Advertisement

A virtual layer of measure based on soft sensors

Original Research

Abstract

In this paper it is proposed a method to design and train a layer of soft sensors based on neural networks in order to constitute a virtual layer of measure in a wireless sensor network. Each soft sensor of the layer esteems the missing values of some hardware sensors by using the values obtained from some other sensors. In so doing, we perform a spatial forecasting. The correlation analysis for all parameter taken into account is used to define a cluster of real sensors used as sources of measure to esteem missing values. An application concerning the fire prevention field is used as a test case and results evaluation.

Keywords

Soft sensors Virtual measurement Neural networks Environmental monitoring 

Notes

Acknowledgments

This research is a part of an Italian Research Project named INSYEME (INtegrated SYstem for EMErgency). We would like to thanks all partners of the project for the useful collaboration and in particular Italdata that has provided the data for the experimentations.

References

  1. Benkhelifa I, Nouali-Taboudjemat N, Moussaoui S (2014) Disaster management projects using wireless sensor networks: an overview, in Advanced Information Networking and Applications Workshops (WAINA). In: 2014 28th International Conference on, pp 605–610. doi: 10.1109/WAINA.2014.99
  2. Chandra R, Zhang M (2012) Cooperative coevolution of elman recurrent neural networks for chaotic time series prediction. Neurocomputing 86:116–123. doi: 10.1016/j.neucom.2012.01.014 CrossRefGoogle Scholar
  3. Chella A, Ciarlini P, Maniscalco U (2006) Neural networks as soft sensors: a comparison in a real world application. In: International Joint Conference on Neural Networks, pp 2662–2668Google Scholar
  4. Ciarlini P, Maniscalco U, Regoliosi G (2006) Validation of soft sensors in monitoring ambient parameters. Ser Adv Math Appl Sci 72:142Google Scholar
  5. Ciarlini P, Maniscalco U (2008) Wavelets and elman neural networks for monitoring environmental variables. J Comput Appl Math 221:302–309. doi: 10.1016/j.cam.2007.10.040. http://portal.acm.org/citation.cfm?id=1414096.1414298
  6. Cleeremans A, Servan-Schreiber D, McClelland J (1989) Finite state automata and simple recurrent networks. Neural Comput 1(3):372–381. doi: 10.1162/neco.1989.1.3.372 CrossRefGoogle Scholar
  7. Elman JL (1990) Finding structure in time. Cogn Sci 14(2):179–211CrossRefGoogle Scholar
  8. Fortuna L, Graziani S, Rizzo A, Xibilia MG (2007) Soft sensors for monitoring and control of industrial processes. Advances in industrial control. Springer, London (9781846284809)Google Scholar
  9. Kadlec P, Gabrys B, Strandt S (2009) Data-driven soft sensors in the process industry. Comput Chem Eng 33(4):795–814CrossRefGoogle Scholar
  10. Lee SD, Zahrani AJ (2013) Employing first principles model-based soft sensors for superior process control and optimization. In: IPTCGoogle Scholar
  11. Leonard JA, Kramer MA, Ungar LH (1992) Using radial basis functions to approximate a function and its error bounds. Neural Netw IEEE Trans 3(4):624–627. doi: 10.1109/72.143377 CrossRefGoogle Scholar
  12. Liu J (2010) Developing soft sensors based on data-driven approach, in Technologies and Applications of Artificial Intelligence (TAAI). Int Conf 2010:150–157. doi: 10.1109/TAAI.2010.34 Google Scholar
  13. Maniscalco U (2005) Virtual sensors to support the monitoring of cultural heritage damage. In: Apolloni B, Marinaro M, Tagliaferri R (eds) Biological and artificial intelligence environments, pp 343–350 (978-1-4020-3432-9)Google Scholar
  14. Maniscalco U, Pilato G, Vassallo G (2011) Soft sensor based on E-NETs. In: Proceeding of the 2011 conference on Neural Nets WIRN10. IOS Press, Amsterdam, pp 172–179 (978–1-60750-691-1). http://portal.acm.org/citation.cfm?id=1940632.1940655
  15. Noda I, Nagao M (1992) A learning method for recurrent networks based on minimization of finite automata. In: Neural networks. IJCNN, International Joint Conference on, vol. 1, pp. 27–321. doi: 10.1109/IJCNN.1992.287211
  16. Paulsson D, Gustavsson R, Mandenius CF (2014) A soft sensor for bioprocess control based on sequential filtering of metabolic heat signals. Sensors 14(10):17864. doi: 10.3390/s141017864. http://www.mdpi.com/1424-8220/14/10/17864
  17. Rojas R (1996) Neural networks: a systematic introduction. Springer, New York (3–540-60505-3)Google Scholar
  18. Tarchi D, Fantacci R, Marabissi D (2009) The Communication Infrastructure for Emergency Management: The In.Sy.Eme. Vision. In: Proceedings of the 2009 International Conference on Wireless Communications and Mobile Computing: connecting the world wirelessly. IWCMC ’09. ACM, New York, pp 618–622 (978–1-60558-569-7). doi: 10.1145/1582379.1582513
  19. Tobler WR (1970) A computer movie simulating urban growth in the detroit region. Econ Geogr 46:234–240 (1970)Google Scholar
  20. Wang J, Zhang W, Li Y, Wang J, Dang Z (2014) Forecasting wind speed using empirical mode decomposition and elman neural network. Appl Soft Comput 23:452–459CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Istituto di Calcolo e Reti ad Alte Prestazioni, CNRPalermoItaly

Personalised recommendations