Classification of time-series images using deep convolutional neural networks

Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.

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

[2]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[3]  Nima Hatami,et al.  Thinned-ECOC ensemble based on sequential code shrinking , 2012, Expert Syst. Appl..

[4]  Sergey Malinchik,et al.  SAX-VSM: Interpretable Time Series Classification Using SAX and Vector Space Model , 2013, 2013 IEEE 13th International Conference on Data Mining.

[5]  Camelia Chira,et al.  Error-Correcting Output Codes for Multi-Label Text Categorization , 2012, IIR.

[6]  Honglak Lee,et al.  Unsupervised feature learning for audio classification using convolutional deep belief networks , 2009, NIPS.

[7]  Gerald Penn,et al.  Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Tim Oates,et al.  Pooling SAX-BoP Approaches with Boosting to Classify Multivariate Synchronous Physiological Time Series Data , 2015, FLAIRS.

[9]  Juan José Rodríguez Diez,et al.  Interval and dynamic time warping-based decision trees , 2004, SAC '04.

[10]  Olufemi A. Omitaomu,et al.  Weighted dynamic time warping for time series classification , 2011, Pattern Recognit..

[11]  Dong Yu,et al.  Exploring convolutional neural network structures and optimization techniques for speech recognition , 2013, INTERSPEECH.

[12]  M. Dalto.  Deep neural networks for time series prediction with applications in ultra-short-term wind forecasting , 2014 .

[13]  Jake Bouvrie,et al.  Notes on Convolutional Neural Networks , 2006 .

[14]  Jürgen Kurths,et al.  Recurrence plots for the analysis of complex systems , 2009 .

[15]  Camelia Chira,et al.  Classifiers with a reject option for early time-series classification , 2013, 2013 IEEE Symposium on Computational Intelligence and Ensemble Learning (CIEL).

[16]  G Pfurtscheller,et al.  Using time-dependent neural networks for EEG classification. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[17]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

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

[19]  Geoffrey Zweig,et al.  Recent advances in deep learning for speech research at Microsoft , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Tim Oates,et al.  Encoding Time Series as Images for Visual Inspection and Classification Using Tiled Convolutional Neural Networks , 2014 .

[21]  Saeid Nahavandi,et al.  Bag-of-words representation for biomedical time series classification , 2012, Biomed. Signal Process. Control..

[22]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

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

[24]  Eamonn J. Keogh,et al.  Fast Shapelets: A Scalable Algorithm for Discovering Time Series Shapelets , 2013, SDM.

[25]  Peter Fu-Ming Hu,et al.  Exploiting Representational Diversity for Time Series Classification , 2012, 2012 11th International Conference on Machine Learning and Applications.

[26]  Yannis Manolopoulos,et al.  Feature-based classification of time-series data , 2001 .

[27]  Reza Ebrahimpour,et al.  ECOC-based training of neural networks for face recognition , 2008, 2008 IEEE Conference on Cybernetics and Intelligent Systems.

[28]  Vinícius M. A. de Souza,et al.  Time Series Classification Using Compression Distance of Recurrence Plots , 2013, 2013 IEEE 13th International Conference on Data Mining.

[29]  Yuan Li,et al.  Rotation-invariant similarity in time series using bag-of-patterns representation , 2012, Journal of Intelligent Information Systems.

[30]  Fei-Fei Li,et al.  Large-Scale Video Classification with Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  D. Ruelle,et al.  Recurrence Plots of Dynamical Systems , 1987 .

[32]  Vinícius M. A. de Souza,et al.  Extracting Texture Features for Time Series Classification , 2014, 2014 22nd International Conference on Pattern Recognition.

[33]  Philip S. Yu,et al.  Early prediction on time series: a nearest neighbor approach , 2009, IJCAI 2009.

[34]  Nima Hatami,et al.  Some proposals for combining ensemble classifiers , 2012 .

[35]  Tim Oates,et al.  Imaging Time-Series to Improve Classification and Imputation , 2015, IJCAI.

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

[37]  J. Theiler,et al.  Grammar-guided Feature Extraction for Time Series Classification , 2005 .