Wireless Presence Detection Using Segmented Signal Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Wi-Fi based presence detection systems face challenges in accurately differentiating between Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) environments and detecting motion due to limitations in extracting reliable features from wireless channel data, especially in multi-device and multi-room scenarios.
Innovation Solution
The method involves extracting statistical features from channel state information (CSI), received signal strength (RSS), and round-trip time (RTT) data to differentiate between LOS and NLOS conditions and detect user motion, using techniques such as computing skewness, variance, and standard deviation, and employing machine learning and graph neural networks to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If statistical features are extracted from wireless signals in multi-device scenarios, then presence detection capability is improved, but measurement precision deteriorates due to signal interference and obstructions
Solution Approach 1:
The patent segments the wireless signal analysis by separating LOS and NLOS signal processing into distinct feature extraction pathways. Different statistical features are computed for LOS and NLOS conditions independently, allowing the system to handle each signal type with optimized metrics rather than using a single generic processing approach that would compromise precision.
Solution Approach 2:
The patent changes the parameters used for signal analysis by computing multiple statistical features (skewness, variance, standard deviation) that are specifically adapted to different signal conditions. By adjusting the feature set based on whether signals are LOS or NLOS, the system maintains measurement precision across varying environmental conditions while enabling robust presence detection.
2Measurement precision
If multiple statistical features are computed from wireless signals, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-determining which statistical features to compute based on the signal type (LOS or NLOS). The system prepares and applies appropriate feature extraction algorithms in advance for each signal condition, avoiding the need to compute all possible features for every signal. This reduces processing complexity while maintaining high detection accuracy through targeted feature selection.
3Reliability
If feature analysis is performed to distinguish LOS and NLOS conditions, then reliability of presence detection is improved, but loss of time increases due to additional processing
Solution Approach 1:
The patent segments the feature analysis process into distinct LOS and NLOS processing streams with dedicated feature sets for each. This segmentation allows parallel processing of different signal types through optimized pathways, reducing the total processing time required to achieve reliable presence detection compared to a unified sequential analysis approach.
Data Source
AI summary
One embodiment provides a method for presence detection based on wireless signal analysis, the method comprising extracting features from wireless signals transmitted between a plurality of stations (STAs) and at least one access-point (AP) located within a space comprising a plurality of portions, wherein the AP is located in a particular portion of the space and a plurality of STAs are located in different portions in the space such that there are non-line-of-sight (NLOS) signals between the AP and the plurality of STAs as a result of signal obstructions within the space, processing the features using feature analysis, and detecting a location of a user motion within a particular portion of the plurality of portions of the space based on the feature analysis.