Semisupervised Radial Basis Function Neural Network With an Effective Sampling Strategy

To alleviate the nonuniform error distribution and slow convergence caused by the uncertainty of sample selection in the training process of artificial neural networks, a semisupervised radial basis function neural network (SS-RBFNN) model with a new sampling strategy is proposed for parametric modeling of microwave components in this article. After evaluating the current training performance, the new sampling strategy selects suitable training samples to ensure each subregion of the whole sampling region with the same level of training and testing accuracy. Meanwhile, the proposed SS-RBFNN simplifies the modeling process to further enhance the modeling accuracy and efficiency. Two numerical examples of a slow-wave defected ground structure dual-band bandpass filter and a microstrip-to-microstrip vertical transition are employed to verify the effectiveness of the proposed model.

[1]  Wei Shao,et al.  Dynamic Adjustment Kernel Extreme Learning Machine for Microwave Component Design , 2018, IEEE Transactions on Microwave Theory and Techniques.

[2]  Witold Pedrycz,et al.  Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering , 2006, Neurocomputing.

[3]  Qi-Jun Zhang,et al.  Artificial neural networks for RF and microwave design - from theory to practice , 2003 .

[4]  S. R. Schmidt,et al.  Understanding industrial designed experiments , 1992 .

[5]  Kun-Chou Lee.  Application of Neural Network and Its Extension of Derivative to Scattering From a Nonlinearly Loaded Antenna , 2007, IEEE Transactions on Antennas and Propagation.

[6]  J.L.G. Tornero,et al.  A neural-network method for the analysis of multilayered shielded microwave circuits , 2006, IEEE Transactions on Microwave Theory and Techniques.

[7]  Wei Shao,et al.  Artificial neural network with data mining techniques for antenna design , 2017, 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting.

[8]  Günther Palm,et al.  Semi-supervised learning for tree-structured ensembles of RBF networks with Co-Training , 2010, Neural Networks.

[9]  Lei Zhu,et al.  Novel Multilayered Ultra-Broadband Bandpass Filters on High-Impedance Slotline Resonators , 2019, IEEE Transactions on Microwave Theory and Techniques.

[10]  Cheng Wu,et al.  Semi-Supervised and Unsupervised Extreme Learning Machines , 2014, IEEE Transactions on Cybernetics.

[11]  Feng Feng,et al.  Parametric Modeling of Microwave Components Using Adjoint Neural Networks and Pole-Residue Transfer Functions With EM Sensitivity Analysis , 2017, IEEE Transactions on Microwave Theory and Techniques.

[12]  D. Wisell,et al.  Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks , 2005, IEEE Transactions on Microwave Theory and Techniques.

[13]  Gaofeng Wang,et al.  A New Training Approach for Parametric Modeling of Microwave Passive Components Using Combined Neural Networks and Transfer Functions , 2009, IEEE Transactions on Microwave Theory and Techniques.

[14]  M.C.E. Yagoub,et al.  Neural-network approaches to electromagnetic-based modeling of passive components and their applications to high-frequency and high-speed nonlinear circuit optimization , 2004, IEEE Transactions on Microwave Theory and Techniques.

[15]  K. Guney,et al.  A Hybrid Method Based on Combining Artificial Neural Network and Fuzzy Inference System for Simultaneous Computation of Resonant Frequencies of Rectangular, Circular, and Triangular Microstrip Antennas , 2009, IEEE Transactions on Antennas and Propagation.

[16]  H.J. Delgado,et al.  A novel neural network combined with FDTD for the synthesis of a printed dipole antenna , 2005, IEEE Transactions on Antennas and Propagation.

[17]  Xin-She Yang,et al.  Flower Pollination Algorithm for Global Optimization , 2012, UCNC.

[18]  Chao Zhang,et al.  Parametric Modeling of EM Behavior of Microwave Components Using Combined Neural Networks and Pole-Residue-Based Transfer Functions , 2016, IEEE Transactions on Microwave Theory and Techniques.

[19]  Hao Ling,et al.  Application of Artificial Neural Networks to Broadband Antenna Design Based on a Parametric Frequency Model , 2007, IEEE Transactions on Antennas and Propagation.

[20]  D. Depriest,et al.  Understanding Industrial Designed Experiments , 1993 .

[21]  Wei Hong,et al.  The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS , 2009, IEEE Transactions on Microwave Theory and Techniques.

[22]  M. Isaksson,et al.  A comparative analysis of behavioral models for RF power amplifiers , 2006, IEEE Transactions on Microwave Theory and Techniques.

[23]  V. Rizzoli,et al.  Computer-aided optimization of nonlinear microwave circuits with the aid of electromagnetic simulation , 2004, IEEE Transactions on Microwave Theory and Techniques.

[24]  Qing Huo Liu,et al.  Parametric Modeling of Microwave Components Based on Semi-Supervised Learning , 2019, IEEE Access.

[25]  J.E. Rayas-Sanchez,et al.  EM-based optimization of microwave circuits using artificial neural networks: the state-of-the-art , 2003, IEEE Transactions on Microwave Theory and Techniques.

[26]  John W. Bandler,et al.  Computer-aided design of RF and microwave circuits and systems , 2002 .