Step Counting Algorithm for Intermittent Movement Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing step counting devices have low accuracy due to failure in recording steps during intermittent movements, leading to incorrect counting when users stop and go during walking.
Innovation Solution
A method that involves obtaining acceleration data with effective peaks, determining time intervals between peaks, and updating step counting data based on feature information within specific conditions, such as variances in amplitude and time intervals, to improve accuracy during intermittent movements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the step counting device uses a predetermined number of effective peaks to update step counting data, then the device structure is simple, but the step counting accuracy is low during intermittent movements
Solution Approach 1:
The patent segments the step counting process into different handling modes: continuous movement mode (using predetermined peak thresholds) and intermittent movement mode (using time interval analysis and feature information assessment). This segmentation allows the system to apply different algorithms based on movement patterns, improving accuracy without requiring complete redesign of the entire system.
Solution Approach 2:
The patent implements dynamic adjustment of step counting parameters based on movement state. When intermittent movement is detected (time interval greater than preset value), the system dynamically switches to a more complex assessment mode involving feature information extraction and variance analysis. This dynamic adaptation resolves the contradiction by adjusting complexity only when needed for accuracy.
2Reliability
If the step counting device requires effective peaks to reach a predetermined number, then the counting criterion is simple, but steps during short intermittent movements are not recorded
Solution Approach 1:
The patent performs preliminary detection of time intervals between effective peaks before applying the predetermined number criterion. When a time interval exceeds the preset value, the system proactively switches to intermittent movement handling mode, extracting feature information and assessing variances in advance. This preliminary action ensures reliable detection of intermittent movements before they are missed by the standard counting method.
Solution Approach 2:
The patent changes the counting parameters dynamically: for continuous movement, it uses a fixed predetermined number of peaks; for intermittent movement, it transitions to analyzing time intervals, extracting feature information, and evaluating variances. This parameter change enables the system to reliably detect and record steps during intermittent movements while maintaining simplicity during continuous movement.
3Productivity
If the step counting device updates data only when effective peaks reach a threshold, then the processing is efficient, but the counting accuracy decreases during stop-and-go movements
Solution Approach 1:
The patent implements periodic checking of time intervals between effective peaks. When a time interval exceeds the preset value, it triggers a periodic assessment of feature information and variances. This periodic action maintains processing efficiency by not continuously applying complex algorithms, while still achieving high accuracy by periodically evaluating intermittent movement conditions and adjusting counting accordingly.
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 step counting accuracy by assessing and updating data during short movements, ensuring accurate recording of steps even when users stop and go, thereby improving the overall accuracy of step counting devices.
Implementation Method 1
an acceleration sensor is generally used to collect acceleration data of the user while walking
Data Source
AI summary
Disclosed are a step counting method, a step counting device, and a computer readable storage medium. The step counting method includes: obtaining acceleration data, the acceleration data including effective peaks (S100); determining a time interval between a current effective peak and an effective peak obtained last time; when the time interval is greater than a preset interval, obtaining a data area of the effective peaks until a next time interval is greater than the preset interval; when the number of effective peaks within the data area is less than a preset value, determining feature information of the effective peaks within the data area; and when the feature information of the effective peaks within the data area satisfies a preset condition, updating step counting data.


