Context-Aware Deep Sequence Learning with Multi-View Factor Pooling for Time Series Classification

In this paper, we propose an effective, multi-view, multivariate deep classification model for time-series data. Multi-view methods show promise in their ability to learn correlation and exclusivity properties across different independent information resources. However, most current multi-view integration schemes employ only a linear model and, therefore, do not extensively utilize the relationships observed across different view-specific representations. Moreover, the majority of these methods rely exclusively on sophisticated, handcrafted features to capture local data patterns and, thus, depend heavily on large collections of labeled data. The multi-view, multivariate deep classification model for time-series data proposed in this paper makes important contributions to address these limitations. The proposed model derives a LSTM-based, deep feature descriptor to model both the view-specific data characteristics and cross-view interaction in an integrated deep architecture while driving the learning phase in a data-driven manner. The proposed model employs a compact context descriptor to exploit view-specific affinity information to design a more insightful context representation. Finally, the model uses a multi-view factor-pooling scheme for a context-driven attention learning strategy to weigh the most relevant feature dimensions while eliminating noise from the resulting fused descriptor. As shown by experiments, compared to the existing multi-view methods, the proposed multi-view deep sequential learning approach improves classification performance by roughly 4% in the UCI multi-view activity recognition dataset, while also showing significantly robust generalized representation capacity against its single-view counterparts, in classifying several large-scale multi-view light curve collections.

[1]  Carlo Vercellis,et al.  Combining discrete SVM and fixed cardinality warping distances for multivariate time series classification , 2010, Pattern Recognit..

[2]  Akshay Pai,et al.  Deep-learnt classification of light curves , 2017, 2017 IEEE Symposium Series on Computational Intelligence (SSCI).

[3]  Houshang Darabi,et al.  Multivariate LSTM-FCNs for Time Series Classification , 2018, Neural Networks.

[4]  Junyi Shen,et al.  Classification of multivariate time series using two-dimensional singular value decomposition , 2008, Knowl. Based Syst..

[5]  T. A. Lister,et al.  Gaia Data Release 2. Summary of the contents and survey properties , 2018, 1804.09365.

[6]  Yun Fu,et al.  Multi-View Time Series Classification: A Discriminative Bilinear Projection Approach , 2016, CIKM.

[7]  Jiaying Liu,et al.  Factorized Bilinear Models for Image Recognition , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[8]  Luis Gravano,et al.  k-Shape: Efficient and Accurate Clustering of Time Series , 2015, SIGMOD Conference.

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

[10]  Shiliang Sun,et al.  A survey of multi-view machine learning , 2013, Neural Computing and Applications.

[11]  Jiasen Lu,et al.  Hierarchical Question-Image Co-Attention for Visual Question Answering , 2016, NIPS.

[12]  Sylvie Gibet,et al.  On Recursive Edit Distance Kernels With Application to Time Series Classification , 2010, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[14]  Joshua B. Tenenbaum,et al.  Separating Style and Content , 1996, NIPS.

[15]  Ming Shao,et al.  Multi-View Low-Rank Analysis with Applications to Outlier Detection , 2018, ACM Trans. Knowl. Discov. Data.

[16]  A. J. Drake,et al.  The Catalina Surveys Southern periodic variable star catalogue , 2017 .

[17]  Ernest E. Croner,et al.  The Palomar Transient Factory: System Overview, Performance, and First Results , 2009, 0906.5350.

[18]  Razvan Pascanu,et al.  How to Construct Deep Recurrent Neural Networks , 2013, ICLR.

[19]  Shiguang Shan,et al.  Multi-View Discriminant Analysis , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Wenyu Zhang,et al.  Multivariate Time Series Classification Using Dynamic Time Warping Template Selection for Human Activity Recognition , 2015, 2015 IEEE Symposium Series on Computational Intelligence.

[21]  H. Hotelling Relations Between Two Sets of Variates , 1936 .

[22]  Billur Barshan,et al.  Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units , 2014, Comput. J..

[23]  Subhransu Maji,et al.  Bilinear CNNs for Fine-grained Visual Recognition , 2015 .

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

[25]  Amy Loutfi,et al.  A review of unsupervised feature learning and deep learning for time-series modeling , 2014, Pattern Recognit. Lett..

[26]  Giorgio Giacinto,et al.  Information fusion in content based image retrieval: A comprehensive overview , 2017, Inf. Fusion.

[27]  Zhongfei Zhang,et al.  Simultaneously Combining Multi-view Multi-label Learning with Maximum Margin Classification , 2012, 2012 IEEE 12th International Conference on Data Mining.