WiFi CSI Occupancy Detection via AI Signal Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wireless communication systems lack effective methods to detect and track occupancy in indoor environments using existing wireless infrastructure, limiting their ability to monitor human activity and optimize energy usage in smart environments.
Innovation Solution
A CSI-based passive occupancy detection system that utilizes existing wireless infrastructure to analyze changes in WiFi signals, leveraging AI and machine learning to model and estimate human presence within a sensing area, without requiring wearable devices, by processing metrics from wireless signals transmitted and received by multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CSI-based passive occupancy detection is implemented using existing WiFi infrastructure, then occupancy detection capability is improved, but system complexity increases
Solution Approach 1:
The system leverages existing WiFi devices and their continuous channel sensing mechanisms to perform occupancy detection without requiring dedicated sensing hardware. The WiFi devices self-serve by utilizing their built-in CSI capabilities and existing pilot signals, eliminating the need for separate occupancy detection infrastructure.
Solution Approach 2:
The invention enables existing WiFi communication devices to perform dual functions: maintaining wireless communication while simultaneously detecting occupancy. The CSI data, originally intended for communication optimization, is repurposed for occupancy detection, allowing one system to serve multiple purposes.
2Measurement precision
If fine-grained CSI measurements are collected for occupancy detection, then measurement precision is improved, but energy consumption increases
Solution Approach 1:
The system utilizes CSI measurements that are already being continuously collected by WiFi devices for communication purposes. Since these measurements are already being taken and processed for channel optimization, reusing them for occupancy detection avoids additional energy expenditure for separate sensing operations.
Solution Approach 2:
The same CSI measurement infrastructure and processing pipeline serve both communication optimization and occupancy detection functions. This multi-functional use of existing measurement capabilities eliminates the need for dedicated energy-consuming sensing hardware and operations.
3Measurement precision
If AI and machine learning models are deployed for occupancy detection, then detection accuracy is improved, but device complexity increases
Solution Approach 1:
The system employs intermediary processing layers that transform raw CSI data into features suitable for AI/ML models. These intermediaries include signal processing steps and feature extraction mechanisms that bridge the gap between raw wireless measurements and high-level occupancy detection, managing complexity through structured data transformation.
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 detection and tracking of occupancy status, enhancing behavioral analysis and energy efficiency by providing fine-grained information on human activity patterns, improving health assessments and energy management in residential and industrial settings.
Implementation Method 1
wireless signals transmitted and received by the plurality of wireless devices
Implementation Method 2
characterizing the disturbance of wireless signals to detect and track the occupancy status
Data Source
AI summary
Wireless device free “occupancy detection” in residential or small industrial properties is an essential function within the broader scope of smart environments. Applications include, monitoring a subject's, e.g. an elderly person, behaviour for health assessments or moving towards more efficient energy usage in smart homes. Changes and disruption of wireless signals transmitted and received by the plurality of wireless devices are collected and analyzed to infer the presence of a subject the sensing area. More particularly, CSI information over time analysed with one or models can estimate the presence of a subject within the sensing area whether the subject moves or stays still.