Sleep staging with hyperdimensional networks
2020, Leonardo Hernández-Cano, Alejandro Hernández-Cano, and Ana Leonor Rivera
Traditionally, sleep staging is done by medical experts, but computer aid will improve sleeping evaluation. We proposea mathematically-motivated algorithm based on Dense Convolutional Networks that encodes polysomnography (PSG) recordingsinto a very high-dimensional vector space to perform sleep-stage scoring. We emphasize the flexibility of our model as it provides aframework to analyze single or multi-channel signals without relying on any statistical information about the dataset. To prove thefeasibility of our model we show results attaining comparable or better accuracy than current state-of-the-art models at a fractionof the time and very limited training data.