Bone Conduction Accelerometer Cough Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cough detection systems in electronic devices rely on microphones, which are susceptible to noise and external disturbances, leading to complex algorithms with high computational costs for accurate detection.
Innovation Solution
The system utilizes a bone conduction accelerometer to detect coughs by combining head movement detection and vocal activity detection, leveraging acceleration measurements in both the time and frequency domains to identify cough patterns with minimal false positives and negatives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If microphone-based cough detection is used, then cough detection capability is provided, but the system becomes susceptible to noise and external disturbances
Solution Approach 1:
The patent replaces the acoustic field (microphone) with the mechanical field (accelerometer) by detecting vibrations through bone conduction. The accelerometer senses mechanical vibrations transmitted through the skull bones during coughing, eliminating susceptibility to acoustic noise and external disturbances while maintaining cough detection capability.
Solution Approach 2:
The patent introduces bone conduction as an intermediary mechanism between the cough source and the sensor. By detecting vibrations transmitted through the skull bones rather than through air, the system creates an isolated detection path that is immune to external acoustic noise while still capturing cough-related vibrations.
2Measurement precision
If complex detection algorithms are used to ensure accurate detection, then detection precision improves, but computational processing costs increase
Solution Approach 1:
The patent extracts and analyzes specific characteristic features from acceleration signals that are unique to coughing events. By identifying and focusing on key temporal and spectral characteristics of cough vibrations, the system achieves high detection precision using simpler algorithms compared to analyzing complete audio signals.
Solution Approach 2:
The patent segments the acceleration signal analysis into distinct temporal phases corresponding to different stages of the cough event. This segmentation allows the use of simplified detection criteria for each phase, reducing overall algorithmic complexity while maintaining high precision in identifying complete cough events.
3Productivity
If wearable devices are used for cough monitoring, then real-time health data tracking is enabled, but device size and convenience are compromised
Solution Approach 1:
The patent integrates the accelerometer into multi-functional wearable devices such as smartwatches, fitness trackers, or hearing aids that users already wear regularly. This approach eliminates the need for dedicated cough monitoring devices, maintaining real-time monitoring capability while improving ease of operation through familiar, comfortable wearables.
4Reliability
If microphone-based systems are used, then cough detection is achieved, but power consumption increases
Solution Approach 1:
The patent replaces the acoustic detection system (microphone) with a mechanical vibration detection system (accelerometer). Accelerometers generally consume less power than microphones and associated audio processing circuits, thereby reducing overall power consumption while maintaining reliable cough detection capability through bone conduction vibration sensing.
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 precise cough detection with reduced noise immunity and lower power consumption compared to microphone-based systems, improving accuracy and battery life.
Implementation Method 1
bone conduction accelerometers are capable of sensing the sound/vibration propagated through human bones
Implementation Method 2
Head movement is detected based on acceleration measurements in the time domain
Implementation Method 3
Vocal activity is detected based on acceleration measurements in the frequency domain
Data Source
AI summary
The present disclosure is directed to cough detection for electronic devices, such as wireless headphones. The cough detection utilizes inertial sensors to perform both head movement detection and vocal activity detection. The dual identification of head movement and vocal activity allows improved detection accuracy, and minimal false detections caused by environmental noise.