Sensor Data Fusion Using Conditional Entropy and Data Curation
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 inefficient data processing and storage requirements, leading to reduced accuracy and increased computational and storage demands.
Innovation Solution
A system and method for sensor data fusion that involves a computer processor analyzing data from multiple sensors, curating the data, linking it based on conditional entropy calculations, fusing the data to create new validated data points, and using AI/ML for real-time processing and validation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data from multiple sources is fused together, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent segments the sensor data fusion process into distinct functional modules: a curation engine for data selection and preprocessing, a link engine for establishing data relationships, and a fusion engine for combining data. This modular segmentation reduces overall system complexity by making each component's function specific and manageable while achieving high measurement precision through their coordinated operation.
Solution Approach 2:
The patent introduces intermediary computational structures including data representations that abstract sensor readings, linkage data structures that mediate relationships between data points, and confidence values that act as intermediaries in validation. These intermediaries simplify the fusion process by providing standardized interfaces between heterogeneous sensor sources and the fusion engine, reducing complexity while maintaining accuracy.
2Adaptability or versatility
If heterogeneous sensor data is processed and stored, then adaptability is improved, but loss of substance increases
Solution Approach 1:
The patent dynamically changes parameters including confidence thresholds, data selection criteria, and fusion methods based on the specific characteristics of incoming sensor data. The system adjusts these parameters in real-time to optimize the balance between adapting to heterogeneous data sources and conserving computational resources, processing only the most relevant data at appropriate detail levels.
Solution Approach 2:
The patent applies partial action by selectively curating and processing only a subset of available sensor data that meets confidence thresholds and relevance criteria. Rather than processing all heterogeneous data equally, the system performs partial processing on high-value data points while filtering or aggregating lower-priority data, thereby maintaining adaptability across multiple sensor types while reducing overall computational resource consumption.
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.