Heuristic Approach to Multivariate Inverse Prediction Problem using Data Reconciliation

  • Martin Rosecky
  • Radovan Somplak
  • Frantisek Janostak
  • Josef Bednar
Keywords: Data reconciliation, Random forest, Regression, Waste management, Optimization, Multivariate calibration, Inverse prediction

Abstract

Some engineering waste management tasks require a complete data sets of its production. However, these sets are not available in most cases. Whether they are not archiving at all or are unavailable for their sensitivity. This article deals with the issue of incomplete datasets at the microregional level. For estimates, the data from higher territorial units and additional information from the micro-region are used. The techniques used in this estimation are illustrated by an example in the field of waste management. In particular, it is an estimate of the amount of waste in individual municipalities. It is based on recorded waste production at district level and total waste management costs, which is available at a municipal level. To estimate the waste production, combinations of linear regression models with random forest models were used, followed by correction by quadratic and nonlinear optimization models. Such task could be seen as a multivariate version of inverse prediction (or calibration) problem, which is not solvable analytically. To test this approach, data for 2010 - 2015 measured in the Czech Republic were used.

References

Smejkalova, V., Somplak R., Nevrly V., Pavlas M.: Design and decomposition of waste prognostic model with hierarchical structures. In: R. Matousek (ed.), In MENDEL, (MENDEL 2018), vol. 24, No. 1, Brno University of Technology, Brno (June 18), ISSN 1803-3814. Manuscript submitted for publication.

Beigl, P., Lebesorger S., Salhofer S.: Modelling municipal solid waste generation: A review. Waste Management 28(1) 200–214 (2008). DOI https://doi.org/10.1016/j.wasman.2006.12.011

Osborne, C.: Statistical Calibration: A Review. International Statistical Review / Revue Internationale De Statistique 59(3), 309–36 (1991). DOI 10.2307/1403690

Nevrly, V., Somplak R., Popela P., Pavlas M., Osicka O., Kudela J.: Heuristic challenges for spatially distributed waste production identification problems. In: R. Matousek (ed.), In MENDEL, (MENDEL 2016), vol. 22, No. 1, pp. 109–116, Brno University of Technology, Brno (June 16), ISSN 1803-3814

Narasimhan, S., Jordache, C.: An Intelligent Use of Process Data, Data Reconciliation and Gross Error Detection. Gulf Publishing Co., Houston (2000)

McCullagh, P., Nelder, J. A.: Generalized linear models, second edn. Chapman & Hall, New York (1989)

Pavlas, M., Somplak R., Smejkalova V., Nevrly V., Szasziov´a L., Kudela J., Popela P.: Spatially distributed production data for supply chain models - Forecasting with hazardous waste. Journal of Cleaner Production 16, 1317–1328 (2017). DOI 10.1016/j.jclepro.2017.06.107

R Core Team (2017). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/

Kalmar, M., Nilsson, J.: The art of forecasting – an analysis of predictive precision of machine learning models. PhD thesis, Uppsala University (2016)

Published
2018-06-01
How to Cite
[1]
RoseckyM., SomplakR., JanostakF. and BednarJ. 2018. Heuristic Approach to Multivariate Inverse Prediction Problem using Data Reconciliation. MENDEL. 24, 1 (Jun. 2018), 71-78. DOI:https://doi.org/10.13164/mendel.2018.1.071.
Section
Articles