Sensor Data Fusion Using Mathematical Validation and Curation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems fail to create actionable data by correlating and fusing heterogeneous, partially heterogeneous, or homogeneous data sources in real-time, leading to excessive computational and storage requirements, and lack of sensor accuracy assurance.
Innovation Solution
A system and method for sensor data fusion that includes a computer processor with curation, link, fusion, inference, and validation engines to curate and mathematically link sensor data before storage, creating a unique dataset with enhanced accuracy and reduced computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If sensor data from multiple sources is fused without mathematical validation, then data quantity increases, but data accuracy and reliability deteriorate
Solution Approach 1:
The patent introduces a mathematical validation mechanism as an intermediary between raw sensor data and fused output. The system validates whether mathematical relationships between sensor readings hold true before fusing data, acting as a gatekeeper that prevents inaccurate data from being combined. This intermediary layer ensures that only mathematically consistent data contributes to the fused result, resolving the contradiction between quantity and accuracy.
Solution Approach 2:
The system implements feedback through continuous validation of mathematical relationships between sensor data points. When the mathematical link between sensors fails validation, the system adjusts by excluding problematic data points or requesting additional validation, creating a closed-loop system that maintains accuracy while processing multiple data sources. This feedback mechanism prevents the accumulation of inaccurate fused data.
2Adaptability or versatility
If all sensor data is stored and processed, then complete data availability is achieved, but computational and storage requirements increase excessively
Solution Approach 1:
The patent extracts only the essential mathematical relationships between sensor data points rather than storing and processing all raw data. By identifying and validating only the critical mathematical links needed for fusion, the system achieves data availability without the burden of processing complete datasets. This extraction approach reduces computational complexity while maintaining the ability to perform accurate fusion when needed.
Solution Approach 2:
The system performs preliminary validation of mathematical relationships between sensors before actual data fusion occurs. By pre-establishing which mathematical links are valid and reliable, the system avoids the need to compute and validate all possible sensor combinations during processing. This preliminary action significantly reduces computational requirements while ensuring data availability for valid relationships.
3Adaptability or versatility
If heterogeneous sensor data is fused without validation, then data integration capability improves, but reliability of fused data deteriorates
Solution Approach 1:
The patent changes the parameter of validation from a binary accept/reject decision to a continuous assessment of mathematical relationship strength. By evaluating the degree to which mathematical relationships hold true between heterogeneous sensors, the system can dynamically adjust fusion based on reliability metrics. This parameter transformation allows the system to integrate diverse sensor types while maintaining reliability through quantitative validation of their relationships.
4Measurement precision
If mathematical validation is performed on all sensor data pairs, then data accuracy improves, but processing time increases
Solution Approach 1:
The patent applies partial validation by focusing mathematical validation only on critical sensor pairs and relationships rather than all possible combinations. The system identifies which mathematical links are essential for the fusion task and validates only those, performing excessive validation only when necessary. This selective approach maintains data accuracy for critical pathways while reducing overall processing time by avoiding redundant validation of non-essential data pairs.
Data Source
AI summary
Systems and methods of sensor data fusion including sensor data capture, curation, linking, fusion, inference, and validation. The systems and methods described herein reduce computational demand and processing time by curating data and calculating conditional entropy. The system is operable to fuse data from a plurality of sensor types. A computer processor optionally stores fused sensor data that the system validates above a mathematical threshold.