CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2013 vol.35 Issue No.03 - March

Subscribe

Issue No.03 - March (2013 vol.35)

pp: 740-754

J. Frank , Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada

S. Mannor , Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel

J. Pineau , Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada

D. Precup , Sch. of Comput. Sci., McGill Univ., Montreal, QC, Canada

ABSTRACT

We present a novel framework for analyzing univariate time series data. At the heart of the approach is a versatile algorithm for measuring the similarity of two segments of time series called geometric template matching (GeTeM). First, we use GeTeM to compute a similarity measure for clustering and nearest-neighbor classification. Next, we present a semi-supervised learning algorithm that uses the similarity measure with hierarchical clustering in order to improve classification performance when unlabeled training data are available. Finally, we present a boosting framework called TDEBOOST, which uses an ensemble of GeTeM classifiers. TDEBOOST augments the traditional boosting approach with an additional step in which the features used as inputs to the classifier are adapted at each step to improve the training error. We empirically evaluate the proposed approaches on several datasets, such as accelerometer data collected from wearable sensors and ECG data.

INDEX TERMS

Time series analysis, Hidden Markov models, Computational modeling, Discrete Fourier transforms, Time measurement, Discrete wavelet transforms, Extraterrestrial measurements, time series classification, Activity recognition, gait recognition, supervised learning, unsupervised learning, wearable computing

CITATION

J. Frank, S. Mannor, J. Pineau, D. Precup, "Time Series Analysis Using Geometric Template Matching",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.35, no. 3, pp. 740-754, March 2013, doi:10.1109/TPAMI.2012.121REFERENCES

- [1] G. Batista, X. Wang, and E. Keogh, "A Complexity-Invariant Distance Measure for Time Series,"
Proc. 11th SIAM Int'l Conf. Data Mining, pp. 699-710, 2011.- [2] K. Kalpakis, D. Gada, and V. Puttagunta, "Distance Measures for Effective Clustering of ARIMA Time-Series,"
Proc. IEEE Int'l Conf. Data Mining, pp. 273-280, 2001.- [3] D. Ge, N. Srinivasan, and S. Krishnan, "Cardiac Arrhythmia Classification Using Autoregressive Modeling,"
BioMedical Eng. OnLine, vol. 1, no. 1, p. 5, 2002.- [4] M. Corduas and D. Piccolo, "Time Series Clustering and Classification by the Autoregressive Metric,"
Computational Statistics & Data Analysis, vol. 52, no. 4, pp. 1860-1872, 2008.- [5] T. Sauer, J. Yorke, and M. Casdagli, "Embedology,"
J. Statistical Physics, vol. 65, no. 3, pp. 579-616, 1991.- [6] H. Kantz and T. Schreiber,
Nonlinear Time Series Analysis. Cambridge Univ. Press, 2004.- [7] M. Small,
Applied Nonlinear Time Series Analysis: Applications in Physics, Physiology and Finance. World Scientific, 2005.- [8] F. Takens, "Detecting Strange Attractors in Turbulence,"
Dynamical Systems and Turbulence, vol. 898, no. 1, pp. 365-381, 1981.- [9] J.A. Ward, P. Lukowicz, and H.W. Gellersen, "Performance Metrics for Activity Recognition,"
ACM Trans. Intelligent Systems Technology, vol. 2, pp. 1-23, Jan. 2011.- [10] J.C. Dunn, "Well-Separated Clusters and Optimal Fuzzy Partitions,"
J. Cybernetics, vol. 4, no. 1, pp. 95-104, 1974.- [11] D.L. Davies and D.W. Bouldin, "A Cluster Separation Measure,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 1, no. 2, pp. 224 -227, Apr. 1979.- [12] O. Chapelle, B. Schölkopf, and A. Zien,
Semi-Supervised Learning. MIT Press, 2006.- [13] E. Keogh, X. Xi, L. Wei, and C.A. Ratanamahatana, "The UCR Time Series Classification/Clustering Homepage," www.cs.ucr.edu/~eamonntime_series_data/, 2006.
- [14] X. Xi, E. Keogh, C. Shelton, L. Wei, and C. Ratanamahatana, "Fast Time Series Classification Using Numerosity Reduction,"
Proc. Int'l Conf. Machine Learning, pp. 1033-1040, 2006.- [15] H. Sakoe, "Dynamic Programming Algorithm Optimization for Spoken Word Recognition,"
IEEE Trans. Acoustics, Speech, and Signal Processing, vol. 26, no. 1, pp. 43-49, Feb. 1978.- [16] C. Ratanamahatana and E. Keogh, "Making Time-Series Classification More Accurate Using Learned Constraints,"
Proc. SIAM Int'l Conf. Data Mining, pp. 11-22, 2004.- [17] K. Beyer, J. Goldstein, R. Ramakrishnan, and U. Shaft, "When Is 'Nearest Neighbor' Meaningful?"
Proc. Int'l Conf. Database Theory, pp. 217-235, 1999.- [18] R. Agrawal, C. Faloutsos, and A. Swami, "Efficient Similarity Search in Sequence Databases,"
Proc. Fourth Int'l Conf. Foundations of Data Organization and Algorithms, pp. 69-84, 1993.- [19] C. Faloutsos, M. Ranganathan, and Y. Manolopoulos, "Fast Subsequence Matching in Time-Series Databases,"
Proc. ACM SIGMOD Int'l Conf. Management of Data, pp. 419-429, 1994.- [20] K. Chan and A. Fu, "Efficient Time Series Matching by Wavelets,"
Proc. Int'l Conf. Data Eng., pp. 126-133, 1999.- [21] F. Korn, H.V. Jagadish, and C. Faloutsos, "Efficiently Supporting Ad Hoc Queries in Large Data Sets of Time Sequences,"
ACM SIGMOD Record, vol. 26, no. 2, pp. 289-300, 1997.- [22] C.S. Burrus, R.A. Gopinath, and H. Guo,
Introduction to Wavelets and Wavelet Transforms: A Primer. Prentice Hall, 1998.- [23] J. Durbin, "The Fitting of Time-Series Models,"
Rev. Int'l Statistical Inst., vol. 28, no. 3, pp. 233-244, 1960.- [24] L. Rabiner and B. Juang, "An Introduction to Hidden Markov Models,"
IEEE ASSP Magazine, vol. 3, no. 1, pp. 4-16, Jan. 1986.- [25] P. Smyth, "Clustering Sequences with Hidden Markov Models,"
Proc. Advances in Neural Information Processing Systems, pp. 648-654, 1997.- [26] B.H. Juang and L.R. Rabiner, "A Probabilistic Distance Measure for Hidden Markov Models,"
AT&T Technical J., vol. 64, no. 2, pp. 391-408, 1985.- [27] L. Bao and S.S. Intille, "Activity Recognition from User-Annotated Acceleration Data,"
Proc. Int'l Conf. Pervasive Computing, pp. 1-17, 2004.- [28] E.A. Heinz, K.S. Kunze, S. Sulistyo, H. Junker, P. Lukowicz, and G. Trster, "Experimental Evaluation of Variations in Primary Features Used for Accelerometric Context Recognition,"
Proc. First European Symp. Ambient Intelligence, pp. 252-263, 2003.- [29] N. Ravi, N. Dandekar, P. Mysore, and M.L. Littman, "Activity Recognition from Accelerometer Data,"
Proc. 17th Conf. Innovative Applications of Artificial Intelligence, pp. 1541-1546, 2005.- [30] T. Huynh and B. Schiele, "Analyzing Features for Activity Recognition,"
Proc. Joint Conf. Smart Objects and Ambient Intelligence, pp. 159-163, 2005.- [31] J. Lester, T. Choudhury, and G. Borriello, "A Practical Approach to Recognizing Physical Activities,"
Proc. Fourth Int'l Conf. Pervasive Computing, pp. 1-16, 2006.- [32] T. Buzug and G. Pfister, "Optimal Delay Time and Embedding Dimension for Delay-Time Coordinates by Analysis of the Global Static and Local Dynamical Behavior of Strange Attractors,"
Physics Rev. A, vol. 45, no. 10, pp. 7073-7084, 1992.- [33] M. Kennel, R. Brown, and H. Abarbanel, "Determining Embedding Dimension for Phase Space Reconstruction Using the Method of False Nearest Neighbors,"
Physics Rev. A, vol. 45, no. 6, pp. 3403-3411, 1992.- [34] A. Galka,
Topics in Nonlinear Time Series Analysis: With Implications for EEG Analysis. World Scientific, 2000.- [35] J. Röschke and J. Aldenhoff, "The Dimensionality of Human's Electroencephalogram During Sleep,"
Biological Cybernetics, vol. 64, no. 4, pp. 307-313, 1991.- [36] R. Esteller, G. Vachtsevanos, J. Echauz, T. Henry, P. Pennell, C. Epstein, R. Bakay, C. Bowen, and B. Litt, "Fractal Dimension Characterizes Seizure Onset in Epileptic Patients,"
Proc. Int'l Conf. Acoustics, Speech, and Signal Processing, vol. 4, pp. 2343-2346, 1999.- [37] K. Bush and J. Pineau, "Manifold Embeddings for Model-Based Reinforcement Learning under Partial Observability,"
Proc. Advances in Neural Information Processing Systems, vol. 22, pp. 189-197, 2009.- [38] P. Indyk and R. Motwani, "Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality,"
Proc. ACM Symp. Theory of Computing, pp. 604-613, 1998.- [39] D. Lemire, "Faster Retrieval with a Two-Pass Dynamic-Time-Warping Lower Bound,"
Pattern Recognition, vol. 42, no. 9, pp. 2169-2180, Sept. 2009.- [40] A.L. Goldberger, L.A.N. Amaral, L. Glass, J.M. Hausdorff, P.C. Ivanov, R.G. Mark, J.E. Mietus, G.B. Moody, C.-K. Peng, and H.E. Stanley, "PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals,"
Circulation, vol. 101, no. 23, pp. e215-e220, 2000.- [41] S. Johnson, "Hierarchical Clustering Schemes,"
Psychometrika, vol. 32, no. 3, pp. 241-254, 1967.- [42] J. WardJr., "Hierarchical Grouping to Optimize an Objective Function,"
J. Am. Statistical Assoc., vol. 58, pp. 236-244, 1963.- [43] M. Friedman, "The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance,"
J. Am. Statistical Assoc., vol. 32, no. 200, pp. 675-701, 1937.- [44] B. Bergmann and G. Hommel, "Improvements of General Multiple Test Procedures for Redundant Systems of Hypotheses,"
Multiple Hypotheses Testing, pp. 100-115, Springer, 1988.- [45] E. Keogh and S. Kasetty, "On the Need for Time Series Data Mining Benchmarks: A Survey and Empirical Demonstration,"
Data Mining and Knowledge Discovery, vol. 7, no. 4, pp. 349-371, 2003.- [46] D. Berndt and J. Clifford, "Using Dynamic Time Warping to Find Patterns in Time Series,"
Proc. AAAI Workshop Knowledge Discovery in Databases, pp. 229-248, 1994.- [47] A. Subramanya, A. Raj, J. Bilmes, and D. Fox, "Recognizing Activities and Spatial Context Using Wearable Sensors,"
Proc. 22nd Conf. Uncertainty in Artificial Intelligence, 2006.- [48] J. Zhu, S. Rosset, H. Zou, and T. Hastie, "Multi-Class AdaBoost," technical report, Dept. of Statistics, Univ. of Michigan, 2005.
- [49] Y. Freund and R. Schapire, "A Decision Theoretic Generalization of On-Line Learning and an Application to Boosting,"
J. Computer and System Sciences, vol. 55, no. 1, pp. 119-139, 1997.- [50] I. Mukherjee and R. Schapire, "A Theory of Multi-Class Boosting,"
Proc. Advances in Neural Information Processing Systems, 2010.- [51] H. Ailisto, M. Lindholm, J. Mantyjarvi, E. Vildjiounaite, and S. Makela, "Identifying People from Gait Pattern with Accelerometers,"
Proc. Soc. Photo-Optical Instrumentation Eng. Conf. Series, vol. 5779, pp. 7-14, 2005.- [52] D. Gafurov, E. Snekkenes, and P. Bours, "Spoof Attacks on Gait Authentication System,"
IEEE Trans. Information Forensics and Security, vol. 2, no. 3, pp. 491-502, Sept. 2007.- [53] M. Bächlin, J. Schumm, D. Roggen, and G. Töster, "Quantifying Gait Similarity: User Authentication and Real-World Challenge,"
Proc. Third Int'l Conf. Biometrics, pp. 1040-1049, 2009. |