Indoor Positioning Accuracy via Fingerprint Batch Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing indoor positioning technologies, such as satellite-based GNSS, face challenges in providing seamless navigation indoors due to inadequate signal penetration through walls and roofs, leading to suboptimal performance compared to outdoor navigation.
Innovation Solution
A method and apparatus that utilize a processor and computer program code to analyze and improve positioning performance by selecting the best combination of fingerprint batches for generating radio environment representations, excluding batches that deteriorate positioning accuracy, and using WLAN and Bluetooth beacons to create optimized radio maps for indoor positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If all available fingerprint batches are used to generate radio environment representations, then the coverage and data availability improve, but the positioning accuracy deteriorates due to inclusion of flawed or useless data
Solution Approach 1:
The patent extracts and removes useless access points and their corresponding fingerprints from the radio environment representations. The system identifies APs that do not contribute to positioning accuracy and excludes them from the radio maps, thereby improving positioning performance by eliminating harmful data while preserving useful fingerprints.
Solution Approach 2:
The patent changes the parameter of data quality by dynamically evaluating and selecting only those fingerprint batches that meet certain quality criteria. The system adjusts the composition of radio environment representations based on measured positioning performance, excluding batches that deteriorate accuracy while maintaining those that improve it.
2Adaptability or versatility
If comprehensive fingerprint data collection is performed to improve positioning coverage, then the positioning availability improves, but the processing complexity and time increase
Solution Approach 1:
The patent extracts only the essential and useful components from large sets of fingerprint data. By removing useless access points and their associated fingerprints, the system reduces the volume of data that needs to be processed and stored, thereby simplifying the overall system complexity while maintaining comprehensive coverage through selective data retention.
Solution Approach 2:
The patent segments the fingerprint data by individual access points and evaluates each AP's contribution to positioning performance separately. This segmentation allows the system to process and evaluate data in manageable units, identifying and removing only those APs that do not contribute to accuracy, thereby reducing processing complexity while maintaining coverage.
3Reliability
If more fingerprint batches are included in radio environment representations, then the positioning reliability improves through more data, but the positioning accuracy worsens due to noisy or incorrect data
Solution Approach 1:
The patent converts the harmful effect of including useless fingerprint data into a benefit by using the presence of such data as an opportunity to identify and remove problematic access points. The system leverages the comprehensive data collection to detect and eliminate sources of error, thereby improving both reliability and accuracy simultaneously.
Solution Approach 2:
The patent implements a feedback mechanism where positioning accuracy is continuously evaluated based on test measurements, and this feedback is used to iteratively improve the radio environment representations. The system uses measured positioning performance to identify and remove useless APs, creating a closed-loop process that continuously enhances both reliability and accuracy.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
An apparatus obtains test data, which comprises radio samples with associated indications of reference locations. The apparatus estimates for each of a plurality of representations of a radio environment positions based on the radio samples of the test data and on the respective representation. Each representation has been generated based on a different selection of batches of fingerprints. Each fingerprint comprises a radio sample and an indication of a location of measurement. Each radio sample includes a characteristic of a radio signal transmitted by at least one beacon and an identification of the respective beacon. The apparatus determines for each representation a positioning performance by comparing the estimated positions with the reference locations. Based on the determined positioning performances, the apparatus determines whether any batch of fingerprints is to be excluded from further use and/or which representation is to be used as a valid representation of the radio environment.