Prediction Model Adaptation Thanks to Control Chart Monitoring - Application to Pollutants Prediction

Philippe Thomas, William Derigent, Marie-Christine Suhner

2014

Abstract

Indoor air quality is a major determinant of personal exposure to pollutants in today’s world since people spend much of their time in numerous different indoor environments. The Anaximen company develops a smart and connected object named Alima, which can measure every minute several physical parameters: temperature, humidity, concentrations of COV, CO2, formaldehyde and particulate matter (pm). Beyond the measurement aspect, Alima presents some data analysis feature named ‘predictive analytics’, whose primary aim is to predict the evolution of indoor pollutants in time. In this article, the neural network (NN) model,embedded in this object and designed for pollutant prediction, is presented. In addition with this NN model, this article also details an approach where batch learning is performed periodically when a too important drift between the model and the system is detected. This approach is based on control charts.

References

  1. Alima, http://getalima.com, 2013.
  2. Cybenko, G., 1989. Approximation by superposition of a sigmoidal function. Math. Control Systems Signals, 2, 4, 303-314.
  3. Du, L., Ke, Y., Su, S., 2012. The Embedded Quality Control System of Product Manufacturing, Advanced Materials Research, 459, 510-513.
  4. Engelbrecht, A.P., 2001. A new pruning heuristic based on variance analysis of sensitivity information. IEEE transactions on Neural Networks, 1386-1399
  5. Funahashi, K., 1989. On the approximate realization of continuous mapping by neural networks. Neural Networks, 2, 183-192.
  6. Han, H.G., Qiao, J.F., 2013. A structure optimisation algorithm for feedforward neural network construction. Neurocomputing, 99, 347-357.
  7. Heskes, T., Wiegerinck, W., 1996. A theoretical comparison of batch-mode, online, cyclic, and almostcyclic learning. IEEE Transactions on Neural Networks, 7, 919-925.
  8. Jones, A.P, 1999. Indoor air quality and health. Atmospheric Environment, 33, 28, 4535-4564.
  9. Liang, N.Y., Huang, G.B., Saratchandran, P., Sundarajan, N., 2006. A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Transactions on Neural Networks, 17, 1411-1423.
  10. Ma, L., Khorasani, K., 2004. New training strategies for constructive neural networks with application to regression problems. Neural Network, 589-609.
  11. Maroni, M., Seifert, B., Lindvall, T., 1995. Indoor Air Quality - a Comprehensive Reference Book. Elsevier, Amsterdam.
  12. Nakama, T., 2009. Theoretical analysis of batch and online training for gradient descent learning in neural networks. Neurocomputing, 73, 151-159.
  13. Nguyen, D., Widrow, B., 1990. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptative weights. Proc. of the Int. Joint Conference on Neural Networks IJCNN'90, 3, 21-26.
  14. NIST/SEMATECH, 2012. e-Handbook of Statistical Methods, http://www.itl.nist.gov/div898/handbook/.
  15. Setiono, R., Leow, W.K., 2000. Pruned neural networks for regression. 6th Pacific RIM Int. Conf. on Artificial Intelligence PRICAI'00, Melbourne, Australia, 500- 509
  16. Shewhart, W.A., 1931. Economic Control of Quality of Manufactured Product, Van Nostrand Reinhold Company, Inc.: Princeton, NJ.
  17. Spengler, J. D., Sexton, K., 1983. Indoor air pollution: a public health perspective. Science, 221, 9-17.
  18. Tague, N.R., 2004. The Quality Toolbox, 2nd Edition, ASQ Quality Press, http://asq.org/learn-aboutquality/data-collection-analysistools/overview/control-chart.html.
  19. Thomas, P., Bloch, G., 1997. Initialization of one hidden layer feedforward neural networks for non-linear system identification. 15th IMACS World Congress on Scientific Computation, Modelling and Applied Mathematics WC'97, 4, 295-300.
  20. Thomas, P., Bloch, G., Sirou, F., Eustache, V., 1999. Neural modeling of an induction furnace using robust learning criteria. Journal of Integrated Computer Aided Engineering, 6, 1, 5-23.
  21. Thomas, P., Suhner, M.C., Thomas, A., 2013. Variance Sensitivity Analysis of Parameters for Pruning of a Multilayer Perceptron: Application to a Sawmill Supply Chain Simulation Model. Advances in Artificial Neural Systems, Article ID 284570, http://dx.doi.org/10.1155/2013/284570
  22. Walsh, P.J., Dudney, C.S., Copenhaver, E.D., 1987. Indoor air quality, ISBM 0-8493-5015-8.
Download


Paper Citation


in Harvard Style

Thomas P., Derigent W. and Suhner M. (2014). Prediction Model Adaptation Thanks to Control Chart Monitoring - Application to Pollutants Prediction . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014) ISBN 978-989-758-054-3, pages 172-179. DOI: 10.5220/0005075501720179


in Bibtex Style

@conference{ncta14,
author={Philippe Thomas and William Derigent and Marie-Christine Suhner},
title={Prediction Model Adaptation Thanks to Control Chart Monitoring - Application to Pollutants Prediction},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)},
year={2014},
pages={172-179},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005075501720179},
isbn={978-989-758-054-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2014)
TI - Prediction Model Adaptation Thanks to Control Chart Monitoring - Application to Pollutants Prediction
SN - 978-989-758-054-3
AU - Thomas P.
AU - Derigent W.
AU - Suhner M.
PY - 2014
SP - 172
EP - 179
DO - 10.5220/0005075501720179