Sensor Data Estimation via Correlation Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Systems with multiple sensors face significant delays in real-time sensor data collection and estimation due to the large amount of data required for missing data complementation, making them unsuitable for immediate responsiveness.
Innovation Solution
A sensor information complementing system that selects relevant sensors based on stored data, estimates information using only correlated sensors, and acquires data from other nodes when necessary, reducing the amount of data needed for estimation and improving precision by excluding irrelevant sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all sensor data is collected and used for missing data estimation, then estimation precision is improved, but processing time increases significantly
Solution Approach 1:
The patent segments the set of all sensors into two groups: relevant sensors whose data is correlated with the target sensor and irrelevant sensors whose data is not correlated. This segmentation allows the system to use only the necessary subset of sensor data for estimation, reducing processing time while maintaining estimation precision by focusing on correlated sensors only.
Solution Approach 2:
The patent applies local quality by treating different sensors differently based on their correlation with the target sensor. Relevant sensors are selected and their data is used for estimation, while irrelevant sensors are excluded. This selective approach ensures that only high-quality, correlated data is processed, maintaining precision while reducing the overall processing burden.
2Loss of information
If data from all sensors is used for estimation, then comprehensive information is obtained, but data transmission and processing load increases
Solution Approach 1:
The patent extracts only the relevant sensor data that is correlated with the target sensor from the complete set of sensor data. By taking out only the necessary information from the full dataset, the system maintains information completeness for the estimation task while significantly reducing data transmission and processing loads by excluding irrelevant sensor data.
3Reliability
If Manhattan distance formula is used to estimate missing data from stored similar data, then missing data can be complemented, but real-time responsiveness is lost
Solution Approach 1:
The patent implements a dynamic approach by determining correlation relationships between sensors in real-time or near real-time, rather than relying on static pre-stored similar data. This dynamic correlation analysis allows the system to quickly identify relevant sensors and perform estimation without the computational overhead of searching through stored similar datasets, thereby maintaining real-time responsiveness while ensuring data completeness.
Data Source
AI summary
Sensor information is regularly acquired from a plurality of sensors and stored. For each of the sensors, other sensors whose information is correlated are selected. When sensor information of a sensor is requested from an application program or the like, while if the requested sensor is available the sensor information is acquired directly from the sensor, if the requested sensor is unavailable the sensor information of sensors relevant to the sensor is acquired and the sensor information of the requested sensor is estimated. As a result, in a system comprising a plurality of sensors, sensor information of an unavailable sensor will be estimated in a short period of time.