Electroencephalogram bioamplifier

Patent metadata

Field	Value
Publication number	US-10952680-B2
Application number	US-201715855870-A
Country	US
Kind code	B2
Filing date	Dec 27, 2017
Priority date	Dec 27, 2017
Publication date	Mar 23, 2021
Grant date	Mar 23, 2021

Abstract

A bioamplifier for analyzing electroencephalogram (EEG) signals is disclosed. The bioamplifier includes an input terminal for receiving an EEG signal from a plurality of sensors coupled to a user. The bioamplifier also includes an analogue-to-digital converter arranged to receive the EEG signal from the input terminal and convert the EEG signal to a digital EEG signal. A data processing apparatus within the bioamplifier is arranged to receive the digital EEG signal from the analogue-to-digital converter and programmed to process, in real time the digital EEG signal using a first machine learning model to generate a cleaned EEG signal having a higher signal-to-noise ratio than the digital EEG signal. The bioamplifier further includes a power source to provide electrical power to the analogue-to-digital converter and the data processing apparatus. The bioamplifier includes a housing that contains the analogue-to-digital converter, the data processing apparatus, the power source, and the sensor input.

First claim

What is claimed is:

1. A bioamplifier for analyzing electroencephalogram (EEG) signals, comprising:
a first input terminal for receiving an EEG signal from a plurality of sensors coupled to a user;
a second input terminal for receiving images from a camera system;
an analogue-to-digital converter arranged to receive the EEG signal from the first input terminal and convert the EEG signal to a digital EEG signal;
a data processing apparatus comprising one or more processors arranged to receive the digital EEG signal from the analogue-to-digital converter, the one or more processors being programmed to process, in real time, the digital EEG signal using a first machine learning model to generate a cleaned EEG signal having a higher signal-to-noise ratio than the digital EEG signal and to process the cleaned EEG signal using a second machine learning model to determine a selection, by the user, of one of a plurality of options presented to the user,
wherein the first machine learning model employs an artifact recognition process to identify and remove artifacts from the digital EEG signal, and
wherein the second machine learning model determines the selection by determining that, within a predetermined time period of the one of a plurality of options being presented to the user, an amplitude of the cleaned EEG signal exceeds a threshold amplitude value;

an output arranged to receive output signals from the data processing apparatus;
a power source arranged to provide electrical power to the analogue-to-digital converter and the data processing apparatus; and
a housing containing the analogue-to-digital converter, the data processing apparatus, the power source, the output, and the input terminal,
wherein the one or more processors are arranged to receive images of a machine readable code from the camera system, and
wherein the one or more processors are programmed to process, in real time: a) the images of the machine readable code to identify an object associated with the machine readable code and viewed by the user, and b) the cleaned EEG signal using the second machine learning model to determine the selection by the user, wherein the selection is a selection of one of two options associated with the object viewed by the user.

2. The bioamplifier of claim 1 , wherein the second machine learning model comprises a neural network or other artificial intelligence architecture.

3. The bioamplifier of claim 1 , further comprising a third input terminal for connecting with a user interface, and wherein the data processing apparatus is programmed to synchronize processing the EEG signal with a presentation of the plurality of options to the user via the user interface.

4. The bioamplifier of claim 1 , wherein the first machine learning model comprises a neural network or other artificial intelligence architecture.

5. The bioamplifier of claim 1 , further comprising an amplifier contained in the housing and arranged to receive the digital EEG signal from the analogue-to-digital converter and provide an amplified digital EEG signal to the data processing apparatus for processing.

6. The bioamplifier of claim 1 , wherein the power source comprises a battery.

7. The bioamplifier of claim 1 , wherein the analogue-to-digital converter is a 24 bit analogue-to-digital converter.

8. The bioamplifier of claim 1 , wherein the bioamplifier has an input impedance of 10 MOhms or more.

9. The bioamplifier of claim 1 , wherein the first input terminal comprises a jack for receiving a connecter from a lead.

10. The bioamplifier of claim 1 , wherein the first input terminal comprises a wireless transceiver for wirelessly receiving the EEG signal.

11. The bioamplifier of claim 1 , wherein the one or more processors are further programmed to:
in response to the second machine learning model determining the selection by the user, select an action from one or more possible actions associated with the object viewed by the user; and
generate an output signal associated with the action.

12. The bioamplifier of claim 11 , wherein the output signal includes a control signal for an electronic device.

13. The bioamplifier of claim 1 , wherein the threshold amplitude value and the predetermined time period are values obtained from training the second machine learning model according to a training process of presenting a series of task-relevant stimuli and non-task relevant-stimuli to users and distinguishing EEG data responsive to presentation of the task-relevant stimuli from EEG data responsive to presentation of the non-task-relevant stimuli, and
wherein the task relevant stimuli are associated with a user-performed task that the users are expected to complete upon perceiving the presentation of the task-relevant stimuli.

14. An EEG detection system comprising:
electroencephalogram (EEG) electrodes;
a bioamplifier communicably coupled to the EEG electrodes, and the bioamplifier comprising:
an analogue-to-digital converter arranged to receive, from the EEG electrodes, an EEG signal of a user and convert the EEG signal to a digital EEG signal;
a data processing apparatus comprising one or more processors arranged to receive the digital EEG signal from the analogue-to-digital converter, the one or more processors being programmed to process, in real time, the digital EEG signal using a first machine learning model to generate a cleaned EEG signal having a higher signal-to-noise ratio than the digital EEG signal and to process the cleaned EEG signal using a second machine learning model to determine a selection, by the user, of one of a plurality of options presented to the user,
wherein the first machine learning model employs an artifact recognition process to identify and remove artifacts from the digital EEG signal, and
wherein the second machine learning model determines the selection by determining that, within a predetermined time period of the one of a plurality of options being presented to the user, an amplitude of the cleaned EEG signal exceeds a threshold amplitude value;
an output arranged to receive output signals from the data processing apparatus;
a power source arranged to provide electrical power to the analogue-to-digital converter and the data processing apparatus; and
a housing containing the analogue-to-digital converter, the data processing apparatus, the power source, and the output; and

a camera system communicably coupled to the bioamplifier,
wherein the one or more processors are arranged to receive images of a machine readable code from the camera system, and
wherein the one or more processors are programmed to process, in real time: a) the images of the machine readable code to identify an object associated with the machine readable code and viewed by the user, and b) the cleaned EEG signal using the second machine learning model to determine the selection by the user, wherein the selection is a selection of one of two options associated with the object viewed by the user.

15. The system of claim 14 , wherein the one or more processors are further programmed to:
in response to the second machine learning model determining the selection by the user, select an action from one or more possible actions associated with the object viewed by the user; and
generate an output signal associated with the action.

16. The system of claim 15 , wherein the output signal includes a control signal for an electronic device.

17. The system of claim 14 , wherein the threshold amplitude value and the predetermined time period are values obtained from training the second machi

Assignees

• X Dev Llc

Inventors

• Laszlo Sarah Ann
• Adolf Brian John
• Levine Gabriella
• Owens Joseph R
• Prewitt Patricia
• Watson Philip Edwin

Classifications

• A61B5/7267 Primary

  involving training the classification device · CPC title

• A61B5/6803

  Head-worn items, e.g. helmets, masks, headphones or goggles · CPC title

• A61B5/291

  for electroencephalography [EEG] · CPC title

• A61B5/0022

  Monitoring a patient using a global network, e.g. telephone networks, internet · CPC title

• A61B5/7203

  for noise prevention, reduction or removal · CPC title