• Journal of the Korean Institute of Gas
• /
• v.3 no.2 s.7
• /
• pp.34-42
• /
• 1999

The discrete variables such as time and sequence must be considered for automating HAZOP analysis of batch processes in contrast with continuous processes. Because these variables can not be explained by the method used in the HAZOP analysis of continuous processes, we have developed the methodology for HAZOP analysis of batch processes on the basis of the relation between discrete variables and continuous ones. In this study, we have discussed the performance of the methodology on a Latex batch process to evaluate its effectiveness.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.143-146
• /
• 2017

심층학습 모델 중 LSTM-CRF는 개체명 인식, 품사 태깅과 같은 sequence labeling에서 우수한 성능을 보이고 있다. 한국어 개체명 인식에 대해서도 LSTM-CRF 모델을 기본 골격으로 단어, 형태소, 자모음, 품사, 기구축 사전 정보 등 다양한 정보와 외부 자원을 활용하여 성능을 높이는 연구가 진행되고 있다. 그러나 이런 방법은 언어 자원과 성능이 좋은 자연어 처리 모듈(형태소 세그먼트, 품사 태거 등)이 없으면 사용할 수 없다. 본 논문에서는 LSTM-CRF와 최소한의 언어 자원을 사용하여 다국어에 대한 개체명 인식에 대한 성능을 평가한다. LSTM-CRF의 입력은 문자 기반의 n-gram 표상으로, 성능 평가에는 unigram 표상과 bigram 표상을 사용했다. 한국어, 일본어, 중국어에 대해 개체명 인식 성능 평가를 한 결과 한국어의 경우 bigram을 사용했을 때 78.54%의 성능을, 일본어와 중국어는 unigram을 사용했을 때 각 63.2%, 26.65%의 성능을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.143-146
• /
• 2017

심층학습 모델 중 LSTM-CRF는 개체명 인식, 품사 태깅과 같은 sequence labeling에서 우수한 성능을 보이고 있다. 한국어 개체명 인식에 대해서도 LSTM-CRF 모델을 기본 골격으로 단어, 형태소, 자모음, 품사, 기구축 사전 정보 등 다양한 정보와 외부 자원을 활용하여 성능을 높이는 연구가 진행되고 있다. 그러나 이런 방법은 언어 자원과 성능이 좋은 자연어 처리 모듈(형태소 세그먼트, 품사 태거 등)이 없으면 사용할 수 없다. 본 논문에서는 LSTM-CRF와 최소한의 언어 자원을 사용하여 다국어에 대한 개체명 인식에 대한 성능을 평가한다. LSTM-CRF의 입력은 문자 기반의 n-gram 표상으로, 성능 평가에는 unigram 표상과 bigram 표상을 사용했다. 한국어, 일본어, 중국어에 대해 개체명 인식 성능 평가를 한 결과 한국어의 경우 bigram을 사용했을 때 78.54%의 성능을, 일본어와 중국어는 unigram을 사용했을 때 각 63.2%, 26.65%의 성능을 보였다.

• Journal of KIISE:Software and Applications
• /
• v.27 no.4
• /
• pp.357-369
• /
• 2000

SMIL(Synchronized Multimedia integration Language) allows integrating a set of independent multimedia objects into a synchronized multimedia presentation. In this paper, I propose modeling rules, formal models, modeling function and an algorithm for SMIL documents using use case diagram and sequence diagram of UML(Unified Modeling Language), It will be used the use case diagram and collaboration diagram for object-oriented visualizing tool to describe the temporal behavior of the presentation. The main contribution of this paper is that developers of SMIL documents easily generate them using this rules and algorithm. And, the formal models and modeling functions provide an environment for processing object-oriented documents.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.23 no.6
• /
• pp.642-649
• /
• 2015

Resistance Spot Welding (RSW) is the method for joining two overlapped base materials when high pressure and current is applied from electrodes. Due to the safety problem such high pressure and voltage, automation should be early adopted. In this paper, the spot welding is developed as a computational model of wheel house from GM Korea and the welding condition such as weld sequence is considered. The computational analysis is preceded as a static and elasto-plastic procedure and used thermal expansion coefficient represents a dependency of spot volume between two panels. In case of welding sequence, the efficiency which depends on the distance between current spot point and the other is calculated in several cases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.7
• /
• pp.1661-1666
• /
• 2010

Due to light condition or shadow around camera, acquired image sequence is often degraded by intensity fluctuation. This artifact is called luminance flicker. As the luminance flicker corrupts the performance of motion estimation or object detection, it should be corrected before further processing. In this paper, we analyze the flicker generation model and propose the new algorithm for flicker reduction. The proposed algorithm considers gain and offset parameter separately, and stabilizes the luminance fluctuation based on these parameters. We show the performance of the proposed method by testing on the sequence with artificially added luminance flicker and real sequence with object motion.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.120-125
• /
• 2018

문서 요약 문제는 최근 심층 신경망을 활용하여 활발히 연구되고 있는 문제 중 하나이다. 많은 기존 연구들이 주로 시퀀스-투-시퀀스 모델을 활용하여 요약을 수행하고 있으나, 아직 양질의 요약을 생성하기에는 많은 문제점이 있다. 시퀀스-투-시퀀스 모델을 활용한 요약에서 가장 빈번히 나타나는 문제 중 하나는 요약문의 생성과정에서 단어나 구, 문장이 불필요하게 반복적으로 생성되는 것이다. 이를 해결하기 위해 다양한 연구가 이루어지고 있으며, 이들 대부분은 요약문의 생성 과정에서 정확한 정보를 주기 위해 모델에 여러 모듈을 추가하였다. 하지만 기존 연구들은 생성 단어가 정답 단어로 나올 확률을 최대화 하도록 학습되기 때문에, 생성하지 말아야 하는 단어에 대한 학습이 부족하여 반복 생성 문제를 해결하는 것에는 한계가 있다. 따라서 본 논문에서는 기존 요약 모델의 복잡도를 높이지 않고, 단어 생성 이력을 직접적으로 이용하여 반복 생성을 제어하는 모델을 제안한다. 제안한 모델은 학습할 때 생성 단계에서 이전에 생성한 단어가 이후에 다시 생성될 확률을 최소화하여 실제 모델이 생성한 단어가 반복 생성될 확률을 직접적으로 제어한다. 한국어 데이터를 이용하여 제안한 방법을 통해 요약문을 생성한 결과, 비교모델보다 단어 반복이 크게 줄어들어 양질의 요약을 생성하는 것을 확인할 수 있었다.

• Journal of Broadcast Engineering
• /
• v.14 no.3
• /
• pp.299-310
• /
• 2009

In this paper, we proposed a new method to correct the zoom lens distortion for the video sequence captured by the zoom lens. First, we defined the nonlinear zoom lens distortion model which is represented by the focal length and the lens distortion using the characteristic that lens distortion parameters are nonlinearly and monotonically changed while the focal length is increased. Then, we chose some sample images from the video sequence and estimated a focal length and a lens distortion parameter for each sample image. Using these estimated parameters, we were able to optimize the zoom lens distortion model. Once the zoom lens distortion model was obtained, lens distortion parameters of other images were able to be computed as their focal lengths were input. The proposed method has been made experiments with many real images and videos. As a result, accurate distortion parameters were estimated from the zoom lens distortion model and distorted images were well corrected without any visual artifacts.

• The KIPS Transactions:PartD
• /
• v.8D no.5
• /
• pp.553-560
• /
• 2001

Bioinformatics is a discipline to support biological experiment projects by storing, managing data arising from genome research. In can also lead the experimental design for genome function prediction and regulation. Among various approaches of the genome research, the proteomics have been drawing increasing attention since it deals with the final product of genomes, i.e., proteins, directly. This paper proposes a data mining technique to predict the structural characteristics of a given protein group, one of dominant factors of the functions of them. After explains associations among amino acid subsequences in the primary structures of proteins, which can provide important clues for determining secondary or tertiary structures of them, it defines a sequence association rule to represent the inter-subsequences. It also provides support and confidence measures, newly designed to evaluate the usefulness of sequence association rules, After is proposes a method to discover useful sequence association rules from a given protein group, it evaluates the performance of the proposed method with protein sequence data from the SWISS-PROT protein database.