• Electronics and Telecommunications Trends
• /
• v.34 no.2
• /
• pp.73-82
• /
• 2019

Airport is shifted airport 1.0 to airport 4.0 called smart airport and services paradigm is changed into direction to point the customer targeted benefits. Smart airports make use of integrated Internet of Things components to provide added-value services. By integrating smart components, airports are being exposed to a larger attack surface and new attack vectors. Self-services such as web or mobile check-in, self check-in/tagging/back drop/boarding, etc. should be strengthened to make airport processes smarter, and technologies such as automatic immigration, smart security search, and automatic AI-based baggage search should be applied. In this paper, we describe the necessity and importance of smart airports and next generation security screening technology. Further, we describe a walk through-type smart security screening system.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.18
• /
• pp.8351-8358
• /
• 2016

Electronic cleansing is an image post processing technique in which the tagged colonic content is subtracted from colon using CTC images. There are post processing artefacts, like: 1) soft tissue degradation; 2) incomplete cleansing; 3) misclassification of polyp due to pseudo enhanced voxels; and 4) pseudo soft tissue structures. The objective of the study was to subtract the tagged colonic content without losing the soft tissue structures. This paper proposes a novel adaptive method to solve the first three problems using a multi-step algorithm. It uses a new edge model-based method which involves colon segmentation, priori information of Hounsfield units (HU) of different colonic contents at specific tube voltages, subtracting the tagging materials, restoring the soft tissue structures based on selective HU, removing boundary between air-contrast, and applying a filter to clean minute particles due to improperly tagged endoluminal fluids which appear as noise. The main finding of the study was submerged soft tissue structures were absolutely preserved and the pseudo enhanced intensities were corrected without any artifact. The method was implemented with multithreading for parallel processing in a high performance computer. The technique was applied on a fecal tagged dataset (30 patients) where the tagging agent was not completely removed from colon. The results were then qualitatively validated by radiologists for any image processing artifacts.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.358-371
• /
• 2003

Automatic word spacing is a process of deciding correct boundaries between words in a sentence including spacing errors. It is very important to increase the readability and to communicate the accurate meaning of text to the reader. The previous statistical approaches for automatic word spacing do not consider the previous spacing state, and thus can not help estimating inaccurate probabilities. In this paper, we propose two statistical word spacing models which can solve the problem of the previous statistical approaches. The proposed models are based on the observation that the automatic word spacing is regarded as a classification problem such as the POS tagging. The models can consider broader context and estimate more accurate probabilities by generalizing hidden Markov models. We have experimented the proposed models under a wide range of experimental conditions in order to compare them with the current state of the art, and also provided detailed error analysis of our models. The experimental results show that the proposed models have a syllable-unit accuracy of 98.33% and Eojeol-unit precision of 93.06% by the evaluation method considering compound nouns.

• Journal of Information Management
• /
• v.40 no.1
• /
• pp.133-156
• /
• 2009

In this study, we link informal Web resources to KISTI NDSL's collections using automatic semantic indexing and tagging to examine the possibility of the service which recommends related documents using the similarity between KISTI's formal information resources and informal web resources. We collect and index Web resources and make automatic semantic linking through STEAK with KISTI's collections for NDSL retrieval. The macro precision which shows retrieval precision per a subject category is 62.6% and the micro precision which shows retrieval precision per a query is 66.9%. The experts' evaluation score is 76.7. This study shows the possibility of semantic linking NDSL retrieval results with Web information resources and expanding information services' coverage to informal information resources.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.6 no.1
• /
• pp.143-149
• /
• 2010

In ubiquitous environment, information retrieval using collaborative filtering is a popular technique for reducing information overload. Collaborative filtering systems can produce personal recommendations by computing the similarity between your preference and the one of other people. We integrate the collaboration filtering method and context-aware information retrieval method. The proposed method enables to find some relevant information to specific user's contexts. It aims to makes more effective information retrieval to the users. The proposed method is conceptually comprised of two main tasks. The first task is to tag context tags by automatic tagging technique. The second task is to recommend items for each user's contexts integrating collaborative filtering and information retrieval. We describe a new integration method algorithm and then present a u-commerce application prototype.

• Annual Conference on Human and Language Technology
• /
• 1998.10c
• /
• pp.20-27
• /
• 1998

기존의 어휘규칙기반 품사태거는 품사문맥이나 어휘확률만을 사용하는 통계적 품사태거에 의해 해결되지 않는 형태론적 중의성을 어휘문맥을 참조하는 어휘규칙을 사용함으로써 효과적으로 해결할 수 있었다. 그러나 어휘규칙을 수작업으로 획득하기 때문에 규칙 획득에 많은 시간이 소요되어 소량의 규칙만이 사용되었다. 본 논문에서는 품사부착말뭉치로부터 어휘규칙을 자동으로 획득하는 방법을 제안한다. 제안된 방법으로 자동획득된 어휘규칙을 사용하여 실험말뭉치의 66.1%를 98.8%의 정확률로 태깅하였다. 이로써 통계적 품사태거만을 사용할 때(95.43% 정확률) 보다 어휘규칙과 결합할 때(96.12% 정확률) 통계적 품사태거의 성능이 약 15.1%(0.69% 정확률)만큼 향상되었다. 또한 제안된 방법은 영어 품사태깅에 대해서도 효과적임이 실험을 통해 증명되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.01a
• /
• pp.49-50
• /
• 2017

PC 또는 모바일 기기를 이용한 검색을 위해서는 키보드 또는 터치패드를 이용하여 키워드를 입력하는 고전적인 방식이 현재까지 널리 사용되고 있다. 음성, 이미지, 제스처 등을 이용한 새로운 검색 기술들이 등장하고 있지만, 관련 검색엔진의 문제로 검색 결과가 다소 미흡한 상태이다. 본 논문에서는 기존의 포털 검색의 키워드 입력 방식과는 달리, 검색하고자 하는 대상을 스마트폰과 같은 모바일 기기의 카메라로 촬영하면 해당 촬영 이미지가 사용자 입장에서는 검색 키워드와 같이 동일한 역할을 할 수 있도록 CNN기법을 사용하여 Image-to-Text 형태의 모바일 비주얼 검색 서비스에 대해 제안한다.

• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.355-362
• /
• 1994

언어처리에 통계 확률적인 방법이 도입되면서 현실적으로 상당한 진전이 있었지만 한국어의 경우에는 대부분 형태소 해석과 품사 태깅에 그치고 있다. 본 논문에서는 구문분석 수준에서의 통계적인 한국어 분석에 쓰일 자료 구축으로서의 구문 태깅의 방법론과 그 자동화에 대해 보고한다.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.385-393
• /
• 2007

Corpora annotated with lots of linguistic information are required to develop robust and statistical natural language processing systems. Building such corpora, however, is an expensive, labor-intensive, and time-consuming work. To help the work, we design and implement an annotation tool for establishing a Korean dependency tree-tagged corpus. Compared with other annotation tools, our tool is characterized by the following features: independence of applications, localization of errors, powerful error checking, instant annotated information sharing, user-friendly. Using our tool, we have annotated 100,904 Korean sentences with dependency structures. The number of annotators is 33, the average annotation time is about 4 minutes per sentence, and the total period of the annotation is 5 months. We are confident that we can have accurate and consistent annotations as well as reduced labor and time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.179-181
• /
• 2000

한국어의 통사적, 의미적 중의성 해결을 위해 하위범주화 사전을 구축하였다. 용언에 따라 제한될 수 있는 문형 패턴과 의미역(semantic roles) 정보의 표준을 정하여 이를 부가하였고 구축한 하위범주화 사전이 명사에 대한 의미를 갖고 있는 계층 시소러스 의미사전과 연동하도록 용언과 명사와의 의미적 연어 관계에 따라 의미마커를 부여했다. 논문에서 구현된 하위범주화 사전이 구문과 어휘의 중의성을 어느 정도 해소하는지 확인하기 위해 반자동적으로 의미 태깅(Sense Tagging)된 말뭉치와 구문분석된 말뭉치를 통해 검증 작업을 수행했다. 이 과정에서 자동으로 하위범주 패턴에 대한 빈도 정보나, 연어정보, 각 의미역과 용언의 통계적 공기 정보 등을 추출하여 하위범주화사전에 추가시켰다. 또한 여기서 얻은 정보를 기준으로 하위범주화 사전을 자동으로 확장하는 알고리즘을 적용하여 확장시켰다.