WiFi-Based Non-Intrusive User Association for Indoor Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user identification schemes for IoT applications in smart homes and buildings are intrusive, require active user participation, and are impractical for continuous operation, especially in WiFi-enabled environments, due to privacy concerns and the need for dedicated infrastructure.
Innovation Solution
A WiFi-based non-intrusive indoor positioning system (WinIPS) that uses unsupervised learning to associate WiFi-enabled mobile devices with their users by analyzing existing WiFi traffic data without requiring user cooperation or device modifications, employing a hierarchical clustering algorithm and signal propagation-based localization to estimate device locations and associate them with users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If biometric identification systems (fingerprint, iris scans) are used, then identification accuracy is improved, but user convenience deteriorates due to required physical interactions and hardware requirements
Solution Approach 1:
The patent replaces mechanical biometric identification systems (fingerprint scanners, iris cameras) with a wireless signal-based identification system. The system uses WiFi probe requests and data frames transmitted by mobile devices to infer user identity and location, eliminating the need for physical contact with biometric sensors and dedicated identification hardware.
Solution Approach 2:
The patent introduces WiFi probe requests and data frames as intermediary carriers of identification information. Instead of directly scanning biometric data, the system uses these wireless communication protocols as intermediaries to extract MAC addresses, signal strength, and location data that indirectly identify the user and their device.
2Adaptability or versatility
If vision-based approaches (face recognition, gait recognition) are used, then identification capability is improved, but privacy concerns and lighting requirements worsen system practicality
Solution Approach 1:
The patent replaces vision-based optical identification systems with wireless signal-based identification. Instead of using cameras to capture facial images or gait patterns, the system uses WiFi radio frequency signals to identify users, thereby eliminating privacy concerns related to visual surveillance and removing dependence on lighting conditions.
Solution Approach 2:
The patent changes the identification parameter from visual characteristics (face appearance, gait patterns) to wireless communication parameters (MAC address, RSSI, data frame content). This parameter transformation allows identification to occur independently of lighting conditions and reduces privacy intrusiveness.
3Measurement precision
If continuous probe request broadcasting is implemented, then device-user association accuracy is improved, but energy consumption and practicality deteriorate
Solution Approach 1:
The patent implements periodic sampling of WiFi probe requests and data frames instead of continuous broadcasting. The system captures identification-relevant information at regular intervals when devices naturally transmit WiFi signals, reducing energy consumption while maintaining sufficient association accuracy through the hierarchical clustering algorithm.
Solution Approach 2:
The patent leverages the mobile device's own WiFi communication activities (probe requests, data frames) as the identification source. Instead of requiring the device to continuously broadcast identification signals, the system passively captures and analyzes the WiFi traffic that the device already generates for normal network operations, making the identification process energy-efficient.
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
Enables accurate user and device association with high accuracy (95.8% for static devices) and seamless delivery of context-aware services without additional infrastructure or user participation, optimizing energy efficiency and personalized services in indoor environments.
Implementation Method 1
employing a hierarchical clustering algorithm and signal propagation-based localization to estimate device locations and associate them with users
Data Source
AI summary
A mobile device and user association system can include wireless routers to execute software for capturing data including received signal strength (RSS) values and media access controller (MAC) addresses for a number of mobile devices (MDs) from existing wireless fidelity (WiFi) traffic. The system can also include a server to receive the RSS values and MAC addresses of the MDs to estimate a location of each MD and generate historical location data of each MD, identify and filter out temporary MDs, classify each non-temporary MDs as either a static device (SD) or a mobile phone (MP), and associate a user with each SD and MP.