Robust Prediction Capability of Feed Forward Back
Propagation Network over Adaptive Neuro Fuzzy
Inference System on Optical Characteristics of Ironbased
Superconductor Glass materials
This research intends to establish the dominant prediction potentiality of Feed Forward Back Propagation Networks
over the Adaptive Neuro Fuzzy Inference Systems. The elementary step contains the analysis on the different transfer functions of
Feed Forward Back Propagation Network in order to identify the most convenient transfer function for estimating optical parameters
of Fe doped Glass material: real parts of Absorption Co-efficient and Refractive Index over Wavelength. The motive behind Fe
doping is that it converts Glass material which acts as a Semiconductor to behave as a Superconductor which eventualizes its high
applicability in the field of Telecommunication, Optoelectronics, Laser Based Manufacturing, Biomedical Engineering and more.
Further, Adaptive Neuro Fuzzy Inference System with different membership functions are examined to reach best probable outcome.
The optical properties in the basic experimental dataset are studied using Spin coater and Ultraviolet Spectrometer ranging in
between 29.3 µg/cm2 to 2623 µg/cm2, whereas, only two samples are considered in this research paper among the given five
samples.
Published In:IJCSN Journal Volume 7, Issue 3
Date of Publication : June 2018
Pages : 166-181
Figures :28
Tables : 19
Anindita Das Bhattacharjee : started her career in industry
as a trainee software developer for a year. She has done M.
Tech in Computer Science from National Institute of
Technology (NIT), Durgapur. She secured a position of First
Class Second in M. Tech. Currently she is working in Swami
Vivekananda Institute of Science and Technology. She has
been teaching for about 10 years in Computer Science. She
is an author of a book “Artificial Intelligence and Soft
Computing for Beginners” published in 2013 and author of
book chapters in the book “Intelligent Analysis for
Multimedia Information” published by IGI Global and
indexed in Scopus.
Shibashis Mitra : is pursuing B. Tech. Final year student in
Computer Science and Engineering in Swami Vivekananda
Institute of Science and Technology.
Asiya Amreen Zaman : is pursuing B. Tech. Final year
student in Computer Science and Engineering in Swami
Vivekananda Institute of Science and Technology. Secured
3rd position in International Olympiad of Science and 2nd
position in Olympiad of English 2011, New Delhi.
In order to develop a robust decision-making model,
a Hybrid Model (ANFIS) which incorporates the
property of parallelism in computing of a Neural
Network along with inference capability of Fuzzy Logic
Designer is used in the comparative analysis but FFBPN
still outperforms the hybrid model ANFIS due to some
of its inherent behavioural properties and also depends
upon the nature of preferred input dataset.
[1] Abdallah M. D., Mohammed E. A. E., Ahmed PS.A.E.,
Elgani PR. A., “Optical Properties of Glass and Plastic
Doped by Fe”, International Journal of Innovative
Science, Engineering & Technology, Vol. 4, Issue 4,
April 2017, pp. 174-183.
[2] James G. N., Mason A. B., “Protocol to determine
accurate absorption co-efficient for iron-containing
transferrin”, Analytical Biochemistry, Vol. 382, 15
November,2008, pp. 150.
[3] Torres J. H., Welch A. J., MS I. C., Motamedi M.,
“Tissue Optical Property measurements:
Overestimation of absorption co-efficient with
spectrophotometric techniques”, American Society for
Laser, Surgery and Medicine, Vol. 14, Issue 3, 1994,
pp. 249-257.
[4] Coronado A. R., Valenzuela A. G., Perez C. S., Barrera
R. G. Miola “Measurement of effective refractive index
of a turbid colloidal suspension using light refraction”,
New Journal of Physics, Vol. 7, 6 April,2005, pp. 1-22.
[5] H. A. K., Suresh Y., “Multilayer feed forward neural
network to predict the speed of wind”, IEEE Xplore
Library, 12 December,2016, pp. 285-290.
[6] Munirathinam S., Ramadoss B., “Feed Forward
Backpropagation Neural Network Model to Predict
Remaining Useful Life Estimation of Ion Implant
Tool”, International Journal of Engineering &
Technology, Vol. 15, December 2015, pp. 64-72.
[7] Asteris P. G., Roussis P. C., Douvika M. G., “Feed-
Forward Neural Network Prediction of the Mechanical
Properties of Sandcrete Materials”, MDPI, 9
June,2017, pp. 1-21.
[8] Abdulshahed A. M., Longstaff A. P., Fletcher S., “The
application of ANFIS prediction models for thermal
error compensation on CNC machine tools”, Applied
Soft Computing, Vol. 27, Issue , February 2014, pp.
158-168.
[9] Boyacioglu M. A., Avci D., “An Adaptive Network-
Based Fuzzy Inference System(ANFIS) for the
prediction of stock market return: The case of Istanbul
Stock Exchange”, Expert Systems with Applications,
Vol. 37, Issue 12, December 2010, pp. 7908-7912.
[10] Mafolo T., Popoola O. M., “Domestic lighting demand
profile prediction using ANFIS and Neural Network”,
International Conference on the Domestic Use of
Energy (DUE), 2016, pp. 1-8.
[11] Sahin M., Erol R., “A Comparative Study of Neural
Networks and ANFIS for Forecasting Attendance Rate
of Soccer Games”, Mathematical and Computational
Applications, Vol., Issue, 2017, pp. 22-43.
[12] Mayilvaganan M. K., Naidu K. B., “Comparative
Study of ANN and ANFIS for the Prediction of
Groundwater Level of a Watershed”. Global Journal of
Mathematical Sciences: Theory and Practical, Vol. 3,
2011, pp. 299-306.
[13] Walia N., Singh H., Sharma A., “ANFIS: Adaptive
Neuro-Fuzzy Inference System- A Survey”,
International Journal of Computer Applications, Vol.
123, Issue 13, August 2015.
[14] Reis S. T. D., Pontuschka W. M., Yang J. B., Faria D.
L. A., “Properties and Structural Features of Iron
Doped BABAL Glasses”, Materials Research, Vol. 6,
Issue 3, 2003, pp. 389-394.
[15] Mandal S., Hazra S., “Structural and physical
properties of Fe2O3-doped lead vanadate glass”,
Journal of Materials research, Vol. 15, Issue 1, Jan
2000, pp. 218-221.
[16] Baino F., Fiume E., Miola M., Leone F., Onida B.,
Laviano F., Gerbaldo R., Verne E., “Fe-Doped Sol-Gel
Glasses and Glass-Ceramics for Magnetic
Hyperthermia”, materials, Vol., Issue, 2018, pp. 2-15.
[17] Mardare D., Apostol E., “TiO2 thin films doped by Ce,
Nb, Fe, deposited onto ITO/glass substrates”,
JOURNAL OF OPTOELECTRONICS AND
ADVANCED MATERIALS, Vol. 8, Issue 3, June
2006, pp. 914-916.
[18] Hua W. M., Sum W. P., Yew E., Ibrahim Z., Hussin R.,
“Structural and Luminescence Properties of Borate
Glass with Lithium and Strontium Modifier Doped
with Transition Metal Ions”, Advanced Materials
Research, Vol. 501, 2012, pp. 71-75.
[19] Nassiri C., Hadri A., Chafi FZ., Hat A. E., Hassanain
N., Rouchdi M., Fares B., Mzerd A., “Structural,
Optical and Electrical Properties of Fe Doped SnO2
Prepared by Spray Pyrolysis”, Journal of materials and
Environmental Sciences, Vol. 8, Issue 2, 2017, pp. 420-
425.
[20] Choudhary B. P., Singh N. B., “Characterization of
Fe3+-doped silver phosphate glasses”, Bulletin Of
materials Science, Vol. 39, Issue 7, December 2016, pp. 1651–1663.
[21] Bora D., Hazarika S., “Optical Properties of Malachite
Green Dye Doped SiO2 Glasses: Effect of Transition
Metal (Fe-I) Used as a Codopant”, International
Journal of Optics, Vol. 2014, 2014, pp. 1-9.
[22] Chiad S. S., “Optical Characterization of NiO Doped
Fe2O3 thin Films Prepared by Spray Pyrolysis
Method”, International Letters of Chemistry, Physics
and Astronomy, Vol. 45, 2015, pp. 50-58.
[23] Dhingra S., Man P. S., “An Adaptive Neuro Fuzzy
Approach for Software Development Time
Estimation”, International Journal of Advanced
Research in Computer Science and Software
Engineering, Vol. 3, Issue 5, May 2013, pp. 586-590.
[24] Jang J. S. R., “ANFIS: Adaptive-Network-Based Fuzzy
Inference System”, IEEE Trans. Systems, Man,
Cybernetics, Vol. 23, Issue (5/6), 1993, pp. 665-685.
[25] Jang J. S. R., Sun C. -T., “Neuro-Fuzzy Modeling and
Control”, Proceeding of the IEEE, Vol. 83, Issue 3,
March 1995, pp. 378-406.
[26] Bonissone, Badami, Chiang, Khedkar, Marcelle,
Schutten, “Industrial Application of Fuzzy Logic at
General Electric”, Proceedings of the IEEE, Vl. 83,
Issue 3, March 1995, pp. 450-465.
[27] Jang J. S. R., Gulley N., Natick, “The Fuzzy Logic
Toolbox for use with MATLAB”, MA: The
MathWorks Inc., 1995.
[28] Michie, Spiegelhart, Taylor(Eds.), Machine Learning,
Neural and Statistical Classification, NY: Ellis
Horwood, 1994.
[29] Breiman, Friedman, Oslhen, Stone, “Classification and
Regression Trees”, CA: Wadsworth and Brooks, 1985.
[30] Ali O. A. M., Ali A. Y., Sumait B. S., “Comparison
between the Effects of Different Types of Membership
Functions on Fuzzy Logic Controller Performance”,
International Journal of Emerging Engineering
Research and technology, Vol. 3, Issue 3, March 2015,
pp. 76-83.
[31] Vafakhah M., “Comparison of cokriging and adaptive
neuro-fuzzy inference system models for suspended
sediment load forecasting”, Arabian Journal of
Geosciences, Vol. 6, Issue 8, August 2013, pp. 3003-
3018.
[32] Yetilmezsoy K., Ozkaya B., Cakmaskci M., “Artificial
Intelligence-Based Prediction Models for
Environmental Engineering”, Neural Network world,
Vol. 3, Issue 11, 18 April,2010, pp. 193-218.
[33] Yetilmezsoy K., Fingas M., Fieldhouse B., “An
Adaptive neuro-fuzzy approach for modeling of waterin-
oil emulsion formation”, Colloids and Surfaces A:
Physicochemical and Engineering Aspects, Vol. 389,
Issue 1-3, 20 September,2011, pp. 50-62.
[34] Azeez D., Ali M. A. M., Gan K.B., Saiboon I.,
“Comparison of adaptive neuro-fuzzy inference system
and artificial neural networks model to categorize
patients in the emergency department”, National Center
for Biotechnology Information, Vol. 2, Issue 1, 29
August,2013, pp. 2-10.
[35] Kumari N., Sunita, Smita, “Comparison of ANNs,
Fuzzy Logic and Neuro-Fuzzy Integrated Approach for
Diagnosis of Coronary Heart Disease: A Survey”,
International Journal of Computer Science and Mobile
Computing, Vol 2, Issue 6, June 2013, pp. 216-224.