Body Sensor Gesture Control via Acceleration Signal Filtering

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing body sensor systems face challenges in reliably distinguishing between user control commands and other movements, particularly when inertial sensors are attached to the body, leading to high false positive detection rates due to non-tap movements like respiration, heart beat, or accidental bumps.

Innovation Solution

The system employs gesture detection algorithms that analyze acceleration signals to identify predefined patterns such as tapping, shaking, and turning, using pre-filtering techniques like complementary median filters and adaptive median filters to suppress false alarms and ensure reliable detection of user-defined gestures without the need for physical buttons.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If inertial sensors are attached to the body for continuous monitoring, then real-time vital sign detection is improved, but false positive gesture detection increases due to body movements

Engineering Contradiction:

Improvegesture detection reliabilityVSAvoidfalse positive detection rate

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The gesture detection process is segmented into multiple independent analysis stages: raw acceleration signal acquisition, signal filtering (complementary and adaptive median filters), feature extraction (peak detection, zero-crossing analysis), pattern matching against predefined gesture templates, and validation through multiple criteria. This segmentation allows each stage to focus on specific aspects of gesture identification, improving overall reliability while reducing false positives from body movements.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Signal processing intermediaries are introduced between the raw sensor data and gesture recognition. Complementary median filters and adaptive median filters act as intermediaries to smooth noise while preserving gesture characteristics. Feature extraction intermediaries transform raw acceleration data into meaningful patterns that can be reliably matched against gesture templates, separating the detection process from direct sensor output.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If physical buttons are provided for sensor control, then user operation is simplified, but hygiene is compromised and device complexity increases

Engineering Contradiction:

Improveuser control convenienceVSAvoiddevice structure complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The mechanical button-pressing system is replaced with an inertial-based gesture recognition system. Instead of requiring physical contact with buttons, the system detects specific movement patterns (gestures) using the inertial sensor. This substitution eliminates mechanical wear, improves hygiene by removing exposed buttons, and reduces device complexity while maintaining ease of operation through intuitive motion-based control.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Speed

If threshold-based tap detection is used, then detection speed is improved, but false positive rate increases due to non-tap movements

Engineering Contradiction:

Improvegesture detection speedVSAvoidgesture detection accuracy

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The detection system uses dynamic, adaptive thresholds rather than fixed thresholds. The complementary median filter and adaptive median filter dynamically adjust to the signal characteristics, allowing the system to maintain high detection speed while adapting to varying motion conditions. This dynamic approach enables rapid response to genuine gestures while filtering out false positives from non-tap movements like respiration or walking.

Inventive Principle:

Principle #15Dynamics

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 enables reliable and user-friendly control of body sensors by reducing false positives and allowing for intuitive gesture-based operations, such as shaking for help calls, while maintaining low power consumption and hygiene by eliminating physical buttons.

Implementation Method 1

sensed accelerations of a body sensor are used for user control of the body sensor, which is realized by detecting predefined gesture patterns in the acceleration output

Methodology Applied

Scientific EffectAccelerometer: Accelerometer

Data Source

PatentUS9898182B2Gesture control for monitoring vital body signs

Publication Date: 2018.02.20 LIFELINE SYST INC

AI summary

The present invention reuses an accelerometer, or, more precise, sensed accelerations of a body sensor for user control of the body sensor. This is achieved by detecting predefined patterns in the acceleration signals that are unrelated to other movements of the patient. These include tapping on/with the sensor, shaking, and turning the sensor. New procedures are described that make it possible to re-use the acceleration sensing for reliable gesture detection without introducing many false positives due to non-gesture movements like respiration, heart beat, walking, etc.