Approximation of phenol concentration using novel hybrid computational intelligence methods

• Autorzy: Paweł Pławiak , Ryszard Tadeusiewicz
• Języki publikacji: EN

Abstrakty

EN

This paper presents two innovative evolutionary-neural systems based on feed-forward and recurrent neural networks used for quantitative analysis. These systems have been applied for approximation of phenol concentration. Their performance was compared against the conventional methods of artificial intelligence (artificial neural networks, fuzzy logic and genetic algorithms). The proposed systems are a combination of data preprocessing methods, genetic algorithms and the Levenberg-Marquardt (LM) algorithm used for learning feed forward and recurrent neural networks. The initial weights and biases of neural networks chosen by the use of a genetic algorithm are then tuned with an LM algorithm. The evaluation is made on the basis of accuracy and complexity criteria. The main advantage of proposed systems is the elimination of random selection of the network weights and biases, resulting in increased efficiency of the systems.

Słowa kluczowe

EN

soft computing; neural networks; genetic algorithms; fuzzy systems; evolutionary-neural systems; pattern recognition; chemometrics

• Wydawca: University of Zielona Gora Press
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2014
• Tom: 24
• Numer: 1
• Strony: 165-181

Daty

wydano

2014

otrzymano

2013-09-10

poprawiono

2013-10-12

Twórcy

autor

Paweł Pławiak

• Institute of Telecomputing, Cracow University of Technology, ul. Warszawska 24, F-5, 31-155 Cracow, Poland
• Department of Automatics and Biomedical Engineering, AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Cracow, Poland

autor

Ryszard Tadeusiewicz

• Department of Automatics and Biomedical Engineering, AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Cracow, Poland

Bibliografia

• Antonelli, M., Ducange, P., Lazzerini, B. and Marcelloni, F. (2009). Learning concurrently partition granularities and rule bases of Mamdani fuzzy systems in a multi-objective evolutionary framework, International Journal of Approximate Reasoning 50(7): 1066-1080.
• Aydogan, E., Karaoglan, I. and Pardalos, P. (2012). hGA: Hybrid genetic algorithm in fuzzy rule-based classification systems for high-dimensional problems, Applied Soft Computing 12(2): 800-806.
• Benrekia, F., Attari, M. and Bermak, A. (2009). FPGA implementation of a neural network classifier for gas sensor array applications, Proceedings of the 6th IEEE International Multi-Conference on Systems, Signals and Devices, Djerba, Tunisia.
• Cevoli, C., Cerretani, L., Gori, A., Caboni, M., Gallina, T., Toschi and Fabbri, A. (2011). Classification of Pecorino cheeses using electronic nose combined with artificial neural network and comparison with GC-MS analysis of volatile compounds, Food Chemistry 129(3): 1315-1319.
• Chandra, R., Frean, M., Zhang, M. and Omlin, C. (2011). Encoding subcomponents in cooperative co-evolutionary recurrent neural networks, Neurocomputing 74(17): 3223-3234.
• Cheng, M.-Y., Tsai, H.-C. and Sudjono, E. (2010). Evolutionary fuzzy hybrid neural network for project cash flow control, Engineering Applications of Artificial Intelligence 23(4): 604-613.
• Cheshmehgaz, H., Haron, H., Kazemipour, F. and Desa, M. (2012). Accumulated risk of body postures in assembly line balancing problem and modeling through a multi-criteria fuzzy-genetic algorithm, Computers & Industrial Engineering 63(2): 503-512.
• Czogała, E. and Ł˛eski, J. (2000). Fuzzy and Neuro-Fuzzy Intelligent Systems, Physica-Verlag, Springer-Verlag Com., Heidelberg/New York, NY.
• Font, J., Manrique, D. and Rios, J. (2010). Evolutionary construction and adaptation of intelligent systems, Expert Systems with Applications 37(12): 7711-7720.
• Ghasemi-Varnamkhasti, M., Mohtasebi, S., Siadat, M., Lozano, J., Ahmadi, H., Razavi, S. and Dicko, A. (2011). Aging fingerprint characterization of beer using electronic nose, Sensors and Actuators B: Chemical 159(1): 51-59.
• Ihokura, K. and Watson, J. (1994). The Stannic Oxide Gas Sensor: Principles and Applications, CRC Press, Boca Raton, FL.
• Lin, C.-J. and Chen, C.-H. (2011). Nonlinear system control using self-evolving neural fuzzy inference networks with reinforcement evolutionary learning, Applied Soft Computing 11(8): 5463-5476.
• Maziarz, W. and Pisarkiewicz, T. (2008). Gas sensors in a dynamic operation mode, Measurement Science and Technology 19(5): 055205.
• Maziarz, W., Potempa, P., Sutor, A. and Pisarkiewicz, T. (2003). Dynamic response of a semiconductor gas sensor analysed with the help of fuzzy logic, Thin Solid Films 436(1): 127-131.
• M.O.S., A. (2002). Technical note, Toulouse, ND, www.alpha-mos.com.
• Nakata, S., Neya, K. and Takemura, K. (2001). Non-linear dynamic responses of a semiconductor gas sensor: Competition effect on the sensor responses to gaseous mixtures, Thin Solid Films 391(2): 293-298.
• Nomura, T., Fujimori, Y., Kitora, M., Matsuura, Y. and Aso, I. (1998). Battery operated semiconductor CO sensor using pulse heating method, Sensors and Actuators B 52(1): 90-95.
• Patan, K. and Patan, M. (2011). Optimal training strategies for locally recurrent neural networks, Journal of Artificial Intelligence and Soft Computing Research 1(22): 103-114.
• Romain, A.-C., Nicolas, J., Wiertz, V., Maternova, J. and Andre, P. (2000). Use of a simple tin oxide sensor array to identify five malodours collected in the field, Sensors and Actuators B: Chemical 62(1): 73-79.
• Rutkowski, L. (2008). Computational Intelligence: Methods and Techniques, Springer, Berlin.
• Shahlaei, M., Madadkar-Sobhani, A., Saghaie, L. and Fassihi, A. (2012). Application of an expert system based on Genetic Algorithm-Adaptive Neuro-Fuzzy Inference System (GA-ANFIS) in QSAR of cathepsin K inhibitors, Expert Systems with Applications 39(6): 6182-6191.
• Snopok, B. and Kruglenko, I. (2002). Multisensor systems for chemical analysis: State-of-the-art in electronic nose technology and new trends in machine olfaction, Thin Solid Films 418(1): 21-41.
• Su, C.-L., Yang, S. and Huang, W. (2011). A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems, Expert Systems with Applications 38(10): 12189-12194.
• Tabor, Z. (2009). Statistical estimation of the dynamics of watershed dams, International Journal of Applied Mathematics and Computer Science 19(2): 349-360, DOI: 10.2478/v10006-009-0030-6.
• Tabor, Z. (2010). Surrogate data: A novel approach to object detection, International Journal of Applied Mathematics and Computer Science 20(3): 545-553, DOI: 10.2478/v10006-010-0040-4.
• Tadeusiewicz, R. (2010a). New Trends in Neurocybernetics, Computer Methods in Materials Science 10(1): 1-7.
• Tadeusiewicz, R. (2010b). Place and role of intelligent systems in computer science, Computer Methods in Materials Science 10(4): 193-206.
• Tadeusiewicz, R. (2011a). How intelligent should be system for image analysis? in H. Kwasnicka and L.C. Jain (Eds.), Innovations in Intelligent Image Analysis, Studies in Computational Intelligence, Vol. 339, Springer-Verlag, Berlin/Heidelberg/New York, NY.
• Tadeusiewicz, R. (2011b). Introduction to intelligent systems, in B.M. Wilamowski and J.D. Irvin (Eds.), The Industrial Electronics Handbook-Intelligent Systems, CRC Press, Boca Raton, FL.
• Tadeusiewicz, R. and Morajda, J. (2012). Artificial intelligence methods, in P. Lula and G. Paliwoda-Pekosz (Eds.), Analysis and Data Processing Computer Methods, Cracow University of Economics Publishing House, Cracow.
• Tallon-Ballesteros, A. and Hervas-Martinez, C. (2011). A two-stage algorithm in evolutionary product unit neural networks for classification, Expert Systems with Applications 38(1): 743-754.
• Tong, D. and Schierz, A. (2011). Hybrid genetic algorithm-neural network: Feature extraction for unpreprocessed microarray data, Artificial Intelligence in Medicine 53(1): 47-56.
• Yang, S.-H. and Chen, Y.-P. (2012). An evolutionary constructive and pruning algorithm for artificial neural networks and its prediction applications, Neurocomputing 86(1): 140-149.
• Yu, H., Wang, J., Xiao, H. and Liu, M. (2009). Quality grade identification of green tea using the eigenvalues of PCA based on the E-nose signals, Sensors and Actuators B: Chemical 140(2): 378-382.
• Zhang, L., Tian, F., Kadri, C., Pei, G., Li, H. and Pan, L. (2011). Gases concentration estimation using heuristics and bio-inspired optimization models for experimental chemical electronic nose, Sensors and Actuators B: Chemical 160(1): 760-770.

Identyfikatory

DOI

10.2478/amcs-2014-0013