• 인지과학
• /
• 제19권4호
• /
• pp.443-458
• /
• 2008

오늘날 웹페이지(Web page)는 많은 정보를 포함하고 있다. 본 논문에서는 정보추출(information extraction) 등에서 유용하게 사용되는 개체명(named entity)을 웹(Web)을 이용하여 영역별로 자동으로 추출하는 집합 확장 시스템을 제안한다. 그 방식은 전체적으로 3단계의 구성을 가진다. 우선 사전을 구축하고자 하는 영역의 몇 개의 원소를 씨앗단어로 이용하여 웹페이지를 검색한다. 다음으로 검색되어진 웹페이지와 씨앗단어 정보를 이용하여 패턴 규칙을 추출한다. 추출된 패턴 규칙을 다시 웹페이지에 적용하여 개체명 후보들을 추출하고 최종적으로 추출된 후보들과 웹페이지 사이의 상호 중요도를 재귀적으로 계산하여 개체명 후보들에 대한 순위를 정하게 된다. 이 방식의 실험은 한국어와 영어로 나누어서 실험을 수행하였고, 한국어는 3개의 영역에서, 영어는 8개의 영역에서 실험을 진행하였다. 그 결과, 한국어에서는 78.72%의 MAP를 얻을 수 있었고, 영어에서는 96.48%의 MAP를 얻었다. 특히, 영어 개체명 인식에서의 성능은 구글에서 제공하고 있는 구글셋의 결과보다도 높은 성능을 보였다.

• 한국측량학회지
• /
• 제31권3호
• /
• pp.229-238
• /
• 2013

지도 일반화 기법을 이용하여 대축척 지도자료로부터 소축척 지도자료를 생산하기 위한 방법론 개발은 수치지형도의 제작, 갱신 등의 관리에 있어서 매우 중요하다. 본 연구에서는 수치지형도의 도로와 같은 네트워크 형태의 객체를 일반화하기 위한 하나의 단계인 선택 기법을 제안, 적용하였다. 이를 위해, 기존의 1:5,000 축척과 1:25,000 축척의 수치지형도를 상호 비교하여 도로 네트워크 객체의 선택과 관련된 기준(선택 객체의 개수, 상대적 중요도) 들을 T$\ddot{o}$pfer의 radical 법칙과 Logit 모형을 이용하여 분석하였다. 여기서 분석된 결과를 바탕으로 하여 테스트 데이터에 대해 선택 모델을 적용하여 1:5,000 수치지형도 도로중심선 레이어로부터 일반화된 1:18,000, 1:72,000 축척의 네트워크 데이터셋을 도출하였다. 일반화된 결과에 대하여 정성적, 정량적 평가를 실시한 결과, 상대적으로 높은 중요도를 가진 네트워크 객체들이 목표 축척수준에 맞게 적절히 선택된 결과를 나타내었다.

• 전기학회논문지
• /
• 제68권3호
• /
• pp.471-479
• /
• 2019

This research proposes a indoor magnetic map matching algorithm that improves the position accuracy by employing multiple magnetic sensors and probabilistic candidate weighting function. Since the magnetic field is easily distorted by the surrounding environment, the distorted magnetic field can be used for position mapping, and multiple sensor configuration is useful to improve mapping accuracy. Nevertheless, the position error is likely to increase because the external magnetic disturbances have repeated pattern in indoor environment and several points have similar magnetic field distortion characteristics. Those errors cause large position error, which reduces the accuracy of the position detection. In order to solve this problem, we propose a method to reduce the error using multiple sensors and likelihood boundaries that uses human walking characteristics. Also, to reduce the maximum position error, we propose an algorithm that weights according to their importance. We performed indoor walking tests to evaluate the performance of the algorithm and analyzed the position detection error rate and maximum distance error. From the results we can confirm that the accuracy of position detection is greatly improved.

• 로봇학회논문지
• /
• 제19권1호
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.

• 대한인간공학회지
• /
• 제18권2호
• /
• pp.35-45
• /
• 1999

Driver centered vehicle design is the important factor for driver's safety, product quality, and so on. Therefore, people has recently recognized the importance of driver centered vehicle design. Especially, in the focus of driver-vehicle interaction system, it is very important factor to ergonomic design of vehicle cockpit. In this study, Sketch Map method was used to measure of driver's cognitive map on IP(Instrument Panel) that is the basic factor to ergonomic design for vehicle cockpit. The compatibility of Sketch Map method was validated for the measurement of driver's cognitive map and then the accuracy between two groups was analyzed using Sketch Map method. Subjects were divided in two groups, the first group of subjects has their own vehicles and driver license, and the second group of subjects doesn't have own vehicle but has driver license. The result showed that for the case of the first group, the shape of IP in the cognitive map was influenced by IP of their each vehicle. However, for the case of the second group, it showed the difference between IP in the cognitive map and IP of experienced vehicle many times because they have been driving various type of vehicle. So, the shape of IP in the cognitive map was influenced by various type of IP.

• 디지털콘텐츠학회 논문지
• /
• 제14권3호
• /
• pp.313-321
• /
• 2013

최근 모바일 스마트 기기의 보급으로 스마트 기기에 탑재된 다양한 센서에서 수집되는 대량이 데이터를 분석하여 처리하는 빅 데이터의 시대는 위치기반 서비스(LBSs: Location-Based Services)에 까지 확대대고 있다. 이동궤적에 대한 데이터도 초 대용량으로 증가하고 있다. 초 대용량 이동궤적 데이터 처리를 위해서는 클라우드 컴퓨팅 기술 및 맵리듀스와 같은 병행처리 플랫폼에 대한 연구가 필요하다. 최근 대용량 데이터의 병렬처리를 위해 맵리듀스 기반의 연구는 진행되고 있으나, 일괄처리 및 키-값 데이터 구조에 적합한 맵리듀스는 실시간 LBS에 적용에 적합하지 않다. 따라서 본 연구는 맵리듀스 특성을 면밀히 분석하고 실시간적 서비스에 적합하도록 모듈 단위로 효율적인 색인 기법 및 검색에 대한 시스템 설계를 제시한다.

• 농촌계획
• /
• 제16권4호
• /
• pp.13-22
• /
• 2010

Rural landscape is an outcome of residents' life activity based on natural environment. Unlike city, rural residents make their own landscape over a period of time interacting with nature through cultivating and building houses and huts based on the background. Therefore, residents' role in rural area is of greater importance than city's and their recognition of landscape is a key factor to evaluate and manage rural landscape. Landscape Evaluation Map which utilizing Feeling Map method is a evaluation tool to [md out residents' recognition of landscape. In this tool, responses evaluate landscape around their living space and mark color dots which mean landscape grade on a map. This research is to examine effectiveness and applicability of the tool, Landscape Evaluation Map, which is recommended to estimate residents' evaluation of landscape. Through analyzing 7 cases of field application, the effectiveness of Landscape Evaluation Map has been verified and also demerits have been drawn. After modifying detailed techniques and developing resident education, Landscape evaluation map could be applied to [md out landscape resources rather than to evaluate whole rural landscape.

• 로봇학회논문지
• /
• 제16권3호
• /
• pp.189-198
• /
• 2021

In this paper, we introduce the software/hardware system that can reliably calculate the distance from sensor to the model regardless of point cloud density. As the 3d point cloud map is widely adopted for SLAM and computer vision, the accuracy of point cloud map is of great importance. However, the 3D point cloud map obtained from Lidar may reveal different point cloud density depending on the choice of sensor, measurement distance and the object shape. Currently, when measuring map accuracy, high reflective bands are used to generate specific points in point cloud map where distances are measured manually. This manual process is time and labor consuming being highly affected by Lidar sparsity level. To overcome these problems, this paper presents a hardware design that leverage high intensity point from three planar surface. Furthermore, by calculating distance from sensor to the device, we verified that the automated method is much faster than the manual procedure and robust to sparsity by testing with RGB-D camera and Lidar. As will be shown, the system performance is not limited to indoor environment by progressing the experiment using Lidar sensor at outdoor environment.

• 한국의류학회지
• /
• 제16권2호
• /
• pp.155-168
• /
• 1992

The purposes of this study were: (1) to identify the image dimensions of apparel stores according to how the consumers rate the importance of store attributes; (2) to classify the apparel stores in Seoul, Korea according to consumers' perception of the image attributes of their preferred store; (3) to develop a positioning map of the apparel stores according to their salient image dimensions; and (4) to classify the female adults in Seoul according to the criteria of their preferred store and to describe the characteristics of target customers according to storetype. 'A questionnaire was developed to measure store patronage, perceived importance of the store image attributes, perception of the store image attributes for the respondent's most frequently patronized store, and demographic information. Data from 520 female adults living in Seoul were analyzed. The results were as follows; 1. The image dimensions of fashion stores were product quality, shopping convenience, location, promotion, atmosphere, product information, design characteristics and price. 2. The apparel stores in Seoul were classified into five groups by the perception of store image, which were labeled as national chain store, designer store, specialty store, wholesale store and independent store, according to their discriminant characteristics. 3. According to the positioning map, product quality and location convenience were identified as the most important apparel store type patronage criteria. 4. The female adult group divided by store preference indicated significant differences in the perceived importance of store attributes. Each group showed multi-store patronage.

• Journal of Microbiology and Biotechnology
• /
• 제25권5호
• /
• pp.637-647
• /
• 2015

In this study, we attempted to understand signaling pathways behind lipid biosynthesis by employing a chemical genetics approach based on small molecule inhibitors. Specific signaling inhibitors of MAP kinase or modulators of cAMP signaling were selected to evaluate the functional roles of each of the key signaling pathways in three different microalgal species: Chlamydomonas reinhardtii, Chlorella vulgaris, and Haematococcus pluvialis. Our results clearly indicate that cAMP signaling pathways are indeed positively associated with microalgal lipid biosynthesis. In contrast, MAP kinase pathways in three microalgal species are all negatively implicated in both lipid and carotenoid biosynthesis.