Broadcast Signal Interference for Stationary Human Proximity Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional human body proximity detection technologies, such as those using passive infrared sensors, fail to recognize user presence when the user is stationary, as they rely on changing voltage outputs which do not occur without movement.
Innovation Solution
A user proximity detection device and method that utilizes the interference phenomenon of broadcast signals to detect human body proximity by receiving signals in a target frequency band and inputting intensity data into a machine learning model, allowing for proximity determination without the need for separate transmitters and independent of user movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a passive infrared sensor (PIR) is used to detect human body proximity by amplifying changing output voltage, then the detection method is simple and does not require separate transmitters, but the proximity cannot be recognized when the user is stationary without movement
Solution Approach 1:
The patent replaces the mechanical movement-dependent PIR sensor system with an electromagnetic wave-based broadcast signal reception system. The receiver captures broadcast signals that are interfered with by the human body's electromagnetic properties, allowing proximity detection without requiring physical movement of the target object.
Solution Approach 2:
The patent changes the detection parameter from voltage output changes (which require movement) to signal intensity changes of received broadcast signals. The machine learning model analyzes signal intensity variations across different frequency bands to detect human body proximity, transforming the detection mechanism from movement-based to field-based parameter measurement.
2Reliability
If broadcast signal interference phenomenon is used to detect human body proximity, then proximity can be detected regardless of user movement, but the device complexity increases due to the need for receivers and machine learning models
Solution Approach 1:
The patent utilizes broadcast signals that are already present in the environment for proximity detection, making the existing receiver serve multiple functions: both receiving broadcast content and detecting human body proximity through signal interference analysis. This eliminates the need for separate dedicated transmitters and receivers solely for detection purposes.
Solution Approach 2:
The system uses the naturally occurring broadcast signals and their interference patterns with the human body as the detection mechanism. The broadcast signals themselves provide the information needed for detection through their interaction with the human body, requiring no additional active transmission components from the detection device.
3Speed
If PIR sensor output voltage is amplified to detect proximity, then the detection response is immediate, but the presence or absence of user cannot be recognized when the user is not moving
Solution Approach 1:
The machine learning model continuously analyzes the received broadcast signal intensities and compares them against learned patterns to determine proximity. This feedback-based approach processes signal variations in real-time, maintaining rapid response while accurately distinguishing between moving and stationary human bodies based on electromagnetic interference patterns.
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
Accurately detects human body proximity regardless of user movement, enabling effective control of external devices and improving convenience in various settings, including autonomous driving systems.
Implementation Method 1
human body proximity inference machine learning model that infers whether a human body is in proximity based on a change in intensity of a received signal according to proximity of the human body
Data Source
AI summary
A user proximity detection device including a receiver configured to receive a signal in a target frequency band, an inference-purpose data generator configured to measure an intensity of a signal received through the receiver and generate inference-purpose data based on the measured intensity of the signal, and a proximity detector configured to input the inference-purpose data into a human body proximity inference machine learning model to determine whether a human body is in proximity. The target frequency band is selected from a broadcast frequency band. In addition, at least one of an autonomous vehicle a user terminal or a server is linked or converged with an artificial intelligence module, an Unmanned Aerial Vehicle (UAV), a robot, an Augmented Reality (AR) device, Virtual Reality (VR), and devices related to 5G service.