Activation of a direct neural interface

Abstract

A method is proposed for activating a direct neural interface (DNI), available to a given user (UT) to control at least one machine. The method comprises: activating (DNI-i ON) a direct neural interface (DNI-i) associated with a mental state detected based on an analysis of a brain signal (SIG.CER.) captured (CAP) repeatedly to control at least said machine via the direct neural interface. Abstract: Figure 4

Description

Title of the invention: Activation of a direct neural interface technical field

[0001] This disclosure falls within the domain of direct neural interfaces (or BCI hereinafter, for "Brain Computer Interface"). Previous technique

[0002] The principle of such BCI interfaces, known as "reactive" interfaces, is based on: - the emission of a stimulus (auditory, visual, or tactile), intended for a user, this stimulus being emitted by a transducer powered by a signal having a modulation frequency chosen for example between 1 and 200Hz, and - in return to the perception of this stimulus by the user, the detection of evoked potentials in an electroencephalogram signal (called "EEG signal" below) in which the aforementioned modulation frequency is found.

[0003] Thus, in the context of a reactive BCI interface, the term "evoked potential" hereafter refers to a signal that appears in electroencephalogram (EEG) signals when a user is exposed to a stimulus. For example, in the SSAEP (Steady-State Auditory Evoked Potential) approach, the stimulus consists of a signal, particularly an auditory or visual signal, having a carrier frequency and to which an amplitude modulation is applied, which can be sinusoidal or square wave (in the form of regular "beeps"). With reference to [Fig. 1], equipment such as a headset with EEG signal sensors makes it possible to measure the EEG signals and to identify the modulation frequency within these signals.

[0004] An example of a stimulus used for an SSAEP application could be a sinusoidal function at a frequency audible to all (for example, from 20 Hz to 20 kHz), and amplitude-modulated at another frequency, for example, between 1 and 200 Hz. The high-frequency sine wave constitutes the carrier wave and allows a user to simply hear the "beeps" of the low-frequency modulating signal. It is the modulating signal that constitutes the information of interest, since it is the modulation frequency that is found in the evoked potential.

[0005] Indeed, it is possible to find stimulation frequencies between approximately 1 and 200 Hz in dedicated areas of the brain, particularly auditory or visual ones. However, at this frequency range of 1 to 200 Hz, these frequencies are low and can be difficult to reproduce and / or hear. This is why a carrier frequency is used as a vector, allowing the user to hear these frequencies more easily. A stimulus (a low-frequency modulating sine wave of the 1 to 200 Hz type) can then generate a measurable evoked potential in the brain at the same frequency. Low frequency, from 1 to 200 Hz (plus any harmonics). This frequency is then measurable in the EEG signals of the person subjected to the stimulus. Therefore, the low-frequency modulation (1 to 200 Hz) can be found in the user's EEG signals.

[0006] Therefore, it is possible to construct an interface by directly searching for the interface signal in the user's brainwaves. The principle of such an interface, called a "BCI" (for "Brain-Computer Interface"), is illustrated in [Fig. 1]. A UT user wears a headset equipped with electroencephalogram (EEG) signal sensors, this headset being part of a general BCI interface. Various stimuli (auditory, visual, or other), each with its own modulation frequency, are delivered to the user, who then focuses on a single stimulus among those presented. The same modulation frequency as that of the stimulus on which the user focused can then be measured in their EEG signals.

[0007] In the example illustrated in [Fig. 1], several stimuli from respective sources HP1, HP2, HP3, having different modulation frequencies and representing, for example, different respective instructions for operating a machine (e.g., "turn left," "turn right," "brake"), are presented simultaneously to a user. The user concentrates on one of them so that their EEG signals reveal the frequency of one of the stimuli HP1, and the function associated with this stimulus is then executed by the machine. In the example of [Fig. 1], the stimuli are delivered by respective loudspeakers HP1, HP2, HP3... and the user then concentrates on one of these sound sources. The stimulus is therefore auditory.

[0008] In the example of a stimulus delivered by a light source, the latter may blink at the aforementioned modulation frequency. An analysis of the user's EEG signals reveals the presence of a frequency corresponding to the blinking frequency. For example, the light source may have a particular color, thus corresponding to a wavelength LO associated with a carrier frequency fp by a relationship of the type LO = c / fp, where c is the speed of light. Some users may be more sensitive to certain colors than others to capture their attention. Thus, the choice of color (and therefore of the carrier frequency fp) can be important, particularly at certain times of day for the same user, to efficiently collect EEG signals revealing a usable evoked potential (i.e., having a frequency corresponding to the modulation or "blinking" frequency of the light source).For example, a wavelength of 0.5pm can be used for blue as the color of visual stimuli in some subjects, or a wavelength of 0.55pm for green to which some users are more sensitive, or 0.65pm for red, a color to which other users are even more sensitive, etc.

[0009] Thus, a direct neural interface, or "DNI," can be used as a human-machine interface, ensuring direct communication between the brain and an external device, such as a computer. Through their brainwaves, a user can then remotely control a device. DNIs can be classified according to their mode of operation: they can be active, reactive, or passive.

[0010] An "active" BCI requires the user to voluntarily produce a brain signal to control an external device. The user voluntarily produces a brain signal by thinking about and / or imagining an object, an action, or something else, using at least one of their senses, i.e. by visualizing a word, a shape, a gesture, or something else, or by imagining the sensation of a manipulation or listening, for example by imagining a movement.

[0011] A so-called "reactive" BCI detects, in the brain, a signal triggered by an external stimulus, for example a flashing light or a sound with particular characteristics, and uses it to control a device, as described above with reference to [Fig.1].

[0012] A so-called "passive" BCI analyzes the user's spontaneous brain activity, without external stimulus or particular intention, which makes it possible to obtain data on their mental state (stress, concentration, fatigue, etc.).

[0013] When a user wishes to activate / initiate a reactive BCI, of the type shown above with reference to [Fig. 1], they are forced to use another method, for example, a computer mouse or keyboard, or a physical button. This can be complicated if the user's hands are not available (occupied with another task, for example) or if the user is a person with reduced mobility.

[0014] Furthermore, the stimuli emitted by a reactive IBC are stressful for the user, who may then experience fatigue or even aggression from these stimuli if they do not need to use the IBC regularly. Moreover, the emission of such stimuli consumes energy. By concentrating on a stimulus aimed at turning off / deactivating the IBC interface, the emission of these stimuli can cease. However, if the user then wants to use the IBC again, there is no means other than a physical one (push button or computer mouse) to reactivate the IBC, which poses a further problem if the user's hands are unavailable or if the user has reduced mobility. Summary

[0015] This disclosure improves the situation.

[0016] A method is proposed for activating a direct neural interface, available to a given user to control at least one machine, the method comprising: - activate a direct neural interface associated with a mental situation detected based on an analysis of a brain signal captured repeatedly to control at least said machine via the direct neural interface.

[0017] This solution then proposes to activate, or initiate, a BCI via the detection of a specific brain signal without needing to have another modality (physical button, computer mouse, or other).

[0018] In an embodiment, the process may include: - detect, based on the analysis of the brain signal captured repeatedly, whether the user is in a predefined mental state, the direct neural interface being activated in response to this detection of said predefined mental state.

[0019] The term "mental situation" of the user means both a situation where the user imagines moving a limb (the left arm, or the right leg), and a mental situation linked to a current state of the user (for example, stress, wakefulness, or others).

[0020] In an embodiment, the process may include: - analyze said brain signal of the user, measured repeatedly by at least one sensor.

[0021] Such a sensor can be placed near an appropriate region of the brain to measure the signal specific to the aforementioned mental situation.

[0022] For example, the detection of this specific brain signal can be achieved using a different IBC than the interface used to control the aforementioned machine. This could involve, for instance, activating / initiating a reactive IBC of the type described above with reference to [Fig. 1], based on a detection carried out by an active IBC (following the user's thought of a gesture, an object, or other) or by a passive IBC (following the user's experience of stress, awakening from drowsiness, or other specific mental states). Alternatively, it could involve activating / initiating an active IBC (controlling a machine through the user's thought of a gesture, an object, or other) based on a detection carried out by an active IBC or a passive IBC (following the user's experience of stress, awakening from drowsiness, or other).Thus, the same BCI interface, of the "active" type in this case, can both detect the specific brain signal, related to the user's current mental state, and control the aforementioned machine (by the user's thought of a gesture, an object or other).

[0023] Thus, in one embodiment, the direct neural interface associated with said mental state for controlling the machine can be one of the following direct neural interfaces: - a reactive direct neural interface; and - an active direct neural interface.

[0024] The term “direct reactive neural interface” means an interface which may be visual, auditory, or otherwise, emitting stimuli modulated at respective frequencies, as presented above with reference to [Fig. 1].

[0025] An "active direct neural interface" is defined as an interface that allows the user to control a machine by thought. For example, thinking about raising the left arm causes the volume of a device to increase, while thinking about raising the right arm causes the volume to decrease.

[0026] Furthermore, in one embodiment, the user's brain signal can be measured by a direct neural interface among the following: - a passive direct neural interface; and - an active direct neural interface.

[0027] It is recalled that a "passive" interface can detect a particular mental situation such as a situation of stress, or of awakening after drowsiness, or others, and that an "active" interface makes it possible to detect that the user is thinking about moving a limb (for example raising the left arm) and this thought can then cause the activation of a reactive BCI for example.

[0028] In one embodiment, the analysis of the brain signal may include a comparison of the measured brain signal to at least one predefined signal corresponding to said predefined mental state.

[0029] This may involve, for example, comparing the time and / or frequency profile of the measured signal to a typical profile associated with this predefined situation.

[0030] In one embodiment, the analysis of the brain signal may, more particularly, include a comparison of the measured brain signal to a plurality of predefined signals, each corresponding to: - to a predefined mental state of the user, and - to a direct neural interface to be activated.

[0031] Thus, depending on the mental situation detected via the analysis of the measured signal, it is possible to activate a specific BCI interface corresponding to the detected mental situation (for example, a detected stress that can generate a BCI interface requesting assistance).

[0032] In one embodiment, predefined signal data are stored in a database corresponding to respective identifiers of direct neural interfaces to be activated.

[0033] Thus, in such an embodiment, it is possible to compare in parallel or in turn (with an order of priority for example for emergency situations) the base signals with the measured brain signal and to activate the BCI interface corresponding to the base signal closest to the measured signal for example.

[0034] In one embodiment, the method may include learning a predefined temporal signal profile, at least for the aforementioned user, and (in a typical inference phase) searching for this temporal profile in the brain signal measured on the user.

[0035] The aforementioned learning can typically be achieved by training an artificial intelligence, for example on the user (at different times of a day, for example) or alternatively on a group of users.

[0036] According to another aspect, a computer program is proposed comprising instructions for implementing all or part of a process as defined herein when this program is executed by a processor. According to another aspect, a non-transient, computer-readable recording medium is proposed on which such a program is recorded.

[0037] According to another aspect, a computer device is proposed, for activating a direct neural interface, available to a given user to control at least one machine, the device comprising a processing circuit for implementing the above process.

[0038] According to yet another aspect, a direct neural interface equipment is proposed, available to a given user to control at least one machine, comprising an activator of the direct neural interface associated with a mental situation detected according to a result provided by an analyzer of a brain signal captured recurrently to control said at least one machine via said direct neural interface.

[0039] In one embodiment, the activator of this equipment may be a computer device as defined above.

[0040] In an embodiment, the equipment may include: - one or more sensors of the direct neural interface, and - one or more sensors for measuring said brain signal, in the same headset intended to be worn by the user.

[0041] In an embodiment where the direct neural interface is reactive and visual stimuli, the equipment may then include a computer screen configured to display respective command icons of the aforementioned machine, these icons flashing at respective frequencies, and a screen page containing these icons may then be displayed on the screen, upon activation of said direct neural interface (i.e. upon detection of the brain signal corresponding to the predefined mental situation).

[0042] In one embodiment, the equipment may include a brain signal analyzer configured to compare the measured brain signal to a plurality of predefined signals, each corresponding to a direct neural interface to be activated, each Direct neural interfaces are reactive and respond to visual stimuli. Thus, the computer screen can be configured to display a screen page specific to a direct neural interface to be activated (following the detection of the mental state associated with that screen page).

[0043] Such a screen can be, for example, a computer tablet capable of displaying a page selected from several possible screen pages of different BCI interfaces, depending on the detected mental state. Brief description of the drawings

[0044] Other features, details and advantages will become apparent from the detailed description below and from the analysis of the accompanying drawings, in which, in addition to [Fig. 1] discussed above: Fig. 2

[0045] [Fig.2] shows examples of brain signals that can be detected by a or several sensors, for example of a passive BCI interface according to one embodiment. Fig. 3

[0046] [Fig.3] shows the steps of a process of the above type, according to an example of realization. Fig. 4

[0047] [Fig.4] schematically shows a device for implementing the following process before, according to an example of implementation. Description of the implementation methods

[0048] The proposed solution consists of activating, or initiating, an active and / or reactive BCI by means of a detection carried out by a passive BCI, or by means of a detection carried out by an active BCI to activate / initiate a reactive BCI of the type described previously with reference to [Fig.1].

[0049] Detection by a passive BCI, for example, can be achieved through metrics presented by the brain signals of users subjected to situations such as a given level of concentration, or stress, fatigue, or a state of drowsiness or wakefulness.

[0050] A passive BCI typically detects when a person wakes up and thus automatically initiates the possibility for a user to interact with a machine via an active or reactive BCI. A passive BCI interface may include one or more sensors that continuously monitor a user's brain to detect a specific signal and, following this detection, activate an active or reactive BCI.

[0051] For example, in the case of using an active BCI, the user can also, for example, imagine moving his left hand (which is detected by the active BCI) and then trigger the switching on of lights or a television via a reactive BCI.

[0052] In another possible embodiment, distinctive "Error-Related Negativity" type signals may appear in a user's EEG signals when they become aware that they have made an error. The detection of such a signal can trigger the activation of an active or reactive BCI. For example, if the user is routinely performing a task and makes an error at some point, a BCI can be activated to allow them to correct this error. Thus, a technician, equipped with a mixed BCI as described herein, may injure themselves, rendering them unable to interact with their arms. This situation generates a measurable Error-Related Negativity type brain signal in their brain.The mixed BCI interface detects this signal and allows it, for example, to initiate emergency communication via an active BCI (imagine a gesture that triggers a call) or a reactive BCI (the detection of the aforementioned signal triggering the generation of stimuli necessary for the implementation of the reactive BCI).

[0053] With reference to [Fig. 2], a first type of signal Sl(t) that can be detected could be, for example, a transition from drowsiness to wakefulness. To this end, one or more sensors judiciously positioned near relevant areas of the brain can measure brain waves for the same user, or for a group of users, who is or are in such a transition from drowsiness to wakefulness. From this, an average temporal profile of this brain signal Sl(t) can be deduced, this average profile being denoted Sm in [Fig. 2].

[0054] Data from this average profile Sm can be stored in memory, with selected standard deviations of amplitudes (one, two, or three times sigma, depending on the noise level of the brain signal to be measured). These standard deviation curves S+ and S- are represented by dashed lines in [Fig. 2]. Thus, typically, a brain signal SIG.CER. commonly measured on a given user can be compared to this profile Sm and the corresponding standard deviations S+ and S- to determine whether that user is currently in such a state of transition from drowsiness to wakefulness. For example, the measured SIG.CER. signal can be smoothed, and it can be verified that this smoothed signal does not fall outside the defined bounds between S+ and S-. In addition, or alternatively, a Fourier transform (e.g., a time-frequency transform) can be performed to analyze the frequencies of these brain signals.

[0055] More generally, as an alternative or complement, artificial intelligence can learn the signal patterns measured during a human user's transition from a state of drowsiness to a state of wakefulness, and it can then be determined by An inference from this artificial intelligence, if the measured brain signal SIG.CER. corresponds to a transition of a given user from drowsiness to wakefulness.

[0056] At the top of [Fig. 2], a brain signal Sl(t) is illustrated, which could correspond to the transition from a state of drowsiness to a state of wakefulness. At the bottom of [Fig. 2], another type of brain signal S2(t) is illustrated, which could, for example, correspond to the onset of a stressful situation in a user. For both types of signals, it is possible, based on learned temporal profiles, to determine a current state for a given user. Thus, it is possible to distinguish several types of brain signals corresponding to different states of a user (wakefulness, stress, or others).

[0057] Sensors for example of a passive neural interface are thus able to measure such brain signals and discriminate them, so as to then activate direct neural interfaces BCI (active and / or reactive) each corresponding to a type of measured brain signal, which then makes it possible to control a machine corresponding to this measured brain signal via an appropriate BCI interface.

[0058] It is therefore possible to create a BDD database of typical brain signals SI, S2, ..., Si, corresponding to distinct user situations (wakefulness, stress, imagining raising the right arm, etc.) linked to respective IBC identifiers (active or reactive) to be activated and allowing the control of distinct machines (for example, a television, a telephone, or a signal transmitter indicating a need for assistance, etc.). These typical brain signals can then be of different types: for example, drowsiness to wakefulness to activate a home automation IBC (controlling electric blind opening, turning on lights, etc.), or a stress brain signal to activate an IBC controlling an assistance signal transmitter, etc.

[0059] Figure 3 illustrates, by way of example, a method using such a BDD database. A first step E1 consists of acquiring brain signals from a given user using continuously active sensors. Each acquired signal is compared, in step E2, to the signals in the BDD database, which was created (for example, by training an artificial intelligence) in a previous step E0. If, typically in step E3, a stressful situation in the user has been detected as corresponding to the brain signal S2, in step E4, a BCI-1 interface can be activated to control a machine in response to a request for assistance, for example.Otherwise (KO arrow at the exit of test E3), the measured signal, compared to other signals in the database, may correspond, for example, to that characterizing a state of wakefulness after drowsiness, and in this case of detection at step E5 of correspondence with this signal IF (OK arrow at the exit of test E5), a corresponding BCL2 interface may be activated at step E6, to control a machine such as by. For example, turning on a radio or television (increasing the volume, changing the station or channel, turning it off, etc.). The process can continue with a plurality of signals from the database being successively tested, and if a match is detected with one of these signals at a general step E7, a corresponding BCLi interface can be activated at step E8. The process can continuously loop back to the first step E1 of measuring the user's brain signal UT, possibly to activate a new BCI interface, depending on a user state commonly detected at step E2 and at one of the steps E3, E5, or E7.

[0060] For each of these BCLi interfaces, "buttons" (for example, computer icons) can flash at different frequencies on a control panel, for example. Thus, in an embodiment, it is possible to use, for example, the same computer screen, such as the screen of a tablet computer (reference TAB in [Fig. 4] described later), to display the icons associated with a BCI interface on the same screen page (and make these icons flash at their own frequencies on this screen) when that BCI interface is activated. Then, if another type of brain signal is detected, the screen page of the tablet TAB is simply updated with new flashing icons to activate another BCI interface following this new detection. Of course, between two detections of a specific brain signal, the tablet can be switched off and only switch on upon detection of one of these specific brain signals.

[0061] A single BCI interface can control different types of machines. It will thus be understood that, overall, functions specific to different user situations (awakeness, stress, etc.) can be grouped in the same BCI interface "page" to control one or more machines depending on a current user situation.

[0062] Furthermore, with reference now to [Fig. 4], the equipment available to the user may advantageously include a single headset carrying at least one CAP sensor to detect the brain signal triggering the activation of a BCI interface, as well as one or (in practice) several sensors to use this BCI. The CAP sensor(s) for detecting the aforementioned brain signal may be positioned near a particular region of the brain to efficiently detect this brain signal. For example, stress can be detected by measuring a CAP sensor positioned near the prefrontal cortex. A situation of Error-Related Negativity can be detected near the dorsal anterior cingulate cortex, as well as near the motor cortex. It will then be understood that several signals can be detected by sensors positioned differently.Thus, the detection of the same mental state can rely on the analysis of several brain signals measured by different sensors and / or positioned differently.

[0063] The other sensor(s) for using the BCI to control a machine are located near the area of ​​the brain that is usually used for the correct use of a BCI (for example, the auditory areas of the brain for a reactive BCI based on sound stimuli, or the vision areas for visual signals).

[0064] All or part of the steps in [Fig. 3] can be implemented by a device as illustrated in [Fig. 4], this device comprising a processing circuit equipped with: - an IN input interface to receive data from one or more CAP sensors of SIG.CER brain signals, - a MEM memory storing, in particular, instruction data from a computer program for the implementation of the above process (and possibly, for example, data from the content of the BDD database), - a PROC processor capable of accessing the MEM memory to read and execute the instructions of the aforementioned computer program, for the implementation of the process, the processor also receiving brain signal data acquired by the CAP sensors, via the IN input interface, and performing an analysis of these signals to possibly detect a current situation of the user UT (stress, wakefulness, etc.), - and an OUT output interface capable of delivering in particular an activation signal of a BCLi interface corresponding to the current situation of the user.

[0065] As previously stated, the BCLi ON activation signal can be interpreted by an input interface of a tablet computer, for example, TAB, to control the display of a screen page on the tablet by flashing (at different frequencies) icons associated with functionalities of the BCLi interface to be activated. The user UT focuses on one of these flashing icons, and the EEG signals (containing this flashing frequency) are detected by the BCI sensors of the equipment worn by the user UT and can then be analyzed to control the operation of one or more machines associated with this BCLi interface. Industrial application

[0066] The present technical solutions can be applied to all existing or future BCIs, which usually require another modality (push button, computer mouse, etc.) to be launched.

[0067] This disclosure is not limited to the forms of embodiment described above, only by way of example, but encompasses all the variants that a person skilled in the art may consider within the framework of the protection sought.

[0068] Typically, the signals measured by a BCI interface (active, reactive, or passive) can be EEG signals as described above, but alternatively also and more generally any brain signals (including MRI (magnetic resonance imaging), or functional MRI or MEG, or others).

Claims

Demands

1. Method of activating a direct neural interface (DNI-BCI), available to a given user (UT) to control at least one machine, the method comprising: - activating (E4; E6; ... E8) a direct neural interface (DNI-BCI-1; DNI-BCI-2; ... DNI-BCI-i) associated with a mental state detected based on an analysis of a brain signal captured recurrently to control at least said machine via the direct neural interface.

2. A method according to claim 1, wherein the method comprises: - detecting (E3; E5; ... E7), based on the analysis of the brain signal captured repeatedly, whether the user (UT) is in a predefined mental state, the direct neural interface being activated (E4; E5. E8) in response to this detection of said predefined mental state.

3. A method according to any one of the preceding claims, wherein the method comprises: - analyzing (E2) said user brain signal, measured repeatedly (El) by at least one sensor (CAP).

4. A method according to any one of the preceding claims, wherein the direct neural interface (BCI-1; BCI-2; ... BCI-i) associated with said mental state for controlling the machine is a direct neural interface among the following: - a reactive direct neural interface; and - an active direct neural interface.

5. A method according to any one of the preceding claims, wherein the user's brain signal is measured by a direct neural interface among the following: - a passive direct neural interface; and - an active direct neural interface.

6. A method according to any one of the preceding claims, wherein the brain signal analysis comprises a comparison (E2) of the measured brain signal (SIG.CER.) among the following comparisons: - a comparison (E2) of the measured brain signal (SIG.CER.) to at least one predefined signal (SI, S2, ... Si) corresponding to said predefined mental state; and - a comparison (E2) of the measured brain signal (SIG.CER.) to a plurality of predefined signals (SI, S2, ... Si) each corresponding: * to a predefined mental state of the user, and * to a direct neural interface (BCI-1; BCI-2; ... BCI-i) to be activated.

7. A method according to claim 6, wherein predefined signal data are stored in a database corresponding to respective identifiers of direct neural interfaces (BCI-1; BCI-2; ... BCI-i) to be activated.

8. A method according to any one of claims 6 or 7, comprising learning a predefined signal time profile (S1(t), S2(t)), at least for said user, and searching for said time profile in the brain signal measured on the user.

9. A computer program comprising instructions for carrying out the method according to any one of the preceding claims, when executed by a processor.

10. Computer device, for activating a direct neural interface (BCI-i), available to a given user (UT) to control at least one machine, the device comprising a processing circuit for implementing the method according to any one of claims 1 to 8.

11. Direct neural interface (DNI-I) equipment, available to a given user (UT) to control at least one machine, comprising a direct neural interface (DNI-I) activator associated with a mental state detected based on a result provided by a brain signal analyzer captured repeatedly to control said at least one machine via said direct neural interface.

12. Equipment according to claim 11, wherein the activator is a computer device according to claim 10.

13. Equipment according to any one of claims 11 or 12, comprising: - one or more direct neural interface sensors (BCI), and - one or more brain signal measurement sensors (CAP) (SIG.CER.), in the same helmet intended to be worn by the user.

14. Equipment according to any one of claims 11 to 13, wherein the direct neural interface (BCI-i) is reactive and to visual stimuli, and, the equipment comprising a computer screen (TAB), configured to display respective machine control icons, said icons flashing at respective frequencies, a screen page containing said icons is displayed on the screen, upon activation of said direct neural interface.

15. Equipment according to claim 14, wherein the equipment comprises a brain signal analyzer configured to compare (E2) the measured brain signal (SIG.CER.) to a plurality of predefined signals (SI, S2, ... Si) each corresponding to a direct neural interface (BCI-1; BCI-2; ... BCI-i) to be activated, each of the direct neural interfaces (BCI-1; BCI-2; ... BCI-i) being reactive and to visual stimuli, and wherein the computer screen (TAB) is configured to display a screen page specific to a direct neural interface to be activated (BCI-1; BCI-2; ... BCI-i).

Images