• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.168-171
• /
• 2005

The present study describes the prediction of the flow induced noise level of a high-speed rotating hexagonal disk and proposes the way how to reduce it. Since a hexagonal disk, which is used in the laser printer and named a polygon mirror, has six sharp comers, there are low and high pressure regions on each of six edges when it rotates. Therefore, the Pressure difference generates three dimension flow field and causes aerodynamic noise. The Ffowcs-Williams and Hawkings(FWH) method is employed for the analysis. We have measured the sound pressure levels and compared them with the computational results. The calculated sound pressure levels agree well with the experimental results. We modified the shape of the edges of a hexagonal disk to reduce the noise level and confirm their effects through numerical computation.

• International Journal of Contents
• /
• v.14 no.4
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• International journal of advanced smart convergence
• /
• v.7 no.4
• /
• pp.40-49
• /
• 2018

We propose a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. We propose detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). The feature vector is applied to LDA and using Euclidean distance of intra-class variance and inter class variance in the 2nd dimension, the final analysis and matching is performed. Experimental results show that the proposed method has a wider distribution when the input image is rotated $45^{\circ}$ left / right. We can improve the recognition rate by applying this feature value to a single algorithm and complex algorithm, and it is possible to recognize in real time because it does not require much calculation amount due to dimensional reduction.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.

• Communications for Statistical Applications and Methods
• /
• v.29 no.1
• /
• pp.41-51
• /
• 2022

We forecast the US oil consumption level taking advantage of google trends. The google trends are the search volumes of the specific search terms that people search on google. We focus on whether proper selection of google trend terms leads to an improvement in forecast performance for oil consumption. As the forecast models, we consider the least absolute shrinkage and selection operator (LASSO) regression and the structured regularization method for large vector autoregressive (VAR-L) model of Nicholson et al. (2017), which select automatically the google trend terms and the lags of the predictors. An out-of-sample forecast comparison reveals that reducing the high dimensional google trend data set to a low-dimensional data set by the LASSO and the VAR-L models produces better forecast performance for oil consumption compared to the frequently-used forecast models such as the autoregressive model, the autoregressive distributed lag model and the vector error correction model.

• Wind and Structures
• /
• v.35 no.4
• /
• pp.287-296
• /
• 2022

Analyzing the typhoon wind hazards is crucial to determine the extreme wind load on engineering structures in the typhoon prone region. In essence, the typhoon hazard analysis is a high-dimensional problem with randomness arising from the typhoon genesis, environmental variables and the boundary layer wind field. This study suggests a dimension reduction approach by decoupling the original typhoon hazard analysis into two stages. At the first stage, the randomness of the typhoon genesis and environmental variables are propagated through the typhoon track model and intensity model into the randomness of the key typhoon parameters. At the second stage, the probability distribution information of the key typhoon parameters, combined with the randomness of the boundary layer wind field, could be used to estimate the extreme wind hazard. The Chinese southeast coastline is taken as an example to demonstrate the adequacy and efficiency of the suggested decoupling approach.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.7
• /
• pp.1030-1037
• /
• 2013

Early detection of anomalies is an important issue in the management of group-housed livestock. In particular, failure to detect oestrus in a timely and accurate way can become a limiting factor in achieving efficient reproductive performance. Although a rich variety of methods has been introduced for the detection of oestrus, a more accurate and practical method is still required. In this paper, we propose an efficient data mining solution for the detection of oestrus, using the sound data of Korean native cows (Bos taurus coreanea). In this method, we extracted the mel frequency cepstrum coefficients from sound data with a feature dimension reduction, and use the support vector data description as an early anomaly detector. Our experimental results show that this method can be used to detect oestrus both economically (even a cheap microphone) and accurately (over 94% accuracy), either as a standalone solution or to complement known methods.

• Journal of the Korean Institute of Navigation
• /
• v.24 no.1
• /
• pp.85-95
• /
• 2000

In the country where the population concentrates in the metropolis with the narrow land, development of the ocean space is necessary. Recently, mega-float offshore structure has been studied as one of the effective utilization of the ocean space. And very large floating structures are now being considered for various applications such as floating airports, offshore cities and so on. This very large structure is relatively flexible compared with real floating structures like large ships. when we estimate dynamic responses of these structures in waves, the elastic deformation is important, because vertical dimension is small compared with horizontal. And it is necessary to examine the effect of ocean wave external force received from the natural environment. In this study, the mat-type large floating structure is made to be analytical model. And the analysis of the dynamic response as it receives regular wave is studied. The finite element method is used in the analysis of structural section of this model. And the analysis is carried out using the boundary element method in the fluid division. The validity of analysis method is verified in comparison with the experimental result in the Japan Ministry of Transport Ship Research Institution. In order to know the characteristics of the dynamic response of the large floating structures, effects of wavelength, bending rigidity of the structure, water depth, and wave direction on dynamic response of the floating structure are studied by use of numerical calculation.

• Smart Structures and Systems
• /
• v.25 no.3
• /
• pp.345-368
• /
• 2020

The present work proposes a self-controlled multi-stage optimization method for damage identification of structures utilizing standard particle swarm optimization (PSO) algorithm. Damage identification problem is formulated as an inverse optimization problem where damage severity in each element of the structure is considered as optimization variables. An efficient objective function is formed using the first few frequencies and mode shapes of the structure. This objective function is minimized by a self-controlled multi-stage strategy to identify and quantify the damage extent of the structural members. In the first stage, standard PSO is utilized to get an initial solution to the problem. Subsequently, the algorithm identifies the most damage-prone elements of the structure using an adaptable threshold value of damage severity. These identified elements are included in the search space of the standard PSO at the next stage. Thus, the algorithm reduces the dimension of the search space and subsequently increases the accuracy of damage prediction with a considerable reduction in computational cost. The efficiency of the proposed method is investigated and compared with available results through three numerical examples considering both with and without noise. The obtained results demonstrate the accuracy of the present method can accurately estimate the location and severity of multi-damage cases in the structural systems with less computational cost.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.142-149
• /
• 2004

It is important to retrieve exact information coinciding with user's need from lots of Usenet news and filter desired information quickly. Differently from email system, we must previously register our interesting news group if we want to get the news information. However, it is not easy for a novice to decide which news group is relevant to his or her interests. In this work, we present a service classifying user preferred news groups among various news groups by the use of Kohonen network. We first extract candidate terms from example documents and then choose a number of representative keywords to be used in Kohonen network from them through fuzzy inference. From the observation of training patterns, we could find the sparsity problem that lots of keywords in training patterns are empty. Thus, a new method to train neural network through reduction of unnecessary dimensions by the statistical coefficient of determination is proposed in this paper. Experimental results show that the proposed method is superior to the method using every dimension in terms of cluster overlap defined by using within cluster distance and between cluster distance.