Abnormality Detection Device for Ionospheric TEC Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for predicting abnormalities in the ionosphere's total electron content (TEC) value using regression models are not accurate enough for reliable abnormality determination.
Innovation Solution
An abnormality detection device that selects a central observation station and surrounding peripheral stations based on distance, calculates a predicted observation value from the peripheral stations, and determines abnormality by estimating errors and correlation values, improving prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a regression model is used to predict TEC values at each observation station independently, then the detection process is simple, but the prediction accuracy is insufficient leading to unreliable abnormality determination
Solution Approach 1:
The patent combines multiple observation stations into a networked system where a central observation station is selected and surrounded by peripheral observation stations. The regression model predicts the central station's TEC values using data from peripheral stations, and abnormality is determined by comparing predicted versus actual values across the network. This merging approach improves prediction accuracy while maintaining manageable system complexity through structured spatial relationships.
2Measurement precision
If more observation stations are used to improve prediction accuracy, then the detection precision improves, but the system complexity and computational load increase
Solution Approach 1:
The patent segments the observation station network into a hierarchical structure with one central observation station and multiple peripheral observation stations. This segmentation allows the system to utilize data from multiple stations for improved accuracy while organizing the complexity into manageable segments with clear functional roles. The central station focuses on abnormality determination while peripheral stations provide predictive data, dividing the computational workload.
Solution Approach 2:
The patent applies local quality by assigning different functional roles to different stations based on their spatial relationships. The central observation station serves as the focal point for abnormality determination, while peripheral stations serve specific predictive functions. This differentiation optimizes the contribution of each station to the overall system performance without requiring uniform complexity across all stations.
3Ease of operation
If independent prediction is performed at each observation station, then the processing is straightforward, but false reporting occurs due to insufficient accuracy
Solution Approach 1:
The patent implements a feedback mechanism where the system predicts TEC values at the central observation station using data from peripheral stations, compares these predictions with actual measured values, and uses the estimation error to determine abnormality. This feedback loop continuously refines the abnormality determination process, improving reliability while maintaining processing simplicity through automated comparison and error analysis.
Data Source
AI summary
Prediction accuracy of a regression model in abnormality determination of a TEC value is improved. Processing executed by an abnormality detection device includes: acquiring an observation value of each of a plurality of observation stations; selecting a central observation station from among the plurality of observation stations, and selecting a plurality of peripheral observation stations from among the plurality of observation stations on the basis of a distance from the central observation station; calculating a predicted observation value of the central observation station based on the observation value of each of the plurality of peripheral observation stations; calculating an estimation error between the predicted observation value and an actual measured value of the central observation station; and determining whether or not the actual measured value of the central observation station is abnormal based on the estimation error.