Wireless Sensor Access Point Localization via Radio Signal Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current workplace monitoring systems lack effective methods for detecting and localizing access points within a space, leading to inefficiencies in tracking device locations and human occupancy, which hinders optimal space utilization and management.
Innovation Solution
A method involving wireless sensors that detect radio signals between computing devices and access points, extracting unique identifiers, and using machine learning and computer vision techniques to develop access point clustering models and device classification models, enabling the localization of access points and tracking of human occupancy within the space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If wireless sensors detect radio signals and extract unique identifiers to localize access points, then measurement precision of device location is improved, but device complexity increases due to the need for clustering models and signal processing
Solution Approach 1:
The system segments the space into multiple zones or areas and classifies devices into different groups based on their signal characteristics and location patterns. This segmentation allows the complex task of device localization to be broken down into manageable units, improving measurement precision while distributing the computational complexity across multiple processing nodes rather than requiring a single complex system
Solution Approach 2:
The patent introduces intermediary components such as access point clustering models and signal processing modules that act as mediators between the wireless sensors and the final localization output. These intermediaries simplify the overall system architecture by providing standardized processing layers that can be independently optimized, reducing the complexity burden on individual components while maintaining high measurement precision
2Productivity
If access point clustering models and device classification models are developed using machine learning, then productivity of space utilization analysis is improved, but loss of information increases due to the complexity of data processing and model training
Solution Approach 1:
The system performs preliminary actions by pre-training access point clustering models and device classification models using historical data and patterns. These pre-trained models capture essential relationships and patterns in advance, enabling rapid and accurate space utilization analysis without requiring complex real-time processing, thus improving productivity while preserving information accuracy through the models' learned representations
Solution Approach 2:
The patent creates simplified representations or copies of the complex device and access point relationships through the clustering models. These models generate summarized information about device groups and their spatial patterns, which can be processed more efficiently than the raw data while maintaining the essential information needed for space utilization analysis, thereby improving productivity without significant information loss
3Device complexity
If manual checks for occupancy and device location are performed, then device complexity is reduced, but loss of time increases due to the need for manual intervention in monitoring
Solution Approach 1:
The system implements self-service by enabling wireless sensors to automatically detect radio signals, extract identifiers, and perform localization without requiring manual intervention. The access point clustering models and device classification models operate autonomously to analyze space utilization patterns, eliminating the need for manual checks while reducing monitoring time. The system serves itself by automatically generating insights and reports that would otherwise require human analysis
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
This solution allows for accurate mapping of access points and computing devices, providing insights into space utilization, reducing manual checks, and enabling informed decisions on occupancy and resource allocation.
Implementation Method 1
detecting a set of radio signals transmitted between a set of computing devices and a set of access points arranged in the space
Data Source
AI summary
One variation of a method includes: detecting a set of radio signals transmitted between a set of computing devices and a set of access points in the space; for each radio signal in the set of radio signals, extracting a pair of unique identifiers representing an initial computing device and an initial access point from the radio signal; storing the pair of unique identifiers in a set of containers; accessing a known position of the wireless sensor; accessing a signal transmission range of an access point based on the set of containers; deriving a signal strength of a radio signal based on the known position and the signal transmission range; in response to the signal strength exceeding a threshold signal strength, deriving a location unit occupied by the access point; and aggregating the location unit into a localization map representing locations of the set of access points in the space.