• The Journal of the Korea Contents Association
• /
• v.7 no.2
• /
• pp.73-83
• /
• 2007

An information retrieval system, using exact match, needs preprocessing or query expansion to generate transliteration variants in order to search foreign word transliteration variants in the documents. This paper proposes an effective method to generate other transliteration variants from a given transliteration. Because simple rewriting of confused characters produces too many false variants, the proposed method controls the generation priority by learning confusion patterns from real uses and calculating their probability. Especially, the left and right context of a pattern is considered, and local rewriting probability and global rewriting probability are calculated to produce more probable variants in earlier stage. The experimental result showed that the method was very effective by showing more than 80% recall with top 20 generations for a transliteration variants set collected from KT SET 2.0.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.25-30
• /
• 2018

Recently with the development of Internet technology, a lot of research area such as retrieval and extracting data have getting important for providing the information efficiently and quickly. Especially, the technique of analyzing and finding the semantic similar words for given korean word such as compound words or generated newly is necessary because it is not easy to catch the meaning or semantic about them. To handle of this problem, word clustering is one of the technique which is grouping the similar words of given word. In this paper, we proposed the korean language clustering technique that clusters the similar words by embedding the words using Word2Vec from the given documents.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1037-1045
• /
• 1996

In this paper, the parallel model for stereo camera is employed to find the heralding angle and the distance between a leading vehicle and the following vehicle, BART(Binocular Autonomous Research Team vehicle). Two TDNNs (Time Delay Neural Network) such as S-TDNN and A-TDNN are introduced to control BART. S-TDNN controls the speed of the following vehicle while A-TDNN controls the steering angle of BATR. A human drives BART to collect data which are used for training the said neural networks. The trained networks performed the vehicle tracking function satisfactorily under the same driving conditions performed by the human driver. The neural network approach has good portability which decreases costs and saves development time for the different types of vehicles.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.2
• /
• pp.229-236
• /
• 1995

The conceptual world of sentence is composed f substantives(nouns) and verbal. The verbal is a semantic center of sentence, the substantives are placed under control of verbal, and they are combined in a various way. In this paper, the structural relation of verbal and substantives are analyzed and the phrase unit sentence which is derived from the result of morphological analysis is interpreted by a variable pattern net. This variable pattern net analyzes the phrases syntactically and semantically and extracts conceptual units of clausal form. This paper expands the traditionally restricted Horn clause theory to the general sentence, separates a simple sentence from a complex sentence automatically, constructs knowledge base by clausal form of logical conceptual units, and applies it to a question-answering system.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.620-628
• /
• 2020

Automatically predicting video highlight is an important task for media industry and streaming platform providers to save time and cost of manual video editing process. We propose a new ensemble model that combines multiple highlight detectors with each focusing on different parts of highlight events. Therefore, our model can capture more information-rich sections of events. Furthermore, the proposed model can extract improved features for highlight detection particularly when the train video set is small. We evaluate our model on e-sports and baseball videos.

• Journal of Korean Society for Geospatial Information Science
• /
• v.5 no.2 s.10
• /
• pp.99-110
• /
• 1997

Image matching to determine the conjugate points in stereo photos is the one of the most important subject in digital photogrammetry and many researches In digital photogrammetric field are on going to automate the image matching process. In this study, we analyzes the effect of allowable correlation coefficient, which controls the accuracy in areal based image matching, on the accuracy of digital photogrammetry. So, some areal based matching methods such as image correlation coefficient matching, image Pyramid matching and interest point matching, are implemented, and the effect of allowable correlation coefficient on accuracy of digital photogrammetry in each method is analyzed. As a result of this study, a method to determine the optimal correlation coefficient is presented.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.482-486
• /
• 2008

본 논문에서는 하드 디스크 드라이브(Hard Disk Drive, HDD) 생산 공정 과정에서 발생할 수 있는 불량 HDD의 결함 분포에 대해서 패턴을 자동으로 분류해주는 기법을 제시한다. 이를 위해서 표준 패턴 클래스로 분류되어 있는 불량 HDD의 각 클래스의 확률 모델을 GMM(Gaussian Mixture Model)로 가정한다. 실험은 전문가에 의해 분류된 실제 HDD 결함 분포로부터 5가지의 특징 값들을 추출한 후, 결함 분포의 클래스를 표현할 수 있는 GMM의 파라미터(Parameter)를 학습한다. 각 모델의 파라미터를 추정하기 위해 EM(Expectation Maximization) 알고리즘을 사용한다. 학습된 GMM의 분류 테스트는 학습에 사용되지 않은 HDD 결함 분포에서 5가지의 특징 값을 입력 값으로 추정된 모델들의 파라미터 값에 의해 사후 확률을 구한다. 계산된 확률 값 중 가장 큰 값을 갖는 모델의 클래스를 표준 패턴 클래스로 분류한다. 그 결과 제시된 GMM을 이용한 HDD의 패턴 분류의 결과 96.1%의 정답률을 보여준다.

• The Journal of Natural Sciences
• /
• v.8 no.1
• /
• pp.101-107
• /
• 1995

The purpose of this work is to develop automatic techniques for converting linear, paper-based documents to a non-linear format suitable for use in hypertext systems. The selected document was partially converted to hypertext manually, and a prototype was created using the rules derived from the manual conversion process. The full conversion was divided into three passes: correcting the electronic linear form of the document, generating a listing of the links in the document, and creating the hypertext document. Passes 2 and 3 were entirely automatic. From this study, it may be concluded that many classes of paper-based documents can be automatically converted to hypertext.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.164-168
• /
• 2007

In this paper, we propose the eye detection algorithms which can apply to the Real-Time Embedded systems. To detect the eye region, the feature vectors are obtained at the first step and then, PCA(Principal Component Analysis) and amplitude projection method is applied to composite the feature vectors. In the decision state, the estimated probability density functions (PDFs) are applied by the proposed Bayesian method to detect eye region in an image from the CCD camera. The simulation results show that our proposed method has a good detection rate on the frontal face and this can be applied to the embedded system because of its small amount of the mathematical complexity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.5 no.2
• /
• pp.371-384
• /
• 2001

In these days, it is continuously increased to the intrusion of system in internet environment. The methods of intrusion detection can be largely classified into anomaly detection and misuse detection. The former uses statistical methods, features selection method in order to detect intrusion, the latter uses conditional probability, expert system, state transition analysis, pattern matching. The existing studies for IDS(intrusion detection system) use combined methods. In this paper, we propose a new intrusion detection algorithm combined both state transition analysis and association mining techniques. For the intrusion detection, the first step is generated state table for transmitted commands through the network. This method is similar to the existing state transition analysis. The next step is decided yes or no for intrusion using the association mining technique. According to this processing steps, we present the automated generation algorithm of the penetration scenarios.