• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.6
• /
• pp.503-511
• /
• 2013

This paper presents a speech enhancement method using non-negative matrix factorization. In training phase, we can obtain each basis matrix from speech and specific noise database. After training phase, the noisy signal is separated from the speech and noise estimate using basis matrix in enhancement phase. In order to improve the performance, we model the change of encoding matrix from training phase to enhancement phase using independent Gaussian distribution models, and then use the constraint of the objective function almost same as that of the above Gaussian models. Also, we perform a smoothing operation to the encoding matrix by taking into account previous value. Last, we apply the Log-Spectral Amplitude type algorithm as gain function.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.143-147
• /
• 2024

Image noise classification is a classical problem in the field of image processing, machine learning, deep learning and computer vision. In this paper, image noise classification is performed using deep learning. Keras deep learning library of TensorFlow is used for this purpose. 6900 images images are selected from the Kaggle database for the classification purpose. Dataset for labeled noisy images of multiple type was generated with the help of Matlab from a dataset of non-noisy images. Labeled dataset comprised of Salt & Pepper, Gaussian and Sinusoidal noise. Different training and tests sets were partitioned to train and test the model for image classification. In deep neural networks CNN (Convolutional Neural Network) is used due to its in-depth and hidden patterns and features learning in the images to be classified. This deep learning of features and patterns in images make CNN outperform the other classical methods in many classification problems.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.2
• /
• pp.772-778
• /
• 2012

In this paper, the states and the parameters in the dynamic system are simultaneously estimated by applying the UKF(Unscented Kalman Filter), which is widely used for estimating the state of non-linear systems. Estimating the parameter is very important in various fields, such as system control, modeling, analysis of performance, and prediction. Most of the dynamic systems which are dealt with in engineering have non-linearity as well as some noise. Therefore, the parameter estimation is difficult. This paper estimates the states and the parameters applying to the UKF, which is a non-linear filter and has strong noise. The augmented equation is used by including the addition of the parameter factors to the original state equation of the system. Moreover, it is simulated by applying to a 2-DOF(Degree of Freedom) dynamic system composed of the pendulum and the slide. The measurement noise of the dynamic equation is assumed to be a Gaussian distribution. As the simulation results show, the proposed parameter estimation performs better than the LSM(Least Square Method). Furthermore, the estimation errors and convergence time are within three percent and 0.1 second, respectively. Consequentially, the UKF is able to estimate the system states and the parameters for the system, despite having measurement data with noise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.7 no.1
• /
• pp.37-45
• /
• 1982

We have analyzed the effect of multipath cochannel interference and Gaussian noise on binary DPSK systems used in land mobile radio communications. Considering multipath channel as non-selective Rayleigh channel, we have found a gnenral equation for bit error rates (BER) deriving the probability density function (p.d.f) of output of phase detector. The numerical results are shown in graphs and discussed as functions of carrier to noise power ratio (CNR), carrier to interferer power ratio (CIR) and correlation of signal component over the pulse length.

• The Journal of Information Technology
• /
• v.2 no.2
• /
• pp.127-138
• /
• 1999

The wavelet transform is widely used in signal processing application. In this paper, a wavelet domain adaptive algorithm(WPTNLMS) is derived and its performances are evaluated in non-stationary environment. Where the input signals are decomposed by the wavelet packet transform for the multi-resolution adaptive processing. And the NLMS is used as an adaptive algorithm in wavelet domain. The proposed technique is applied to noise cancellation of the Doppler signal which is added with white Gaussian noise.

• ETRI Journal
• /
• v.9 no.3
• /
• pp.3-12
• /
• 1987

In this paper, a non-classical autocorrelation detector adopting a newly defined test statistic is introduced to solve the typical problem of detecting a narrowband signal transmitted over an additive white Gaussian noise (AWGN) channel. Error probability analyses are performed for a noncoherent frequency-shift-keying (FSK) system employing the proposed test-statistic. Through the histogram approach, the probability density functions of the test-statistics are plotted to explain the analysis model. All numerical results obtained indicate the limited improvement in error performance under the lower signal-to-noise ratio (SNR) and the use of higher number of samples per bit will finally provide the almost same confident potential of improvement in error rate as the system using matched filters (MFs) gives.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11b
• /
• pp.1078-1082
• /
• 2001

An alternative formulation of the Helmholtz integral equation is derived to express the pressure field explicitly in terms of the velocity vector of a radiating surface. This formulation, derived for arbitrary sources, is similar in form to the Rayleigh's formula for planar sources. Because the pressure field is expressed explicitly as a surface integral of the particle velocity, which can be implemented numerically using standard Gaussian quadratures, there is no need to use Boundary element method to solve a set of simultaneous equations for the surface pressure at the discretized nodes. Furthermore the non-uniqueness problem inherent in methods based on Helmholtz integral equation is avoided. Validation of this formulation is demonstrated for some simple geometries.

• Journal of Advanced Navigation Technology
• /
• v.3 no.2
• /
• pp.97-107
• /
• 1999

Passive sensors such as Laser Range Finder(LRF) and Forward Looking Infrared(FLIR) camera frequently used for tracking aircraft landing produce the measurements of elevation angle contaminated by large noise due to the exhaust plume disturbance. This results in poor tracking performance if the extended Kalman filter is used for estimation of the range and elevation which are corrupted by the non-Gaussian noise such as plume disturbance. In this paper, an adaptive estimation filter and the extended Kalman filter is combined to produce a combination-type filter. In this approach the adaptive filter is used for the plume-type disturbance noise and the extended Kalman filter is utilized for the measurement of Gaussian type. The proposed combination filter is effective for the trajectory estimation of landing aircraft under the influence of unknown bias and numerical simulations illustrate the performance of the proposed filter.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.3
• /
• pp.48-55
• /
• 2001

A novel method to reduce additive non-stationary noise is proposed. The method requires neither the information about noise nor the estimate of the noise statistics from any pause regions. The enhancement is performed on a band-by-band basis for each time frame. Based on both the decision on whether a particular band in a frame is speech or noise dominant and the masking property of the human auditory system, an appropriate amount of noise is reduced using spectral subtraction. The proposed method was tested on various noisy conditions (car noise, Fl6 noise, white Gaussian noise, pink noise, tank noise and babble noise) and on the basis of comparing segmental SNR with spectral subtraction method and visually inspecting the enhanced spectrograms and listening to the enhanced speech, the method was able to effectively reduce various noise while minimizing distortion to speech.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.1001-1004
• /
• 2006

Many researches have been processed to reconstruct corrupted an image by noise in fields of signal processing such as image recognition and compute. vision, and AWGN(additive white gaussian noise) and impulse noise are representative. Impulse noise consists of fired-valued(salt & pepper) impulse noise and random-valued impulse noise, and non-linear filters such as SM(standard median) filters are used to remove this noise. But basic SM filters still generate many errors in edge regions of an image, and in order to overcome this problem a variety of methods have been researched. In this paper, we proposed an impulse noise removal algorithm which is superior to the edge preserving capacity. At this tine, after detecting a noise by using the noise detector, we applied a noise removal algorithm based on the min-max operation and compared the capacity with existing methods through simulation.