Sensor Data Fusion with Conditional-Entropy Curation Before Storage
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 mathematically link sensor data in real-time, 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 is stored before fusion, then data availability is improved, but storage requirements and computational demands increase excessively
Solution Approach 1:
The system performs data curation, mathematical linking, and fusion operations before storing the fused dataset. The curation engine prepares data by categorizing it into properties and sub-properties, the link engine establishes mathematical relationships between data points, and the fusion engine combines correlated data points into a condensed fused dataset. This preliminary processing reduces the volume of data that needs to be stored while ensuring data availability for fusion operations.
Solution Approach 2:
The fusion engine merges multiple sensor data points into a single fused dataset by identifying and combining correlated data points. The system correlates data points from different sensors based on their properties and sub-properties, then fuses them into a condensed representation that retains essential information while reducing overall data volume and storage requirements.
2Productivity
If heterogeneous sensor data is fused without prior curation and linking, then processing speed is improved, but data accuracy and correlation quality deteriorate
Solution Approach 1:
The system performs preliminary curation and linking operations on heterogeneous sensor data before fusion. The curation engine categorizes data into properties and sub-properties, establishing a structured framework. The link engine then creates mathematical relationships between correlated data points from different sensors. These preliminary actions ensure data accuracy and proper correlation while enabling efficient subsequent fusion processing.
Solution Approach 2:
The system transforms heterogeneous sensor data into a standardized format with defined properties and sub-properties through the curation engine. By changing the parameter representation of diverse sensor inputs into a common structured framework, the system enables accurate correlation and fusion while maintaining processing efficiency across different sensor types.
3Speed
If real-time sensor data fusion is implemented, then responsiveness is improved, but power consumption and computational load increase
Solution Approach 1:
The fusion engine combines correlated sensor data points into a condensed fused dataset, reducing the total volume of data that requires processing and storage. By merging redundant or correlated information from multiple sensors into a single fused representation, the system achieves real-time responsiveness while reducing computational load and power consumption associated with processing large volumes of raw sensor data.
Solution Approach 2:
The link engine extracts and identifies correlated data points from heterogeneous sensor inputs, separating essential correlated information from redundant data. By extracting only the correlated portions of sensor data that contribute to the fused output, the system reduces unnecessary computational processing and power consumption while maintaining real-time fusion capabilities.
4Measurement precision
If data is curated and linked before fusion, then fusion accuracy is improved, but processing complexity increases
Solution Approach 1:
The system divides the data processing workflow into distinct modular engines: the curation engine that categorizes data into properties and sub-properties, the link engine that establishes mathematical relationships, and the fusion engine that combines correlated data. This segmentation of processing functions into separate modular components improves fusion accuracy through systematic data preparation while managing complexity through clear separation of concerns and specialized processing for each stage.
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.