The recent developments in knowledge based neural modeling

Şimşek, Murat; Zhang, Qi‐Jun; Kabir, Humayun; Cao, Yazi; Şengör, Neslihan Serap

doi:10.1016/j.procs.2010.04.147

Cited by 10 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PKID totalizes the advantages of PKI and SD knowledge-based modeling methods as introduced in [9] [13]. The quality of the mapping here is enhanced by entering the knowledge obtained from MLP ( ) with the knowledge of ( ) to be PKID's inputs in the second training step.…”

Section: Prior Knowledge Input With Difference Modeling Methods (Pkid)mentioning

confidence: 99%

See 1 more Smart Citation

New modeling of reconfigurable microstrip antenna using hybrid structure of simulation driven and knowledge based artificial neural networks

Aoad¹,

Aydın²

2020

Pamukkale J Eng Sci

View full text Add to dashboard Cite

Öz Knowledge-based modeling has a critical role to embed existing knowledge to improve modeling performance. Since reconfigurable antenna can provide more operational frequencies than the classical antennas, a knowledge-based hybrid structure is used in this work to obtain efficient model and producing optimum new models for a reconfigurable microstrip antenna. The hybrid structure consists of two phases. The first phase generates initial knowledge which is used in knowledge-based modeling structure to obtain design parameters. Artificial neural network based multilayer perceptron can generate necessary knowledge for a knowledge-based model after the training process. Knowledge-based modeling improves the accuracy of the initial model to determine design parameters corresponding to the design target. Source difference, prior knowledge Input and prior knowledge input with difference can be applied to realize an efficient knowledgebased strategy. 3D-EM simulation generates the new model in terms of the design parameters of the proposed application. It has three switching states for operating, which are organized by two resistor circuits representing ON/OFF states. Switch positions and geometrical parameters can be used for satisfying design targets between 1 GHz and 6 GHz for the efficient antenna design. Bilgi tabanlı modelleme, modelleme performansını geliştirmek için mevcut bilgiyi içine katmak için kritik bir role sahiptir. Yeniden yapılandırılabilir anten, klasik antenlerden daha fazla operasyonel frekans sağlayabildiğinden, bu çalışmada bilgi tabanlı bir hibrid yapı, verimli bir model elde etmek ve aynı zamanda yeniden yapılandırılabilir bir N-şekilli mikroşerit anten (RNSMA) için optimum yeni çözümler üretmek için kullanılmıştır. Hibrid yapı iki aşamadan oluşmaktadır. İlk aşama, tasarım parametrelerini elde etmek için bilgi tabanlı modelleme yapısında kullanılan başlangıç bilgisini üretmektedir. Yapay sinir ağı tabanlı çok katmanlı algılayıcı, eğitim sürecinden sonra bilgi tabanlı bir model için gerekli bilgiyi üretebilir. Bilgi tabanlı modelleme, tasarım hedefine karşılık gelen tasarım parametrelerini belirlemek için başlangıç modelinin doğruluğunu geliştirir. Verimli bilgi temelli bir stratejiyi gerçekleştirmek için Ön Bilgi Girişi (PKI), Kaynak Farkı (SD) ve Ön Bilgi Girişi ile Fark (PKID) uygulanabilir. 3B-EM simülasyonu, RNSMA'nın tasarım parametrelerine bağlı olarak yeni çözümü üretir. Önerilen anten, AÇIK/KAPALI durumlarını kullanarak iki direnç devresi tarafından kontrol edilen üç çalışma moduna sahiptir. Anahtar konumları ve geometrik parametreler verimli bir anten tasarımı için 1 GHz ve 6 GHz arasında tasarım hedeflerini karşılamak için kullanılabilir.

show abstract

Section: Prior Knowledge Input With Difference Modeling Methods (Pkid)mentioning

confidence: 99%

“…They have more accuracy, often faster, have better interpolation and extrapolation data process and require minimal training knowledge compared to traditional ANN (e.g. Multilayer perceptron (MLP)) [9], [13].…”

Section: Introductionmentioning

confidence: 99%

New modeling of reconfigurable microstrip antenna using hybrid structure of simulation driven and knowledge based artificial neural networks

Aoad¹,

Aydın²

2020

Pamukkale J Eng Sci

View full text Add to dashboard Cite

show abstract

“…The idea of SD (Simsek et al, 2010;Zhang and Gupta, 2000) is in combining two training data sets to be the target of the network. These data sets are the EM simulation outputs of = [ 1 , 2 , 3 ] which represents the fine data and the output response of MLP ( ) obtained from the first step.…”

Section: Source Difference Methods (Sd)mentioning

confidence: 99%

“…In testing stage, two testing data sets are selected. The testing data sets are selected outside training data which are used to test the accuracy of the models for extrapolation (Simsek et al, 2010). The number of hidden layers is two for all methods.…”

Section: Prior Knowledge Input With Differentmentioning

confidence: 99%

Developing New Solutions for a Reconfigurable Microstrip Patch Antenna by Inverse Artificial Neural Networks

Aoad

Şimşek

2018

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

This paper presents the use of inverse artificial neural networks (ANNs) to develop and optimize a reconfigurable 5-fingers shaped microstrip patch antenna. New solutions are produced by using three accurate prior knowledge inverse ANNs with sufficient amount of training data where the frequency information is incorporated into the structure of ANNs. The proposed antenna can operate with four modes, which are controlled by two PIN diode switches with ON/OFF states, and it resonates at multiple frequencies between 2-7 GHz. The complexity of the input/output relationship is reduced by using prior knowledge. Three independent methods of incorporating knowledge in the second step of the training process with a multilayer perceptron (MLP) in the first step are demonstrated and their results are compared to EM simulation.

show abstract

“…The final ANN‐model will be described in this case with huge mathematical formulae. However, with the knowledge‐based modeling techniques, the neural networks are used to improve and optimize the accuracy of models existing in microwave simulators. Several knowledge‐based modeling techniques have been used in microwave modeling mainly Knowledge‐Based Neural Network method, Prior Knowledge Input method, and Space Mapping Neural Network method (SMNN) …”

Section: Introductionmentioning

confidence: 99%

Neuro-space mapping modeling approach for trapping and self-heating effects on GaAs and GaN devices

Elhamadi

Boussouis

Touhami

et al. 2017

Int J RF Microw Comput Aided Eng

View full text Add to dashboard Cite

In recent years, neural networks have been successfully applied for modeling the nonlinear microwave devices as GaAs and GaN MESFETs/HEMTs. Many modeling approaches have been developed for small and large signal applications. In this contribution, a neuro-space mapping approach is proposed for modeling the trapping and the self-heating effects on GaAs and GaN devices. The Angelov empirical model is used as the coarse model, which can be adjusted using DC and Pulsed I/V measurements at different static bias points. The proposed approach is tested for the MGF1923 GaAs MESFET and for an 8 3 75 lm AlGaN/GaN HEMT. DC and transient simulation results are compared to DC and Pulsed I/V measurements. Good results are obtained for the DC and dynamics I/V characteristics at different static bias points. K E Y W O R D S neural networks, pulsed I/V measurements, self-heating effect, space mapping, trapping effect Int J RF Microw Comput Aided Eng. 2017;27:e21106.

show abstract

The recent developments in knowledge based neural modeling

Cited by 10 publications

References 22 publications

New modeling of reconfigurable microstrip antenna using hybrid structure of simulation driven and knowledge based artificial neural networks

New modeling of reconfigurable microstrip antenna using hybrid structure of simulation driven and knowledge based artificial neural networks

Developing New Solutions for a Reconfigurable Microstrip Patch Antenna by Inverse Artificial Neural Networks

Neuro-space mapping modeling approach for trapping and self-heating effects on GaAs and GaN devices

Contact Info

Product

Resources

About