Knowledge‐based neural network approaches for modeling and estimating radon concentrations

Akkala, Arjun; Bhatt, Deepak L.; Devabhaktuni, Vijay; Kumar, Ashok

doi:10.1002/ep.11617

Cited by 11 publications

(19 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Though SMNN has better performance in evaluating FB among all the interpolation techniques, considering the remaining evaluation parameters, it can be mentioned that SMNN did not perform better over other interpolation techniques. However, ANNs and KBNNs have performed better over conventional interpolation techniques using the split‐sample validation . The CANN model has shown better performance in evaluating five of the performance measures among all the interpolation techniques discussed.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Interpolation techniques for modeling and estimating indoor radon concentrations in Ohio: Comparative study

Gummadi

Bhatt

Adusumilli

et al. 2014

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

Radon‐222 and its parent, radium‐226, is a naturally occurring radioactive decay product of uranium‐238. The US Environmental Protection Agency (USEPA) states that 10% of total lung cancer cases in the United States are directly attributable to indoor radon. The USEPA has categorized Ohio as a Zone 1 state (i.e., the average indoor radon screening level is greater than 4 pCi/L). To implement preventive measures, it is necessary to know radon concentration levels in all the zip codes of a geographic area. However, it is not possible to survey all the zip codes, owing to reasons such as inapproachability. In such places where radon data are unavailable, several interpolation techniques are used to estimate the radon concentrations. This article presents a comparison between recently developed interpolation techniques such as neural network techniques, support vector regression (SVR), random forest regression (RFR), and the conventional interpolation techniques. The performance of all the techniques has been assessed using 10‐fold cross‐validation data. This study confirmed that the correction‐based artificial neural networks have performed better over SVR and RFR with least validation error of 3.63. © 2014 American Institute of Chemical Engineers Environ Prog, 34: 169–177, 2015

show abstract

Section: Resultsmentioning

confidence: 99%

“…The Space Mapped Neural Network (SMNN) was proposed in Devabhaktuni et al [30] and was used to estimate the radon concentration in Akkala et al [20]. The SMNN is used to map the fine model input-space into a coarse model input-space using a space-mapping (SM) technique.…”

Section: Knowledge-based Neural Networkmentioning

confidence: 99%

Interpolation techniques for modeling and estimating indoor radon concentrations in Ohio: Comparative study

Gummadi

Bhatt

Adusumilli

et al. 2014

Env Prog and Sustain Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…The study uses the same set of input–output data, as is utilized in traditional interpolation technique which requires the spatial distribution of radon samples (i.e., latitude, longitude, and its corresponding radon concentration) as described in . Thus, in the case of radon modeling using ANN, the model inputs are latitude and longitude represented by x , and the corresponding desired model output by y (as radon), such that

y = f (x)

…”

Section: Conventional Ann Modeling Approachmentioning

confidence: 99%

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

Yerrabolu

Mareddy

Bhatt

et al. 2012

Env Prog and Sustain Energy

Self Cite

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

“…ANNs are also considered as black box models and have poor extrapolation and generalization capabilities. To enhance the generalization and extrapolation capabilities Knowledge Based Neural Network (KBNN) were introduced [4]. The most widely implemented KBNNs are Prior Knowledge Input (PKI), Source Difference Method (SDM) and Space Mapped Neural Networks (SMNN).…”

Section: Introductionmentioning

confidence: 99%

A robust correction model based neural network modeling framework for electromagnetic simulations and RF measurements

Adusumilli

Almalkawi

Devabhaktuni

2013

82nd ARFTG Microwave Measurement Conference

Self Cite

View full text Add to dashboard Cite

This paper introduces a new artificial neural networks (ANNs)-based correction-modeling approach for simulations and measurements. The proposed approach improves the accuracy of conventional neural models by reversing input-output variables in a systematic manner, while keeping the model structures simple relative to complex knowledge-based ANNs (KBNNs). The approach facilitates accurate/fast neural network modeling of practical electromagnetic (EM) structures, for which, training data is expensive. Two examples are presented to demonstrate the accuracy, efficiency, and feasibility of the proposed modeling approach. The first example is a broadband wire monopole antenna loaded by an annular dielectric ring resonator (DRR) at the antenna feed point. The second example is a metallic waveguide (WG) tube coated with inhomogeneous lossy materials for enhanced electromagnetic interference (EMI) shielding. The proposed approach is significant to RF circuit designers since it helps in building accurate models using reduced numbers of fullwave EM simulations and/or RF measurements.Index Terms -Artificial neural networks (ANNs), correction based neural network (CBNN), dielectric ring resonator (DRR), waveguide.

show abstract

Knowledge‐based neural network approaches for modeling and estimating radon concentrations

Cited by 11 publications

References 40 publications

Interpolation techniques for modeling and estimating indoor radon concentrations in Ohio: Comparative study

Interpolation techniques for modeling and estimating indoor radon concentrations in Ohio: Comparative study

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

A robust correction model based neural network modeling framework for electromagnetic simulations and RF measurements

Contact Info

Product

Resources

About