UDC 69.003

USING DETRENDING METHODS FOR INTELLIGENT PROCESSING OF CONSTRUCTION PROCESS MONITORING DATA Using detrending methods for intelligent processing of construction process monitoring data

Published in Construction and Architecture · Volume 11, Issue 1, 2023 · Pages 12–12 · Rubric: 2.1.14. LIFE CYCLE MANAGEMENT OF CONSTRUCTION OBJECTS (TECHNICAL SCIENCES)
DOI: https://doi.org/10.29039/2308-0191-2022-11-1-12-12
Received: 16.01.2023 Accepted: 19.02.2023 Published: 24.03.2023 Language of publication: ru-RU
Data processing of monitoring systems of various processes at the stage of construction and operation of buildings requires the development of special tools that belong to the field of artificial intelligence. The trend removal method is one of the ways to preprocess data collected from various sensors and IoT devices that monitor the state of buildings, structures and soil masses during construction and operation. This article analyzes how different approaches to detrending time series affect the performance and accuracy of algorithms for CI computational intelligence models. The analysis compares three approaches: linear detrending, non-linear detrending, and first-order differentiation. Five representative methods are used as CI models: DENFIS dynamic evolving fuzzy neural network, GP Gaussian process, MLP multilayer perceptron, OP-ELM optimally trimmed extremal learning machine, and SVM support vector machine. There are three main conclusions from the experiments performed on the four datasets: 1) detrending does not improve overall performance, 2) the empirical mode decomposition method provides better performance than linear detrending, and 3) first-order differentiation in some cases can be effective and in some cases counterproductive for series with common patterns.
digital technologies, monitoring of construction processes, artificial intelligence, data preprocessing, detrending
Text References
Text (PDF)
Read Download

1. Nie, S.Y.; Wu, X.Q. A historical study about the developing process of the classical linear time series models. // In Proceedings of The Eighth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA); Springer: Berlin, Heidelberg, Germany, 2013; Volume 212, pp. 425-433.

2. Kenmei, B., Antoniol, G., di Penta, M. Trend analysis and issue prediction in large-scale open source systems. // In 2008 12th European Conference on Software Maintenance and Reengineering; 2008; pp. 73-82.

3. Gao, K., Khoshgoftaar, T.M.: A comprehensive empirical study of count models for software fault prediction. // IEEE Transactions on Reliability 56(2); 2007; pp. 223-236.

4. Agosto, A.; Cavaliere, G.; Kristensen, D.; Rahbek, A. Modeling corporate defaults: Poisson autoregressions with exogenous covariates (PARX). J. Empir. Financ.; 2016; pp. 640-663.

5. Karlis, D.; Meligkotsidou, L. Multivariate Poisson regression with covariance structure. // Stat. Comput.; 2005; pp. 255-265.

6. Lennon, H. Gaussian Copula Modelling for Integer-Valued Time Series. // Ph.D. Thesis, University of Manchester, Manchester, UK, 2016.

7. Fokianos, K. Count time series models. // Time Ser. Appl. Handb. Stat.; 2012; pp. 315-347.

8. Snyder, R. D., A. B. Koehler, and J. K. Ord. Forecasting for Inventory Control with Exponential Smoothing. // International Journal of Forecasting, 18 (1); 2002; pp. 5-18.

9. Xiong, H.; Shang P. Detrended fluctuation analysis of multivariate time series. // Commun. Nonlinear Sci.; 2017; pp. 12-21.

10. Flores-Marquez, E.L.; Ramírez-Rojas, A.; Telesca, L. Multifractal detrended fluctuation analysis of earthquake magnitude series of Mexican South Pacific Region. // Appl. Math. Comput.; 2015; pp. 1106-1114.

11. Cao, L.; Mees, A.; Judd, K. Dynamics from multivariate time series. // Physica D 1998; pp. 75-88.

12. Krzyszczak, J.; Baranowski, P.; Zubik, M.; Hoffmann, H. Temporal scale influence on multifractal properties of agro-meteorological time series. // Agric. Forest Meteorol.; 2017; pp. 223-235.

13. Zhang, G.,P. Time series forecasting using a hybrid ARIMA and neural network model. // Neurocomputing 50; 2003; pp. 159-175.

14. Conejo, A. J., Plazas, M. A., Espinola, R., & Molina, A. B. Day-ahead electricity price forecasting using the wavelet transform and ARIMA models. // IEEE Transactions on Power Systems 20 (2); 2005; pp. 1035-1042.

15. Aussem, A., Murtagh, F. Combining neural network forecasts on wavelet-transformed time series. // Connection Science 9 (1); 1997; pp. 113-122.

16. Msiza, I. S., F. V. Nelwamondo and T. Marwala. Artificial Neural Networks and Support Vector Machines for Water Demand Time Series Forecasting. // In: IEEE International Conference on Systems, Man and Cybernetics; Montreal; 2007; pp. 638-643.

17. Sifuzzaman, M., M. R. Islam, and M. Z. Ali. Application of Wavelet Transform and Its Advantages Compared to Fourier Transform. // Journal of Physical Sciences 13 (1); 2009; pp. 121-134.

18. Norden E Huang, Zheng Shen, Steven R Long, Manli C Wu, Hsing H Shih, Quanan Zheng, Nai-Chyuan Yen, Chi Chao Tung, Henry H Liu. The empirical mode decomposition and the Hilbert spectrum for non-linear and non-stationary time series analysis. // Proc. R. Soc. Lond.; 1998; pp. 903-995.

19. T. Tanaka, D. P. Mandic. Complex Empirical Mode Decomposition. // IEEE Sig. Proc. Lett., vol. 14, no. 2; 2007; pp. 101-104.

20. P. Flandrin, G. Rilling, P. Gonçalvès. Empirical mode decomposition as a filter bank. // IEEE Signal Process. Lett., vol. 11, no. 2; 2004; pp. 112-114.

21. Behforooz, H, Papamichael, N: Improved orders of approximation derived from interpolatory cubic splines. // BIT. 19; 1979; pp. 19-26.

22. J. C. Andre, L. M. Vincent, D. O’Connor, W. R. Ware. Applications of Fast Fourier transform to Deconvolution in Single Photon Counting. // J. of Phys. Chem. Vol. 83, No. 17; 1979; pp. 2285-2294.

23. N. Beaudoin. A high accuracy mathematical and numerical method for Fourier transform, integral, derivatives and polynomial splines of any order. // Canadian Journal of Physics. Vol. 76, No. 9; 1998; pp. 659-677.

24. S. M. Molaei and M. R. Keyvanpour. An analytical review for event prediction system on time series. // 2nd International Conference on Pattern Recognition and Image Analysis (IPRIA); 2015; pp. 16.

25. E N. K. Kasabov, Q. Song. DENFIS: Dyanamic evolving neural fuzzy inference system and its application for time-series prediction. // IEEE Trans. Fuzzy Systems, vol.10, no.2; 2002; pp. 144-154.

26. Y. S. Abu-Mostafu, A. F. Atiya, M. magdon-Ismail, H. White. Introduction to the special issue on neural networks in financial engineering. // IEEE Transaction Neural Networks, vol.12, no.4; 2001; pp. 653-656.

27. Y. Miche, A. Sorjamaa, P. Bas, O. Simula, C. Jutten, A. Lendasse. OP-ELM: Optimally pruned extreme learning machine. // IEEE Trans.. Neural Netw., vol. 21, no. 1; 2010; pp. 158-162.

28. Y. Miche, A. Sorjamaa, A. Lendasse. OP-ELM: Theory, Experiments and a Toolbox. // In Proc. Int. Conf. Artif. Neural Netw., ser. Lect. Notes Comput. Sci, vol. 5163, Prague, Czech Republic; 2008; pp. 145-154.

29. Rahaman A, Islam M, Islam M, Sadi M, Nooruddin S. Developing IoT based smart health monitoring systems: a review. // Rev d’Intell Artif. 33(6); 2019; pp. 435-440.

30. https://www.kaggle.com/taranvee/smart-home-dataset-with-weather-information

31. https://www.kaggle.com/lucabasa/dutch-energy

32. https://www.kaggle.com/atulanandjha/temperature-readings-iot-devices

33. https://www.kaggle.com/anikannal/solar-power-generation-data

34. Guyon I, Elisseeff A. An introduction to variable and feature selection. // J Mach Learn Res 3; 2003; pp. 1157-1182.

35. Ansley, C. F., Kohn, R. Prediction mean squared error for state-space models with estimated parameters. // Biometrika 73; 1986; pp. 467-473.

36. Kagan, P. The use of digital technologies in building organizational and technological design / E3S Web Conf. Volume 263, 2021, XXIV International Scientific Conference “Construction the Formation of Living Environment” (FORM-2021) 263, 04040 (2021) doi:https://doi.org/10.1051/e3sconf/202126304040