Indoor Location Fingerprint Deduplication via Mutual Information Entropy
Solution Overview
Problem
Conventional mobile devices struggle with accurate location determination indoors due to the lack of GPS signals and high error margins, especially in buildings or tunnels, where GPS signals are unreliable or unavailable.
Innovation Solution
A system that uses a location server to receive survey data from sampling devices, interpolate and extrapolate signal measurements, and provide location fingerprint data to mobile devices for accurate indoor location determination, employing particle filters and Kalman filters to adjust weights and reduce error rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS signals are used for location determination, then outdoor location accuracy is achieved, but indoor location determination fails due to lack of satellite line of sight
Solution Approach 1:
The patent introduces Wi-Fi access points as intermediary signal sources to replace GPS satellites for indoor location determination. Sampling devices collect Wi-Fi signal measurements from access points throughout the venue, creating a fingerprint database that enables location tracking without direct satellite line of sight.
Solution Approach 2:
The patent creates a virtual GPS-like positioning system using Wi-Fi signals by constructing location fingerprint databases that replicate the functionality of GPS. The system copies the triangulation/trilateration approach of GPS but uses Wi-Fi access points as pseudo-satellites to provide location data indoors.
2Measurement precision
If multiple signal sources are used for location determination, then accuracy improves, but computation complexity increases due to correlated measurements
Solution Approach 1:
The patent extracts and removes correlated signal measurements from the calculation process by identifying signal sources with high mutual information entropy. The system separates independent signal sources from correlated ones, using only the independent sources for location computation to reduce redundancy and computational load.
Solution Approach 2:
The patent changes the parameter selection by using mutual information entropy as a criterion to filter signal sources. By transforming the selection criterion from simple signal strength to information-theoretic independence measure, the system optimizes the set of signal sources used for location determination.
3Manufacturing precision
If survey data is collected at many locations, then location fingerprint quality improves, but data size and processing time increase
Solution Approach 1:
The patent performs preliminary actions by pre-collecting and pre-processing survey data during venue setup. Location fingerprints are constructed in advance and stored in databases, so that during actual location determination, the system only needs to query and compare against pre-computed data rather than performing complex calculations in real-time.
Solution Approach 2:
The patent segments the venue into discrete sampling locations and associates each with specific Wi-Fi access point measurements. This segmentation allows the system to divide the large survey dataset into manageable location-specific fingerprints, enabling efficient retrieval and comparison during location determination.
Data Source
AI summary
Methods, systems, and computer program product for deduplicating location fingerprint data for a venue are described. A system including a location server, or a mobile device, or both, can deduplicate the location fingerprint data. Deduplicating the location fingerprint data can include identifying correlated signal sources the signals of which are mutually dependent such that measurements of one signal source can be used to predict measurements of another. The system can determine a mutual information entropy value for each pair of signal sources, and identify the correlated signal sources based on high mutual information entropy value. The system can adjust weights of the correlated signal sources in location determination