• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.407-409
• /
• 2021

Under the influence of the 4th industrial revolution, various technologies such as artificial intelligence and automation are being grafted into industrial sites, and accordingly, the importance of data processing is increasing. Digital images may generate noise due to various reasons, and may affect various systems such as image recognition and classification and object tracking. To compensate for these shortcomings, we propose an image restoration algorithm based on pattern information of non-noise pixels. According to the distribution of non-noise pixels inside the filtering mask, the proposed algorithm switched the filtering process by dividing the interpolation method into a pattern that can be applied, a pattern based on region division, and a randomly arranged pixel pattern. preserves and restores the image. The proposed algorithm showed superior performance compared to the existing impulse noise removal algorithm.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.54 no.3
• /
• pp.166-173
• /
• 2005

Preserving image features, edges and details in the process of impulsive noise filtering is an important problem. To avoid image blurring, only corrupted pixels must be filtered. In this paper, we propose an effective impulse noise detection method using Self-Organizing Neural Network(SONN) which applies median filter selectively for removing random-valued impulse noises while preserving image features, edges and details. Using a $3\times3$ window, we obtain useful local features with which impulse noise patterns are classified. SONN is trained with sample image patterns and each pixel pattern is classified by its local information in the image. The results of the experiments with various images which are the noise range of $5-15\%$ show that our method performs better than other methods which use multiple threshold values for impulse noise detection.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.3
• /
• pp.185-192
• /
• 2004

Vibration table is required to obtain high packing density in expendable pattern casting process. Packing density. which is an important manufacture factor, depends on the vibration pattern induced by vibration table. In general, circular vibration pattern is recognized as the best pattern. The existing vibration table is investigated to identify current vibration pattern and consider a countermeasure. Modal test is utilized to identify the dynamic characteristics of vibration table, and finite element method is used to propose the improved design. In simulation using finite element method, the position of stiffeners is obtained to satisfy the required dynamic characteristics.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.160-165
• /
• 2002

Vibration table is required to obtain high packing density in expendable pattern casting process. Packing density, which is an important manufacture factor, depends on the vibration pattern induced by vibration table. In general, circular vibration pattern is recognized as the best pattern. The existing vibration table is investigated to identify current vibration pattern and consider a countermeasure. Modal test is utilized to identify the dynamic characteristics of vibration table, and finite element method is used to present the improved design.

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.119-124
• /
• 2017

This study investigates how perception of easy sentences varies with prosody pattern, sound intensity, and signal-to-noise ratio(SNR) in young adults with normal hearing who were in their 20's. The results showed that the presence of proper prosody pattern in the sentences increased correct perception rate of the target sentences, and that the lower the intensity and SNR, the lower the sentence perception scores. The results also showed that SNR had a greater effect on the sentence perception scores than sound intensity. There was a significant decrease of perception scores starting at the level of 15 dB and +3 SNR for the sentences with prosody pattern, while starting at the level of 18 dB and +6 SNR for the sentences without prosody pattern, ending up with a very poor perception score as sound intensity and SNR gets lower. There was a significant difference in the perception score of the sentences with prosody pattern between 20 year-old group and 21 year or older group in several listening conditions of sound intensity and SNR.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.24 no.11
• /
• pp.907-918
• /
• 2014

In this study for the prediction of 3D underwater radiated noise pattern, a comparison between the proposed method(DHIE, Discrete Helmholtz Integral Equation) and the 3D underwater radiated noise calculation results using the measurement of near-field acoustic pressure data is performed. The near-field acoustic pressure in water is measured for the calculation of the far-field radiated noise pattern and the far-field acoustic power. Also the vibration field of the underwater structure is measured in simultaneously. Using the total far-field acoustic power and the vibration field on the surface of the structure, the proposed method(DHIE) can predict the underwater radiated noise pattern of the far-field The predicted results show the reasonable agreement within about 5dB comparing with the experiment result.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.11a
• /
• pp.287-290
• /
• 2007

This study examines the characteristics of noise occerred at a hydroelectric power plant by using the on-line partial discharge measured by eletrical detecting method under the high voltage rotating machines. In addition, it analyzes the noise pattern into frequency and its scale component by using the FTT technique.

• ETRI Journal
• /
• v.16 no.1
• /
• pp.35-43
• /
• 1994

In this paper, the robustness of the artificial neural networks to noise is demonstrated with a multilayer perceptron, and the reason of robustness is due to the statistical orthogonality among hidden nodes and its hierarchical information extraction capability. Also, the misclassification probability of a well-trained multilayer perceptron is derived without any linear approximations when the inputs are contaminated with random noises. The misclassification probability for a noisy pattern is shown to be a function of the input pattern, noise variances, the weight matrices, and the nonlinear transformations. The result is verified with a handwritten digit recognition problem, which shows better result than that using linear approximations.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.2
• /
• pp.75-82
• /
• 2015

Noises from the large scale marine propeller are calculated numerically on non-cavitation condition. The hydrodynamic analysis is carried out by potential based panel method with time marching free wake approach. The distribution of hydrodynamic loads on the propeller surface and noise signals are obtained using the unsteady Bernoulli's equation and the Farasssat's formula respectively. It turns out that the noise signal at the narrow band shows strong peak at the blade passage frequency, and the peak value at the 1/3 octave band also shows the same trend. Noise signals and directivity patterns for both the thickness and the loading noise are compared with each other. The directivity pattern for the loading noise shows minor lobe at the backward side of the rotating disc plane.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.35 no.3
• /
• pp.323-327
• /
• 1999

Most of the underwater noise emitted by small fishing boat are owing to vibration of main engine and generator etc.. This paper describe on the spectrum analysis of underwater noise by engine generating in small fishing boat in order to build up comfortable environment for fisheries man and to reduce ambient noise. The obtained results are summerized as follows:1. When the underwater noise of 10ton class fishing boat measure and the frequency spectrum in varied revolution of engine 750, 900, 1000rpm analyze, the frequency pattern is similar to each other, the faster revolution of engine increase, the higher frequency spectrum level becomes. 2. In comparison of spectrum level of underwater noise between 10ton class and 14ton class fishing boat, the former level is higher than the latter. 3. Frequency spectrum pattern of two 14ton class fishing boat is similar to each other but spectrum level is a little difference, it is suggested to different by fitting condition of engine.