Non-linear filtering of ultrasonic signals using neural networks

Vicen, Raul; Gil, Ricardo; Jarabo, Pilar; Rosa, Michele De; López-Giraldo, Francisco E.; Martínez, Delio Aristizabal

doi:10.1016/j.ultras.2003.11.002

Cited by 19 publications

(8 citation statements)

References 14 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Non-linear frequency-domain based techniques, e.g. Split Spectrum Processing (SSP) [4], Neural Networks [5] and Wavelet denoising [6] have been used to extract the signal of interest from a noisy background. The principles of wavelet theory and ultrasonic application can be found in several texts [7].…”

Section: Introductionmentioning

confidence: 99%

Comparison of cascade and concurrent signal denoising methods

Kubinyi

Šmı́d

2011

2011 IEEE International Ultrasonics Symposium

View full text Add to dashboard Cite

An important issue in ultrasonic nondestructive testing is the detection of flaw echoes in the presence of background noise created by instrumentation and by clutter noise. Signal averaging, autoregressive analysis, spectrum analysis, matched filtering and the wavelet transform have all been used to filter noise in ultrasonic signals. Widely-used wavelet threshold estimation algorithms are not designed for EMAT pulse-echo signals, and therefore do not exploit their unique impulse nature. The approaches to ultrasonic signal filtering proposed in this paper are based on wavelet denoising combined with other denoising algorithms. The denoising algorithms are combined with a knowledge ultrasonic echo detection and system frequency characteristics. The compared methods were evaluated on signals measured with EMAT probes and under various Signal-toNoise Ratio (SNR) conditions, and they outperform the wavelet transform with the UNIVERSAL threshold estimation method. The results indicated SNR enhancement up to 60 dB with real EMAT data.

show abstract

Section: Introductionmentioning

confidence: 99%

Comparison of cascade and concurrent signal denoising methods

Kubinyi

Šmı́d

2011

2011 IEEE International Ultrasonics Symposium

View full text Add to dashboard Cite

show abstract

“…The Hopfield and the Cellular neural networks can be given as main examples for these types of neural networks [2][3][4][5][6][7][8][9].…”

Section: Introductionmentioning

confidence: 99%

Image feature extraction by dynamic neural filtering and phase-only joint transform correlation

Bal

2007

Optics & Laser Technology

View full text Add to dashboard Cite

“…They have significant application fields such as identification, modeling, control, filtering, pattern recognition etc. [2][3][4][5][6] . Hopfield neural network (HNN) belongs to the class of dynamic neural networks since it has feed-back connections from output layer to input layer.…”

Section: Introductionmentioning

confidence: 99%

<title>Improved dynamic neural filtering technique by Widrow-recurrent learning algorithm</title>

Bal

2005

SPIE Proceedings

View full text Add to dashboard Cite

Neural network based image processing algorithms present numerous advantages due to their supervised adjustable weight and bias coefficients. Among various neural network architectures, dynamic neural networks, Hopfield and Cellular neural networks have been found inherently suitable for filtering applications. These kind of neural networks present two important features; supervised learnable and optimization properties. Using these properties, dynamic neural filtering technique has been developed based on Hopfield neural networks 1 . The filtering structure involves adjustable a filter mask and 2D convolution operation instead of weight matrix operations. To improve the supervised training properties, Widrow-recurrent learning algorithm has been proposed in this paper. Since the proposed learning algorithm requires less computation, consumption time in the training stage has been decreased considerably compared to previous reported supervised techniques for dynamic neural filtering 1 .

show abstract

Non-linear filtering of ultrasonic signals using neural networks

Cited by 19 publications

References 14 publications

Comparison of cascade and concurrent signal denoising methods

Comparison of cascade and concurrent signal denoising methods

Image feature extraction by dynamic neural filtering and phase-only joint transform correlation

<title>Improved dynamic neural filtering technique by Widrow-recurrent learning algorithm</title>

Contact Info

Product

Resources

About