A novel shapelet transformation method for classification of multivariate time series with dynamic discriminative subsequence and application in anode current signals

Abstract

Classification of multi-dimension time series (MTS) plays an important role in knowledge discovery of time series. Many methods for MTS classification have been presented. However, most of these methods did not consider the kind of MTS whose discriminative subsequence was not restricted to one dimension and dynamic. In order to solve the above problem, a method to extract new features with extended shapelet transformation is proposed in this study. First, key features is extracted to replace k shapelets to calculate distance, which are extracted from candidate shapelets with one class for all dimensions. Second, feature of similarity numbers as a new feature is proposed to enhance the reliability of classification. Third, because of the time-consuming searching and clustering of shapelets, distance matrix is used to reduce the computing complexity. Experiments are carried out on public dataset and the results illustrate the effectiveness of the proposed method. Moreover, anode current signals (ACS) in the aluminum reduction cell are the aforementioned MTS, and the proposed method is successfully applied to the classification of ACS.

Keywords

anode current signals / key features / distance matrix / feature of similarity numbers / shapelet transformation

References

[1] HeG-l, DuanY, PengR, JingX-y, QianT-y, WangL-l. Early classification on multivariate time series [J]. Neurocomputing, 2015, 149: 777-787

[2] KongL-s, YangC-h, LiJ-q, WangY-l. Generic reconstruction technology based on rst for multivariate time series of complex process industries [J]. Journal of Central South University, 2012, 19(5): 1311-1316

[3] ZengM, LiJ-h, MengQ-h, ZhangX-n. Temporal-spatial cross-correlation analysis of non-stationary near-surface wind speed time series [J]. Journal of Central South University, 2017, 24(3): 692-698

[4] MaharajE A, AlonsoA M. Discriminant analysis of multivariate time series: Application to diagnosis based on ecg signals [J]. Computational Statistics & Data Analysis, 2014, 70: 67-87

[5] MONBET V, AILLIOT P. Sparse vector Markov switching autoregressive models. Application to multivariate time series of temperature [J]. Computational Statistics & Data Analysis, 2017: S0167947316302584.

[6] GóreckiT, LuczakM. Multivariate time series classification with parametric derivative dynamic time warping [J]. Expert Systems with Applications, 2015, 42(5): 2305-2312

[7] ElbaumS, MalishevskyA G, RothermelG. Test case prioritization: A family of empirical studies [J]. IEEE transactions on software engineering, 2002, 28(2): 159-182

[8] YE L, KEOGH E J. Time series shapelets: A new primitive for data mining [C]// Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Paris, France, 2009.

[9] ESMAEL B, ARNAOUT A, FRUHWIRTH R K, THONHAUSER G. Multivariate time series classification by combining trend-based and value-based approximations [C]// International Conference on Computational Science and its Applications. Springer, 2012: 392–403.

[10] WengX-q, ShenJ-y. Classification of multivariate time series using two-dimensional singular value decomposition [J]. Knowledge-Based Systems, 2008, 21(7): 535-539

[11] WangL, WangZ-g, LiuS. An effective multivariate time series classification approach using echo state network and adaptive differential evolution algorithm [J]. Expert Systems with Applications, 2016, 43: 237-249

[12] GhalwashM F, ObradovicZ. Early classification of multivariate temporal observations by extraction of interpretable shapelets [J]. BMC Bioinformatics, 2012, 13(1): 195

[13] ZhangD-h, QianL-y, MaoB-j, HuangC, SiY-l. A data-driven design for fault detection of wind turbines using random forests and XGboost [J]. IEEE Access, 2018, 6: 21020-21031

[14] PENG Man-man, LUO Jun. A novel key-points based shapelets transform for time series classification [C]// 2017 13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD). IEEE, 2017: 2268–2273.

[15] YeL, KeoghE. Time series shapelets: A novel technique that allows accurate, interpretable and fast classification [J]. Data Mining and Knowledge Discovery, 2011, 22(12): 149-182

[16] FuT C. A review on time series data mining [J]. Engineering Applications of Artificial Intelligence, 2011, 24(1): 164-181

[17] MUEEN A, KEOGH E, YOUNG N E. Logical-shapelets: An expressive primitive for time series classification [C]// Proceedings of ACM SIGKDD: International Conference on Knowledge Discovery and Data Mining. 2011

[18] RAKTHANMANON T, KEOGH E. Fast shapelets: A scalable algorithm for discovering time series shapelets [C]// proceedings of the 2013 SIAM International Conference on Data Mining. SIAM, 2013: 668–676.

[19] XING Z Z, JIAN P, YU P S. Early prediction on time series: A nearest neighbor approach [C]// IJCAI 2009, Proceedings of the 21st International Joint Conference on Artificial Intelligence. Pasadena, California, USA, July 11–17, 2009.

[20] PATRI O P, PANANGADAN A V, CHELMIS C, PRASANNA V K. Extracting discriminative features for event-based electricity disaggregation [C]// 2014 IEEE Conference on Technologies for Sustainability (SusTech). IEEE, 2014: 232–238.

[21] HillsJ, LinesJ, BaranauskasE, MappJ, BagnallA. Classification of time series by shapelet transformation [J]. Data Mining and Knowledge Discovery, 2014, 28(4): 851-881

[22] BOSTROM A, BAGNALL A. A shapelet transform for multivariate time series classification [J]. arXiv:1712.06428, 2017.

[23] PATRI O P, KANNAN R, PANANGADAN A V, PRASANNA V K. Multivariate time series classification using inter-leaved shapelets [C]// NIPS 2015 Time Series Workshop. 2015

[24] GHALWASH M F, RADOSAVLJEVIC V, OBRADOVIC Z. Extraction of interpretable multivariate patterns for early diagnostics [C]// 2013 IEEE 13th International Conference on Data Mining. IEEE, 2013: 201–210.

[25] PATRI O P, SHARMA A B, CHEN H, JIANG G, PANANGADAN A V, PRASANNA V K. Extracting discriminative shapelets from heterogeneous sensor data [C]// 2014 IEEE International Conference on Big Data (Big Data). IEEE, 2014: 1095–1104.

[26] LINES J, DAVIS L M, HILLS J, BAGNALL A. A shapelet transform for time series classification [C]// Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2012: 289–297.

[27] ZalewskiW, SilvaF, MaletzkeA G, FerreroC A. Exploring shapelet transformation for time series classification in decision trees [J]. Knowledge-Based Systems, 2016, 11280-91

[28] ZhangZ-g, ZhangH-w, WenY-l, ZhangY, YuanX-j. Discriminative extraction of features from time series [J]. Neurocomputing, 2018, 275: 2317-2328

[29] PEI W, DIBEKLIOĞLU H, TAX D M, van DER MAATEN L. Time series classification using the hidden-unit logistic model [J]. arXiv:1506.05085, 2015.

[30] CETIN M S, MUEEN A, CALHOUN V D. Shapelet ensemble for multi-dimensional time series [C]// Proceedings of the 2015 SIAM International Conference on Data Mining. SIAM, 2015: 307–315.

[31] RishI. An empirical study of the naive Bayes classifier [C]. IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, 2001, Seattle, Washington, USA, IJCAI: 4146

[32] YueW-c, ChenX-f, GuiW-h, XieY-f, ZhangH-l. A knowledge reasoning fuzzy-Bayesian network for root cause analysis of abnormal aluminum electrolysis cell condition [J]. Frontiers of Chemical Science and Engineering, 2017, 11(3): 414-428

[33] EICK I, KLAVENESS A, ROSENKILDE C, SEGATZ M, GUDBRANDSEN H, SOLHEIM A, SKYBAKMOEN E, EINARSRUD K. Voltage and bubble release behaviour in a laboratory cell at low anode-cathode distance [C]// Proc. 10th Australasian Aluminium Smelting Technology Conference, Launceston, TAS. 2011.

[34] CheungC-Y, MenictasC, BaoJ, Skyllas-KazacosM, WelchB J. Characterization of individual anode current signals in aluminum reduction cells [J]. Industrial & Engineering Chemistry Research, 2013, 52(28): 9632-9644

[35] YangS, ZouZ, LiJ, ZhangH-l. Online anode current signal in aluminum reduction cells: Measurements and prospects [J]. JOM, 2016, 68(2): 623-634