Cascaded Contextual Region-based Convolutional Neural Network for Event Detection from Time Series Signals: A Seismic Application

Many existing event detection models are point-wised, meaning they classify data points at each timestamp. In this paper, inspired by object detection in 2D imagery, we propose a CNN-based model to give two coordinates for each event denoting the beginning and end. To capture events with dramatically various lengths, we develop a cascaded model which consists of more downsampling layers and we directly use receptive fields as anchors. The take into account the temporal correlation of proposals, we build a contextual block inspired by atrous convolutions. Label dependent loss is used to mitigate the impact caused by omitted positive events.

[1]  Oliver Kramer,et al.  Event Detection in Marine Time Series Data , 2015, KI.

[2]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[3]  George Papandreou,et al.  Rethinking Atrous Convolution for Semantic Image Segmentation , 2017, ArXiv.

[4]  Christopher John Young,et al.  A comparison of select trigger algorithms for automated global seismic phase and event detection , 1998, Bulletin of the Seismological Society of America.

[5]  Iasonas Kokkinos,et al.  DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.

[8]  Milos Hauskrecht,et al.  Mining recent temporal patterns for event detection in multivariate time series data , 2012, KDD.

[9]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[10]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[11]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[12]  Clara E Yoon,et al.  Earthquake detection through computationally efficient similarity search , 2015, Science Advances.

[13]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Gautam Shroff,et al.  Multi-sensor event detection using shape histograms , 2014, CODS.

[15]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[16]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[17]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  R. V. Allen,et al.  Automatic phase pickers: Their present use and future prospects , 1982 .

[19]  Subutai Ahmad,et al.  Unsupervised real-time anomaly detection for streaming data , 2017, Neurocomputing.

[20]  Sebastián Dormido,et al.  Unsupervised Event Characterization and Detection in Multichannel Signals: An EEG application , 2016, Sensors.

[21]  Xiangyu Zhang,et al.  Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  G. Beroza,et al.  An autocorrelation method to detect low frequency earthquakes within tremor , 2008 .

[23]  Nagarajan Natarajan,et al.  Learning with Noisy Labels , 2013, NIPS.

[24]  C. Marone,et al.  Laboratory observations of slow earthquakes and the spectrum of tectonic fault slip modes , 2016, Nature Communications.

[25]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[27]  Bing Liu,et al.  Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression , 2003, ICML.

[28]  Shiann-Tsong Sheu,et al.  A low complexity algorithm for earthquake detection system , 2016, 2016 International Conference On Communication Problem-Solving (ICCP).

[29]  Philip S. Yu,et al.  Building text classifiers using positive and unlabeled examples , 2003, Third IEEE International Conference on Data Mining.

[30]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[32]  Chris Marone,et al.  The effect of shear load on frictional healing in simulated fault gouge , 1998 .

[33]  Katherine A. Klise,et al.  Event Detection from Water Quality Time Series , 2007 .