Approximation by nonlinear wavelet networks

Zhang, Q.; Benveniste, Albert

doi:10.1109/icassp.1991.150188

Cited by 14 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal of training the classifier is to minimize the error E=E(dn_vn)2 (4) where 4 and v are the desired and actual outputs for the n-th training signal .s(t), by optimizing c, a, b, and w in Eqs. 2 and 3.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

<title>Adaptive time-frequency classification of acoustic backscatter</title>

1995

View full text Add to dashboard Cite

An adaptive time-frequency classifier algorithm is detailed and tested on a data set of acoustic backscatter from a metallic manmade object and natural clutter with synthetic reverberation noise. The algorithm is improved over previous versions in that it operates directly on time signals rather than their wavelet transforms, and in that the features measure time-frequency energy and are insensitive to phase differences (due to signal variations). The time-frequency features are initialized by selecting wavelet transform coefficients with the highest Fisher ratios. Similarities and differences of this classification algorithm with matching pursuit, a representation algorithm, are discussed. This is done to show the need to treat classification differently than representation for realistic cases where class boundaries significantly overlap. The adaptive classifier is shown to have significantly higher detection rates than Fourier transform and wavelet transform methods, as compared by receiver operating characteristics.

show abstract

Section: Introductionmentioning

confidence: 99%

“…A number of methods have been developed for representing (as opposed to classifying) signals based on adaptively selecting a small number of time-frequency atoms (i.e., regions used as building blocks) [3,4,5,6,7,8,9]. Matching pursuit [9], in particular, embodies attractive properties that carry over to classification.…”

Section: Introductionmentioning

confidence: 99%

<title>Adaptive time-frequency classification of acoustic backscatter</title>

1995

View full text Add to dashboard Cite

show abstract

“…Our approach in this paper is similar to [11] and an extension of Szu et al [6] with the emphasis on adaptive sampling and an application of such a sampling for compression and classification of ECG signals. In short, the significant result of this paper which is different from other previous work is the theoretical proof that the proposed adaptive sampling scheme constitutes a frame and thus the neural network architecture that is used in estimating the wavelet parameters is a numerically stable technique to reconstruct the signal x(t) from the adaptively generated basis functions.…”

Section: Definition 1 the Family ( J ) J ∈J In A Hilbert Space H Is mentioning

confidence: 95%

“…The problem of combining wavelets and neural networks have been considered by other researchers before [9][10][11]6] but these studies did not mention the adaptive sampling concepts. Our approach in this paper is similar to [11] and an extension of Szu et al [6] with the emphasis on adaptive sampling and an application of such a sampling for compression and classification of ECG signals.…”

Section: Definition 1 the Family ( J ) J ∈J In A Hilbert Space H Is mentioning

confidence: 99%

Adaptive wavelets for signal classification and compression

Kadambe

Srinivasan

2006

AEU - International Journal of Electronics and Communications

View full text Add to dashboard Cite

“…Wavelet neural network (WNN) uses wavelet function as node functions and trains its weights, the dilation and the translation. WNN have been in wide use, such as in load forecast [11], function approximation [12][13], system identification [14][15], noise removal [18], etc.…”

Section: Introductionmentioning

confidence: 99%

Image Denoising: An Approach Based on Wavelet Neural Network and Improved Median Filtering

Yao

Guo

2006

2006 6th World Congress on Intelligent Control and Automation

View full text Add to dashboard Cite

Wavelet neural network (WNN) is introduced into the field of digital image denoising due to the excellent local feature and adaptive ability. The procedure of denoising can be looked as an approximating procedure from noisy image to original image. The better WNN has approximation performance, the better denoising performance. Researches have shown that WNN does well in the approximation of nonlinear function and consequently it can be employed in image denoising. In our denoising approach, feature extracting is performed with the help of an improved median filtering, and feature values normalized by exponential function are input into the WNN trained by the classic but efficient gradient descent method (GDM). The feature value is sensitive to the pepper noise in dark background and salt noise in normal background. The experimental results showed that the proposed approach was superior to traditional median filtering in the ability of preserving fine details and excellent fidelity and also indicated the efficiency of the proposed approach in the case of high intensity noise.

show abstract

Approximation by nonlinear wavelet networks

Cited by 14 publications

References 15 publications

<title>Adaptive time-frequency classification of acoustic backscatter</title>

<title>Adaptive time-frequency classification of acoustic backscatter</title>

Adaptive wavelets for signal classification and compression

Image Denoising: An Approach Based on Wavelet Neural Network and Improved Median Filtering

Contact Info

Product

Resources

About