Multi-Sensor Data Fusion Using Conditional Entropy and Validation
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 inefficiencies in data processing, storage, and computational requirements, leading to reduced accuracy and increased power consumption.
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
1Measurement precision
If sensor data from multiple sources is fused using traditional methods, then data integration is achieved, but accuracy is reduced and power consumption increases
Solution Approach 1:
The patent applies preliminary action by pre-processing sensor data through curating and linking before fusion. The curation engine prepares data by filtering and organizing it, while the link engine establishes relationships between data points beforehand. This preliminary preparation reduces the computational burden during the actual fusion process, thereby lowering power consumption while maintaining accuracy.
Solution Approach 2:
The patent segments the data fusion process into distinct functional modules: curation engine, link engine, fusion engine, inference engine, and validation engine. Each engine handles specific tasks independently, allowing for optimized resource allocation and reduced computational overhead. This segmentation enables the system to process data more efficiently with lower power consumption.
2Measurement precision
If sensor data from multiple sources is fused using traditional methods, then data integration is achieved, but computational requirements increase
Solution Approach 1:
The curation and linking engines perform preliminary data preparation by organizing, filtering, and establishing relationships between sensor data points before fusion. This pre-processing reduces the complexity of the fusion operation itself, as the data is already structured and relationships are pre-established, thereby reducing overall computational requirements.
Solution Approach 2:
The patent divides the complex fusion process into separate engines with specific functions. The curation engine handles data preparation, the link engine manages relationships, the fusion engine performs integration, the inference engine generates insights, and the validation engine ensures accuracy. This segmentation allows each component to be optimized independently, reducing overall computational complexity.
3Measurement precision
If sensor data from multiple sources is fused using traditional methods, then data integration is achieved, but storage requirements increase
Solution Approach 1:
The patent extracts only the essential and relevant features from multi-source sensor data through the curation and link engines. Instead of storing and processing all raw data, the system identifies and extracts key data points and relationships that are necessary for accurate fusion. This extraction reduces storage requirements while preserving the accuracy needed for effective data fusion.
4Adaptability or versatility
If heterogeneous sensor data is processed together, then comprehensive data fusion is achieved, but processing efficiency decreases
Solution Approach 1:
The patent applies local quality by treating different types of sensor data with specialized processing approaches. The curation engine adapts its processing based on the specific characteristics of each data source, and the link engine establishes appropriate relationships based on data type. This localized, adaptive processing maintains comprehensiveness for heterogeneous data while improving efficiency by avoiding uniform, overly complex processing for all data types.
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.