• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.470-474
• /
• 2019

한글 OCR 성능을 높이기 위해 딥러닝 모델을 활용하여 문자인식 부분을 개선하고자 하였다. 본 논문에서는 폰트와 사전데이터를 사용해 딥러닝 모델 학습을 위한 한글 문장 이미지 데이터를 직접 생성해보고 이를 활용해서 한글 문장의 OCR 성능을 높일 다양한 모델 조합들에 대한 실험을 진행했다. 딥러닝 모델은 STR(Scene Text Recognition) 구조를 사용해 변환, 추출, 시퀀스, 예측 모듈 각 24가지 모델 조합을 구성했다. 딥러닝 모델을 활용한 OCR 실험 결과 한글 문장에 적합한 모델조합은 변환 모듈을 사용하고 시퀀스와 예측 모듈에는 BiLSTM과 어텐션을 사용한 모델조합이 다른 모델 조합에 비해 높은 성능을 보였다. 해당 논문에서는 이전 한글 OCR 연구와 비교해 적용 범위를 글자 단위에서 문장 단위로 확장하였고 실제 문서 이미지에서 자주 발견되는 유형의 데이터를 사용해 애플리케이션 적용 가능성을 높이고자 한 부분에 의의가 있다.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• The KIPS Transactions:PartD
• /
• v.16D no.4
• /
• pp.541-548
• /
• 2009

Many companies have recently apply SLA and execute IT service by using SLA. However, there are no objective standards for selection and improvement of SLA evaluation metrics. We derive and present measurement attributes that are criteria for selection and improvement of SLA evaluation metrics as measurement metrics. We execute a case study based on D company in order to verify whether the measurement metrics are applicable. We apply and evaluate the measurement metrics that are applicable to D company, and then we designate an improvement line. We propose improvement guidelines of the measurement metrics which score is less than the improvement line's and derive SLA evaluation metrics. We prove that the way of selection and improvement is useful by applying SLA evaluation metrics to D company.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.11 no.2
• /
• pp.103-114
• /
• 2013

The Korea Atomic Energy Research Institute has developed a performance assessment model implementing the A-KRS concept, which was constructed with the GoldSim. In the A-KRS concept, spent nuclear fuel produced from pressurized-water-reactor operations would be pyroprocessed to reduce waste volume and radioactivity. The wastes to be disposed of in a geologic repository are comprised of metal and ceramic waste forms. In this study, results of simulations conducted to establish credibility and build confidence for the A-KRS model are presented. Specifically, release rates and breakthrough times simulated using the A-KRS model were compared to corresponding results from the U.S. NRC SOAR model. In addition, the A-KRS model results were compared to published release rates from the SKB repository performance assessment. This comparison of the A-KRS model results to other independent performance assessments is expected to form part of a suite of model verification and validation activities to provide confidence that the A-KRS model has been implemented appropriately.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.5
• /
• pp.39-49
• /
• 2017

A Space Launch Vehicle (SLV) for Launching Satellites Consists of Multi-stage Rockets for the Purpose of Efficient Flight and Accomplishes the Launch Mission through Flight Events such as Stage Separation, Engine Start and Stop. In this Process, the SLV is Supposed to Undergo the Processes of the Powered Flight Section in which the Engine Generates Thrust and the Ballistic Flight Section in which there is no Thrust Repeatedly. Because it is Difficult to Express these Flight Characteristics of the SLV as a Single Dynamics Model, much Research on Tracking Algorithms using Multiple Models has been Undertaken. In case of using the Multiple Model Tracking Algorithm, it is Expected to Improve the Tracking Performance of the SLV. However, it is Difficult to Select Proper Dynamics Models to be used and the Calculation Amount Increases due to the use of Multiple Models. In this Paper, we Propose a Method to Track the SLV with Diverse Flight Characteristics Efficiently by only Two Kalman Filters using Constant Acceleration Model and Adaptive Singer Model.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.225-233
• /
• 2011

Stock market prices, economic indices, trends and changes of social phenomena, etc. are categorized as time series data. Research on time series data has been prevalent for a while as it could not only lead to valuable representation of data but also provide future trends as well as changes in direction. We take a conventional model based approach, known as Markov chain modeling for the prediction on stock market prices. To improve prediction accuracy, we apply Markov modeling over carefully selected intervals of training data to fit the trend under consideration to the model. Another method we take is to apply clustering to data and build models of the resultant clusters. We confirmed that clustered models are better off in predicting, however, with the loss of prediction rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.196-198
• /
• 2003

본 논문에서는 스네이크 모델의 에너지 최소화 알고리즘을 개선하여 속도와 정확도에 대한 문제를 해결한다. 개선된 알고리즘은 스네이크를 이루는 정점들의 적합성에 따라 탐색 윈도우를 가변적으로 확장시킴으로써 빠르고 정확하게 윤곽선을 추출한다. 또한 정점의 정렬과정을 통해 정점이 지역적 최소점에 빠지는 것을 방지하며 스네이크의 연속성과 완만성을 보존한다.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1999.05a
• /
• pp.152-152
• /
• 1999

• Review of KIISC
• /
• v.5 no.3
• /
• pp.49-68
• /
• 1995

X.500 디렉토리 표준은 전세계적인 규모의 정보통신망을 상호 연결하여 다목적 분산 디렉토리 서비스를 구축하기 위한 기초를 제공한다. 본래의 디렉토리 표준'은 ITU에서 1988년 X.500시리즈로 발표되었고, 1992년에 확장 개선된 표준이 제정되어 계속 그 적용 분야를 넓혀가고 있다. 본 고에서는 디렉토리 모델에 대한 일반적 기능을 살펴보고 인증 골격과 액세스 제어를 중심으로 한 정보보호 서비스에 관하여 고찰하였다.

• Journal of Applied Biological Chemistry
• /
• v.64 no.3
• /
• pp.299-307
• /
• 2021

Accumulation of amyloid beta (Aβ) and oxidative stress are the most common reason of Alzheimer's disease (AD). In the present study, we investigated the cognitive improvement effects of butanol (BuOH) fraction from Momordica charantia in Aβ_25-35-induced AD mouse model. To develop an AD mouse model, mice were received injection of Aβ_25-35, and then orally administered BuOH fraction from M. charantia at doses of 100 and 200 mg/kg/day during 14 days. In the T-maze and novel object recognition test, administration of BuOH fraction from M. charantia L. at doses of 100 and 200 mg/kg/day improved spatial ability and novel object recognition by increased explorations of novel route and new object. In addition, BuOH fraction of M. charantia-administered groups improved learning and memory abilities by decreased time to reach hidden platform in Morris water maze test. Oral administration of BuOH fraction from M. charantia significantly inhibited lipid peroxidation and nitric oxide levels in the brain, liver, and kidney compared with Aβ_25-35-induced control group. These results indicated that BuOH fraction of M. charantia improved Aβ_25-35-induced cognitive impairment by attenuating oxidative stress. Therefore, M. charantia could be useful for protection from Aβ_25-35-induced cognitive impairment.