Autoencoder Networks for Water Demand Predictive Modelling

Ishmael S. Msiza, Tshilidzi Marwala

Abstract

Following a number of studies that have interrogated the usability of an autoencoder neural network in various classification and regression approximation problems, this manuscript focuses on its usability in water demand predictive modelling, with the Gauteng Province of the Republic of South Africa being chosen as a case study. Water demand predictive modelling is a regression approximation problem. This autoencoder network is constructed from a simple multi-layer network, with a total of 6 parameters in both the input and output units, and 5 nodes in the hidden unit. These 6 parameters include a figure that represents population size and water demand values of 5 consecutive days. The water demand value of the fifth day is the variable of interest, that is, the variable that is being predicted. The optimum number of nodes in the hidden unit is determined through the use of a simple, less computationally expensive technique. The performance of this network is measured against prediction accuracy, average prediction error, and the time it takes the network to generate a single output. The dimensionality of the network is also taken into consideration. In order to benchmark the performance of this autoencoder network, a conventional neural network is also implemented and evaluated using the same measures of performance. The conventional network is slightly outperformed by the autoencoder network.

References

  1. Bougadis, J., Adamowski, K., and Diduch, R. (2005). Short-term Municipal Water Demand Forecasting. In Hydrological Processes 19. pp 137-148.
  2. Cooks, J. (2004). 100 Years of Excellence 1903-2003. Rand Water, Johannesburg, 1st edition.
  3. Hessel, M., Borgatelli, F., and Ortalli, F. (2014). A Novel Approach to Model Design and Tuning through Automatic Parameter Screening and Optimisation - Theory and Application to a Helicopter Flight Simulator Case Study. In 4th Intl. Conf. on Simulation & Modelling Methodologies, Technol., and Appl. pp 24-35.
  4. Jain, A., Varshney, A. K., and Joshi, U. C. (2001). Shortterm Water Demand Forecast Modelling at IIT Kanpur Using Artificial Neural Networks. In IEEE Trans. on Water Resources Management 15. pp 299-321.
  5. Leke-Betechuoh, B., Marwala, T., and Tettey, T. (2006). Autoencoder Networks for HIV Classification. In Current Science 91. pp 1467-1473.
  6. Marivate, V. N., Nelwamondo, F. V., and Marwala, T. (2008). Investigation into the Use of Autoencoder Neural Networks, Principal Component Analysis and Support Vector Regression in Estimating Missing HIV Data. In 17th World Congress of the Intl. Federation of Automatic Control. pp 682-689.
  7. Marwala, T. (2016). Handbook of Machine Learning: Foundation of Artificial Intelligence . Imperial College Press, London, (Accepted for Publication) edition.
  8. Msiza, I. S., Nelwamondo, F. V., and Marwala, T. (2007). Water Demand Forecasting Using Multi-layer Perceptron and Radial Basis Functions. In IEEE Intl. Joint Conf. on Neural Networks. pp 13-18.
  9. Msiza, I. S., Nelwamondo, F. V., and Marwala, T. (2008). Water Demand Prediction Using Artificial Neural Networks and Support Vector Regression. In Journal of Computers 3. pp 1-8.
  10. Msiza, I. S., Szewczyk, M., Halinka, A., Pretorius, J. H., Sowa, P., and Marwala, T. (2011). Neural Networks on Transformer Fault Detection: Evaluating the Relevance of the Input Space Parameters. In IEEE PES Power Systems Conf. & Exposition. DOI: 10.1109/PSCE.2011.5772567.
  11. Nabney, I. T. (2004). Algorithms for Pattern Recognition. Springer, Heidelberg, 4th edition.
  12. Nelwamondo, F. V., Golding, D., and Marwala, T. (2013). A Dynamic Programming Approach to Missing Data Estimation Using Neural Networks. In Information Sciences 237. pp 49-58.
  13. Solanki, A., Agrawal, H., and Khare, K. (2015). Predictive Analysis of Water Quality Parameters using Deep Learning. In Intl. Journal of Computer Appl. 125. pp 29-34.
  14. Thompson, B. B., Marks, R. J., Choi, J. J., El-Sharkawi, M. A., Huang, M.-Y., and Bunje, C. (2002). Implicit Learning in Autoencoder Novelty Assessment. In IEEE Intl. Joint Conf. on Neural Networks. pp 2878- 2883.
  15. Utts, J. M. and Heckard, R. F. (2015). Mind on Statistics. Cengage Learning, Stanford, 5th edition.
  16. van Deventer, V. and Mojapelo-Batka, M. (2013). A Student's A-Z of Psychology. Juta & Company, South Africa, 2nd edition.
  17. Yuan, Y. and Jia, K. (2015). A Water Quality Assessment Method Based on Sparse Autoencoder. In IEEE Intl. Conf. on Signal Processing, Communications & Computing. pp 1-4.
  18. Zhiyin, W., Long, Y., and Shengwei, T. (2015). Water Body Extraction Method Based on Stacked Autoencoder. In Journal of Computer Appl. 35. pp 2706-2709.
Download


Paper Citation


in Harvard Style

Msiza I. and Marwala T. (2016). Autoencoder Networks for Water Demand Predictive Modelling . In Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH, ISBN 978-989-758-199-1, pages 231-238. DOI: 10.5220/0005977202310238


in Bibtex Style

@conference{simultech16,
author={Ishmael S. Msiza and Tshilidzi Marwala},
title={Autoencoder Networks for Water Demand Predictive Modelling},
booktitle={Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,},
year={2016},
pages={231-238},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005977202310238},
isbn={978-989-758-199-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications - Volume 1: SIMULTECH,
TI - Autoencoder Networks for Water Demand Predictive Modelling
SN - 978-989-758-199-1
AU - Msiza I.
AU - Marwala T.
PY - 2016
SP - 231
EP - 238
DO - 10.5220/0005977202310238