An In-Ear Sleep Modulation SoC Featuring a CNN-LSTM Accelerator with Long-Kernel Memory Reuse and Runtime Dynamic Quantization.

Abstract

This work presents a 65 nm SoC for closed-loop in-ear sleep modulation. The SoC performs low-noise in-ear EEG sensing, CNN-LSTM-based sleep stage classification, and phase-specific auditory stimulation under 1 mW. A dedicated accelerator is developed, featuring a memory reuse technique to efficiently process long kernels required for low-frequency EEG feature extraction. A runtime dynamic quantization is incorporated, reducing model size by 3.88× with only a 0.28% loss in accuracy. A sensitivity of 98.3% is achieved for deep sleep detection, enabling effective sleep modulation.