Sensor Data Fusion Using Conditional Entropy and Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems face challenges in accurately fusing heterogeneous, partially heterogeneous, or homogeneous data sources, leading to inefficiencies in computational processing, storage demands, and the inability to create actionable data.
Innovation Solution
A system and method for sensor data fusion that utilizes a computer processor with multiple engines (curation, link, fusion, inference, and validation) to curate, link, and fuse sensor data from various sources, creating a unique dataset with new data points and validating their accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If sensor data from multiple sources is fused to create comprehensive datasets, then data completeness and information quality are improved, but computational processing requirements and storage demands increase
Solution Approach 1:
The system performs preliminary actions by curating and pre-processing sensor data before fusion operations. The curation engine prepares data in advance by filtering, validating, and organizing sensor inputs, so that when fusion is needed, the computational workload is already reduced. This preliminary preparation minimizes the computational burden during actual fusion operations while maintaining data completeness.
Solution Approach 2:
The system extracts only the essential and relevant features from heterogeneous sensor data during the curation phase, rather than processing entire datasets. The curation engine identifies and extracts key data points and characteristics that are most valuable for fusion, discarding redundant information. This extraction approach maintains information quality while significantly reducing computational requirements for subsequent fusion operations.
2Measurement precision
If heterogeneous sensor data is fused to create new data points, then data quality and actionable insights are improved, but system complexity increases
Solution Approach 1:
The system segments the complex fusion process into distinct functional modules: a curation engine for data preparation, a fusion engine for combining data points, and a validation engine for quality assurance. Each module handles a specific aspect of the fusion process, making the overall system more manageable despite processing heterogeneous data. This segmentation allows the system to maintain high data quality while controlling complexity through modular architecture.
Solution Approach 2:
The curation engine acts as an intermediary between raw heterogeneous sensor data and the fusion engine. It standardizes and prepares data from different sources before they enter the fusion process, creating a unified intermediate representation. This intermediary layer simplifies the fusion operation by handling the complexity of heterogeneous data integration, allowing the fusion engine to focus on combining data points without dealing with source-specific variations.
3Reliability
If comprehensive sensor data fusion is performed to create actionable datasets, then data reliability is improved, but processing time and computational resources increase
Solution Approach 1:
The validation engine performs preliminary validation checks on sensor data during the curation phase, identifying and flagging unreliable data points before they enter the fusion process. This preliminary validation ensures that only reliable data is fused, maintaining data reliability while avoiding the time cost of validating every fused result. The system prepares validated data in advance, reducing processing time during actual fusion operations.
4Loss of information
If multiple sensor data sources are integrated to create unique datasets, then information completeness is improved, but storage requirements increase
Solution Approach 1:
The curation engine extracts only the essential features and key data points from comprehensive sensor datasets during the preparation phase. Instead of storing and processing entire raw datasets from multiple sensors, the system extracts and retains only the most valuable information. This extraction approach maintains information completeness for fusion operations while significantly reducing the storage requirements by eliminating redundant and less critical data.
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 that the system validates above a mathematical threshold.