SiFall: Practical Online Fall Detection with RF Sensing
arXiv:2301.03773 · doi:10.1145/3560905.3568517
Abstract
Falls present a significant global public health challenge, especially in today's aging society, underscoring the importance of developing an effective fall detection system. Non-invasive radio-frequency (RF) based fall detection has garnered substantial attention due to its wide coverage and privacy-preserving nature. Existing RF-based fall detection systems approach falls as an activity classification problem, assuming that human falls introduce reproducible patterns to the RF signals. However, we argue that falls are inherently accidental, making their impact uncontrollable and unforeseeable. We propose a fundamentally different approach to fall detection by shifting the focus from directly identifying hard-to-quantify falls to recognizing normal, repeatable human activities, thus treating falls as abnormal activities outside the normal activity distribution. We introduce a self-supervised incremental learning system incorporating FallNet, a deep neural network that employs unsupervised learning techniques. Our real-time fall detection system prototype leverages WiFi Channel State Information (CSI) sensing data and has been extensively tested with 16 human subjects.
arXiv commentThis paper is accepted by SenSys 2022. Copyright may be transferred without notice
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Scikit-learn: Machine Learning in Python
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Learning for Anomaly Detection: A Review
- Optimal detection of changepoints with a linear computational cost
- Empirical Evaluation of Rectified Activations in Convolutional Network
- RF-Based Human Activity Recognition Using Signal Adapted Convolutional Neural Network
- mD-Track: Leveraging Multi-Dimensionality in Passive Indoor Wi-Fi Tracking
- Time series classification for varying length series