• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.521-528
• /
• 2000

One of the hidden problems in a domain theory is that an agent does not understand the meaning of its action. Graphplan uses mutex to improve efficiency, but it does not understand negation and suffers from a redundancy problem. Introducing a negative function not in IPP partially helps to solve this kind of problem. However, using a negative function comes with its own price in terms of time and space. Observing that a human utilizes opposite concept to negate a fact based on MDL principle, we hypothesize that using a positive atom rather than a negative function to represent a negative fact is a more efficient technique for building an intelligent agent. We show empirical results supporting our hypothesis in IPP domains. To autonomously learn the human-like concept, we generate a cycle composed of opposite operators from a domain theory and extract opposite literals through experimenting with the operators.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.9
• /
• pp.33-38
• /
• 2014

The FCM based hybrid RBF network is a heterogeneous learning network model that applies FCM algorithm between input and middle layer and applies Max_Min algorithm between middle layer and output. The Max-Min neural network uses winner nodes of the middle layer as input but shows inefficient learning in performance when the input vector consists of too many patterns. To overcome this problem, we propose a dynamic learning rate control based on fuzzy logic. The proposed method first classifies accurate/inaccurate class with respect to the difference between target value and output value with threshold and then fuzzy membership function and fuzzy decision logic is designed to control the learning rate dynamically. We apply this proposed RBF network to the character recognition problem and the efficacy of the proposed method is verified in the experiment.

• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1356-1364
• /
• 2016

This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.

• The KIPS Transactions:PartB
• /
• v.17B no.1
• /
• pp.93-98
• /
• 2010

In this paper, we introduce a system that summarizes product evaluation through linguistic analysis to effectively utilize explosively increasing product reviews. Our system analyzes polarities of product reviews by product features, based on which customers evaluate each product like 'design' and 'material' for a skirt product category. The system shows to customers a graph as a review summary that represents percentages of positive and negative reviews. We build an opinion word dictionary for each product feature through context based automatic expansion with small seed words, and judge polarity of reviews by product features with the extracted dictionary. In experiment using product reviews from online shopping malls, our system shows average accuracy of 69.8% in extracting judgemental word dictionary and 81.8% in polarity resolution for each sentence.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.1
• /
• pp.1-10
• /
• 2012

Recent spatial information technology has brought innovative improvement in both efficiency and accuracy. Especially, airborne LiDAR system(ALS) is one of the practical sensors to obtain 3D spatial information. Constructing reliable 3D spatial data infrastructure is world wide issue and most of the significant tasks involved with modeling manmade objects. This study aims to create a test data set for developing automatic building modeling methods by simulating point cloud data. The data simulates various roof types including gable, pyramid, dome, and combined polyhedron shapes. In this study, a robust bottom-up method to segment surface patches was proposed for generating building models automatically by determining model key points of the objects. The results show that building roofs composed of the segmented patches could be modeled by appropriate mathematical functions and the model key points. Thus, 3D digitizing man made objects could be automated for digital mapping purpose.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.35-44
• /
• 2004

Web contents created for desktop screens give rise to problems when they are to be displayed on the small screens of mobile terminals. While in some cases some of the objects of a page may not be displayable due to the lack of browser capability, the entire page may not be displayable due to the incompatibility with the browser in other cases. In this paper, we introduce a new mobile content adaptation approach based on web clipping, which transforms an original page into one that is optimally displayed on a mobile terminal. In this method, a source page is automatically clipped and transformed according to the clip specification made by the content provider using a clip editing tool. The clip editing tool allows the user to specify group clips, multi-level cups and dynamic clips as well as simple clips, and the presentation layout through a graphic user interface. Based on the clip specifications, each clip is transformed into an intermediate meta-language document, which in turn is transformed into a presentation page in the target markup language. Transcoding of image objects in major image file formats is also supported.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.195-200
• /
• 2016

본 연구는 MUSE 감성 코퍼스를 활용하여 문장의 극성과 키워드의 극성이 얼마만큼 일치하고 일치하지 않은지를 분석함으로써 특히 문장의 극성과 키워드의 극성이 불일치하는 유형에 대한 연구의 필요성을 역설하고자 한다. 본 연구를 위하여 DICORA에서 구축한 MUSE 감성주석코퍼스 가운데 IT 리뷰글 도메인으로부터 긍정 1,257문장, 부정 1,935문장을, 맛집 리뷰글 도메인으로부터는 긍정 2,418문장, 부정 432문장을 추출하였다. UNITEX를 이용하여 LGG를 구축한 후 이를 위의 코퍼스에 적용하여 나타난 양상을 살펴본 결과, 긍 부정 문장에서 반대 극성의 키워드가 실현된 경우는 두 도메인에서 약 4~16%의 비율로 나타났으며, 단일 키워드가 아닌 구나 문장 차원으로 극성이 표현된 경우는 두 도메인에서 약 25~40%의 비교적 높은 비율로 나타났음을 확인하였다. 이를 통해 키워드의 극성에 의존하기 보다는 문장과 키워드의 극성이 일치하지 않는 경우들, 가령 문장 전체의 극성을 전환시키는 극성전환장치(PSD)가 실현된 유형이나 문장 내 극성 어휘가 존재하지 않지만 구 또는 문장 차원의 극성이 표현되는 유형들에 대한 유의미한 연구가 수행되어야 비로소 신뢰할만한 오피니언 자동 분류 시스템의 구현이 가능하다는 것을 알 수 있다.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.791-798
• /
• 2002

In this thesis. we present a new method for inducing a probabilistic dependency grammar (PDG) from text corpus. As words in Korean are composed of a set of more basic morphemes, there exist various dependency relations in a word. So, if the induction process does not take into account of these in-word dependency relations, the accuracy of the resulting grammar nay be poor. In comparison with previous PDG induction methods. the main difference of the proposed method lies in the fact that the method takes into account in-word dependency relations as well as inter-word dependency relations. To access the performance of the proposed method, we conducted an experiment using a manually-tagged corpus of 25,000 sentences which is complied by Korean Advanced Institute of Science and Technology (KAIST). The grammar induction produced 2,349 dependency rules. The parser with these dependency rules shoved 69.77% accuracy in terms of the number of correct dependency relations relative to the total number dependency relations for best-1 parse trees of sample sentences. The result shows that taking into account in-word dependency relations in the course of grammar induction results in a more accurate dependency grammar.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.567-576
• /
• 2003

Spatial data mining, i.e., discovery of interesting characteristics and patterns that may implicitly exists in spatial databases, is a challenging task due to the huge amounts of spatial data. Clustering algorithms are attractive for the task of class identification in spatial databases. Several methods for spatial clustering have been presented in recent years, but have the following several drawbacks increase costs due to computing distance among objects and process only memory-resident data. In this paper, we propose an efficient grid cell based spatial clustering method for spatial data mining. It focuses on resolving disadvantages of existing clustering algorithms. In details, it aims to reduce cost further for good efficiency on large databases. To do this, we devise a spatial clustering algorithm based on grid ceil structures including cell relationships.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.489-500
• /
• 2003

Due to the rapid growth of Internet, modern software applications must support many web-based functionalities than traditional software applications. These web-based functional supports increase the complexity of software architecture and the cost of software development. Therefore, the development of an efficient environment that web characteristics are well reflected is the most important. In this thesis, we have presented an efficient environment for development of web applications. For the presented environment, after considering the web characteristics, we defined a Process for web applications and modeling environment. The Presented environment has three main functions : $\circled1$ it Provides a modeling environment for design of web-based applications, $\circled2$ it has a modeling language called WML(web-application modeling language), $\circled3$ it automatically extracts web pages from diagrams. As a result, using the three main functions of the presented environment, we can easily design, develop, and maintain the web applications.