A method, computer program, computer program product and system for configuration of a sensor system
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sensor systems face challenges in efficiently sampling and reconstructing data due to high requirements for sensor density and computational power, leading to increased costs, bandwidth demands, and prolonged acquisition times, while reducing sensor numbers or sampling frequency compromises accuracy.
Innovation Solution
A computer-implemented method for configuring a sensor system using a training dataset and a dictionary to determine an optimal sub-sampling operator, which selects the most important sample positions, allowing for reduced hardware and processing needs while maintaining measurement criteria, by forming a cost function and solving for the unknown variable Z to minimize error within specified constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the number of sensors and sampling frequency are reduced, then hardware cost and processing requirements are reduced, but measurement accuracy deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-computing an optimal sub-sampling operator during an offline training phase using a dense sensor array. This pre-computed operator captures the essential information needed for accurate measurements, which is then applied during online operation with a reduced sensor array. The training dataset is gathered beforehand to learn the optimal sampling pattern, resolving the contradiction between reduced hardware and maintained accuracy.
Solution Approach 2:
The patent changes the parameter of sensor array configuration from a fixed dense array to a dynamically optimized sparse array. By using the optimal sub-sampling operator derived from training data, the system transforms the sampling strategy to select only the most informative samples, thereby maintaining measurement accuracy while reducing the number of active sensors and sampling frequency.
2Quantity of substance
If the number of sensors and sampling frequency are reduced, then bandwidth requirements and processing needs are reduced, but data quality deteriorates
Solution Approach 1:
The patent applies the extraction principle by using the optimal sub-sampling operator to extract only the most informative samples from the sensor data. Instead of processing all samples from a dense array, the system identifies and extracts the critical subset of samples that contain the essential information, thereby reducing data quantity while preventing information loss.
Solution Approach 2:
The optimal sub-sampling operator is pre-computed during an offline training phase using a dense sensor array to capture comprehensive data patterns. This preliminary computation identifies which sample positions contain the most important information, allowing the system to selectively acquire only those critical samples during operation, thus maintaining data quality with fewer samples.
3Measurement precision
If a dense array of high frequency and resolution sensors is used, then measurement accuracy is improved, but acquisition time and computational power requirements increase
Solution Approach 1:
The patent applies preliminary action by performing offline training with a dense sensor array to pre-compute the optimal sub-sampling operator. This training phase captures the essential data patterns and relationships, which are then reused during online operation. As a result, the system can achieve comparable accuracy with a sparse array and reduced sampling frequency, significantly decreasing acquisition time without sacrificing measurement precision.
Solution Approach 2:
The patent applies partial action by using only the essential subset of sensors and samples identified by the optimal sub-sampling operator, rather than deploying the full dense array at high sampling frequency. The offline training ensures that this partial configuration captures sufficient information for accurate measurements, thereby reducing acquisition time while maintaining precision.
Data Source
Figure 1
Figure 2
Figure 3a~3b
AI summary
The present disclosure relates to a computer-implemented method for r configuration of a sensor system, said method (500) comprising providing (510,520), for a training dataset X consisting of at least one data element Xi for a measurement of the sensor system (200) relating to an initial set-up of the sensor system (200), a dictionary D forming a signal model comprising at least one basis function and at least one set of sparse coefficients S. Each set of sparse coefficients Si and the dictionary D represents one of the data elements Xi of said training dataset X. Determining (530) an optimal sub-sampling operator ψ based on the dictionary D and said at least one set of sparse coefficients S, wherein the optimal sub-sampling operator ψ is a selection of a true subset of the sample positions of the training dataset X, wherein the true subset corresponds to the sample positions containing the most important samples of the training dataset X. Configuring (540) the sensor system (200) based on the initial set-up of the sensor system (200) and the optimal sub-sampling operator ψ.