Wearable Blood Flow Action Recognition via Spectral Noise Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable devices face challenges in accurately recognizing user actions due to noise in blood flow information caused by body motion, which affects the accuracy of action and action part recognition.
Innovation Solution
The method and device acquire target blood flow information from specific parts of the body and use reference information to determine the action and action part by identifying differences in the blood flow patterns, employing techniques such as threshold setting, cross-correlation computation, and signal feature analysis to filter out noise and enhance recognition accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If blood flow information is used for action recognition, then the recognition capability is enhanced, but noise from body motion reduces measurement precision
Solution Approach 1:
The patent segments the blood flow signal into multiple frequency components through spectral analysis, separating the action-related frequency components from noise components. This allows selective processing of different frequency bands to enhance action recognition while filtering out motion noise.
Solution Approach 2:
The patent introduces reference information as an intermediary to compare with target blood flow information. By computing similarity between target and reference signals, the system can distinguish action-induced changes from motion-induced noise, improving measurement precision.
2Device complexity
If traditional image recognition or acceleration sensors are used, then device complexity is reduced, but recognition accuracy and versatility are limited
Solution Approach 1:
The patent replaces mechanical sensors (acceleration sensors) and complex imaging systems with photoplethysmography-based blood flow detection. This optical method provides richer action recognition capabilities while maintaining wearable device simplicity.
Solution Approach 2:
The patent transforms the approach from detecting mechanical motion (acceleration) to detecting physiological parameter changes (blood flow). This parameter transformation enables more accurate and versatile action recognition while using simpler optical sensors.
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 approach provides a new mechanism for accurately recognizing user actions and action parts by filtering noise from blood flow information, thereby improving the input capabilities of wearable devices and user experience.
Implementation Method 1
acquiring target photoplethysmography (PPG) information of the first part or a second part corresponding to the first part
Data Source
AI summary
The present application provides methods and devices for determining an action and/or an action part, and generally relates to the field of wearable devices. A method disclosed herein comprises: in response to that a first part on a body of a user executes an action, acquiring target blood flow information of the first part or a second part corresponding to the first part; and determining the first part and/or the action according to the target blood flow information and reference information. The methods and devices disclosed provide a new scheme for recognizing an action and/or an action part.