• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2E
• /
• pp.25-29
• /
• 2001

In this paper, we propose a new method for selecting the threshold on wavelet packet denoising. In selecting threshold, the method using median is not efficient. Because this method can not recover unvoiced signal corrupted by noise. So we partition a speech signal corrupted by noise into the pure noise section and voiced section using autocorrelation and entropy. The autocorrelation and entropy can reflect disorder of noise. The new method yields more improved denoising effect. Especially unvoiced signal is very nicely reconstructed, and SNR is improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2310-2332
• /
• 2020

In recent years, deep learning techniques have achieved tremendous successes in natural language processing, speech recognition and image processing. Collaborative filtering(CF) recommendation is one of widely used methods and has significant effects in implementing the new recommendation function, but it also has limitations in dealing with the problem of poor scalability, cold start and data sparsity, etc. Combining the traditional recommendation algorithm with the deep learning model has brought great opportunity for the construction of a new recommender system. In this paper, we propose a novel collaborative recommendation model based on auxiliary stacked denoising autoencoder(ASDAE), the model learns effective the preferences of users from auxiliary information. Firstly, we integrate auxiliary information with rating information. Then, we design a stacked denoising autoencoder based collaborative recommendation model to learn the preferences of users from auxiliary information and rating information. Finally, we conduct comprehensive experiments on three real datasets to compare our proposed model with state-of-the-art methods. Experimental results demonstrate that our proposed model is superior to other recommendation methods.

• Nuclear Engineering and Technology
• /
• v.33 no.5
• /
• pp.483-497
• /
• 2001

In this work, a neuro-fuzzy inference system combined with the wavelet denoising, PCA (principal component analysis) and SPRT (sequential probability ratio test) methods is developed to detect the relevant sensor failure using other sensor signals. The wavelet denoising technique is applied to remove noise components in input signals into the neuro-fuzzy system The PCA is used to reduce the dimension of an input space without losing a significant amount of information. The PCA makes easy the selection of the input signals into the neuro-fuzzy system. Also, a lower dimensional input space usually reduces the time necessary to train a neuro-fuzzy system. The parameters of the neuro-fuzzy inference system which estimates the relevant sensor signal are optimized by a genetic algorithm and a least-squares algorithm. The residuals between the estimated signals and the measured signals are used to detect whether the sensors are failed or not. The SPRT is used in this failure detection algorithm. The proposed sensor-monitoring algorithm was verified through applications to the pressurizer water level and the hot-leg flowrate sensors in pressurized water reactors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.5
• /
• pp.853-860
• /
• 2001

This paper presents the new two denoising methods using wavelet. One is new spatially selective noise filtration(NSSNF) using spatial correlation and the other is undecimated discrete wavelet transform (UDWT) threshold-based. NSSNF got the flexible gain special property of SNR adding new parameter at the existing SSNF and UDWT had superior denosing effect than orthogonal wavelet transform(OWT) applied soft-threshold by applied hard-threshold. We selected additive white gaussian noise(AWGN) in this test environment. Also we analyzed and compared ousting denoising method using SNR as standard of judgement of improvemental effect.

• International Journal of Aeronautical and Space Sciences
• /
• v.12 no.4
• /
• pp.371-378
• /
• 2011

In this paper, the wavelet denoising techniques using thresholding method are applied to the low cost micro electromechanical system (MEMS)-global positioning system(GPS) integrated system. This was done to improve the navigation performance. The low cost MEMS signals can be distorted with conventional pre-filtering method such as low-pass filtering method. However, wavelet denoising techniques using thresholding method do not distort the rapidly-changing signals. They can reduce the signal noise. This paper verified the improvement of the navigation performance compared to the conventional pre-filtering by simulation and experiment.

• Journal of information and communication convergence engineering
• /
• v.5 no.1
• /
• pp.1-6
• /
• 2007

In the process of the acquisition, storage, transmission of signals, noises are generated by various causes and the degradation phenomenon by noises tends to generate serious errors for the signal with information. So, in order to analyze and remove these noises, studies on numerous mathematical methods such as the Fourier transform have been implemented. And recently there have been many ongoing wavelet-based denoising algorithms representing excellent characteristics in time-frequency localization and multiresolution analysis, but the method to remove additive white Gaussian noise (AWGN) and the impulse noise simultaneously was not given. So, to reconstruct the corrupted signal by noises, in this paper a novel wavelet-based denoising algorithm was proposed and using signal-to-noise ratio (SNR) this method was compared to conventional methods.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1242-1245
• /
• 2018

In this paper, we have implemented a network that overcomes the over-blurring phenomenon that occurs when removing Gaussian noise. In the conventional filtering method, blurring of the original image is performed to remove noise, thereby eliminating high frequency components such as edges and corners. We propose a network that reducing over blurring while maintaining denoising performance by adding denoised high frequency components to denoisers based on CNN.

• Proceedings of the KSMRM Conference
• /
• 2005.09a
• /
• pp.69-69
• /
• 2005

• Journal of IKEEE
• /
• v.20 no.2
• /
• pp.136-142
• /
• 2016

This paper presents a non-local means (NLM) denoising algorithm based on a new weighting function using a mixed norm. The fidelity of the difference between an anchor patch and the reference patch in the NLM denoising depends on noise level and local activity. This paper introduces a new weighting function based on a mixed norm type of which the order is determined by noise level and local activity of an anchor patch, so that the performance of the NLM denoising can be enhanced. Experimental results demonstrate the objective and subjective capability of the proposed algorithm. In addition, it was verified that the proposed algorithm can be used to improve the performance of the other $l_2$ norm based non-local means denoising algorithms

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1250-1256
• /
• 2019

Although one can easily generate real-world 3D mesh data using a 3D printer or a depth camera, the generated data inevitably includes unnecessary noise. Therefore, mesh denoising is essential to obtain intact 3D mesh data. However, conventional mathematical denoising methods require preprocessing and often eliminate some important features of the 3D mesh. To address this problem, this paper proposes a deep learning based 3D mesh denoising method. Specifically, we propose a convolution-based autoencoder model consisting of an encoder and a decoder. The convolution operation applied to the mesh data performs denoising considering the relationship between each vertex constituting the mesh data and the surrounding vertices. When the convolution is completed, a sampling operation is performed to improve the learning speed. Experimental results show that the proposed autoencoder model produces faster and higher quality denoised data than the conventional methods.