• Journal of Korean Tunnelling and Underground Space Association
• /
• v.5 no.3
• /
• pp.291-299
• /
• 2003

Electrical resistivity prospecting has been recently increased in the application to tunnel, landslide and other investigations in the civil engineering field. Therefore, it is essential to establish the rock mass classification technique using electrical resistivity data. In this paper, the authors, try to propose a technique which can classify tunnel rock mass using seismic wave velocities derived from electrical resistivity data. In addition, the applicability of the proposed tunnel rock mass classification technique is discussed, by comparing estimated support patterns with actually performed ones.

• The KIPS Transactions:PartB
• /
• v.11B no.7 s.96
• /
• pp.849-854
• /
• 2004

This paper proposes an algorithm to enhance the execution time of kNN in the document classification. The proposed algorithm is to enhance the execution time by minimizing the computing cost of the similarity between two documents by using the list of pairs, while the conventional kNN uses the iist of pairs. The 1ist of pairs can be obtained by applying the matrix transposition to the list of pairs at the training phase of the document classification. This paper analyzed the proposed algorithm in the time complexity and compared it with the conventional kNN. And it compared the proposed algorithm with the conventional kNN by using routers-21578 data experimentally. The experimental results show that the proposed algorithm outperforms kNN about $90{\%}$ in terms of the ex-ecution time.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2D
• /
• pp.227-234
• /
• 2009

At present, the length of deceleration lane at freeway diverging areas are designed based on the design speed of main lines and ramps. This is possible on assumption that diverging vehicles decelerate at deceleration section after moving to shoulder lane in advance. But with high diverging volume, several vehicles will try to change to exit lane at the same time. This will cause the distribution of main lane flows or some vehicles may encounter short deceleration length because they miss the proper time to change the lane. The purpose of this study is to establish a design guideline of the length of deceleration section considering the volume of diverging traffic. Also, the results of analysis by the FRESIM simulation model shows that some improvements in respect of delays, speeds and speed deviations of mainline and deceleration lane.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.19-22
• /
• 2019

상완동맥은 어깨에서부터 팔꿈치까지 내려오는 상완골의 내측부에 존재하며 혈압을 측정할 때 사용되는 혈관이다. 이 혈관은 골절로 인해 찢어지거나, 또는 혈액순환에 문제가 생겨 혈관이 막히는 경우가 발생한다. 이러한 경우 혈관의 상태를 확인하기 위하여 색조 도플러 초음파 검사를 사용하지만, 사용자에 따라 영상을 통한 판단 기준이 다르다는 문제점이 발생한다. 따라서 본 논문에서는 FCM과 Fuzzy Decision Tree를 이용한 영상 처리를 통해 일관성 있는 판단기준을 세우기 위한 혈류의 속도를 제안한다. 색조 도플러 초음파 영상에서의 상완 동맥을 추출하여 기울기를 이용한 FCM 알고리즘을 통해 소속도를 추출한 뒤 퍼지 룰에 적용하여 의사 결정 트리로 등급을 분류하고 결과적으로 혈류 속도를 추출한다. 색조 도플러 초음파 영상에서 환자의 개인 정보를 보호하기 위해 개인 정보 영역을 제거하여 ROI 영역을 추출하고 ROI 영역을 이진화를 통하여 상완동맥이 있는 영역을 추출한다. 이진화 된 ROI 영역에서 혈관 영상의 혈류 방향으로의 무게중심을 설정하고 각각의 픽셀과 무게중심 선과의 거리를 이용하여 소속도를 추출한 후 FCM을 사용하여 최적의 기울기를 선정한다. FCM을 통해 추출한 최종 소속도를 이용하여 퍼지 룰에 적용한 뒤 계산된 T-norm과 소속도의 분산을 이용하여 의사 결정 트리를 형성 트리의 단말 노드들은 각 픽셀을 분류한다. 분류되어진 데이터들의 노드별 소속도 평균을 구한 뒤 디퍼지화를 통해 COG(Center of Gravity)를 계산한다. 마지막으로 그 값을 이용하여 혈류 속도에 영향을 미치는 정도를 계산한 뒤 최종 혈류의 속도를 제안한다.

• Explosives and Blasting
• /
• v.21 no.4
• /
• pp.1-10
• /
• 2003

The classification of weak rocks is normally connected with the rippability classifications. The excavation of rock is frequently carried out by blasting. A classification of the weak rocks by test blasting with small quantity of explosives was attempted in the present study. The crater ratio and blasting constant that resoled from test blasting were used as a e parameter of the classification. The seismic velocity of rock mass and Protodyakonov's index were also applied for the also rock classification.

• Journal of Energy Engineering
• /
• v.4 no.3
• /
• pp.394-401
• /
• 1995

본 연구는 중심부에 액체, 외주부에 산화제가 흐르는 기액 동축분류의 유동장에 대한 것이다. 기액 동축 분사기는 연료의 분사량이 적은 소형 연소시스템을 고려하여, 실험은 연공비(W1/Wa)가 0.6 이하를 대상으로, 물과 공기를 사용하여 분사조건에 따른 분무특성과 기액 2상 분무류의 기본구조를 조사하여 액적의 확산, 기액혼합특성에 대하여 검토하여 다음과 같은 결론을 얻었다. 반경방향 기상속도분포 및 액적유속분포는 분구직경 및 분사조건에 관계없이 정규분포에 가까운 형태를 취하고 있으며, 각각 식 (2) 및 (3)으로 나타낼 수 있다. 기상속도는 반치폭은 축방향에 따라 일정한 구배 (≒4.6)로서 증가하며, 기상만의 단상분류의 구배(≒6)에 비해서 완만하다. 액적유속 반치폭은 축방향에 따라 더욱 완만한 구배(≒3.1)로서 증가한다. 무차원 액적유속분포는 축방향에 따라 일정한 구배(n≒1.5)로서 감소한다. 액적의 확산은 상대적으로 기액유량비가 클수록 효과적으라고는 말할 수 없고, 최대 확산을 이루는 최적의 기액유량비가 존재한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.568-570
• /
• 2002

최근, 분류기 쪽에서는 모듈라 학습을 이용한 방법들에 대해서 상당한 관심이 모아지고 있다. 모듈라 학습 방법은 divide and conquer 개념에 바탕을 두고 있기 때문에 복잡한 문제에 대해서 학습 질 측면이나 학습 속도 면에서 단일 분류기에 비해 좋은 결과들을 나타내고 있다. 인공신경망을 이용한 분류 방법 쪽에서도 이러한 연구들이 이루어지고 있다. 본 논문에서는 번호판 인식을 위한 간단한 형태의 모듈라 신경망을 제안하고 이의 성능을 평가하였다. 실험 결과, 일반적인 차량 번호판의 영상에서 성공적인 결과를 보였으며, 잡음에 의한 훼손된 번호판도 좋은 인식 결과를 보였다. 또한 인식률 측면 뿐만 아니라 학습 속도 면에서도 상당한 이득이 있었다.

• Journal of ILASS-Korea
• /
• v.4 no.4
• /
• pp.30-37
• /
• 1999

The breakup characteristics of liquid sheet formed by the liquid rocket injector has a close relation with the combustion efficiency. In this paper, basic characteristics of droplet size and velocity distribution were measured with PDPA for the Like Doublet Impinging Injector. Test variables were the angle of impact, the diameter of orifice and jet velocity. Water was used as test fluid. As a result, for impingement angle less than 90 degree, following correlations were obtained between drop size and design parameters : $D_{32}({\mu}m)=295.0{\times}V^{-0.09}\times(2\theta)^{-0.1}{\times}d^{0.072}$. For impingement angle greater than 100 degree, drop sizes were increased but eventually converged to a certain limiting value.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.498-504
• /
• 2004

This paper presents a new text classifier based on a feature projection technique. In feature projections, training documents are represented as the projections on each feature. A classification process is based on individual feature projections. The final classification is determined by the sum from the individual classification of each feature. In our experiments, the proposed classifier showed high performance. Especially, it have fast execution speed and robustness with noisy data in comparison with k-NN and SVM, which are among the state-of-art text classifiers. Since the algorithm of the proposed classifier is very simple, its implementation and training process can be done very simply. Therefore, it can be a useful classifier in text classification tasks which need fast execution speed, robustness, and high performance.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.1C
• /
• pp.63-74
• /
• 2008

Site response analyses were performed based on equivalent linear technique using the local geologic and dynamic site characteristics, which include soil profiles, shear wave velocity profiles and depth to bedrock for 125 sites collected in Korean Peninsula. From the results of site response analyses, 2-parameters site classification system based on the combination of mean shear wave velocity of soil and depth to bedrock was newly recommended for regions of shallow bedrock depth in Korea. First, as the borders of bedrock depth (H) for site classification were determined as 10m and 20m, the soil sites were divided into 3 classes as $H_1$, $H_2$ and $H_3$ sites. And then, the 3 site classes were subdivided into 7 classes based on the mean shear wave velocity of soil ($V_{s,soil}$). The feasibility of new site classification system was verified and the representative site coefficients ($F_a$ and $F_v$) and design response spectrum were suggested by analyzing uniform trend and dispersion of site coefficients for each site class. The suggested site coefficients and the regression curves present the nonlinear characteristics of soils according to the change of rock outcrop acceleration with uniform trend effectively. From the comparison between the mean values of response spectrum which was acquired from the site response analysis and the suggested design response spectrum, there was a little difference in some of site classes and it was verified to adjust the integration interval to make it more suitable for the site condition in Korea.