• 한국지능시스템학회논문지
• /
• 제24권6호
• /
• pp.622-627
• /
• 2014

본 논문은 웨이블릿 변환과 선형 판별 분석법 그리고 유전알고리즘을 이용하여 걸음걸이 인식률을 향상시키는 방법을 제안한다. 걸음걸이 에너지 영상에서 웨이블릿 변환으로 분해된 4개의 대역을 얻는다. 분해된 대역을 선형 판별 분석법으로 영상의 특징을 추출한다. 추출된 4개 대역의 특징들과 학습영상의 특징들 사이의 유클리디안 거리를 계산하고, 각 대역에서 계산된 거리 값에 유전알고리즘으로 최적화된 4개의 가중치를 부여한다. 4개 대역의 거리 값과 가중치와의 선형결합으로 계산된 새로운 거리 값을 바탕으로 최근접 이웃 분류 방법을 이용하여 인식 실험을 수행한다. 실험 결과에서 가중치 융합 전 인식률 보다 융합 후 인식률이 더 높은 것을 확인 할 수 있다.

• 한국정보통신학회논문지
• /
• 제18권6호
• /
• pp.1294-1301
• /
• 2014

본 논문에서는 화자 인식의 성능을 개선하기 위해서 유성음 및 무성음에 대한 별도의 확률분포 모델링을 사용하였다. 또한, 종래의 멜-주파수 캡스트럼 계수 이외에 유성음 구간에서 추가적으로 왜도, 첨도, 하모닉 대 잡음비 등을 추출하여 활용하였다. 화자 인식을 위한 스코어는 유성음 및 무성음 확률분포 모델에서 각각 구해지는데 전수 조사방식에 의해서 최적의 스코어 결합 가중치가 결정되었다. 제안된 방식의 화자인식기의 성능은 종래의 멜-주파수 캡스트럼 계수 및 화자당 하나의 혼합 가우시안 기반 확률분포 모델링을 사용한 방식과 비교되었으며 실험 결과 제안된 방식이 가우시안 혼합의 수가 낮아질수록 더 큰 성능 향상을 얻음을 알 수 있었다.

• 디지털콘텐츠학회 논문지
• /
• 제11권4호
• /
• pp.597-606
• /
• 2010

본 논문에서는 증강현실 환경에서 보다 강건한 카메라 정보 추정을 위한 입자필터 기반의 카메라 추적 기법에 대해서 설명한다. 실시간 카메라 추적을 위해서는 일반적으로 칼만 필터, 또는 확장 칼만 필터 등이 많이 이용되지만, 카메라의 급격한 흔들림 및 장면의 가려짐 등과 같은 불안정한 조건에서는 정상적인 카메라 추적이 매우 힘들다는 단점이 있다. 본 논문에서 제안하는 입자필터링 기법은 시스템 상태에 대한 측정 표본입자의 가중치를 별도의 가중치 계산과정을 이용하지 않고 가우스 분포를 기반으로 계산하였으며, 카메라 입자를 수렴시키기 위한 별도의 처리과정을 거치지 않고 시스템의 실제 불확실도에 근사화되도록 재표본화된 표본입자 집합을 이용하여 카메라 상태의 추정을 수행하였다. 또한 제안된 방법은 보다 많은 수의 표본 입자를 이용하는 환경에서도 실시간 처리가 가능한 장점이 있다. 실험을 통하여 다양한 환경 하에서 제안된 방법의 효율성과 정확성을 확인하였다.

• 산업경영시스템학회지
• /
• 제38권3호
• /
• pp.56-63
• /
• 2015

Several fields of science have demanded large-scale workflow support, which requires thousands of CPU cores or more. In order to support such large-scale scientific workflows, high capacity parallel systems such as supercomputers are widely used. In order to increase the utilization of these systems, most schedulers use backfilling policy: Small jobs are moved ahead to fill in holes in the schedule when large jobs do not delay. Since an estimate of the runtime is necessary for backfilling, most parallel systems use user's estimated runtime. However, it is found to be extremely inaccurate because users overestimate their jobs. Therefore, in this paper, we propose a novel system for the runtime prediction based on workload-aware clustering with the goal of improving prediction performance. The proposed method for runtime prediction of parallel applications consists of three main phases. First, a feature selection based on factor analysis is performed to identify important input features. Then, it performs a clustering analysis of history data based on self-organizing map which is followed by hierarchical clustering for finding the clustering boundaries from the weight vectors. Finally, prediction models are constructed using support vector regression with the clustered workload data. Multiple prediction models for each clustered data pattern can reduce the error rate compared with a single model for the whole data pattern. In the experiments, we use workload logs on parallel systems (i.e., iPSC, LANL-CM5, SDSC-Par95, SDSC-Par96, and CTC-SP2) to evaluate the effectiveness of our approach. Comparing with other techniques, experimental results show that the proposed method improves the accuracy up to 69.08%.

• 대한기관식도과학회지
• /
• 제6권1호
• /
• pp.102-107
• /
• 2000

Monocytoid B-cell lymphoma is uncommon, low grade lymphoma originating from monocytoid B lymphocytes. Monocytoid B-cell lymphoma usually presents as a localized lymphadenopathy. Peripheral lymph nodes are most often involved, particularly those in the frequent in the head and neck area. A distinctive feature is the association of monocytoid B-cell lymphoma with autoimmune diseases. Sjogren Syndrome had been present in 22% of patient with monocytoid lymphoma. Extranodal involvement by monocytoid lymphoma was reported in the salivary gland, breast, thyroid, and stomach. There were also occasional extensions to the liver and retroperitoneum. The bone marrow and peripheral blood involvement by monocytoid lymphoma is very rare, which is frequently seen in hairly cell leukemia. Fever, weight loss, and other constitutional signs are usually absent. Most patients have no symptoms, and the only sign is enlarged lymph nodes. The clinical course remains indolent; most patients are in complete remission and recurrence with progression to a high-grade lymphoma of large cell type was recorded only in a few cases. Authors experienced a case of monocytoid B-cell lymphoma associated with Sjogren Syndrome mistaken to simple cervical lymphadenitis in a 60-year-old female. We report this case with a review of literatures.

• 한국농촌건축학회논문집
• /
• 제10권1호
• /
• pp.101-109
• /
• 2008

It is very hard to find out Tongbanga-millhouse installed nearby a streamlet to use water with Tongbanga(a kind of water-mill) to polish cereals by pounding like a visage of its old days. It plays an important part in folkloric, architectural and educational aspects. The purpose of this study is to analyse the architectural features of Tongbanga and millhouse itself so that to find the way how to build and fabricate the materials and frame members. Therefore this study has been focused on the composition principle and fabrication method of Tongbanga-millhouse on the side of architecture. The fabrication methods of its house in accordance with regular sequences are as follows. ${\cdot}$ Firstly the decision of location of Tongbanga-millhouse and Hwak(a big mortar made of stone). ${\cdot}$ Slantly three rafter installation at an angle of $50^{\circ}$ to err on the safe side and then slantly fifteen rafter installation making a circular cone shape. ${\cdot}$ Installation of twigs to be circles from bottom to top. ${\cdot}$ Manifoldly covering of trunks peeling the barks from flax plants. ${\cdot}$ Threefoldly thatching with upside barks of oak trees. ${\cdot}$ Placing woods alike rafter on the bark thatches as a weight not to fly away by wind. ${\cdot}$ Binding woods alike rafter with vines of arrowroots to maintain the proper place. The decayed Tongbanga-millhouse by means of upper ways was restored out of all recognition.

• 한국통신학회논문지
• /
• 제37권5A호
• /
• pp.375-387
• /
• 2012

본 연구에서는 움직이는 CCD 카메라로부터 입력된 영상에서 색상 및 질감 성분을 기반으로 하는 파티클 필터를 이용하여 실시간으로 객체를 추적할 수 있는 알고리즘을 제안한다. 초기 영상에서 추적하고자 하는 객체를 선택하면 이를 타깃 파티클로 결정하고, 타깃 파티클로 부터 추적을 위한 초기 상태가 모델링 된다. 이후 프레임부터 N개의 파티클들이 랜덤 분포로 생성되고 각 파티클로 부터 질감 정보인 로컬 CS-LBP (Centre Symmetric Local Binary Patterns)모델과 색상 분포 모델이 특징 모델로 사용된다. 각 특징 모델에 대해 바타차리야 (Bhattacharyya) 거리를 사용하여 각 파티클과 타깃 파티클 간의 특징 관측 우도(likelihood)를 구하고 이를 각 파티클의 가중치로 설정 한다. 각 파티클의 가중치를 기반으로 가중치가 가장 높은 파티클을 새로운 타깃으로 설정하고, 각 파티클들을 재 샘플링 한다. 본 실험결과에서는 여러 가지 특징을 조합하여 실험을 하였고, 그 결과 색상 분포 모델과 로컬 CS-LBP를 조합했을 때 추적 성능이 가장 우수한 것을 확인할 수 있었다.

• 한국군사과학기술학회지
• /
• 제10권3호
• /
• pp.139-147
• /
• 2007

In military transportation, the use of wide trailer for transporting the large and heavy weight equipments such as tank, armoured vehicle, and mobile gunnery is quite common. So, the vulnerability of causing traffic accidents for these wide military trailer to bump or collide with another car in adjacent lane is very high due to its broad width in excess of its own lane's width. Also, the possibility of these strayed accidents can be increased especially by the careless driver. In this paper, the recognition system of lane and vehicle headway direction is developed to detect the possible collision and warn the driver to prevent the fatal accident. In the system development, Kalman filtering is used first to extract the border of driving lane from the video images supplied by the CCD camera attached to the vehicle and the driving lane detection is completed with regression analysis. Next, the vehicle headway direction is recognized by using neural network scheme with the extracted parameters of the detected driving lane feature. The practical experiments for the developed system are also carried out in the real traffic road of Seoul city area and the results show us the more than 90% accuracy in recognizing the driving lane and vehicle headway direction.

• 패션비즈니스
• /
• 제13권4호
• /
• pp.60-76
• /
• 2009

Expression of woman characters in fusion traditional dramas plays a role of making the progress of dramas not bigoted and new. Especially, woman characters have a high weight as a heroine by an increase in their image in fusion traditional dramas. Expression of characters harmonizing modern with tradition has also given a help in reflecting a trend of the present times. Hair style and face makeup of woman characters in fusion traditional dramas are in the process of fusionization getting an effect from postmodernism. They are expressing the hair style of symbolization modern elements of hair style to traditional hair styles. They also expressed a neutral image with faded hair styles in the shaggy cut style and dye of neoplaticism. Neo-hippie style was changed into the style of naturalism and nationalism and the hair style braided in various branches as the one of Indians was changed into a primitive and national feature. It is producing a new style by permitting even a long-hair permanent wave hair style. Expression of straight hair style, a long-hair shaggy & bulging wave style and a hair style of neoplaticism, was distinguished. In the side of face makeup, they expressed its luxurious and splendid style by attaching great importance to its luster and are exposing images of characters by a smoky makeup emphasizing eye lines. Their face makeup was almost never separated from present dramas as using pearl shadow in a glossy lips makeup and color, which made it possible to express it more dramatically in fusion traditional dramas than in present dramas. In the event of the makeup element of fusion traditional dramas permitting diversity, the character makeup of fusion traditional dramas made a foundation to show people diverse elements of makeup by mix & match a present elements and past elements of historical research, which made it possible to express a unique makeup or a special makeup. Diverse makeup expressions were limited by reflection of illumination even in the existing videos. Therefore, 'Fusion' made it possible to express it more freely in fusion traditional dramas than in present dramas.

• 패션비즈니스
• /
• 제13권3호
• /
• pp.118-135
• /
• 2009

This study is done in Shanghai area by sample survey of female college students. Through direct contact survey, this study collected and analyzed information on figure to understand feature of breasts and measurements of body to provide base information to improve product of brassiere for adult female in China. Data was analyzed by using SPSSWIN 13.0 Program and SAS 9.0. 1. From a result of analysis on the body measures to understand the characteristics of the shape of the breast of the Chinese female college students(18$\sim$24 years old), the bust circumference was 83.86cm and the underbust circumference was 73.37cm and the cup size of a brassiere was 75A. 2. From a result of analysis on the bust measures to understand the relations between the front, lateral and cross-sectional proportions of the bust and the shape of the breast in the Chinese female college students, the chest height was 0.77, the bust height was 0.71 and the underbust height was 0.68 as the information of the body type that shows the location of the bust that is the measure of an item to a height as the front proportion of the bust. For the lateral proportion of the bust, the chest depth of the waist depth was 0.98, the bust depth, 1.21 and the underbust depth, 1.03. While the bust depth/waist depth is ideal when being 1.3, it was 1.21 in this study to be close to the ideal lateral shape. For the cross-sectional proportion of the bust, the area of the largest evenness was the bust followed by the waist, underbust and chest in order. 3. From a result of analysis on the correlation between measured items necessary to understand the characteristic of the shape of the breast, to set up the sizes and to produce the patterns, the underbust circumference had a relatively high correlation between the items of breadth, depth and circumference and weight as the items of basic areas.