순환신경망 기반 저가형 뇌파 분류기를 이용한 생체신호 인터페이스 연구
A Study on a Bio-signal Interface with a RNN based Low-cost Brainwave Classifier
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
We proposed the RNN (Recurrent Neural Network)-based EEG classifier that can recognize the excited or unstable states of bedridden patients using a low-cost single-channel EEG measuring device. This is also efficient for elderly patients with difficulty in moving, paralysis below the neck, or illness. In spite of poor EEG acquisition signals due to low-cost devices, our proposed model using a GRU (Gate Recurrent Unit) neural network showed the accuracy of 100% when the state of a brain was normal or stable, and the accuracy of 90% when the state of a brain was excited or unstable.
Abstract
We proposed the RNN (Recurrent Neural Network)-based EEG classifier that can recognize the excited or unstable states of bedridden patients using a low-cost single-channel EEG measuring device. This is also efficient for elderly patients with difficulty in moving, paralysis below the neck, or illness. In spite of poor EEG acquisition signals due to low-cost devices, our proposed model using a GRU (Gate Recurrent Unit) neural network showed the accuracy of 100% when the state of a brain was normal or stable, and the accuracy of 90% when the state of a brain was excited or unstable.
참고문헌 (12)
- "2019 Japan Report - Thinking about Korea while looking at Japan"[URL]
- "2023 Elderly Statistics"[URL]
- J. -H. Lee, "EEG-based Customized Driving Control Model Design", IEMEK Journal of Embedded Systems and Applications, 18(2), pp.81~87 (2023)[DOI]
- D. R. Cox, "The regression analysis of binary sequences", Journal of the Royal Statistical Society. Series B(Methodological), 20(2), pp.215~232 (1958)
- T. K. Ho, "Random decision forests", 3rd International Conference on Document Analysis and Recognition, pp.278~282 (1995)
- G. Ke, "Lightgbm : A highly efficient gradient boosting decision tree", 31st Conference on Neural Information Processing Systems(NIPS 2017), pp.3146~3154 (2017)
- D. P. Kingma, "Adam : A Method for Stochastic Optimization", International Conference on Learning Representations, pp.1~15 (2015)
- S. Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997)[DOI]