• ETRI Journal
• /
• v.44 no.3
• /
• pp.438-449
• /
• 2022

This study proposes a dependency grammar-based self-attention multilayered bidirectional long short-term memory (DG-M-Bi-LSTM) model for subject-predicate-object (SPO) tuple recognition from natural language (NL) sentences. To add recent knowledge to the knowledge base autonomously, it is essential to extract knowledge from numerous NL data. Therefore, this study proposes a high-accuracy SPO tuple recognition model that requires a small amount of learning data to extract knowledge from NL sentences. The accuracy of SPO tuple recognition using DG-M-Bi-LSTM is compared with that using NL-based self-attention multilayered bidirectional LSTM, DG-based bidirectional encoder representations from transformers (BERT), and NL-based BERT to evaluate its effectiveness. The DG-M-Bi-LSTM model achieves the best results in terms of recognition accuracy for extracting SPO tuples from NL sentences even if it has fewer deep neural network (DNN) parameters than BERT. In particular, its accuracy is better than that of BERT when the learning data are limited. Additionally, its pretrained DNN parameters can be applied to other domains because it learns the structural relations in NL sentences.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.11a
• /
• pp.169-171
• /
• 2007

We need two operation modes to obtain the complex hologram without bias and the conjugate image in the modified triangular interferometer(MTI). To solve the problem, we proposed the optimized MTI with one wave plate, which can obtain cosine and sine functions by the combination of one wave plate and one linear polarizer. In the extraction of phase term using the combination of polarization components, the phase error occurs, and we simulated such potential phase errors in the optimized MTI.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1998.08a
• /
• pp.227-230
• /
• 1998

문헌정보학분야의 용어사전을 이용한 자동시소러스 구축을 위한 첫단계로$\ulcorner$문헌정보학 용어사전$\lrcorner$ MRD를 구성하고 이를 이용하여 상위어 자동 추출알고리즘을 개발하였다. MRD구성시 전처리과정을 통하여 상위어 추출에 불필요한 정보가 수록되는 것을 방지하였다. 상위어 추출을 위한 알고리즘 개발은 무작위 표본추출을 통하여 $\ulcorner$문헌정보학 용어사전$\lrcorner$에 기술된 문장의 구문적 특성을 분석한 후, 이 구문정보를 이용하여 수행하였다. 본 연구에서 제시된 알고리즘의 효율성 평가결과 89.4%의 정확도를 보였다.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.05a
• /
• pp.117-119
• /
• 2007

We need two operation modes to obtain the complex hologram without bias and the conjugate image in the modified triangular interferometer(MTI). To solve the problem, we proposed the optimized MTI with one wave plate, which can obtain cosine and sine functions by the combination of one wave plate and one linear polarizer. In the extraction of phase term using the combination of polarization components, the phase error occurs, and we analyzed such potential phase errors in the optimized MTI.

• Journal of the Optical Society of Korea
• /
• v.11 no.1
• /
• pp.10-17
• /
• 2007

We need two operation modes to obtain the complex hologram without bias and the conjugate image in the modified triangular interferometer (MTI). To solve the problem, we proposed the optimized MTI with one wave plate, which can obtain cosine and sine functions by the combination of one wave plate and one linear polarizer. In the extraction of phase term using the combination of polarization components, the phase error occurs, and we analyzed such potential phase errors in the optimized MTI.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2005.08a
• /
• pp.125-132
• /
• 2005

본 연구는 공공기관에서 생산되는 기록물로서 가장 일반적이고 대표적인 공문서의 장기보존과 접근을 위한 상호운용성을 갖춘 보존 메타데이터 요소를 설정하는데 그 목적이 있다. 구체적으로는 기록물관리 표준인 ISO 15489에서 제안하는 메타데이터 요소와 우리나라의 메타데이터 요소의 비교분석을 통해 전자문서관리시스템의 최고 핵심인 공문서의 보존 메타데이터 항목을 연구하였다. 이는 향후 우리나라 환경에 적합한 표준화된 기록물 보존 메타데이터를 구축하는데 유용한 기초 자료로 활용할 수 있을 것이다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.922-924
• /
• 2004

지식 정보의 확산에 따라 기존 전문분야 용어집에 수록되지 않은 용어의 수가 폭발적으로 증가하고 있다 이에 따라 용어집을 자동으로 구축하는 작업이 필요하게 되었다. 본 논문에서는 의학분야 코퍼스에서 주어진 전문용어에 대한 정의문을 자동으로 추출하는 방법을 제안한다. 우선, 정의문의 구문적 패턴과 용어의 어휘구성 패턴을 이용하여 용어의 상위개념을 추정한다. 상위개념별로 구축된 특성 어휘 목록을 이용하여 구문적 패턴으로 뽑힌 문장에 등장하는 어휘의 적합성 여부를 판단하여 정의문을 추출한다. 실험 결과 코퍼스에 정의 정보가 있는 48개의 용어에 대하여 71.43%의 정확률을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.6
• /
• pp.2612-2633
• /
• 2020

Due to the explosive growth of multimedia speech data, how to protect the privacy of speech data and how to efficiently retrieve speech data have become a hot spot for researchers in recent years. In this paper, we proposed an encrypted speech retrieval scheme based on long short-term memory (LSTM) neural network and deep hashing. This scheme not only achieves efficient retrieval of massive speech in cloud environment, but also effectively avoids the risk of sensitive information leakage. Firstly, a novel speech encryption algorithm based on 4D quadratic autonomous hyperchaotic system is proposed to realize the privacy and security of speech data in the cloud. Secondly, the integrated LSTM network model and deep hashing algorithm are used to extract high-level features of speech data. It is used to solve the high dimensional and temporality problems of speech data, and increase the retrieval efficiency and retrieval accuracy of the proposed scheme. Finally, the normalized Hamming distance algorithm is used to achieve matching. Compared with the existing algorithms, the proposed scheme has good discrimination and robustness and it has high recall, precision and retrieval efficiency under various content preserving operations. Meanwhile, the proposed speech encryption algorithm has high key space and can effectively resist exhaustive attacks.

• Journal of Korean Society of Water and Wastewater
• /
• v.28 no.6
• /
• pp.635-645
• /
• 2014

The changes of rainfall pattern and impervious covers have increased disaster risks in urbanized areas. Impervious covers such as roads and building roofs have been dramatically increased. So, it is falling the ability safety of flood defense equipments to exist. Runoff coefficient means ratio of runoff by whole rainfall which is able to directly contribute at surface runoff during rainfall event. The application of accurate runoff coefficients is very important in sewer pipelines design. This study has been performed to estimate runoff characteristics change which are applicable to the process of sewer pipelines design or various public facilities design. It has used the SHER model, a long-term runoff model, to analyze the impact of a rising impervious covers on runoff coefficient change. It thus analyzed the long-term runoff to analyze rainfall basins extraction. Consequently, it was found that impervious surfaces could be a important factor for urban flood control. We could suggest the application of accurate runoff coefficients in accordance to the land Impervious covers. The average increase rates of runoff coefficients increased 0.011 for 1% increase of impervious covers. By having the application of the results, we could improve plans for facilities design.

• ETRI Journal
• /
• v.42 no.2
• /
• pp.217-229
• /
• 2020

Long-term electroencephalography (EEG) monitoring is time-consuming, and requires experts to interpret EEG signals to detect seizures in patients. In this paper, we propose a novel automated method called adaptive slope of wavelet coefficient counts over various thresholds (ASCOT) to classify patient episodes as seizure waveforms. ASCOT involves extracting the feature matrix by calculating the mean slope of wavelet coefficient counts over various thresholds in each frequency subband. We validated our method using our own database and a public database to avoid overtuning. The experimental results show that the proposed method achieved a reliable and promising accuracy in both our own database (98.93%) and the public database (99.78%). Finally, we evaluated the performance of the method considering various window sizes. In conclusion, the proposed method achieved a reliable seizure detection performance with a short-term window size. Therefore, our method can be utilized to interpret long-term EEG results and detect momentary seizure waveforms in diagnostic systems.