JP6946734B2 - Behavior prediction method and behavior prediction device - Google Patents

Description

The present invention relates to a behavior prediction method and a behavior prediction device.

Conventionally, when measuring an electroencephalogram, an electrode is placed on the head by wearing a cap provided with a measurement probe (electrode) to measure the electroencephalogram (see Patent Document 1). As a method of arranging the electrodes, it is common to arrange the electrodes in accordance with the international 10-20 law.

Japanese Unexamined Patent Publication No. 2012-73329

However, when 21 electrodes are arranged according to the electrode arrangement method based on the international 10-20 law, the number of electrodes arranged is large and it takes time to attach the electrodes.

In view of the above problems, an object of the present invention is to provide a behavior prediction method and a behavior prediction device capable of suppressing the number of electrodes attached to the head when measuring an electroencephalogram and attaching the electrodes in a short time. do.

According to one aspect of the present invention, a plurality of electrodes are arranged on the human head only in the region including the cranial parietal surface of the primary motor area and the supplementary motor area, and the human electroencephalogram is measured using the plurality of electrodes. It is characterized in that the motor preparation potential is calculated from the measured brain waves to predict human behavior.

According to the present invention, it is possible to provide a behavior prediction method and a behavior prediction device capable of suppressing the number of electrodes attached to the head when measuring an electroencephalogram and attaching the electrodes in a short time.

It is a block diagram which shows an example of the behavior prediction apparatus which concerns on 1st Embodiment. It is a graph which shows an example of the waveform of an electroencephalogram. It is the schematic for demonstrating the detection method of the exercise preparation potential. It is a side view of the head which shows the electrode arrangement method by the international 10-20 method. It is a top view of the head which shows the electrode arrangement method by the international 10-20 method. It is a schematic diagram which shows an example of the potential distribution of an electroencephalogram. It is a schematic diagram which shows an example of the brain for explaining a primary motor area and a supplementary motor area. It is the schematic which shows an example of the electrode arrangement method which concerns on 1st Embodiment. It is a graph which shows the waveform of the electroencephalogram measured by the electrode E1 (FC3). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E2 (FCz). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E3 (FC4). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E4 (C3). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E5 (Cz). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E6 (C4). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E7 (CP3). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E8 (CPz). It is a graph which shows the waveform of the electroencephalogram measured by the electrode E9 (CP4). It is a flowchart which shows an example of the behavior prediction method which concerns on 1st Embodiment. It is a flowchart which shows an example of the electrode arrangement method which concerns on 1st Embodiment. It is the schematic which shows an example of the electrode arrangement method which concerns on 1st Embodiment. It is the schematic which shows an example of the electrode arrangement method which concerns on 1st Embodiment. It is the schematic which shows an example of the electrode arrangement method which concerns on 1st Embodiment. It is the schematic which shows an example of the experiment which concerns on 1st Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is a graph which shows the correct answer rate in the case of the electrode arrangement of FIGS. 13A to 13H. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement which concerns on 2nd Embodiment. It is a graph which shows the correct answer rate in the case of the electrode arrangement of FIGS. 15A to 15N. It is a flowchart which shows an example of the electrode arrangement method which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement method which concerns on 2nd Embodiment. It is the schematic which shows an example of the electrode arrangement method which concerns on 2nd Embodiment. It is a flowchart which shows an example of the electrode arrangement method which concerns on other embodiment of this invention.

Hereinafter, the first and second embodiments of the present invention will be described with reference to the drawings. In the description of the drawings below, the same or similar reference numerals are attached to the same or similar parts. It should be noted that each drawing is a schematic one and may differ from the actual one. Further, the first and second embodiments of the present invention shown below exemplify an apparatus and a method for embodying the technical idea of the present invention, and the technical idea of the present invention comprises a constitution. The structure, arrangement, etc. of parts are not specified as follows. The technical idea of the present invention may be modified in various ways within the technical scope specified by the claims stated in the claims.

(First Embodiment)
As the behavior prediction device according to the first embodiment of the present invention, a case where the behavior prediction device is mounted on a vehicle and predicts the behavior of the driver will be illustrated. As shown in FIG. 1, the behavior prediction device according to the first embodiment includes a controller (behavior prediction calculation circuit) 1, a brain wave meter 2 connected to the controller 1, a running state sensor group 3, and an ambient condition sensor group 4. , The actuator group 5 and the output device 6. The controller 1, the electroencephalograph 2, the traveling state sensor group 3, the surrounding condition sensor group 4, the actuator group 5, and the output device 6 can transmit and receive data, signals, and information to and from each other by wire or wirelessly.

The controller 1 performs an arithmetic logical operation using the brain wave data output from the brain wave meter 2 for the processing required for the operation performed by the behavior prediction device according to the first embodiment, and according to the result of the arithmetic logic operation. It is a control circuit such as an electronic control unit (ECU) that outputs a control command (control signal) to the actuator group 5 and the output device 6. The controller 1 includes, for example, a processor 11, a storage device 12, and an input / output interface (not shown). The processor 11 is a device such as a microprocessor equivalent to an arithmetic logic unit (ALU), a control circuit (control device), a central processing unit (CPU) including various registers, and the like. The storage device 12 is composed of a semiconductor memory, a disk medium, or the like, and may include a storage medium such as a register, a cache memory, a ROM and a RAM used as a main storage device. For example, the processor 11 can execute a program (behavior prediction program) that is stored in the storage device 12 in advance and indicates a series of processes necessary for the operation of the action prediction device according to the first embodiment.

The controller 1 may have a programmable logic device (PLD) such as a field programmable gate array (FPGA), and is equivalently set in a general-purpose semiconductor integrated circuit by processing by software. It may be a functional logic circuit or the like. Each part constituting the controller 1 may be composed of a single piece of hardware, or may be composed of separate hardware.

The electroencephalograph 2 detects the electroencephalogram (brain activity) of the driver (human) and outputs the detected electroencephalogram data to the controller 1. The electroencephalograph 2 has an electrode group (plurality of electrodes) 21 for measuring electroencephalogram, an amplifier 22 that amplifies a plurality of electroencephalogram data which are potential changes collected by the electrode group 21, and a plurality of electroencephalogram data output from the amplifier 22. It has a filter 23 for extracting frequency components in a predetermined passing band from the above, and an A / D converter 24 for sampling analog data of the extracted electroencephalogram data at a predetermined sampling cycle and converting it into digital data. A part of the functions other than the electrode group 21 of the electroencephalograph 2 may be built in the controller 1.

The electroencephalograph 2 detects a weak potential difference signal generated between a plurality of electrodes attached to the driver's head as electrical activity generated in the driver's brain. For example, the controller 1 calculates the exercise preparation potential (MRP) generated in the driver's brain by frequency-analyzing the potential difference signal between the electroencephalogram data of each electrode detected by the electroencephalograph 2. The exercise preparation potential is a kind of event-related potential (ERP) that shows the reaction of the brain that appears as a result of thinking and cognition, and is a potential generated when the hand, leg, or the like is spontaneously moved. The brain waves that form the basis of the exercise preparation potential are generated before the driver actually begins to act. Therefore, the exercise preparation potential is detected about 2 seconds before the timing when the driver starts the action, and is detected larger than about 400 ms before. Therefore, by calculating the exercise preparation potential, it is possible to predict the driver's behavior (behavioral intention) before the driver actually starts the behavior. Here, the case where the motion preparation potential is calculated by frequency analysis is illustrated, but the pattern analysis is not limited to the frequency analysis, and any signal analysis may be performed.

FIG. 2 is a diagram showing an example of a feature vector in an electroencephalogram signal. Here, N feature quantities are extracted from the electroencephalogram data before the driver's action starts, and the electroencephalogram feature vector P = (p1, p2, ..., PN) is generated. As the feature amount, for example, a value sampled at regular intervals is used. As shown in FIG. 3, the feature amounts of the past exercise preparation potentials are stored in a database in advance, and the region D to be arranged in the feature space is determined. The definition of the region D is, for example, if there are a plurality of samples, a circle centered on the center of gravity of the vector set {P} and having a radius as the standard deviation σ is determined as the region D. Then, it is determined whether or not the feature vector P of the exercise preparation potential measured in real time from the driver enters the region D. Here, it is determined that the exercise preparation potential is generated when the feature vector P enters the region D, and it is determined that the exercise preparation potential is not generated when the feature vector P is not in the region D.

The electrode group 21 for measuring the electroencephalogram of the electroencephalograph 2 is arranged on the surface of the human head. For example, the electrode group 21 can be non-invasively attached by attaching the electrode group 21 to an electrode cap, a band, a net, or the like and attaching the electrode group 21 to the head. The method of attaching the electrode group 21 is not particularly limited, and the electrodes may be fixed with, for example, a conductive paste, or the needle-shaped electrodes may be inserted into the scalp.

As a conventional electrode placement method for electroencephalogram measurement, an electrode placement method based on the international 10-20 method is common. As shown in FIGS. 4A and 4B, the electrode placement method based on the International 10-20 method is between the nasal root PA and the occipital nodule PB, and between the left auricular anterior point PC and the right auricular anterior point PD. Divided into 10%, 20%, 20%, 20%, 20%, 10%, and 21 electrodes Fp1, Fp2, F7, F3, Fz, F4, F8, A1, T3, C3, Cz at the divided positions. , C4, T4, A2, T5, P3, Pz, P4, T6, O1, O2.

Electrodes Fp1 and Fp2 are frontal poles (anatomically frontal frontal lobe), electrodes F3 and F4 are frontal (anatomically motor field), and electrodes C3 and C4 are central (anatomically central). Grooves), electrodes P3 and P4 on the crown (anatomically sensory area), electrodes O1 and O2 on the back of the head (anatomically visual area), and electrodes F7 and F8 on the anterior temporal region (anatomically) Lower frontal area) Electrodes T3 and T4 are the medial temporal region (anatomically the medial temporal lobe), electrodes T5 and T6 are the posterior temporal region (anatomically posterior temporal lobe), and electrodes A1 and A2. Is located in the ear canal, the electrode Fz is located in the median frontal region, the electrode Cz is located in the median center, and the electrode Pz is located in the median parietal region.

As shown by broken lines in FIGS. 4A and 4B, the electrodes FC3, FCz, FC4 and the electrodes CP3, CPz, CP4 are electrodes defined by the extended international 10-20 method (10% method), which is an extension of the international 10-20 method. Is. The electrodes FC3, FCz and FC4 are located at the frontal region and the central portion between the electrodes F3, Fz and F4 and the electrodes C3, Cz and C4, respectively. The electrodes CP3, CPz and CP4 are located at the central portion and the crown portion between the electrodes C3, Cz and C4 and the electrodes P3, Pz and P4, respectively.

As a method for measuring brain waves, a unipolar induction method, a bipolar induction method, and an average reference electrode method can be adopted. The unipolar induction method is a method of measuring the potential difference between the reference electrode and the electrode (exploration electrode) on the surface of the head, using the electrode of the ear canal as a reference electrode. The bipolar induction method is a method of measuring the potential difference between two points of each electrode on the surface of the head. The average reference electrode method is a method of measuring the potential difference between the reference electrode and the electrode (exploration electrode) on the surface of the head, using the point where all the electrodes are connected as the reference electrode.

Here, in the electrode arrangement method based on the international 10-20 method, it is necessary to arrange a large number of 21 electrodes, it takes time to attach the electrodes, and the measurement load of the subject or the like increases. In order to optimize the electrode arrangement, the present inventors conducted an experiment in which a large number of electrodes E were arranged as shown in FIG. 5 to calculate the exercise preparation potential, and investigated a portion where the exercise preparation potential was likely to appear. rice field. As a result of the experiment, as shown in FIG. 5, it was found that the motor preparatory potential often appears near the crown surface of the primary motor area and the supplementary motor area. In the potential distribution of FIG. 5, the magnitude of the exercise preparation potential is divided stepwise, and the larger the exercise preparation potential is, the denser the dots are. As shown in FIG. 6, the primary motor cortex 101 is a region in front of the central groove 103 in the central part of the cerebral cortex of the human brain 100, and has a function of outputting motor commands to the brain stem and spinal cord. The supplementary motor area 102 is located in front of the primary motor area 101 and has functions such as control of the movement sequence.

Therefore, in the embodiment of the present invention, the electrodes are selectively and intensively arranged on the surface of the head only in the region (electrode arrangement region) including the cranial crown surface of the primary motor area 101 and the supplementary motor area 102. As a result, the motor preparation potential is efficiently detected while reducing the number of electrodes other than the electrode arrangement region. For example, as shown in FIG. 7, an electrode arrangement region R0 including the cranial crown surface of the primary motor area 101 and the supplementary motor area 102 is set, and electrodes E1 to E9 (corresponding to the electrode group 21 in FIG. 1) are set in the electrode arrangement area R0. ) Is placed. In FIG. 7, a straight line L1 connecting the procerus PA and the occipital nodule PB and a straight line L2 connecting the left auricular anterior point PC and the right auricular anterior point PD are shown by broken lines. FIG. 7 illustrates the case where the electrode arrangement region R0 is an ellipse having a major axis in the left-right direction (direction parallel to the straight line L2) of the head, but the present invention is not limited to this. For example, the electrode arrangement region R0 may have an elliptical shape having a major axis in the anteroposterior direction (direction parallel to the straight line L1) of the head, may be circular, or may be rectangular.

For example, the electrode arrangement region R0 is the electrodes FC3, FCz, FC4, C3, Cz, C4, CP3, CPz, CP4 defined by the international 10-20 method and the extended international 10-20 method shown in FIGS. 4A and 4B. Set to a range that includes the positions of electrodes Fp1, Fp2, F7, F3, Fz, F4, F8, A1, A2, T3, T4, T5, P3, Pz, P4, T6, O1, O2. You may. Further, the electrode arrangement region R0 is further expanded to further include the positions of the electrodes F3, Fz, F4, P3, Pz, P4, and the electrodes Fp1, Fp2, F7, F8, A1, A2, T3, T4, T5, T6. , O1 and O2 may be set in a range that does not include the positions.

In the electrode arrangement region R0, 3 × 3 electrodes E1 to E9 are dispersedly arranged. For example, the electrodes E1 to E9 are located at the positions of the electrodes FC3, FCz, FC4, C3, Cz, C4, CP3, CPz, CP4 defined by the international 10-20 method and the extended international 10-20 method shown in FIG. Have been placed. The electrodes E2 are arranged at the left and right central portions of the supplementary motor area 102 shown in FIG. 6, and the electrodes E1 and E3 are arranged symmetrically with the electrodes E2 in between. The electrodes E5 are arranged at the left and right central portions of the primary motor cortex 101 shown in FIG. 6, and the electrodes E4 and E6 are arranged symmetrically with the electrode E5 in between. The electrodes E8 are arranged on the crown, and the electrodes E7 and E9 are arranged symmetrically with the electrode E8 in between. 8A-8I show an example of brain waves measured from each of the electrodes E1 to E9.

Note that FIG. 7 illustrates a case where nine electrodes E1 to E9 are arranged, but the number of electrodes is not limited to this. For example, the number of electrodes may be less than 9, as long as the data of the exercise preparation potential can be sufficiently calculated. The number may be 10 or more, but the number of electrodes is preferably small from the viewpoint of mounting time and measurement load. Further, the arrangement positions of the electrodes E1 to E9 are not limited, and the electrodes may be arranged at positions other than the arrangement positions of the electrodes based on the international 10-20 method and the extended international 10-20 method, and may be arranged within the electrode arrangement region R0. For example, various patterns can be adopted (an example of electrode arrangement will be described later in the second embodiment). When the unipolar induction method is used, in addition to the electrodes (exploration electrodes) E1 to E9 arranged in the electrode arrangement area R0, a reference electrode is arranged in the earlobe, the tip of the nose, etc. outside the electrode arrangement area R0. May be good. Further, the shapes of the electrodes E1 to E9 are not particularly limited, and various shapes such as a disk shape can be adopted.

The traveling state sensor group 3 shown in FIG. 1 includes a vehicle speed sensor 31, an accelerator opening sensor 32, a brake switch 33, a steering operation amount sensor 34, and a winker switch 35. The vehicle speed sensor 31 detects the vehicle speed from the wheel speed of the vehicle and outputs the detected vehicle speed to the controller 1. The accelerator opening sensor 32 detects the accelerator opening of the vehicle from the amount of depression of the accelerator pedal, and outputs the detected accelerator opening to the controller 1. The brake switch 33 detects the operating state of the brake such as the presence or absence of operation of the brake pedal of the vehicle, and outputs the detected operating state of the brake to the controller 1. The steering operation amount sensor 34 detects the operation angle of the steering wheel of the vehicle or the steering angle of the steering wheel as the steering operation amount, and outputs the detected steering operation amount to the controller 1. The winker switch 35 detects the operating state of the direction indicator (winker), that is, the on / off of the left direction switch and the on / off of the right direction switch, and outputs the detected operating state of the winker to the controller 1.

The ambient condition sensor group 4 includes a camera 41, a radar 42, a map database (DB) 43, and a Global Positioning System (GPS) receiver 44. The camera 41 is an image sensor that captures a predetermined range around the vehicle and acquires image data. The camera 41 is composed of, for example, a CCD wide-angle camera provided in the upper part of the front window in the vehicle interior. The camera 41 may be a stereo camera or an omnidirectional camera, and may include a plurality of image sensors. From the acquired image data, the camera 41 detects the road around the vehicle and the structures around the road, road markings, signs, other vehicles, pedestrians, etc. as the surrounding conditions of the vehicle, and the surroundings of the detected vehicle. The status data is output to the controller 1.

As the radar 42, a laser range finder (LRF) or a range finder radar using millimeter waves or ultrasonic waves can be adopted, and the radar 42 is composed of, for example, a millimeter wave radar provided in a front grill. The radar 42 scans a predetermined range around the vehicle and detects obstacles such as other vehicles existing around the vehicle. The radar 42 detects, for example, the relative position (direction) between the obstacle and the vehicle, the relative speed of the obstacle, the distance from the vehicle to the obstacle, and the like as the surrounding conditions of the vehicle. The radar 42 outputs the detected data of the surrounding condition of the vehicle to the controller 1.

As the map DB 43, a storage medium such as a semiconductor memory or a disk medium can be used. The map DB 43 stores map information including road type, road alignment, lane width, vehicle traffic direction, speed limit, and the like. The map information database may be managed by the server, and only the updated map information difference data may be acquired through, for example, a telematics service, and the map information stored in the map DB 43 may be updated. The map DB 43 may be built in the storage device 12 of the controller 1.

The GPS receiver 44 acquires the latitude, longitude and altitude of the vehicle as the current position of the vehicle based on the radio waves received from the artificial satellite. The controller 1 collates the current position of the vehicle acquired by the GPS receiver 44 with the map stored in the map DB 43, and acquires the current position of the vehicle on the map stored in the map DB 43. The controller 1 sets a travel route from the current position of the vehicle on the map to the destination set by the driver or the like, and presents the set travel route to the driver by the display of the display or the voice of the speaker. It is possible to control the running of the vehicle along the set running route.

The controller 1 predicts the driver's behavior by calculating the exercise preparation potential from the electroencephalogram data measured by the electroencephalograph 2. When the driver's behavior is predicted, the controller 1 further determines the driver's behavior based on the driving condition of the vehicle detected by the traveling condition sensor group 3 and the surrounding condition of the vehicle detected by the surrounding condition sensor group 4. The intention is estimated, and a control command is output to the actuator group 5 and the output device 6. For example, the controller 1 predicts the driver's behavior when it is determined that the vehicle is stopped due to a right or left turn based on the vehicle speed detected by the vehicle speed sensor 31 and the operating state of the winker detected by the winker switch 35. If so, a control command is output to the actuator group 5 to support the starting operation and the right / left turning operation.

The actuator group 5 includes, for example, an accelerator opening actuator 51, a brake control actuator 52, and a steering actuator 53. The accelerator opening actuator 51 includes, for example, an electronically controlled throttle valve, and controls the accelerator opening of the vehicle based on a control command signal from the controller 1. The brake control actuator 52 is composed of a hydraulic circuit used for, for example, VDC (Vehicle Dynamics Control) or the like, and controls the braking operation of the brake of the vehicle based on the signal of the control command from the controller 1. The steering actuator 53 controls the steering of the vehicle based on the signal of the control command from the controller 1. The output device 6 includes a display 61 and a buzzer 62. The display 61 and the buzzer 62 present (notify), for example, the starting intention of the vehicle to the surroundings of the vehicle based on the signal of the control command from the controller 1.

Next, an example of the behavior prediction method according to the first embodiment will be described with reference to the flowchart of FIG. In step S1, the controller 1 and the electroencephalograph 2 and the like are used to determine a region (electrode arrangement region) R0 for measuring the electroencephalogram of the head of the subject (driver) as shown in FIG. In step S2, the electrodes E1 to E9 are arranged in the electrode arrangement area R0 of the driver's head by attaching the electrode cap to the driver's head. In step S3, during the driver's driving operation, the electroencephalograph 2 measures the driver's electroencephalogram using the plurality of electrodes E1 to E9. In step S4, the controller 1 predicts the driver's behavior (behavioral intention) by calculating the exercise preparation potential from the electroencephalogram data measured by the electroencephalograph 2. In step S5, the controller 1 executes various driving assistance by controlling the actuator group 5 and the output device 6 based on the predicted driver behavior.

Here, an example of a method for determining the electrode arrangement region R0 (electrode arrangement method) in step S1 of FIG. 9 will be described with reference to the flowchart of FIG. In step S11, as shown in FIG. 11A, a predetermined number (for example, nine) of electrodes E1 to E9 are temporarily arranged at predetermined positions on the driver's head. The work of attaching the electrodes E1 to E9 to the electrode cap or the like and the work of attaching the electrode cap or the like may be performed manually or automatically and mechanically. For example, the electrode E5 is placed at the position of the electrode Cz defined by the international 10-20 method, and the electrodes FC3, FCz, FC4, C3, C4 defined by the international 10-20 method and the extended international 10-20 method are arranged. Electrodes E1 to E4 and E6 to E7 are arranged inside the rectangular region surrounded by CP3, CPz, and CP4.

In step S12, for example, as shown in FIG. 12, when the vehicle 201 is traveling on a road with two lanes on each side, the driver (subject) is made to perform a steering operation at the marks 202 and 203 to change lanes. Conduct an experiment to detect brain waves. The electroencephalograph 2 selects one of the nine electrodes E1 to E9, the electrode E1, and measures the driver's electroencephalogram using the electrode E1. The case is not limited to the case where the electrode E1 is selected, and other electrodes E2 to E4 and E6 to E9 may be selected. In step S13, the controller 1 calculates the amplitude of the exercise preparation potential from the electroencephalogram data measured by the electroencephalograph 2, and determines whether or not the calculated amplitude of the exercise preparation potential is equal to or greater than a predetermined threshold value. A predetermined threshold value can be appropriately set and can be stored in the storage device 12 in advance. The predetermined threshold value may be set for each of the electrodes E1 to E9, or may be set individually for each of the electrodes E1 to E9. When it is determined that the amplitude of the exercise preparation potential is equal to or greater than a predetermined threshold value, it can be determined that the brain wave to be detected has been measured correctly, so the process proceeds to step S15.

In step S15, as shown in FIG. 11B, the electrode E1 is moved and arranged so as to be separated from the intersection of the electrode E5 and the straight lines L1 and L2 in a predetermined direction by a predetermined distance. The predetermined distance and the predetermined distance can be appropriately set individually for each of the electrodes E1 to E9, and can be stored in the storage device 12 in advance. FIG. 10B illustrates a case where the electrode E1 moves diagonally away from the electrode E5 as a predetermined direction, but the present invention is not limited to this. For example, the electrode E1 may move in the front direction of the head (direction parallel to the straight line L1) or may move in the left direction of the head (direction parallel to the straight line L2). Then, returning to step S12, the driver wearing the electrode cap that has moved the electrode E1 performs the driving operation of changing lanes in the same manner, the electroencephalograph 2 measures the driver's brain wave using the electrode E1, and in step S13. The exercise preparation potential is calculated from the brain wave data. While it is determined in step S13 that the amplitude of the exercise preparation potential is equal to or greater than a predetermined threshold value, this operation is repeated to move the electrode E1 so as to expand the electrode arrangement region.

On the other hand, when it is determined in step S13 that the amplitude of the exercise preparation potential is less than a predetermined threshold value, the amplitude of the exercise preparation potential does not increase even if the electrode E1 is arranged further away, and the exercise preparation potential cannot be calculated correctly. Since it can be determined, the process proceeds to step S14. In step S14, the position of the electrode E is determined at the current position or the position before moving to the current position.

In step S16, the controller 1 determines whether or not the arrangement positions of all the electrodes E1 to E9 have been determined. It is assumed that the arrangement position of the central electrode E1 is predetermined. When it is determined that the arrangement positions of all the electrodes E1 to E9 have not been determined, the processes of steps S12 to S15 are repeated for the remaining electrodes whose arrangement positions have not been determined. For example, returning to step S12, the amplitude of the exercise preparation potential is calculated for the electrode E2. When it is determined in step S13 that the amplitude of the exercise preparation potential is equal to or greater than a predetermined threshold value, the electrode E2 is moved away from the electrode E5 in step S15 as shown in FIG. 11C. The order in which the arrangement positions of the electrodes E1 to E4 and E6 to E9 are determined is not particularly limited. For example, the electrodes E2, E3, E6, E9, E8, E7, and E4 are determined clockwise with the electrode E1 as the starting point. You may.

On the other hand, when it is determined in step S16 that the arrangement positions of all the electrodes E1 to E9 are determined, the electrode arrangement regions including all the electrodes E1 to E9 are determined, and the process is completed. As a result, the electrode arrangement region R0 shown in FIG. 6 can be set. The electrodes E1 to E9 may be arranged at fixed positions in the electrode arrangement area R0, or may be arranged at different positions within the electrode arrangement area R0. Further, the number of electrodes may be increased or decreased as compared with the electrodes E1 to E9.

As described above, according to the first embodiment, the electrode arrangement region R0 including the cranial crown of the primary motor area 101 and the supplementary motor area 102, which are the sources of the exercise preparation potential, is set, and the electrode arrangement region R0 is included. Electrodes are selectively arranged on the head, and the number of electrodes other than the electrode arrangement region R0 is reduced. This makes it possible to suppress the electrode arrangement area and the number of electrodes, reduce the measurement load, and efficiently detect the exercise preparation potential as compared with the case where 21 electrodes are arranged according to the international 10-20 method. Therefore, the behavior of the driver can be appropriately predicted, and when the behavior is predicted, various information can be provided to the driver and driving support can be executed.

Further, by arranging the electrodes E4 and E6 symmetrically from the central portion of the primary motor cortex 101, the motor preparation potential can be efficiently detected. Further, by arranging the electrodes E1 and E3 symmetrically from the center of the supplementary motor area 102, the motor preparation potential can be efficiently detected. Furthermore, by arranging the electrode FCz also in the center of the frontal region, the exercise preparation potential can be efficiently detected.

Further, when determining the electrode arrangement region R0, the electrodes E1 to E9 are temporarily arranged to detect the amplitude of the exercise preparation potential, determine whether or not the detected amplitude of the exercise preparation potential is equal to or greater than the threshold value, and determine the threshold value. When the above is determined, the electrodes E1 to E9 are moved so as to expand the electrode arrangement area, and when it is determined to be less than the threshold value, the positions of the electrodes E1 to E9 are determined to appropriately determine the electrode arrangement area. can do.

(Second Embodiment)
Since the behavior prediction device according to the second embodiment of the present invention has the same configuration as the behavior prediction device according to the first embodiment shown in FIG. 1, duplicate description will be omitted. In the second embodiment, as an experiment for optimizing the electrode arrangement, the electrode arrangement pattern is changed to calculate the prediction accuracy (correct answer rate), which is the ratio at which the behavior of the subject (driver) can be predicted. Then, the electrodes are arranged using this.

13A to 13H show electrode arrangement patterns A to H, respectively. In the electrode arrangement pattern A shown in FIG. 13A, one electrode E1 is arranged at the position of the electrode Cz defined by the international 10-20 method. The electrode arrangement pattern B shown in FIG. 13B has three electrodes E1 to E3, and the electrodes E1 and E3 are arranged on a straight line L2 with the electrode E2 on the crown sandwiched therein. Electrodes E1 to E3 are located at electrodes C1, Cz, and C2 as defined by the international 10-20 method and the extended international 10-20 method. In the electrode arrangement pattern C shown in FIG. 13C, three electrodes E4 to E6 are further arranged behind the electrodes E1 to E3 with respect to the electrode arrangement pattern B shown in FIG. 13B. The electrodes E4 to E6 are located at electrodes CP1, CPz, and CP2 defined by the international 10-20 method and the extended international 10-20 method. In the electrode arrangement pattern D shown in FIG. 13D, three electrodes E4 to E6 are further arranged in front of the electrodes E1 to E3 with respect to the electrode arrangement pattern B shown in FIG. 13B. The electrodes E4 to E6 are located at the electrodes FC1, FCz, FC2 defined by the international 10-20 method and the extended international 10-20 method.

In the electrode arrangement pattern E shown in FIG. 13E, three electrodes E7 to E9 are further arranged behind the electrodes E1 to E3 with respect to the electrode arrangement pattern D shown in FIG. 13D. In the electrode arrangement pattern F shown in FIG. 13F, the front electrodes E4 and E6 and the rear electrodes E7 and E9 are arranged away from the straight line L1 with respect to the electrode arrangement pattern E shown in FIG. 13E. Electrodes E4, E6, E7, E9 are located at electrodes FC3, FC4, CP3, CP4 defined by the International 10-20 Act and the Extended International 10-20 Act.

In the electrode arrangement pattern G shown in FIG. 13G, the electrodes E1 and E3 on the straight line L2 are arranged away from the straight line L1 with respect to the electrode arrangement pattern F shown in FIG. 13F. Electrodes E1, E3 are located at electrodes C3 and C4 as defined by the International 10-20 Act. In the electrode arrangement pattern H shown in FIG. 13H, two electrodes E10 and E11 are further arranged between the electrodes E1 and E2 and between the electrodes E2 and E3 with respect to the electrode arrangement pattern G shown in FIG. 13G. .. The electrodes E1, E10, E11, and E3 are arranged symmetrically from the center of the primary motor cortex 101. The electrodes E4 and E6 are arranged symmetrically from the center of the supplementary motor area 102. The electrode E5 is located in the center of the frontal region.

In FIG. 14, in the case of the electrode arrangement patterns A to H shown in FIGS. 13A to 13H, a behavior prediction experiment such as a lane change shown in FIG. 12 was performed, and the correct answer rate (TPR) capable of predicting the behavior which is the experimental result. ) Is shown. The vertical solid line is the earliest timing variation in the experimental example for multiple subjects (for example, a plot of the correct answer example at the earliest timing when the exercise preparation potential of changing lanes could be calculated), and the solid line curve is the correct answer. Shows the average value of the rate. The vertical dashed line is the highest accuracy variation in the experimental example for multiple subjects (for example, a plot of the correct answer example that could reliably calculate the exercise preparation potential of changing lanes), and the dashed line curve is the average of the correct answer rate. Indicates a value. As shown in FIG. 14, it can be seen that the correct answer rate (prediction accuracy) improves as the number of electrodes and the electrode arrangement region increase from the electrode arrangement pattern A to the electrode arrangement pattern H.

15A to 15N show electrode arrangement patterns a to n, respectively. The electrode arrangement pattern a shown in FIG. 15A has nine electrodes E1 to E9, three electrodes E4 to E6 are arranged in front of the three electrodes E1 to E3, and three electrodes E7 to E7 are arranged behind the three electrodes E4 to E3. E9 is placed. Electrodes E1 to E9 are located at electrodes C1, Cz, C2, FC3, FCz, FC4, CP3, CPz, CP4 defined by the international 10-20 method and the extended international 10-20 method. In the electrode arrangement pattern b shown in FIG. 15B, the electrodes E1 and E3 are arranged on the left and right sides of the electrode arrangement pattern a shown in FIG. 15A. Electrodes E1 and E3 are located at electrodes C3 and C4 as defined by the International 10-20 Act. In the electrode arrangement pattern c shown in FIG. 15C, the electrode E10 is further arranged between the electrodes E1 and E2, and the electrode E11 is further arranged between the electrodes E2 and E3 with respect to the electrode arrangement pattern b shown in FIG. 15B. There is.

In the electrode arrangement pattern d shown in FIG. 15D, the electrodes E1 and E2 are arranged symmetrically with the straight line L1 interposed therebetween, the electrodes E3 and E4 are arranged in front of the electrodes E1 and E2, and the electrodes E5 and E6 are arranged behind the electrodes E1 and E2. ing. The electrode E7 is arranged on the straight line L1 in front of the electrodes E3 and E4. The electrodes E1 to E7 are located at the electrodes C1, CC2, FC1, FC2, CP1, CP2, Fz defined by the international 10-20 method and the extended international 10-20 method. In the electrode arrangement pattern e shown in FIG. 15E, the electrode E8 is further arranged on the straight line L1 behind the electrodes E5 and E6 with respect to the electrode arrangement pattern d shown in FIG. 15D. Electrode E8 is located at electrode Pz as defined by the International 10-20 Act. In the electrode arrangement pattern f shown in FIG. 15F, the electrode E9 is further arranged at the intersection of the straight lines L1 and L2 with respect to the electrode arrangement pattern e shown in FIG. 15E.

In the electrode arrangement pattern g shown in FIG. 15G, the electrode E1 is arranged at the intersection of the straight lines L1 and L2, the electrodes E2 and E3 are arranged symmetrically with the straight line L1 in front of the electrode E1, and the electrodes E4 and E5 are arranged rearward. Is placed. The electrode E6 is arranged on the straight line L1 in front of the electrodes E2 and E3. In the electrode arrangement pattern h shown in FIG. 15H, the electrode E7 is further arranged on the straight line L1 behind the electrodes E4 and E5 with respect to the electrode arrangement pattern g shown in FIG. 15G. In the electrode arrangement pattern i shown in FIG. 15I, the electrode E1 is arranged at the intersection of the straight lines L1 and L2, and the electrode E2 is arranged on the right side of the electrode E1. The electrodes E4 and E7 are arranged in front of the electrode E1, and the electrode E3 is arranged on the left side of the electrode E4. The electrode E6 is arranged behind the electrode E1, and the electrode E5 is arranged on the left side of the electrode E6.

In the electrode arrangement pattern j shown in FIG. 15J, the electrode E1 is arranged at the intersection of the straight lines L1 and L2, the electrodes E2 and E3 are arranged on the straight line L1 in front of the electrode E1, and the electrodes E4 and E5 are arranged on the straight line L1 behind. Have been placed. That is, five electrodes E1 to E5 are arranged on the straight line L1. The electrodes E1 to E5 are located at the electrodes Cz, FCz, Fz, CPz, Pz defined by the international 10-20 method and the extended international 10-20 method. In the electrode arrangement pattern k shown in FIG. 15K, the electrodes E6 and E7 are arranged on the left side of the electrodes E2 and E4, and the electrodes E8 to E10 are arranged on the right side of the electrodes E3, E1 and E5 with respect to the electrode arrangement pattern j shown in FIG. 15J. Are further arranged. In the electrode arrangement pattern l shown in FIG. 15L, the electrodes E6 to E8 are arranged on the left side of the electrodes E3, E1 and E5, and the electrodes E9 and E10 are arranged on the right side of the electrodes E2 and E4 with respect to the electrode arrangement pattern j shown in FIG. 15J. Are further arranged.

In the electrode arrangement pattern m shown in FIG. 15M, the electrode E11 is arranged on the right side of the electrode E1 and the electrodes E12 and E13 are further arranged on the left side of the electrodes E2 and E4 with respect to the electrode arrangement pattern l shown in FIG. 15L. .. In the electrode arrangement pattern n shown in FIG. 15N, the electrodes E9, E10, and E11 are arranged on the right side of the electrodes E2, E3, and E4 with respect to the electrode arrangement pattern j shown in FIG. Electrodes E6, E7 and E8 are further arranged.

In FIG. 16, in the case of the electrode arrangement patterns a to n shown in FIGS. 15A to 15N, a behavior prediction experiment such as a lane change shown in FIG. 12 was performed, and the correct answer rate was such that the behavior as an experimental result could be predicted. Show the relationship. In FIG. 16, it can be seen that the prediction accuracy is lowered if there is no electrode in the central portion as in the electrode arrangement patterns d and e. Further, it can be seen that the prediction accuracy is lowered when the number of electrodes in the central portion is small as in the electrode arrangement patterns f, g, and h. Further, it can be seen that the prediction accuracy is lowered when the electrodes are located only in the central portion as in the electrode arrangement pattern j. Therefore, it is preferable that there are many electrodes in the central portion and the electrodes are arranged not only in the central portion but also in the peripheral portion as in the electrode arrangement patterns a, b, c, i, k, l, m, and n. ..

The behavior prediction method according to the second embodiment is the same as the behavior prediction method according to the first embodiment shown in FIG. The electrode arrangement method according to the second embodiment corresponding to step S1 shown in FIG. 9 will be described with reference to the flowchart of FIG.

In step S21, for example, as shown in FIG. 18A, an initial electrode arrangement region R1 is set on the head of the driver (subject), and a predetermined number of electrodes E1 to E9 are temporarily arranged in the electrode arrangement region R1. In step S22, electrodes E1 to E9 are attached to the head as shown in FIG. 18A, an experiment is performed in which the driver changes lanes as shown in FIG. 12, and the electroencephalograph 2 measures the driver's brain waves. In step S23, the controller 1 can correctly calculate the action preparation potential by calculating the action preparation potential from the electroencephalogram data measured by the electroencephalograph 2 and comparing the amplitude of the action preparation potential with a predetermined threshold value. Determine if. This experiment is repeated a plurality of times while changing the driver as necessary, and the controller 1 calculates the correct answer rate (first prediction accuracy), which is the ratio at which the action preparation potential can be calculated correctly. The calculated correct answer rate is stored in the storage device 12. The calculation result of the action preparation potential obtained by repeating the experiment a plurality of times is stored in the storage device 12 in advance, and the controller 1 reads the calculation result of the action preparation potential from the storage device 12 to calculate the correct answer rate. May be good.

In step S24, as shown in FIG. 18B, the surrounding electrodes E1 to E4 and E6 to E9 are arranged so as to be separated from the central electrode E5 by a predetermined distance in a predetermined direction, and the electrodes E1 to E9 are included. The electrode arrangement region R2 is enlarged. A predetermined direction and a predetermined distance for moving the electrodes E1 to E4 and E6 to E9 can be individually set as appropriate, and can be stored in the storage device 12 in advance. For example, by moving the electrodes E1 and E7 to the left and moving the electrodes E3 and E9 to the right without moving the electrodes E2 and E8, a rectangular pattern similar to the electrode arrangement pattern G shown in FIG. 13G is obtained. May be.

In step S25, electrodes E1 to E9 are attached as shown in FIG. 18B, an experiment is performed in which the driver changes lanes as shown in FIG. 12, and the electroencephalograph 2 measures the driver's brain waves. In step S26, the controller 1 can correctly calculate the action preparation potential by calculating the action preparation potential from the electroencephalogram data measured by the electroencephalograph 2 and comparing the amplitude of the action preparation potential with a predetermined threshold value. Determine if. This experiment is repeated a plurality of times while changing the driver as necessary, and the controller 1 calculates the correct answer rate (second prediction accuracy), which is the ratio at which the action preparation potential can be calculated correctly. The calculated correct answer rate is stored in the storage device 12. The calculation result of the action preparation potential obtained by repeating the experiment a plurality of times is stored in the storage device 12 in advance, and the controller 1 reads the calculation result of the action preparation potential from the storage device 12 to calculate the correct answer rate. May be good.

In step S27, the controller 1 reads out the correct answer rate (first prediction accuracy) acquired in step S23 and the correct answer rate (second prediction accuracy) acquired in step S26, and the electrode arrangement regions R1 and R2 before and after expansion. Calculate the difference value of the correct answer rate in the case of. In step S28, the controller 1 determines whether or not the difference value of the correct answer rate is equal to or greater than a predetermined threshold value. A predetermined threshold value can be appropriately set and can be stored in the storage device 12 in advance. When it is determined that the difference value of the correct answer rate is equal to or greater than a predetermined threshold value, it can be determined that the prediction accuracy is effectively improved by expanding the electrode arrangement region R2. Therefore, the process returns to step S24, and the electrode arrangement region R2 is further expanded to perform the same operation.

On the other hand, when it is determined in step S28 that the difference value of the correct answer rate is less than a predetermined threshold value, it can be determined that the prediction accuracy is not effectively improved even if the electrode arrangement region R2 is further expanded, so the process proceeds to step S29. do. In step S29, the controller 1 is determined in the current electrode arrangement area R2 or the previous electrode arrangement area R1.

As described above, according to the second embodiment, there are a plurality of electrode placement regions within a certain distance including the cranial crown of the primary motor area 101 and the supplementary motor area 102, which are the sources of the exercise preparation potential. By selectively arranging the electrodes of, the measurement site of the brain wave and the number of electrodes are suppressed compared to the case where 21 electrodes are arranged according to the international 10-20 method, the measurement load is reduced, and the exercise preparation potential is made more efficient. Can be calculated. Therefore, the behavior of the driver can be appropriately predicted, and when the behavior is predicted, various information can be provided to the driver and driving support can be executed.

Further, for example, as shown in FIG. 13H, by arranging the electrodes E1, E10, E11, and E3 symmetrically from the central portion of the primary motor cortex 101, the motor preparation potential can be efficiently detected. Further, by arranging the electrodes E4 and E6 symmetrically from the center of the supplementary motor area 102, the motor preparation potential can be efficiently detected. Furthermore, by arranging the electrode E5 at the center of the frontal region, the exercise preparation potential can be efficiently detected.

Further, when determining the electrode arrangement region, the electrode arrangement area is determined within a range in which the improvement rate of the behavior prediction accuracy does not decrease by a certain amount or more when the electrode arrangement area is expanded. That is, the first prediction accuracy that can predict the behavior by using the plurality of temporarily arranged electrodes is acquired. Further, the range of the plurality of temporarily arranged electrodes is expanded, and the second prediction accuracy capable of predicting the behavior using the plurality of electrodes in the expanded range is acquired. Then, it is determined whether or not the difference value of the first and second prediction accuracy is equal to or greater than the threshold value, and when it is determined to be equal to or greater than the threshold value, the electrode arrangement region is expanded. On the other hand, when it is determined that the difference value between the first and second prediction accuracy is less than the threshold value, the electrode arrangement region is determined. Thereby, the electrode arrangement region can be appropriately determined.

(Other embodiments)
As mentioned above, the present invention has been described by the first and second embodiments, but the statements and drawings that form part of this disclosure should not be understood as limiting the invention. Various alternative embodiments, examples and operational techniques will be apparent to those skilled in the art from this disclosure.

For example, the procedure of the flowchart of the electrode arrangement method shown in FIG. 19 may be applied. In step S31, the electrodes E1 to E9 are temporarily arranged as shown in FIG. 8A. In step S32, the electroencephalograph 2 measures the electroencephalogram using each of the electrodes E1 to E9 shown in FIG. 8A, and detects the amplitude of the exercise preparation potential for each of the electrodes E1 to E9. In step S33, the controller 1 determines whether or not the amplitude of the exercise preparation potential for each of the electrodes E1 to E9 is equal to or greater than a predetermined threshold value. When it is determined that all the amplitudes of the exercise preparation potentials for each of the electrodes E1 to E9 are equal to or higher than a predetermined threshold value, the process proceeds to step S35. In step S35, the electrode arrangement region is expanded by moving the electrodes E1 to E4 and E6 to E9 as shown in FIG. 18B, instead of moving one electrode E1 as shown in FIG. 8B. On the other hand, if it is determined in step S33 that any one or more of the amplitudes of the exercise preparation potentials for each of the electrodes E1 to E9 is less than the threshold value, the process proceeds to step S34, and the current electrode arrangement area or the previous electrode arrangement area is determined. Confirm with. As described above, the electrode arrangement region can be appropriately determined also in the procedure of the flowchart of the electrode arrangement method shown in FIG.

Further, the behavior prediction device and the behavior prediction method according to the first and second embodiments have been illustrated as being applied to the prediction of the behavior of the driver of the vehicle, but the present invention is not particularly limited thereto. For example, it can be applied as a brain machine interface (BMI) for predicting the behavior of various human beings such as occupants other than the driver of a vehicle, occupants of a ship or aircraft, robot operators, game players, and the like. can.

It goes without saying that the present invention includes various embodiments not described here. Therefore, the technical scope of the present invention is defined only by the matters specifying the invention relating to the reasonable claims from the above description.

1 ... Controller 2 ... Brain wave meter 3 ... Running state sensor group 4 ... Ambient condition sensor group 5 ... Actuator group 6 ... Output device 11 ... Processor 12 ... Storage device 21 ... Electrode group 22 ... Amplifier 23 ... Filter 24 ... A / D conversion Instrument 31 ... Vehicle speed sensor 32 ... Accelerator opening sensor 33 ... Brake switch 34 ... Steering operation amount sensor 35 ... Winker switch 41 ... Camera 42 ... Radar 43 ... Map DB
44 ... GPS receiver 51 ... Accelerator opening actuator 52 ... Brake control actuator 53 ... Steering actuator 61 ... Display 62 ... Buzzer 100 ... Brain 101 ... Primary motor area 102 ... Supplementary motor area 103 ... Central groove 201 ... Vehicles 202, 203 ... Marks E1 to E13 ... Electrodes R0, R1, R2 ... Electrode placement area

Claims (7)

Multiple electrodes were placed on the human head only in the area including the cranial parietal surface of the primary motor area and the supplementary motor area.
The human brain wave is measured using the potential difference signals of the plurality of electrodes, and the human brain wave is measured.
A behavior prediction method characterized in that an exercise preparation potential is calculated from the measured electroencephalogram to predict the human behavior. The behavior prediction method according to claim 1, wherein at least a part of the plurality of electrodes is symmetrically arranged from the central portion of the primary motor cortex. The behavior prediction method according to claim 1 or 2, wherein at least a part of the plurality of electrodes is symmetrically arranged from the central portion of the supplementary motor area. The behavior prediction method according to any one of claims 1 to 3, wherein at least a part of the plurality of electrodes is arranged at the center of the human frontal region. Multiple electrodes were placed on the human head only in the area including the cranial parietal surface of the primary motor area and the supplementary motor area.
The human brain wave was measured using the plurality of electrodes, and the human brain wave was measured.
In the behavior prediction method for predicting human behavior by calculating the exercise preparation potential from the measured brain waves.
Calculate the amplitude of the exercise preparation potential,
It is determined whether or not the calculated amplitude is equal to or greater than the threshold value.
When it is determined that the threshold value is equal to or higher than the threshold value, the area is expanded.
Behavior prediction how to said determining said region when it is determined to be less than the threshold value. Multiple electrodes were placed on the human head only in the area including the cranial parietal surface of the primary motor area and the supplementary motor area.
The human brain wave was measured using the plurality of electrodes, and the human brain wave was measured.
In the behavior prediction method for predicting human behavior by calculating the exercise preparation potential from the measured brain waves.
The plurality of electrodes are temporarily arranged on the head, and the plurality of electrodes are temporarily arranged.
Obtaining the first prediction accuracy that could predict the behavior using the plurality of temporarily arranged electrodes,
The range of the plurality of temporarily arranged electrodes is expanded, and the range is expanded.
Obtaining a second prediction accuracy that could predict the behavior using the plurality of electrodes in the expanded range,
It is determined whether or not the difference value of the first and second prediction accuracy is equal to or greater than the threshold value.
When it is determined that the threshold value is equal to or higher than the threshold value, the area is expanded.
Behavior prediction how to said determining said region when it is determined to be less than the threshold value. An electroencephalograph that measures the human brain wave using the potential difference signals of a plurality of electrodes arranged on the human head only in the area including the cranial parietal surface of the primary motor area and the supplementary motor area.
A behavior prediction device including a controller that calculates an exercise preparation potential from the measured electroencephalogram and predicts the human behavior.

Images