Indian Journal of Science and Technology

Open Access Open Access  Restricted Access Subscription Access

Boosting Algorithms Applied to Microwave Heating Simulation


Affiliations
1 Escuela de Ingenierías Eléctrica, Electrónica y de Telecomunicaciones, Universidad Industrial de Santander, Colombia
2 Escuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Mexico
 

Background/Objectives: In this work, we present an efficient design methodology that uses boosting algorithms to improve the accuracy of any given learning algorithm by combining the output of individual weak learners. Methods: First, a finite-difference time-domain model of a loaded rectangular wave guide yields the desired input-output response of a microwave heating system. Then, it is used to train neural networks used as weak learners in the boosting algorithm. Findings: The method is easy to implement and have a tendency not to over fit the training data. Data show that performance of the boosting algorithm increases with the number of neural networks. An example that uses 34 neural networks, with three hidden layers, fits 96 of 100 temperature profiles of the heating system with a previously defined ischolar_main mean square error below 1°C. Applications: Two simple examples of inverse modelling problems of the heating system were solved efficiently using the output of the boosting algorithm.
User

  • Kecman V. Learning and soft computing: Support Vector Machines, Neural Networks and Fuzzy Logic Models. Bradford Book; 2001.

  • Clarke SM, Griebsch JH, Simpson TW. Analysis of support vector regression for approximation of complex engineering analyses. Journal of Mechanical Design. 2005; 127(6):1077–87. https://doi.org/10.1115/1.1897403.

  • Ibrahim D. An overview of soft computing. Procedia Computer Science. 2016; 102:34–8. https://doi.org/10.1016/j.procs.2016.09.366.

  • Hao F, Park DS, Pei Z. When social computing meets soft computing: Opportunities and insights. Human-centric Computing and Information Sciences. 2018 Dec; 8(1):1–8. https://doi.org/10.1186/s13673-018-0131-z.

  • Chandra S, Agrawal S, Chauhan DS. Soft computing based approach to evaluate the performance of solar PV module considering wind effect in laboratory condition. Energy Reports. 2018 Nov; 4:252–9. https://doi.org/10.1016/j.egyr.2017.11.001.

  • Kahrobaee S, Haghighi MS, Akhlaghi IA. Improving non-destructive characterization of dual phase steels using data fusion. Journal of Magnetism and Magnetic Materials. 2018 Jul; 458:317–26. https://doi.org/10.1016/j.jmmm.2018.03.049.

  • Rajabi-Vandechali M, Abbaspour-Fard MH, Rohani A. Development of a prediction model for estimating tractor engine torque based on soft computing and low cost sensors. Measurement. 2018 Jun; 121:83–95. https://doi.org/10.1016/j.measurement.2018.02.050.

  • Liu B, Yang H, Lancaster MJ. Global optimization of microwave filters based on a surrogate model-assisted evolutionary algorithm. IEEE Transactions on Microwave Theory and Techniques. 2017 Jun; 65(6):1976–85. https://doi.org/10.1109/TMTT.2017.2661739.

  • Goksu H, Pommerenke DJ, Wunsch DC. FDTD data extrapolation using Multi-Layer Perceptron (MLP). 2003 IEEE Symposium on Electromagnetic Compatibility Symposium Record (Cat No03CH37446), IEEE. 2003; 2:735–7.

  • Yang Y, Hu SM, Chen RS. A combination of FDTD and least-squares Support Vector Machines for analysis of microwave integrated circuits. Microwave and Optical Technology Letters. 2005 Feb; 44(3):296–9. https://doi.org/10.1002/mop.20615.

  • Pedre-o-Molina JL, Monzo-Cabrera J, Sánchez-Hernandez D. A new predictive neural architecture for solving temperature inverse problems in microwave-assisted drying processes. Neurocomputing. 2005 Mar; 64:521–8. https://doi.org/10.1016/j.neucom.2004.11.026.

  • Delgado HJ, Thursby MH. A novel Neural Network combined with FDTD for the synthesis of a printed dipole antenna. IEEE Xplore: IEEE Transactions on Antennas and Propagation. 2005 Jul; 53(7):2231–6. https://doi.org/10.1109/TAP.2005.850706.

  • Chu HS, Hoefer WJR. Enhancement of time domain analysis and optimization through Neural Networks. International Journal of RF and Microwave Computer. 2007 Mar; 17(2):179–88. https://doi.org/10.1002/mmce.20212.

  • Murphy EK, Yakovlev VV. RBF network optimization of complex microwave systems represented by small FDTD modeling data sets. IEEE Transactions on Microwave Theory and Techniques. 2006 Jul; 54(7):3069–83. https://doi.org/10.1109/TMTT.2006.877059.

  • Murphy EK, Yakovlev VV. Reducing a number of full-wave analyses in RBF Neural Network optimization of complex microwave structures. IEEE MTT-S International Microwave Symposium Digest; 2009. p. 1253–6.

  • Freund Y, Schapire RE. A brief introduction to boosting. Transactions of the Japanese Society for Artificial Intelligence. 1999; 14(5):771–80.

  • Bertini Junior JR, Nicoletti M do C. An iterative boosting-based ensemble for streaming data classification. Information Fusion. 2019 Jan; 45:66–78. https://doi.org/10.1016/j.inffus.2018.01.003.

  • Liu B, Yan S, You H, Dong Y, Li Y, Lang J, et al. Road surface temperature prediction based on gradient extreme learning machine boosting. Computers and Industrial Engineering. 2018 Aug; 99:294–302. https://doi.org/10.1016/j.compind.2018.03.026.

  • Saien S, Moghaddam HA, Fathian M. A unified methodology based on sparse field level sets and boosting algorithms for false positives reduction in lung nodules detection. International Journal of Computer Assisted Radiology and Surgery. 2018 Mar; 13(3):397–409. PMid: 28795318. https://doi.org/10.1007/s11548-017-1656-8.

  • Chen P, Pan C. Diabetes classification model based on boosting algorithms. BMC Bioinformatics. 2018 Dec; 19(1):1–109. PMid: 29587624 PMCid: PMC5872396. https://doi.org/10.1186/s12859-018-2090-9.

  • Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences. 1997 Aug; 55(1):119–39. https://doi.org/10.1006/jcss.1997.1504.

  • Solomatine DP, Shrestha DL. AdaBoost.RT: A boosting algorithm for regression problems. IEEE International Joint Conference on Neural Networks (IEEE Cat No04CH37541); 2004. p. 1163–8.

  • Zhou L, Lai KK. Adaboosting Neural Networks for credit scoring. The Sixth International Symposium on Neural Networks (ISNN 2009); 2009. p. 875–84. PMCid: PMC2721908. https://doi.org/10.1007/978-3-642-01216-7_93.

  • Tian HX, Mao ZZ. An ensemble ELM based on modified AdaBoost.RT algorithm for predicting the temperature of molten steel in ladle furnace. IEEE Transactions on Automation Science and Engineering. 2010 Jan; 7(1):73–80. https://doi.org/10.1109/TASE.2008.2005640.

  • Peng T, Zhou J, Zhang C, Zheng Y. Multi-step ahead wind speed forecasting using a hybrid model based on twostage decomposition technique and AdaBoost-extreme learning machine. Energy Conversion and Management. 2017 Decl 153:589–602. https://doi.org/10.1016/j.enconman. 2017.10.021.

  • Hu M, Hu Z, Zhang M, Fu C. Research on wind power forecasting method based on improved AdaBoost.RT and KELM algorithm. Dianwang-jishu = Power System Technology. 2017; 41(2):536–42.

  • Zhou Z, Liu D. An ensemble SVR based on modified Adaboost.RT algorithm for predicting the degradation of a gas turbine compressor. Prognostics and System Health Management Conference (PHM-Chengdu), IEEE; 2016. p. 1–6. https://doi.org/10.1109/PHM.2016.7819927.

  • Gunasekaran S, Yang HW. Effect of experimental parameters on temperature distribution during continuous and pulsed microwave heating. Journal of Food Engineering. 2007 Feb; 78(4):1452–6. https://doi.org/10.1016/j.jfoodeng.2006.01.017.

  • Aguilera Bermudez E. Estudio y contribucion a los procesos de simulacion numerica computacional en fenómenos de calentamiento electromagnetico. [Tesis Doctoral]. Ph.D. Thesis, Universidad de los Andes; 2012.

  • Makul N, Rattanadecho P. Microwave pre-curing of natural rubber-compounding using a rectangular wave guide. International Communications in Heat and Mass Transfer. 2010 Aug; 37(7):914–23. https://doi.org/10.1016/j.icheat-masstransfer. 2010.03.001.


Abstract Views: 197

PDF Views: 0




  • Boosting Algorithms Applied to Microwave Heating Simulation

Abstract Views: 197  |  PDF Views: 0

Authors

Ernesto Aguilera
Escuela de Ingenierías Eléctrica, Electrónica y de Telecomunicaciones, Universidad Industrial de Santander, Colombia
Ivan Amaya
Escuela de Ingeniería y Ciencias, Tecnologico de Monterrey, Mexico
Rodrigo Correa
Escuela de Ingenierías Eléctrica, Electrónica y de Telecomunicaciones, Universidad Industrial de Santander, Colombia

Abstract


Background/Objectives: In this work, we present an efficient design methodology that uses boosting algorithms to improve the accuracy of any given learning algorithm by combining the output of individual weak learners. Methods: First, a finite-difference time-domain model of a loaded rectangular wave guide yields the desired input-output response of a microwave heating system. Then, it is used to train neural networks used as weak learners in the boosting algorithm. Findings: The method is easy to implement and have a tendency not to over fit the training data. Data show that performance of the boosting algorithm increases with the number of neural networks. An example that uses 34 neural networks, with three hidden layers, fits 96 of 100 temperature profiles of the heating system with a previously defined ischolar_main mean square error below 1°C. Applications: Two simple examples of inverse modelling problems of the heating system were solved efficiently using the output of the boosting algorithm.

References





DOI: https://doi.org/10.17485/ijst%2F2018%2Fv11i38%2F131980