Robust training of microwave neural models

Devabhaktuni, Vijay; Xi, Changgeng; Wang, Fang; Zhang, Qi‐Jun

doi:10.1002/mmce.10016

Cited by 29 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NN techniques are in use for a wide variety of microwave applications such as embedded passives [5], transmission line components [6][7][8], vias [9], bends [10], coplanar waveguide (CPW) components [11], spiral inductors [12], FETs [13], amplifiers [14,15], etc. NNs are used in impedance matching [16,17], inverse modeling [18], measurements [19], and synthesis [20].…”

Section: Neural Network Developmentmentioning

confidence: 99%

Levenberg-Marquardt and Conjugate Gradient Neuro-Modeling of Simulated Miniature Rectangular Microstrip Antenna

Mishra¹,

Janvale²,

Kasar³

et al. 2012

Advanced Computational Techniques in Electromagnetics

View full text Add to dashboard Cite

Neural-network computational modules have recently gained recognition as an unconventional and useful tool for RF and microwave modeling and design. Neural networks can be trained to learn the behaviour of passive/active components/circuits. This work presents artificial neural network (ANN) for design of IE3D simulated miniature microstrip antenna. In the presented work, the artificial neural network is used for accurate determination of different parameters like resonant frequency, bandwidth, return loss, and voltage standing wave ratio (VSWR) of square and rectangular microstrip patch antenna. The developed neural network model which uses the data of simulated hundred antennas is based on Levenberg-Marquardt (LM) and conjugate gradient (CG) feed-back propagation. The developed ANN models for rectangular microstrip antennas (RMSAs) are in very good agreement with the experimental results available in the literature. The comparative analysis of developed models is presented which gives higher accuracy than that reported elsewhere.

show abstract

Section: Neural Network Developmentmentioning

confidence: 99%

Levenberg-Marquardt and Conjugate Gradient Neuro-Modeling of Simulated Miniature Rectangular Microstrip Antenna

Mishra¹,

Janvale²,

Kasar³

et al. 2012

Advanced Computational Techniques in Electromagnetics

View full text Add to dashboard Cite

show abstract

“…ANN's have emerged as a powerful tool in signal processing, pattern recognition, and other applications . However, to a certain extent the accuracy of the neural models depends on the adequacy of training data.…”

Section: Introductionmentioning

confidence: 99%

Correction Model‐BasedANNModeling Approach for the Estimation of Radon Concentrations inOhio

Yerrabolu

Mareddy

Bhatt

et al. 2012

Env Prog and Sustain Energy

View full text Add to dashboard Cite

According to National Cancer Institute, radon is one of the major causes for lung cancer related deaths after smoking in US. To prevent deaths due to radon inhalation there is a need to determine the level of radon concentration in each locality, for example, zip code and this would help ease the identification of areas with high radon concentration thereby allowing the necessary preventive measures to be taken. However, factors like inapproachability hinder the process of estimating radon concentration in some places. In such places it is a common practice to estimate the radon concentrations using several interpolation techniques. In this article, a new approach that improves the accuracy of the neural model with the help of sensitivity‐based correction model for modeling and estimating radon concentrations in Ohio is proposed. The results are compared with commonly used techniques such as kriging, radial basis function (RBF), inverse distance weighting (IDW), global polynomial interpolation (GPI), local polynomial interpolation (LPI), and the recently developed conventional ANN modeling approach. Further, model accuracies of all the above models are evaluated based on Willmott's Index and the ranked performance measures criteria with emphasis on the extreme‐end (peak‐end, low‐end), and mid‐range radon concentrations. The results demonstrate the effectiveness of the proposed approach in estimating the radon concentrations with the percentage improvement of 70–80% prediction accuracy, compared to the other techniques. © 2012 American Institute of Chemical Engineers Environ Prog, 32: 1223–1233, 2013

show abstract

“…They are known for their ability to model highly complicated input-output relationships that are difficult for conventional techniques [34]. After learning and abstracting from either measured or simulated data, referred to as training data, through a process called training, neural models provide instant answers to the task learnt [35,36]. Theoretically, neural models can be considered as black-box models, whose accuracy depends on the training data presented.…”

Section: Brief Introduction To Annsmentioning

confidence: 99%

“…Theoretically, neural models can be considered as black-box models, whose accuracy depends on the training data presented. A good collection of training data, i.e., data that is well-distributed, sufficient, and accurately measured/simulated, is suggested for obtaining an accurate neural model [35][36][37].…”

Section: Brief Introduction To Annsmentioning

confidence: 99%

Development of an ANN Interpolation Scheme for Estimating Missing Radon Concentrations in Ohio

Akkala¹

2011

TOEBMJ

View full text Add to dashboard Cite

Radon (Rn) is a chemically inert, naturally occurring radioactive gas. It is one of the main causes of lung cancer second to smoking, and accounts for about 25,000 deaths every year in the US alone according to the National Cancer Institute. In order to initiate preventive measures to reduce the deaths caused by radon inhalation, it is helpful to have radon concentration data for each locality, e.g. zip code. However, such data are not available for each and every zip code in Ohio, owing to several reasons including inapproachability. In places where data is unavailable, radon concentrations must be estimated using interpolation techniques. This paper presents a new interpolation technique based on Artificial Neural Networks (ANNs) for modeling and predicting radon concentrations in Ohio, US. Several ANNs were first trained and then validated using available data. From the resulting models, the model with lowest validation error was identified. Model accuracies using the proposed approach was found to be significantly better compared to conventional interpolation techniques such as Kriging and Radial Basis Functions.

show abstract

Robust training of microwave neural models

Cited by 29 publications

References 23 publications

Levenberg-Marquardt and Conjugate Gradient Neuro-Modeling of Simulated Miniature Rectangular Microstrip Antenna

Levenberg-Marquardt and Conjugate Gradient Neuro-Modeling of Simulated Miniature Rectangular Microstrip Antenna

Correction Model‐BasedANNModeling Approach for the Estimation of Radon Concentrations inOhio

Development of an ANN Interpolation Scheme for Estimating Missing Radon Concentrations in Ohio

Contact Info

Product

Resources

About