Beacon Sensor Network Fingerprint for Dynamic Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Network-centric localization approaches in Wi-Fi enterprise networks face inaccuracies due to dynamic environmental factors affecting RF propagation, as traditional network mapping is labor-intensive and often performed infrequently, leading to sparse data and reduced localization accuracy.
Innovation Solution
A beacon sensor-based network fingerprint is generated through crowd-sourced data from mobile devices, combining access point and beacon sensor data to create an overlay network that accounts for dynamic environmental factors, improving localization accuracy by increasing temporal density of fingerprinting data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional network mapping is performed manually and infrequently, then labor cost is reduced, but localization accuracy deteriorates due to sparse data and inability to capture dynamic environmental factors
Solution Approach 1:
The system enables self-service by having mobile devices automatically perform fingerprinting measurements and contribute data to the network map without manual intervention. Clients autonomously collect RF signal data and beacon sensor data, then submit this data to the server, which automatically updates the network map. This eliminates the need for manual network mapping while enabling continuous, frequent updates to capture dynamic environmental changes.
Solution Approach 2:
The system implements feedback mechanisms where the server receives continuous data from multiple mobile devices, processes this information to update the network map, and uses this updated map to improve localization accuracy. The system also provides feedback to clients about their location, creating a closed-loop system that continuously refines the network map based on real-world measurements.
2Measurement precision
If Wi-Fi fingerprinting alone is used, then system complexity is kept simple, but localization accuracy deteriorates due to lack of reference for RF propagation variations
Solution Approach 1:
The system merges Wi-Fi fingerprinting with beacon sensor data to create a more robust localization system. By combining data from both RF signal strength measurements and beacon sensor readings, the system creates a composite network map that leverages the strengths of both technologies. This integration provides better reference data for RF propagation variations while maintaining manageable system complexity through unified processing architecture.
3Reliability
If manual network mapping is performed, then device autonomy is reduced, but data quality improves through controlled measurement processes
Solution Approach 1:
The system transitions from static, manual network mapping to a dynamic, autonomous system where mobile devices continuously collect and contribute data. The network map evolves automatically as new measurements are received from devices moving through the environment. This dynamic approach maintains data quality through multiple independent measurements while maximizing device autonomy, as each device independently contributes to the collective knowledge base.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Example implementations relate to beacon sensor based network fingerprints. For example, a location analytics device for beacon sensor based network fingerprints may include a processing resource and a memory resource storing readable instructions. The instructions may cause the processing resource to receive signal strength readings from a plurality of access points (APs) for transmissions originating from a target client device, compare the received signal strength readings for the target client device, to a beacon sensor based network fingerprint generated from a reference client device, and determine a location of the target client device based on the comparison of the received signal strength and the beacon sensor based network fingerprint.