Therefore, it is valuable to predict ENSO early and accurately to minimize these effects. However, predicting the strength of ENSO remains a challenge due to its complexity (Sun et al., 2016;Timmermann et al., 2018). Also, the increasing diversity of ENSO behavior since 2000 has led to a growing interest in the type of ENSO events (Geng et al., 2020). ENSO can be mainly divided into Eastern Pacific (EP) and Central Pacific (CP) types (Yeh et al., 2009), based on the distribution of the Sea Surface Temperature Anomaly (SSTA) during its maturation phase. However, some events that the SSTA is relatively high over the central and eastern Pacific Ocean cannot be classified as CP or EP types. Zhang et al. ( 2019) classified ENSO into EP, CP, and a mixture of the two (MIX) types of EI Niño (La Niña). To the best of our knowledge, the definition of ENSO type has not come to an agreement. Because the effects of different ENSO types vary greatly, for example, different EI Niño events have a different impact on US winter temperatures (Yu et al., 2012) and the East Asian climate (Yuan & Yang, 2012). Hence, the prediction of ENSO type is important for improving the quality of climate forecasts.
In the field of human health monitoring, intelligent diagnostic methods have drawn much attention recently to tackle the health problems and challenges faced by patients. In this paper, an efficient and flexible diagnostic method is proposed, which enables the simultaneous use of a machine learning method and sparsity-based representation technique. Specifically, the proposed method is based on a convolutional neural network (CNN) and generalized minimax-concave (GMC) method. First, measured potential signals, for instance, electroencephalogram (EEG) and electrocardiogram (ECG) signals are directly inputted into the designed network based on CNN for health conditions classification. The designed network adopts small convolution kernels to enhance the performance of feature extraction. In the training process, small batch samples are applied to improve the generalization of the model. Meanwhile, the ''Dropout'' strategy is applied to overcome the overfitting problem in fully connected layers. Then, for a record of the interested EEG or ECG signal, the sparse representation of useful time-frequency features can be estimated via the GMC method. Case studies of seizure detection and arrhythmia signal analysis are adopted to verify the performance of the proposed method. The experimental results demonstrate that the proposed method can effectively identify different health conditions and maximally enhance the sparsity of time-frequency features. INDEX TERMS Feature extraction, convolutional neural network, deep learning, sparse representation, health monitoring.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.