Sensor Data Fusion Using Curation and Entropy-Based Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems fail to create actionable data by curating and linking sensor data before fusion, leading to excessive storage and computational requirements, and they do not generate new datasets that enhance sensor accuracy or predict future events.
Innovation Solution
A system that includes a computer processor with curation, link, fusion, inference, and validation engines to mathematically link and fuse sensor data, creating a unique dataset that is validated and used to instruct robotic components, minimizing storage and computational demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data is stored and processed without curation and linking, then data fusion can be performed, but storage and computational requirements become excessive
Solution Approach 1:
The system performs preliminary curation and linking of sensor data before fusion operations. The curation engine pre-processes sensor data to identify and remove redundant information, while the link engine establishes relationships between data points. This preliminary processing reduces the volume of data that needs to be stored and processed during fusion, directly resolving the contradiction between maintaining sensor accuracy and reducing storage requirements
Solution Approach 2:
The system extracts only the essential and relevant features from sensor data during the curation phase. By identifying and removing redundant data points while preserving critical information, the system maintains the reliability needed for accurate sensor fusion while significantly reducing the quantity of data that must be stored and processed
2Reliability
If sensor data is stored and processed without curation and linking, then data fusion can be performed, but computational requirements become excessive
Solution Approach 1:
The curation and link engines perform preliminary processing to organize and optimize sensor data before fusion. This pre-processing establishes data relationships and removes redundancies, so that the actual fusion operations require fewer computational resources. The system pays computational cost upfront in organized processing to avoid much higher costs during fusion operations
Solution Approach 2:
The system segments the data processing workflow into distinct phases: curation, linking, and fusion. Each phase handles specific tasks with optimized computational requirements. The curation phase prepares data structures, the link phase establishes relationships, and the fusion phase performs the actual sensor integration. This segmentation allows each component to be computationally efficient while maintaining overall sensor accuracy
3Productivity
If traditional sensor data fusion is performed without creating new datasets, then existing data is utilized, but actionable data and predictions cannot be generated
Solution Approach 1:
The sensor fusion system automatically generates new actionable datasets and predictions without requiring external intervention. The inference engine continuously analyzes fused sensor data to identify patterns, predict future events, and generate actionable insights autonomously. This self-service capability transforms raw sensor data into valuable information products, directly improving productivity while the automated nature manages system complexity
Solution Approach 2:
The system implements feedback loops where generated predictions and inferences are validated against actual sensor data. The validation engine compares predicted outcomes with real-world measurements, and this feedback is used to refine and improve future predictions. This feedback mechanism ensures the generation of high-quality actionable data while managing complexity through iterative improvement rather than requiring overly complex initial designs
4Measurement precision
If manual validation of sensor data is performed, then data accuracy can be ensured, but human intervention is required and processing time increases
Solution Approach 1:
The validation engine performs automated validation of sensor data and fused results without human intervention. It uses statistical methods and comparison against expected patterns to assess data quality and accuracy automatically. This self-validating capability maintains high measurement precision while achieving full automation, eliminating the need for manual validation processes
Solution Approach 2:
The system replaces manual human validation with automated computational validation. The validation engine uses algorithms and statistical analysis to assess data accuracy, substituting the mechanical process of human review with an automated electronic system. This substitution maintains or improves measurement precision while dramatically increasing automation level and reducing processing time
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.