• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.576-583
• /
• 2020

This paper proposes a technique to determine the spam comments on YouTube, which have recently seen tremendous growth. On YouTube, the spammers appeared to promote their channels or videos in popular videos or leave comments unrelated to the video, as it is possible to monetize through advertising. YouTube is running and operating its own spam blocking system, but still has failed to block them properly and efficiently. Therefore, we examined related studies on YouTube spam comment screening and conducted classification experiments with six different machine learning techniques (Decision tree, Logistic regression, Bernoulli Naive Bayes, Random Forest, Support vector machine with linear kernel, Support vector machine with Gaussian kernel) and ensemble model combining these techniques in the comment data from popular music videos - Psy, Katy Perry, LMFAO, Eminem and Shakira.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.471-475
• /
• 2004

LiDAR의 표고점 데이터에서 건물, 수목 등과 같이 주위보다 높은 고도 값을 가지는 대상물을 제거하여 DEM을 생성하기 위한 여러 가지 필터링 기법들이 개발되고 있으며 대표적인 필터링 방법으로는 분산을 이용한 linear prediction 기법, 주변 점들과의 경사관계를 이용한 slope-based 기법, morphology 필터, dual rank 필터 등이 있다. 이러한 기법들은 커널(kernel)의 크기를 대상 지역에 맞도록 사용자가 직접 지정해주어야 하고, 건물의 크기가 다양한 지역에 적용하기 위해서는 가변 크기(variable size)의 커널을 필요로 한다. 본 연구에서는 다양한 크기의 건물이 존재하는 지역에 대하여 커널의 크기를 변화시키지 않고 필터링을 수행하는 새로운 커널 연산 기법을 제안하였다. 또한 기존 필터링 기법에서는 커널에 의해 갱신된 연산값이 다음 연산에 반영되지 않으나 본 연구에서는 갱신된 값이 바로 다음 연산에 반영되도록 하였다. 건물과 수목 등을 제거하기 위하여 주변 화소와의 높이 차를 이용하였으며 대상물이 제거된 부분은 주변 화소를 이용하여 보간하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.161-164
• /
• 1996

The authors have recently proposed a new method for identifying Volterra kernels of nonlinear control systems by use of M-sequence and correlation technique. A specially chosen M-sequence is added to the nonlinear system to be identified, and the crosscorrelation function between the input and output is calculated. Then every crosssection of Volterra kernels up to 3rd order appears at a specified delay time point in the crosscorrelation. This method is applied to a saturation-type nonlinear feedback control system of mechanical-electrical servo system having torque saturation nonlinearity. Simulation experiments show that we can obtain Volterra kernels of saturation-type nonlinear system, and a good agreement is observed between the observed output and the calculated one from the measured Volterra kernels.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1443-1448
• /
• 2003

Model Predictive Control (MPC) has recently found wide acceptance in industrial applications, but its potential has been much impounded by linear models due to the lack of a similarly accepted nonlinear modelling or data based technique. The authors have recently developed a new method for obtaining Volterra kernels of up to third order by use of pseudorandom M-sequence. By use of this method, nonparametric NMPC is derived in discrete-time using multi-dimensional convolution between plant data and Volterra kernel measurements. This approach is applied to an industrial polymerisation process using Volterra kernels of up to the third order. Results show that the nonparametric approach is very efficient and effective and considerably outperforms existing methods, while retaining the original data-based spirit and characteristics of linear MPC.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.335-338
• /
• 2005

In this paper, we proposed a new MCTF (Motion Compensated Temporal Filtering) technique and its hardware (H/W) architecture for SVC (Scalable Video Coding). Since the proposed MCTF Kernel has a extensible architecture, it executes temporal filtering using (5,3) and (3,1) lifting operation. Also it has the same output data rate as the input, and it can continuously produce filtered frames after some latency time. Since the proposed architecture has simpler architecture than previous ones, it is easily mapped into H/W and has optimized memory usage rate and low cost.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.849-852
• /
• 2005

A factorization is an extremely important part of multi-level logic synthesis. The number of literals in a factored from is a good estimate of the complexity of a logic function, and can be translated directly into the number of transistors required for implementation. Factored forms are described as either algebraic or Boolean, according to the trade-off between run-time and optimization. A Boolean factored form contains fewer number of literals than an algebraic factored form. In this paper, we present a new method for a Boolean factorization. The key idea is to identify two-cube Boolean subexpression pairs from given expression. Experimental results on various benchmark circuits show the improvements in literal counts over the algebraic factorization based on Brayton's co-kernel cube matrix.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.108-116
• /
• 2018

In this paper, we propose an image enhancement method based on Multi-Scale Retinex theory that designs Unsharp Masking Filter (UMF) and emphasizes the contrast ratio adaptively. Unsharp Masking (UM) technique emphasizes image sharpness and improves contrast ratio by adding high frequency component to the original image. The high frequency component is obtained by differentiating between original image and low frequency image. In this paper, we present how to design an UMF kernel and to adaptively apply it to increase the contrast ratio according to multi-scale retinex theory which resembles human visual system. Experimental results show that the proposed method has better quantitative performance indexes such as PSNR, ambe & SSIM and better qualitative feature like halo artifact suppression.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.6 no.4
• /
• pp.89-99
• /
• 2003

Smoothed particle hydrodynamics, SPH, is a gridless Lagrangian technique which is a useful alternative numerical analysis method to simulate high velocity deformation problems as well as astrophysical and cosmological problems. The SPH method brings about some difficulties such as tensile Instability and stress oscillation. A new SPH method, so called normalized algorithm, was introduced to overcome these difficulties. In this paper we aimed to estimate this method and have developed an one-dimensional normalized SPH program. The high velocity impact model of an aluminum bar has been analysed by using the developed program and a commercial hydrocode, LS-DYNA. The obtained numerical results showed good agreement with the results of the same model in reference. The program also showed more stable results than those of LS-DYNA in stress oscillation. We hopefully expect that the developed one-dimensional normalized SPH program can be used to solve hydrodynamic problems especially for explosive detonation analysis.

• Journal of Mechanical Science and Technology
• /
• v.15 no.10
• /
• pp.1386-1397
• /
• 2001

In this paper, the plane elasticity equations are used to investigate the in-plane normal (mode I) and shear (mode II) behavior of a crack perpendicular to and terminating at the interface in bonded media with a graded interfacial zone. The interfacial Bone is treated as a nonhomogeneous interlayer with the continuously varying elastic modulus between the two dissimilar, homogeneous semi-infinite constituents. For each of the individual loading modes, based on the Fourier integral transform technique, a singular integral equation with a Cauchy kernel is derived in a separate but parallel manner. In the numerical results, the values of corresponding modes of stress intensity factors are illustrated for various combinations of material and geometric parameters of the bonded media in conjunction with the effect of the material nonhomogeneity within the graded interfacial zone.

• Journal of the Korea Computer Industry Society
• /
• v.7 no.4
• /
• pp.293-298
• /
• 2006

A factorization is an extremely important part of multi-level logic synthesis. The number of literals in a factored form is a good estimate of the complexity of a logic function, and can be translated directly into the number of transistors required for implementation. Factored forms are described as either algebraic or Boolean, according to the trade-off between run-time and optimization. A Boolean factored form contains fewer number of literals than an algebraic factored form. In this paper, we present a new method for a Boolean factorization. The key idea is to identify two-cube Boolean subexpression pairs from given expression. Experimental results on various benchmark circuits show the improvements in literal counts over the algebraic factorization based on Bryton's co-kernel cube matrix.