Analog Gated Recurrent Neural Network for Detecting Chewing Events
This work addresses the problem of low-power chewing detection for wearable health monitoring, representing an incremental advance with domain-specific application.
The paper tackled the problem of detecting chewing events using a novel analog gated recurrent neural network implemented in CMOS technology, achieving 91% recall and 94% F1-score on unseen data while consuming 1.1 uW of power.
We present a novel gated recurrent neural network to detect when a person is chewing on food. We implemented the neural network as a custom analog integrated circuit in a 0.18 um CMOS technology. The neural network was trained on 6.4 hours of data collected from a contact microphone that was mounted on volunteers' mastoid bones. When tested on 1.6 hours of previously-unseen data, the neural network identified chewing events at a 24-second time resolution. It achieved a recall of 91% and an F1-score of 94% while consuming 1.1 uW of power. A system for detecting whole eating episodes -- like meals and snacks -- that is based on the novel analog neural network consumes an estimated 18.8uW of power.