• 정보과학회 논문지
• /
• 제42권2호
• /
• pp.227-234
• /
• 2015

본 논문에서는 데이터 분포를 고려한 다중 인스턴스 지지 벡터 기계 학습 알고리즘을 제안한다. 기존의 방법은 긍정 가방 안에서 "가장 긍정"인 인스턴스만 고려하여 마진을 찾는다. 일반적으로 다중 인스턴스로 표현된 데이터에서, 긍정 가방에 포함된 인스턴스들 중 실제로 긍정을 나타내는 인스턴스들은 자질 공간 상에서 서로 유사한 곳에 위치해 있다. 제안한 방법은 기존의 다중 인스턴스 지지 벡터 기계 학습 알고리즘 중에서 긍정 인스턴스들의 교차점을 찾아 이 교차점과 거리를 계산하여 "가장 긍정"인 인스턴스를 선택한다. 긍정 인스턴스들의 교차점인 피벗 포인트를 구하는 방식은 두 가지이다. 먼저, 학습과정 중 추정된 긍정 인스턴스들의 중심점을 사용하는 방법과 학습 시작 시에 가장 긍정일 것으로 예상되는 긍정 인스턴스들의 중심점을 찾는 방법으로 나뉜다. 총 12개의 벤치마크 다중 인스턴스 데이터 셋을 통해 제안한 방법이 기존의 학습 알고리즘에 비해 더 좋은 성능을 보임을 보인다.

• Geomechanics and Engineering
• /
• 제25권1호
• /
• pp.17-30
• /
• 2021

This paper develops a convenient approach for deterministic and probabilistic evaluations of tunnel face stability using support vector machine classifiers. The proposed method is comprised of two major steps, i.e., construction of the training dataset and determination of instance-based classifiers. In step one, the orthogonal design is utilized to produce representative samples after the ranges and levels of the factors that influence tunnel face stability are specified. The training dataset is then labeled by two-dimensional strength reduction analyses embedded within OptumG2. For any unknown instance, the second step applies the training dataset for classification, which is achieved by an ad hoc Python program. The classification of unknown samples starts with selection of instance-based training samples using the k-nearest neighbors algorithm, followed by the construction of an instance-based SVM-KNN classifier. It eventually provides labels of the unknown instances, avoiding calculate its corresponding performance function. Probabilistic evaluations are performed by Monte Carlo simulation based on the SVM-KNN classifier. The ratio of the number of unstable samples to the total number of simulated samples is computed and is taken as the failure probability, which is validated and compared with the response surface method.

• Journal of Information Technology Applications and Management
• /
• 제26권2호
• /
• pp.111-123
• /
• 2019

In this paper, software activity, software activity instance, and the quality of the activity instance are defined as the 'activity which is performed on the software product by a person or a group of persons,' the 'distinctive and individual performance of software activity,' and the 'performer's evaluation on how good or bad his/her own activity instance is,' respectively. The representative values of the instance quality population associated with a product and its sub-population are defined as the (software) activity quality and activity quality characteristic of the product, respectively. The activity quality model in this paper classifies activity quality characteristics according to the classification hierarchy of software activity by the goal. In the model, a quality characteristic can have two types of sub-characteristics : Special sub-characteristic and component sub-characteristic, where the former is its super-characteristic too simultaneously and the latter is not its super-characteristic but a part of its super-characteristic. The activity quality model is parsimonious, coherent, and easy to understand and use. The activity quality model can serve as a corner stone on which a software quality body of knowledge, which constituted with a set of models parsimonious, coherent, and easy to understand and use and the theories explaining the cause-and-relationships among the models, can be built. The body of knowledge can be called the (grand) activity-centric quality model of software.

• 한국산업정보학회논문지
• /
• 제10권1호
• /
• pp.28-37
• /
• 2005

본 논문은 퍼지 추론을 이용하여 소수문서로부터 대표 용어들을 추출하고 가중치를 부여하는 기존 방법의 유용성을 평가하고자 GIS (Generalized Instance Set) 알고리즘에 이를 적용시켜 그 성능을 평가하여 보았다. GIS 는 학습 문서 집합에 대한 일반화 (generalization) 과정을 통해 문서 그룹들을 형성하고 이 그룹의 대표 문서 (generalized instance)를 생성한 후 k- 알고리즘을 적용하는 방법이다. 본 논문에서는 바로 이 일반화 과정의 한 방법으로 퍼지 추론을 이용한 방법을 사용하였다. 상대적 성능 평가를 위하여 이 일반화(generalization) 과정에 Rocchio와 Widrow-Hoff 방법도 적용시켜 문서 분류 성능을 비교하였다. 실험 결과, 긍정적 문서만을 고려할 경우는 좋은 성능을 보이지만 부정적 문서를 같이 고려할 경우는 성능이 상대적으로 좋지 않음을 확인 할 수 있었다.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.209-214
• /
• 2021

Panoptic segmentation, which is now widely used in computer vision such as medical image analysis, and autonomous driving, helps understanding an image with holistic view. It identifies each pixel by assigning a unique class ID, and an instance ID. Specifically, it can classify 'thing' from 'stuff', and provide pixel-wise results of semantic prediction and object detection. As a result, it can solve both semantic segmentation and instance segmentation tasks through a unified single model, producing two different contexts for two segmentation tasks. Semantic segmentation task focuses on how to obtain multi-scale features from large receptive field, without losing low-level features. On the other hand, instance segmentation task focuses on how to separate 'thing' from 'stuff' and how to produce the representation of detected objects. With the advances of both segmentation techniques, several panoptic segmentation models have been proposed. Many researchers try to solve discrepancy problems between results of two segmentation branches that can be caused on the boundary of the object. In this survey paper, we will introduce the concept of panoptic segmentation, categorize the existing method into two representative methods and explain how it is operated on two methods: top-down method and bottom-up method. Then, we will analyze the performance of various methods with experimental results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권7호
• /
• pp.3714-3732
• /
• 2019

With the rapid development of network, Intrusion Detection System(IDS) plays a more and more important role in network applications. Many data mining algorithms are used to build IDS. However, due to the advent of big data era, massive data are generated. When dealing with large-scale data sets, most data mining algorithms suffer from a high computational burden which makes IDS much less efficient. To build an efficient IDS over big data, we propose a classification algorithm based on data clustering and data reduction. In the training stage, the training data are divided into clusters with similar size by Mini Batch K-Means algorithm, meanwhile, the center of each cluster is used as its index. Then, we select representative instances for each cluster to perform the task of data reduction and use the clusters that consist of representative instances to build a K-Nearest Neighbor(KNN) detection model. In the detection stage, we sort clusters according to the distances between the test sample and cluster indexes, and obtain k nearest clusters where we find k nearest neighbors. Experimental results show that searching neighbors by cluster indexes reduces the computational complexity significantly, and classification with reduced data of representative instances not only improves the efficiency, but also maintains high accuracy.

• 정보학연구
• /
• 제4권4호
• /
• pp.89-100
• /
• 2001

XML(extensible Markup Language)은 W3C(World Wide Web Consortium)에서 표준으로 제정, 발표한 대표적인 전자문서 표준이다. XML 문서는 구조화된 정보를 체계적으로 생성하고 전송할 수 있으며, 기존의 파일 형태 정보에 비하여 의미적인 정보 단위를 구조로 표현하고 이러한 구조 정보를 이용해 문서의 관리 및 검색, 저장에 이용할 수 있다. 이에 본 논문에서는 XML의 구조적 정보를 이용하여 저장 검색하기 위한 XML 저장 시스템을 설계 및 구현하였다. 문서의 기본 단위인 엘리먼트(element) 단위로 모델링(modeling)하여 저장하였고, 저장된 XML 정보를 구조 단위로 검색 할 수 있도록 모델링 하였다. 또한 DTD(Document Type Definition)와 인스턴스(instance)에 대하여 스키마(schema)를 생성하여 다양한 문서에 대한 구조를 효과적으로 관리, 저장할 수 있도록 하였다.

• 한국전자거래학회지
• /
• 제10권4호
• /
• pp.1-18
• /
• 2005

대표적인 전자거래 프레임워크인 ebXML에서 비즈니스 프로세스 명세(BPS: Business Process Specification)는 최종적으로 XML 버전의 BPSS( Business Process Specification Schema)를 준수하는 사례로서 규정되어야 한다. 보다 완전하고 일치되게 XML버전의 BPSS 사례를 정의하기 위해서는 모든 의미 제약을 검증하는 과정이 필수적이다. 그러나, XML Schema 구조체의 제약으로 인해서 XML버전의 BPSS는 이러한 의미 제약을 완벽하게 규정하고 있지 못하다. 이 논문에서는 최종적으로 실행될 XML 버전의 BPSS사례에 대한 검증을 지원하기 위해서, BPSS의 XML Schema에 표현되지 못한 의미 제약들을 체계적으로 발견하고, 이들을 명시적으로 표현하여 재활용하는 방법을 제시한다. 이러한 방법으로 XML 버전 BPSS 사례를 편리하게 검증하고, 오류 수정을 안내하며, 기업간 비즈니스 프로세스 표준화와 적용의 효율성을 증대시킬 수 있다.

• 한국안전학회지
• /
• 제34권6호
• /
• pp.50-57
• /
• 2019

In this study, various types of deep learning models that have been proposed recently are classified according to data input / output types and analyzed to find the deep learning model suitable for constructing a crack detection model. First the deep learning models are classified into image classification model, object segmentation model, object detection model, and instance segmentation model. ResNet-101, DeepLab V2, Faster R-CNN, and Mask R-CNN were selected as representative deep learning model of each type. For the comparison, ResNet-101 was implemented for all the types of deep learning model as a backbone network which serves as a main feature extractor. The four types of deep learning models were trained with 500 crack images taken from real concrete structures and collected from the Internet. The four types of deep learning models showed high accuracy above 94% during the training. Comparative evaluation was conducted using 40 images taken from real concrete structures. The performance of each type of deep learning model was measured using precision and recall. In the experimental result, Mask R-CNN, an instance segmentation deep learning model showed the highest precision and recall on crack detection. Qualitative analysis also shows that Mask R-CNN could detect crack shapes most similarly to the real crack shapes.

• Advances in concrete construction
• /
• 제5권3호
• /
• pp.221-240
• /
• 2017

The modeling of the mechanical behavior of quasi-brittle materials is still a challenge task, mainly in failure processes when fracture and plasticity phenomena become important actors in dissipative processes which occur in materials like concrete, as instance. Many homogenization-based approaches have been proposed to deal with heterogeneous materials in the last years. In this context, a computational homogenization modeling for concrete is presented in this work using the concept of Representative Volume Element (RVE). The material is considered as a three-phase material consisting of interface zone (ITZ), matrix and inclusions-each constituent modeled by an independent constitutive model. The Representative Volume Element (RVE) consists of inclusions idealized as circular shapes symmetrically and nonsymmetrically placed into the specimen. The interface zone is modeled by means of cohesive contact finite elements. The inclusion is modeled as linear elastic and matrix region is considered as elastoplastic material. A set of examples is presented in order to show the potentialities and limitations of the proposed modeling. The consideration of the fracture processes in the ITZ is fundamental to capture complex macroscopic characteristics of the material using simple constitutive models at mesoscopic level.