Gaussian Process Location Estimation Using Signal Strength Bins
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current location determination technologies for mobile devices, such as GPS and radio wave triangulation, face challenges including high power consumption, accuracy issues, and environmental limitations, particularly in areas with limited satellite visibility or insufficient wave sources.
Innovation Solution
A method using Gaussian processes trained with signal strength measurements from wireless signal emitters to estimate device location, employing measurement bins to store and process data efficiently, reducing computational complexity and enabling location determination without specific location-finding hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS technology is used for location determination, then location accuracy is improved, but power consumption increases significantly
Solution Approach 1:
The patent replaces GPS (mechanical/satellite-based system) with a wireless signal-based location system that uses computational models to determine location based on signal strength measurements from wireless emitters, thereby reducing power consumption while maintaining location accuracy
Solution Approach 2:
The patent creates a computational model (Gaussian process) that copies and simulates the location determination function of GPS using alternative data (signal strength measurements) and mathematical models, allowing location to be determined without actual satellite signals
2Use of energy by moving object
If radio wave triangulation is used for location determination, then power consumption is reduced, but location accuracy deteriorates and environmental restrictions increase
Solution Approach 1:
The patent changes the approach from physical signal triangulation to statistical parameter modeling, using Gaussian processes to model signal strength patterns and predict location based on learned relationships between signal measurements and position
Solution Approach 2:
The patent introduces a computational intermediary (Gaussian process model) that mediates between raw signal strength measurements and location determination, allowing accurate location inference without direct physical signal analysis or triangulation
3Measurement precision
If computational models are trained on big data, then location estimation accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the training data into measurement bins organized by location and wireless emitter characteristics, allowing the complex big data to be processed in manageable chunks through histogram aggregation and statistical summaries rather than processing all data simultaneously
Solution Approach 2:
The patent extracts key statistical features (mean, standard deviation, median) from the complex signal strength data and uses these simplified representations to train the Gaussian process model, removing unnecessary data complexity while preserving essential location information
Data Source
AI summary
Disclosed are apparatus and methods for providing outputs; e.g., location estimates, based on signal strength measurements. A computing device can receive a particular signal strength measurement, which can include a wireless-signal-emitter (WSE) identifier and a signal strength value and can be associated with a measurement location. The computing device can determine one or more bins; each bin including statistics for WSEs and associated with a bin location. The statistics can include mean and standard deviation values. The computing device can: determine a particular bin whose bin location is associated with the measurement location for the particular signal strength measurement, determine particular statistics of the particular bin associated with a wireless signal emitter identified by the WSE identifier of the particular signal strength measurement, and update the particular statistics based on the signal strength value. The computing device can provide an estimated location output based on the bins.