Signal Decomposition Using Reference Signal Partitioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Blind Source Separation (BSS) techniques face challenges in accurately identifying and isolating individual source signals from mixed sensor responses, particularly in environments with multiple active sources, due to limitations in defining hidden source signals and the ambiguity in source images generated by BSS algorithms.
Innovation Solution
The system processes data signals by subtracting identified signal terms and using reference signals organized into mutually independent partitioning support sets to compute additional independent signal terms, allowing for the identification of independent signal terms through decomposition and statistical analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional Blind Source Separation (BSS) techniques are used to separate source signals from mixed sensor responses, then the separation process can be performed without prior knowledge of sources, but the accuracy of identifying individual source signals deteriorates due to ambiguity in source images and limitations in defining hidden source signals
Solution Approach 1:
The patent introduces reference signals as an intermediary element that mediates between the mixed sensor responses and the hidden source signals. These reference signals serve as a bridge, providing a known basis for comparison that enables more accurate source separation while maintaining the blind operation capability. The reference signals are processed through the mixing model to create deflated versions that help identify contributing sources without requiring direct observation of the hidden sources themselves.
Solution Approach 2:
The patent transforms the source separation problem by changing the parameter space from directly analyzing mixed signals to analyzing deflated signals derived from reference signals. By computing deflated versions of reference signals through the mixing model and comparing them with actual sensor responses, the system identifies contributing sources with improved accuracy. This parameter transformation allows the system to work with known reference parameters rather than unknown source parameters.
2Quantity of substance
If multiple signal sources are simultaneously active in the environment, then the sensor captures comprehensive environmental information, but the ability to isolate individual source signals deteriorates due to the additive mixture of multiple sources in the sensor response
Solution Approach 1:
The patent segments the mixed sensor response into contributions from individual sources by systematically testing each reference signal against the deflated data signals. Each reference signal represents a potential source component, and through iterative deflation and comparison, the system separates the comprehensive mixture into discrete source contributions. This segmentation process maintains the complete environmental information while organizing it into identifiable source components.
Solution Approach 2:
The patent performs preliminary actions by organizing reference signals into mutually independent partitioning support sets before the actual source separation process. This preliminary organization creates a structured framework that guides the subsequent decomposition of mixed signals. By pre-establishing the reference signal structure and computing their deflated versions in advance, the system prepares the necessary tools for accurate source isolation without having to process the complex mixture directly from scratch.
3Measurement precision
If reference signals are organized into mutually independent partitioning support sets to compute additional independent signal terms, then the decomposition accuracy of data signals improves, but the computational complexity and system structure deteriorates
Solution Approach 1:
The patent segments the reference signals into mutually independent partitioning support sets, where each set handles specific independent signal terms. This segmentation divides the complex decomposition task into manageable independent parts, improving accuracy by allowing specialized processing for each support set while keeping the overall system structure organized and modular.
Solution Approach 2:
The patent transitions from analyzing signals in the time domain to computing images in the frequency domain. By organizing reference signals into support sets and computing their images on deflated data signals, the system adds a frequency domain dimension to the analysis. This dimensional transformation enables more accurate decomposition by exploiting spectral characteristics while maintaining computational tractability through structured support set organization.
Data Source
AI summary
A system processes data signals consisting of sums of independent signal terms, zero or more of which signal terms may already have been identified, in order to generate one or more additional terms. Deflated versions of the data signals are created by subtracting from the data signals any previously identified signal terms. Additional independent signal terms are computed using a set of reference signals organized into mutually independent partioning support sets. The images of each support set are computed on the data signals. Computed images on a data signal that are non-zero are identified as additional independent signal terms of that data signal.