously. You may. Further, the drowsiness detection device 100 may not be set as the exhalation start point even if a time point at which the respiratory differential signal changes from positive to negative appears while the respiratory signal is equal to or higher than the threshold value. As a result, the drowsiness detection device 100 starts erroneous exhalation when a time point at which the respiratory differential signal changes from positive to negative appears due to a detection error of the sensor device 211 or the like before the respiratory signal is completely lowered. You can avoid setting points.

Further, when the breathing signal vibrates relatively finely and the time points at which the breathing differential signal changes from negative to positive appear continuously, the drowsiness detection device 100 sets the time point at which the breathing signal first appears as the inhalation start point. You may. Further, the drowsiness detection device 100 may not be set as the inhalation start point even if a time point at which the respiratory differential signal changes from negative to positive appears while the respiratory signal is equal to or higher than the threshold value. As a result, the drowsiness detection device 100 starts erroneous inhalation when a time point at which the respiratory differential signal changes from negative to positive appears due to a detection error of the sensor device 211 or the like before the respiratory signal is completely lowered. You can avoid setting points. Next, the description proceeds to FIG.

In FIG. 12, the drowsiness detection device 100 reciprocals the calculated respiratory cycle and calculates the respiratory frequency. The drowsiness detection device 100 stores the respiration frequency array including the calculated respiration frequency by using the respiration information table 500. The respiratory frequency is as shown in the waveform of graph 1200 in FIG. The vertical axis of the graph in FIG. 12 indicates the respiratory frequency. The horizontal axis of the graph 1200 in FIG. 12 indicates time. Next, assuming that the drowsiness detection device 100 once determines that the subject 110 is drowsy based on the respiration frequency, and then determines that the subject 110 is not drowsy based on the respiration frequency. The description shifts to FIG.

In FIG. 13, the drowsiness detection device 100 determines that the subject 110 is not drowsy based on the respiratory frequency, but actually exhales whether or not the subject 110 continues to be drowsy. Judgment is made based on the ratio of time to inhalation time, and the drowsiness of the subject 110 is accurately detected.

Similar to FIG. 11, the drowsiness detection device 100 differentiates the respiratory signal received from the sensor device 211 to generate a respiratory differential signal. The drowsiness detection device 100 calculates the time point at which the respiratory differential signal changes from positive to negative as the exhalation start point, and calculates the time point at which the respiratory differential signal changes from negative to positive as the inspiration start point, and analyzes information. It is stored using the table 400.

The drowsiness detection device 100 refers to the analysis information table 400 and calculates the exhalation interval from the exhalation start point to the inspiration start point. The drowsiness detection device 100 stores the exhalation interval array including the calculated exhalation interval by using the exhalation / inhalation information table 600. The drowsiness detection device 100 calculates the inspiration interval from the inspiration start point to the exhalation start point. The drowsiness detection device 100 stores the inspiration interval array including the calculated inspiration interval by using the exhalation / inspiration information table 600.

The drowsiness detection device 100 divides the calculated exhalation interval by the sampling frequency to calculate the exhalation time. The drowsiness detection device 100 stores the exhalation time array including the calculated exhalation time using the exhalation / inspiration information table 600. The drowsiness detection device 100 divides the calculated inspiration interval by the sampling frequency to calculate the inspiration time. The drowsiness detection device 100 stores the inspiration time sequence including the calculated inspiration time by using the exhalation / inspiration information table 600.

The drowsiness detection device 100 pairs the calculated exhalation time and inspiration time, and calculates the ratio of the inspiration time to the exhalation time as the exhalation-inspiration ratio. Here, the drowsiness detection device 100 specifies the minimum value of the sequence length of the exhalation time sequence and the inspiration time sequence, and the data for the sequence length longer than the minimum value is not paired. Not used to calculate the ratio. The drowsiness detection device 100 stores the exhalation-breath ratio array including the calculated exhalation-inspiration ratio using the exhalation-inspiration information table 600.

The drowsiness detection device 100 calculates the standard deviation of the exhalation-breath ratio as the awakening effort value. The drowsiness detection device 100 stores the awakening effort value array including the calculated awakening effort value using the exhalation / inhalation information table 600. When the calculated awakening effort value is equal to or greater than the awakening effort threshold value, the drowsiness detection device 100 determines that the subject 110 is in the “awakening effort” state and the subject 110 is in the “sleepy” state. On the other hand, when the calculated awakening effort value is lower than the awakening effort threshold value, the drowsiness detection device 100 determines that the subject 110 is not "awakening effort in progress". The drowsiness detection device 100 stores the determination result array including the determination result by using the exhalation / inhalation information table 600. Next, the description shifts to FIG. 14, and an example of the determination result will be described.

In FIG. 14, graph 1400 shows the time course of respiratory drowsiness. The vertical axis of the graph 1400 is the magnitude of the respiratory drowsiness value. The horizontal axis of graph 1400 is time. Line 1401 in graph 1400 is the time variation of respiratory drowsiness value. Line 1402 in graph 1400 is the respiratory drowsiness threshold. In the black frame of the graph 1400, the respiratory drowsiness value is larger than the respiratory drowsiness threshold.

Graph 1410 shows the drowsiness correct answer value, which is the degree of drowsiness actually occurring in the subject 110. The drowsiness correct answer value is a value obtained by a person evaluating the drowsiness of the subject 110 based on a video or the like according to a drowsiness estimation method from facial expressions. The drowsiness correct answer value is expressed by, for example, "0" indicating that it has not occurred, "1" indicating that it has occurred, and "2" indicating that it has occurred and the drowsiness is strong. The vertical axis of the graph 1410 is the magnitude of the drowsiness correct answer value. The horizontal axis of graph 1410 is time. Line 1411 of the graph 1410 is the time change of the drowsiness correct answer value. In the black frame of the graph 1410, the subject 110 is drowsy.

Graph 1420 shows the result of determining whether or not the subject 110 is drowsy based on the respiratory drowsiness value of the graph 1400. The vertical axis of the graph 1420 is the result of determining whether or not the subject 110 is drowsy. The results of determining whether or not the subject 110 is drowsy are, for example, "0" indicating that drowsiness has not occurred, "1" indicating that drowsiness has occurred, and that drowsiness has occurred and is strong. It is represented by "2" indicating. The horizontal axis of the graph 1420 is time. The line 1421 of the graph 1420 is the time change of the judgment result. In the black frame of the graph 1420, the subject 110 is actually drowsy, but the respiratory drowsiness value is larger than the respiratory drowsiness threshold, and it is determined from the respiratory drowsiness value that the subject 110 is drowsy. I haven't been able to.

Graph 1430 shows the time change of the awakening effort value. The vertical axis of the graph 1430 is the magnitude of the awakening effort value. The horizontal axis of graph 1430 is time. Line 1431 of the graph 1430 is a time change of the awakening effort value. Line 1432 in graph 1430 is the arousal effort threshold. In the black frame of the graph 1430, the arousal effort value is larger than the respiratory drowsiness threshold.

Graph 1440 shows the result of determining whether or not the subject 110 is drowsy based on the awakening effort value of graph 1430. The vertical axis of the graph 1440 is the result of determining whether or not the subject 110 is drowsy. The results of determining whether or not the subject 110 is drowsy are, for example, "0" indicating that drowsiness has not occurred, "1" indicating that drowsiness has occurred, and that drowsiness has occurred and is strong. It is represented by "2" indicating. The horizontal axis of graph 1440 is time. The line 1441 of the graph 1440 is the time change of the judgment result. In the black frame of the graph 1440, it can be determined that the subject 110 is drowsy.

As a result, the drowsiness detection device 100 can use the breathing cycle, the exhalation time, and the like as an index value based on breathing for determining whether or not the subject 110 is drowsy. It is possible to improve the accuracy of detecting that drowsiness is occurring in 110. Then, if the subject 110 is drowsy, the drowsiness detection device 100 prevents the traffic accident by using sound, vibration, odor, or the like to eliminate the drowsiness of the subject 110, thereby preventing traffic safety. It can be secured.

(Example of drowsiness detection processing procedure)
Next, an example of the drowsiness detection processing procedure will be described with reference to FIG.

FIG. 15 is a flowchart showing an example of the drowsiness detection processing procedure. In FIG. 15, the drowsiness detection device 100 executes the respiratory frequency calculation process described later in FIG. 16 (step S1501).

Next, the drowsiness detection device 100 executes the respiratory drowsiness determination process described later in FIG. 17 (step S1502). Then, the drowsiness detection device 100 determines whether or not the determination result is "sleepy" (step S1503). Here, when the determination result is "sleepy" (step S1503: Yes), the drowsiness detection device 100 outputs "sleepy" as the determination result (step S1504), and ends the drowsiness detection process.

On the other hand, when the determination result is "awakening" (step S1503: No), the drowsiness detection device 100 executes the awakening effort determination necessity determination process described later in FIG. 20 (step S1505). Next, the drowsiness detection device 100 determines whether or not the determination result is “determination unnecessary” (step S1506). Here, when the determination result is "determination unnecessary" (step S1506: Yes), the drowsiness detection device 100 outputs "awakening" as the determination result (step S1507), and ends the drowsiness detection process.

On the other hand, when the determination result is "determination required" (step S1506: No), the drowsiness detection device 100 executes the awakening effort value calculation process described later in FIGS. 21 and 22 (step S1508). Next, the drowsiness detection device 100 executes the awakening effort threshold setting process described later in FIG. 23 (step S1509).

Then, the drowsiness detection device 100 determines whether or not the awakening effort value is equal to or greater than the awakening effort threshold value (step S1510). When the awakening effort value is equal to or greater than the awakening effort threshold value (step S1510: Yes), the drowsiness detection device 100 outputs “sleepy” as a determination result (step S1511), and ends the drowsiness detection process.

On the other hand, when the awakening effort value is smaller than the awakening effort threshold value (step S1510: No), the drowsiness detection device 100 outputs "awakening" as a determination result (step S1512), and ends the drowsiness detection process.

(Example of respiratory frequency calculation processing procedure)
Next, an example of the respiratory frequency calculation processing procedure will be described with reference to FIG.

FIG. 16 is a flowchart showing an example of the respiratory frequency calculation processing procedure. In FIG. 16, the drowsiness detection device 100 applies a bandpass filter that extracts a respiratory frequency component to the respiratory signal (step S1601). The bandpass filter is, for example, a filter that extracts a respiratory frequency component of 0.05 to 0.8 Hz.

Next, the drowsiness detection device 100 differentiates the respiratory signal and calculates the respiratory differential signal (step S1602). Then, the drowsiness detection device 100 calculates the point where the respiratory differential signal changes from positive to negative as the inspiration start point, and calculates the point where the respiratory differential signal changes from negative to positive as the exhalation start point (step S1603). ).

Next, the drowsiness detection device 100 calculates the interval between the inspiration start point and the inspiration start point as the breathing interval (step S1604). Then, the drowsiness detection device 100 divides the respiration interval by the sampling frequency to calculate the respiration cycle (step S1605).

Next, the drowsiness detection device 100 reciprocals the respiratory cycle and calculates the respiratory frequency (step S1606). Then, the drowsiness detection device 100 ends the respiration frequency calculation process.

(Example of respiratory drowsiness judgment processing procedure)
Next, an example of the respiratory drowsiness determination processing procedure will be described with reference to FIG.

FIG. 17 is a flowchart showing an example of the respiratory drowsiness determination processing procedure. In FIG. 17, the drowsiness detection device 100 determines whether or not a respiration frequency of x minutes or more is stored in the respiration frequency array (step S1701). Here, when the respiratory frequency of x minutes or more is not stored (step S1701: No), the drowsiness detection device 100 sets "awakening" in the determination result (step S1702), and ends the respiratory drowsiness determination process.

On the other hand, when the respiratory frequency of x minutes or more is stored (step S1701: Yes), the drowsiness detection device 100 executes the respiratory drowsiness value calculation process described later in FIG. 18 (step S1703). The x-minute is, for example, 10 minutes in consideration of the time from overstrain to calming down at the start of operation. Next, the drowsiness detection device 100 executes the respiratory drowsiness threshold setting process described later in FIG. 19 (step S1704).

Then, the drowsiness detection device 100 determines whether or not the respiratory drowsiness value is equal to or lower than the respiratory drowsiness threshold value (step S1705). Here, when the respiratory drowsiness value is not equal to or less than the respiratory drowsiness threshold value (step S1705: No), the drowsiness detection device 100 sets "awakening" in the determination result (step S1706), and ends the respiratory drowsiness determination process.

On the other hand, when the respiratory drowsiness value is equal to or lower than the respiratory drowsiness threshold value (step S1705: Yes), the drowsiness detection device 100 sets "sleepy" in the determination result (step S1707), and ends the respiratory drowsiness determination process.

(Example of respiratory drowsiness value calculation processing procedure)
Next, an example of the respiratory drowsiness value calculation processing procedure will be described with reference to FIG.

FIG. 18 is a flowchart showing an example of the respiratory drowsiness value calculation processing procedure. In FIG. 18, the drowsiness detection device 100 acquires the respiratory frequency array for the past time a (step S1801). The time a is, for example, 4 minutes. Next, the drowsiness detection device 100 averages the respiratory frequency arrangement for the past time a and calculates the respiratory drowsiness value (step S1802). Then, the drowsiness detection device 100 ends the respiratory drowsiness value calculation process.

(Example of respiratory drowsiness threshold setting processing procedure)
Next, an example of the respiratory drowsiness threshold setting processing procedure will be described with reference to FIG.

FIG. 19 is a flowchart showing an example of the respiratory drowsiness threshold setting processing procedure. In FIG. 19, the drowsiness detection device 100 determines whether or not there is respiratory information for the time b corresponding to the previous running (step S1901). The time b is, for example, 90 minutes.

Here, when there is respiratory information for time b (step S1901: Yes), the drowsiness detection device 100 sets the average value of the respiratory drowsiness value for time b to A, and sets the standard value of the respiratory drowsiness value for time b. The deviation value is set to B (step S1902). Then, the drowsiness detection device 100 shifts to the process of step S1904.

On the other hand, when there is no respiratory information for time b (step S1901: No), the drowsiness detection device 100 sets 0 as the average value of the respiratory drowsiness value to A, and sets 0 as the standard deviation value of the respiratory drowsiness value to B. (Step S1903). Then, the drowsiness detection device 100 shifts to the process of step S1904.

In step S1904, the drowsiness detection device 100 determines whether or not there is respiratory information for the past time c (step S1904). The time c is, for example, 8 minutes. Here, when there is no respiratory information for the time c (step S1904: No), the drowsiness detection device 100 calculates the respiratory drowsiness threshold value = A-weighting coefficient K × B (step S1905). Then, the drowsiness detection device 100 ends the respiratory drowsiness threshold setting process.

On the other hand, when there is respiratory information for time c (step S1904: Yes), the drowsiness detection device 100 sets the average value of the respiratory drowsiness value for time c to C (step S1906). Next, the drowsiness detection device 100 sets the standard deviation value of the respiratory drowsiness value for the time c to D (step S1907). Then, the drowsiness detection device 100 sets the maximum value of B and D to E (step S1908).

Next, the drowsiness detection device 100 calculates the respiratory drowsiness threshold value = C + weighting coefficient K × E (step S1909). Then, the drowsiness detection device 100 ends the respiratory drowsiness threshold setting process.

(Example of procedure for determining the necessity of awakening effort judgment)
Next, an example of the procedure for determining the necessity of determining the awakening effort will be described with reference to FIG.

FIG. 20 is a flowchart showing an example of the procedure for determining the necessity of awakening effort determination. In FIG. 20, the drowsiness detection device 100 determines whether or not it is determined to be “sleepy” within the past time d by the respiratory drowsiness determination process (step S2001). The time d is, for example, 10 minutes in consideration of the duration of concentration.

Here, if it is determined to be "sleepy" within the past time d (step S2001: Yes), the drowsiness detection device 100 determines "determination required" (step S2002), and awakening effort determination necessity determination processing. To finish.

On the other hand, if it is not determined to be "sleepy" within the past time d (step S2001: No), the drowsiness detection device 100 determines that "determination is unnecessary" (step S2003), and awakening effort determination necessity determination process. To finish.

(Example of awakening effort value calculation processing procedure)
Next, an example of the awakening effort value calculation processing procedure will be described with reference to FIGS. 21 and 22.

21 and 22 are flowcharts showing an example of the awakening effort value calculation processing procedure. In FIG. 21, the drowsiness detection device 100 differentiates the respiratory signal and calculates the respiratory differential signal (step S2101).

Next, the drowsiness detection device 100 calculates the point where the respiratory differential signal changes from positive to negative as the inspiration start point, and calculates the point where the respiratory differential signal changes from negative to positive as the exhalation start point (step). S2102). Then, the drowsiness detection device 100 calculates the interval between the inspiration start point and the exhalation start point as the inspiration interval (step S2103).

Next, the drowsiness detection device 100 calculates the interval between the exhalation start point and the inspiration start point as the exhalation interval (step S2104). Then, the drowsiness detection device 100 divides the inspiration interval and the exhalation interval by the sampling frequency to calculate the inspiration time and the exhalation time (step S2105).

Next, the drowsiness detection device 100 calculates the integrated value from the inspiration start point to the exhalation start point as the inspiration power (step S2106). Then, the drowsiness detection device 100 calculates the integrated value from the exhalation start point to the inspiration start point as the exhalation power (step S2107).

Next, the drowsiness detection device 100 divides the inspiration power and the exhalation power by the sampling frequency to calculate the inspiration amplitude and the exhalation amplitude (step S2108). Then, the drowsiness detection device 100 shifts to the process of step S2201.

In FIG. 22, the drowsiness detection device 100 determines whether or not to use the inspiration time and the exhalation time for calculating the awakening effort value (step S2201). When the inhalation time and the exhalation time are used (step S2201: Yes), the drowsiness detection device 100 acquires the exhalation time sequence for the past time e (step S2202). The time e is, for example, 8 minutes.

Next, the drowsiness detection device 100 acquires the inspiration time array for the past time e (step S2203). Then, the drowsiness detection device 100 calculates the minimum value of the sequence lengths of the exhalation time sequence and the inspiration time sequence (step S2204).

Next, the drowsiness detection device 100 deletes the element in the portion where the sequence length is longer than the calculated minimum value from the exhalation time sequence and the inspiration time sequence (step S2205). Then, the drowsiness detection device 100 generates an exhalation-inspiration ratio sequence based on the exhalation time sequence and the inspiration time sequence (step S2206). After that, the drowsiness detection device 100 shifts to the process of step S2212.

On the other hand, when the inspiration time and the exhalation time are not used (step S2201: No), the drowsiness detection device 100 acquires the exhalation amplitude array for the past time e (step S2207). Next, the drowsiness detection device 100 acquires the inspiration amplitude array for the past time e (step S2208). Then, the drowsiness detection device 100 calculates the minimum value of the array lengths of the exhalation amplitude array and the inspiration amplitude array (step S2209).

Next, the drowsiness detection device 100 deletes an element from the exhalation amplitude array and the inspiration amplitude array in a portion where the array length is longer than the calculated minimum value (step S2210). Then, the drowsiness detection device 100 generates an exhalation-inspiration ratio array based on the exhalation amplitude array and the inspiration amplitude array (step S2211). After that, the drowsiness detection device 100 shifts to the process of step S2212.

In step S2212, the drowsiness detection device 100 calculates the standard deviation of the exhalation-inspiration ratio as the awakening effort value based on the exhalation-inspiration ratio arrangement (step S2212). Then, the drowsiness detection device 100 ends the awakening effort value calculation process.

(Example of awakening effort threshold setting processing procedure)
Next, an example of the awakening effort threshold setting processing procedure will be described with reference to FIG. 23.

FIG. 23 is a flowchart showing an example of the awakening effort threshold setting processing procedure. In FIG. 23, the drowsiness detection device 100 determines whether or not there is exhalation / inspiration information for the past time f (step S2301). The time f is, for example, 5 minutes.

Here, when there is no exhalation / inspiration information for the past time f (step S2301: No), the drowsiness detection device 100 sets the awakening effort threshold value = 0 (step S2302), and ends the awakening effort threshold value setting process. do.

On the other hand, when there is breath / breath information for the past time f (step S2301: Yes), whether or not the drowsiness detection device 100 has the breath / breath information for the time g corresponding to the previous run. Is determined (step S2303). The time g is, for example, 90 minutes.

Here, when there is exhalation and inspiration information for time g (step S2303: Yes), the drowsiness detection device 100 sets the standard deviation value of the awakening effort value for time g to C (step S2304), and steps. The process proceeds to S2306.

On the other hand, when there is no exhalation / inspiration information for time g (step S2303: No), the drowsiness detection device 100 sets 0 to C as the standard deviation value of the awakening effort value (step S2305). Then, the drowsiness detection device 100 shifts to the process of step S2306.

In step S2306, the drowsiness detection device 100 sets the average value of the awakening effort values for the past time h to A (step S2306). Next, the drowsiness detection device 100 sets the standard deviation value of the awakening effort value for the time h to B (step S2307). Then, the drowsiness detection device 100 sets the maximum value of B and C to D (step S2308).

Next, the drowsiness detection device 100 calculates the awakening effort threshold value = A + weighting coefficient K × D (step S2309). Then, the drowsiness detection device 100 ends the awakening effort threshold setting process.

As described above, according to the drowsiness detection device 100, when it is determined that the respiratory cycle or amplitude of the subject 110 satisfies the first condition based on the information of the respiratory cycle or amplitude of the subject 110. , It can be determined that the subject 110 is drowsy. Further, according to the drowsiness detection device 100, when it is determined that drowsiness has occurred and then it is determined that the first condition is no longer satisfied, the time or amplitude of the exhalation of the subject 110 for each breath is determined. It can be determined whether or not the index value indicating the variation satisfies the second condition. Further, according to the drowsiness detection device 100, when it is determined that the second condition is satisfied, it is determined that the subject 110 is drowsy, and when it is determined that the second condition is not satisfied, the subject 110 is determined. It can be determined that drowsiness does not occur in the patient. As a result, the drowsiness detection device 100 can improve the accuracy of detecting that the subject 110 is drowsy.

According to the drowsiness detection device 100, when it is determined that drowsiness is occurring and then the first condition is no longer satisfied, the time or amplitude of inspiration of the subject 110 for each breath varies. It can be determined whether or not the indicated index value satisfies the third condition. Further, according to the drowsiness detection device 100, when it is determined that the third condition is satisfied, it is determined that the subject 110 is drowsy, and when it is determined that the third condition is not satisfied, the subject 110 is determined. It can be determined that drowsiness does not occur in the patient. As a result, the drowsiness detection device 100 can improve the accuracy of detecting that the subject 110 is drowsy.

According to the drowsiness detection device 100, after it is determined that drowsiness has occurred, it is between the time when the respiratory cycle or amplitude of the subject 110 is determined that the first condition is not satisfied and the predetermined time elapses. , It is possible to determine whether or not the second condition is satisfied. As a result, the drowsiness detection device 100 does not determine whether or not drowsiness is occurring based on the second condition after the elapse of the predetermined time, and after the drowsiness is resolved, drowsiness is erroneously generated. It is possible to suppress the determination of the presence.

According to the drowsiness detection device 100, after it is determined that drowsiness has occurred, it is between the time when the respiratory cycle or amplitude of the subject 110 is determined that the first condition is not satisfied and the predetermined time elapses. , It is possible to determine whether or not the third condition is satisfied. As a result, the drowsiness detection device 100 does not determine whether or not drowsiness is occurring based on the third condition after the elapse of the predetermined time, and after the drowsiness is resolved, drowsiness is erroneously generated. It is possible to suppress the determination of the presence.

According to the drowsiness detection device 100, the index value indicating the variation in the exhalation time or amplitude for each breath of the subject 110 in the time zone of the first length is based on the comparison result with the predetermined threshold value. It is possible to determine whether or not the two conditions are satisfied. As a result, the drowsiness detection device 100 can use an index value indicating the variation in the time or amplitude of the exhalation of the subject 110 for each breath in the time zone in which the subject 110's respiratory tendency appears. .. Therefore, the drowsiness detection device 100 can easily reflect the respiratory tendency of the subject 110 in the index value, and can improve the accuracy of detecting that the subject 110 is drowsy. ..

According to the drowsiness detection device 100, a predetermined threshold value can be set based on an index value indicating a variation in the time or amplitude of the exhalation of the subject 110 for each breath in the time zone of the second length. As a result, the drowsiness detection device 100 determines the predetermined value based on the index value indicating the variation in the exhalation time or amplitude for each breath of the subject 110 in the time zone of the length in which the tendency of the subject 110 to breathe appears. A threshold can be set. Therefore, the drowsiness detection device 100 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy.

According to the drowsiness detection device 100, the index value indicating the variation in the inhalation time or amplitude for each breath of the subject 110 in the time zone of the first length is based on the comparison result with the predetermined threshold value. It is possible to determine whether or not the three conditions are satisfied. As a result, the drowsiness detection device 100 can use an index value indicating the variation in the time or amplitude of the exhalation of the subject 110 for each breath in the time zone in which the subject 110's respiratory tendency appears. .. Therefore, the drowsiness detection device 100 can easily reflect the respiratory tendency of the subject 110 in the index value, and can improve the accuracy of detecting that the subject 110 is drowsy. ..

According to the drowsiness detection device 100, a predetermined threshold value can be set based on an index value indicating a variation in the inspiration time or amplitude for each breath of the subject 110 in the time zone of the second length. As a result, the drowsiness detection device 100 determines the predetermined value based on the index value indicating the variation in the exhalation time or amplitude for each breath of the subject 110 in the time zone of the length in which the tendency of the subject 110 to breathe appears. A threshold can be set. Therefore, the drowsiness detection device 100 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy.

According to the drowsiness detection device 100, a standard deviation of the ratio of the exhalation time to the inspiration time for each breath of the subject 110 can be used as the index value. As a result, the drowsiness detection device 100 can relatively easily evaluate the degree of variation in the exhalation time and the inspiration time for each breath of the subject 110 even if the breathing cycle of the subject 110 varies. can do. Therefore, the drowsiness detection device 100 can improve the accuracy of detecting that the subject 110 is drowsy.

According to the drowsiness detection device 100, whether or not the first condition is satisfied is determined based on the comparison result between the respiratory cycle or amplitude statistical value of the subject 110 and the predetermined threshold value in the time zone of the third length. Can be determined. As a result, the drowsiness detection device 100 causes drowsiness in the subject 110 based on the statistical value of the respiratory cycle or amplitude of the subject 110 in the time zone in which the respiratory tendency of the subject 110 appears. It is possible to improve the accuracy of detecting the presence.

According to the drowsiness detection device 100, a predetermined threshold value can be set based on an index value indicating a variation in the respiratory cycle or amplitude of the subject 110 in the time zone of the fourth length. As a result, the drowsiness detection device 100 does not have to manually set the predetermined threshold value, can reduce the burden on the user, and can easily set the predetermined threshold value with high accuracy.

The drowsiness detection method described in the present embodiment can be realized by executing a program prepared in advance on a computer such as a personal computer or a workstation. The drowsiness detection program described in the present embodiment is executed by being recorded on a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, an MO, or a DVD, and read from the recording medium by the computer. Further, the drowsiness detection program described in the present embodiment may be distributed via a network such as the Internet.

The following additional notes are further disclosed with respect to the above-described embodiment.

(Appendix 1) When it is determined that the respiratory cycle or amplitude of the subject satisfies the first condition based on the information of the respiratory cycle or amplitude of the subject, the subject is drowsy. Judging that
When it is determined that the subject is drowsy and the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the subject's exhalation for each breath is determined. Whether or not the index value indicating the variation in time or amplitude of the subject satisfies the second condition, or whether or not the index value indicating the variation in inhalation time or amplitude for each breath of the subject satisfies the third condition. Judge whether
When it is determined that the second condition or the third condition is satisfied, it is determined that the subject is drowsy, and when it is determined that the second condition or the third condition is not satisfied, the subject is said to be drowsy. Judge that the subject is not drowsy,
A drowsiness detection device characterized by having a control unit.

(Appendix 2) The control unit
After it is determined that the subject is drowsy, the subject is said to have a predetermined time between the time when it is determined that the subject's respiratory cycle or amplitude no longer satisfies the first condition. Whether or not the index value indicating the variation in the exhalation time or amplitude for each breath of the subject satisfies the second condition, or the index value indicating the variation in the inhalation time or amplitude for each breath of the subject. The drowsiness detection device according to Appendix 1, wherein the device determines whether or not the third condition is satisfied.

(Appendix 3) The control unit
When it is determined that the subject is drowsy and then the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the said in the time zone of the first length. An appendix characterized in that it is determined whether or not the second condition is satisfied based on the comparison result between the index value indicating the variation in the time or amplitude of the exhalation for each breath of the subject and the predetermined threshold value. The drowsiness detection device according to 1 or 2.

(Appendix 4) The control unit
The following is described in Appendix 3, wherein the predetermined threshold value is set based on an index value indicating a variation in the time or amplitude of exhalation for each breath of the subject in the time zone of the second length. Drowsiness detector.

(Appendix 5) The control unit is
When it is determined that the subject is drowsy and then the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the said in the time zone of the first length. An appendix characterized in that it is determined whether or not the third condition is satisfied based on the comparison result between the index value indicating the variation in the inhalation time or amplitude for each breath of the subject and the predetermined threshold value. The drowsiness detection device according to any one of 1 to 4.

(Appendix 6) The control unit is
The description in Appendix 5, wherein the predetermined threshold value is set based on an index value indicating a variation in the inhalation time or amplitude for each breath of the subject in the time zone of the second length. Drowsiness detector.

(Appendix 7) The index value is any one of Appendix 1 to 6, characterized in that the index value is a standard deviation of the ratio of the exhalation time and the inhalation time for each breath of the subject. The drowsiness detection device described in.

(Appendix 8) The control unit is
It is characterized in that it is determined whether or not the first condition is satisfied based on the comparison result between the statistical value of the respiratory cycle or amplitude of the subject in the time zone of the third length and the predetermined threshold value. The drowsiness detection device according to any one of Supplementary note 1 to 7.

(Appendix 9) The control unit is
The drowsiness detection device according to Appendix 8, wherein the predetermined threshold value is set based on an index value indicating a variation in the respiratory cycle or amplitude of the subject in the time zone of the fourth length.

(Appendix 10) To the computer
Based on the information on the respiratory cycle or amplitude of the subject, when it is determined that the respiratory cycle or amplitude of the subject satisfies the first condition, it is determined that the subject is drowsy.
When it is determined that the subject is drowsy and the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the subject's exhalation for each breath is determined. Whether or not the index value indicating the variation in time or amplitude of the subject satisfies the second condition, or whether or not the index value indicating the variation in inhalation time or amplitude for each breath of the subject satisfies the third condition. Judge whether
When it is determined that the second condition or the third condition is satisfied, it is determined that the subject is drowsy, and when it is determined that the second condition or the third condition is not satisfied, the subject is said to be drowsy. Judge that the subject is not drowsy,
A drowsiness detection program characterized by executing processing.

100 Drowsiness detection device 110 Target person 200 Drowsiness detection system 210 Seat belt 211 Sensor device 220 Scale 300 Bus 301 CPU
302 Memory 303 Network I / F
304 Recording medium I / F
305 Recording medium 306 Alarm 307 Sensor I / F
310 Network 400 Analysis information table 500 Breathing information table 600 Breathing and breathing information table 700 Storage unit 701 Acquisition unit 702 First judgment unit 703 Second judgment unit 704 Output unit 800 Breathing signal 801 First judgment processing unit 802 Second judgment processing Part 803 Respiratory frequency calculation part 804 Respiratory drowsiness value calculation part 805 Respiratory drowsiness threshold calculation part 806 Respiration drowsiness judgment part 807 Breath breath ratio calculation part 808 Awakening effort value calculation part 809 Awakening effort threshold calculation part 810 Awakening effort judgment necessity determination Part 811 Awakening effort judgment part 900,1200,1400,1410,1420,1430,1440 Graph 1401,1402,1411,1421,1431,1432,1441 Line

Claims (7)

Based on the information on the respiratory cycle or amplitude of the subject, when it is determined that the respiratory cycle or amplitude of the subject satisfies the first condition, it is determined that the subject is drowsy.
When it is determined that the subject is drowsy and the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the subject's exhalation for each breath is determined. Whether or not the index value indicating the variation in time or amplitude of the subject satisfies the second condition, or whether or not the index value indicating the variation in inhalation time or amplitude for each breath of the subject satisfies the third condition. Judge whether
When it is determined that the second condition or the third condition is satisfied, it is determined that the subject is drowsy, and when it is determined that the second condition or the third condition is not satisfied, the subject is said to be drowsy. Judge that the subject is not drowsy,
A drowsiness detection device characterized by having a control unit. The control unit
After it is determined that the subject is drowsy, the subject is said to have a predetermined time between the time when it is determined that the subject's respiratory cycle or amplitude no longer satisfies the first condition. Whether or not the index value indicating the variation in the exhalation time or amplitude for each breath of the subject satisfies the second condition, or the index value indicating the variation in the inhalation time or amplitude for each breath of the subject. The drowsiness detection device according to claim 1, wherein the device determines whether or not the third condition is satisfied. The control unit
When it is determined that the subject is drowsy and then the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the said in the time zone of the first length. wherein the index value indicating the variation in time or amplitude of exhaled per breath of the subject, based on a result of comparison between the first predetermined threshold value, determines whether the second condition is satisfied, the The drowsiness detection device according to claim 1 or 2. The control unit
The first predetermined threshold is set based on an index value indicating a variation in the time or amplitude of exhalation for each breath of the subject in the time zone of the second length. 3. The drowsiness detection device according to 3. The control unit
It is determined whether or not the first condition is satisfied based on the result of comparison between the statistical value of the respiratory cycle or amplitude of the subject in the time zone of the third length and the second predetermined threshold value. The drowsiness detection device according to any one of claims 1 to 4. The control unit
The drowsiness according to claim 5 , wherein the second predetermined threshold value is set based on an index value indicating a variation in the respiratory cycle or amplitude of the subject in the time zone of the fourth length. Detection device. On the computer
Based on the information on the respiratory cycle or amplitude of the subject, when it is determined that the respiratory cycle or amplitude of the subject satisfies the first condition, it is determined that the subject is drowsy.
When it is determined that the subject is drowsy and the respiratory cycle or amplitude of the subject no longer satisfies the first condition, the subject's exhalation for each breath is determined. Whether or not the index value indicating the variation in time or amplitude of the subject satisfies the second condition, or whether or not the index value indicating the variation in inhalation time or amplitude for each breath of the subject satisfies the third condition. Judge whether
When it is determined that the second condition or the third condition is satisfied, it is determined that the subject is drowsy, and when it is determined that the second condition or the third condition is not satisfied, the subject is said to be drowsy. Judge that the subject is not drowsy,
A drowsiness detection program characterized by executing processing.

Images