Context awareness through the use of wearable computing. Use Context-Aware Mask Reminder System Using Wearable Computing

Abstract:

This diploma thesis explores the development of a context-aware mask reminder system leveraging wearable computing technology. The system aims to detect the wearing of a medical mask through hand movement recognition using a smartwatch when entering public spaces where mask usage is obligatory for public health reasons, such as hospitals. Deep Learning models will be employed for mask detection, while BLE beacons will be utilized to determine proximity to areas mandating mask usage.

Introduction:

In the current global health landscape, the wearing of medical masks in public spaces plays a crucial role in preventing the spread of infectious diseases. However, individuals may forget or overlook the necessity of wearing masks, especially in areas where their usage is mandatory. This thesis proposes a novel solution utilizing wearable computing to address this issue by detecting mask wearing and providing timely reminders when entering designated public spaces.

Objectives:

• Develop a wearable computing system capable of detecting the wearing of a medical mask through hand movement recognition using a smartwatch.

• Implement Deep Learning models to accurately identify mask usage based on hand gestures captured by the smartwatch sensors.

• Integrate BLE beacons to determine the proximity of the user to areas where mask wearing is obligatory, such as hospitals or public transportation hubs.

• Design an intuitive user interface for the mask reminder system, providing timely notifications and alerts to the wearer. Methodology: The methodology involves the following steps:

• Research and Development: Explore existing wearable computing technologies and Deep Learning algorithms suitable for mask detection and context awareness.

• Data Collection and Model Training: Gather hand movement data for mask wearing and develop Deep Learning models trained on labeled datasets to recognize mask usage.

• BLE Beacon Integration: Deploy BLE beacons in designated public spaces and configure the wearable device to detect beacon signals for proximity detection.

• System Implementation: Develop the mask reminder system integrating the smartwatch, Deep Learning models, and BLE beacon functionality.

• Testing and Evaluation: Conduct comprehensive testing to assess the accuracy of mask detection, the effectiveness of proximity detection, and user satisfaction with the reminder system. Expected Contributions:

• Development of a context-aware mask reminder system using wearable computing technology, addressing the challenge of mask compliance in public health settings.

• Demonstration of the feasibility and effectiveness of utilizing Deep Learning models and BLE beacons for mask detection and proximity awareness.

• Potential impact on public health by promoting adherence to mask-wearing guidelines through timely reminders and notifications.

Conclusion:

This thesis presents a novel approach to enhancing mask compliance in public spaces through the integration of wearable computing technology. By leveraging Deep Learning models for mask detection and BLE beacons for proximity awareness, the proposed system offers a proactive solution to ensure adherence to mask-wearing guidelines, particularly in critical environments like hospitals. Moving forward, further research and refinement of context-aware wearable systems hold promise for bolstering public health initiatives and mitigating the spread of infectious diseases.