Robust IoT time series classification with data compression and deep learning

Abstract Internet of Things (IoT) and wearable systems are very resource limited in terms of power, memory, bandwidth and processor performance. Sensor time series compression can be regarded as a direct way to use memory and bandwidth resources efficiently. On the other hand, the time series classification has recently attracted great attention and has found numerous potential uses in areas such as finance, industry and healthcare. This paper investigates the effect of lossy compression techniques on the time series classification task using deep neural networks. Furthermore, this paper proposes an efficient compression approach for univariate and multivariate time series that combines the lifting implementation of the discrete wavelet transform with an error-bound compressor, namely Squeeze (SZ), to attain an optimal trade-off between data compression and data quality.

[1]  Jacques Demerjian,et al.  Using DWT Lifting Scheme for Lossless Data Compression in Wireless Body Sensor Networks , 2018, 2018 14th International Wireless Communications & Mobile Computing Conference (IWCMC).

[2]  Raphaël Couturier,et al.  An energy efficient IoT data compression approach for edge machine learning , 2019, Future Gener. Comput. Syst..

[3]  Franck Cappello,et al.  Fast Error-Bounded Lossy HPC Data Compression with SZ , 2016, 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS).

[4]  Wei-Ying Ma,et al.  Web-page classification through summarization , 2004, SIGIR '04.

[5]  Davide Anguita,et al.  A Public Domain Dataset for Human Activity Recognition using Smartphones , 2013, ESANN.

[6]  Simon A. Dobson,et al.  Compression in wireless sensor networks , 2013 .

[7]  Leonid Boytsov,et al.  Decoding billions of integers per second through vectorization , 2012, Softw. Pract. Exp..

[8]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[9]  Martin Isenburg,et al.  Fast and Efficient Compression of Floating-Point Data , 2006, IEEE Transactions on Visualization and Computer Graphics.

[10]  Mohsen Guizani,et al.  Internet of Things: A Survey on Enabling Technologies, Protocols, and Applications , 2015, IEEE Communications Surveys & Tutorials.

[11]  Wim Sweldens,et al.  The lifting scheme: a construction of second generation wavelets , 1998 .

[12]  Tossaporn Srisooksai,et al.  Practical data compression in wireless sensor networks: A survey , 2012, J. Netw. Comput. Appl..

[13]  Dirk Helbing,et al.  Saving Human Lives: What Complexity Science and Information Systems can Contribute , 2014, Journal of statistical physics.

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

[15]  George Karabatis,et al.  Discrete wavelet transform-based time series analysis and mining , 2011, CSUR.

[16]  Samuel Madden,et al.  Sprintz , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[17]  Arijit Ukil,et al.  IoT Data Compression: Sensor-Agnostic Approach , 2015, 2015 Data Compression Conference.

[18]  Massimo Piccardi,et al.  Compressive Sensing of Time Series for Human Action Recognition , 2010, 2010 International Conference on Digital Image Computing: Techniques and Applications.

[19]  Biljana Risteska Stojkoska,et al.  Data compression for energy efficient IoT solutions , 2017, 2017 25th Telecommunication Forum (TELFOR).

[20]  Jeremiah D. Deng,et al.  Impact of Compression Ratio and Reconstruction Methods on ECG Classification for E-Health Gadgets: A Preliminary Study , 2018, Australasian Conference on Artificial Intelligence.

[21]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[22]  Jacques Demerjian,et al.  Using Adaptive Sampling and DWT Lifting Scheme for Efficient Data Reduction in Wireless Body Sensor Networks , 2018, 2018 14th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[23]  Tuong Ly Le,et al.  Lossless Data Compression Algorithm to Save Energy in Wireless Sensor Network , 2018, 2018 4th International Conference on Green Technology and Sustainable Development (GTSD).

[24]  Awais Ahmad,et al.  Urban planning and building smart cities based on the Internet of Things using Big Data analytics , 2016, Comput. Networks.