An extended functional network model and its application for a gas sensing system

Functional networks (FNs) are a promising numerical scheme that produces accurate solutions for several problems in science and engineering with less computational effort than other conventional numerical techniques such as neural networks. By using domain knowledge in addition to data knowledge, functional networks can be regarded as a generalization of neural networks: they allow to design arbitrary functional models without neglecting possible functional constraints involved by the model. The computational efficiency of functional networks can be improved by combining this scheme with finite differences when highly oscillating systems have to be considered. The main focus of this paper is on the possible questions arising from the application of this combined scheme to an identification problem when non-smooth functions are involved and noisy data are possible. These issues are not covered by the current literature. An extended version, based on a piecewise approach, and a stability criterion are proposed and applied to the quantitative identification problem in a gas sensing system in its transient state. Numerical simulations show that our scheme allows good accuracy, avoiding the error accumulation and the sensitivity to noisy data by means of the stability criterion.

[1]  Enrique F. Castillo,et al.  A Minimax Method for Learning Functional Networks , 2000, Neural Processing Letters.

[2]  Bart L. M. Happel,et al.  Design and evolution of modular neural network architectures , 1994, Neural Networks.

[3]  E. Castillo,et al.  Working with differential, functional and difference equations using functional networks , 1999 .

[4]  Emad A. El-Sebakhy,et al.  Software reliability identification using functional networks: A comparative study , 2009, Expert Syst. Appl..

[5]  Yongquan Zhou,et al.  Application of Functional Networks to Solving Functional Equations , 2005, 2005 International Conference on Neural Networks and Brain.

[6]  Devendra K. Chaturvedi,et al.  Improved generalized neuron model for short-term load forecasting , 2004, Soft Comput..

[7]  Enrique Castillo,et al.  Functional Equations in Applied Sciences , 2004 .

[8]  Michael Bruen,et al.  Functional networks in real-time flood forecasting—a novel application , 2005 .

[9]  Stefania Tomasiello,et al.  A functional network to predict fresh and hardened properties of self‐compacting concretes , 2011 .

[10]  Yoshinobu Matsuura,et al.  Toward the realization of an intelligent gas sensing system utilizing a non-linear dynamic response , 2000 .

[11]  A. Carlo,et al.  Optimization of a NOx gas sensor based on single walled carbon nanotubes , 2006 .

[12]  Peter Alfred Payne,et al.  An intelligent gas sensing system , 1997 .

[13]  Saeid Nahavandi,et al.  A Low-Cost Intelligent Gas Sensing Device for Military Applications , 2008, 2008 Congress on Image and Signal Processing.

[14]  M. Penza,et al.  Metal-modified and vertically aligned carbon nanotube sensors array for landfill gas monitoring applications , 2010, Nanotechnology.

[15]  Amparo Alonso-Betanzos,et al.  A Measure of Noise Immunity for Functional Networks , 2001, IWANN.

[16]  Carlos Dafonte,et al.  A comparison between functional networks and artificial neural networks for the prediction of fishing catches , 2004, Neural Computing & Applications.

[17]  K. Thiruvenkatasamy,et al.  Tidal level forecasting using functional and sequential learning neural networks , 2006 .

[18]  Oscar Fontenla-Romero,et al.  Functional Networks , 2009, Encyclopedia of Artificial Intelligence.

[19]  D. Vlachos,et al.  Fuzzy Neural Networks For Gas Sensing , 1995, Proceedings of the International Solid-State Sensors and Actuators Conference - TRANSDUCERS '95.

[20]  El-Sebakhy.  Functional Networks as a Novel Approach for Prediction of Permeability in a Carbonate Reservoir , 2007 .

[21]  Fevzullah Temurtas,et al.  A study on transient and steady state sensor data for identification of individual gas concentrations in their gas mixtures , 2007 .

[22]  Emad A. El-Sebakhy.  Functional networks as a novel data mining paradigm in forecasting software development efforts , 2011, Expert Syst. Appl..

[23]  J. Bock,et al.  Signal conditioning for semiconductor gas sensors being used as detectors in gas-chromatographs and similar applications , 1998 .

[24]  D. S. Vlachos,et al.  An adaptive neural network topology for degradation compensation of thin film tin oxide gas sensors , 1997 .