Sensor Data Fusion Using Conditional Entropy and Pre-Correlation
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 efficiently, leading to excessive computational and storage requirements, and they do not generate new datasets that provide sensor accuracy and predictive insights.
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 fuse sensor data, creating a unique dataset with accuracy values, reducing computational and storage needs by correlating data before storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data from multiple sources is fused to create actionable data, then data accuracy and predictive insights are improved, but computational and storage requirements increase
Solution Approach 1:
The system performs preliminary correlation and fusion of sensor data before storage by creating a data repository that pre-processes and links heterogeneous data sources. This preliminary action reduces the computational burden during query execution by having data ready in a correlated state, thus improving accuracy while managing storage requirements efficiently.
Solution Approach 2:
The patent introduces an intermediary data repository that acts as a mediator between raw sensor data and query processing. This intermediary structure pre-correlates data from multiple sources, reducing the need for intensive real-time computation when generating actionable data, thereby balancing accuracy improvement with computational resource management.
2Loss of information
If heterogeneous sensor data sources are correlated and fused, then new actionable datasets are generated, but system complexity increases
Solution Approach 1:
The system segments the complex task of data fusion into distinct functional components: a data repository for storage, a query interface for access, and automated correlation processes. This segmentation manages system complexity by organizing heterogeneous data handling into modular, manageable parts that can operate independently yet cooperatively.
Solution Approach 2:
The patent implements self-service automation where the system automatically correlates and fuses sensor data without requiring manual intervention for each data processing task. The automated processes continuously maintain the data repository and generate actionable datasets, reducing operational complexity while maximizing information utilization.
3Productivity
If data is processed and fused in real-time, then predictive capabilities are enhanced, but power consumption increases
Solution Approach 1:
The system performs preliminary data correlation and repository building during periods when full processing power is available, preparing data structures in advance. This preliminary action enables faster, lower-power query execution and real-time predictive capabilities, as the heavy lifting of data correlation has already been completed and stored efficiently.
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.