Mobile Context Detection via Motion-Audio Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile devices face challenges in reliably determining their context, such as being in a vehicle, due to limitations in using motion sensors alone, which may not differentiate between environments, and audio signals that can be affected by noise, leading to inaccurate context detection.
Innovation Solution
A mobile device equipped with both motion and audio sensors, utilizing a processing unit that combines movement and audio data through machine-learning algorithms and finite state machines to determine context, with conditional audio sensor activation to conserve power and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If motion sensors alone are used to determine context, then device complexity is reduced, but measurement precision deteriorates
Solution Approach 1:
The patent combines motion sensors and audio sensors into an integrated context determination system. The processing unit fuses data from both sensor types to improve context detection accuracy while managing overall system complexity through unified processing architecture.
Solution Approach 2:
The patent creates a composite sensing system that integrates multiple sensor modalities (motion and audio) to achieve superior context detection performance. This composite approach leverages the complementary strengths of different sensor types to overcome the limitations of individual sensors.
2Measurement precision
If audio sensors are always activated for context determination, then measurement precision improves, but use of energy increases
Solution Approach 1:
The patent implements conditional audio sensor activation based on motion sensor triggers. Instead of continuous operation, the audio sensor is activated periodically or event-driven when motion patterns suggest a context change is likely, reducing energy consumption while maintaining detection accuracy.
Solution Approach 2:
The processing unit uses motion sensor data to preliminarily assess the likelihood of context changes before activating the audio sensor. This preliminary filtering action prevents unnecessary audio sensor activation in situations where context changes are improbable, conserving energy while preserving detection capability when needed.
3Measurement precision
If audio signals are used without motion context filtering, then measurement precision improves, but object-affected harmful factors increase
Solution Approach 1:
The processing unit acts as an intermediary that filters and contextualizes audio signals based on motion sensor data. It mediates between raw audio input and context determination, using motion context as a gating mechanism to accept or reject audio-based context assessments, thereby reducing noise interference.
Solution Approach 2:
The system implements feedback loops where motion sensor data continuously informs audio sensor processing decisions. The processing unit uses real-time motion context to adjust audio signal processing parameters and threshold settings, creating a feedback mechanism that adapts to current environmental conditions and reduces noise impact.
Data Source
AI summary
According to a first aspect of the present disclosure, a mobile device is provided, comprising: a motion sensor configured to detect one or more movements of the mobile device; an audio sensor configured to capture one or more audio signals; a processing unit configured to determine a context of the mobile device in dependence on at least one movement detected by the motion sensor and at least one audio signal captured by the audio sensor. According to a second aspect of the present disclosure, a corresponding method for determining a context of a mobile device is conceived. According to a third aspect of the present disclosure, a corresponding computer program is provided.