A Comprehensive Neuro-Fuzzy Approach in Predicting Dielectric Loss on Doped and Undoped Terbium Manganites

Abstract
Authors
Keywords
Conclusion
References

Artificial Neural Networks is considered as one of the successful machine learning technique to model expert behavioral systems and it is competent enough to minimize human efforts in manual prediction. This research anticipates the applicability of the Adaptive Neuro-Fuzzy Modeling approach in the Dielectric Loss prediction. Prediction of Dielectric loss parameter has wide range of applicability in electric circuits of radio, and television systems. The difficulty lies in Dielectric loss parameter is its high dependency on the nature of dielectric material and at different frequency. Doped and undoped Terbium Manganite is chosen as dielectric material to perform comparative analysis. The Adaptive Neuro Fuzzy Inference System, with its inherent knowledge representation mechanism, nonlinear behavior and adaptive control property can replace almost all basic predictor neural networks. This hybrid model establishes the superior capability in prediction over Feed forward backpropagation networks. Finally an analysis is made statistically between Hybrid learning and back-propagation learning mechanism in Adaptive Neuro-Fuzzy inference system to achieve best suited learning algorithm in dielectric loss prediction.

Published In : IJCSN Journal Volume 7, Issue 2

Date of Publication : April 2018

Pages : 115-125

Figures :23

Tables : 06

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.

Dibyajyoti Chatterjee : is a final year B.Tech student of Computer Science and Engineering.

Jitsoma Dey : is a final year B.Tech student of Computer Science and Engineering.

Adaptive Neuro-Fuzzy Systems, Dielectric Loss, Doping, Tolerance, Transfer Functions, Semiconductor

This research initially aims to cater efficient applicability of Neuro Fuzzy Networks in the diversified province of Semiconductor in predicting Dielectric Loss parameter with respect to different temperature at different frequencies. The primary behavioral analysis is made on the basis of prediction accuracy percentage, achieved by Artificial Neural Networks with their Forward Chaining mechanism to predict dielectric loss parameter of doped and undoped Terbium Manganites. The research significantly shows, enhanced performance of ANFIS with respect to Feed-forward back propagation networks at initial stages; later ANFIS with Hybrid learning rule is proven as well suited dielectric loss predictor in the domain of semiconductor doping. The comparative analysis made for doped and undoped Terbium Manganites at Tolerance 0.005 Hybrid Learning Algorithm of ANFIS performs better than other two approaches. But at tolerance level up to 0.01 both the learning Mechanism of ANFIS performs equally; hence the superiority of Hybrid learning rule in lower tolerance of ANFIS is clearly visible over the statistical comparisons.

[1] J. Xu, Y. Cui, H. Xu , “Dielectric properties of TbMnO3 ceramics doped with Bi and Fe ions”, Results in Physics, Vol. 6, 2016, pp. 811-816. [2] J.L. Izquierdo, G. Bolanos, O. Moran, “Effect of the Al-doping on the electrical and thermoelectric response of TbMnO3 polycrystalline samples: Evidence of polaronic transport”, Journal of Alloys and Compounds, Vol. 652, 2015, pp. 292-297. [3] A.M. Badr, H.A. Elshaikh, I.M. Ashraf, “Impacts of Temperature and Frequency on the Dielectric Properties for Insight into the Nature of the Charge Transports in the T12S Layered Single Crystals”, Journal of Modern Physics, Vol. 2, 2011, pp. 12-25. [4] A.L. Ward, “Prediction of second breakdown power”, Journal of Electrostatics, Vol. 24, 1990, pp. 83-93. [5] Z. Zhang, H. Zhang, H. Zhao, Z. Yu, L. He, J. Li, “Prediction of the electronic structures, thermodynamic and mechanical properties in manganese doped magnesium-based alloys and their saturated hydrides based on density functional theory”, Journal of Power Sources, Vol. 280, 2015, pp. 147-154. [6] T.W. Canzler, U. Denker, O. Fadhel, Q. Huang, C. Rothe, A.W.N. AG, “Application of Redox doping in OTFTs”. SPIE, Vol 7054, 2008. [7] Y. Rajakarunanayake, J.O. McCaldin, T.C. x, “Electric field assisted doping of semiconductors during epitaxial growth”, Journal of Crystal Growth, Vol. 111, 1991, pp. 782-78. [8] V. Kolomoets, V. Ermakov, L. Panasyuk, S. Fedosov, B. Orasgulyev, P. Nazarchuk, “Application of high uniaxial strain method for semiconductor parameter determination”, Journal of Physica B: Condensed Matter, Vol. 417, pp. 46-48. [9] M. Kenzelmann, A. B. Harris, S. Jonas, C. Broholm, J. Schefer, S. B. Kim, C.L. Zhang, S. W. Cheong, O. P. Vajk, J. W. Lynn, “Magnetic inversion symmetry Breaking and Ferroelectricity”, Phys.Rev.Lett.95, 087206, 2005. [10] B. Senff, P. Link, K. Hradil, A. Hiess, L. P. Regnault, Y. Sidis, N. Aliouane, B. N. Argyriou, M. TbMnO3: Evidence for a Hybridized Soft Mode”, Phys.Rev.Lett.98, 137206, 2007. [11] Amin Hedayatim Moghaddam, Moein Hedayati Moghaddam, Morteza Esfandyari, “Stock market index prediction using artificial neural network”, 2016 [12] Aditya Mukerji, Chandranath Chatterjee, N. Raghuwanshi, “Flood forecasting using ANN, Neuro- Fuzzy, and Neuro-GA models”, Journal of Hydrologic Engineering, Vol. 14(6), pp. 647-652. [13] Arthi K, Tamilarasi A, “Prediction of autistic disorder using neuro fuzzy system by applying ANN technique”, 2008 [14] H.Wang, E.M.Weig, A.N.Cleland, J.M.Martinis, “Microwave dielectric loss at single photon energies and millikelvin temperatures”, 2008 [15] Jang, Sun, Mizutani (1997), “Neuro-Fuzzy and Soft Computing”, pp. 335-368. [16] P. Mullai, Eldon R. Rene, H. Suck Park, P.L. Sabarathinam, Adaptive Neural Based Fuzzy Inference System(ANFIS) Modeling of an Anaerobic Wastewater Treatment Process, IGI Global, 2012. [17] Neha Mathur, Ivan Glesk, ArjanBuis, “Comparison of adaptive neuro-fuzzy inference system (ANFIS) and Gaussian processes for machine learning (GPML) algorithms for the prediction of skin temperature in lower limb prostheses’’, Medical Engineering & Physics,Vol. 38, Issue 10,2016, pp.1083-1089. [18] Dhifaf Azeez, Mohd Alauddin Mohd Ali, Kok Beng Gan,Ismail Saiboon, “Comparison of adaptive neurofuzzy inference system and artificial neutral networks model to categorize patients in the emergency department”, Springerplus,2013,Vol.2,2013,pp.416. [19]Ahmed Al-Hmouz ,Jun Shen , R. Al-Hmouz ,Jun Yan, “Modeling and Simulation of an Adaptive Neuro- Fuzzy Inference System (ANFIS) for Mobile Learning”,in IEEE Xplore,2011,Vol.5,pp. 226-237. [20] Wayan Suparta , Kemal Maulana Alhasa,”A comparison of ANFIS and MLP models for the prediction of precipitable water vapor”, in IEEE Xplore,2013. [21] A.A. MasrurAhmed, Syed Mustakim Ali Shah , “Application of adaptive neuro-fuzzy inference system (ANFIS) to estimate the biochemical oxygen demand (BOD) of Surma River”, Journal of King Saud University - Engineering Sciences,Vol.29,2017,pp- 237-243.