http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
클래스 영역의 다차원 구 생성에 의한 프로토타입 기반 분류
심세용(Seyong Shim),황두성(Doosung Hwang) 한국컴퓨터정보학회 2015 韓國컴퓨터情報學會論文誌 Vol.20 No.2
본 논문에서는 최근접 이웃 규칙을 이용한 프로토타입 선택 기반 분류 학습을 제안하였다. 각 훈련 데이터가 대표하는 클래스 영역을 구(sphere)로 분할하는데 최근접 이웃 규칙을 적용시키며, 구의 내부는 동일 클래스 데이터들만 포함하도록 한다. 프로토타입은 구의 중심점이며 프로토타입의 반지름은 가장 인접한 다른 클래스 데이터와 가장 먼 동일 클래스 데이터의 중간 거리 값으로 결정한다. 그리고 전체 훈련 데이터를 대표하는 최소의 프로토타입 집합을 선택하기 위해 집합 덮개 최적화를 이용하여 프로토타입 선택 문제를 변형시켰다. 제안하는 프로토타입 선택 방법은 클래스 별 적용이 가능한 그리디 알고리즘으로 설계되었다. 제안하는 방법은 계산 복잡도가 높지 않으며, 대규모 훈련 데이터에 대한 병렬처리의 가능성이 높다. 프로토타입 기반 분류 학습은 선택된 프로토타입 집합을 새로운 훈련 데이터 집합으로 사용하고 최근접 이웃 규칙을 적용하여 테스트 데이터의 클래스를 예측한다. 실험에서 제안하는 프로토타입 기반 분류기는 최근접 이웃 학습, 베이지안 분류 학습과 다른 프로토타입 분류기에 비해 일반화 성능이 우수하였다. In this paper, we propose a prototype-based classification learning by using the nearest-neighbor rule. The nearest-neighbor is applied to segment the class area of all the training data into spheres within which the data exist from the same class. Prototypes are the center of spheres and their radii are computed by the mid-point of the two distances to the farthest same class point and the nearest another class point. And we transform the prototype selection problem into a set covering problem in order to determine the smallest set of prototypes that include all the training data. The proposed prototype selection method is based on a greedy algorithm that is applicable to the training data per class. The complexity of the proposed method is not complicated and the possibility of its parallel implementation is high. The prototype-based classification learning takes up the set of prototypes and predicts the class of test data by the nearest neighbor rule. In experiments, the generalization performance of our prototype classifier is superior to those of the nearest neighbor, Bayes classifier, and another prototype classifier.
FISH Karyotype Analysis of Fagopyrum tartaricum Gaerth (Tartary buckwheat) using Repetitive DNAs
Yoon-Ha Ju,Franklin Hinosa Mancia,Seyong Yoon,Heekyung Park,Soeun Yoon,Jiin Park,Sunmi Joung,Su Jeong Kim,Yul Ho Kim,Hwang Bae Sohn,Ki-Byung Lim,Hyun Hee Kim,Yoon-Jung Hwang 한국원예학회 2016 한국원예학회 학술발표요지 Vol.2016 No.10
정영만(Youngman Jeong),구경민(Kyungmin Koo),황유진(Yujin Hwang),장세용(Seyong Jang),이영호(Yeongho Lee),이동혁(Donghyuk Lee),이재근(Jaekeun Lee) 대한설비공학회 2008 설비공학 논문집 Vol.20 No.11
This paper presents the measurement of ground thermal conductivity and the characteristics of ground thermal diffusion by a ground heat exchanger(GHE). A borehole is installed to a depth of 175 m with a diameter of 150 ㎜. To analyze the thermal diffusion property of the GHE, thermocouples are installed under the ground near the GHE. The outdoor temperature, the ground temperature, and the water temperature of the GHE are monitored for evaluating the characteristics of ground thermal diffusion. The ground thermal conductivity is evaluated by the in-situ thermal response tester and the line source model. It is found to be 3.08 W /m℃ in this study. The ground temperature is greatly dependent on the outdoor temperature from the ground surface to 2.5 m in depth and is stable below 10m in depth. The surface temperature of the GHE varies as a function of the temperature of circulating water. But the ground temperature at 1.5 m far from the GHE is not changed in accordance with the temperature of circulating water.
Learning-to-rank 기법을 활용한 서울 경마경기 순위 예측
정준형,신동욱,황세용,박건웅,Junhyoung Chung,Donguk Shin,Seyong Hwang,Gunwoong Park 한국통계학회 2024 응용통계연구 Vol.37 No.2
This research applies both point-wise and pair-wise learning strategies within the learning-to-rank (LTR) framework to predict horse race rankings in Seoul. Specifically, for point-wise learning, we employ a linear model and random forest. In contrast, for pair-wise learning, we utilize tools such as RankNet, and LambdaMART (XGBoost Ranker, LightGBM Ranker, and CatBoost Ranker). Furthermore, to enhance predictions, race records are standardized based on race distance, and we integrate various datasets, including race information, jockey information, horse training records, and trainer information. Our results empirically demonstrate that pair-wise learning approaches that can reflect the order information between items generally outperform point-wise learning approaches. Notably, CatBoost Ranker is the top performer. Through Shapley value analysis, we identified that the important variables for CatBoost Ranker include the performance of a horse, its previous race records, the count of its starting trainings, the total number of starting trainings, and the instances of disease diagnoses for the horse.