Spike Train Decoding Using Temporal Clustering for Neural Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in decoding a user's intended motion for remote-controlled devices and immersive technologies, such as prosthetics and virtual reality applications, as they struggle to accurately capture and implement user intentions from neural signals.
Innovation Solution
The system determines spike trains from a subject's cerebral cortex neurons, using temporal-relation values and clustering algorithms to identify feature vectors and decode intended motion by establishing successive layers of clusters, allowing for the detection of consistent clusters indicative of specific motions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional neural signal decoding methods are used, then device control is achieved, but decoding accuracy of intended motion is insufficient
Solution Approach 1:
The patent segments the decoding process into multiple layers (first layer, second layer, successive layers), where each layer processes temporal relations at different time constants. This hierarchical segmentation allows the system to capture motion intentions at multiple temporal scales, improving decoding accuracy while organizing complexity in a structured manner
Solution Approach 2:
The patent introduces a temporal dimension by computing temporal-relation values between spike trains at different time constants (τ). This transforms the decoding from a static analysis to a temporal-dynamic analysis, adding a new dimension for distinguishing intended motions and improving measurement precision
2Measurement precision
If multiple temporal scales are analyzed, then motion decoding precision is improved, but computational complexity increases
Solution Approach 1:
The computational process is segmented into distinct layers, each handling a specific time constant. The first layer processes at one time constant, the second layer at another, and successive layers at additional time constants. This segmentation allows parallel processing of different temporal scales without overwhelming computational burden at any single stage
Solution Approach 2:
The system computes temporal relations with multiple time constants (excessive action) to ensure comprehensive coverage of all relevant motion temporal scales. This partial redundancy in computation across layers ensures that no significant motion pattern is missed, improving precision while distributing computational load
Data Source
AI summary
Disclosed herein, in certain embodiments, are methods and systems for utilizing spike trains. In one aspect, encompassed by the disclosure is a method comprising: determining, by at least one processor, a plurality of spike trains from a plurality of neurons of a cerebral cortex of a subject. The method may comprise determining, by the at least one processor, a plurality of first layer feature vectors, the plurality of first layer feature vectors including a first feature vector that comprises temporal-relation values of a subset of the plurality of spike trains with respect to a time instance of a reference spike train of the subset, corresponding to a time constantτ having a first value. The method may comprise establishing, by the at least one processor, a first layer comprising a first plurality of clusters of the first layer feature vectors.