Sensor Data Fusion Using Mathematical Linking and Validation
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, creating a unique dataset with enhanced accuracy and reduced computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sensor data from multiple sources is collected and stored for later analysis, then data completeness is improved, but computational requirements and storage needs increase excessively
Solution Approach 1:
The system performs preliminary data fusion by mathematically linking sensor data points and creating aggregated datasets before storage. The curation engine processes raw sensor data in real-time, combining multiple data points into single fused data points that retain essential information while reducing volume. This preliminary action ensures data completeness is maintained through mathematical relationships while minimizing storage requirements.
Solution Approach 2:
The fusion engine merges multiple sensor data points from heterogeneous sources by establishing mathematical links between them. When data points are mathematically linked, they are combined into a single aggregated data point that represents the collective information. This merging process reduces the total quantity of stored data while preserving the essential relationships and information content through the mathematical linkages.
2Loss of information
If raw sensor data from multiple sources is stored without processing, then data availability is improved, but computational processing requirements increase
Solution Approach 1:
The system performs preliminary fusion and aggregation of sensor data in real-time before storage, creating mathematically linked datasets that are ready for analysis. The curation and fusion engines process data as it arrives, establishing mathematical relationships and creating aggregated representations. This preliminary action reduces the computational burden during later analysis phases while maintaining data availability through the preserved mathematical linkages.
Solution Approach 2:
The system transforms raw sensor data into mathematically linked aggregated data points by changing the parameter representation. Instead of storing individual raw data points, the system creates fused data points that represent multiple original points through mathematical relationships. This parameter change reduces computational processing requirements while maintaining the ability to retrieve and analyze the underlying information when needed.
3Productivity
If heterogeneous sensor data is fused without mathematical validation, then data fusion speed is improved, but data accuracy and reliability decrease
Solution Approach 1:
The validation engine provides feedback mechanisms that verify the accuracy and reliability of fused data points. When sensor data points are mathematically linked and fused, the validation engine checks whether the mathematical relationships hold true and whether the fused result accurately represents the source data. This feedback process ensures data reliability while maintaining fusion speed by using efficient validation algorithms that operate in real-time alongside the fusion process.
Solution Approach 2:
The system performs preliminary validation checks during the data fusion process itself, rather than as a separate post-processing step. The validation engine works concurrently with the fusion engine, verifying mathematical linkages and data accuracy as data points are being fused. This preliminary validation action ensures reliability is maintained while minimizing impact on fusion speed through integrated processing.
4Loss of time
If all sensor data is processed and fused in real-time, then data freshness is improved, but computational complexity increases
Solution Approach 1:
The system segments the data processing function into distinct modular engines: a curation engine that prepares and categorizes data, a fusion engine that performs the actual mathematical linking and aggregation, and a validation engine that verifies accuracy. This segmentation allows each engine to specialize in its specific task, improving real-time processing efficiency while managing system complexity through clear separation of concerns and modular architecture.
Solution Approach 2:
The mathematical linking framework provides a universal method that can handle heterogeneous sensor data from multiple sources with different formats and characteristics. The same fusion and validation mechanisms work across diverse data types, reducing the need for separate specialized processing paths. This universality simplifies the overall system architecture while maintaining the ability to process all sensor data in real-time with consistent accuracy.
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.