Sensor Data Fusion with Pre-Curation for Real-Time Accuracy
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 in real-time, leading to excessive computational and storage requirements, and lack the ability to generate new datasets that enhance sensor accuracy and predict future events.
Innovation Solution
A system and method for sensor data fusion that includes a computer processor with curation, link, fusion, inference, and validation engines, which curate and link sensor data before fusion, creating a unique dataset by mathematically linking sensor outputs exceeding a predefined threshold, and using artificial intelligence to validate and adjust thresholds based on data sources and environmental factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data from multiple sources is fused without pre-curation and linking, then data fusion can be performed, but computational and storage requirements become excessive
Solution Approach 1:
The system performs preliminary curation and linking of sensor data before fusion. The curation engine pre-processes raw sensor data to extract relevant features and remove redundant information. The linking engine then associates curated data from multiple sensors based on spatial, temporal, and semantic relationships. This preliminary processing reduces the volume and complexity of data requiring fusion, thereby lowering computational and storage requirements while maintaining fusion reliability
Solution Approach 2:
The data fusion system is segmented into distinct functional modules: a curation engine for pre-processing individual sensor streams, a linking engine for associating data across sensors, and a fusion engine for combining linked data. This segmentation allows each module to handle specific tasks efficiently, avoiding the need to process all raw sensor data through the entire fusion pipeline, thus reducing overall computational burden while preserving accuracy
2Loss of information
If all sensor data is processed and stored for fusion, then complete data availability is achieved, but storage demands increase excessively
Solution Approach 1:
The curation engine extracts only the most relevant features and data elements from raw sensor streams based on pre-defined criteria and contextual relevance. Instead of storing and processing complete raw datasets, the system curates condensed representations that retain essential information for fusion decisions. This extraction approach maintains data availability for fusion while dramatically reducing storage requirements by eliminating redundant and irrelevant data
3Productivity
If sensor data fusion creates new actionable datasets, then predictive capability is enhanced, but system complexity increases
Solution Approach 1:
The linking engine serves as an intermediary between the curation and fusion engines. It establishes semantic, spatial, and temporal relationships between curated sensor data, creating a structured framework that guides the fusion process. This intermediary layer organizes data relationships before fusion occurs, enabling the generation of new actionable datasets with predictive capabilities while managing system complexity through structured intermediate representation
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.