Sensor Data Fusion with Curation and Linking for Validated Inference
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 computational and storage requirements, and they do not generate new datasets that enhance sensor accuracy or 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 to mathematically link and validate sensor data, creating a unique dataset that enhances accuracy and reduces computational and storage demands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If sensor data is fused without prior curation and linking, then the fusion process is simpler and faster, but computational and storage requirements become excessive and actionable data is not generated
Solution Approach 1:
The system performs curation and linking of sensor data before fusion operations. The curation engine pre-processes sensor data by filtering, validating, and organizing it according to predefined criteria. The linking engine establishes relationships between curated data points from different sensors based on spatial, temporal, and semantic correlations. This preliminary processing reduces the volume and complexity of data requiring fusion, thereby decreasing computational and storage requirements while maintaining fusion speed.
Solution Approach 2:
The data fusion system is divided into distinct functional modules: a curation engine for preprocessing individual sensor streams, a linking engine for establishing data relationships, and a fusion engine for combining linked data. This segmentation allows each module to optimize its operations independently, with the curation and linking stages reducing data complexity before the fusion stage, thus balancing processing speed with resource efficiency.
2Adaptability or versatility
If traditional sensor data fusion is used, then existing systems can operate with current architecture, but they fail to create new datasets that enhance sensor accuracy or predict future events
Solution Approach 1:
The system introduces an intermediary processing layer between raw sensor data and final fusion output. This layer includes the curation engine that standardizes data formats and the linking engine that creates semantic relationships between data points from different modalities. These intermediaries transform heterogeneous sensor data into a unified, structured format that enables the fusion engine to generate new datasets with enhanced accuracy and predictive capabilities, while maintaining compatibility with existing sensor systems.
Solution Approach 2:
The system creates composite datasets by fusing data from multiple heterogeneous sensor sources (e.g., LIDAR, cameras, radar) through the curation-linking-fusion pipeline. The curation engine preserves unique characteristics of each sensor type, the linking engine establishes cross-sensor relationships, and the fusion engine combines them into composite data structures that contain richer information than individual sensors, thereby enhancing measurement precision and enabling predictive analytics.
3Reliability
If all sensor data is processed and stored for fusion, then complete data availability is achieved, but computational overhead and storage demands become excessive
Solution Approach 1:
The system applies partial processing to sensor data by selectively curating and linking only the most relevant data points based on predefined criteria such as data quality metrics, temporal recency, and spatial relevance. The curation engine filters out redundant or low-quality data, and the linking engine focuses on establishing relationships for high-priority data points. This partial action approach maintains sufficient data availability for reliable fusion while significantly reducing computational energy consumption compared to processing all sensor data in full detail.
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.