REFII Model as a Base for Data Mining Techniques Hybridization with Purpose of Time Series Pattern Recognition

  • Goran Klepac
  • Robert Kopal
  • Leo Mršić
Part of the Studies in Computational Intelligence book series (SCI, volume 611)


The article will present the methodology for holistic time series analysis, based on time series transformation model REFII (REFII is an acronym for Raise-Equal-Fall and the model version is II or 2) Patel et al. (Mining motifs in massive time series databases, 2002) [1], Perng and Parker (SQL/LPP: a time series extension of SQL based on limited patience patterns, 1999) [2], Popivanov and Miller (Similarity search over time series data using wavelets, 2002) [3]. The main purpose of REFII model is to automate time series analysis through a unique transformation model of time series. The advantage of this approach to a time series analysis is the linkage of different methods for time series analysis linking traditional data mining tools in time series, and constructing new algorithms for analyzing time series. REFII model is not a closed system, which means that there is a finite set of methods. This is primarily a model used for transformation of values of time series, which prepares data used by different sets of methods based on the same model of transformation in the domain of problem space. REFII model gives a new approach in time series analysis based on a unique model of transformation, which is a base for all kind of time series analyses. In combination with elements of other methods, such as self-organizing maps or frequent-pattern trees, REFII models can make new hybrid methods for efficient time temporal data mining. Similar principle of hybridization could be used as a tool for time series temporal pattern recognition. The article describes real case study illustrating practical application of described methodology.


Time series transformation Pattern recognition Data mining REFII Data mining and time series integration Self-organizing maps Decision tree Frequent-pattern tree 


  1. 1.
    Patel P, Keogh E, Lin J, Lonardi S (2002) Mining motifs in massive time series databases. In: Proceedings of the 2002 IEEE international conference on data mining, Maebashi City, Japan, 9–12 Dec 2002Google Scholar
  2. 2.
    Perng CS, Parker DS (1999) SQL/LPP: a time series extension of SQL based on limited patience patterns. Technical report 980034 UCLA, Computer ScienceGoogle Scholar
  3. 3.
    Popivanov I, Miller RJ (2002) Similarity search over time series data using wavelets. In: Proceedings of the 18th international conference on data engineering, San Jose, CA, 26 Feb 26 Mar 1 to appearGoogle Scholar
  4. 4.
    Cha J, Cho BR (2014) Classical statistical inference extended to truncated populations for continuous process improvement: test statistics, P‐values, and confidence intervals. In: Quality and Reliability Engineering InternationalGoogle Scholar
  5. 5.
    Šošić I, Serdar V (1990) Uvod u statistiku, Školska knjiga-ZagrebGoogle Scholar
  6. 6.
    Apostolos-Paul R (1996) Neural networks in capital markets. Wiley, New YorkGoogle Scholar
  7. 7.
    Bisoi R, Dash PK (2014) A hybrid evolutionary dynamic neural network for stock market trend analysis and prediction using unscented Kalman filter. Appl Soft Comput 19:41–56CrossRefGoogle Scholar
  8. 8.
    Taylor JG (1996) Neural networks and their applications. Wiley, LondonGoogle Scholar
  9. 9.
    Gaxiola F, Melin P, Valdez F, Castillo O (2014) Interval type-2 fuzzy weight adjustment for back propagation neural networks with application in time series prediction. Inf Sci 260:1–14CrossRefMathSciNetGoogle Scholar
  10. 10.
    Jha GK, Sinha K (2014) Time-delay neural networks for time series prediction: an application to the monthly wholesale price of oilseeds in India. Neural Comput Appl 24(3–4):563–571CrossRefGoogle Scholar
  11. 11.
    Kliček B, Zekić-Sušac M (2002) A nonlinear strategy of selecting NN architectures for stock return predictions, finance. In: Proceedings from the 50th anniversary financial conference svishtov, Bulgaria, ABAGAR, Veliko Tarnovo, pp 325–355, Apr 11–12 2002Google Scholar
  12. 12.
    Lin C-J (1997) SISO nonlinear system identification using a fuzzy-neural hybrid system. Int J Neural Syst 8(3):325–337Google Scholar
  13. 13.
    Dostál P, Zelinka I, Guanrong C, Rössler OE, Snasel V, Abraham A (2013) Nostradamus 2013: prediction, modeling and analysis of complex systems. In: Forecasting of time series with fuzzy logic, pp 155–161Google Scholar
  14. 14.
    Lin J, Keogh E, Patel P, Lonardi S (2001) Finding motifs in time series. In: 1st workshop on temporal data mining at 7 th ACM SIGKDD International conference of knowledge discovery and data mining, Edmont Alberta Canada, 27–30 July 27–30Google Scholar
  15. 15.
    Lin J, Keogh E, Patel, P, Lonardi S (2002) Clustering of time series subsequences in meaningless: implications for previous and future research. In: 2nd workshop on temporal data mining at 8 th ACM SIGKDD international conference of knowledge discovery and data mining, Edmont Alberta Canada, 23–26 JulyGoogle Scholar
  16. 16.
    Lin J, Keogh E, Lonardi S, Chiu B (2003) A symbolic representation of time series, with implications for streaming algorithms. In: Proceedings of the 8th ACM SIGMOD workshop on research issues in data mining and knowledge discovery, San Diego, CA, 13 June 2003Google Scholar
  17. 17.
    Heikki M, Hanu T, Verkamo I (1997) Discovery of frequent episodes in event sequences. University of Helsinki Finland, Report C-1997-15Google Scholar
  18. 18.
    Heikki M, Gunopulos D, Das G (2001) Finding similar time series. Technical Report D-2001-4, University of Helsinki FinlandGoogle Scholar
  19. 19.
    Pratt K (2001) Locating patterns in discrete time series. University of South Florida, these, 2001Google Scholar
  20. 20.
    Bang, Y-K, Lee C-H (2008) Fuzzy time series prediction with data preprocessing and error compensation based on correlation analysis. In: Proceedings of the 2008 third international conference on convergence and hybrid information technology, pp 714–721, 11–13 Nov 2008Google Scholar
  21. 21.
    Fong S, Lan K, Wong R (2013) Classifying human voices by using hybrid SFX time-series preprocessing and ensemble feature selection. BioMed Res Int 2013:27Google Scholar
  22. 22.
    Pyle D (1999) Data preparation for data mining. Morgan Kaufmann Publishers, Inc., New YorkGoogle Scholar
  23. 23.
    Wu CL, Chau KW, Fan C (2010) Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. J Hydrol 389(1):146–167CrossRefGoogle Scholar
  24. 24.
    Sasaki H, Fujita S (2014) Pro-shareholder income distribution, debt accumulation, and cyclical fluctuations in a post-Keynesian model with labor supply constraints. Eur J Econ Econ Policies: Interv 11(1):10–30Google Scholar
  25. 25.
    Westphal C, Blaxton T (1998) Data mining solutions–methods and tools for solving real world problems. Wiley, New YorkGoogle Scholar
  26. 26.
    Lao W, Wang Y, Peng C, Ye C, Zhang Y (2014) Time series forecasting via weighted combination of trend and seasonality respectively with linearly declining increments and multiple sine functions. In: 2014 international joint conference on neural networks (IJCNN), IEEE, pp 832–837Google Scholar
  27. 27.
    Dougherty ER, Giardina CR (1988) Mathematical methods for artificial intelligence and autonomous systems. Prentice-Hall, Englewood CliffGoogle Scholar
  28. 28.
    Han J, Pei J, Yin J (2000) Mining frequent patterns without candidate generation. In: Proceedings of ACM SIGMOID, pp 1–12Google Scholar
  29. 29.
    Wang C, Wang XS (2000) Supporting content-based searches on time series via approximation. In: Proceedings of the 12th international conference on scientific and statistical database management, Berlin, Germany, pp 69–81, 26–28 July 26–28 2000Google Scholar
  30. 30.
    Xsniaping G (1998) Pattern matching in financial time series data.
  31. 31.
    Han J, Kamber M (2011) Data mining-concepts and techniques. Morgan Kaufmann Publishers, San FranciscoGoogle Scholar
  32. 32.
    Caraça-Valente JP, Lopez-Chavarrias I (2000) Discovering similar patterns in time series. In: Proceedings of the 6th ACM SIGKDD international conference on knowledge discovery and data mining, Boston, MA, pp 497–505, 20–23 Aug 2000Google Scholar
  33. 33.
    Chiu B, Keogh E, Lonardi S (2003) Probabilistic discovery of time series motifs. In: The 9th ACM SIGKDD international conference on knowledge discovery and data mining, Washington, DC, USA, pp 493–498, 24–27 Aug 2003Google Scholar
  34. 34.
    Craven MW (1997) Understanding time series networks: a case study in rule extraction. Int J Neural Syst 8(4):373–384Google Scholar
  35. 35.
    Das G, Gunopulos D, Mannila H (1997) Finding similar time series. In: Proceedings of principles of data mining and knowledge discovery, 1st European symposium, Trondheim, Norway, pp 88–100, 24–27 Jun 1997Google Scholar
  36. 36.
    Aggarwal CC, Han J (2014) Frequent pattern mining. Springer International Publishing, SwitzerlandGoogle Scholar
  37. 37.
    Klepac G, Kopal R, Mršić L (2014) Developing churn models using data mining techniques and social network analysis. IGI Global. doi: 10.4018/978-1-4666-6288-9, ISBN13: 9781466662889, ISBN10: 1466662883, EISBN13: 9781466662896
  38. 38.
    Mršić L (2012) Decision support model in retail based on time series transformation methodology (REFII) and Bayes network. Doctoral thesis, Faculty of Humanities and Social Sciences, Zagreb, CroatiaGoogle Scholar
  39. 39.
    Williams, JG, Weiqiang L, Mehmet AO (2002) An overview of temporal data mining. In: Simeon JS, Graham JW, Markus H (eds) Proceedings of the 1st Australian data mining workshop (ADM02), University of Technology, Sydney, Canberra, Australia, pp 83–90, ISBN 0-9750075-0-5Google Scholar
  40. 40.
    Williams JG, Weiqiang L, Mehmet O (2000) Temporal data mining using multi-level local polynomial models. In: Proceedings of the 2nd international conference on intelligent data engineering and automated learning (IDEAL00). Lecture Notes in Computer Science, vol 1983. Springer Hong KongGoogle Scholar
  41. 41.
    Williams, JG, Weiqian L, Mehmet O (2001) Temporal data mining using hidden markov-local polynomial models. In: David C, Graham W, Qing L (eds) Proceedings of the 5th Pacific Asia conference on knowledge discovery and data mining (PAKDD01). Lecture Notes in Artificial Intelligence, vol 2035. Springer, Hong Kong, ChinaGoogle Scholar
  42. 42.
    Williams, JG, Rohan B, Graham W, Hongxing H (2001) Feature selection for temporal health records, advances in knowledge discovery and data mining. David C, Graham W, Qing L (eds) Proceedings of the 5th Pacific Asia conference on knowledge discovery and data mining (PAKDD01). Lecture Notes in Artificial Intelligence, vol 2035. Springer, Hong Kong, ChinaGoogle Scholar
  43. 43.
    Williams, JG, Weiqiang L, Mehmut O (2002) Mining temporal patterns from health care data. In: Proceedings of the 4th international conference on data warehousing and knowledge discovery (DaWaK02). Lecture Notes in Computer Science, vol 2454. Springer, Pages 221–231, ISBN 3-540-44123-9Google Scholar
  44. 44.
    Williams, JG (2003) Mining the data stream, invited plenary. In: International conference on hybrid intelligent systems melbourne, Australia, Dec 2003Google Scholar
  45. 45.
    Williams JG, Chris K, Rohan B, Lifang G, Simon H, Hongxing H, Chris R, Deanne V (2003) Temporal event mining of linked medical claims data. In: Proceedings of the PAKDD03 workshop on data mining for actionable knowledge DMAK-2003 Seoul, Korea, Apr 2003Google Scholar
  46. 46.
    Fanchi, JR (2000) Math refresher for scientists and engineers, 2nd edn. Wiley-IEEE Press, HobokenGoogle Scholar
  47. 47.
    Javor P (1988) Uvod u matematičku analizu, Školska knjiga- ZagrebGoogle Scholar
  48. 48.
    Mardešić S (1977) Matematička analiza I, Školska KnjigaGoogle Scholar
  49. 49.
    Han J, Wang W, Yu SP, Yang J (2002) Mining long patterns in a noisy environment. In; ACM SIGMOID, Madison USA, June 2002Google Scholar
  50. 50.
    Han J, Xifeng Y, Ashfar J (2003) CloSpan: mining closed sequential patterns in large datasets. NSF IIS-02-09199, University of IllinoisGoogle Scholar
  51. 51.
    Han J, Pei B, Mortazavi-Asl J, Wang H, Pinto Q, Chen U Dayal, Hsu M-C (2004) Mining sequential patterns by pattern-growth: the prefix span approach. IEEE Trans Knowl Data Eng 16(10):2004Google Scholar
  52. 52.
    Wu J, Wan L, Xu Z (2012) Algorithms to discover complete frequent episodes in sequences. New frontiers in applied data mining. Springer, Berlin, pp 267–278CrossRefGoogle Scholar
  53. 53.
    Brazma A, Jonassen I, Vilo J, Ukkonen E (1998) Pattern discovery in biosequences. Lecture Notes in Artificial Intelligence, vol 1433. Springer, New York, pp 256–270Google Scholar
  54. 54.
    Wang W, Yang J, Yu P (2001) Mining long sequential patterns in a noisy environment. IBM Research Report 2001Google Scholar
  55. 55.
    Keogh E, Smyth P (1997) A probabilistic approach to fast pattern matching in time series databases. In: Proceedings of the 3rd international conference on knowledge discovery and data mining, Newport Beach, CA, pp 20–24, 14–17 Aug 1997Google Scholar
  56. 56.
    Keogh E, Pazzani M (1998) An enhanced representation of time series which allows fast and accurate classification, clustering and relevance feedback. In: Proceedings of the 4th international conference on knowledge discovery and data mining, New York, NY, pp 239-241, 27–31 Aug 1998Google Scholar
  57. 57.
    Keogh E, Chu S, Hart D, Pazzani M (2001) An online algorithm for segmenting time series. In: IEEEGoogle Scholar
  58. 58.
    Keogh EG (2011) Data, mining time series data. International encyclopedia of statistical science. Springer, Berlin, pp 339–342CrossRefGoogle Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  1. 1.Raiffeisenbank AustriaZagrebCroatia
  2. 2.IN2data Data Science CompanyZagrebCroatia

Personalised recommendations