• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.1-17
• /
• 2013

In this article, several types of hybrid forecasting models are suggested. In particular, hybrid models using the generalized additive model (GAM) are newly suggested as an alternative to those using neural networks (NN). The prediction performances of various hybrid and non-hybrid models are evaluated using simulated time series data. Five different types of seasonal time series data related to an additive or multiplicative trend are generated over different levels of noise, and applied to the forecasting evaluation. For the simulated data with only seasonality, the autoregressive (AR) model and the hybrid AR-AR model performed equivalently very well. On the other hand, if the time series data employed a trend, the SARIMA model and some hybrid SARIMA models equivalently outperformed the others. In the comparison of GAMs and NNs, regarding the seasonal additive trend data, the SARIMA-GAM evenly performed well across the full range of noise variation, whereas the SARIMA-NN showed good performance only when the noise level was trivial.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.65-74
• /
• 2021

Recently, studies on Korean spelling correction have been actively conducted based on machine translation and automatic noise generation. These methods generate noise and use as train and data set. This has limitation in that it is difficult to accurately measure performance because it is unlikely that noise other than the noise used for learning is included in the test set In addition, there is no practical error type standard, so the type of error used in each study is different, making qualitative analysis difficult. This paper proposes new 'error type classification' for deep learning-based Korean spelling correction research, and error analysis perform on existing commercialized Korean spelling correctors (System A, B, C). As a result of analysis, it was found the three correction systems did not perform well in correcting other error types presented in this paper other than spacing, and hardly recognized errors in word order or tense.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.39-46
• /
• 2019

In this paper, combining features is proposed as a way to enhance the classification accuracy of sounds under noisy environments using the CNN (Convolutional Neural Network) structure. A robust log Mel-filter bank using Wiener filter and PNCCs (Power Normalized Cepstral Coefficients) are extracted to form a 2-dimensional feature that is used as input to the CNN structure. An ebird database is used to classify 43 types of bird species in their natural environment. To evaluate the performance of the combined features under noisy environments, the database is augmented with 3 types of noise under 4 different SNRs (Signal to Noise Ratios) (20 dB, 10 dB, 5 dB, 0 dB). The combined feature is compared to the log Mel-filter bank with and without incorporating the Wiener filter and the PNCCs. The combined feature is shown to outperform the other mentioned features under clean environments with a 1.34 % increase in overall average accuracy. Additionally, the accuracy under noisy environments at the 4 SNR levels is increased by 1.06 % and 0.65 % for shop and schoolyard noise backgrounds, respectively.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.2
• /
• pp.176-184
• /
• 2013

Quantification of road noise is a challenging issue in the development of tire noise since its transfer paths are complicated. In this paper, a simplified model to estimate the road noise is developed. Transfer path of the model is from wheel to interior. The method uses the wheel excitation force estimated throughout inverse method. In inversion procedure, the Tikhonov regularization method is used to reduce the inversion error. To estimate the wheel excitation force, the vibration of knuckle is measured and transfer function between knuckle and wheel center is also measured. The wheel excitation force is estimated by using the measured knuckle vibration and the inversed transfer function. Finally interior noise due to wheel force is estimated by multiplying wheel excitation force in the vibro-acoustic transfer function. This vibro-acoustic transfer function is obtained throughout measurement. The proposed method is validated by using cleat excitation method. Finally, it is applied to the estimation of interior noise of the vehicle with different types of tires during driving test.

• Journal of the Korean GEO-environmental Society
• /
• v.11 no.7
• /
• pp.15-24
• /
• 2010

Noise and vibration due to pile driving cause residents nearby construction sites to file civil complaints and to the extent of bringing construction to a halt. To deal with this issue, construction engineers have worked strenuously to develop several types of low noise & low vibration pile methods. In this study, a new noise and vibration-free precast screw pile method proposed as a low noise & low vibration pile. It penetrates into the ground by rotating and pressing to avert noise and vibration while maximizing bearing capacity. A prototype of noise and vibration-free precast screw pile method was manufactured, which is not seen anywhere in Korea and elsewhere, and have undergone pilot tests twice to determine construction method. Based on this study, features of the noise & vibration-free screw pile method, production of screw concrete pile prototype, two pilot tests and subsequent construction method were determined.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.21 no.5
• /
• pp.30-41
• /
• 2017

Types of noise barrier installed for noise attenuation are largely divided into noise-absorbing format and noise-proofing format. In these days, installation of transparent noise barrier is general trend to solve problems that hinder sunshine and landscape. Some kinds of transparent boards are used to one of components in noise barriers, but in some cases, less transparency and worse pollution due to yellowing phenomena, and severe material deformation are to harm the urban aesthetics Therefore laminated-tempered glass board in that yellowing phenomena does not occur can be replaced as a transparent one to secure those shortcomings. In this paper, the structural safety against train induced vibration and the resistibility to wind load are analyzed for laminated-tempered glass system as a component of noise barrier installed on Metro railway elevated bridges. Also the appropriateness is evaluated through flexural bending performance test, compressive strength test, modulus of elasticity tests, and impact test for the system or the glass material itself. All of these processes are intended to present the deployment of logic to evaluate the adequacy for the system.

• Progress in Superconductivity
• /
• v.11 no.2
• /
• pp.152-157
• /
• 2010

We have fabricated the low noise liquid helium(LHe) dewar with a different shape of thermal shield to apply the 64-channel SQUID(Superconducting Quantum Interference Device) gradiometer. The first shape of thermal shield was made of an aluminum plate with a wide width of 100 mm slit and the other shape was modified with a narrow width of 20 mm slit. The two types of dewars were estimated by comparing the thermal noise and the signal-to-noise ratio(SNR) of magnetocardiography(MCG) using the $1^{st}$ order SQUID gradiometer system cooled each dewar. The white noise was different as a point of the dewar. The noise was increased as close as the edge of dewar, and also increased at the thermal shield with the more wide width slit. The white noise of the dewar with thermal shield of 100 mm slit was 6.5 fT/$Hz^{1/2}$ at the center of dewar and 25 fT/$Hz^{1/2}$ at the edge, and the white noise of the other one was 3.5 - 7 fT/$Hz^{1/2}$. We measured the MCG using 64-channel SQUID gradiometer cooled at each LHe dewar and compared the SNR of MCG signal. The SNR was improved of 10 times at the LHe dewar with a modified thermal shield.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.455-458
• /
• 2008

Former times Information Technology generally has only depended on text or sound, while nowadays information is being moved through a variety of image media. Cell phone, TV and computer have been major elements of modem society as mediators using image signal. Therefore, image signal processing also has been treated importantly and done actively. The processing has been developed in many fields of digital image processing technologies as image data compression, recognition, restoration, etc. Noises are inevitably generated by using the signals during the processing, and typical types of the noise are Impulse(salt & pepper) and AWGN(Addiction White Gaussian Noise). To reduce the noise, various kinds of filters have been developed, and according to each noise, it is being used different filter each. However, the noise is not generated by one signal but by a complex. In this paper, I suggested an image filter to remove the complex noise, and compared with existing filters' methods for verification.

• International Journal of Highway Engineering
• /
• v.14 no.2
• /
• pp.19-28
• /
• 2012

A measuring technique for tire-pavement interaction noise that uses a proposed noble close proximity(NCPX) method, which has been proofed in terms of the reliability and consistency of interaction noise measurement through several researches, equipped with surface microphones has been adopted in order to perform bridge deck pavement noise evaluations on four different pavement surfaces. Through field testing measurement of bridge deck pavement in Seoul inner ring road, the appropriate noise-measuring procedures have been used for evaluating the noise characteristics of four different surfaces. Measuring results show that tire-pavement noise levels vary depending on the surface types and vehicle speeds. Furthermore, the different characteristics of tire-pavement interaction noise can be found before and after the new surface construction of bridge deck pavements in terms of the 1/3 octave band analysis of vehicle speed.

• Journal of Environmental Science International
• /
• v.16 no.7
• /
• pp.771-778
• /
• 2007

This study has been conducted to achieve the following objectives: First, in order to understand the horizontal propagation and attenuation characteristics for the railroad traffic noise, we selected areas within 100 meters away from the railroad and then selected Saemaul-ho and Mugoongwha-ho as the subjects for our experiment. In this way, we analyzed the horizontal propagation and attenuation characteristics for the traffic noise occurring in diversified areas. Second, in order to understand the vertical propagation and attenuation characteristics for the railroad traffic noise, we measured and analyzed the distributional characteristics of vertical sound pressure levels on each floor of multi-storied apartment buildings according to changes of traffic load and types, and the existence or nonexistence of soundproof walls. For the case of the railroad traffic noise, we also selected Samaul-ho and Mugoongwha-ho as the subjects for our experiment, and we measured and analyzed the different noise levels on each floor of multi-storied apartment buildings from the soundproof wall. The results of Horizontal propagation and attenuation characteristics for the railroad traffic noise are as follows: In cases of the flat land, cutting land, and bridge area, as distance increases, the sound pressure level steadily decreases. The sound pressure level for the bridge area is higher than that of the flat land with a measurement of $5.5{\sim}10.2\;dB(A)$. Vertical propagation and attenuation characteristics for the railroad traffic noise are as follows: The amount of sound pressure level decrease is $14.2{\sim}14.8\;dB(A)$ for Samaul-ho and $13.5{\sim}14.3\;dB(A)$ for Mugoongwha-ho when measuring the vertical sound pressure levels at heights lower than 4.5 m, which indicates a fairly large decrease. At 6 m, the amount of decrease is 8.6 dB(A) for Samaul-ho and 8.2 dB(A) for Mugoongwha-ho, which indicates a small decrease.