• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.226-226
• /
• 2023

하천유량, 댐유입량 등을 예측하기 위해 다양한 Long Short-Term Memory (LSTM) 방법들이 활발하게 적용 및 개발되고 있다. 최근 연구들은 s2s (sequence-to-sequence), Attention 기법 등을 통해 LSTM의 성능을 개선할 수 있음을 제시하고 있다. 이에 따라 본 연구에서는 LSTM-s2s와 LSTM-s2s에 attention까지 첨가한 모델을 구축하고, 시간 단위 자료를 사용하여 유입량 예측을 수행하여, 이의 실제 댐 운영에 모델들의 활용 가능성을 확인하고자 하였다. 소양강댐 유역을 대상으로 2013년부터 2020년까지의 유입량 시자료와 종관기상관측기온 및 강수량 데이터를 학습, 검증, 평가로 나누어 훈련한 후, 모델의 성능 평가를 진행하였다. 최적 시퀀스 길이를 결정하기 위해 R², RRMSE, CC, NSE, 그리고 PBIAS을 사용하였다. 분석 결과, LSTM-s2s 모델보다 attention까지 첨가한 모델이 전반적으로 성능이 우수했으며, attention 첨가 모델이 첨두값 예측에서도 높은 정확도를 보였다. 두 모델 모두 첨두값 발생 동안 유량 패턴을 잘 반영하였지만 세밀한 시간 단위 변화량 패턴 모의에는 한계가 있었다. 시간 단위 예측의 한계에도 불구하고, LSTM-s2s에 attention까지 추가한 모델은 향후 댐유입량 예측에 활용될 수 있을 것으로 판단한다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.297-300
• /
• 2019

문서 요약은 길이가 긴 원본 문서의 의미는 유지한 채 원본보다 짧은 문서나 문장을 생성하는 자연어 처리 태스크이다. 본 논문에서는 Maximal Marginal Relevance(MMR)를 이용한 sequence-to-sequence 문장 추출 모델을 이용하여 의미가 중복되는 문장을 최소화하는 문장을 추출하고 추출된 문장을 sequence-to-sequence 모델을 통해 요약문을 생성하는 2단계 문서 요약 모델을 제안한다. 실험 결과 MMR을 활용하지 않았던 기존의 방법론보다 Rouge 성능이 향상되었다.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.614-618
• /
• 2016

As information on the internet and the data from smart devices are growing, the amount of stream data is also increasing in the real world. The stream data, which is a potentially large data, requires online learnable models and algorithms. In this paper, we propose a novel class of models: predictive convolutional neural networks to be able to perform online learning. These models are designed to deal with longer patterns as the layers become higher due to layering convolutional operations: detection and max-pooling on the time axis. As a preliminary check of the concept, we chose two-month gathered GPS data sequence as an observation sequence. On learning them with the proposed method, we compared the original sequence and the regenerated sequence from the abstract information of the models. The result shows that the models can encode long-range patterns, and can generate a raw observation sequence within a low error.

• Journal of IKEEE
• /
• v.1 no.1 s.1
• /
• pp.83-92
• /
• 1997

Multipath ATM switch architectures have the potential to accommodate easily the design of high-speed and large capacity ATM switches which can handle a very large amount of switching throughputs. However, the multipath architecture inevitably encounters out-of-sequence problems. We propose a multipath switch model to analyze the out-of-sequence phenomenon. And we analyze the out-of-sequence performance dependency on the architecture parameters : the number of multipath, the trunk utilization, the switch size, and the number virtual channels/trunk. Indexing terms : ATM switch, Multipath archltecture, Out-of-sequence performance, Cell sequence integrity, Analytical model.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.134-140
• /
• 2018

A chat system is a computer program that understands user's miscellaneous utterances and generates appropriate responses. Sometimes a chat system needs to answer users' simple information-seeking questions. However, previous generative chat systems do not consider how to embed knowledge entities (i.e., subjects and objects in triple knowledge), essential elements for question-answering. The previous chat models have a disadvantage that they generate same responses although knowledge entities in users' utterances are changed. To alleviate this problem, we propose a knowledge entity embedding method for improving question-answering accuracies of a generative chat system. The proposed method uses a Siamese recurrent neural network for embedding knowledge entities and their synonyms. For experiments, we implemented a sequence-to-sequence model in which subjects and predicates are encoded and objects are decoded. The proposed embedding method showed 12.48% higher accuracies than the conventional embedding method based on a convolutional neural network.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.542-549
• /
• 2017

Sequence-to-sequence models and similar pointer networks suffer from performance degradation when an input is composed of multiple sentences or when the length of the input sentence is long. To solve this problem, this paper proposes a hierarchical pointer network model that uses both the word level and sentence level information to encode input sequences composed of several sentences at the word level and sentence level. We propose a hierarchical pointer network based coreference resolution that performs a coreference resolution for all mentions. The experimental results show that the proposed model has a precision of 87.07%, recall of 65.39% and CoNLL F1 74.61%, which is an improvement of 21.83% compared to an existing rule-based model.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.127-140
• /
• 2021

Recently, sequence data containing time information, such as sensor measurement data and purchase history, has been generated in various applications. So far, many methods for finding sequences that are significantly different from other sequences among given sequences have been proposed. However, most of them have a limitation that they consider only the order of elements in the sequences. Therefore, in this paper, we propose a new anomalous sequence detection method that considers both the order of elements and the time interval between elements. The proposed method uses an extended LSTM autoencoder model, which has an additional layer that converts a sequence into a form that can help effectively learn both the order of elements and the time interval between elements. The proposed method learns the features of the given sequences with the extended LSTM autoencoder model, and then detects sequences that the model does not reconstruct well as anomalous sequences. Using experiments on synthetic data that contains both normal and anomalous sequences, we show that the proposed method achieves an accuracy close to 100% compared to the method that uses only the traditional LSTM autoencoder.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.176-180
• /
• 2016

대화형 시스템이 사람의 경청 기술을 모방할 수 있다면 대화 상대방과 더 효과적으로 상호작용 할 수 있을 것이다. 본 논문에서는 시스템이 경청 기술을 모방할 수 있도록 사용자의 발화를 기반으로 질문을 생성하는 것에 대해 연구하였다. 그리고 이러한 연구를 위해 필요한 데이터를 Image captioning과 Visual QA 데이터를 기반으로 생성하고 활용하는 방안에 대해 제안한다. 또한 이러한 데이터를 Attention 메커니즘을 적용한 Sequence to sequence 모델에 적용하여 질문을 생성하고, 생성된 질문의 질문 유형을 분석하였다. 마지막으로 사람이 작성한 질문과 모델의 질문 생성 결과 비교를 BLEU 점수를 이용하여 수행하였다.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.176-180
• /
• 2016

대화형 시스템이 사람의 경청 기술을 모방할 수 있다면 대화 상대방과 더 효과적으로 상호작용 할 수 있을 것이다. 본 논문에서는 시스템이 경청 기술을 모방할 수 있도록 사용자의 발화를 기반으로 질문을 생성하는 것에 대해 연구하였다. 그리고 이러한 연구를 위해 필요한 데이터를 Image captioning과 Visual QA 데이터를 기반으로 생성하고 활용하는 방안에 대해 제안한다. 또한 이러한 데이터를 Attention 메커니즘을 적용한 Sequence to sequence 모델에 적용하여 질문을 생성하고, 생성된 질문의 질문 유형을 분석하였다. 마지막으로 사람이 작성한 질문과 모델의 질문 생성 결과 비교를 BLEU 점수를 이용하여 수행하였다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.7 no.3
• /
• pp.11-22
• /
• 1997

The number of output sequence was proposed as a characteristic of binary sequence generators for cryptographic application, but in general most of binary sequence generators have single number of output sequence. In this paper, we propose two types of binary sequence generators with a large number of output sequences. The first one is a Switched-Tap LFSR (STLFSR) and it applies to the generalized nonlinear function and the Geffe's generator as example. The other is a generalized memory sequence generator(GMEM-BSG) which is an improved version of the Golic's memory sequence generator (MEM-BSG) with a large number of output sequences, and its period, linear complexity, and the number of output sequence are derived.