• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2008년도 공동추계학술대회
• /
• pp.73-75
• /
• 2008

최근 소위 Web 2.0 개념을 채택하는 다양한 웹 서비스 시스템구축이 보편화되면서 웹 검색 기능을 이용하는 일반 사용자나 전문 사용자에게 사용자 친화적이고 보다 빠른 성능의 웹 어플리케이션이 제공되고 있다. 참여와 공유를 목적으로 하는 Web 2.0 패러다임을 Web Happing이나 Web GIS 어플리케이션과 연계하는 연구나 기술 개발 분야도 중요한 이슈로 부각되고 있다. 특히 국내외적으로 실질적인 웹 컴퓨팅 기술과 연계되는 개방형 매핑 API를 이용한 매쉬업 어플리케이션 개발의 필요성과 산업적 수요는 급격히 증가하고 있는 추세이다. 본 연구에서는 이러한 배경을 바탕으로 하여 Google Map API를 이용한 공간정보 저작 매쉬업(Mashup) 어플리케이션을 시험 개발하고자 한다. 구현 결과로 별도의 Web GIS 웹 서버와 데이터베이스 서버에 대한 권한이 없어도 웹 클라이언트상에서 일반 웹 사용자가 Google Mapping 서버를 이용하여 자신의 공간정보를 직접 제작이 가능하도록 하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.287-289
• /
• 2005

This paper presents a hybrid neural network system which used a Self-Organizing Map and Multilayer Perceptron for the problem of Malay syllables speech recognition. The novel idea in this system is the usage of a two-dimension Self-organizing feature map as a sequential mapping function which transform the phonetic similarities or acoustic vector sequences of the speech frame into trajectories in a square matrix where elements take on binary values. This property simplifies the classification task. An MLP is then used to classify the trajectories that each syllable in the vocabulary corresponds to. The system performance was evaluated for recognition of 15 Malay common syllables. The overall performance of the recognizer showed to be 91.8%.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.134.1-134
• /
• 2001

The paper presents a sonar based map building method. The environment is a room or area inside a building, which is composed of four types of geometric primitives(corners, edges, cylinders, and walls). We also assume the environment can be modeled into two dimensional map in terms of planes(walls), points(corner and edge), and circle(cylinder). In a real world where most of the object surfaces are specular ones, a sonar sensor suffers from a multipath effect which results in a wrong interpretation of the location of an object. To reduce the effect and uncertainty, the method employs a simple thresholding technique for extracting circular arc features called regions of constant depth(RCD) from scanning sonar data. The usefulness of the approach is illustrated with the results produced by sets of experiments.

• East Asian mathematical journal
• /
• 제30권5호
• /
• pp.583-597
• /
• 2014

In this paper, we study an area-preserving piecewise linear map with the feature of dangerous border collision bifurcations. Using this map, we study dynamical properties occurred in the invariant set, specially related to the boundary of KAM-tori, and the existence and stabilities of periodic orbits. The result shows that elliptic regions having periodic orbits and chaotic region can be divided by smooth curve, which is an unexpected result occurred in area preserving smooth dynamical systems.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.654-658
• /
• 2002

The purpose of this paper is to establish an effective featured based inspection planning system for OMM(On-Machine Measurement) process. In this system, an effective inspection process planning is accomplished by determining the number of measuring points, their locations and probing paths using fuzzy logic, Hammersley method and TSP problem. Also, an effective collision-free algorithm Is proposed based on the EZ-map analysis. All the inspection planning processes are performed based on the defined inspection features those are derived from the CAD database. Proposed inspection planning method is simulated for the given sample wrokpieces, and the results are analyzed. The results show that the proposed method can be successfully implemented in real OMM process.

• 한국지진공학회:학술대회논문집
• /
• 한국지진공학회 1997년도 춘계 학술발표회 논문집 Proceedings of EESK Conference-Fall 1997
• /
• pp.21-26
• /
• 1997

For 262 locations throughout the southern part of Korean peninsula, intensities of 13 December 1996 Yeongweol earthquake are estimated to make an isoseismal map and investigate attenuation properties in the southern part of Korea. Due to the inherent uncertainties in the estimation of intensities, obtained intensity map show quite scattered pattern of intensity distribution. Estimated intensities range from III to possibly Ⅷ. In case of intensity larger than Ⅵ, considerable damages such as fracturing of walls are reported one of the most significant feature of the intensity map is, considering its magnitude 4.7 reported by KMA, the felt area is appeared to be unusually large covering most of the Korean peninsula except Cheju island. This result indicates ether the magnitude is underestimated or the focus of this earthquake is much deeper. Assuming shallow(less than 10km) intraplate earthquake, we obtained average magnitude 5.6 by using the area encircled by isoseismal contour lines from intensity IV to intensity Ⅶ. This ambiguity can be clarified if more reliable focal depth is estimated by using teleseismic earthquake records in the future.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.555-557
• /
• 2003

Location-based services allow consumers to receive services based on their geographic location data. For example, businesses can provide information to find traffic facility, public restaurant, a hospital, and a station based on the consumer’s location at a particular moment. Also, they wish to grasp a accurate location based service in mobile device or PDA. So, this paper shows that presentation service offers a base-map to be overlaid OpenLS (Open Location Services)’s directory service, route determination service, geocode and reverse-geocode service. The presentation service is the portrayal of a map and portrayal of feature as map overlays.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2012년도 한국컴퓨터종합학술대회논문집 Vol.39 No.1(C)
• /
• pp.385-387
• /
• 2012

MR 영상에서 간의 인식은 간에 존재하는 질병을 파악하는 것뿐만 아니라 간에 대한 치료 방법이나 수술방법을 결정하는 중요한 정보를 제공한다. 이러한 일반적인 간의 인식 방법은 영역 분할 알고리즘을 기반으로 처리되어진다. IT분야에서의 영역 분할 알고리즘은 대부분 밝기 정보, 형태 정보, 패턴 분석 등 다양한 입력 정보의 컴퓨팅 처리를 통해 처리되어 진다. 그러나 이러한 컴퓨팅 방법으로는 앞서 언급된 입력정보들이 의미가 없을 경우, 영역 분할에 많은 제약이 따르게 된다. 따라서 본 논문은 이러한 컴퓨팅 처리의 근본적인 제약사항을 해결하고자, MR 이론의 R2-map정보 기반의 효과적인 영역 분할 방법은 제안하였다. 본 방법은 간 영역이 포함된 영상에서 실험하였으며, R2-map맵의 일부 특징점을 Region growing의 Seed point로 설정하여 경계가 모호하더라도 영역 분할이 가능하게끔 하였다. 해당 영상의 실험 결과 8.5%의 평균 오차로 일반적인 영역 분할 알고리즘에 비해 높은 정확도가 산출되었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2012년도 춘계학술발표대회
• /
• pp.191-194
• /
• 2012

Rendering maps is an essential feature of the user interface component of a location based service (LBS) system. However, a developer may not too much worry about implementing the rendering maps part of his or her system because there are quite a few publicly available libraries that provide all kinds of functions of manipulating maps. Google Maps, Yahoo Map, Naver Map, Daum Map, and so on are example sites that provide those libraries. Rendering drawings is to indoor LBS as rendering maps is to LBS. However, there is no such thing as Google Maps that provides libraries for rendering drawings. This paper introduces a few web services and a library that is useful in developing user interfaces of indoor LBS systems.

• Journal of Information Processing Systems
• /
• 제18권4호
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.