TEMDnet: A Novel Deep Denoising Network for Transient Electromagnetic Signal With Signal-to-Image Transformation

Chen, Kecheng; Pu, Xiaorong; Ren, Yazhou; Qiu, Hang; Fan, Lin; Zhang, Saimin

doi:10.1109/tgrs.2020.3034752

Cited by 351 publications

(20 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the least-squares generative adversarial network (LSGAN) [ 22 ], the conditional generative adversarial network (CGAN) [ 23 ], and other methods were used to improve the model and achieved a better denoising effect than traditional methods, there are still problems such as slow model convergence. In References [ 9 , 10 , 11 ], the authors transformed the problem of signal denoising into that of image denoising, processed the image with CNN, and achieved good results in the field of seismic signal and transient electromagnetic (TEM) signal denoising. This method will not cause large deviation in amplitude, time, and phase information after signal denoising, but it cannot achieve perfect separation of signal and noise.…”

Section: Related Workmentioning

confidence: 99%

“…A detailed description of the signal noise reduction method based on DL will be discussed later in the second section. Although these works have achieved good results, there are still some drawbacks: (i) The perfect separation of signal and noise cannot be realized [ 9 , 10 , 11 ]; (ii) The existing noise reduction methods based on the generative adversarial network (GAN) [ 12 ] still have the problems of long training time and slow convergence speed in the training process [ 13 , 14 ]; (iii) The requirements for the number of signal sampling points are high. When the number of signal sampling points is too small and the waveform is not obvious, a satisfactory denoising effect cannot be achieved [ 15 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Method of Noise Reduction for Radio Communication Signal Based on RaGAN

Peng

Fang

Fan

et al. 2023

Sensors

View full text Add to dashboard Cite

Radio signals are polluted by noise in the process of channel transmission, which will lead to signal distortion. Noise reduction of radio signals is an effective means to eliminate the impact of noise. Using deep learning (DL) to denoise signals can reduce the dependence on artificial domain knowledge, while traditional signal-processing-based denoising methods often require knowledge of the artificial domain. Aiming at the problem of noise reduction of radio communication signals, a radio communication signal denoising method based on the relativistic average generative adversarial networks (RaGAN) is proposed in this paper. This method combines the bidirectional long short-term memory (Bi-LSTM) model, which is good at processing time-series data with RaGAN, and uses the weighted loss function to construct a noise reduction model suitable for radio communication signals, which realizes the end-to-end denoising of radio signals. The experimental results show that, compared with the existing methods, the proposed algorithm has significantly improved the noise reduction effect. In the case of a low signal-to-noise ratio (SNR), the signal modulation recognition accuracy is improved by about 10% after noise reduction.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Method of Noise Reduction for Radio Communication Signal Based on RaGAN

Peng

Fang

Fan

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…이때, 는 잡음(noise)이 추가된 습득 신호(acquired signal), 는 측정하고자 하는 이상적인 신호, 는 원하지 않지만 측 정되는 잡음이다. 여기서, 시간영역 전자탐사(transient/ time-domain EM, TEM)과 시간영역 유도분극과 같은 탐 사에서의 잡음 제거는 비유일해를 가진 불량조건 문제에서 수치 저하(forward degraded) 과정을 기반으로 진행할 수 있다 (Chen et al, 2020). 즉, 베이지안(Bayesian) 관점에서 사후 확률 분포(posteriori distribution)로서의 해인  는 일 반적으로 최대 사후 확률(maximum a posteriori, MAP) 문 제를 해결함으로써 다음과 같이 계산할 수 있다 (Zhang et al, 2017b;Kataoka and Yasuda, 2019;Delon and Houdard, 2018).…”

Section:     unclassified

“…의 탐사에서 많이 사용되고 있다(Cho, 2006). 이러한 전자 탐사는 전기비저항 탐사와 마찬가지로 전기비저항 구조를 역산하여 해석하므로 앞선 전기비저항 탐사와 유사한 과정 으로 역산을 수행할 때 심층학습을 적용하는 연구가 이뤄 지고 있으며(Kingma and Ba, 2014;Noh et al, 2020;Bang et al, 2021), 현장에서 획득하는 과정에서 발생하는 잡음 을 심층학습을 적용하여 제거하는 연구도 다수 진행되고 있다(Chen et al, 2020;Lin et al, 2019). 이외에도 전자탐 사 역산 결과에 심층학습을 적용하여 암염체의 경계를 해 석 및 예측하는 연구도 진행된 바 있다(Oh et al, 2019;Oh et al, 2020).역산진동수 영역 전자탐사 역산에 심층학습의 적용은 CO 2 포 화도 예측을 위한 수치모형자료에 CNN 방법을 적용한 Puzyrev(2019)에 의해 시작되었고, 이 방법에서는 최적화 방법으로 계산 효율성이 좋고 수렴이 빠른 아담 최적화 (Adam optimization) 알고리듬(Kingma and Ba, 2014)을 사용하였다.…”

unclassified

Research Trends and Case Studies of Deep Learning Applications in Geo-electric and Electromagnetic Surveys

Jeong¹,

Jang

Caesary

et al. 2022

J. Korean Soc. Miner. Energy Resour. Eng.

View full text Add to dashboard Cite

Technological innovations within the context of electrical and electromagnetic (EM) surveys have allowed for a rapid, efficient, and easier acquisition of a high quantity of data. Such innovations have been integral in mineral exploration and groundwater surveys. On the other hand, conventional inversion of electrical or EM survey data is computationally time-consuming and expensive. To circumvent the limitations of conventional inversion, the implementation of deep learning (DL) using improved neural networks has garnered substantial attention. In this study, we review various DL methods that can be used as substitutes for traditional inversion methods. Specifically, we investigate cases highlighting the successful implementation of DL to electrical or EM surveys and also comprehensively examine the advantages and disadvantages of such an application of DL.

show abstract

“…Experiments show that CIPAL is more time-saving than similar architectures. On the other hand, it helps us understand that different types of representations are very important for RSI intelligent understanding [7].…”

Section: Introductionmentioning

confidence: 99%

Remote Sensing Image Water Body Recognition Algorithm Based on Deep Convolution Generating Network and Combined Features

Zhao

Feng

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The application of remote sensing images in water body recognition has become an effective method for ecological environment detection and evaluation, which has the disadvantages of low efficiency due to the existence of interpretation marks and rich interpretation experience in the current water body environment recognition, and overreliance on human experience. In this paper, the water body recognition method is applied to remote sensing images by combining the deep convolution generation network and the combined features, which has the advantage of high recognition accuracy. In the convolutional neural network, a five-layer convolutional neural network is used to construct a remote sensing water information extraction model, the transfer learning idea is introduced, and the densely connected feature fusion structure is added, so as to achieve the purposes of accelerating the convergence speed of the neural network, reducing the requirements of the neural network on the scale of training data, and reducing the loss of spatial hierarchical information and small object information. Compared with SVM, DBN, and CNN models, the experimental results show that the recognition accuracy of the proposed method is as high as 95. 69% under the constraint of scale window, which has a wide range of application scenarios and practical significance.

show abstract

TEMDnet: A Novel Deep Denoising Network for Transient Electromagnetic Signal With Signal-to-Image Transformation

Cited by 351 publications

References 43 publications

A Method of Noise Reduction for Radio Communication Signal Based on RaGAN

A Method of Noise Reduction for Radio Communication Signal Based on RaGAN

Research Trends and Case Studies of Deep Learning Applications in Geo-electric and Electromagnetic Surveys

Remote Sensing Image Water Body Recognition Algorithm Based on Deep Convolution Generating Network and Combined Features

Contact Info

Product

Resources

About