Sensor Data Fusion Pipeline for Accurate Low-Load Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems fail to accurately fuse heterogeneous, partially heterogeneous, or homogeneous data sources due to inefficient data processing and storage requirements, leading to reduced computational efficiency and increased storage needs.
Innovation Solution
A system and method for sensor data fusion that utilizes a computer processor with a curation engine, link engine, fusion engine, inference engine, and validation engine to curate, link, fuse, infer, and validate sensor data from multiple sources, creating a unique dataset with enhanced accuracy and reduced computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data from multiple sources is fused using traditional methods, then data integration is achieved, but computational processing requirements and storage needs increase significantly
Solution Approach 1:
The patent segments the sensor data fusion process into distinct functional modules: a curation engine that filters and prepares raw sensor data, a link engine that identifies relationships between curated data points, and a fusion engine that generates new data points from linked data. This segmentation allows each module to perform specialized operations efficiently, reducing overall computational requirements while maintaining fusion accuracy.
Solution Approach 2:
The curation engine performs preliminary actions by filtering, validating, and organizing raw sensor data before it reaches the fusion engine. By pre-processing data to remove redundancies and inconsistencies upfront, the system reduces the computational burden on subsequent fusion operations and minimizes storage requirements for raw data.
2Loss of information
If heterogeneous sensor data is integrated comprehensively, then data completeness improves, but storage demands increase
Solution Approach 1:
The fusion engine merges multiple curated data points into single new data points that encapsulate the essential information from all input sources. By combining redundant or complementary data into unified representations, the system maintains information completeness while significantly reducing the volume of data requiring storage.
Solution Approach 2:
The system discards redundant raw sensor data after it has been curated and its essential information extracted. The curation engine identifies and eliminates duplicate or unnecessary data points, while the fusion engine recovers and preserves critical information in compressed new data point formats, optimizing storage efficiency.
3Speed
If real-time sensor data fusion is performed, then responsiveness improves, but computational complexity increases
Solution Approach 1:
The patent divides the real-time fusion system into specialized engines (curation, linking, fusion) that operate in parallel pipelines. This segmentation enables simultaneous processing of different data streams without sequential bottlenecks, improving real-time responsiveness while managing complexity through modular architecture.
Solution Approach 2:
The system implements periodic processing cycles where the curation engine continuously filters incoming sensor data, the link engine periodically identifies relationships, and the fusion engine generates new data points at regular intervals. This periodic action structure provides predictable real-time performance while simplifying synchronization and resource management.
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.