Gamma spectrum denoising method based on improved wavelet threshold

Xie, Bo; Xiong, Zhangqiang; Wang, Zhijian; Li-jiao, Zhang; Zhang, Dazhou; Li, Fusheng

doi:10.1016/j.net.2020.01.025

Cited by 51 publications

(27 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different kinds of filters, based on the spatial or frequency domains of images, have been proposed in many works for the denoising of visible, infrared, computed tomography and magnetic resonance imaging [ 52 , 53 , 54 , 55 ]. Frequency domain-based filtering tools, also known as transform domain filtering tools [ 53 ], are applicable as digital signal processing tools in both the 1-D and 2-D domains.…”

Section: Methodsmentioning

confidence: 99%

“…DWT depends on a threshold in order to differentiate between signal and noise. Discrete wavelet threshold denoising can be used to perform a multi-scale and multi-resolution analysis on noisy images with small root mean square errors and high signal-to-noise ratios; however, signal oscillations during hard threshold denoising, as well as constant deviations during soft threshold denoising, are inevitable in traditional wavelet threshold denoising methods [ 55 ]. In [ 53 ], the current image denoising methods, based on transform domain filtering, were reviewed and compared.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of Cracking Widths in a Concrete Wall Based on TIR Radiances of Cracking

2020

Sensors

View full text Add to dashboard Cite

The techniques of concrete crack detection, as well as assessments based on thermography coupled with ultrasound, have been presented in many works; however, they have generally needed an additional source of thermal infrared (TIR) radiance and have only been applied in laboratories. Considering the accessibility of thermal infrared cameras, a TIR camera (NEC F30W) was employed to detect cracking in the concrete wall of an historic house with a western architectural style in Kinmen, Taiwan, based on the TIR radiances of cracking. An operation procedure involving a series of image processing and statistical analysis processes was designed to evaluate the performance of the TIR camera in the assessment of the cracking width. This procedure using multiple measurements was implemented from March to August 2019, and the t-tests indicated that the temperature differences between the inside and outline of the concrete cracks remained insignificant as the temperature or relative humidity (RH) in the subtropical climate rose. The experimental results of the operation procedure indicated that the maximum focusing range, which is related to the size of the sensor array, and the minimum detectable crack width of a TIR camera should be 1.0 m and 6.0 mm, respectively, in order to derive a linear regression model with a determination coefficient R2 of 0.733 to estimate the cracking widths, based on the temperature gradients. The validation results showed that there was an approximate R2 value of 0.8 and a total root mean square error of ±2.5 mm between the cracking width estimations and the observations.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Assessment of Cracking Widths in a Concrete Wall Based on TIR Radiances of Cracking

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In fact, in engineering applications, since the analyzed signal is discrete, it is usually necessary to discretize the wavelet transform. The DWT (Discrete Wavelet Transform) can be calculated following ( 16 The basic principle of DWT decomposition is as follows: the original signal is continuously decomposed through high-pass and low-pass filters [17]. First, the original signal is passed through high-pass and low-pass filters to obtain high-frequency components (H1) and low-frequency components (L1).…”

Section: A Wavelet Threshold Denoisingmentioning

confidence: 99%

A Neural-Network-Based Method for Ash Fouling Prediction of Heat Transfer Surface in Coal-Fired Power Plant Boiler

Shi

Cui

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Soot blowing optimization and health management of coal-fired power plant boiler has received increasing attention in recent years. The ash fouling monitoring and prediction are the basis for achieve this goal. Nowadays, with the development of neural network technology, the new data-driven methodologies are provided for ash fouling monitoring and prediction. This paper presents a comprehensive method based on neural-network for ash fouling prediction. Firstly, the health factor-clearness factor of the heated surface was established from the actual heat transfer coefficient and the theoretical heat transfer coefficient. Wavelet threshold denoising algorithm will be used as data preprocessing method. Secondly, use Ensemble Empirical Mode Decomposition (EEMD) to obtain a series of frequency stable parts. Finally, Encoder-Decoder based Attention (EDA) is used to predict the ash deposit on the heat transfer surface. The EDA model consists of an encoder, a decoder and an attention mechanism. The encoder and decoder are composed of BI-LSTM and LSTM respectively. The function of the attention mechanism is that the output of each time step of the encoder is given a different degree of attention, and it is sent to the decoder as an attention vector after a weighted average operation. Ash accumulation data on the heat transfer surface of various devices are used to verify the effectiveness of the proposed hybrid model. In addition, the experimental results show that this method has better prediction accuracy than other variant models.INDEX TERMS Soot blowing optimization, ash fouling prediction, ensemble empirical mode decomposition (EEMD), long short-term memory (LSTM), encoder-decoder based attention (EDA)

show abstract

“…The image degradation concept can be described mathematically as x = y + n, where x is the degraded form of the original image y, and n is the added noise, generally referred as additive white Gaussian noise (AWGN) as shown in Figure 1. Methods of image denoising concentrate on restoring the denoised image y from its cross ponding noisy image x through eliminating or reducing noise n. To date, a denoising method that has given very satisfactory results is that based on first generation [6,7] and second generation wavelets such as curvelets [8,9] or contourlets [10,11]. These methods carry out a multiresolution analysis [12] or multiscale analysis for denoising an additive white and Gaussian noise.…”

Section: Introductionmentioning

confidence: 99%

“…Methods of image denoising concentrate on restoring the denoised image

from its cross ponding noisy image

through eliminating or reducing noise

. To date, a denoising method that has given very satisfactory results is that based on first generation [ 6 , 7 ] and second generation wavelets such as curvelets [ 8 , 9 ] or contourlets [ 10 , 11 ]. These methods carry out a multiresolution analysis [ 12 ] or multiscale analysis for denoising an additive white and Gaussian noise.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Gaussian Denoiser for Multiple-Level Image Denoising

Khan

Jin

Haider

et al. 2021

Sensors

View full text Add to dashboard Cite

Image denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural network-based denoising approaches come across a blurriness issue that produces denoised images blurry on texture details. To resolve the blurriness issue, we first performed a theoretical study of the cause of the problem. Subsequently, we proposed an adversarial Gaussian denoiser network, which uses the generative adversarial network-based adversarial learning process for image denoising tasks. This framework resolves the blurriness problem by encouraging the denoiser network to find the distribution of sharp noise-free images instead of blurry images. Experimental results demonstrate that the proposed framework can effectively resolve the blurriness problem and achieve significant denoising efficiency than the state-of-the-art denoising methods.

show abstract

Gamma spectrum denoising method based on improved wavelet threshold

Cited by 51 publications

References 15 publications

Assessment of Cracking Widths in a Concrete Wall Based on TIR Radiances of Cracking

Assessment of Cracking Widths in a Concrete Wall Based on TIR Radiances of Cracking

A Neural-Network-Based Method for Ash Fouling Prediction of Heat Transfer Surface in Coal-Fired Power Plant Boiler

Adversarial Gaussian Denoiser for Multiple-Level Image Denoising

Contact Info

Product

Resources

About