Systems and methods for controlling a device based on detection of transient oscillatory or pseudo-oscillatory bursts
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12186089-B2
Publication Date
2025-01-07
Expiration Date
Abstract
Systems, methods, and apparatus for controlling a device based on the detection of transient oscillatory or pseudo-oscillatory bursts are disclosed. For example, a method can comprise detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject. The method can also comprise extracting one or more burst features from the one or more transient oscillatory or pseudo-oscillatory bursts detected within a detection period. The method can also comprise predicting a thought generated or conjured by the subject or a change in mental state evoked by the subject by applying at least one of a machine learning algorithm and a feature threshold to the one or more burst features extracted within the detection period. An input command associated with the prediction can be transmitted to the device in order to control the device.
Core Innovation
The invention relates to controlling a device by detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject. The transient oscillatory or pseudo-oscillatory bursts are generated in response to a thought generated by the subject or a change in mental state evoked by the subject, and the approach operates on ongoing or real-time neural signal recordings captured by a recording device.
The invention extracts one or more burst features from the detected transient oscillatory or pseudo-oscillatory bursts within a detection period of between 1 ms and 100 ms. The extracted burst features are then input to a machine learning algorithm to obtain a prediction concerning the thought generated by the subject or the change in mental state evoked by the subject, and the prediction is used to drive device control through an input command based on the prediction.
In alternative aspects, the invention uses a feature threshold applied to the extracted burst features. It determines the thought generated by the subject or the change in mental state evoked by the subject when the one or more burst features meets or exceeds the feature threshold, and the system and method are configured to control a device that is a computing device, a mobility vehicle, a peripheral device of the computing device, or a software application running on the computing device.
Claims Coverage
The document includes three independent claims covering methods and a system. Across these independent claims, the core inventive features are burst-based interpretation of transient oscillatory or pseudo-oscillatory bursts, burst feature extraction within a 1 ms to 100 ms detection period, and using either a machine learning algorithm prediction or a feature-threshold determination to generate an input command for device control.
Burst-based detection from ongoing neural recordings for thought/mental-state control
detecting one or more transient oscillatory or pseudo-oscillatory bursts from an ongoing neural signal recording of a subject captured by a recording device, wherein the one or more transient oscillatory or pseudo-oscillatory bursts are generated in response to a thought generated by the subject or a change in mental state evoked by the subject
Burst feature extraction within a 1 ms to 100 ms detection period
extracting, using one or more processors of a computing device communicatively coupled to the recording device, one or more burst features from the one or more transient oscillatory or pseudo-oscillatory bursts detected within a detection period of between 1 ms and 100 ms
Machine learning prediction from burst features for device control
inputting the one or more burst features extracted within the detection period to a machine learning algorithm to obtain as an output from the machine learning algorithm a prediction concerning the thought generated by the subject or the change in mental state evoked by the subject; and controlling the device with an input command based on the prediction
Device control using burst features and machine learning in a system
a recording device configured to capture an ongoing neural signal recording of a subject; and a computing device having one or more processors communicatively coupled to the recording device, wherein the one or more processors are programmed to detect one or more transient oscillatory or pseudo-oscillatory bursts, extract one or more burst features within a detection period of between 1 ms and 100 ms, input the one or more burst features to a machine learning algorithm to obtain a prediction, and control the device via an input command transmitted to the device, wherein the device is a computing device, a mobility vehicle, a peripheral device of the computing device, or a software application running on the computing device, and wherein the input command is based on the prediction
Feature-threshold determination from burst features for thought/mental-state control
applying a feature threshold to the one or more burst features extracted within the detection period using the one or more processors of the computing device; determining, using the one or more processors of the computing device, the thought generated by the subject or the change in mental state evoked by the subject when the one or more burst features extracted within the detection period meets or exceeds the feature threshold; and controlling the device with an input command based on the prediction
Overall, the independent claims cover controlling a computing device, mobility vehicle, peripheral device, or software application by detecting transient oscillatory or pseudo-oscillatory bursts in ongoing neural recordings, extracting burst features within a 1 ms to 100 ms detection period, and translating those features into either a machine learning algorithm prediction or a feature-threshold determination used to issue an input command for device control.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?