AutoencoderClass imbalanceDeep learningThe rapid growth of network-related services in the last decade has produced a huge amount of sensitive data on the internet. But networks are very much prone to intrusions
The idea of using a deep autoencoder to encode seismic waveform features and then use them in different seismological applications is appealing. In this paper, we designed tests to evaluate this idea of using autoencoders as feature extractors for different seismological applications, such as event...
1) For simplicity, thanks to the strong feature representation ability of vision transformers, the ViTPose pipeline can be extremely simple. For example, it does not require any specific domain knowledge to design the backbone encoder and enjoys a plain and non-hierarchical encoder structure by ...
The authors explored the application of deep neural networks within ATHMoS in [27]. An autoencoder was applied for automatic feature extraction, and a Long-Short-Term-Memory (LSTM)-Recurrent Neural Network (RNN) structure was used for anomaly detection. The authors found, however, that due to...
Jiang et al. [54] adopted a semi-supervised learning approach to improve the precision, recall, and F1-score with their Tri-CAD anomaly detection framework. It applies to univariate time series and uses various techniques such as wavelet transform and deep learning autoencoders. ...