Sensor Data Fusion With Pre-Storage Correlation for Real-Time Use
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor data fusion systems fail to create actionable data by correlating and fusing sensor data before storage, leading to excessive computational and storage requirements, and lack real-time data processing capabilities.
Innovation Solution
A system and method for sensor data fusion that includes capturing, curating, linking, fusing, inferring, and validating sensor data in real-time or near real-time, creating a unique dataset by correlating data before storage, thereby reducing computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor data is fused after storage in existing systems, then data availability is maintained, but computational requirements and storage needs become excessive
Solution Approach 1:
The system performs data fusion operations before storage by implementing a data fusion engine that correlates sensor data in real-time during the data ingestion phase. This preliminary fusion reduces the volume of data that needs to be stored while maintaining data availability, thereby decreasing computational requirements and storage needs without sacrificing reliability.
2Productivity
If sensor data is fused in real-time, then actionable data is provided, but power consumption increases
Solution Approach 1:
The system implements selective data fusion by identifying and fusing only the most relevant sensor data based on predefined criteria and data quality metrics. This partial action approach provides actionable insights in real-time without processing and fusing all available sensor data, thereby reducing power consumption while maintaining productivity.
Solution Approach 2:
The system dynamically adjusts fusion parameters such as correlation thresholds, data sampling rates, and fusion frequency based on operational conditions and data quality. This allows the system to optimize the balance between real-time processing capability and power consumption by changing operational parameters rather than maintaining fixed high-power settings.
3Quantity of substance
If heterogeneous sensor data is correlated before storage, then storage needs are reduced, but system complexity increases
Solution Approach 1:
The system segments the data fusion process into distinct functional modules including a data ingestion engine, data fusion engine, and data quality assessment engine. Each module handles specific aspects of heterogeneous data correlation independently, which reduces overall system complexity by breaking down the complex task into manageable, specialized components while still achieving storage reduction through pre-storage fusion.
4Loss of information
If data fusion creates new datasets, then actionable data is enhanced, but processing time increases
Solution Approach 1:
The system implements incremental data fusion that processes and creates new datasets in continuous small batches rather than waiting for complete datasets. This allows the system to rush through processing by providing actionable insights from partial data as it becomes available, reducing processing time while maintaining enhanced data quality through continuous fusion operations.
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.