Convolutional Transformer-in-Transformer for Automatic Sleep Stage Classification

Moogyeong Kim, Wonzoo Chung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, a convolutional transformer-in-transformer architecture is proposed to capture local and global dependencies along time and frequency axes for automatic sleep staging. Existing sleep staging methods based on transformers have weaknesses in capturing local dependencies since they utilize fully-connected layers only. Inspired by the convolutional transformer in the computer vision domain that captures both local and global features well by taking advantage of both convolutional neural network and transformer, we propose to utilize convolutional projection with transformer-in-transformer architecture for feature extraction and aggregation. Numerical simulation results confirm that the proposed method outperforms existing sleep staging methods on the sleep heart health study (SHHS) dataset, in terms of macro F1-score.

Original languageEnglish
Title of host publication12th International Winter Conference on Brain-Computer Interface, BCI 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350309430
DOIs
Publication statusPublished - 2024
Event12th International Winter Conference on Brain-Computer Interface, BCI 2024 - Gangwon, Korea, Republic of
Duration: 2024 Feb 262024 Feb 28

Publication series

NameInternational Winter Conference on Brain-Computer Interface, BCI
ISSN (Print)2572-7672

Conference

Conference12th International Winter Conference on Brain-Computer Interface, BCI 2024
Country/TerritoryKorea, Republic of
CityGangwon
Period24/2/2624/2/28

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • Automatic Sleep Staging
  • Convolutional Transformer-in-Transformer (TNT)
  • Electroencephalogram (EEG)

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Signal Processing

Fingerprint

Dive into the research topics of 'Convolutional Transformer-in-Transformer for Automatic Sleep Stage Classification'. Together they form a unique fingerprint.

Cite this