scholarly journals An ECG Denoising Method Based on the Generative Adversarial Residual Network

2021 ◽  
Vol 2021 ◽  
pp. 1-23
Author(s):  
Bingxin Xu ◽  
Ruixia Liu ◽  
Minglei Shu ◽  
Xiaoyi Shang ◽  
Yinglong Wang
Keyword(s):  
Noise Reduction ◽  
Reduction Process ◽  
Experimental Results ◽  
Depth Information ◽  
Ecg Signal ◽  
Massachusetts Institute Of Technology ◽  
Residual Network ◽  
Denoising Autoencoder ◽  
Generative Adversarial Network ◽  
Ecg Denoising

High-quality and high-fidelity removal of noise in the Electrocardiogram (ECG) signal is of great significance to the auxiliary diagnosis of ECG diseases. In view of the single function of traditional denoising methods and the insufficient performance of signal details after denoising, a new method of ECG denoising based on the combination of the Generative Adversarial Network (GAN) and Residual Network is proposed. The method adopted in this paper is based on the GAN structure, and it restructures the generator and discriminator. In the generator network, residual blocks and Skip-Connecting are used to deepen the network structure and better capture the in-depth information in the ECG signal. In the discriminator network, the ResNet framework is used. In order to optimize the noise reduction process and solve the lack of local relevance considering the global ECG problem, the differential function and overall function of the maximum local difference are added in the loss function in this paper. The experimental results prove that the method used in this article has better performance than the current excellent S-Transform (S-T) algorithm, Wavelet Transform (WT) algorithm, Stacked Denoising Autoencoder (S-DAE) algorithm, and Improved Denoising Autoencoder (I-DAE) algorithm. Experiments show that the Root Mean Square Error (RMSE) of this method in the Massachusetts Institute of Technology and Beth Israel Hospital (MIT-BIH) noise pressure database is 0.0102, and the Signal-to-Noise Ratio (SNR) is 40.8526 dB, which is compared with that of the most advanced experimental methods. Our method improves the SNR by 88.57% on average. Besides the three noise intensities for comparison experiments, additional noise reduction experiments are also performed under four noise intensities in our paper. The experimental results verify the scientific nature of the model, which is that our method can effectively retain the important information conveyed by the original signal.

Metallographic Estimation of the Number of Forming Metallic Particles Obtained during Direct and Indirect Reduction of Metals from Complex Oxides

2019 ◽  
Vol 946 ◽  
pp. 523-527
Author(s):  
Arman S. Bilgenov ◽  
P.A. Gamov ◽  
V.E. Roshchin
Keyword(s):  
Metal Forming ◽  
Solid Phase ◽  
Quantitative Estimation ◽  
Direct Reduction ◽  
Reduction Process ◽  
Complex Oxide ◽  
Experimental Results ◽  
Solid Carbon ◽  
Indirect Reduction ◽  
Co Gas

The direct reduction of metals from a complex oxide with low iron content by solid carbon and indirect reduction by CO gas were studied in a vertical laboratory resistance furnace at 1300 °C for an hour reduction time. The experimental results were described from the point of view of the electrochemical nature of the metal reduction process, that involves the interaction of ions and electrons in the oxide lattice. The technique was developed by using the two different software programs for the quantitative estimation of the areas, average size and number of the metal forming in a complex oxide with extensive fields of vision. The obtained results of the quantitative characteristics of the metal forming during solid-phase carbo-thermal reduction were presented. The processes of reduction by solid carbon and CO gas based on the areas occupied by metal particles were quantitatively compared. The experimental results and the prospects for further experimental work were assessed and outlined.

scholarly journals PCDRN: Progressive Cascade Deep Residual Network for Pansharpening

2020 ◽  
Vol 12 (4) ◽  
pp. 676 ◽  
Author(s):  
Yong Yang ◽  
Wei Tu ◽  
Shuying Huang ◽  
Hangyuan Lu
Keyword(s):  
High Resolution ◽  
Loss Function ◽  
High Frequency ◽  
Experimental Results ◽  
Superior Performance ◽  
Residual Network ◽  
High Quality ◽  
Convolution Approach ◽  
Visual Assessments ◽  
Coarse To Fine

Pansharpening is the process of fusing a low-resolution multispectral (LRMS) image with a high-resolution panchromatic (PAN) image. In the process of pansharpening, the LRMS image is often directly upsampled by a scale of 4, which may result in the loss of high-frequency details in the fused high-resolution multispectral (HRMS) image. To solve this problem, we put forward a novel progressive cascade deep residual network (PCDRN) with two residual subnetworks for pansharpening. The network adjusts the size of an MS image to the size of a PAN image twice and gradually fuses the LRMS image with the PAN image in a coarse-to-fine manner. To prevent an overly-smooth phenomenon and achieve high-quality fusion results, a multitask loss function is defined to train our network. Furthermore, to eliminate checkerboard artifacts in the fusion results, we employ a resize-convolution approach instead of transposed convolution for upsampling LRMS images. Experimental results on the Pléiades and WorldView-3 datasets prove that PCDRN exhibits superior performance compared to other popular pansharpening methods in terms of quantitative and visual assessments.

Technique for Removing Unnecessary Superimposed Patterns from Image using Generative Network

2021 ◽  
Author(s):  
Kazutake Uehira ◽  
Hiroshi Unno
Keyword(s):  
Color Image ◽  
Depth Map ◽  
Experimental Results ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Blue Component ◽  
Component Image

A technique for removing unnecessary patterns from captured images by using a generative network is studied. The patterns, composed of lines and spaces, are superimposed onto a blue component image of RGB color image when the image is captured for the purpose of acquiring a depth map. The superimposed patterns become unnecessary after the depth map is acquired. We tried to remove these unnecessary patterns by using a generative adversarial network (GAN) and an auto encoder (AE). The experimental results show that the patterns can be removed by using a GAN and AE to the point of being invisible. They also show that the performance of GAN is much higher than that of AE and that its PSNR and SSIM were over 45 and about 0.99, respectively. From the results, we demonstrate the effectiveness of the technique with a GAN.

scholarly journals Development and Evaluation of Light-Weight Active Noise Cancellation Earphones

2018 ◽  
Vol 8 (7) ◽  
pp. 1178 ◽  
Author(s):  
Sen Kuo ◽  
Yi-Rou Chen ◽  
Cheng-Yuan Chang ◽  
Chien-Wen Lai
Keyword(s):  
Noise Reduction ◽  
Real Time ◽  
Random Noise ◽  
Active Noise Control ◽  
Noise Cancellation ◽  
Experimental Results ◽  
Path Model ◽  
Light Weight ◽  
Active Noise ◽  
Natural Sound

This paper presents the development of active noise control (ANC) for light-weight earphones, and proposes using music or natural sound to estimate the critical secondary path model instead of extra random noise. Three types of light-weight ANC earphones including in-ear, earbud, and clip phones are developed. Real-time experiments are conducted to evaluate their performance using the built-in microphone inside KEMAR’s ear and to compare with commercially-available ANC headphones and earphones. Experimental results show that the developed light-weight ANC earphones achieve higher noise reduction than the commercial ANC headphones and earphones, and the in-ear ANC earphone has the best noise reduction performance.

scholarly journals Recovery of Iron, Chromium, and Nickel from Pickling Sludge Using Smelting Reduction

Metals ◽  
2018 ◽  
Vol 8 (11) ◽  
pp. 936 ◽  
Author(s):  
Zhaohui Tang ◽  
Xueyong Ding ◽  
Xinlin Yan ◽  
Yue Dong ◽  
Chenghong Liu
Keyword(s):  
Reduction Process ◽  
Slag Basicity ◽  
Experimental Results ◽  
Iron Ores ◽  
Reduction Temperature ◽  
Smelting Reduction ◽  
Reduction Time ◽  
Temperature Reduction ◽  
Pickling Sludge ◽  
Iron Chromium

This paper reports the recoveries of iron, chromium, and nickel from pickling sludge using coal-based smelting reduction. The influences of slag basicity (CaO/SiO2, which is controlled by high phosphorus oolitic hematite iron ores), reduction temperature, reduction time, and the C/O mole ratio on the recoveries of Fe, Cr, and Ni are investigated systematically. The experimental results show that high recoveries of Fe (98.91%), Cr (98.46%), and Ni (99.44%) are produced from pickling sludge with optimized parameters for the smelting reduction process. The optimized parameters are a slag basicity of 1.5; a reduction temperature of 1550 °C, a reduction time of 90 min, and a C/O mole ratio of 2.0. These parameters can be used as technical support for the recycling of pickling sludge with pyrometallurgy.

scholarly journals Deep Residual Network with Sparse Feedback for Image Restoration

2018 ◽  
Vol 8 (12) ◽  
pp. 2417 ◽  
Author(s):  
Zhenyu Guo ◽  
Yujuan Sun ◽  
Muwei Jian ◽  
Xiaofeng Zhang
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
Deep Neural Network ◽  
Convergence Speed ◽  
Fast Convergence ◽  
Experimental Results ◽  
Residual Network ◽  
Unknown Parameters ◽  
Noisy Images ◽  
Blurred Images

A deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are added in the middle and the last layers, which are called FbResNet. FbResNet has fast convergence speed and effective denoising performance. In addition, it can also reduce the artificial Mosaic trace at the seam of patches, and visually pleasant output results can be produced from the blurred images or noisy images. Experimental results show the effectiveness of our designed model and method.

Friction Reduction Due to Lubrication Oil Changes in a Lean-Burn 4-Stroke Natural Gas Engine: Experimental Results

2007 ◽  
Author(s):  
Kris Quillen ◽  
Rudolph H. Stanglmaier ◽  
Victor Wong ◽  
Ed Reinbold ◽  
Rick Donahue ◽  
...  
Keyword(s):  
Natural Gas ◽  
Department Of Energy ◽  
Experimental Results ◽  
Friction Reduction ◽  
Massachusetts Institute Of Technology ◽  
Test Bed ◽  
Computational Tools ◽  
Gas Engine ◽  
Natural Gas Engine ◽  
Lubrication Oil

A project to reduce frictional losses from natural gas engines is currently being carried out by a collaborative team from Waukesha Engine Dresser, Massachusetts Institute of Technology (MIT), Colorado State University (CSU), and ExxonMobil. This project is part of the Advanced Reciprocating Engine System (ARES) program led by the US Department of Energy. Changes in lubrication oil have been identified as a way to potentially help meet the ARES goal of developing a natural gas engine with 50% brake thermal efficiency. Previous papers have discussed the computational tools used to evaluate piston-ring/cylinder friction and described the effects of changing various lubrication oil parameters on engine friction. These computational tools were used to predict the effects of changing lubrication oil of a Waukesha VGF 18-liter engine, and this paper presents the experimental results obtained on the engine test bed. Measured reductions in friction mean effective pressure (FMEP) were observed with lower viscosity lubrication oils. Test oil LEF-H (20W) resulted in a ∼ 1.9% improvement in mechanical efficiency (ηmech) and a ∼ 16.5% reduction in FMEP vs. a commercial reference 40W oil. This improvement is a significant step in reaching the ARES goals.

Sign in / Sign up

Export Citation Format

Share Document