Body-Attached Microphone for Activity Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for activity recognition in mobile devices, such as classifying user motion, face challenges with high power consumption and limited accuracy when using accelerometer sensors and external microphones.

Innovation Solution

The use of body-attached microphones to capture internal sound vibrations, which improves accuracy and reduces power consumption by distinguishing activities that do not generate distinct external sounds and is less susceptible to ambient noise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If accelerometer sensors and external microphones are used for activity recognition, then device functionality is provided, but power consumption is high and accuracy is limited

Engineering Contradiction:
Improveactivity recognition accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts the microphone from its traditional external position and places it inside the user's body (e.g., in the ear canal or attached to the skin). This extraction allows the system to capture internal body vibrations directly, improving activity recognition accuracy while reducing the need for high-power external sensors and processing

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces the user's body as an intermediary medium between the sound source and the microphone. By capturing vibrations transmitted through body tissues, the system obtains more accurate activity information with lower power consumption compared to using external microphones that must compete with ambient noise

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If external microphones are used to capture ambient sounds, then activity detection is possible, but accuracy is limited due to ambient noise interference

Engineering Contradiction:
Improveactivity detection accuracyVSAvoidambient noise interference
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The microphone is extracted from the external environment and placed inside the body, removing it from the harmful ambient noise field. This allows clean capture of internal vibrations without contamination from external sounds

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent converts the body's own tissues into a beneficial transmission medium. The body tissues that could potentially dampen sounds become instead a direct transmission path for vibration signals, providing clear activity information free from ambient noise interference

Inventive Principle:
Principle #22Blessing in disguise (Convert harm into benefit)

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 enhances the accuracy of activity classification and reduces power consumption by utilizing internal sound waves, effectively addressing the limitations of existing technologies.

Implementation Method 1

body attached microphones to capture sound of vibrations transported through the user's body

Methodology Applied
Scientific EffectSound wave transmission through body: Sound

Implementation Method 2

detect motion of the terminal and thereby the motion and activity of the user

Methodology Applied
Scientific EffectAcceleration detection: Accelerometer

Data Source

PatentEP2636371B1Activity classification
Publication Date: 2016.10.19 SONY MOBILE COMM INC
  • EP2636371B1 patent drawingFigure 1~2
  • EP2636371B1 patent drawingFigure 3~4

AI summary

The present invention relates to a method and device for classifying an activity of an object, the method comprising: receiving a sound signal from a sensor, determining type of sound based on said sound signal, and determining said activity based on said type of sound.