Wrist Detection Algorithm Using Variance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable devices face challenges in accurately determining whether they are properly secured to a user's skin, leading to potential false identifications and inefficient operation.
Innovation Solution
The implementation of algorithms that calculate variances based on signals measured by light sensors and compare them to thresholds to improve the accuracy of wrist-detection, incorporating light emitters and sensors to assess the device's securement through variance checks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If simple presence detection is used to determine device secured state, then device operation can be adjusted, but false identifications occur reducing accuracy
Solution Approach 1:
The detection algorithm is segmented into multiple independent variance checks: first variance check compares signal variance to a first threshold, second variance check compares to a second threshold. This segmentation allows each check to contribute independently to the final determination, improving accuracy without requiring a monolithic complex algorithm.
Solution Approach 2:
The patent performs multiple variance checks (excessive action) rather than a single check. The first variance check uses a lower threshold to detect potential wrist presence, then a second variance check with a higher threshold confirms the determination. This partial repeated verification reduces false identifications while maintaining manageable algorithm complexity.
2Measurement precision
If multiple variance checks with thresholds are implemented, then accuracy of wrist-detection is improved, but algorithm complexity increases
Solution Approach 1:
The measurement process is segmented into distinct variance calculation stages. Each stage computes variance against a specific threshold independently, allowing the system to achieve high measurement precision through multiple simple comparisons rather than one complex measurement algorithm.
Solution Approach 2:
The patent changes the threshold parameter between variance checks. The first variance check uses a first threshold value, while the second variance check uses a different second threshold value. This parameter variation enables the system to detect different signal characteristics at different sensitivity levels, improving precision without requiring complex adaptive algorithms.
3Ease of operation
If device functions remain enabled continuously, then user convenience is maintained, but power consumption increases
Solution Approach 1:
The system continuously monitors signal variance and uses this feedback to dynamically adjust device operation. When variance indicates the device is off-wrist, the system provides feedback to disable certain functions, reducing power consumption. When on-wrist is detected, functions are re-enabled, maintaining user convenience. This feedback loop optimizes power usage based on actual device state.
Solution Approach 2:
The patent implements dynamic adjustment of device functions based on detected wrist presence. Rather than static enabled/disabled states, the system dynamically transitions between operational modes according to real-time variance analysis, balancing power savings with user convenience based on actual usage conditions.
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
Enhances the accuracy of determining whether a device is secured to the user's skin, enabling appropriate adjustments in operation, such as disabling functions for power-saving or security purposes, and preventing false identifications.
Implementation Method 1
a photoplethysmogram (PPG) signal can be obtained by measuring the perfusion of blood within the skin of a user
Data Source
AI summary
Algorithms for detecting whether a device is properly secured to a user's skin are described. The operation of a device, such as a wearable device, can be adjusted based on whether the device is properly secured to a user's skin (e.g., on-wrist) or not properly secured to the user's skin (e.g., off-wrist). For example, certain functions can be disabled for power-saving, security or other purposes if the device is off-wrist. In order to avoid falsely identifying the device as off-wrist or on-wrist, algorithms for detecting whether the device is on-wrist or off-wrist can calculate one or more variances based on signals measured by a light sensor and compare the one or more variances with one or more thresholds. Comparing the one or more variances to the one or more threshold can improve the accuracy of wrist-detection algorithms.