• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.395-406
• /
• 2017

The purpose of this study is to identify the pattern of daily electricity demand through clustering and classification. The hourly data was collected by KPS (Korea Power Exchange) between 2008 and 2012. The time trend was eliminated for conducting the pattern of daily electricity demand because electricity demand data is times series data. We have considered k-means clustering, Gaussian mixture model clustering, and functional clustering in order to find the optimal clustering method. The classification analysis was conducted to understand the relationship between external factors, day of the week, holiday, and weather. Data was divided into training data and test data. Training data consisted of external factors and clustered number between 2008 and 2011. Test data was daily data of external factors in 2012. Decision tree, random forest, Support vector machine, and Naive Bayes were used. As a result, Gaussian model based clustering and random forest showed the best prediction performance when the number of cluster was 8.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.1
• /
• pp.177-183
• /
• 2010

In continuous vocabulary recognition system by statistical method vocabulary recognition to be performed using probability distribution it also modeling using phoneme clustering for based sample probability parameter presume. When vocabulary search that low recognition rate problem happened in express vocabulary result from presumed probability parameter by not defined phoneme and insert phoneme and it has it's bad points of gaussian model the accuracy unsecure for one clustering modeling. To improve suggested probability distribution mixed gaussian model to optimized for based resemble Euclidean and Bhattacharyya distance measurement method mixed clustering modeling that system modeling for be searching phoneme probability model in clustered model. System performance as a result of represent vocabulary dependence recognition rate of 98.63%, vocabulary independence recognition rate of 97.91%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.5
• /
• pp.1143-1148
• /
• 2014

This paper has analyzed the change of subthreshold swing for doping distribution function of asymmetric double gate(DG) MOSFET. The basic factors to determine the characteristics of DGMOSFET are dimensions of channel, i.e. channel length and channel thickness, and doping distribution function. The doping distributions are determined by ion implantation used for channel doping, and follow Gaussian distribution function. Gaussian function has been used as carrier distribution in solving the Poisson's equation. Since the Gaussian function is exactly not symmetric for top and bottome gates, the subthreshold swings are greatly changed for channel length and thickness, and the voltages of top and bottom gates for asymmetric double gate MOSFET. The deviation of subthreshold swings has been investigated for parameters of Gaussian distribution function such as projected range and standard projected deviation in this paper. As a result, we know the subthreshold swing is greatly changed for doping profiles and bias voltage.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.225-230
• /
• 2012

When a car accident happened, the accident vehicle should broadcast a safe message to its neighbors in multi-hop. However, the pure flooding is difficult to protect a chain-reaction collision because of the frequent collision and the communication delay. To solve this problem, we proposes a back-off algorithm applied to the estimation of the neighbor node count using the t-distribution. And we proposes a MAC protocol preventing the communication delay by separating the neighbor's count collection channel and data channel. As a result, we show the frame reception success rate of our protocol improved more 10% than the previous protocol.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.111-117
• /
• 2007

This paper presents a novel approach to speech enhancement based on a complex Laplacian probability density function (pdf). With a use of goodness-of-fit (GOF) test we show that the complex Laplacian pdf is more suitable to describe the conventional Gaussian pdf. The likelihood ratio (LR) is applied to derive the speech absence probability in the speech enhancement algorithm. The performance of the proposed algorithm is evaluated by the objective test and yields better results compared with the conventional Gaussian pdf-based scheme.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38A no.2
• /
• pp.183-190
• /
• 2013

In this paper, we propose a spatially adaptive noise detection and removal algorithm for a single degraded image. Under the assumption that an observed image is Gaussian-distributed, the noise information is estimated by local statistics of degraded image, and the degree of the additive noise is detected by the local statistics of the estimated noise. In addition, we describe a noise removal method taking a modified Gaussian filter which is adaptively determined by filter parameters and window size. The experimental results demonstrate the capability of the proposed algorithm.

• Korean Journal of Optics and Photonics
• /
• v.32 no.6
• /
• pp.276-285
• /
• 2021

This paper reports the study of the line-beam optical system of the laser lift-off (LLO) equipment used in the OLED manufacturing process. To obtain both a long process depth and a narrow width of the line beam, even with the poor M² value of the laser source, the research is focused on the optical system, including the beam transformation unit (BTU). We also propose optical configurations for the super-Gaussian distribution and the fiber-based BTU for the flat-top distribution.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.27-33
• /
• 2022

In this paper, we propose a novel generator architecture for multi-domain style transfer method not an image to image translation, as a method of generating a styled image by transfering a style to the content image. A latent vector and Gaussian noises are added to the generator of GAN so that a high quality image is generated while considering the characteristics of various data distributions for each domain and preserving the features of the content data. With the generator architecture of the proposed GAN, networks are configured and presented so that the content image can learn the styles for each domain well, and it is applied to the domain composed of images of the four seasons to show the high resolution style transfer results.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.340-345
• /
• 2021

최근 많은 연구들이 BERT를 활용하여, 주어진 문맥에서 언어학/문법적으로 적절하지 않은 단어를 인지하고 찾아내는 성과를 보고하였다. 하지만 일반적으로 딥러닝 관점에서 NLL기법(Negative log-likelihood)은 주어진 문맥에서 언어 변칙에 대한 정확한 성격을 규명하기에는 어려움이 있다고 지적되고 있다. 이러한 한계를 해결하기 위하여, Li et al.(2021)은 트랜스포머 언어모델의 은닉층별 밀도 추정(density estimation)을 통한 가우시안 확률 분포를 활용하는 가우시안 혼합 모델(Gaussian Mixture Model)을 적용하였다. 그들은 트랜스포머 언어모델이 언어 변칙 예문들의 종류에 따라 상이한 메커니즘을 사용하여 처리한다는 점을 보고하였다. 이 선행 연구를 받아들여 본 연구에서는 한국어 기반 언어모델인 KoBERT나 KR-BERT도 과연 한국어의 상이한 유형의 언어 변칙 예문들을 다른 방식으로 처리할 수 있는지를 규명하고자 한다. 이를 위해, 본 연구에서는 한국어 형태통사적 그리고 의미적 변칙 예문들을 구성하였고, 이 예문들을 바탕으로 한국어 기반 모델들의 성능을 놀라움-갭(surprisal gap) 점수를 계산하여 평가하였다. 본 논문에서는 한국어 기반 모델들도 의미적 변칙 예문을 처리할 때보다 형태통사적 변칙 예문을 처리할 때 상대적으로 보다 더 높은 놀라움-갭 점수를 보여주고 있음을 발견하였다. 즉, 상이한 종류의 언어 변칙 예문들을 처리하기 위하여 다른 메커니즘을 활용하고 있음을 보였다.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.147-159
• /
• 2013

In medical visualization, volume visualization is widely used. Applying 3D images to diagnose requires high resolution and accurately implement visualization techniques are being researched accordingly. However, when a three-dimensional image volume visualization is implemented using volume data, aliasing will occur since using discrete data. Supersampling method, getting lots of samples, is used to reduce artifacts. One of the supersampling methods is Catmull-rom spline. This method calculates accurate interpolation value because it is easy to compute and pass through control points. But, Catmull-rom spline method occurs overshoot or undershoot in large gradient of pixel values. So, interpolated values are different from original signal. In this paper, we propose an adaptive adjusting weights interpolation method using Gaussian function. Proposed method shows that overshoot is reduced on the point has a large gradient and PSNR is higher than other interpolated image results.