Period Estimation For Incomplete Time Series

Natural and human-engineered systems often exhibit periodic behavior. Examples include the climate system, migration of animals in the wild, consumption of electricity in the power grid and others. The behavior of such systems, however, is not perfectly periodic. The time series we collect from them are often noisy and incomplete due to limitations of data collection and transmission, or due to sensor malfunction and outages. In addition, there are often multiple periods, for example, air temperature and pressure oscillates daily and yearly with the seasons. Hence, accurate and robust period estimation from raw time series is a fundamental task often employed in downstream applications such as traffic prediction and anomaly detection.In this paper, we study the period estimation problem in noisy time series with multiple periods and missing values. We propose a method based on a Ramanujan periodic dictionary and a vector completion model to estimate missing values. To account for the block structure in the Ramanujan periodic dictionary, we introduce a graph Laplacian group lasso regularization which enables robust and efficient period learning in the presence of missing observations. In our extensive experiments on datasets from diverse domains, our proposed methodology outperforms state-of-art baselines in terms of accuracy of period estimation.

[1]  Eamonn J. Keogh,et al.  Matrix Profile II: Exploiting a Novel Algorithm and GPUs to Break the One Hundred Million Barrier for Time Series Motifs and Joins , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[2]  Philip S. Yu,et al.  On Periodicity Detection and Structural Periodic Similarity , 2005, SDM.

[3]  Athanasios G. Paliatsos,et al.  Statistical evaluation of selected air pollutants in Athens, Greece , 1995 .

[4]  P. P. Vaidyanathan,et al.  Detecting tandem repeats in DNA using Ramanujan Filter Bank , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[5]  Li Su,et al.  Monaural Source Separation Using Ramanujan Subspace Dictionaries , 2018, IEEE Signal Processing Letters.

[6]  Christos Faloutsos,et al.  AutoCyclone: Automatic Mining of Cyclic Online Activities with Robust Tensor Factorization , 2017, WWW.

[7]  Anders P. Eriksson,et al.  Efficient computation of robust low-rank matrix approximations in the presence of missing data using the L1 norm , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  N. Lomb Least-squares frequency analysis of unequally spaced data , 1976 .

[9]  P. P. Vaidyanathan,et al.  Detection of protein repeats using the Ramanujan Filter Bank , 2016, 2016 50th Asilomar Conference on Signals, Systems and Computers.

[10]  Xuan Liang,et al.  PM2.5 data reliability, consistency, and air quality assessment in five Chinese cities , 2016 .

[11]  Christian Jutten,et al.  Sequential Blind Source Extraction For Quasi-Periodic Signals With Time-Varying Period , 2009, IEEE Transactions on Biomedical Engineering.

[12]  S. Mostafa Mousavi,et al.  Seismic Signal Denoising and Decomposition Using Deep Neural Networks , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Matthew E. P. Davies,et al.  BEAT TRACKING WITH A TWO STATE MODEL , 2005 .

[14]  Philippe Fournier-Viger,et al.  PHM: Mining Periodic High-Utility Itemsets , 2016, ICDM.

[15]  A. Gnauck Interpolation and approximation of water quality time series and process identification , 2004, Analytical and bioanalytical chemistry.

[16]  Emily B. Fox,et al.  A Unified Framework for Long Range and Cold Start Forecasting of Seasonal Profiles in Time Series , 2017, ArXiv.

[17]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Shi-Wen Deng,et al.  Ramanujan subspace pursuit for signal periodic decomposition , 2015, ArXiv.

[19]  Yisong Yue,et al.  NAOMI: Non-Autoregressive Multiresolution Sequence Imputation , 2019, NeurIPS.

[20]  P. P. Vaidyanathan,et al.  The farey-dictionary for sparse representation of periodic signals , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  G. Sapiro,et al.  A collaborative framework for 3D alignment and classification of heterogeneous subvolumes in cryo-electron tomography. , 2013, Journal of structural biology.

[22]  Noah Simon,et al.  A Sparse-Group Lasso , 2013 .

[23]  William A. Sethares,et al.  Periodicity transforms , 1999, IEEE Trans. Signal Process..

[24]  Eamonn J. Keogh,et al.  Matrix Profile I: All Pairs Similarity Joins for Time Series: A Unifying View That Includes Motifs, Discords and Shapelets , 2016, 2016 IEEE 16th International Conference on Data Mining (ICDM).

[25]  P. P. Vaidyanathan,et al.  Nested Periodic Matrices and Dictionaries: New Signal Representations for Period Estimation , 2015, IEEE Transactions on Signal Processing.

[26]  Wei Zhang,et al.  PRED: Periodic Region Detection for Mobility Modeling of Social Media Users , 2017, WSDM.

[27]  Srinivasan Parthasarathy,et al.  Robust periodicity detection algorithms , 2006, CIKM '06.

[28]  Jiawei Han,et al.  Mining Periodicity from Dynamic and Incomplete Spatiotemporal Data , 2014 .

[29]  T. Bollerslev,et al.  Intraday periodicity and volatility persistence in financial markets , 1997 .

[30]  Wei Cao,et al.  BRITS: Bidirectional Recurrent Imputation for Time Series , 2018, NeurIPS.

[31]  Hadi Fanaee-T,et al.  Event labeling combining ensemble detectors and background knowledge , 2014, Progress in Artificial Intelligence.

[32]  Constantine Frangakis,et al.  Multiple imputation by chained equations: what is it and how does it work? , 2011, International journal of methods in psychiatric research.

[33]  M. Nakashizuka A Sparse Decomposition for Periodic Signal Mixtures , 2007, 2007 15th International Conference on Digital Signal Processing.

[34]  Petko Bogdanov,et al.  PERCeIDs: PERiodic CommunIty Detection , 2019, 2019 IEEE International Conference on Data Mining (ICDM).

[35]  Gautham J. Mysore,et al.  Audio Imputation Using the Non-negative Hidden Markov Model , 2012, LVA/ICA.

[36]  Jiawei Han,et al.  ePeriodicity: Mining Event Periodicity from Incomplete Observations , 2015, IEEE Transactions on Knowledge and Data Engineering.

[37]  Walid G. Aref,et al.  Multiple and Partial Periodicity Mining in Time Series Databases , 2002, ECAI.

[38]  Jiawei Han,et al.  Detecting Multiple Periods and Periodic Patterns in Event Time Sequences , 2017, CIKM.

[39]  Emmanuel J. Candès,et al.  Exact Matrix Completion via Convex Optimization , 2008, Found. Comput. Math..

[40]  Yi Ma,et al.  The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices , 2010, Journal of structural biology.

[41]  R. Weron Electricity price forecasting: A review of the state-of-the-art with a look into the future , 2014 .

[42]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[43]  Piotr Indyk,et al.  Identifying Representative Trends in Massive Time Series Data Sets Using Sketches , 2000, VLDB.

[44]  Jiawei Han,et al.  Mining periodic behaviors for moving objects , 2010, KDD.