A 3D convolutional neural network based near-field acoustical holography method with sparse sampling rate on measuring surface

Measurement ◽  
2021 ◽  
Vol 177 ◽  
pp. 109297
Author(s):  
Jiaxuan Wang ◽  
Zhifu Zhang ◽  
Yizhe Huang ◽  
Zhuang Li ◽  
Qibai Huang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Near Field ◽  
Sampling Rate ◽  
Sparse Sampling ◽  
Measuring Surface ◽  
Acoustical Holography

Near-field acoustical holography incorporating compressive sampling: Effect of measurement distance and array density

2020 ◽  
Vol 68 (6) ◽  
pp. 470-489
Author(s):  
Tongyang Shi ◽  
Weimin Thor ◽  
J. Stuart Bolton
Keyword(s):  
Sound Source ◽  
Near Field ◽  
Source Region ◽  
Sampling Rate ◽  
Sound Field ◽  
Compressive Sampling ◽  
Sound Power ◽  
L1 Norm ◽  
Measured Intensity ◽  
Acoustical Holography

To identify sound source locations and strength by using near-field acoustical holography (NAH), many microphones are generally required in order to span the source region and to ensure a sufficiently high spatial sampling rate. It is often the case that hundreds of microphones are needed, so such measurements are costly, which has limited the application of NAH in industrial settings. Recently, however, it has been shown that it is possible to accurately identify concentrated sound sources with a limited number of microphones based on compressive sampling theory. Here, the theory of the four NAH methods that were studied in the present work, that is, statistically optimized near-field acoustical holography (SONAH), wideband acoustical holography (WBH), l1-norm minimization, and a hybrid compressive sampling method, is briefly reviewed. Note that the latter three procedures incorporate elements of compressive sampling. Then, a simulation with one monopole as the sound source was conducted to illustrate some basic characteristics of these algorithms. In the experimental portion of the work, a multi-element loudspeaker was used as the sound source. A near-field intensity scan was conducted to measure both the true intensity spatial distribution and the sound power generated by the loudspeaker to provide a basis against which the values obtained from the holography reconstructions could be compared. The sound field was reconstructed by using both near- and far-field measurements, and the number of microphone measurements used to reconstruct the sound field was systematically decreased by increasing the spacing between microphones. Both in the simulation and experiment, the sound field was reconstructed by using the four NAH methods mentioned above. Then, the reconstruction results were comparedwith the measured intensity results in terms of spatial localization and sound power, and the benefits of the compressive sampling approach are illustrated.

Effect on Measurement of the Radiated Acoustic Field of Underwater Structure Based on NAH with Swinging Measuring Surface

2012 ◽  
Vol 197 ◽  
pp. 778-781
Author(s):  
Lin Na Zhou ◽  
Shao Chun Ding ◽  
Ruo Yu Zhang ◽  
Jing Jun Lou ◽  
Shi Jian Zhu
Keyword(s):  
Sound Pressure ◽  
Power Level ◽  
Near Field ◽  
Sound Intensity ◽  
Sound Power ◽  
Mean Square ◽  
Sound Power Level ◽  
Measuring Surface ◽  
Underwater Structure ◽  
Acoustical Holography

This paper analyzes the effects of the swinging NAH(Near field Acoustical Holography) measuring array on measurement of the sound power level of underwater structure. We use the method of sound intensity integral, the method of mean square sound pressure and the method of NAH reversal pressure to calculate the sound power level under certain collection of frequency with measuring surface in different states. We also analyze the relative error of results acquired by those methods, which can help validating the reliability and the error estimate of the results calculated with NAH.

scholarly journals Enhanced Millimeter-Wave 3-D Imaging via Complex-Valued Fully Convolutional Neural Network

Electronics ◽  
2022 ◽  
Vol 11 (1) ◽  
pp. 147
Author(s):  
Handan Jing ◽  
Shiyong Li ◽  
Ke Miao ◽  
Shuoguang Wang ◽  
Xiaoxi Cui ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Millimeter Wave ◽  
Near Field ◽  
Back Propagation ◽  
Three Dimensional ◽  
Activation Function ◽  
Back Propagation Algorithm ◽  
Parametric Rectified Linear Unit ◽  
Complex Valued

To solve the problems of high computational complexity and unstable image quality inherent in the compressive sensing (CS) method, we propose a complex-valued fully convolutional neural network (CVFCNN)-based method for near-field enhanced millimeter-wave (MMW) three-dimensional (3-D) imaging. A generalized form of the complex parametric rectified linear unit (CPReLU) activation function with independent and learnable parameters is presented to improve the performance of CVFCNN. The CVFCNN structure is designed, and the formulas of the complex-valued back-propagation algorithm are derived in detail, in response to the lack of a machine learning library for a complex-valued neural network (CVNN). Compared with a real-valued fully convolutional neural network (RVFCNN), the proposed CVFCNN offers better performance while needing fewer parameters. In addition, it outperforms the CVFCNN that was used in radar imaging with different activation functions. Numerical simulations and experiments are provided to verify the efficacy of the proposed network, in comparison with state-of-the-art networks and the CS method for enhanced MMW imaging.

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network

Non-Blind Image Deconvolution Based on “Ringing” Removal Using Convolutional Neural Network

2020 ◽  
Vol 2020 (10) ◽  
pp. 181-1-181-7
Author(s):  
Takahiro Kudo ◽  
Takanori Fujisawa ◽  
Takuro Yamaguchi ◽  
Masaaki Ikehara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Architecture ◽  
Large Scale ◽  
Blind Deconvolution ◽  
Training Dataset ◽  
Image Deconvolution ◽  
Classic Problem ◽  
Key Points ◽  
Blind Image

Image deconvolution has been an important issue recently. It has two kinds of approaches: non-blind and blind. Non-blind deconvolution is a classic problem of image deblurring, which assumes that the PSF is known and does not change universally in space. Recently, Convolutional Neural Network (CNN) has been used for non-blind deconvolution. Though CNNs can deal with complex changes for unknown images, some CNN-based conventional methods can only handle small PSFs and does not consider the use of large PSFs in the real world. In this paper we propose a non-blind deconvolution framework based on a CNN that can remove large scale ringing in a deblurred image. Our method has three key points. The first is that our network architecture is able to preserve both large and small features in the image. The second is that the training dataset is created to preserve the details. The third is that we extend the images to minimize the effects of large ringing on the image borders. In our experiments, we used three kinds of large PSFs and were able to observe high-precision results from our method both quantitatively and qualitatively.

Sign in / Sign up

Export Citation Format

Share Document