• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.4
• /
• pp.357-362
• /
• 2010

This paper proposes the speech and noise recognition system by using a neural network in order to detect the speech and noise sections at each frame. The proposed neural network consists of a layered neural network training by back-propagation algorithm. First, a power spectrum obtained by fast Fourier transform and linear predictive coefficients are used as the input to the neural network for each frame, then the neural network is trained using these power spectrum and linear predictive coefficients. Therefore, the proposed neural network can train using clean speech and noise. The performance of the proposed recognition system was evaluated based on the recognition rate using various speeches and white, printer, road, and car noises. In this experiment, the recognition rates were 92% or more for such speech and noise when training data and evaluation data were the different.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.2021_2022
• /
• 2009

Partial discharges(PD) is a important factor to evaluate the insulation state in high voltage electric machinery. However, measuring PD under the circumstances of power plant is occasionally impossible due to the relatively high magnitude of noise which is emanated from the operating machinery. In some case, the instrument measuring PD can not even perform a calibration that initializes tools and enhance the accuracy. This paper presents that we devised a noise reduction method and demonstrated the usefulness in acquiring reliable PD signals. We attached a series of filter and transformer at the input of power source of the instruments which refrains high noise signals from incoming to the instruments. We experimented the efficiency of noise reduction applying the device into the Dangjin Power Plant and Factory. As a result of testing with the filter and transformer, we can easily calibrate the PD signal compared to the case without the device. Additionally, we can detect the small PD signal which was unperceived with a normal device.

• Journal of KSNVE
• /
• v.5 no.3
• /
• pp.361-371
• /
• 1995

The vibration of reactor internals should be monitored and diagnosed for the early detection of the failure of reactor pressure vessel. This can be performed by analyzing the time-history signals from the excore neutron flux detertors. The conventional method is an on-demand system which generates power spectra through Fast Fourier Transform(FFT) algorithm. The operator can make his own decision to detect abnormal vibration using these spectra. This post- processing method, however, requires special expertise in the reactor noise analysis and signal processing for random data. It may mislead the operator into erroneous decision-making, if he is a novice in reactor noise analysis. Hence this study is focused on the automated monitoring and diagnosis procedure for the reactor noise analysis, especially on the Fuzzy algorithm to recognize the pattern of the vibration of Core Suport Barrel. The excore neutron signals of Yonggwang Nuclear Power Plant unit 3 is acquired and analyzed using conventional FFT spectra and tested to adopt the Fuzzy method. An Automated Monitoring and Diagnosis System for CSB Vibration using this Fuzzy method is proposed. Furthermore, vibration data for CSB of Youggwang Nnclear Power Plant unit 3 is presented.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.3
• /
• pp.85-94
• /
• 2011

Spectrum sensing is one of the most important technologies in cognitive radio. Although many studies have considered energy detection technique as the spectrum sensing technique, noise variance in practical systems is difficult to estimate accurately. Thus, in the real system, the probability of false alarm will not be maintained constant. In this paper, with considering that the cognitive radio does not know the primary user's signal, we propose a new spectrum sensing scheme which can operate without the information of noise variance. Through simulations, we show that the proposed scheme can detect spectrum with the condition of unknown noise information and have robustness for the change of noise variance.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.102-107
• /
• 2019

This paper proposes a method to improve the mass spectral detection performance of the residual gas analyzer. By improving the mode estimation method for setting the threshold value and improving the additive noise elimination method, it is possible to detect mass spectrums having low peak values of the threshold level difficult to distinguish from noise. Ion signal blocks for each mass index with noise removed by the improved method are effective for eliminating invalid ion signals based on the linear and quadratic fittings. The mass spectrum can be obtained from the quadratic fitted curves for the reconstructed ion signal block using only the valid ion signals. In addition, the resolution of the mass spectrum can be improved by correcting the error caused by the shift of the spectral peak position. To verify the performance of the proposed method, computer simulations were performed using real ion signals obtained from the residual gas analysis system under development. The simulation results show that the proposed method is valid.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.111-116
• /
• 2014

Using only laser range finder to detect the obstacles in an environment that contains transparent obstacles can not guarantee autonomous mobile robot from collision problem. To solve this problem, a mobile robot using laser range finder must be used additional sensor device such as sonar sensor that can detect the transparent obstacle. In this paper, a method is addressed to deal with the problem to detect the transparent obstacles within environment only by using laser range finder for mobile robot. In case the recognized transparent obstacle, the proposed algorithm is to localize the transparent obstacle to extract and process the reflected noise. This algorithm ensures autonomous of mobile robot only using laser range finder. The effectiveness of the proposed algorithm is evaluated by the real mobile robot and real laser range finder experiments with three case studies.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.9-15
• /
• 2009

This paper proposes a cancellation algorithm of impulse noise using a rank-order method. The proposed method is a fast and simple algorithm that is composed of two parts. The first part involves noise detection using a fuzzy technique, where an image is divided into RGB color channels. Then every pixel in each color channel is investigated and assigned a probability indicating its chances of being a noise pixel. At this time, the rank order method using a noise-detection mask is utilized for accurate noise detection. Thereafter, the second part involves noise-cancellation, where each noise-pixel value in an image is replaced in proportion to its fuzzy probability. Through the experiments, both the conventional and proposed methods were simulated and compared. As a result, it is shown that proposed method is able to detect noisy pixels more accurately, and produce resulting images with high PSNR values.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.896-902
• /
• 2018

This study examined the flow and noise inside a sirocco fan for ventilation as a commercial program. To confirm only the location and power of the noise source, flow analysis was performed with steady state flow analysis. Through flow analysis, the flow was observed in the sirocco fan and the velocity vector. The pressure distribution inside was observed with contours. From the results of steady analysis, the position and size of the noise source could be seen using the 'Curle surface acoustic power' and 'Proudman acoustic power'. The Curle surface acoustic power can be used to observe the noise from the surface. The Proudman acoustic power can be used to detect noise generated in the flow region because the position and size of the noise source generated inside the sirocco fan can be seen only in the steady state. Therefore it is necessary to further analyze the unsteady state to check the frequency of the noise generated. This study provides basic data for improving the performance of the Sirocco fan and reducing the noise.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.2
• /
• pp.53-58
• /
• 2005

Points of sharp variations in images are the most important components when we analyze singularities of images. And they include a variety of information about the image's location and shape etc. So a lot of researches for detecting those edges have been continuing even now and at the early stage of the research, edge detection operators used relation among neighborhood pixels. However, such methods do not have excellent performance in the image which exists noise and can not detect edge selectively. In the meantime, the wavelet transform which is presented as a new technique of signal processing field is able to detect multiscale edge and is being applied widely in many fields that analyze singularities such as edge. For this reason, in this paper we detected image's line-edge elements with 2-D wavelet function, which is independent of line's width, in mixed noise environment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.7
• /
• pp.1376-1382
• /
• 2016

In this paper, we present a visual quality enhancement technique for conventional three-dimensional (3D) photon counting integral imaging using background noise removal algorithm. Photon counting imaging can detect a few photons from desired objects and visualize them under severely photon-starved conditions such as low light level environment. However, when a lot of photons are generated from background, it is difficult to detect photons from desired objects. Thus, the visual quality of the reconstructed image may be degraded. Therefore, in this paper, we propose a new photon counting imaging method that removes unnecessary background noise and detects photons from only desired objects. In addition, integral imaging can be used to obtain 3D information and visualize the 3D image by statistical estimations such as maximum likelihood estimation. To prove and evaluate our proposed method, we implement the optical experiment and calculate mean square error.