Sensor Data Fusion with Real-Time Curation and Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems fail to create actionable data by correlating and fusing sensor data before storage, leading to excessive computational and storage requirements, and lack real-time data processing capabilities, especially for heterogeneous and partially heterogeneous data sources.
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 link sensor data in real-time or near-real-time, creating a unique dataset by correlating and fusing heterogeneous, partially heterogeneous, or homogeneous data sources, thereby reducing computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sensor data is stored before fusion, then data availability is improved, but computational and storage requirements increase excessively
Solution Approach 1:
The system performs preliminary actions by curating and linking sensor data in real-time before storage. The curation engine processes incoming sensor data streams, organizing and preparing them for fusion, while the link engine establishes relationships between data points from different sensors. This preliminary processing ensures data is ready for fusion without requiring excessive storage of raw data, as only curated and linked data is retained.
Solution Approach 2:
The system extracts only the essential and relevant features from sensor data during the curation process. The curation engine identifies and extracts meaningful data characteristics, discarding redundant information. This extraction approach maintains data availability for fusion while significantly reducing the quantity of data that needs to be stored and processed.
2Adaptability or versatility
If heterogeneous sensor data is fused without preprocessing, then data fusion capability is improved, but data quality and correlation accuracy deteriorate
Solution Approach 1:
The system segments the data fusion process into distinct functional stages: curation, linking, fusion, inference, and validation. Each stage is handled by a dedicated engine that processes data with specific operations. This segmentation allows heterogeneous sensor data to be systematically prepared and correlated at each stage, improving both fusion capability and correlation accuracy through structured processing.
Solution Approach 2:
The link engine acts as an intermediary between the curation engine and the fusion engine. It establishes correlations and relationships between curated data points from different sensors before fusion occurs. This intermediary processing ensures that heterogeneous data sources are properly correlated and contextualized, improving measurement precision while maintaining fusion versatility.
3Speed
If real-time data processing is implemented, then response time is improved, but computational complexity increases
Solution Approach 1:
The computational workload is segmented across multiple specialized engines (curation, linking, fusion, inference, validation), each performing specific operations on sensor data. This segmentation distributes computational complexity across modular components, making real-time processing more manageable while maintaining fast response times through parallel processing capabilities.
Solution Approach 2:
The system performs partial processing at each stage, focusing on the most critical operations needed for real-time response. The curation engine performs essential data organization, the link engine establishes key correlations, and the fusion engine combines the most relevant data points. This partial action approach achieves real-time response without requiring exhaustive processing of all possible data relationships.
4Reliability
If multiple engines are used for data processing, then data processing quality is improved, but system complexity increases
Solution Approach 1:
The system segments data processing into five distinct engines, each responsible for a specific function: curation (data organization), linking (correlation establishment), fusion (data combination), inference (pattern recognition), and validation (quality assurance). This segmentation improves processing quality by dedicating specialized operations to each engine while managing complexity through modular architecture where each engine can be independently developed and maintained.
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.