We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Predicting the Remaining Time before Earthquake Occurrence Based on Mel Spectrogram Features Extraction and Ensemble Learning.
- Authors
Zhang, Bo; Xu, Tao; Chen, Wen; Zhang, Chongyang
- Abstract
Predicting the remaining time before the next earthquake based on seismic signals generated in a laboratory setting is a challenging research task that is of significant importance for earthquake hazard assessment. In this study, we employed a mel spectrogram and the mel frequency cepstral coefficient (MFCC) to extract relevant features from seismic signals. Furthermore, we proposed a deep learning model with a hierarchical structure. This model combines the characteristics of long short-term memory (LSTM), one-dimensional convolutional neural networks (1D-CNN), and two-dimensional convolutional neural networks (2D-CNN). Additionally, we applied a stacking model fusion strategy, combining gradient boosting trees with deep learning models to achieve optimal performance. We compared the performance of the aforementioned feature extraction methods and related models for earthquake prediction. The results revealed a significant improvement in predictive performance when the mel spectrogram and stacking were introduced. Additionally, we found that the combination of 1D-CNN and 2D-CNN has unique advantages in handling time-series problems.
- Subjects
FEATURE extraction; BOOSTING algorithms; DEEP learning; EARTHQUAKES; CONVOLUTIONAL neural networks; SPECTROGRAMS; EARTHQUAKE prediction; EARTHQUAKE hazard analysis
- Publication
Applied Sciences (2076-3417), 2023, Vol 13, Issue 22, p12268
- ISSN
2076-3417
- Publication type
Article
- DOI
10.3390/app132212268