Sensor Data Fusion Validation for Real-Time Actionable Data
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 before storage, leading to excessive computational and storage requirements, and lack real-time accuracy and predictive capabilities.
Innovation Solution
A system and method for sensor data fusion that includes a computer processor with curation, linking, fusion, inference, and validation engines to mathematically link and validate sensor data exceeding a predefined threshold, creating a unique dataset in near real-time, reducing computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sensor data is stored and processed after collection, then data availability is improved, but computational and storage requirements increase excessively
Solution Approach 1:
The system performs data fusion in near real-time as data is generated, rather than storing all raw data for later processing. The curation engine prepares and filters data, the linking engine correlates data points, and the fusion engine combines them immediately, creating actionable insights before storage is needed. This preliminary action eliminates the need for excessive storage and post-processing computational resources.
2Productivity
If heterogeneous sensor data is fused without mathematical validation, then data processing speed is improved, but data accuracy decreases
Solution Approach 1:
The validation engine continuously monitors fused data points and compares them against expected ranges and correlations. When data points are linked by the linking engine, the validation engine verifies their mathematical consistency and accuracy. This feedback mechanism ensures data accuracy is maintained while processing occurs in near real-time, as validation happens concurrently with fusion rather than as a separate post-processing step.
3Adaptability or versatility
If all sensor data is stored for future analysis, then analytical capability is improved, but storage requirements increase excessively
Solution Approach 1:
The system extracts only the essential information from raw sensor data through the fusion process, creating condensed fused data points that contain the most valuable insights. The curation engine identifies and extracts relevant data characteristics, the linking engine extracts correlations between data points, and the fusion engine synthesizes these into compact fused results. This extraction process maintains analytical capability while dramatically reducing storage requirements compared to storing all raw data.
4Loss of time
If data fusion is performed in near real-time, then response time is improved, but computational complexity increases
Solution Approach 1:
The system segments the data fusion process into distinct functional modules: the curation engine handles data preparation and filtering, the linking engine manages data correlation, the fusion engine performs data combination, and the validation engine ensures accuracy. This segmentation allows each component to perform its specific function efficiently in near real-time, reducing overall computational complexity compared to a monolithic fusion system that would need to handle all operations simultaneously.
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.