JP6601279B2 - Sleepiness determination program, sleepiness determination device, and sleepiness determination method - Google Patents

Description

  The present invention relates to a drowsiness determination program, a drowsiness determination device, and a drowsiness determination method.

  Conventionally, a drowsiness determination device that determines whether or not a driver is drowsy based on a sleepiness level calculated by detecting a pulse wave signal from a driving driver and performing heartbeat fluctuation analysis is known. ing. In the sleepiness determination device, for example, an RSA (Respiratory Sinus Arrhythmia) component is extracted by performing heartbeat fluctuation analysis on the detected pulse wave signal, and the sleepiness level of the driver is calculated using the extracted RSA component. In addition, in the sleepiness determination device, when it is determined that the calculated sleepiness level is equal to or greater than a predetermined threshold, it is determined that the driver is drowsy and an alarm is output. As a result, the state of the driving driver is improved from the state of drowsiness to the awake state.

Japanese Patent Laying-Open No. 2015-80624 JP-A-2-277435 JP 2010-12100 A

  However, in the case of the method of calculating the sleepiness level using the RSA component, the case where the sleepiness level is determined to be low may include a state in which the driver resists sleepiness (wakefulness effort state). . This is because in the case of the sleepiness degree calculated using the RSA component, it is impossible to distinguish the arousal effort state from the normal arousal state.

  For this reason, if it is an arousal effort state, it should be determined that it is originally a state of drowsiness and alarm output should be performed. However, in the conventional drowsiness determination device, the calculated sleepiness level is low, so the driver's state Could be misjudged as being awake. As a result, warning output is not performed, and there is a possibility that driving is continued without improving the driver's state from the awakening effort state to the awakening state.

  An object of one aspect is to improve the determination accuracy for determining drowsiness.

According to one aspect, the drowsiness determination program is
The first blood pressure component is extracted by frequency analysis of the time change of the pulse interval calculated from the pulse wave signal of the subject output from the pulse sensor,
By analyzing the time change of the pulse amplitude calculated from the pulse wave signal, the second blood pressure component is extracted,
The computer executes a process of determining whether or not the subject is resistant to drowsiness based on a deviation in magnitude of the difference between the first blood pressure component and the second blood pressure component Let

  The determination accuracy for determining drowsiness can be improved.

It is a 1st figure which shows an example of a sleepiness determination system. It is a figure which shows the hardware constitutions of the navigation apparatus which is an example of a drowsiness determination apparatus. It is a figure which shows the function structure of the sleepiness determination part of the navigation apparatus which is an example of a sleepiness determination apparatus. It is a figure for demonstrating the function of a space | interval analysis part. It is a figure for demonstrating the function of an amplitude analysis part. It is a figure for demonstrating the function of a sleepiness degree calculation part. It is a figure for demonstrating the function of a wakefulness effort analysis part. It is a figure for demonstrating the function of an arousal level analysis part. It is a figure for demonstrating the function of the awakening effort state determination part. It is a flowchart of a drowsiness determination process. It is a flowchart of a sleepiness degree calculation process. It is a flowchart of an arousal effort state determination process. It is a 2nd figure which shows an example of a sleepiness determination system. It is a 3rd figure which shows an example of a sleepiness determination system.

  Each embodiment will be described below with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, the duplicate description is abbreviate | omitted by attaching | subjecting the same code | symbol.

[First Embodiment]
First, the sleepiness determination system including the sleepiness determination device according to the first embodiment will be described. FIG. 1 is a first diagram illustrating an example of a sleepiness determination system.

  As shown in FIG. 1, the drowsiness determination system 100 is mounted on a vehicle 150 and includes a pulse sensor 110, a navigation device 120, a speaker device 130, and a display device 140.

  The pulse sensor 110 is a sensor that detects a heartbeat (pulse wave) and outputs heartbeat data (pulse wave signal) in the earlobe of the driver 160 that drives the vehicle 150. The pulse wave signal output from the pulse sensor 110 is input to the navigation device 120. That is, the driver 160 who drives the vehicle 150 becomes a subject whose pulse wave is detected by the pulse sensor 110 during driving.

  The navigation device 120 is an example of a drowsiness determination device. The navigation device 120 is installed with a sleepiness determination program and an alarm program, and the navigation device 120 functions as the sleepiness determination unit 121 and the alarm unit 122 by executing these programs.

  The speaker device 130 is connected to the navigation device 120 and outputs, for example, alarm information output from the alarm unit 122 of the navigation device 120 as a voice. The display device 140 is connected to the navigation device 120, and displays and outputs alarm information output from the alarm unit 122 of the navigation device 120, for example. By outputting the warning information from the speaker device 130 or by outputting the warning information from the display device 140, the awakening level of the driver 160 is increased, and the state of the driver 160 is awakened from the state of drowsiness. It can be improved to the state.

  Note that the display device 140 also functions as an operation unit that receives an operation on the navigation device 120 from the driver 160, and an operation instruction received by the display device 140 from the driver 160 is input to the navigation device 120.

  Next, the hardware configuration of the navigation device 120 will be described. FIG. 2 is a diagram illustrating a hardware configuration of a navigation device that is an example of the drowsiness determination device. In FIG. 2, among the hardware included in the navigation device 120, particularly hardware related to functioning as the drowsiness determination unit 121 and the alarm unit 122 is illustrated.

  As shown in FIG. 2, the navigation device 120 includes a CPU (Central Processing Unit) 201, a ROM (Read Only Memory) 202, and a RAM (Random Access Memory) 203. In addition, the navigation device 120 includes an auxiliary storage device 204, a connection device 205, and a drive device 206. These hardwares are connected to each other via a bus 207.

  The CPU 201 is a computer that executes various programs (for example, a drowsiness determination program, an alarm program, etc.) stored in the auxiliary storage device 204.

  The ROM 202 is a nonvolatile memory. The ROM 202 functions as a main storage unit that stores various programs, data, and the like necessary for the CPU 201 to execute various programs stored in the auxiliary storage device 204. Specifically, the ROM 202 stores a boot program such as a basic input / output system (BIOS) or an extensible firmware interface (EFI).

  The RAM 203 is a volatile memory, and includes a DRAM (Dynamic Random Access Memory), an SRAM (Static Random Access Memory), and the like. The RAM 203 functions as a main storage unit that provides a work area that is expanded when various programs stored in the auxiliary storage device 204 are executed by the CPU 201.

  The auxiliary storage device 204 is a computer-readable storage device that records various programs installed in the navigation device 120 and data generated by executing the various programs.

  The connection device 205 is a device that connects various external devices such as the pulse sensor 110, the speaker device 130, and the display device 140 to the navigation device 120. Thereby, various information can be transmitted and received between the pulse sensor 110, the speaker device 130, the display device 140, and the navigation device 120.

  The drive device 206 is a device for setting the recording medium 210. The recording medium 210 here includes a medium for recording information optically, electrically or magnetically, such as a CD-ROM, a flexible disk, a magneto-optical disk or the like. The recording medium 210 also includes a semiconductor memory that electrically records information, such as a ROM and a flash memory.

  The various programs stored in the auxiliary storage device 204 are installed by, for example, setting the distributed recording medium 210 in the drive device 206 and reading the various programs recorded in the recording medium 210 by the drive device 206. May be. Alternatively, various programs stored in the auxiliary storage device 204 may be installed by being downloaded from a network via a communication device (not shown).

  Next, the functional configuration of the navigation device 120 will be described. FIG. 3 is a diagram illustrating a functional configuration of a navigation device that is an example of a drowsiness determination device.

  As shown in FIG. 3, the sleepiness determination unit 121 includes a pulse wave signal acquisition unit 301, an interval analysis unit 302, an amplitude analysis unit 303, a sleepiness level calculation unit 304, a wakefulness effort analysis unit 305, a wakefulness level analysis unit 306, and a wakefulness effort. A state determination unit 307 is included.

  The pulse wave signal acquisition unit 301 acquires the pulse wave signal output from the pulse sensor 110. When the vehicle 150 is in an IG (Ignition) -ON state and the driver 160 wears the pulse sensor 110 on the earlobe, a pulse wave signal is output from the pulse sensor 110. Thereby, the pulse wave signal acquisition unit 301 acquires a pulse wave signal.

  The interval analysis unit 302 calculates the time change of the pulse interval by extracting the pulse interval of the driver 160 at each time from the acquired pulse wave signal, and performs frequency analysis on the time change of the calculated pulse interval. Further, the interval analysis unit 302 detects a low frequency peak from the power spectrum waveform obtained by performing frequency analysis, and extracts a blood pressure component. Further, the interval analysis unit 302 detects a high frequency peak from the power spectrum waveform obtained by performing frequency analysis, and extracts a respiratory component. Note that the interval analysis unit 302 notifies the awakening effort analysis unit 305 of the extracted blood pressure component. In addition, the interval analysis unit 302 notifies the sleepiness level calculation unit 304 of the extracted respiratory component.

  The amplitude analysis unit 303 extracts the pulse amplitude of the driver 160 at each time from the acquired pulse wave signal, thereby calculating the time change of the pulse amplitude, and performs frequency analysis on the time change of the calculated pulse amplitude. In addition, the amplitude analysis unit 303 detects a low frequency peak from the power spectrum waveform obtained by performing frequency analysis, and extracts a blood pressure component. Furthermore, the amplitude analysis unit 303 detects a high frequency peak from the power spectrum waveform obtained by performing the frequency analysis, and extracts a respiratory component. The amplitude analyzing unit 303 notifies the extracted blood pressure component to the arousal effort analyzing unit 305 and the arousal level analyzing unit 306.

  The sleepiness level calculation unit 304 calculates the sleepiness level based on the respiratory component received from the interval analysis unit 302. Note that the sleepiness level calculation unit 304 has a sleepiness level calculation table for calculating the sleepiness level of the driver 160. The sleepiness level calculation unit 304 calculates the sleepiness level by referring to the sleepiness level calculation table. In addition, when the sleepiness level calculation unit 304 determines that the calculated sleepiness level is equal to or greater than a predetermined threshold, the sleepiness level calculation unit 304 notifies the alarm unit 122 of the determination result.

  The awakening effort analysis unit 305 determines the degree of active activity of the driver 160 based on the deviation of the magnitude of the difference between the blood pressure component received from the interval analysis unit 302 and the blood pressure component received from the amplitude analysis unit 303.

  It is assumed that the awakening effort analysis unit 305 has an active activity determination table for determining the degree of active activity of the driver 160. The awakening effort analysis unit 305 determines the degree of active activity of the driver 160 by referring to the active activity determination table.

  In addition, when it is determined that the degree of active activity of the driver 160 corresponds to a predetermined condition (“wakeful effort”), the wakefulness effort analyzing unit 305 notifies the wakefulness effort state determining unit 307 of the determination result.

  The arousal level analysis unit 306 analyzes whether or not the fluctuation of the peak value of the power spectrum waveform included in the blood pressure component received from the amplitude analysis unit 303 is an extremely long period, thereby determining whether or not the fluctuation tends to increase. judge.

  In addition, when the arousal level analysis unit 306 determines that the amount of deviation from the reference value of the peak value of the power spectrum waveform included in the blood pressure component received from the amplitude analysis unit 303 is equal to or greater than a predetermined threshold value, The time at which the corresponding pulse wave signal is detected is extracted as a singular point. In addition, the arousal level analysis unit 306 determines whether or not the appearance frequency of singular points in a range retroactive from the present time is equal to or greater than a predetermined threshold value.

  Furthermore, when the arousal level analysis unit 306 determines that the fluctuation of the ultra-long cycle tends to increase and determines that the appearance frequency of the singularity is equal to or higher than a predetermined threshold, the arousal level of the driver 160 is low. And the determination result is notified to the awakening effort state determination unit 307.

  The awakening effort state determination unit 307 determines whether or not the driver 160 is in an awakening effort state. The driver 160 being in the “wakefulness effort state” refers to a state in which the driver 160 resists drowsiness. The awakening effort state determination unit 307 determines that the driver 160 is in the awakening effort state when the determination result is received from the awakening effort analysis unit 305 and the determination result is received from the awakening level analysis unit 306.

  Note that the determination result received by the wakefulness effort state determination unit 307 from the wakefulness effort analysis unit 305 is a determination result indicating that the degree of active activity of the driver 160 corresponds to “wakefulness effort”. The determination result received by the arousal effort state determination unit 307 from the arousal level analysis unit 306 is a determination result indicating that the driver 160 has a low arousal level.

  If the driver 160 determines that the driver 160 is in the wake effort state, the wake effort state determination unit 307 notifies the warning unit 122 of the determination result.

  When the alarm unit 122 receives the determination result from the drowsiness level calculation unit 304 (that is, when it is determined that the drowsiness level is equal to or higher than a predetermined threshold), the alarm unit 122 outputs a predetermined alarm information to the speaker device 130 by voice. . Alternatively, the alarm unit 122 displays and outputs predetermined alarm information on the display device 140.

  Further, even when the warning unit 122 receives the determination result from the wakefulness effort state determination unit 307 (that is, when it is determined that the state is the wakefulness effort state), the alarm information defined in advance in the speaker device 130 is displayed. Is output as audio. Alternatively, the alarm unit 122 displays and outputs predetermined alarm information on the display device 140.

  As described above, in the drowsiness determination system 100 according to the first embodiment, in addition to determining that the drowsiness level of the driver 160 is equal to or higher than the predetermined threshold, the driver 160 identifies that the driver 160 is in the awakening effort state. If the sleepiness determination system 100 in the first embodiment is identified as being in an awakening effort state, a process for improving the awakening effort state to the awakening state is performed. For this reason, although the driver 160 is in the awakening effort state, it is erroneously determined that the driver 160 is in the awakening state because the sleepiness level is low, and the vehicle 150 is not improved from the awakening effort state to the awakening state. It is possible to avoid a situation in which the driving of the vehicle is continued.

  Next, further detailed functions of each unit included in the drowsiness determination unit 121 will be described with reference to FIGS. First, details of the function of the interval analysis unit 302 included in the sleepiness determination unit 121 will be described. FIG. 4 is a diagram for explaining the function of the interval analysis unit.

  As shown in FIG. 4A, the interval analysis unit 302 includes a first peak value detection unit 401, an interval calculation unit 402, a first frequency analysis unit 403, a first respiratory component extraction unit 404, a first Blood pressure component extraction unit 405.

  The first peak value detection unit 401 detects the peak of the pulse wave signal acquired by the pulse wave signal acquisition unit 301. A graph 410 in FIG. 4B is a graph in which the horizontal axis represents time and the vertical axis represents the pulse wave signal value. When the pulse wave signal shown in the graph 410 is acquired, the first peak value detection unit 401 extracts peaks (420 to 431).

The interval calculation unit 402 calculates the interval (pulse interval) of each peak detected by the first peak value detection unit 401. If the pulse wave signals shown in graph 410, time the peak 420 to peak 431 is _{detected, respectively,} is t 0 _{~t 11.} Therefore, the interval calculation unit 402 calculates pulse intervals T _{0 to} T ₁₀ by calculating a difference between each time. Note that a table 440 in FIG. 4B is a table showing the pulse intervals calculated by the interval calculation unit 402 at each time. Furthermore, a graph 450 in FIG. 4B is a graph showing the time change of the pulse interval by plotting Table 440 with time on the horizontal axis and pulse interval on the vertical axis.

  The first frequency analysis unit 403 performs frequency analysis of the time change of the pulse interval calculated by the interval calculation unit 402 with a predetermined time width, and calculates a power spectral density (PSD). The graph 460 in FIG. 4B is obtained by the frequency analysis of the time change (see graph 450) of the pulse interval calculated by the interval calculation unit 402 in the range of the time width 451 by the first frequency analysis unit 403. The obtained power spectrum waveform is shown.

In the graph 460, the horizontal axis represents frequency, and the vertical axis represents power spectral density. As shown in the graph 460, when the time change of the pulse interval (graph 450) is frequency-analyzed, power spectral density peaks (peak values = P ₁ and P ₂ ) appear at two locations on the low frequency side and the high frequency side.

Among these, the peak frequency (F ₁ ) appearing on the low frequency side is referred to as “blood pressure modulation frequency”. The combination (P ₁ , F ₁ ) of the peak value (P ₁ ) and the blood pressure modulation frequency (F ₁ ) is referred to as “first blood pressure component”.

Further, the peak frequency (F ₂ ) appearing on the high frequency side is referred to as “breathing motion modulation frequency”. A combination (P ₂ , F ₂ ) of the peak value (P ₂ ) and the respiratory motion modulation frequency (F ₂ ) is referred to as a “first respiratory component”.

The first respiratory component extraction unit 404 extracts the first respiratory component based on the result of frequency analysis by the first frequency analysis unit 403. The graph 460 shows the first respiratory component (P ₂₎ based on the result of frequency analysis performed by the first respiratory component extraction unit 404 in the range of the time width 451 with time = t ₁ as the end time. , F ₂ ) are extracted.

  The first respiratory component extraction unit 404 notifies the sleepiness level calculation unit 304 of the extracted first respiratory component.

The first blood pressure component extraction unit 405 extracts the first blood pressure component based on the result of the frequency analysis by the first frequency analysis unit 403. The graph 460 shows the first blood pressure component (P ₁₎ based on the result of the frequency analysis performed by the first blood pressure component extraction unit 405 in the range of the time width 451 with time = t ₁ as the end time. , F ₁ ) are extracted.

  Note that the first blood pressure component extraction unit 405 notifies the extracted first blood pressure component to the awakening effort analysis unit 305.

  Next, the function of the amplitude analysis unit 303 included in the sleepiness determination unit 121 will be described. FIG. 5 is a diagram for explaining the function of the amplitude analyzer.

  As shown in FIG. 5A, the amplitude analysis unit 303 includes a second peak value detection unit 501, an amplitude calculation unit 502, a second frequency analysis unit 503, a second respiratory component extraction unit 504, a second Blood pressure component extraction unit 505.

  The second peak value detection unit 501 detects the peak of the pulse wave signal acquired by the pulse wave signal acquisition unit 301. A graph 510 in FIG. 5B is a graph in which the horizontal axis represents time and the vertical axis represents the pulse wave signal value. When the pulse wave signal shown in the graph 510 is acquired, the second peak value detection unit 501 extracts peaks (420_1 to 431_1, 420_2 to 431_2).

The amplitude calculator 502 calculates an amplitude (pulse amplitude) based on each peak detected by the second peak value detector 501. In the case of the pulse wave signal shown in the graph 510, the amplitude calculator 502 uses the pulse amplitude A ₀ to P as the pulse amplitude corresponding to the times t _{0 to} t ₁₁ based on the peaks 420_1 to 431_1 and the peaks 420_2 to 431_2, respectively. to calculate the a _11. Note that a table 530 in FIG. 5B is a table in which the amplitude calculation unit 502 indicates the pulse amplitude corresponding to each time. Further, a graph 540 in FIG. 5B is a graph showing a time change of the pulse amplitude by plotting Table 530 with time on the horizontal axis and pulse amplitude on the vertical axis.

  The second frequency analysis unit 503 performs frequency analysis on the time variation of the pulse amplitude calculated by the amplitude calculation unit 502 with a predetermined time width, and calculates a power spectral density. A graph 550 in FIG. 5B is a result of the second frequency analysis unit 503 performing frequency analysis on the time variation of the pulse amplitude calculated by the amplitude calculation unit 502 (see the graph 540) in the range of the time width 541. The obtained power spectrum waveform is shown.

In the graph 550, the horizontal axis represents frequency, and the vertical axis represents power spectral density. As shown in the graph 550, when the time change of the pulse amplitude (graph 540) is frequency-analyzed, power spectral density peaks (peak values = p ₁ and p ₂ ) appear at two locations on the low frequency side and the high frequency side.

Among these, the peak frequency (f ₁ ) appearing on the low frequency side is referred to as “blood pressure modulation frequency”. A combination (p ₁ , f ₁ ) of the peak value (p ₁ ) and the blood pressure modulation frequency (f ₁ ) is referred to as a “second blood pressure component”.

Further, the peak frequency (f ₂ ) appearing on the high frequency side is referred to as “breathing motion modulation frequency”. A combination (p ₂ , f ₂ ) of the peak value (p ₂ ) and the respiratory motion modulation frequency (f ₂ ) is referred to as a “second respiratory component”.

The second respiratory component extraction unit 504 extracts a second respiratory component based on the result of frequency analysis by the second frequency analysis unit 503. The graph 550 shows the second respiratory component (p ₂₎ based on the result of frequency analysis performed by the second respiratory component extraction unit 504 in the range of the time width 541 with time = t ₁ as the end time. , F ₂ ) are extracted.

The second blood pressure component extraction unit 505 extracts the second blood pressure component based on the result of the frequency analysis by the second frequency analysis unit 503. The graph 550 shows the second blood pressure component (p ₁₎ based on the result of the frequency analysis performed by the second blood pressure component extraction unit 505 in the range of the time width 541 with time = t ₁ as the end time. , F ₁ ) are extracted.

  Note that the second blood pressure component extraction unit 505 notifies the extracted second blood pressure component to the wakefulness effort analysis unit 305 and the wakefulness level analysis unit 306.

  Next, the function of the sleepiness level calculation unit 304 included in the sleepiness determination unit 121 will be described. FIG. 6 is a diagram for explaining the function of the sleepiness level calculation unit.

  As illustrated in FIG. 6A, the sleepiness level calculation unit 304 includes a first respiratory component acquisition unit 601, an abnormal value removal unit 602, and a conversion unit 603.

The first respiratory component acquisition unit 601 acquires the first respiratory component (P ₂ , F ₂ ) extracted by the first respiratory component extraction unit 404 of the interval analysis unit 302. FIG. 6B shows that the first respiratory component acquisition unit 601 converts the first respiratory component extracted by the first respiratory component extraction unit 404 to each time (t ₁ , t ₂ , t ₃ ,..., T _n ).

  The abnormal value removing unit 602 removes an abnormal value from the first respiratory component acquired by the first respiratory component acquisition unit 601 in association with each time. The abnormal value removing unit 602 removes the first respiratory component determined to be an abnormal value by the awakening effort analyzing unit 305 described later from the first respiratory component acquired in association with each time.

  The conversion unit 603 calculates the sleepiness level for the first respiratory component that has not been removed by the abnormal value removing unit 602 among the first respiratory components acquired by the first respiratory component acquisition unit 601.

Note that the conversion unit 603 has a sleepiness level calculation table in which the sleepiness level is associated with the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ). FIG. 6C is a graph showing a sleepiness level calculation table in which the sleepiness level is associated with the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ).

As shown in FIG. 6C, the sleepiness level calculation table is defined so that the sleepiness level becomes smaller as the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ) are larger (going to the upper right). Yes. In addition, the sleepiness level calculation table is defined such that the sleepiness level increases as the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ) are smaller (lower left).

The conversion unit 603 refers to the sleepiness level calculation table to calculate the sleepiness level based on the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ) included in the first respiratory component.

In the example of FIG. 6C, the sleepiness degree calculation table is graphed, and each time (t ₁ , t ₂ , t ₃ ,...) Acquired by the first respiratory component acquisition unit 601 is further obtained. A state in which the first respiratory component corresponding to t _n ) is plotted is shown. In the example of FIG. 6C, since the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ) are large at time = t _{1 to} t ₃ , the conversion unit 603 calculates the sleepiness level as “1”. is doing. In addition, with the passage of time, the respiratory motion modulation frequency (F ₂ ) and the peak value (P ₂ ) decrease, and at time = t _n , the conversion unit 603 calculates the sleepiness level as “4”. .

  When the sleepiness degree is calculated by referring to the sleepiness degree calculation table, the conversion unit 603 further determines whether or not the calculated sleepiness degree is equal to or greater than a predetermined threshold (for example, 4). When the conversion unit 603 determines that the calculated sleepiness level is equal to or greater than a predetermined threshold, the conversion unit 603 notifies the alarm unit 122 of the determination result.

  Next, the function of the wakefulness effort analysis unit 305 included in the drowsiness determination unit 121 will be described. FIG. 7 is a diagram for explaining the function of the awakening effort analysis unit.

  As shown in FIG. 7A, the wakefulness effort analysis unit 305 includes a first blood pressure component acquisition unit 701, a second blood pressure component acquisition unit 702, a blood pressure component analysis unit 703, an active activity determination unit 704, An abnormal value determination unit 705 is included.

The first blood pressure component acquisition unit 701 acquires the first blood pressure component (F ₁ , P ₁ ) extracted by the first blood pressure component extraction unit 405 of the interval analysis unit 302.

The second blood pressure component acquisition unit 702 acquires the second blood pressure component (f ₁ , p ₁ ) extracted by the second blood pressure component extraction unit 505 of the amplitude analysis unit 303.

The blood pressure component analysis unit 703 includes first and second blood pressure components (F ₁ , P ₁ ) and (f ₁ , p ₁ ) acquired by the first and second blood pressure component acquisition units 701 and 702, respectively. ), The deviation of the magnitude of the deviation is calculated using the following equation.

  A graph 710 in FIG. 7B is a graph for explaining the deviation of the magnitude of the deviation, the horizontal axis represents the frequency, and the vertical axis represents the power spectral density. A graph 710 shows a power spectrum waveform (see graph 460 in FIG. 4) obtained by frequency analysis of the time change of the pulse interval, and a power spectrum waveform (FIG. 4) obtained by frequency analysis of the time change of the pulse amplitude. 5 (see graph 550 in FIG. 5). In the graph 710 of FIG. 7B, the deviation of the magnitude of the deviation corresponds to the deviation of the magnitude of the arrow 711.

  The active activity determination unit 704 determines the degree of active activity of the driver 160 based on the deviation of the magnitude of the deviation calculated by the blood pressure component analysis unit 703. Note that the active activity determination unit 704 has an active activity determination table. The active activity determination unit 704 determines the degree of active activity of the driver 160 by referring to the active activity determination table.

  A graph 720 in FIG. 7B is a graph of the active activity determination table. As shown in the graph 720, the degree of active activity includes “monotone”, “low tone”, “wakefulness effort”, “fighting”, and “strangeness”.

When both the deviation of the blood pressure modulation frequency (| f ₁ −F ₁ |) and the deviation of the peak value difference (| p ₁ −P ₁ |) are small (the deviation of the deviation is 0.5σ or less) ), The active activity determination unit 704 determines that the level of the driver's active activity is “monotonic”. Thereafter, as the deviation between the difference in blood pressure modulation frequency (| f ₁ −F ₁ |) and the difference between the peak values (| p ₁ −P ₁ |) increases, the active activity determination unit 704 determines the degree of active activity. Are determined as “low tone”, “awakening effort”, “fighting”, and “turbulence”, respectively.

  When the active activity determination unit 704 determines that the degree of active activity corresponds to a predetermined condition (“wakefulness effort”) based on the deviation of the magnitude of deviation (the magnitude deviation of the arrow 711), the determination result is obtained. The alerting state determination unit 307 is notified.

The abnormal value determination unit 705 determines whether or not the deviation of the deviation calculated by the blood pressure component analysis unit 703 (the deviation of the magnitude of the arrow 711) is equal to or greater than a predetermined threshold value. When the abnormal value determination unit 705 determines that the deviation of the deviation (the deviation of the magnitude of the arrow 711) is equal to or greater than a predetermined threshold, the first respiratory component (F ₂ , P ₂ ) at this time Is determined to be an abnormal value, and the sleepiness degree calculation unit 304 is notified. In this case, the conversion unit 603 of the sleepiness level calculation unit 304 does not calculate the sleepiness level based on the first respiratory component (F ₂ , P ₂ ) at this time (that is, the sleepiness level is not updated).

  Next, the function of the arousal level analysis unit 306 included in the sleepiness determination unit 121 will be described. FIG. 8 is a diagram for explaining the function of the arousal level analysis unit.

  As shown in FIG. 8A, the wakefulness level analysis unit 306 includes an ultralong period analysis unit 801, a singular signal analysis unit 802, and a wakefulness level determination unit 803.

The ultra-long cycle analysis unit 801 acquires the second blood pressure component (f ₁ , p ₁ ) extracted by the second blood pressure component extraction unit 505 of the amplitude analysis unit 303. In addition, the super long period analysis unit 801 determines whether or not the peak value (p ₁ ) included in the acquired second blood pressure component (f ₁ , p ₁ ) tends to increase in the super long period. . When it is determined that there is an increasing tendency in the ultra-long cycle, the determination result is notified to the awakening level determination unit 803.

A graph 810 in FIG. 8B is a graph showing a time change of the peak value (p ₁ ) included in the second blood pressure component (f ₁ , p ₁ ). In the graph 810, the horizontal axis represents time, and the vertical axis represents power spectral density. The ultra-long cycle analysis unit 801 obtains an analysis result (a variation in the ultra-long cycle) 811 by analyzing the graph 810 with an ultra-long cycle. Based on the analysis result 811, the ultralong cycle analysis unit 801 determines whether or not the peak value (p ₁ ) included in the second blood pressure component (f ₁ , p ₁ ) tends to increase in the ultralong cycle. Determine.

The singular signal analysis unit 802 acquires the second blood pressure component (f ₁ , p ₁ ) extracted by the second blood pressure component extraction unit 505 of the amplitude analysis unit 303. Further, the singular signal analysis unit 802 calculates a deviation amount from the reference value of the peak value (p ₁ ) included in the acquired second blood pressure component (f ₁ , p ₁ ). The singular signal analysis unit 802 calculates the minimum peak value (min (p ₁ )) among the peak values (p ₁ ) included in the second blood pressure component (f ₁ , p ₁ ) acquired so far. Used as a reference value.

  If the singular signal analysis unit 802 determines that the amount of deviation from the calculated reference value is greater than or equal to a predetermined threshold, the singular signal analysis unit 802 determines that the corresponding pulse wave signal is a singular signal. Also, the singular signal analysis unit 802 determines the time when the corresponding pulse wave signal is detected as a singular point. Further, the singular signal analysis unit 802 calculates the appearance frequency of the singular point in a range that goes back for a predetermined period from the present time, and when determining that the appearance frequency is equal to or higher than a predetermined threshold, notifies the awakening level determination unit 803 of the determination result. To do.

FIG. 8C shows the amount of deviation of the peak value (p ₁ ) included in the second blood pressure component (f ₁ , p ₁ ) from the minimum peak value (min (p ₁ )) at each time. (See arrows 820_3, 820_n, etc.) is calculated. If the singular signal analysis unit 802 determines that the calculated deviation amount (see arrows 820_3, 820_n, etc.) is equal to or greater than a predetermined threshold value, the singular signal analysis unit 802 determines that the corresponding pulse wave signal is a singular signal and the corresponding pulse wave The time when the signal is detected is determined as a singular point. In FIG. 8B, arrows 821 to 824 indicate times determined as singular points by the singular signal analysis unit 802. When the singular points in the range retroactive from the present time are the arrow 823 and the arrow 824, the singular signal analysis unit 802 determines whether the appearance frequency of the two singular points is equal to or higher than a predetermined threshold. judge. If the singular signal analysis unit 802 determines that the appearance frequency of the two singular points is equal to or higher than a predetermined threshold, the singular signal analysis unit 802 notifies the awakening level determination unit 803 of the determination result.

  The arousal level determination unit 803 determines the determination result notified from the ultralong cycle analysis unit 801 (the peak value of the blood pressure component tends to increase in the ultralong cycle) and the determination result notified from the singular signal analysis unit 802 ( The appearance frequency of the singular point is equal to or higher than a predetermined threshold).

  The awakening level determination unit 803 determines that the awakening level of the driver 160 is low when the determination result is acquired from the ultralong period analysis unit 801 and the determination result is acquired from the singular signal analysis unit 802. When it is determined that the awakening level of the driver 160 is low, the awakening level determination unit 803 notifies the determination result to the awakening effort state determination unit 307.

  Next, the function of the awakening effort state determination unit 307 included in the sleepiness determination unit 121 will be described. FIG. 9 is a diagram for explaining the function of the awakening effort state determination unit 307.

  As illustrated in FIG. 9, the arousal effort state determination unit 307 includes an active activity determination result acquisition unit 901, a wakefulness level determination result acquisition unit 902, and a determination unit 903.

  The active activity determination result acquisition unit 901 acquires a determination result (determination result that the degree of active activity of the driver 160 corresponds to “wakeful effort”) from the active activity determination unit 704 of the awakening effort analysis unit 305. When the active activity determination result acquisition unit 901 acquires the determination result, the active activity determination result acquisition unit 901 notifies the determination unit 903.

  The arousal level determination result acquisition unit 902 acquires a determination result (a determination result indicating that the driver 160 has a low arousal level) from the arousal level determination unit 803 of the arousal level analysis unit 306. The awakening level determination result acquisition unit 902 notifies the determination unit 903 when the determination result is acquired.

  If there is a notification from the active activity determination result acquisition unit 901 and a notification from the wakefulness level determination result acquisition unit 902, the determination unit 903 determines that the state of the driver 160 is an awakening effort state. If the determination unit 903 determines that the state is an awakening effort state, the determination unit 903 notifies the alarm unit 122 of the determination result.

  Next, the flow of sleepiness determination processing in the sleepiness determination system 100 will be described. FIG. 10 is a flowchart of sleepiness determination processing.

  In the flowchart shown in FIG. 10, the process starts when the driver 160 wears the pulse sensor 110 on the earlobe while the vehicle 150 is IG-ON. In step S <b> 1001, the pulse wave signal acquisition unit 301 acquires a pulse wave signal from the pulse sensor 110.

  In step S1002, the interval analysis unit 302 extracts the first respiratory component and the first blood pressure component by analyzing the pulse wave signal acquired by the pulse wave signal acquisition unit 301.

  In step S1003, the amplitude analysis unit 303 extracts the second respiratory component and the second blood pressure component by analyzing the pulse wave signal acquired by the pulse wave signal acquisition unit 301.

  In step S1004, the sleepiness level calculation unit 304 executes sleepiness level calculation processing for calculating the sleepiness level based on the first respiratory component. Details of the flowchart of the sleepiness level calculation process will be described later.

  In step S1005, the wakefulness effort analysis unit 305, the wakefulness level analysis unit 306, and the wakefulness effort state determination unit 307 perform wakefulness effort state determination processing based on the first blood pressure component and the second blood pressure component. The details of the flowchart of the awakening effort state determination process will be described later.

  In step S1006, the warning unit 122 determines whether or not the determination result is notified from the sleepiness level calculation unit 304 in step S1004 (whether or not the sleepiness level of the driver 160 is equal to or greater than a predetermined threshold).

  If it is determined in step S1006 that the determination result is notified from the sleepiness level calculation unit 304 (the sleepiness level of the driver 160 is equal to or greater than a predetermined threshold), the process proceeds to step S1008. In step S1008, the warning unit 122 outputs or displays warning information to the driver 160 as a sound, and the process proceeds to step S1009.

  On the other hand, when it is determined in step S1006 that the determination result is not notified from the sleepiness level calculation unit 304 (the sleepiness level of the driver 160 is less than a predetermined threshold value), the process proceeds to step S1007. In step S1007, the warning unit 122 determines whether or not the determination result is notified from the awakening effort state determination unit 307 in step S1005 (whether or not the state of the driver 160 is the awakening effort state).

  In step S1007, when it is determined that the determination result is notified from the awakening effort state determination unit 307 (the state of the driver 160 is the awakening effort state), the process proceeds to step S1008, and the warning information is output by voice or display. After that, the process proceeds to step S1009. As described above, in the sleepiness determination process according to the first embodiment, even when it is determined that the sleepiness level is less than the predetermined threshold, if it is determined that the state of the driver 160 is the awakening effort state, an alarm output is performed. I do.

  On the other hand, if it is determined in step S1007 that the determination result is not notified from the awakening effort state determination unit 307 (the state of the driver 160 is not the awakening effort state), the process proceeds to step S1009.

  In step S1009, the pulse wave signal acquisition unit 301 determines whether to end the drowsiness determination process. If it is determined to continue the drowsiness determination process, the process returns to step S1001. On the other hand, if it is determined in step S1009 that the drowsiness determination process is to be terminated, the drowsiness determination process is terminated.

  Next, a flowchart of details of each process included in the drowsiness determination process of FIG. 10 (drowsiness level calculation process (step S1004), arousal effort state determination process (step S1005)) will be described.

  FIG. 11 is a flowchart showing details of the sleepiness level calculation process. In step S1101, the first respiratory component acquisition unit 601 acquires a first respiratory component. In step S1102, the abnormal value removing unit 602 determines whether or not the acquired first respiratory component is an abnormal value.

  When the arousal effort state determination process (step S1005) is executed and the determination result that the first respiratory component is an abnormal value is received from the arousal effort analysis unit 305, in step S1102, the abnormal value removal unit 602 is received. Determines that the acquired first respiratory component is an abnormal value. If the abnormal value removing unit 602 determines in step S1002 that the acquired first respiratory component is an abnormal value, the process returns to step S1006 in FIG.

  On the other hand, if the determination result that the second respiratory component is an abnormal value is not received from the wakefulness effort analysis unit 305 in step S1102, it is determined that the acquired second respiratory component is not an abnormal value. Then, the process proceeds to step S1103. In step S1103, the conversion unit 603 calculates the sleepiness level by referring to the sleepiness level calculation table using the first respiratory component acquired in step S1101.

  In step S1104, the conversion unit 603 determines whether the calculated sleepiness level is equal to or greater than a predetermined threshold. If it is determined in step S1104 that it is less than the predetermined threshold, the process returns to step S1006 in FIG. On the other hand, if it is determined in step S1104 that the threshold is equal to or greater than the predetermined threshold value, the process proceeds to step S1105.

  In step S1105, the conversion unit 603 notifies the alarm unit 122 of a determination result indicating that the drowsiness level of the driver 160 is equal to or greater than a predetermined threshold.

  FIG. 12 is a flowchart showing details of the arousal effort state determination process. In step S1201, the wakefulness effort analysis unit 305 acquires a first blood pressure component and a second blood pressure component.

  In step S1202, the wakefulness effort analysis unit 305 calculates a deviation of the magnitude of the difference between the acquired first blood pressure component and the second blood pressure component, and determines the degree of active activity. The awakening effort analysis unit 305 determines whether or not the first respiratory component is an abnormal value based on the calculated deviation of the magnitude of the deviation. To the sleepiness level calculation unit 304.

  In step S1203, the wakefulness effort analysis unit 305 determines whether or not the determined degree of active activity corresponds to “wakefulness effort”. If it is determined in step S1203 that the determined level of active activity does not correspond to “wakefulness effort”, the process returns to step S1006 in FIG.

  On the other hand, if it is determined in step S1203 that the determined degree of active activity corresponds to “wakefulness effort”, the determination result is notified to the alertness state determination unit 307, and the process proceeds to step S1204. In step S1204, the arousal level analysis unit 306 analyzes the fluctuation of the ultralong cycle of the peak value of the second blood pressure component.

  In step S1205, the arousal level analysis unit 306 determines whether or not the fluctuation of the ultralong cycle of the peak value of the second blood pressure component analyzed in step S1204 is increasing. If it is determined in step S1205 that the change in the ultra-long cycle does not tend to increase, the process returns to step S1006 in FIG.

  On the other hand, if it is determined in step S1205 that the fluctuation of the ultra-long cycle tends to increase, the process proceeds to step S1206. In step S1206, the arousal level analysis unit 306 determines whether or not the corresponding pulse wave signal is a singular signal based on the amount of deviation from the reference value of the peak value of the second blood pressure component. When it is determined that the signal is a singular signal, the arousal level analysis unit 306 determines that the time when the corresponding pulse wave signal is detected is a singular point. In step S1207, the arousal level analysis unit 306 analyzes the frequency of appearance of singular points in a range that is traced back for a predetermined period from the current time.

  In step S1208, the arousal level analysis unit 306 determines whether or not the appearance frequency of singular points is equal to or higher than a predetermined threshold. If it is determined in step S1208 that it is less than the predetermined threshold, the process returns to step S1006 in FIG.

  On the other hand, if it is determined in step S1208 that it is equal to or greater than the predetermined threshold, the determination result is notified to the awakening effort state determination unit 307, and the process proceeds to step S1209. In step S1209, the wakefulness effort state determination unit 307 determines that the current state of the driver 160 is the wakefulness effort state, notifies the determination result to the warning unit 122, and then returns to step S1006 in FIG.

  As is clear from the above description, in the sleepiness determination system according to the first embodiment, the frequency change of the time change of the pulse interval is analyzed, and the respiratory component of the power spectrum waveform is extracted to calculate the sleepiness level of the driver. . In the sleepiness determination system according to the first embodiment, the difference between the blood pressure component extracted by the frequency analysis of the time change of the pulse interval and the blood pressure component extracted by the frequency analysis of the time change of the pulse amplitude is large. Based on the deviation, the degree of active activity of the driver is determined. Further, in the sleepiness determination system according to the first embodiment, the driver is based on the fluctuation of the ultralong period of the peak value of the blood pressure component extracted by the frequency analysis of the time change of the pulse amplitude and the appearance frequency of the singular point. Determine the level of arousal. In the sleepiness determination system according to the first embodiment, when the driver's active activity level corresponds to “wakefulness effort” and it is determined that the level of alertness is low, the driver's state is awakening effort state. judge. Furthermore, in the sleepiness determination system according to the first embodiment, when the calculated sleepiness level is high, an alarm is output, and even when the calculated sleepiness level is low, it is determined that the driver's state is the awakening effort state In the case of alarm output.

  Thus, according to the drowsiness determination system in the first embodiment, it is possible to identify that the state of the driver is the awakening effort state. For this reason, even when it is determined that the sleepiness level is low, it is possible to correctly determine the state of drowsiness and output an alarm.

  As a result, according to the drowsiness determination system in the first embodiment, the determination accuracy for determining drowsiness can be improved.

[Second Embodiment]
In the first embodiment, the case where the navigation device 120 is caused to function as the drowsiness determination unit 121 and the alarm unit 122 has been described. However, the device for realizing the drowsiness determination unit 121 and the alarm unit 122 is not limited to the navigation device 120. For example, the server device may function as the drowsiness determination unit 121.

  FIG. 13 is a second diagram illustrating an example of a drowsiness determination system. Hereinafter, the drowsiness determination system 1300 illustrated in FIG. 13 will be described focusing on differences from the first embodiment.

  As shown in FIG. 13, the sleepiness determination system 1300 is different from the sleepiness determination system 100 of FIG. 1 in that it includes a server device 1310 and a communication device 1320.

  The communication device 1320 is, for example, a DCM (Data Communication Module), is mounted on the vehicle 150, and communicates with the server device 1310 that manages the vehicle 150.

  The server device 1310 has a sleepiness determination program installed therein, and the server device 1310 functions as the sleepiness determination unit 121 by executing the program.

  According to the sleepiness determination system 1300, the pulse wave signal detected by the driver 160 is transmitted to the server device 1310 via the navigation device 120 and the communication device 1320. Further, when a determination result indicating that the sleepiness level is high is transmitted from the server device 1310 based on the transmitted pulse wave signal, or when a determination result indicating that the state is an awakening effort state is transmitted, the navigation device 120 receives these determination results via the communication device 1320. As a result, the navigation device 120 can output an alarm via the speaker device 130 or the display device 140.

[Third Embodiment]
In the first embodiment, the case where the navigation device 120 is caused to function as the drowsiness determination unit 121 and the alarm unit 122 has been described. However, the device for realizing the drowsiness determination unit 121 and the alarm unit 122 is not limited to the navigation device 120. For example, a portable terminal possessed by the driver 160 may function as the drowsiness determination unit 121.

  FIG. 14 is a third diagram illustrating an example of a drowsiness determination system. Hereinafter, the drowsiness determination system 1400 or 1420 illustrated in FIG. 14 will be described focusing on differences from the first embodiment.

  As shown in FIG. 14A, the sleepiness determination system 1400 is different from the sleepiness determination system 100 of FIG.

  The portable terminal 1410 is a terminal possessed by the driver 160 and acquires a pulse wave signal by connecting to the pulse sensor 110. In addition, the sleepiness determination program is installed in the mobile terminal 1410. Thereby, the mobile terminal 1410 functions as the drowsiness determination unit 121.

  In addition, the mobile terminal 1410 transmits and receives information to and from the navigation device 120 by, for example, near field communication. The portable terminal 1410 transmits a determination result to the navigation device 120 when the sleepiness determination unit 121 determines that the sleepiness level is high or when it is determined that the sleepiness state is awakening effort. As a result, the navigation device 120 can output an alarm via the speaker device 130 or the display device 140.

  Note that the output destination of the alarm information is not limited to the speaker device 130 or the display device 140 connected to the navigation device 120. For example, you may utilize the speaker function and display function which a portable terminal has.

  FIG. 14B illustrates an example of the sleepiness determination system 1420 that causes the mobile terminal 1430 to function as the drowsiness determination unit 121 and the alarm unit 122 and outputs alarm information using the speaker function and the display function of the mobile terminal 1430. . According to the sleepiness determination system 1420, the sleepiness determination process can be executed in any vehicle that can be driven by the driver.

[Other Embodiments]
In the first to third embodiments, the wakefulness effort state determination unit 307 determines that the degree of active activity of the driver 160 corresponds to “wakefulness effort” and determines that the wakefulness level of the driver 160 is low. In this case, it is determined that the state of the driver 160 is an awakening effort state. However, the wakefulness effort state determination unit 307 determines whether the active activity level of the driver 160 corresponds to “wakefulness effort” or when it is determined that the wakefulness level of the driver 160 is low. It may be determined that the state is an awakening effort state.

  In the first to third embodiments, the wakefulness level determination unit 803 has a tendency that the fluctuation of the ultralong cycle of the peak value of the second blood pressure component tends to increase and the appearance frequency of the singularity is predetermined. When it is determined that the value is equal to or greater than the threshold value, it is determined that the awakening level of the driver 160 is low. However, the arousal level determination unit 803 determines that the fluctuation of the ultralong cycle of the peak value of the second blood pressure component tends to increase, or the appearance frequency of the singularity is equal to or higher than a predetermined threshold. In any case of the determination, it may be determined that the arousal level is low.

  In the first to third embodiments, the interval analysis unit 302 and the amplitude analysis unit 303 have been described as using the pulse wave signal acquired by the pulse wave signal acquisition unit 301. However, the interval analysis unit 302 and the amplitude analysis unit 303 may use the pulse wave signal acquired by the pulse wave signal acquisition unit 301 after removing abnormal values.

  In the first to third embodiments, the wakefulness analysis unit 305 notifies the warning unit 122 of the determination result when it is determined that the active activity level of the driver 160 corresponds to “wakefulness effort”. As explained. However, the awakening effort analysis unit 305 may notify the warning unit 122 of the calculated deviation of the magnitude of the deviation when it is determined that the active activity level of the driver 160 corresponds to “wakefulness effort”. Good. Thereby, the alarm unit 122 can perform processing according to the deviation of the magnitude of the deviation.

  In the first to third embodiments, the alarm unit 122 has been described as outputting alarm information by voice or display. However, the output form of the alarm unit 122 is not limited to this, and for example, a vibrator (not shown) may be vibrated. Or you may make it the alarm part 122 output the signal for switching to an automatic driving | operation.

In addition, in the disclosed technology, forms such as the following supplementary notes are conceivable.
(Appendix 1)
The first blood pressure component is extracted by frequency analysis of the time change of the pulse interval calculated from the pulse wave signal of the subject output from the pulse sensor,
By analyzing the time change of the pulse amplitude calculated from the pulse wave signal, the second blood pressure component is extracted,
Determining whether the subject is in a state of resistance to drowsiness based on a deviation in magnitude of deviation between the first blood pressure component and the second blood pressure component;
A drowsiness determination program that causes a computer to execute processing.
(Appendix 2)
Analyzing the time change of the pulse interval calculated from the pulse wave signal, extracting a respiratory component having a higher frequency than the first blood pressure component,
Calculate sleepiness according to the extracted respiratory component,
When it is determined that the calculated sleepiness level is equal to or greater than a predetermined threshold, an alarm is output.
Causing the computer to perform processing;
Even when it is determined that the calculated sleepiness level is less than a predetermined threshold, if it is determined that the subject is in a state of resistance to sleepiness, an alarm is output. The sleepiness determination program according to appendix 1.
(Appendix 3)
It is determined whether or not the fluctuation of the ultralong cycle of the peak value of the second blood pressure component tends to increase,
Calculating the frequency at which the amount of deviation from the reference value of the peak value of the second blood pressure component is equal to or greater than a predetermined threshold;
Causing the computer to perform processing;
It is determined that the deviation of the magnitude of the difference between the first blood pressure component and the second blood pressure component satisfies a predetermined condition, and the fluctuation of the ultralong cycle of the second blood pressure component tends to increase. The supplementary note 2 is characterized in that, when it is determined that there is a frequency and the frequency is determined to be equal to or greater than a predetermined threshold, the subject is determined to be in a state of resisting sleepiness. Drowsiness determination program.
(Appendix 4)
When it is determined that the deviation of the magnitude of the difference between the first blood pressure component and the second blood pressure component is less than a predetermined threshold, the sleepiness degree corresponding to the extracted respiratory component is calculated. The sleepiness determination program according to appendix 2, characterized in that:
(Appendix 5)
A first extraction means for extracting a first blood pressure component by performing frequency analysis on a time change of a pulse interval calculated from a pulse wave signal of a subject output from a pulse sensor;
A second extraction means for extracting a second blood pressure component by performing frequency analysis on the time variation of the pulse amplitude calculated from the pulse wave signal;
Determining means for determining whether or not the subject is in a state of resistance to drowsiness based on a deviation in magnitude of a deviation between the first blood pressure component and the second blood pressure component. A drowsiness determination device characterized by the above.
(Appendix 6)
Computer
By extracting the time change of the pulse interval from the pulse wave signal of the subject output from the pulse sensor and performing frequency analysis, the first blood pressure component is extracted,
By extracting the time change of the pulse amplitude from the pulse wave signal and performing frequency analysis, the second blood pressure component is extracted,
Determining whether the subject is in a state of resistance to drowsiness based on a deviation in magnitude of deviation between the first blood pressure component and the second blood pressure component;
A drowsiness determination method characterized by executing processing.

  Note that the present invention is not limited to the configurations shown here, such as combinations with other elements, etc., in the configurations described in the above embodiments. These points can be changed without departing from the spirit of the present invention, and can be appropriately determined according to the application form.

100: Sleepiness determination system 110: Pulse sensor 120: Navigation device 121: Sleepiness determination unit 122: Alarm unit 130: Speaker device 140: Display device 150: Vehicle 160: Driver 301: Pulse wave signal acquisition unit 302: Interval analysis unit 303: Amplitude analysis unit 304: Drowsiness level calculation unit 305: Arousal effort analysis unit 306: Arousal level analysis unit 1300: Drowsiness determination system 1310: Server device 1320: Communication device 1400: Drowsiness determination system 1410: Mobile terminal 1420: Drowsiness determination system 1430: Mobile device

Claims (4)

The first blood pressure component is extracted by frequency analysis of the time change of the pulse interval calculated from the pulse wave signal of the subject output from the pulse sensor,
By analyzing the time change of the pulse amplitude calculated from the pulse wave signal, the second blood pressure component is extracted,
Determining whether the subject is in a state of resistance to drowsiness based on a deviation in magnitude of deviation between the first blood pressure component and the second blood pressure component;
A drowsiness determination program that causes a computer to execute processing. Analyzing the time change of the pulse interval calculated from the pulse wave signal, extracting a respiratory component having a higher frequency than the first blood pressure component,
Calculate sleepiness according to the extracted respiratory component,
When it is determined that the calculated sleepiness level is equal to or greater than a predetermined threshold, an alarm is output.
Causing the computer to perform processing;
Even if it is determined that the calculated sleepiness level is less than a predetermined threshold, if it is determined that the subject is in a state of resistance to sleepiness, an alarm is output. The sleepiness determination program according to claim 1. A first extraction means for extracting a first blood pressure component by performing frequency analysis on a time change of a pulse interval calculated from a pulse wave signal of a subject output from a pulse sensor;
A second extraction means for extracting a second blood pressure component by performing frequency analysis on the time variation of the pulse amplitude calculated from the pulse wave signal;
Determining means for determining whether or not the subject is in a state of resistance to drowsiness based on a deviation in magnitude of a deviation between the first blood pressure component and the second blood pressure component. A drowsiness determination device characterized by the above. Computer
The first blood pressure component is extracted by frequency analysis of the time change of the pulse interval calculated from the pulse wave signal of the subject output from the pulse sensor,
By analyzing the time change of the pulse amplitude calculated from the pulse wave signal, the second blood pressure component is extracted,
Determining whether the subject is in a state of resistance to drowsiness based on a deviation in magnitude of deviation between the first blood pressure component and the second blood pressure component;
A drowsiness determination method characterized by executing processing.

Images