상세 보기
초록
In this letter, we propose an earthquake event classification model utilizing a feedback network and curriculum learning (CL). In particular, we propose the CL method with a feature concatenation using gated convolution so that CL can be effectively performed in consideration of the feedback structure. We show that the proposed model is effective through comparison experiments with the existing model using the earthquake dataset for Korean Peninsula and the Stanford earthquake dataset.
키워드
Earthquakes; Feature extraction; Convolution; Logic gates; Hidden Markov models; Kernel; Task analysis; Convolutional neural network (CNN); curriculum learning (CL); earthquake event classification; feature fusion; feedback
- 제목
- Feedback Network With Curriculum Learning for Earthquake Event Classification
- 저자
- Min, Jeongki; Ku, Bonwha; Ko, Hanseok
- 발행일
- 2022
- 유형
- Article
- 권
- 19