• 응용통계연구
• /
• 제31권3호
• /
• pp.417-426
• /
• 2018

최근 동물실험의 대체방법 중 하나로 쥐의 줄기세포 유래 배상체를 이용하여 독성을 시험하는 방법이 개발되었다. 이는 동물에 직접 약물을 주입하는 것이 아닌 배상체 세포에 약물을 투입하여 세포의 변화에 따른 측정값들을 얻는 방법이다. 본 연구에서는 다범주 세포독성 자료를 이용해 통계적 기법인 판별분석(discriminant analysis)과 머신러닝 기법인 서포트 벡터 머신(support vector machine), 인공신경망(artificial neural network), k-인접이웃분류(k-nearest neighbor)의 성능을 비교하였다. 알고리즘의 성능은 분류 정확도(accuracy)와 가중카파계수(weighted Cohen's kappa coefficient)로 비교하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권9호
• /
• pp.419-424
• /
• 2016

특허 정보검색에서는 검색 정확도를 높이거나 유사 특허들을 검색하기 위한 목적으로 청구항 등 특허 기술 문서의 내용을 대표하는 개체명 인식이 필요하다. 본 연구에서는 특허 개체명을 자동으로 인식하기 위하여 기계 학습 기법에서 태깅 문제 해결에 매우 우수한 성능을 보이는 조건부 랜덤 필드 기법을 이용하는 특허 개체명 인식 방법을 제안하였다. 개체명 태깅이 되어 있는 특허 문서 말뭉치에서 66만 어절을 학습용 데이터로 사용하여 특허 개체명 시스템을 구축하고, 7만 어절을 평가용 데이터로 사용하여 성능 평가를 하였다. 실험 결과에 의하면 개체명 인식 정확도는 93.6%이고, 개체명 인식 성능을 수작업 태깅 결과와 비교하여 일치도를 평가했을 때 카파 계수는 0.67로 나타났다. 이 카파 계수값은 두 사람의 수작업 태깅 결과에 대한 카파 계수 0.6 보다 높은 것으로 특허 개체명 인식 시스템이 수작업 태깅을 대신하여 실용적으로 활용될 수 있음을 확인하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• Imaging Science in Dentistry
• /
• 제48권2호
• /
• pp.121-125
• /
• 2018

Purpose: Detecting laryngeal cartilages (triticeous and thyroid cartilages) on panoramic radiographs is important because they may be confused with carotid artery calcifications in the bifurcation region, which are a risk factor for stroke. This study assessed the efficiency of panoramic radiography in the diagnosis of calcified laryngeal cartilages using cone-beam computed tomography (CBCT) as the reference standard. Materials and Methods: A total of 312 regions(142 bilateral, 10 left, 18 right) in 170 patients(140 males, 30 females) were examined. Panoramic radiographs were examined by an oral and maxillofacial radiologist with 11 years of experience. CBCT scans were reviewed by 2 other oral and maxillofacial radiologists. The kappa coefficient(${\kappa}$) was calculated to determine the level of intra-observer agreement and to determine the level of agreement between the 2 methods. Diagnostic indicators(sensitivity, specificity, accuracy, and false positive and false negative rates) were also calculated. P values <.05 were considered to indicate statistical significance. Results: Eighty-two images were re-examined to determine the intra-observer agreement level, and the kappa coefficient was calculated as 0.709 (P<.05). Statistically significant and acceptable agreement was found between the panoramic and CBCT images (${\kappa}=0.684$ and P<.05). The sensitivity, specificity, diagnostic accuracy rate, the false positive rate, and the false negative rate of the panoramic radiographs were 85.4%, 83.5%, 84.6%, 16.5%, and 14.6%, respectively. Conclusion: In most cases, calcified laryngeal cartilages could be diagnosed on panoramic radiographs. However, due to variation in the calcifications, diagnosis may be difficult.

• Wind and Structures
• /
• 제16권1호
• /
• pp.47-60
• /
• 2013

A dominant opening in a windward wall, which generates large internal pressures in a building, is a critical structural design criterion. The internal pressure fluctuations are a function of the dominant opening area size, internal volume size and external pressure at the opening. In addition, many buildings have background leakage, which can attenuate internal pressure fluctuations. This study examines internal pressure in buildings for a range of dominant opening areas, internal volume sizes and background porosities. The effects of background porosity are incorporated into the governing equation. The ratio of the background leakage area $A_L$ to dominant opening area $A_W$ is presented in a non-dimensional format through a parameter, ${\phi}_6-A_L/A_W$. Background porosity was found to attenuate the internal pressure fluctuations when ${\phi}_6$ is larger than 0.2. The dominant opening discharge coefficient, ${\kappa}$ was estimated to lie between 0.05 to 0.40 and the effective background porosity discharge coefficient ${\kappa}^{\prime}_L$, was estimated to be between 0.05 to 0.50.

• 한국전산유체공학회:학술대회논문집
• /
• 한국전산유체공학회 2002년도 춘계 학술대회논문집
• /
• pp.79-87
• /
• 2002

The present work analyzed the effect of mixing vane shape on the flow structure and heat transfer downstream of mixing vane in a subchannel of fuel assembly, by obtaining velocity and pressure fields, turbulent intensity, flow-mixing factors, heat transfer coefficient and friction factor using three-dimensional RANS analysis. NJl5, NJ25, NJ35, NJ45, which were designed by the authors, were tested to evaluate the performances in enhancing the heat transfer. Standard $\kappa-\epsilon$ model is used as a turbulence closure model, and, periodic and symmetry conditions are set as boundary conditions. The flow blockage ratio is kept constant, but the twist angle of mixing vane is changed. The results with three turbulence models( $\kappa-\epsilon$, $\kappa-\omega$, RSM) were compared with experimental data.

• 한국해양공학회지
• /
• 제15권3호
• /
• pp.1-8
• /
• 2001

With uniform heat generation within the wall of the cylinder placed in a cross flow, heat flows by conduction in the circumferential direction due to the asymmetric nature of the fluid flow around the perimeter of the cylinder. The circumferential heat flow affects the wall temperature distribution to such an extent that in some cases significantly different results may be obtained for geometrically similar surfaces. In the present investigation, the effects of circumferential wall heat conduction on local convective heat transfer is investigated for the case of forced convection around horizontal cylinder in cross flow of air. Two-dimensional temperature distribution $T_w$/(${\gamma}$,${\theta}$) is presented through the numerical analysis. The one-dimensional and two-dimensional solutions are in good agreement with experimental results of local heat transfer coefficients.

• 한국표면공학회:학술대회논문집
• /
• 한국표면공학회 2018년도 춘계학술대회 논문집
• /
• pp.53-53
• /
• 2018

Thermoelectric materials can convert directly waste heat to electricity and vice versa. The improvement of the thermoelectric efficiency strongly depends on the dimensionless figure of merit, $ZT=S^2{\sigma}T/{\kappa}$, where S is the Seebeck coefficient, ${\sigma}$ is the electrical conductivity, T is the absolute temperature, and ${\kappa}$ is the thermal conductivity. The thermal conductivity consists of the electronic contribution (${\kappa}_e$) and phonon contribution (${\kappa}_{ph}$). It is very challenge to increase the power factor, $S^2{\sigma}$ and to reduce the thermal conductivity simultaneously because the power factor and electronic thermal conductivity are coupled. One strategy is to decrease the phonon thermal conductivity. The phonon thermal conductivity can be decreased by controlling the grain size and structural defects such as dislocations and twinning. In order to achieve enhancements in thermoelectric efficiency, microstructures that can form numerous interfaces have been investigated intensively for controlling the transport of charge carriers and heat carrying phonons. In this presentation, we report the heterogeneous microstructure of $Mg_2Si_{0.6}Sn_{0.4}$ thermoelectric materials and investigation of its influence on thermoelectric properties.

• 한국전산유체공학회지
• /
• 제21권2호
• /
• pp.12-24
• /
• 2016

The standard ${\kappa}-{\varepsilon}$ and realizable ${\kappa}-{\varepsilon}$ models are adopted to improve the prediction performance on the recirculating flow. In this paper, the backward facing step flows are used to assess the prediction performance of the recirculation zone. The model constants of turbulence model are obtained by the experimental results and they have a different value according to the flow. In the case of an isotropic flow situation, decaying of turbulent kinetic energy should follow a power law behavior. In accordance with the power law, the coefficients for the dissipation rate of turbulent kinetic energy are not universal. Also, the other coefficients as well as the dissipation coefficient are not constant. As a result, a suitable coefficients can be varied according to each of the flow. The changes of flow over the backward facing step in accordance with model constants of the ${\kappa}-{\varepsilon}$ models show that the reattachment length is dependent on the growth rate(${\lambda}$) and the ${\kappa}-{\varepsilon}$ models can be improved the prediction performance by changing the model constants about the recirculating flow. In addition, it was investigated for the curvature correction effect of the ${\kappa}-{\varepsilon}$ models in the recirculating flow. Overall, the curvature corrected ${\kappa}-{\varepsilon}$ models showed an excellent prediction performance.

• 대한치과의사협회지
• /
• 제54권11호
• /
• pp.880-896
• /
• 2016

The comparison of the repeated measurements is often needed to see whether they agree sufficiently, when a measurement is repeated under identical conditions by different raters. Such investigations are often analyzed inappropriately, by using correlation coefficient. The purpose of this study is to introduce statistical methods for accessing the agreement of the repeated measurements, which include Bland-Altman plot, intra class correlation, Passing-Bablok regression and Cohen's kappa coefficient, and to show how to execute them using examples.