Context Mining of Sedentary Behaviour for Promoting Self-Awareness Using a Smartphone.

Area of Science:

• Health Informatics
• Human-Computer Interaction
• Wearable Technology

Background:

• Increasing sedentary behavior poses significant health risks.
• Societal shifts contribute to prolonged periods of sitting.
• Effective monitoring and intervention strategies are needed to combat sedentary lifestyles.

Purpose of the Study:

• To develop a framework for mining temporal contexts of sedentary behavior using smartphone sensors.
• To enable real-time identification of sedentary situations and micro-contexts.
• To reduce sedentary behavior by promoting active breaks and self-management.

Main Methods:

• Utilizing smartphone accelerometer data to distinguish between 'still' and 'active' user states.
• Processing environmental sound data to recognize specific sedentary micro-contexts (e.g., computer work, TV watching).
• Implementing a framework for real-time context identification and user feedback through visualization.

Main Results:

• The proposed framework successfully identifies sedentary contexts in real-time.
• The system demonstrated a substantial reduction in sedentary behavior during testing.
• User-focused visualization aids in monitoring and managing sedentary routines.

Conclusions:

• Smartphone sensors can effectively mine temporal contexts of sedentary behavior.
• The developed application shows promise in reducing sedentary behavior and promoting physical activity.
• This approach supports user self-management for healthier routines.