A Systematic Approach for Designing a Neural Network Using Existing Algorithms to Detect H2, CH4, and CO Gases

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    A neural network has different parameters like weight, bias, activation function and hidden layers. Different algorithms are applied to set the parameters and various normalization techniques applied to the input data also differs the performance of the network. So, it is very important for a designer to design the network by considering the above variables like the number of layers, different normalization techniques, different activation functions and different algorithms. It is very important to optimize all these parameters for better performance.

     

     


  • Keywords


    activation function; hidden layers; MSE; neural network; normalization, training algorithms.

  • References


      [1] B. Mondal, M.S. Meetei, J. Das, C. Roy Chaudhuri, H. Saha, “Quantitative recognition of flammable and toxic gases with artificial neural network using metal oxide gas sensors in embedded platform,” Engineering Science and Technology, an International Journal, Volume 18, Issue 2, 2015, Pages 229-234.

      [2] B. Tudu, B. Kow, N. Bhattacharyya and R. Bandyopadhyay, "Comparison of multivariate normalization techniques as applied to electronic nose based pattern classification for black tea," 3rd International Conference on Sensing Technology, Tainan, 2008, pp. 254-258.

      [3] Dae-Sik Lee, Sang-Woo Ban, Minho Lee and Duk-Dong Lee, "Micro gas sensor array with neural network for recognizing combustible leakage gases," in IEEE Sensors Journal, vol. 5, no. 3, pp. 530-536, June 2005.

      [4] X. Zhai, A. A. S. Ali, A. Amira and F. Bensaali, "MLP Neural Network Based Gas Classification System on Zynq SoC," in IEEE Access, vol. 4, no. , pp. 8138-8146, 2016.

      [5] Zhenya Zhang, Hongmei Cheng, Shuguang Zhang, “Research on the Performance of Feed Forward Neural Network Based Temprature Field Identification Model in Intelligent Building”, IEEE, 2011.

      [6] Guang-Bin Huang, "Learning capability and storage capacity of two-hidden-layer feedforward networks," in IEEE Transactions on Neural Networks, vol. 14, no. 2, pp. 274-281, Mar 2003.

      [7] D. Stathakis, “How many hidden layers and nodes?”, International Journal of Remote Sensing, Vol. 30, No. 8, 20 April 2009, 2133-2147.

      [8] P. Gao, C. Chen and S. Qin, "An Optimization Method of Hidden Nodes for Neural Network," Second International Workshop on Education Technology and Computer Science, Wuhan, 2010, pp. 53-56.

      [9] G. Bebis and M. Georgiopoulos, "Feed-forward neural networks," in IEEE Potentials, vol. 13, no. 4, pp. 27-31, Oct.-Nov. 1994.

      [10] J. Tsai, J. Chou, and T. Liu, “Tuning the structure and parameters of a Neural Network by using hybrid Taguchi-genetic algorithm,” IEEE, Vol. 17, No. 1, Jan 2006.


 

View

Download

Article ID: 28693
 
DOI: 10.14419/ijet.v7i4.22.28693




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.