Indoor Location Accuracy Using RVM Signal Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location measurement technologies, such as A-GPS, face significant challenges in accurately determining the location of user equipment (UE) indoors due to limited GPS signal reception, leading to errors of several hundred meters and inability to measure location without three or more detectable access points (APs).
Innovation Solution
A method utilizing machine learning and a relevance vector machine (RVM) regression to differentiate between line of sight (LOS) and non-line of sight (NLOS) signals from multiple access points, applying weights to mitigate NLOS signals and improve indoor location measurement accuracy, even with fewer than three detectable APs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If A-GPS technology is used for location measurement, then location accuracy is improved to within several meters, but GPS signal reception becomes limited or impossible in indoor environments
Solution Approach 1:
The patent introduces access points (APs) as intermediary devices to enable location measurement in indoor environments where GPS signals cannot penetrate. The APs act as mediators between the UE and the location estimation system, providing alternative signal sources that can be received indoors. The system uses signals from multiple APs to estimate location when GPS is unavailable, thus maintaining reliability in indoor settings.
2Reliability
If traditional location measurement methods are used indoors, then location can be measured using GPS through outdoor antennas, but location accuracy deteriorates significantly with errors of several hundred meters
Solution Approach 1:
The patent replaces the GPS satellite-based electromagnetic signal system with a terrestrial wireless local area network (WLAN) based system using access points. Instead of relying on GPS signals that cannot penetrate buildings, the system substitutes with Wi-Fi or other WLAN signals from APs that are designed to operate indoors. This substitution enables accurate indoor location measurement by using a different signal infrastructure appropriate for the indoor environment.
3Measurement precision
If machine learning and RVM regression are applied to differentiate LOS and NLOS signals, then indoor location accuracy is improved, but device complexity and computational requirements increase
Solution Approach 1:
The patent applies machine learning techniques to pre-train classification models that can distinguish between LOS and NLOS signal conditions. By performing preliminary training and model development offline, the system reduces the computational burden during real-time location estimation. The pre-trained models can quickly classify signal types and apply appropriate weighting factors without requiring complex real-time computations, thus balancing accuracy improvement with acceptable device complexity.
Data Source
AI summary
A method of measuring a location of a user equipment (UE) located indoors in a wireless network includes receiving signals from a plurality of access points (APs), performing training for machine learning using the received signals or information acquired from the received signals, setting a weight vector to be applied to a relevance vector machine (RVM) method using data subjected to the training for machine learning, and applying RVM regression to the set weight vector and measured strengths of the received signals and determining whether the signals received from the plurality of APs are line of sight (LOS) signals or non line of sight (NLOS) signals.