• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제3권2호
• /
• pp.43-46
• /
• 2014

시계열 데이터는 시간에 따라 변화되는 실수 값을 저장한 것이다. 시계열 데이터에서 사용자 질의 시퀀스가 주어졌을 때, 유사한 서브시퀀스를 가지는 데이터 시퀀스를 검색하는 서브시퀀스 매칭은 매우 중요한 문제이다. 본 논문에서는 인스턴스 레벨의 새로운 서브시퀀스 매칭 방법인 I-Match (Instance-Match)를 제안한다. I-Match는 인스턴스 레벨에서 가상 윈도우를 생성하여 질의 시퀀스와 데이터 시퀀스를 비교하여 착오 해답을 줄이는 방법으로 기존 방법인 Dual Match에 비해 후보의 개수를 줄임으로써 성능을 향상시켰다. 실험을 통해 I-Match의 질의 처리 시간이 Dual Match와 비교하여 최대 2.95배 빠르며, 후보의 개수를 줄임을 보인다.

• 한국멀티미디어학회논문지
• /
• 제9권12호
• /
• pp.1552-1559
• /
• 2006

In a web environment, similar information exists in many different places in diverse formats. Even duplicate information is stored in the various databases using different terminologies. Since most information serviced in the current World Wide Web however had been constructed before the advent of ontology, it is practically almost impossible to construct ontology for all those resources in the web. In this paper, we assume that most information in the web environment exist in the form of RDBMS, and propose a matching method between domain ontology and existing RDBMS tables for semantic retrieval. In the processing of extracting a local ontology, some problems such as losing domain in formation can occur since the correlation of domain ontology has not been considered at all. To prevent these problems, we propose an instance-based matching which uses relational information between RDBMS tables and relational information between classes in domain ontology. To verify the efficiency of the method proposed in this paper, several experiments are conducted using the digital heritage information currently serviced in the countrywide museums. Results show that the proposed method increase retrieval accuracy in terms of user relevance and satisfaction.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.283-286
• /
• 2007

This paper proposes a genetic algorithm (GA) approach to instance selection in case-based reasoning (CBR) for the prediction of Korea Stock Price Index (KOSPI). CBR has been widely used in various areas because of its convenience and strength in complex problem solving. Nonetheless, compared to other machine learning techniques, CBR has been criticized because of its low prediction accuracy. Generally, in order to obtain successful results from CBR, effective retrieval of useful prior cases for the given problem is essential. However, designing a good matching and retrieval mechanism for CBR systems is still a controversial research issue. In this paper, the GA optimizes simultaneously feature weights and a selection task for relevant instances for achieving good matching and retrieval in a CBR system. This study applies the proposed model to stock market analysis. Experimental results show that the GA approach is a promising method for instance selection in CBR.

• 한국콘텐츠학회논문지
• /
• 제6권10호
• /
• pp.25-33
• /
• 2006

시맨틱 환경에서의 시맨틱 검색을 위해서는 분산된 자원의 관리와 처리가 중요한 요소이다. 분산된 자원의 효율적인 검색을 위해서는 온톨로지의 사용이 필수적이지만, 모든 자원에 대한 통합적인 온톨로지를 구축하는 것은 현실적으로 매우 어려운 일이다. 본 논문에서는 웹 환경에서의 대부분의 자원은 관계형 데이터베이스 형태로 저장되어져 있다고 가정하고, 시맨틱 검색을 위하여 분산된 관계형 데이터베이스 테이블과 도메인 온톨로지간의 매칭을 위한 방법을 제안한다. 기존의 관계형 데이터베이스와 도메인 온톨로지간의 매칭에 관한 연구들은 관계형 데이터베이스에서 로컬 온톨로지를 추출하여 도메인 온톨로지와의 매칭을 수행하였다. 그러나, 로컬 온톨로지를 추출하는 과정에서 도메인 온톨로지와의 상관관계를 이용하지 않음으로 인하여 도메인 정보가 손실되는 문제점을 가지고 있다. 이에 대한 해결책으로 관계형 데이터베이스의 인스턴스들과 도메인 온톨로지의 인스턴스간의 유사도 측정을 통한 정보 손실을 방지하였으며, 관계형 데이터베이스내의 테이블들간의 관계와 온톨로지에서의 클래스들간의 관계 정보를 이용하여 보다 효율적인 매칭이 가능하도록 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권9호
• /
• pp.2483-2494
• /
• 2024

Instance segmentation is a challenging research in the field of computer vision, which combines the prediction results of object detection and semantic segmentation to provide richer image feature information. Focusing on the instance segmentation in the street scene, the real-time instance segmentation method based on SOLOv2 is proposed in this paper. First, a cross-stage fusion backbone network based on position attention is designed to increase the model accuracy and reduce the computational effort. Then, the loss of shallow location information is decreased by integrating two-way feature pyramid networks. Meanwhile, cross-stage mask feature fusion is designed to resolve the small objects missed segmentation. Finally, the adaptive minimum loss matching method is proposed to decrease the loss of segmentation accuracy due to object occlusion in the image. Compared with other mainstream methods, our method meets the real-time segmentation requirements and achieves competitive performance in segmentation accuracy.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권6호
• /
• pp.464-469
• /
• 2010

상하위 관계 자동 추출은 분류체계를 자동 구축하는 데 있어서 핵심적인 내용이며, 이렇게 자동으로 구축된 분류 체계는 정보 추출과 같은 여러 가지 분야에 있어서 중요하게 사용된다. 본 논문에서는 카테고리 구조로부터 상하위 관계를 추출하는 방식에 대하여 제안한다. 본 논문에서는 판별하고자 하는 카테고리 구조뿐만이 아닌, 그와 관련된 다른 카테고리 구조까지 고려하여 카테고리 이름에 나타난 토큰들간의 수식 그래프를 구축한 후, 그래프 분석 알고리즘을 통하여 각 카테고리 구조가 상하위 관계일 가능성에 대한 점수를 매긴다. 실험 결과, 본 알고리즘은 기존의 연구로 상하위 관계임을 판별할 수 없었던 일부 카테고리 구조에 대하여 성공적으로 상하위 관계인지를 판별하였다.

• 대한기계학회논문집
• /
• 제17권11호
• /
• pp.2711-2722
• /
• 1993

Most of the current 2-D object recognition systems are model-based. In such systems, the representation of each of a known set of objects are precompiled and stored in a database of models. Later, they are used to recognize the image of an object in each instance. In this thesis, the approach method for the 2-D object recognition is treating an object boundary as a string of structral units and utilizing string matching to analyze the scenes. To reduce string matching time, models are rebuilt by means of fuzzy c-means clustering algorithm. In this experiments, the image of objects were taken at initial position of a robot from the CCD camera, and the models are consturcted by the proposed algorithm. After that the image of an unknown object is taken by the camera at a random position, and then the unknown object is identified by a comparison between the unknown object and models. Finally, the amount of translation and rotation of object from the initial position is computed.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 한국지능정보시스템학회
• /
• pp.389-398
• /
• 2007

Case-based reasoning (CBR) is one of the most popular prediction techniques for medical diagnosis because it is easy to apply, has no possibility of overfitting, and provides a good explanation for the output. However, it has a critical limitation - its prediction performance is generally lower than other artificial intelligence techniques like artificial neural networks (ANNs). In order to obtain accurate results from CBR, effective retrieval and matching of useful prior cases for the problem is essential, but it is still a controversial issue to design a good matching and retrieval mechanism for CBR systems. In this study, we propose a novel approach to enhance the prediction performance of CBR. Our suggestion is the simultaneous optimization of feature weights, instance selection, and the number of neighbors that combine using genetic algorithms (GAs). Our model improves the prediction performance in three ways - (1) measuring similarity between cases more accurately by considering relative importance of each feature, (2) eliminating redundant or erroneous reference cases, and (3) combining several similar cases represent significant patterns. To validate the usefulness of our model, this study applied it to a real-world case for evaluating cytological features derived directly from a digital scan of breast fine needle aspirate (FNA) slides. Experimental results showed that the prediction accuracy of conventional CBR may be improved significantly by using our model. We also found that our proposed model outperformed all the other optimized models for CBR using GA.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.4968-4986
• /
• 2017

In this paper, we primarily address the difficulty of automatic generation of a plausible depth map from a single image in an unstructured environment. The aim is to extrapolate a depth map with a more correct, rich, and distinct depth order, which is both quantitatively accurate as well as visually pleasing. Our technique, which is fundamentally based on a preexisting DepthTransfer algorithm, transfers depth information at the level of superpixels. This occurs within a framework that replaces a pixel basis with one of instance-based learning. A vital superpixels feature enhancing matching precision is posterior incorporation of predictive semantic labels into the depth extraction procedure. Finally, a modified Cross Bilateral Filter is leveraged to augment the final depth field. For training and evaluation, experiments were conducted using the Make3D Range Image Dataset and vividly demonstrate that this depth estimation method outperforms state-of-the-art methods for the correlation coefficient metric, mean log10 error and root mean squared error, and achieves comparable performance for the average relative error metric in both efficacy and computational efficiency. This approach can be utilized to automatically convert 2D images into stereo for 3D visualization, producing anaglyph images that are visually superior in realism and simultaneously more immersive.

• 한국건설관리학회논문집
• /
• 제5권5호
• /
• pp.151-162
• /
• 2004

Current methods for construction site modeling employ large, expensive laser range scanners that produce dense range point clouds of a scene from different perspectives. Days of skilled interpretation and of automatic segmentation may be required to convert the clouds to a finished CAD model. The dynamic nature of the construction environment requires that a real-time local area modeling system be capable of handling a rapidly changing and uncertain work environment. However, in practice, large, simple, and reasonably accurate embodying volumes are adequate feedback to an operator who, for instance, is attempting to place materials in the midst of obstacles with an occluded view. For real-time obstacle avoidance and automated equipment control functions, such volumes also facilitate computational tractability. In this research, a human operator's ability to quickly evaluate and associate objects in a scene is exploited. The operator directs a laser range finder mounted on a pan and tilt unit to collect range points on objects throughout the workspace. These groups of points form sparse range point clouds. These sparse clouds are then used to create geometric primitives for visualization and modeling purposes. Experimental results indicate that these models can be created rapidly and with sufficient accuracy for automated obstacle avoidance and equipment control functions.