An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

Bermani, E.; Caorsi, S.; Raffetto, Mirco

doi:10.2528/pier99052001

Cited by 31 publications

(27 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, they sometimes make classification more complicated, which is called the curse of dimensionality. It is required to reduce the number of features [20]. Principal component analysis (PCA) is an efficient tool to reduce the dimension of a data set consisting of a large number of interrelated variables while retaining most of the variations.…”

Section: Feature Reductionmentioning

confidence: 99%

A New Classifier for Polarimetric Sar Images

Zhang¹,

Wu²,

Wei³

2009

PIER

View full text Add to dashboard Cite

Abstract-This paper proposes a hybrid classifier for polarimetric SAR images. The feature sets consist of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM) based texture features. Then, the features are reduced by principle component analysis (PCA). A 3-layer neural network (NN) is constructed, trained by resilient back-propagation (RPROP) method to fasten the training and early stop (ES) method to prevent the overfitting. The results of San Francisco and Flevoland sites compared to Wishart Maximum Likelihood and wavelet-based method demonstrate the validness of our method in terms of confusion matrix and overall accuracy. In addition, NNs with and without PCA are compared. Results show the NN with PCA is more accurate and faster.

show abstract

Section: Feature Reductionmentioning

confidence: 99%

A New Classifier for Polarimetric Sar Images

Zhang¹,

Wu²,

Wei³

2009

PIER

View full text Add to dashboard Cite

show abstract

“…It should be pointed that its is not required to explicitly define the nonlinear function ϕ and the nonlinear mapping is realized by selecting a function K so that it represents a positive-definite kernel function. In this paper, gaussian kernel functions, whose effectiveness in dealing with subsurface sensing has been already assessed [5], are taken into account.…”

Section: Lbe-based Technique For Buried Object Detection -The Svm Algmentioning

confidence: 99%

“…The detection problem is reformulated into a regression one, where the data (i.e., the measures of the anomalous field) and the unknowns (i.e., the position of the object as well as its geometric and dielectric characteristic according to the adopted parameterization) are related by means of an approximated function to be estimated through an off-line data fitting process (training phase). As a matter of fact, approaches based on both neural networks (NNs) [5,6] and SVMs [7,8] have been satisfactorily applied for buried object detection in presence of single-illumination acquisition systems. On the other hand, the use of a multi-illumination strategy certainly would improve the localization accuracy of the LBE-based approach, but could greatly complicate the mandatory training procedure.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Source Strategy Based on a Learning-by-Examples Technique for Buried Object Detection

Bermani¹,

Boni²,

Caorsi³

et al. 2004

PIER

View full text Add to dashboard Cite

Abstract-In the framework of buried object detection and subsurface sensing, some of the main difficulties in the reconstruction process are certainly due to the aspect-limited nature of available measurement data and to the requirement of an on-line reconstruction. To limit these problems, a multi-source (MS) learning-by-example (LBE) technique is proposed in this paper. In order to fully exploit the more attractive features of the MS strategy, the proposed approach is based on a support vector machine (SVM). The effectiveness of the MS-LBE technique is evaluated by comparing the achieved results with those obtained by means of a previously developed single-source (SS) SVMbased procedure for an ideal as well as a noisy environment.

show abstract

“…Artificial neural networks (ANNs) have been exploited in different EMC problems such as detection and identification of vehicles based on their unintended radiated emissions [12], target discrimination [13,14], calculation of multilayer magnetic shielding [15], estimating PCB configuration from EMI measurements [16], characterization and modeling of the susceptibility of integrated circuits to conducted electromagnetic disturbances [17], recognition and identification of radiated EMI for shielding apertures [18], prediction of electromagnetic field in metallic enclosures [19], adaptive beamforming [20,21], PAD modeling [22], and detection of dielectric cylinders buried in a lossy half-space [23]. This paper takes advantage of MLP neural networks to model and estimate motorcycle's radiated emissions in terms of the registered velocity.…”

Section: Introductionmentioning

confidence: 99%

Modeling Radiated Electromagnetic Emissions of Electric Motorcycles in Terms of Driving Profile Using MLP Neural Networks

Wefky¹,

Espinosa²,

Santiago³

et al. 2013

PIER

View full text Add to dashboard Cite

Abstract-Current automotive electromagnetic compatibility (EMC) standards do not discuss the effect of the driving profile on real traffic vehicular radiated emissions. This paper describes a modeling methodology to evaluate the radiated electromagnetic emissions of electric motorcycles in terms of the driving profile signals such as the vehicle velocity remotely controlled by means of a CAN bus. A time domain EMI measurement system has been used to measure the temporal evolution of the radiated emissions in a semi-anechoic chamber. The CAN bus noise has been reduced by means of adaptive frequency domain cancellation techniques. Experimental results demonstrate that there is a temporal relationship between the motorcycle velocity and the radiated emission power in some specific frequency ranges. A Multilayer Perceptron (MLP) neural model has been developed to estimate the radiated emissions power in terms of the motorcycle velocity. Details of the training and testing of the developed neural estimator are described.

show abstract

An Inverse Scattering Approach Based on A Neural Network Technique for the Detection of Dielectric Cylinders Buried in a Lossy Half-Space

Cited by 31 publications

References 17 publications

A New Classifier for Polarimetric Sar Images

A New Classifier for Polarimetric Sar Images

A Multi-Source Strategy Based on a Learning-by-Examples Technique for Buried Object Detection

Modeling Radiated Electromagnetic Emissions of Electric Motorcycles in Terms of Driving Profile Using MLP Neural Networks

Contact Info

Product

Resources

About