Earliness-Aware Deep Convolutional Networks for Early Time Series Classification

We present Earliness-Aware Deep Convolutional Networks (EA-ConvNets), an end-to-end deep learning framework, for early classification of time series data. Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series. Consequently, our framework is able to make highly reliable early predictions, outperforming various state-of-the-art methods for early time series classification, while also being competitive when compared to the state-of-the-art time series classification algorithms that work with \emph{fully observed} time series data. To the best of our knowledge, the proposed framework is the first to perform data-driven (deep) feature learning in the context of early classification of time series data. We perform a comprehensive set of experiments, on several benchmark data sets, which demonstrate that our method yields significantly better predictions than various state-of-the-art methods designed for early time series classification. In addition to obtaining high accuracies, our experiments also show that the learned deep shapelets based features are also highly interpretable and can help gain better understanding of the underlying characteristics of time series data.

[1]  Hyrum S. Anderson,et al.  Classifying with confidence from incomplete information , 2013, J. Mach. Learn. Res..

[2]  Antoine Cornuéjols,et al.  Early Classification of Time Series as a Non Myopic Sequential Decision Making Problem , 2015, ECML/PKDD.

[3]  Philip S. Yu,et al.  Early classification on time series , 2012, Knowledge and Information Systems.

[4]  Xiaoli Li,et al.  Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition , 2015, IJCAI.

[5]  Lars Schmidt-Thieme,et al.  Learning DTW-Shapelets for Time-Series Classification , 2016, CODS.

[6]  Jason Lines,et al.  Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles , 2015, IEEE Transactions on Knowledge and Data Engineering.

[7]  Ryan P. Adams,et al.  Learning Ordered Representations with Nested Dropout , 2014, ICML.

[8]  Einoshin Suzuki,et al.  Minimizing response time in time series classification , 2015, Knowledge and Information Systems.

[9]  Eamonn J. Keogh,et al.  Time series shapelets: a new primitive for data mining , 2009, KDD.

[10]  Jacek M. Zurada,et al.  Efficient Learning of Timeseries Shapelets , 2016, AAAI.

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

[12]  Liu Xiao-ying Fast Subsequence Matching in Time-series Database , 2008 .

[13]  Patrick Schäfer The BOSS is concerned with time series classification in the presence of noise , 2014, Data Mining and Knowledge Discovery.

[14]  Yun Fu,et al.  Early Classification of Ongoing Observation , 2014, 2014 IEEE International Conference on Data Mining.

[15]  Clément Farabet,et al.  Torch7: A Matlab-like Environment for Machine Learning , 2011, NIPS 2011.

[16]  Didier Stricker,et al.  LSTM-Based Early Recognition of Motion Patterns , 2014, 2014 22nd International Conference on Pattern Recognition.

[17]  Clu-istos Foutsos,et al.  Fast subsequence matching in time-series databases , 1994, SIGMOD '94.

[18]  Seiichi Uchida,et al.  Early recognition of sequential patterns by classifier combination , 2008, 2008 19th International Conference on Pattern Recognition.

[19]  Antonio Pescapè,et al.  Early Classification of Network Traffic through Multi-classification , 2011, TMA.

[20]  Xiang Zhang,et al.  Character-level Convolutional Networks for Text Classification , 2015, NIPS.

[21]  Jian Pei,et al.  Reliable Early Classification on Multivariate Time Series with Numerical and Categorical Attributes , 2015, PAKDD.

[22]  Mohamed F. Ghalwash,et al.  Extraction of Interpretable Multivariate Patterns for Early Diagnostics , 2013, 2013 IEEE 13th International Conference on Data Mining.

[23]  Yong Duan,et al.  Early classification on multivariate time series , 2015, Neurocomputing.

[24]  Amy McGovern,et al.  Identifying predictive multi-dimensional time series motifs: an application to severe weather prediction , 2010, Data Mining and Knowledge Discovery.

[25]  Ryo Kurazume,et al.  Early Recognition and Prediction of Gestures , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[26]  Mohamed F. Ghalwash,et al.  Early classification of multivariate time series using a hybrid HMM/SVM model , 2012, 2012 IEEE International Conference on Bioinformatics and Biomedicine.

[27]  Yixin Chen,et al.  Multi-Scale Convolutional Neural Networks for Time Series Classification , 2016, ArXiv.

[28]  Einoshin Suzuki,et al.  Time-sensitive Classification of Behavioral Data , 2013, SDM.

[29]  Jian Pei,et al.  A brief survey on sequence classification , 2010, SKDD.

[30]  Yixin Chen,et al.  An integrated data mining approach to real-time clinical monitoring and deterioration warning , 2012, KDD.

[31]  Mohamed F. Ghalwash,et al.  Utilizing temporal patterns for estimating uncertainty in interpretable early decision making , 2014, KDD.

[32]  Lars Schmidt-Thieme,et al.  Learning time-series shapelets , 2014, KDD.

[33]  Jason Lines,et al.  Time series classification with ensembles of elastic distance measures , 2015, Data Mining and Knowledge Discovery.

[34]  Eamonn J. Keogh,et al.  Reliable early classification of time series based on discriminating the classes over time , 2016, Data Mining and Knowledge Discovery.

[35]  Donald J. Berndt,et al.  Using Dynamic Time Warping to Find Patterns in Time Series , 1994, KDD Workshop.

[36]  Yi Zheng,et al.  Time Series Classification Using Multi-Channels Deep Convolutional Neural Networks , 2014, WAIM.

[37]  Jonathan Tompson,et al.  Efficient object localization using Convolutional Networks , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  Philip S. Yu,et al.  Extracting Interpretable Features for Early Classification on Time Series , 2011, SDM.

[39]  Carlos J. Alonso,et al.  Boosting Interval-Based Literals: Variable Length and Early Classification , 2002 .