Neural Signal BCI Control to Reduce False Switch Selections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current brain-computer interfaces (BCIs) for locked-in patients with severe mobility limitations face challenges due to tedious automatic switch scanning and difficulty in engaging single virtual switches, often resulting in erroneous selections and false positives.
Innovation Solution
A method and system that detect changes in neural-related signals, such as beta-band oscillations, using endovascular devices and machine learning classifiers to transmit input commands based on intensity variations, providing feedback and allowing control of devices like personal computing devices, IoT devices, and mobility vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automatic switch scanning is used to control devices, then locked-in patients can access peripherals through a single switch, but the process becomes tedious and error-prone with false positives
Solution Approach 1:
The patent replaces the mechanical/sequential automatic switch scanning process with a neural signal-based detection system. Instead of scanning through options sequentially and relying on manual correction, the system uses neural-related signals (such as EEG, EOG, or other brain signals) to directly detect user intent and trigger appropriate controls, thereby eliminating the tedious scanning process and reducing false positives while maintaining accessibility for locked-in patients
2Measurement precision
If neural-related signals are used to detect user intent, then control accuracy can be improved, but false positives occur and detection reliability is compromised
Solution Approach 1:
The patent implements feedback mechanisms to continuously monitor and adjust the neural signal detection process. The system provides feedback to both the user and the control system, allowing for real-time correction of false positives and improvement of detection reliability. This feedback loop enables the system to learn from errors and refine its signal interpretation, thereby maintaining high measurement precision while improving overall reliability
Solution Approach 2:
The patent employs preliminary actions by pre-configuring the system with expected neural signal patterns and establishing baseline detection parameters before actual use. This preparation allows the system to better distinguish between valid user intent signals and false positives during operation, improving detection reliability without sacrificing precision
3Device complexity
If a single virtual switch is provided for control, then device complexity is reduced, but engagement difficulty increases for locked-in patients
Solution Approach 1:
The patent substitutes the mechanical engagement requirement with neural signal-based activation. Instead of requiring physical or manual engagement with a virtual switch, the system detects user intent through neural-related signals and automatically triggers the appropriate control function. This maintains the simplicity of a single control interface while eliminating the engagement difficulty associated with traditional virtual switches
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables locked-in patients to independently control devices with reduced complexity and fewer errors by detecting neural signal intensity changes, facilitating seamless interaction with various devices.
Implementation Method 1
The neural-related signal can be detected via electrodes of the endovascular device implanted within the subject. For example, the neural-related signal can be detected via electrodes of the endovascular device implanted within the brain of the subject.
Data Source
AI summary
Systems and methods of controlling a device using detected changes in a neural-related signal of a subject are disclosed. In one embodiment, a method of controlling a device or software application comprises detecting a first change in a neural-related signal of a subject, detecting a second change in the neural-related signal, and transmitting an input command to the device upon or following the detection of the second change in the neural-related signal. The neural-related signal can be detected using a neural interface implanted within a brain of the subject.