Research and experiment with some activation functions in sleep stage classification using deep learning methods

  • Thuy Tran Tan

Abstract

Sleep disorders are becoming increasingly complex in today’s
society. Analyzing sleep structure provides valuable information about
sleep types, sleep cycles, and variations in different stages. However, manual sleep stage classification is challenging and time-consuming, limiting
its clinical use. Deep learning methods have demonstrated promise for
automated sleep stage classification, but they face challenges such as
class imbalance and the need for interpretability. This paper investigates
three deep learning methods, TinySleepNet, TS-TCC, and CA-TCC, using the Expanded Sleep-EDF dataset. We evaluate the performance of
these methods and propose methods to address the aforementioned challenges. Our results show that deep learning methods can achieve high
accuracy for sleep stage classification, especially with the proposed enhancements. We also developed a sleep stage classification tool based on
methods.

Author Biography

Thuy Tran Tan

huy Trang Tan1[0009-0001-7117-1101], Thi Hong Nguyen1[0009-0001-0656-4830],
and Phi Long Duong1[0000-0003-0717-0005]
1Faculty of Information Systems, University of Information Technology, Vietnam
National University, Ho Chi Minh City, Vietnam. {19522384,
19521550}@gm.uit.edu.vn, longdp@uit.edu.vn

References

Thuy Trang Tan1[0009−0001−7117−1101], Thi Hong Nguyen1[0009−0001−0656−4830],
and Phi Long Duong1[0000−0003−0717−0005]
1Faculty of Information Systems, University of Information Technology, Vietnam
National University, Ho Chi Minh City, Vietnam. {19522384,
19521550}@gm.uit.edu.vn, longdp@uit.edu.vn
Published
2024-05-28