Interval Feature Transformation for Time Series Classification Using Perceptually Important Points
Source abstract
Abstract
A novel feature reconstruction method, referred to as interval feature transformation (IFT), is proposed for time series classification. The IFT uses perceptually important points to segment the series dynamically into subsequences of unequal length, and then extract interval features from each time series subsequence as a feature vector. The IFT distinguishes the best top-k discriminative feature vectors from a data set by information gain. Utilizing these discriminative feature vectors, transformation is applied to generate new k-dimensional data which are lower-dimensional representations of the original data. In order to verify the effectiveness of this method, we use the transformed data in conjunction with some traditional classifiers to solve time series classification problems and make comparative experiments to several state-of-the-art algorithms. Experiment results verify the effectiveness, noise robustness and interpretability of the IFT.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Time Series Analysis and Forecasting · Complex Systems and Time Series Analysis · Music and Audio Processing
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China
Hubei Research Center for Educational Informationization, Central China Normal University, Wuhan 430079, China
References (39)
Show source-provided references
1. Least-Squares Wavelet Analysis of Unequally Spaced and Non-stationary Time Series and Its Applications10.1007/s11004-017-9691-0 ↗
2. Exploring convolutional neural network structures and optimization techniques for speech recognition
3. Abdel-Hamid, O., Mohamed, A.R., Jiang, H., and Penn, G. (2012, January 25–30). Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition. Proceedings of the 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, Kyoto, Japan.10.1109/ICASSP.2012.6288864 ↗
4. Bag-of-words representation for biomedical time series classification10.1016/j.bspc.2013.06.004 ↗
5. Lines, J. (2015). Time Series Classification through Transformation and Ensembles. [Ph.D. Thesis, University of East Anglia].
6. Fulcher, B.D. (2018). Feature-based time-series analysis. Feature Engineering for Machine Learning and Data, CRC Press.10.1201/9781315181080-4 ↗
7. Boosted discriminant projections for nearest neighbor classification10.1016/j.patcog.2005.06.004 ↗
8. kn-nearest neighbor classification10.1109/TIT.1972.1054888 ↗
9. Ratanamahatana, C.A., and Keogh, E. (2004, January 22–24). Making time-series classification more accurate using learned constraints. Proceedings of the Fourth SIAM International Conference on Data Mining, Lake Buena Vista, FA, USA.10.1137/1.9781611972740.2 ↗
10. Weighted dynamic time warping for time series classification10.1016/j.patcog.2010.09.022 ↗
11. Dynamic time warping constraint learning for large margin nearest neighbor classification10.1016/j.ins.2011.03.001 ↗
12. A Time Series Forest for Classification and Feature Extraction10.1016/j.ins.2013.02.030 ↗
13. Ye, L., and Keogh, E. (2009). Time series shapelets: A new primitive for data mining. Knowl. Discov. Data Min., 947–956.10.1145/1557019.1557122 ↗
14. Classification of time series by shapelet transformation10.1007/s10618-013-0322-1 ↗
15. pyts: A python package for time series classification
16. The BOSS is concerned with time series classification in the presence of noise10.1007/s10618-014-0377-7 ↗
17. Patel, P., Keogh, E., Lin, J., and Lonardi, S. (2002, January 9–12). Mining Motifs in Massive Time Series Databases. Proceedings of the 2002 IEEE International Conference on Data Mining, Maebashi City, Japan.
18. Senin, P., and Malinchik, S. (2013, January 7–10). SAX-VSM: Interpretable Time Series Classification Using SAX and Vector. Proceedings of the 2013 IEEE 13th International Conference on Data Mining, Dallas, TX, USA.10.1109/ICDM.2013.52 ↗
19. Boosting interval based literals10.3233/IDA-2001-5305 ↗
20. Using interval information granules to improve forecasting in fuzzy time series10.1016/j.ijar.2014.11.002 ↗
21. Highly Comparative Feature-Based Time-Series Classification10.1109/TKDE.2014.2316504 ↗
22. Feature-based Classification of Time-series Data
23. Lin, J., and Li, Y. (2009). Finding Structural Similarity in Time Series Data Using Bag-of-Patterns Representation. International Conference on Scientific and Statistical Database Management, Springer.10.1007/978-3-642-02279-1_33 ↗
24. Fourier transformation as a method of reducing the sampling interval of a digital time series10.1016/0098-3004(88)90057-X ↗
25. Hariharan, G. (2019). Wavelet Analysis—An Overview. Wavelet Solutions for Reaction–Diffusion Problems in Science and Engineering, Springer. Forum for Interdisciplinary Mathematics.10.1007/978-981-32-9960-3 ↗
26. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis10.1098/rspa.1998.0193 ↗
27. Ensemble empirical mode decomposition parameters optimization for spectral distance measurement in hyperspectral remote sensing data10.3390/rs6032069 ↗
28. Yu, J., Yin, J., Zhou, D., and Zhang, J. (2006). A Pattern Distance-Based Evolutionary Approach to Time Series Segmentation. Intelligent Control and Automation, Springer.10.1007/978-3-540-37256-1_99 ↗
29. A prediction scheme using perceptually important points and dynamic time warping10.1016/j.eswa.2014.04.028 ↗
30. Perceptually important points of mobility patterns to characterise bike sharing systems: The Dublin case10.1016/j.jtrangeo.2016.06.010 ↗
31. Mining Emerging Patterns from Time Series Data with Time Gap Constraint
32. Time series shapelets: A novel technique that allows accurate, interpretable and fast classification10.1007/s10618-010-0179-5 ↗
33. Mueen, A., Keogh, E., and Young, N.E. (2011, January 21). Logical-Shapelets: An Expressive Primitive for Time Series Classification. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego, CA, USA.10.1145/2020408.2020587 ↗
34. Hoang, A.D., Eamonn, K., Kaveh, K., Chin-Chia, M.Y., Yan, Z., Shaghayegh, G., Chotirat, A.R., Chen, Y.P., Hu, B., and Nurjahan, B. (2018, October 01). The UCR Time Series Classification Archive. Available online: https://www.cs.ucr.edu/~eamonn/time_series_data_2018/.
35. Scikit-learn: Machine Learning in Python
36. Statistical comparisons of classifiers over multiple data sets
37. A comparison of alternative tests of significance for the problem of m rankings10.1214/aoms/1177731944 ↗
38. Nemenyi, P.B. (1963). Distribution-Free Multiple Comparisons. [Ph.D. Thesis, Princeton University].
39. (2011, February 01). Physical Activity Monitoring for Aging People. Available online: http://www.pamap.org.