Proximity Sensing: Modeling and Understanding Noisy RSSI-BLE Signals and Other Mobile Sensor Data for Digital Contact Tracing

Abstract

As we await a vaccine, social-distancing via efficient contact tracing has emerged as the primary health strategy to dampen the spread of COVID-19. To enable efficient digital contact tracing, we present a novel system to estimate pair-wise individual proximity, via a joint model of Bluetooth Low Energy (BLE) signals with other on-device sensors (accelerometer, magnetometer, gyroscope). We explore multiple ways of interpreting the sensor data stream (time-series, histogram, etc) and use several statistical and deep learning methods to learn representations for sensing proximity. We report the normalized Decision Cost Function (nDCF) metric and analyze the differential impact of the various input signals, as well as discuss various challenges associated with this task.

Accepted to IEEE/ICACT' 2021: International Conference on Advanced Communication Technology. Also presented at the Machine Learning for Mobile Health workshop at NeurIPS 2020

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• mixup: Beyond Empirical Risk Minimization
• Measurement-Based Evaluation Of Google/Apple Exposure Notification API For Proximity Detection in a Commuter Bus
• Coronavirus Contact Tracing: Evaluating The Potential Of Using Bluetooth Received Signal Strength For Proximity Detection
• Using Bluetooth Low Energy (BLE) Signal Strength Estimation to Facilitate Contact Tracing for COVID-19
• Flipping the Perspective in Contact Tracing