Neural Signal Switch Control for Locked-In BCI Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current brain-computer interfaces (BCIs) for locked-in patients with severe mobility limitations face challenges in controlling peripherals due to tedious automatic switch scanning and difficulty in detecting neural-related signals, leading to false positives and inefficient control.
Innovation Solution
A method and system that utilize changes in neural-related signals, such as beta-band oscillations, to detect reductions and increases in signal intensity, allowing for the transmission of input commands through a single virtual switch, with feedback mechanisms and machine learning classifiers to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If automatic switch scanning is used to control peripherals, then locked-in patients can access devices, but the control process becomes tedious and time-consuming
Solution Approach 1:
The system performs preliminary actions by continuously monitoring neural signals and pre-positioning the virtual switch in a ready state, so that when the patient intends to make a selection, the switch is already prepared for immediate activation without requiring sequential scanning through multiple items
Solution Approach 2:
The invention extracts the core activation function from the complex scanning process, isolating the neural signal detection and switch activation as a separate, direct control mechanism that operates independently from the peripheral device interface, allowing patients to bypass the tedious scanning sequence
2Device complexity
If a single virtual switch is used for control, then the system becomes simpler, but detecting neural signals becomes more difficult and prone to false positives
Solution Approach 1:
The system employs dynamic thresholds and adaptive signal processing that adjust in real-time based on the patient's neural signal characteristics, allowing the detection sensitivity to optimize itself continuously rather than using fixed, static parameters that would increase false positives
Solution Approach 2:
The system implements feedback mechanisms where the detected neural signals and their outcomes are continuously monitored and used to adjust detection parameters, providing real-time correction that reduces false positives while maintaining simple virtual switch control
3Adaptability or versatility
If automatic switch scanning is used, then multiple items can be accessed, but erroneous selections require waiting for complete scanning cycle to restart
Solution Approach 1:
The system prepares multiple virtual switch instances in advance, each pre-configured for different items or functions, so that when an error occurs, the patient can immediately activate a different pre-prepared switch without waiting for the scanning cycle to complete
Solution Approach 2:
The control interface is segmented into multiple independent virtual switch elements that can be individually activated, allowing the patient to select from multiple items through discrete neural signal detections rather than sequential scanning, enabling immediate correction of erroneous selections
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.