The classification of infrasound events has considerable importance in improving the capability to identify the types of natural disasters.The traditional infrasound classification mainly relies on machine learning al...The classification of infrasound events has considerable importance in improving the capability to identify the types of natural disasters.The traditional infrasound classification mainly relies on machine learning algorithms after artificial feature extraction.However,guaranteeing the effectiveness of the extracted features is difficult.The current trend focuses on using a convolution neural network to automatically extract features for classification.This method can be used to extract signal spatial features automatically through a convolution kernel;however,infrasound signals contain not only spatial information but also temporal information when used as a time series.These extracted temporal features are also crucial.If only a convolution neural network is used,then the time dependence of the infrasound sequence will be missed.Using long short-term memory networks can compensate for the missing time-series features but induces spatial feature information loss of the infrasound signal.A multiscale squeeze excitation–convolution neural network–bidirectional long short-term memory network infrasound event classification fusion model is proposed in this study to address these problems.This model automatically extracted temporal and spatial features,adaptively selected features,and also realized the fusion of the two types of features.Experimental results showed that the classification accuracy of the model was more than 98%,thus verifying the effectiveness and superiority of the proposed model.展开更多
The verification of nuclear test ban necessitates the classification and identification of infrasound events.The accurate and eff ective classification of seismic and chemical explosion infrasounds can promote the cla...The verification of nuclear test ban necessitates the classification and identification of infrasound events.The accurate and eff ective classification of seismic and chemical explosion infrasounds can promote the classification and identification of infrasound events.However,overfitting of the signals of seismic and chemical explosion infrasounds easily occurs during training due to the limited amount of data.Thus,to solve this problem,this paper proposes a classification method based on the mixed virtual infrasound data augmentation(MVIDA)algorithm and multiscale squeeze-and-excitation ResNet(MS-SE-ResNet).In this study,the eff ectiveness of the proposed method is verified through simulation and comparison experiments.The simulation results reveal that the MS-SE-ResNet network can eff ectively determine the separability of chemical explosion and seismic infrasounds in the frequency domain,and the average classification accuracy on the dataset enhanced by the MVIDA algorithm reaches 81.12%.This value is higher than those of the other four types of comparative classification methods.This work also demonstrates the eff ectiveness and stability of the augmentation algorithm and classification network in the classification of few-shot infrasound events.展开更多
基金supported by the Shaanxi Province Natural Science Basic Research Plan Project(2023-JC-YB-244).
文摘The classification of infrasound events has considerable importance in improving the capability to identify the types of natural disasters.The traditional infrasound classification mainly relies on machine learning algorithms after artificial feature extraction.However,guaranteeing the effectiveness of the extracted features is difficult.The current trend focuses on using a convolution neural network to automatically extract features for classification.This method can be used to extract signal spatial features automatically through a convolution kernel;however,infrasound signals contain not only spatial information but also temporal information when used as a time series.These extracted temporal features are also crucial.If only a convolution neural network is used,then the time dependence of the infrasound sequence will be missed.Using long short-term memory networks can compensate for the missing time-series features but induces spatial feature information loss of the infrasound signal.A multiscale squeeze excitation–convolution neural network–bidirectional long short-term memory network infrasound event classification fusion model is proposed in this study to address these problems.This model automatically extracted temporal and spatial features,adaptively selected features,and also realized the fusion of the two types of features.Experimental results showed that the classification accuracy of the model was more than 98%,thus verifying the effectiveness and superiority of the proposed model.
基金supported by the Natural Science Foundation of Shaanxi Province(2023-JC-YB-221).
文摘The verification of nuclear test ban necessitates the classification and identification of infrasound events.The accurate and eff ective classification of seismic and chemical explosion infrasounds can promote the classification and identification of infrasound events.However,overfitting of the signals of seismic and chemical explosion infrasounds easily occurs during training due to the limited amount of data.Thus,to solve this problem,this paper proposes a classification method based on the mixed virtual infrasound data augmentation(MVIDA)algorithm and multiscale squeeze-and-excitation ResNet(MS-SE-ResNet).In this study,the eff ectiveness of the proposed method is verified through simulation and comparison experiments.The simulation results reveal that the MS-SE-ResNet network can eff ectively determine the separability of chemical explosion and seismic infrasounds in the frequency domain,and the average classification accuracy on the dataset enhanced by the MVIDA algorithm reaches 81.12%.This value is higher than those of the other four types of comparative classification methods.This work also demonstrates the eff ectiveness and stability of the augmentation algorithm and classification network in the classification of few-shot infrasound events.
