Wireless Terminal Geolocation Using Adaptive Radio Signatures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing geolocation methods based on RSSI levels in wireless communication systems face challenges such as high complexity, cost, and lack of precision due to dependence on fixed network topology, making them unsuitable for large areas and prone to obsolescence.
Innovation Solution
A method that reduces the size of the radio signature by selecting a limited number of base stations for measurement, incorporating their geographic positions, and using machine learning to estimate location, allowing for geolocation in large areas and adapting to network changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If a fixed set of base stations is used to define radio signature, then the geolocation method is simple to implement, but it becomes obsolete when network topology changes
Solution Approach 1:
The patent applies dynamics by making the radio signature adaptable to network topology changes. Instead of using a fixed set of base stations, the signature is dynamically reconstructed by selecting base stations based on signal strength thresholds and geographic position, allowing the system to adapt automatically when the network topology changes.
Solution Approach 2:
The patent changes the parameters used to define the radio signature from a fixed base station set to a dynamic selection based on signal strength (RSSI thresholds) and geographic coordinates. This parameter change allows the signature to remain valid across different network configurations.
2Measurement precision
If all base stations are included in the radio signature, then the geolocation precision is improved, but the complexity of the learning algorithm increases
Solution Approach 1:
The patent extracts only the necessary base stations for defining the radio signature by applying RSSI thresholds and geographic position filters. This extraction process reduces the number of base stations from the total network set to a minimal subset that provides sufficient geolocation precision while reducing algorithm complexity.
Solution Approach 2:
The patent applies local quality by selecting base stations based on their local signal strength characteristics and geographic positions relative to the terminal. Each base station is evaluated individually based on its contribution to the signature, rather than uniformly including all base stations.
3Measurement precision
If GPS receiver is integrated into the object, then the geolocation precision is improved, but the cost and energy consumption increase substantially
Solution Approach 1:
The patent substitutes the mechanical/GPS-based positioning system with a signal-processing-based system using existing wireless communication infrastructure. Instead of using dedicated GPS hardware, the system uses RSSI measurements from base stations combined with machine learning to achieve geolocation, eliminating the need for additional GPS receivers.
Solution Approach 2:
The patent makes the wireless communication system multi-functional by using the existing base station communication infrastructure for both data transmission and geolocation purposes. The same wireless channels used for communication are also used for measuring signal strength and determining position, eliminating the need for separate dedicated positioning hardware.
4Measurement precision
If RSSI levels from many base stations are used, then the geolocation accuracy is improved, but the function defining distance becomes very complex due to multiple influencing parameters
Solution Approach 1:
The patent introduces machine learning algorithms as an intermediary between raw RSSI measurements and distance estimation. Instead of directly modeling the complex physical relationship between RSSI and distance with explicit formulas, the machine learning model learns the mapping from signal strength patterns to positions, handling the complexity of multiple influencing parameters automatically.
Solution Approach 2:
The patent changes the approach from explicit mathematical modeling of distance-RSSI relationships to implicit pattern recognition through machine learning. By transforming the problem from solving complex physical equations to learning from training data, the system handles the complexity of multiple parameters (obstacles, interference, movement) without requiring explicit models for each factor.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method achieves accurate geolocation with reduced complexity and cost, being resilient to network topology changes and suitable for large geographic areas without additional hardware or energy consumption.
Implementation Method 1
The server then applies a learning algorithm to this data in order to produce a function which makes it possible to estimate, from a radio signature observed for a terminal located at an unknown position, the geographic position of the terminal
Data Source
Figure 1~2
Figure 3~4
Figure 5~6
AI summary
The invention concerns a method (10) for geolocating a terminal of a wireless communication system, based on a learning method making it possible to estimate the geographical position of a terminal using both a radio signature corresponding to a set of values representative of the quality of radio links existing between the terminal located at the sought position and a plurality of base stations of said wireless communication system, as well as a reference data set associating radio signatures with known geographical positions. To limit the complexity of the learning algorithm and to make it resistant to topology changes of the access network, the geolocation method is characterized in that each radio signature contains a selection of N values among the set of measured values, as well as the geographical positions of the corresponding base stations.