JP2015189402A - driver state determination device and driver state determination program - Google Patents
driver state determination device and driver state determination program Download PDFInfo
- Publication number
- JP2015189402A JP2015189402A JP2014069682A JP2014069682A JP2015189402A JP 2015189402 A JP2015189402 A JP 2015189402A JP 2014069682 A JP2014069682 A JP 2014069682A JP 2014069682 A JP2014069682 A JP 2014069682A JP 2015189402 A JP2015189402 A JP 2015189402A
- Authority
- JP
- Japan
- Prior art keywords
- driver
- frequency band
- state determination
- driver state
- predetermined high
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 claims abstract description 42
- 238000001228 spectrum Methods 0.000 claims abstract description 30
- 238000010183 spectrum analysis Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 38
- 230000003595 spectral effect Effects 0.000 claims description 11
- 210000005036 nerve Anatomy 0.000 claims description 8
- 230000002889 sympathetic effect Effects 0.000 claims description 8
- 210000005037 parasympathetic nerve Anatomy 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 6
- 230000001133 acceleration Effects 0.000 description 3
- 230000000881 depressing effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000009499 grossing Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 210000000467 autonomic pathway Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000002792 vascular Effects 0.000 description 1
Abstract
Description
本発明は、ドライバの車両運転時の疲労度又は緊張度などのドライバ状態を判定する技術に関する。 The present invention relates to a technique for determining a driver state such as a fatigue level or a tension level when a driver drives a vehicle.
例えば下記の特許文献1には、非線形解析技術を利用して、ドライバの運転能力の判定を行う技術が開示されている。特許文献1の開示技術によれば、ドライバの運転操作量(例えば、ドライバによるペダル操作やハンドル操作など)、及び、車両の走行状態(例えば、前進/後進の情報)に基づいてドライバの運転特徴量を算出し、当該運転特徴量からリアプノフ指数を算出して、算出されたリアプノフ指数が健常時の指数値を下回った場合にドライバの運転能力が劣化していると判定することが可能である。 For example, Patent Document 1 below discloses a technique for determining the driving ability of a driver using a nonlinear analysis technique. According to the technology disclosed in Patent Document 1, the driving characteristics of the driver based on the driving operation amount of the driver (for example, pedal operation or steering wheel operation by the driver) and the traveling state of the vehicle (for example, forward / reverse information). It is possible to determine that the driver's driving ability has deteriorated when the calculated Lyapunov index is calculated from the driving feature amount and the calculated Lyapunov index falls below the normal index value. .
また、例えば下記の特許文献2には、被験者の脈波の振幅変動のパワースペクトル密度を算出し、当該パワースペクトル密度の低周波領域の積分値LF(Low Frequency)及び高周波領域の積分値HF(High Frequency)を算出して、低周波領域の積分値LFと高周波領域の積分値HFとの比の対数を、血管系の交感神経機能の指標として求める技術が開示されている。また、従来から心拍数変動に基づく心臓の交感神経の機能の指標として高周波領域の積分値HFが用いられ、心臓の副交感神経の機能の指標として低周波領域の積分値LFと高周波領域の積分値HFとの比が用いられていることも開示されている。 Further, for example, in Patent Document 2 below, the power spectrum density of the amplitude fluctuation of the subject's pulse wave is calculated, and the integral value LF (Low Frequency) of the low frequency region and the integral value HF (High Frequency region) of the power spectrum density ( High Frequency) is calculated, and the logarithm of the ratio of the integral value LF in the low frequency region and the integral value HF in the high frequency region is calculated as an index of the sympathetic nerve function of the vascular system. Further, conventionally, an integrated value HF in the high frequency region is used as an index of the function of the heart sympathetic nerve based on heart rate fluctuation, and an integrated value LF in the low frequency region and an integrated value of the high frequency region are used as an index of the function of the heart parasympathetic nerve. It is also disclosed that a ratio with HF is used.
本発明は、従来存在しなかった新たな構成によって、ドライバの車両運転操作によって発生する情報に基づき、ドライバの車両運転時の疲労度又は緊張度などのドライバ状態を判定するドライバ状態判定装置及びドライバ状態判定プログラムを提供することを目的とする。 The present invention relates to a driver state determination device and a driver for determining a driver state such as a fatigue level or a tension level during driving of a vehicle based on information generated by the driving operation of the driver by a new configuration that has not existed in the past. An object is to provide a state determination program.
上記目的を達成するため、本発明によれば、車両の運転を行うドライバの運転時の疲労度又は緊張度を判定するドライバ状態判定装置であって、
前記ドライバの運転操作に係る運転操作量を取得し、非線形解析処理を行うことによって前記運転操作量に関するリアプノフ指数を算出する非線形解析部と、
前記リアプノフ指数の時系列データのパワースペクトル密度を算出し、算出された前記パワースペクトル密度における所定の低周波数帯域の積分値と、所定の高周波数帯域の積分値とを算出する周波数スペクトル分析部と、
前記所定の低周波数帯域の積分値、及び、前記所定の高周波数帯域の積分値の両方の値の時系列変化から前記ドライバの疲労度又は緊張度を判定するドライバ状態判定部とを、
有するドライバ状態判定装置が提供される。
In order to achieve the above object, according to the present invention, there is provided a driver state determination device for determining a fatigue level or a tension level during driving of a driver who drives a vehicle,
A nonlinear analysis unit that obtains a driving operation amount related to the driving operation of the driver and calculates a Lyapunov exponent related to the driving operation amount by performing nonlinear analysis processing;
Calculating a power spectrum density of the time series data of the Lyapunov exponent, a frequency spectrum analysis unit for calculating an integral value of a predetermined low frequency band and an integral value of a predetermined high frequency band in the calculated power spectrum density; ,
A driver state determination unit that determines a fatigue level or a tension level of the driver from a time-series change of both the integrated value of the predetermined low frequency band and the integrated value of the predetermined high frequency band;
A driver state determination device is provided.
また、上記目的を達成するため、本発明によれば、車両の運転を行うドライバの運転時の疲労度又は緊張度を判定するドライバ状態判定方法をコンピュータに実行させるためのドライバ状態判定プログラムであって、
前記ドライバの運転操作に係る運転操作量を取得し、非線形解析処理を行うことによって前記運転操作量に関するリアプノフ指数を算出する非線形解析ステップと、
前記リアプノフ指数の時系列データのパワースペクトル密度を算出し、算出された前記パワースペクトル密度における所定の低周波数帯域の積分値と、所定の高周波数帯域の積分値とを算出する周波数スペクトル分析ステップと、
前記所定の低周波数帯域の積分値、及び、前記所定の高周波数帯域の積分値の両方の値の時系列変化から前記ドライバの疲労度又は緊張度を判定するドライバ状態判定ステップとを、
有する前記ドライバ状態判定方法の各ステップを前記コンピュータに実行させるドライバ状態判定プログラムが提供される。
In order to achieve the above object, according to the present invention, there is provided a driver state determination program for causing a computer to execute a driver state determination method for determining a fatigue level or a tension level during driving of a driver who operates a vehicle. And
A nonlinear analysis step of obtaining a driving operation amount related to the driving operation of the driver and calculating a Lyapunov exponent related to the driving operation amount by performing nonlinear analysis processing;
Calculating a power spectrum density of the time series data of the Lyapunov exponent, and a frequency spectrum analyzing step of calculating an integral value of a predetermined low frequency band and an integral value of a predetermined high frequency band in the calculated power spectrum density; ,
A driver state determination step of determining a fatigue level or a tension level of the driver from a time-series change of both the integrated value of the predetermined low frequency band and the integrated value of the predetermined high frequency band;
A driver state determination program for causing the computer to execute each step of the driver state determination method is provided.
本発明は上記の構成を有し、ドライバの通常の車両運転操作(アクセルペダル、ブレーキペダル、ハンドルの操作など)の操作量に係る情報に基づき、簡素な構成でドライバの疲労度又は緊張度などのドライバ状態を判定できるという効果を奏する。 The present invention has the above-described configuration, and based on the information related to the amount of operation of the driver's normal vehicle driving operation (accelerator pedal, brake pedal, steering wheel operation, etc.), the driver's fatigue level or tension level, etc. with a simple configuration The driver state can be determined.
以下、図面を参照しながら、本発明の実施の形態について説明する。 Hereinafter, embodiments of the present invention will be described with reference to the drawings.
本発明は、ドライバの車両運転操作の操作量に係る情報に基づいて、ドライバの自律神経における交感神経と副交感神経の活躍状態を解析し、この解析結果の時系列変化からドライバ状態(例えば、ドライバの疲労度又は緊張度)を判定するものである。すなわち、本発明は、ドライバに何らかの特別なセンサ(例えば、ドライバの脈拍を計測するセンサなど)を装着させることなく、ドライバによる車両の運転操作の監視結果に基づいてドライバの車両運転時の疲労度又は緊張度の判定を試みるものである。 The present invention analyzes the active state of the sympathetic nerve and the parasympathetic nerve in the driver's autonomic nerve based on the information related to the operation amount of the vehicle driving operation of the driver, and the driver state (for example, driver Fatigue level or tension level). That is, according to the present invention, the driver's fatigue level when driving the vehicle based on the monitoring result of the driving operation of the vehicle by the driver without attaching any special sensor (for example, a sensor for measuring the pulse of the driver) to the driver. Or it tries to determine the degree of tension.
まず、本発明の実施の形態におけるドライバ状態判定装置の構成の一例について説明する。図1は、本発明の実施の形態におけるドライバ状態判定装置の一例を示すブロック図である。 First, an example of the configuration of the driver state determination device according to the embodiment of the present invention will be described. FIG. 1 is a block diagram illustrating an example of a driver state determination apparatus according to an embodiment of the present invention.
図1に示されているドライバ状態判定装置100は、非線形解析部110、周波数スペクトル分析部120、ドライバ状態判定部130を有している。なお、図1には、各機能がブロックによって図示されているが、これらの各機能は、ハードウェア及び/又はプログラム(コンピュータによって実行可能なプログラム)によって実現可能である。 The driver state determination apparatus 100 illustrated in FIG. 1 includes a nonlinear analysis unit 110, a frequency spectrum analysis unit 120, and a driver state determination unit 130. In FIG. 1, each function is illustrated as a block, but each of these functions can be realized by hardware and / or a program (a program that can be executed by a computer).
非線形解析部110は、車両を運転するドライバの運転操作に係る運転操作量を監視するドライバ操作検出センサ191から、当該運転操作量を含むセンシング情報を受信し、センシング情報に対して非線形解析処理を行う機能を有している。 The nonlinear analysis unit 110 receives sensing information including the driving operation amount from the driver operation detecting sensor 191 that monitors the driving operation amount related to the driving operation of the driver who drives the vehicle, and performs nonlinear analysis processing on the sensing information. Has the function to perform.
なお、ドライバ操作検出センサ191としては、例えば、アクセルペダルの踏み量(踏み込みの角度や踏み込む力など)を検出するセンサ、ブレーキペダルの踏み量(踏み込みの角度や踏み込む力など)を検出するセンサ、ハンドルの操作距離(ハンドルの操舵距離(例えば、ハンドルの回転角度などから把握できる操舵量)やトルクなど)を検出するセンサなどを利用することが可能である。また、センシング情報として、さらに、車両の走行状態を検出する車両センサ192(例えば、車両の速度を測定する車速センサや、車両の加速度を速定する加速度センサ)から出力される車両状態情報を利用してもよい。また、アクセルペダルの踏み量の代用として車両信号から得られるスロットル開度を利用してもよい。 The driver operation detection sensor 191 includes, for example, a sensor that detects an accelerator pedal depression amount (depression angle, depressing force, etc.), a sensor that detects a brake pedal depressing amount (depression angle, depressing force, etc.), It is possible to use a sensor or the like that detects an operation distance of the handle (a steering distance of the handle (for example, a steering amount that can be grasped from a rotation angle of the handle) or a torque). Further, as the sensing information, vehicle state information output from a vehicle sensor 192 that detects the traveling state of the vehicle (for example, a vehicle speed sensor that measures the speed of the vehicle or an acceleration sensor that determines the acceleration of the vehicle) is used. May be. Moreover, you may utilize the throttle opening obtained from a vehicle signal as a substitute of the depression amount of an accelerator pedal.
具体的には、非線形解析部110は、ドライバ操作検出センサ191において検出されたセンシング情報(例えば、上述のアクセルペダルの踏み量を検出するセンサにおいて検出されたアクセルペダルの踏み量)をミリ秒オーダ(ミリ秒単位)で取得し、取得したセンシング情報(あるいは、算出用に加工又は抽出されたセンシング情報の一部)をドライバの運転特徴量としてアトラクタ化し、算出された結果(運転特徴量がアトラクタされたもの)のゆらぎ解析処理を行って、当該運転特徴量に係るリアプノフ指数を算出する処理を行う機能を有している。 Specifically, the nonlinear analysis unit 110 calculates sensing information detected by the driver operation detection sensor 191 (for example, the amount of depression of the accelerator pedal detected by the sensor that detects the amount of depression of the accelerator pedal) on the order of milliseconds. (Millisecond units), and the acquired sensing information (or a part of sensing information processed or extracted for calculation) is converted into an attractor as a driving feature of the driver, and the calculated result (the driving feature is the attractor) A function of performing a process of calculating a Lyapunov exponent related to the driving feature amount.
また、周波数スペクトル分析部120は、非線形解析部110で算出されたリアプノフ指数を取得し、周波数スペクトル分析技術に基づいてリアプノフ指数の時系列データのパワースペクトル密度を求め、当該パワースペクトル密度から、低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値を算出する機能を有している。 Further, the frequency spectrum analysis unit 120 acquires the Lyapunov exponent calculated by the nonlinear analysis unit 110, obtains the power spectrum density of the time-series data of the Lyapunov exponent based on the frequency spectrum analysis technique, and calculates the power spectrum density from the power spectrum density. It has a function of calculating power spectral density values of the frequency band and the high frequency band.
また、ドライバ状態判定部130は、周波数スペクトル分析部120で算出された低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値を用いて、ドライバの疲労度又は緊張度の判定を行う機能を有している。 In addition, the driver state determination unit 130 has a function of determining the fatigue level or the tension level of the driver using the power spectrum density values of the low frequency band and the high frequency band calculated by the frequency spectrum analysis unit 120. Have.
なお、図1では、ドライバ状態判定装置100が、非線形解析部110、周波数スペクトル分析部120、ドライバ状態判定部130のすべての機能を包含している状態が図示されているが、非線形解析部110、周波数スペクトル分析部120、ドライバ状態判定部130の一部又はすべてが独立した装置(コンピュータ)によって実現されてもよい。例えば、ドライバ操作検出センサ191から出力されるセンシング情報(さらには、車両センサ192から出力される車両状態情報)がいったんメモリ上に書き込まれ、非線形解析部110が、当該メモリ上に書き込まれたセンシング情報(さらには、車両状態情報)を読み出して非線形解析処理を行ってもよい。また同様に、非線形解析部110から出力されるリアプノフ指数がいったんメモリ上に書き込まれ、周波数スペクトル分析部120が、当該メモリ上に書き込まれたリアプノフ指数を読み出して周波数スペクトル分析処理を行ってもよい。また同様に、周波数スペクトル分析部120から出力される低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値がいったんメモリ上に書き込まれ、ドライバ状態判定部130が、当該メモリ上に書き込まれた低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値を読み出してドライバ状態判定処理を行ってもよい。 1 shows a state in which the driver state determination device 100 includes all the functions of the nonlinear analysis unit 110, the frequency spectrum analysis unit 120, and the driver state determination unit 130, the nonlinear analysis unit 110 is illustrated. In addition, part or all of the frequency spectrum analysis unit 120 and the driver state determination unit 130 may be realized by an independent device (computer). For example, the sensing information output from the driver operation detection sensor 191 (and the vehicle state information output from the vehicle sensor 192) is once written on the memory, and the nonlinear analysis unit 110 writes the sensing information written on the memory. Information (further, vehicle state information) may be read out to perform nonlinear analysis processing. Similarly, the Lyapunov exponent output from the nonlinear analysis unit 110 may be once written on the memory, and the frequency spectrum analysis unit 120 may read the Lyapunov exponent written on the memory and perform frequency spectrum analysis processing. . Similarly, the values of the power spectrum density of the low frequency band and the high frequency band output from the frequency spectrum analysis unit 120 are once written on the memory, and the driver state determination unit 130 is written on the memory. The driver state determination process may be performed by reading the power spectral density values of the low frequency band and the high frequency band.
次に、図1に示すドライバ状態判定装置100に基づいて、本発明の実施の形態におけるドライバ状態判定装置100のデータ処理の一例について説明する。図2は、本発明の実施の形態におけるドライバ状態判定装置100のデータ処理の一例を示すフローチャートである。 Next, an example of data processing of the driver state determination device 100 according to the embodiment of the present invention will be described based on the driver state determination device 100 shown in FIG. FIG. 2 is a flowchart showing an example of data processing of the driver state determination apparatus 100 according to the embodiment of the present invention.
本発明の実施の形態におけるドライバ状態判定装置100では、まず非線形解析部110が、ドライバ操作検出センサ191において検出及び出力されたセンシング情報(さらには、車両センサ192から出力された車両状態情報を考慮してもよい)に基づいて非線形解析処理を行い、リアプノフ指数を算出及び出力する(ステップS100)。次に、周波数スペクトル分析部120が、非線形解析部110から出力されたリアプノフ指数に基づいて周波数スペクトル分析処理を行い、低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値を算出及び出力する(ステップS200)。そして、ドライバ状態判定部130が、周波数スペクトル分析部120から出力された低周波数帯域及び高周波数帯域のそれぞれのパワースペクトル密度の値に基づいてドライバ状態判定処理を行い、ドライバ状態判定結果を出力する(ステップS300)。 In the driver state determination apparatus 100 according to the embodiment of the present invention, the nonlinear analysis unit 110 first considers sensing information detected and output by the driver operation detection sensor 191 (and further considers vehicle state information output from the vehicle sensor 192). The Lyapunov exponent is calculated and output (step S100). Next, the frequency spectrum analysis unit 120 performs frequency spectrum analysis processing based on the Lyapunov exponent output from the nonlinear analysis unit 110, and calculates and outputs the values of the power spectrum density in each of the low frequency band and the high frequency band. (Step S200). Then, the driver state determination unit 130 performs a driver state determination process based on the power spectrum density values of the low frequency band and the high frequency band output from the frequency spectrum analysis unit 120, and outputs a driver state determination result. (Step S300).
以下、図2に示す各ステップS100〜S300の処理の一例について説明する。 Hereinafter, an example of the processing of steps S100 to S300 illustrated in FIG. 2 will be described.
図3及び図4は、本発明の実施の形態における非線形解析処理(図2に示すステップS100)の一例を示すフローチャートである。非線形解析部110で行われる非線形解析処理は、センシング情報をアトラクタ化する処理(図3)と、当該アトラクタ化によって生成されたアトラクタを用いてリアプノフ指数を算出する処理(図4)とに大別される。 3 and 4 are flowcharts showing an example of nonlinear analysis processing (step S100 shown in FIG. 2) in the embodiment of the present invention. The nonlinear analysis process performed by the nonlinear analysis unit 110 is roughly divided into a process for converting the sensing information into an attractor (FIG. 3) and a process for calculating the Lyapunov exponent using the attractor generated by the attractor (FIG. 4). Is done.
図3に示すように、非線形解析部110は、ドライバ操作検出センサ191において検出されたセンシング情報をミリ秒オーダ(ミリ秒単位)で取得し(ステップS101)、取得したセンシング情報の値をアトラクタ化する(ステップS102)。なお、センシング情報として、例えばアクセルペダルの踏み量を検出するセンサにおいて検出されたアクセルペダルの踏み量など、ドライバが通常の車両運転を行う際に発生する情報(運転操作情報)を利用することが可能である。また、前進/後進あるいは加速/制動などの車両状態に従って、生成したアトラクタを分類してもよい。以上の処理により、非線形解析部110は、センシング情報をドライバの運転特徴量として取り扱い、アトラクタ化することが可能となる。 As shown in FIG. 3, the nonlinear analysis unit 110 acquires sensing information detected by the driver operation detection sensor 191 in millisecond order (millisecond unit) (step S101), and converts the value of the acquired sensing information into an attractor. (Step S102). As sensing information, for example, information (driving operation information) generated when the driver performs normal vehicle driving, such as the amount of depression of the accelerator pedal detected by a sensor that detects the amount of depression of the accelerator pedal, may be used. Is possible. The generated attractors may be classified according to vehicle conditions such as forward / reverse or acceleration / braking. Through the above processing, the nonlinear analysis unit 110 can treat the sensing information as the driving feature amount of the driver and make it an attractor.
次に、図4に示すように、非線形解析部110は、生成したアトラクタを取得し(ステップS103)、過去のアトラクタ行列に対する安定傾向を解析して現在のリアプノフ指数を算出し(ステップS104)、算出されたリアプノフ指数の遷移(時系列データ)をログとして蓄積(ロギング)する(ステップS105)。なお、図4に図示されているリアプノフ指数の算出は任意の周期で行われてよく、例えば、0.5秒周期で行うことが可能である。また、車両状態に従ってアトラクタを分類している場合には、各分類ごとにリアプノフ指数を算出してもよい。 Next, as shown in FIG. 4, the nonlinear analysis unit 110 acquires the generated attractor (step S103), analyzes the stability tendency with respect to the past attractor matrix, and calculates the current Lyapunov exponent (step S104). The calculated transition (time series data) of the Lyapunov exponent is accumulated (logged) as a log (step S105). Note that the Lyapunov exponent shown in FIG. 4 may be calculated at an arbitrary cycle, for example, at a cycle of 0.5 seconds. Further, when attractors are classified according to the vehicle state, the Lyapunov index may be calculated for each classification.
なお、本発明の実施の形態におけるゆらぎ解析処理の具体的な計算については、例えば、図5に図示されているように実行することが可能である。図5は、本発明の実施の形態におけるゆらぎ解析処理の具体的な計算方法の一例を示す図である。なお、ゆらぎ解析処理の計算方法は、図5に図示されているものに限定されるものではない。非線形解析の技術については様々な研究が行われており、現在及び今後確立される任意の解析技術を本発明に適用することが可能である(例えば、此処まで来た複雑系解析ツール、http://www.ieice.org/cs/csbn/program/papers/04_1_miao.pdfを参照)。 Note that the specific calculation of the fluctuation analysis process in the embodiment of the present invention can be executed as shown in FIG. 5, for example. FIG. 5 is a diagram illustrating an example of a specific calculation method of the fluctuation analysis process according to the embodiment of the present invention. Note that the calculation method of the fluctuation analysis process is not limited to that shown in FIG. Various studies have been conducted on the technique of nonlinear analysis, and any analysis technique established now and in the future can be applied to the present invention (for example, the complex system analysis tool that has come here, http: //www.ieice.org/cs/csbn/program/papers/04_1_miao.pdf)
次に、周波数スペクトル分析処理(図2に示すステップS200)について説明する。図6は、本発明の実施の形態における周波数スペクトル分析処理(図2に示すステップS200)の一例を示すフローチャートである。周波数スペクトル分析部120は、非線形解析部110で算出されたリアプノフ指数の時系列データのパワースペクトル密度を求め、低周波数帯域の積分値LFと高周波数帯域の積分値HFとを算出する。 Next, the frequency spectrum analysis process (step S200 shown in FIG. 2) will be described. FIG. 6 is a flowchart showing an example of the frequency spectrum analysis process (step S200 shown in FIG. 2) in the embodiment of the present invention. The frequency spectrum analysis unit 120 obtains the power spectrum density of the time series data of the Lyapunov exponent calculated by the nonlinear analysis unit 110, and calculates the integration value LF in the low frequency band and the integration value HF in the high frequency band.
図6において、周波数スペクトル分析部120は、まず非線形解析部110で算出されたリアプノフ指数の時系列データx(t)を取得する(ステップS201)。なお、リアプノフ指数のサンプリングレートは任意に設定可能であるが、例えば、2ヘルツ(0.5秒周期、以下、単位ヘルツをHzと表記する)で算出されるリアプノフ指数に関して、サンプリングレート=10秒(0.1Hz)の範囲内の値を取得する場合を一例として説明する。この場合、周波数スペクトル分析部120は、ステップS201において、リアプノフ指数の時系列データx(t)から時系列に並ぶ20個のリアプノフ指数を取得する。 In FIG. 6, the frequency spectrum analysis unit 120 first acquires time series data x (t) of the Lyapunov exponent calculated by the nonlinear analysis unit 110 (step S201). Note that the sampling rate of the Lyapunov exponent can be arbitrarily set. For example, with respect to the Lyapunov exponent calculated at 2 hertz (0.5 second period, hereinafter, the unit hertz is expressed as Hz), the sampling rate is 10 seconds. A case where a value within the range of (0.1 Hz) is acquired will be described as an example. In this case, the frequency spectrum analyzer 120 acquires 20 Lyapunov exponents arranged in time series from the Lyapunov exponent time-series data x (t) in step S201.
続いて、周波数スペクトル分析部120は、取得したリアプノフ指数の時系列データx(t)のパワースペクトル密度PSD(f)を算出する(ステップS202)。なお、パワースペクトル密度は、例えば図6に数式の一例(例えば、周波数fの範囲を0Hz〜1Hzとする)として記載されているものであり、その算出方法に関しては従来の周波数スペクトル分析技術で行われる方法と同様の方法を用いればよい。その結果、例えば図7(1)に示されているようなリアプノフ指数の時系列データが存在する場合、所定のサンプリングレート(例えば、10秒)の範囲内に位置するリアプノフ指数の振幅変動に関してパワースペクトル密度の計算を行うと、図7(2)に示すように、パワースペクトル密度の周波数分布を得ることができる。 Subsequently, the frequency spectrum analysis unit 120 calculates the power spectral density PSD (f) of the acquired Lyapunov exponent time-series data x (t) (step S202). Note that the power spectral density is described as an example of an equation in FIG. 6 (for example, the range of the frequency f is 0 Hz to 1 Hz), and the calculation method thereof is performed by a conventional frequency spectrum analysis technique. A method similar to the method described above may be used. As a result, for example, when time series data of Lyapunov exponents as shown in FIG. 7 (1) exists, the power with respect to the amplitude fluctuation of Lyapunov exponents located within a predetermined sampling rate (for example, 10 seconds) is determined. When the spectral density is calculated, a frequency distribution of the power spectral density can be obtained as shown in FIG.
そして、周波数スペクトル分析部120は、得られたパワースペクトル密度PSD(f)の低周波数帯域の積分値LFを算出し(ステップS203)、さらに、パワースペクトル密度PSD(f)の高周波数帯域の積分値HFを算出する(ステップS204)。なお、低周波数帯域は、高周波数帯域より低周波数側に存在するが、両方の帯域に重なりがあってもよい。本発明者らは、低周波数帯域及び高周波数帯域のそれぞれの範囲について様々な設定を試み、現時点では、低周波数帯域を0.04Hz〜0.15Hzとし、高周波数帯域を0.15Hz〜0.4Hzとした場合に有効な結果が得られることを見出している。ただし、本発明はこれらの値に限定されるものではない。 Then, the frequency spectrum analysis unit 120 calculates an integrated value LF of the obtained power spectral density PSD (f) in the low frequency band (step S203), and further integrates the high frequency band of the power spectral density PSD (f). A value HF is calculated (step S204). The low frequency band exists on the lower frequency side than the high frequency band, but both bands may overlap. The present inventors tried various settings for the respective ranges of the low frequency band and the high frequency band. At present, the low frequency band is set to 0.04 Hz to 0.15 Hz, and the high frequency band is set to 0.15 Hz to 0.00. It has been found that an effective result can be obtained when the frequency is set to 4 Hz. However, the present invention is not limited to these values.
また、周波数スペクトル分析部120は、サンプリングするパワースペクトル密度の時系列データx(t)を時系列に沿ってずらしながら、パワースペクトル密度PSD(f)の低周波数帯域の積分値LF、パワースペクトル密度PSD(f)の高周波数帯域の積分値HFを算出していくことで、所定のサンプリングレート(例えば、10秒)間隔の出力を行う。また、周波数スペクトル分析部120は、後述のドライバ状態判定処理で用いられる積分値LFと積分値HFとの比(LF/HF)を演算して出力してもよい。なお、本発明者らは、実際に被験者を用いて実験を行い、被験者(ドライバ)の交感神経の活躍状態が積分値LFと積分値HFとの比(LF/HF)と相関を有し、被験者(ドライバ)の副交感神経の活躍状態が積分値HFと相関を有することを見出した。つまり、積分値LFと積分値HFとの比(LF/HF)は被験者(ドライバ)の交感神経の活躍状態の指標として利用可能であり、積分値HFは被験者(ドライバ)の副交感神経の活躍状態の指標として利用可能である。 Further, the frequency spectrum analysis unit 120 shifts the time series data x (t) of the power spectrum density to be sampled along the time series, while integrating the low frequency band integrated value LF and power spectrum density of the power spectrum density PSD (f). By calculating the integrated value HF of the high frequency band of PSD (f), output is performed at a predetermined sampling rate (for example, 10 seconds) interval. Further, the frequency spectrum analyzer 120 may calculate and output a ratio (LF / HF) between an integral value LF and an integral value HF used in a driver state determination process described later. In addition, the present inventors actually conducted an experiment using a subject, and the active state of the sympathetic nerve of the subject (driver) has a correlation with the ratio (LF / HF) between the integral value LF and the integral value HF, It was found that the active state of the parasympathetic nerve of the subject (driver) has a correlation with the integrated value HF. That is, the ratio (LF / HF) between the integral value LF and the integral value HF can be used as an indicator of the active state of the sympathetic nerve of the subject (driver), and the integrated value HF is the active state of the parasympathetic nerve of the subject (driver). It can be used as an indicator of
次に、ドライバ状態判定処理(図2に示すステップS300)について説明する。図8は、本発明の実施の形態におけるドライバ状態判定処理(図2に示すステップS300)の一例を示すフローチャートである。図8において、ドライバ状態判定部130は、周波数スペクトル分析部120から所定のサンプリングレート(例えば、10秒間隔)で出力されるパワースペクトル密度PSD(f)の低周波数帯域の積分値LF(あるいは、積分値LFと積分値HFとの比)、及び、パワースペクトル密度PSD(f)の高周波数帯域の積分値HFを取得する(ステップS301)。 Next, the driver state determination process (step S300 shown in FIG. 2) will be described. FIG. 8 is a flowchart showing an example of the driver state determination process (step S300 shown in FIG. 2) in the embodiment of the present invention. In FIG. 8, the driver state determination unit 130 integrates the low frequency band integrated value LF (or the power spectrum density PSD (f) output from the frequency spectrum analysis unit 120 at a predetermined sampling rate (for example, at intervals of 10 seconds) (or The ratio between the integral value LF and the integral value HF) and the integral value HF in the high frequency band of the power spectral density PSD (f) are acquired (step S301).
続いて、ドライバ状態判定部130は、LF/HF及びHFのそれぞれの時系列データを正規化した後(ステップS302)、正規化されたLF/HF(以下、正規化LF/HFと記載)、正規化されたHF(以下、正規化HFと記載)のそれぞれの微分時系列データを求めるとともに、波形データのピークを得るために、平滑化微分法を用いてこれらの微分時系列データの平滑化を行う。(ステップS303)。 Subsequently, the driver state determination unit 130 normalizes each time series data of LF / HF and HF (step S302), and then normalizes LF / HF (hereinafter referred to as normalized LF / HF), In order to obtain each differential time series data of normalized HF (hereinafter referred to as normalized HF) and obtain a peak of waveform data, smoothing of these differential time series data using a smoothing differential method I do. (Step S303).
そして、ドライバ状態判定部130は、ステップS303で算出された正規化HFの微分時系列データと正規化LF/HFの微分時系列データとの差(正規化HFの微分時系列データ−正規化LF/HFの微分時系列データ)を算出する(ステップS304)。本発明者らは、上記の正規化HFの微分時系列データと正規化LF/HFの微分時系列データとの差(正規化HFの微分時系列データ−正規化LF/HFの微分時系列データ)が大きい場合に、被験者(ドライバ)の疲労度又は緊張度が高いこと、すなわち、ドライバの疲労度又は緊張度の指標として「正規化HFの微分時系列データ−正規化LF/HFの微分時系列データ」が利用可能であることを見出した。ドライバ状態判定部130は、「正規化HFの微分時系列データ−正規化LF/HFの微分時系列データ」の値の大きさに基づいて疲労度又は緊張度を数値化したり、あるいは、あらかじめ定められた閾値(例えば、試行実験を行うことにより、一般的な閾値又は被験者(ドライバ)に特有の閾値を決定することが可能)を超えた場合に疲労度又は緊張度が高くなっていることを示す情報を出力したりすることによって、ドライバの疲労度又は緊張度を判定して出力することが可能である(ステップS305)。 Then, the driver state determination unit 130 calculates the difference between the normalized HF differential time series data calculated in step S303 and the normalized LF / HF differential time series data (normalized HF differential time series data-normalized LF). / HF differential time series data) is calculated (step S304). The present inventors have made a difference between the differential time series data of the normalized HF and the normalized time series data of the normalized LF / HF (differential time series data of the normalized HF−differentiated time series data of the normalized LF / HF. ) Is large, the fatigue level or tension level of the subject (driver) is high, that is, as an indicator of the fatigue level or tension level of the driver, “normalized HF differential time series data−normalized LF / HF differential time” We found that "series data" is available. The driver state determination unit 130 quantifies the fatigue level or the tension level based on the magnitude of the value of “normalized HF differential time-series data−normalized LF / HF differential time-series data” or determines in advance. That fatigue or tension is high when a given threshold is exceeded (for example, by performing a trial experiment, it is possible to determine a general threshold or a threshold specific to the subject (driver)) By outputting the indicated information, it is possible to determine and output the driver's fatigue level or tension level (step S305).
なお、従来技術として、例えば特許文献2に開示されているように、被験者の脈波の振幅変動に対して周波数スペクトル分析を行うことによって、被験者の交感神経及び副交感神経の活躍状態を判定する技術が存在しているが、本発明者らは、被験者の脈波の変動時系列データであるRRI(R-R Interval)に基づく値と、本発明の実施の形態におけるリアプノフ指数の振幅変動から得られる値との相関を確認するための実験を繰り返し行ってきた。その結果、図9に示すように、RRIから得られる積分値LF/HF及び積分値HFと、本発明に係る積分値LF/HF及び積分値HFとの間に、顕著な相関があることを確認している。従来の技術ではRRIを得るためにドライバに対して脈波センサなどの特別な装置(車両を運転する際にドライバが装着することのない装置)の装着をドライバに強いることになるが、一方、本発明によれば、ドライバの通常の車両運転操作(アクセルペダル、ブレーキペダル、ハンドルの操作など)の操作量に係る情報に基づき、簡素な構成でドライバの疲労度又は緊張度を判定することが可能となる。 As a conventional technique, for example, as disclosed in Patent Document 2, a technique for determining the active state of a subject's sympathetic nerve and parasympathetic nerve by performing frequency spectrum analysis on the amplitude fluctuation of the pulse wave of the subject. However, the present inventors have obtained a value based on the RRI (RR Interval), which is the time series data of the subject's pulse wave, and the value obtained from the amplitude fluctuation of the Lyapunov exponent in the embodiment of the present invention. We have repeatedly conducted experiments to confirm the correlation. As a result, as shown in FIG. 9, there is a significant correlation between the integral value LF / HF and the integral value HF obtained from the RRI and the integral value LF / HF and the integral value HF according to the present invention. I have confirmed. In the prior art, in order to obtain RRI, the driver is forced to install a special device such as a pulse wave sensor (a device that is not worn by the driver when driving the vehicle). According to the present invention, it is possible to determine a driver's fatigue level or tension level with a simple configuration based on information related to an operation amount of a driver's normal vehicle driving operation (accelerator pedal, brake pedal, steering wheel operation, etc.). It becomes possible.
本発明は、ドライバの通常の車両運転操作(アクセルペダル、ブレーキペダル、ハンドルなどの操作)の操作量に係る情報に基づき、簡素な構成でドライバの疲労度又は緊張度などのドライバ状態を判定することができるという効果を有しており、ドライバの車両運転時の疲労度又は緊張度などのドライバ状態の判定を行う技術に適用可能である。 The present invention determines a driver state such as a driver's fatigue level or tension level with a simple configuration based on information related to an operation amount of a driver's normal vehicle driving operation (operation of an accelerator pedal, a brake pedal, a handle, etc.). Therefore, the present invention can be applied to a technique for determining a driver state such as a fatigue level or a tension level when the driver is driving a vehicle.
100 ドライバ状態判定装置
110 非線形解析部
120 周波数スペクトル分析部
130 ドライバ状態判定部
191 ドライバ操作検出センサ
192 車両センサ
DESCRIPTION OF SYMBOLS 100 Driver state determination apparatus 110 Nonlinear analysis part 120 Frequency spectrum analysis part 130 Driver state determination part 191 Driver operation detection sensor 192 Vehicle sensor
Claims (10)
前記ドライバの運転操作に係る運転操作量を取得し、非線形解析処理を行うことによって前記運転操作量に関するリアプノフ指数を算出する非線形解析部と、
前記リアプノフ指数の時系列データのパワースペクトル密度を算出し、算出された前記パワースペクトル密度における所定の低周波数帯域の積分値と、所定の高周波数帯域の積分値とを算出する周波数スペクトル分析部と、
前記所定の低周波数帯域の積分値、及び、前記所定の高周波数帯域の積分値の両方の値の時系列変化から前記ドライバの疲労度又は緊張度を判定するドライバ状態判定部とを、
有するドライバ状態判定装置。 A driver state determination device that determines the degree of fatigue or tension during driving of a driver who drives a vehicle,
A nonlinear analysis unit that obtains a driving operation amount related to the driving operation of the driver and calculates a Lyapunov exponent related to the driving operation amount by performing nonlinear analysis processing;
Calculating a power spectrum density of the time series data of the Lyapunov exponent, a frequency spectrum analysis unit for calculating an integral value of a predetermined low frequency band and an integral value of a predetermined high frequency band in the calculated power spectrum density; ,
A driver state determination unit that determines a fatigue level or a tension level of the driver from a time-series change of both the integrated value of the predetermined low frequency band and the integrated value of the predetermined high frequency band;
A driver state determination device.
前記ドライバの運転操作に係る運転操作量を取得し、非線形解析処理を行うことによって前記運転操作量に関するリアプノフ指数を算出する非線形解析ステップと、
前記リアプノフ指数の時系列データのパワースペクトル密度を算出し、算出された前記パワースペクトル密度における所定の低周波数帯域の積分値と、所定の高周波数帯域の積分値とを算出する周波数スペクトル分析ステップと、
前記所定の低周波数帯域の積分値、及び、前記所定の高周波数帯域の積分値の両方の値の時系列変化から前記ドライバの疲労度又は緊張度を判定するドライバ状態判定ステップとを、
有する前記ドライバ状態判定方法の各ステップを前記コンピュータに実行させるドライバ状態判定プログラム。 A driver state determination program for causing a computer to execute a driver state determination method for determining a fatigue level or a tension level during driving of a driver driving a vehicle,
A nonlinear analysis step of obtaining a driving operation amount related to the driving operation of the driver and calculating a Lyapunov exponent related to the driving operation amount by performing nonlinear analysis processing;
Calculating a power spectrum density of the time series data of the Lyapunov exponent, and a frequency spectrum analyzing step of calculating an integral value of a predetermined low frequency band and an integral value of a predetermined high frequency band in the calculated power spectrum density; ,
A driver state determination step of determining a fatigue level or a tension level of the driver from a time-series change of both the integrated value of the predetermined low frequency band and the integrated value of the predetermined high frequency band;
A driver status determination program for causing a computer to execute each step of the driver status determination method.
The operation amount of any one of an accelerator pedal, a brake pedal, and a handle that is operated by the driver when driving the vehicle is used as the driving operation amount related to the driving operation of the driver. The driver state determination program as described in one.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014069682A JP6173249B2 (en) | 2014-03-28 | 2014-03-28 | Driver state determination device and driver state determination program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014069682A JP6173249B2 (en) | 2014-03-28 | 2014-03-28 | Driver state determination device and driver state determination program |
Publications (2)
Publication Number | Publication Date |
---|---|
JP2015189402A true JP2015189402A (en) | 2015-11-02 |
JP6173249B2 JP6173249B2 (en) | 2017-08-02 |
Family
ID=54424270
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2014069682A Expired - Fee Related JP6173249B2 (en) | 2014-03-28 | 2014-03-28 | Driver state determination device and driver state determination program |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP6173249B2 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017197002A (en) * | 2016-04-27 | 2017-11-02 | 株式会社デンソーアイティーラボラトリ | Driver tension determination device and driver tension determination method |
JP2018114859A (en) * | 2017-01-19 | 2018-07-26 | 株式会社デンソーアイティーラボラトリ | Driver tension level display device and method of displaying driver tension level |
JP2019122446A (en) * | 2018-01-12 | 2019-07-25 | 株式会社デンソーアイティーラボラトリ | Examinee state estimation device and examinee state estimation method |
JP2020074805A (en) * | 2018-11-05 | 2020-05-21 | 株式会社安藤・間 | Method and device for presuming driver's state |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0558192A (en) * | 1991-09-03 | 1993-03-09 | Toyota Motor Corp | Asleep driving detecting device |
JPH06107030A (en) * | 1992-09-24 | 1994-04-19 | Toyota Motor Corp | Dozing driving detection device |
JPH07143972A (en) * | 1993-11-25 | 1995-06-06 | Matsushita Electric Works Ltd | Method and apparatus for judging sleeping condition |
JPH09123790A (en) * | 1995-08-28 | 1997-05-13 | Mitsubishi Motors Corp | Vehicle operating condition detecting device |
JPH09308614A (en) * | 1996-05-21 | 1997-12-02 | Matsushita Electric Ind Co Ltd | Driver monitoring device and safety system using the same |
JPH10288942A (en) * | 1997-04-15 | 1998-10-27 | N Plan:Kk | Driving diagnosing method for automobile and motorcycle |
JPH11128185A (en) * | 1997-10-31 | 1999-05-18 | Matsushita Electric Ind Co Ltd | Method of and device for analyzing heartbeat fluctuation |
JP2002230699A (en) * | 2001-01-31 | 2002-08-16 | Mazda Motor Corp | Operation load judgment device, operation load judgment method, computer program for executing said method, and storage medium with said computer program stored therein |
JP2004350773A (en) * | 2003-05-27 | 2004-12-16 | Denso Corp | Sleepiness degree detector |
JP2005279113A (en) * | 2004-03-30 | 2005-10-13 | Toshiba Corp | Apparatus and method for determining sleeping condition |
JP2008264138A (en) * | 2007-04-18 | 2008-11-06 | Delta Tooling Co Ltd | Sleep state judgement apparatus, sleep state judgement method and computer program |
JP2009022610A (en) * | 2007-07-20 | 2009-02-05 | Delta Tooling Co Ltd | Degree of fatigue computing device and computer program |
JP2009028085A (en) * | 2007-07-24 | 2009-02-12 | Nissan Motor Co Ltd | Biological condition evaluation equipment |
JP2009146185A (en) * | 2007-12-14 | 2009-07-02 | Fujitsu Ten Ltd | Degree-of-fatigue determination device |
JP2009289251A (en) * | 2008-04-30 | 2009-12-10 | Toyota Central R&D Labs Inc | Consciousness deterioration driving detection device, driving support apparatus, and program |
JP2011067501A (en) * | 2009-09-28 | 2011-04-07 | Panasonic Corp | Method for determination of interview sheet |
JP2011227883A (en) * | 2010-03-31 | 2011-11-10 | Denso It Laboratory Inc | Device for determining ability to drive and method for determining ability to drive |
JP2013202123A (en) * | 2012-03-27 | 2013-10-07 | Tohoku Univ | Autonomic nerve function measurement device |
-
2014
- 2014-03-28 JP JP2014069682A patent/JP6173249B2/en not_active Expired - Fee Related
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0558192A (en) * | 1991-09-03 | 1993-03-09 | Toyota Motor Corp | Asleep driving detecting device |
JPH06107030A (en) * | 1992-09-24 | 1994-04-19 | Toyota Motor Corp | Dozing driving detection device |
JPH07143972A (en) * | 1993-11-25 | 1995-06-06 | Matsushita Electric Works Ltd | Method and apparatus for judging sleeping condition |
JPH09123790A (en) * | 1995-08-28 | 1997-05-13 | Mitsubishi Motors Corp | Vehicle operating condition detecting device |
JPH09308614A (en) * | 1996-05-21 | 1997-12-02 | Matsushita Electric Ind Co Ltd | Driver monitoring device and safety system using the same |
JPH10288942A (en) * | 1997-04-15 | 1998-10-27 | N Plan:Kk | Driving diagnosing method for automobile and motorcycle |
JPH11128185A (en) * | 1997-10-31 | 1999-05-18 | Matsushita Electric Ind Co Ltd | Method of and device for analyzing heartbeat fluctuation |
JP2002230699A (en) * | 2001-01-31 | 2002-08-16 | Mazda Motor Corp | Operation load judgment device, operation load judgment method, computer program for executing said method, and storage medium with said computer program stored therein |
JP2004350773A (en) * | 2003-05-27 | 2004-12-16 | Denso Corp | Sleepiness degree detector |
JP2005279113A (en) * | 2004-03-30 | 2005-10-13 | Toshiba Corp | Apparatus and method for determining sleeping condition |
JP2008264138A (en) * | 2007-04-18 | 2008-11-06 | Delta Tooling Co Ltd | Sleep state judgement apparatus, sleep state judgement method and computer program |
JP2009022610A (en) * | 2007-07-20 | 2009-02-05 | Delta Tooling Co Ltd | Degree of fatigue computing device and computer program |
JP2009028085A (en) * | 2007-07-24 | 2009-02-12 | Nissan Motor Co Ltd | Biological condition evaluation equipment |
JP2009146185A (en) * | 2007-12-14 | 2009-07-02 | Fujitsu Ten Ltd | Degree-of-fatigue determination device |
JP2009289251A (en) * | 2008-04-30 | 2009-12-10 | Toyota Central R&D Labs Inc | Consciousness deterioration driving detection device, driving support apparatus, and program |
JP2011067501A (en) * | 2009-09-28 | 2011-04-07 | Panasonic Corp | Method for determination of interview sheet |
JP2011227883A (en) * | 2010-03-31 | 2011-11-10 | Denso It Laboratory Inc | Device for determining ability to drive and method for determining ability to drive |
JP2013202123A (en) * | 2012-03-27 | 2013-10-07 | Tohoku Univ | Autonomic nerve function measurement device |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017197002A (en) * | 2016-04-27 | 2017-11-02 | 株式会社デンソーアイティーラボラトリ | Driver tension determination device and driver tension determination method |
US10980463B2 (en) | 2016-04-27 | 2021-04-20 | Denso It Laboratory, Inc. | Driver's tension level determining apparatus and driver's tension level determining method |
JP2018114859A (en) * | 2017-01-19 | 2018-07-26 | 株式会社デンソーアイティーラボラトリ | Driver tension level display device and method of displaying driver tension level |
JP2019122446A (en) * | 2018-01-12 | 2019-07-25 | 株式会社デンソーアイティーラボラトリ | Examinee state estimation device and examinee state estimation method |
JP2020074805A (en) * | 2018-11-05 | 2020-05-21 | 株式会社安藤・間 | Method and device for presuming driver's state |
JP7217576B2 (en) | 2018-11-05 | 2023-02-03 | 株式会社安藤・間 | Driver state estimation method and device |
Also Published As
Publication number | Publication date |
---|---|
JP6173249B2 (en) | 2017-08-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6173249B2 (en) | Driver state determination device and driver state determination program | |
JP4252268B2 (en) | Fatigue level determination system, fatigue level determination method, and fatigue level determination program | |
JP6216406B1 (en) | Driver tension determination device and driver tension determination method | |
KR20140095291A (en) | Apparatus and method for measurement stresss based on movement and heart rate of user | |
JP6809126B2 (en) | Drowsiness determination device and drowsiness determination method | |
JP4433739B2 (en) | Work stress evaluation apparatus and work stress evaluation method | |
JP7217576B2 (en) | Driver state estimation method and device | |
US20150374278A1 (en) | Method for controlling gait-training apparatus using biofeedback | |
JP5874367B2 (en) | Heart rate signal processing apparatus and heart rate signal processing method | |
CN113343928B (en) | Method and device for detecting rail wave mill of speed change section high-speed railway and computer equipment | |
JP4701694B2 (en) | Arousal level determination device and arousal level determination method | |
JP2014222189A (en) | Vehicle noise determination apparatus and noise determination method | |
JP2009219541A (en) | Drunk state detector | |
JP6187589B2 (en) | Trunk muscle contraction detector | |
Nema et al. | Wavelet-frequency analysis for the detection of discontinuities in switched system models of human balance | |
JP2013123524A (en) | Wakefullness determining device, wakefullness determining method and program | |
WO2004008957A1 (en) | Work pleasantness evaluating device and work pleasantness evaluating method | |
JP6689214B2 (en) | Driver tension degree display device and driver tension degree display method | |
JP4930839B2 (en) | State evaluation apparatus and state evaluation program | |
JP6791708B2 (en) | Drowsiness estimation device and drowsiness estimation program | |
JP6750229B2 (en) | Drowsiness detection program, drowsiness detection method, and drowsiness detection device | |
JP2004089272A (en) | Method and device for biological state estimation, and program | |
US20210386358A1 (en) | Electromyography processing apparatus, electromyography processing method and electromyography processing program | |
JP6531187B2 (en) | Body sound analysis device, body sound analysis method, computer program and recording medium | |
CN112319537B (en) | Train air brake state real-time evaluation method, system and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20160815 |
|
A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20170530 |
|
TRDD | Decision of grant or rejection written | ||
A01 | Written decision to grant a patent or to grant a registration (utility model) |
Free format text: JAPANESE INTERMEDIATE CODE: A01 Effective date: 20170606 |
|
A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20170704 |
|
R150 | Certificate of patent or registration of utility model |
Ref document number: 6173249 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |
|
R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
R250 | Receipt of annual fees |
Free format text: JAPANESE INTERMEDIATE CODE: R250 |
|
LAPS | Cancellation because of no payment of annual fees |