• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.12
• /
• pp.562-570
• /
• 2002

The Purpose of this paper is to design and manufacture an educational system in order to demonstrate the causes and effects of electromagnetic induction.'rho educational system described in this study is a "jumping ring apparatus". This system demonstrates the principle of electromagnetic induction, a force from AC sources, Lenz's law of repulsion and transformer. The educational system is composed of a jumping ring apparatus, a sensor array, encoder, A/D converter, D/A converter and nonlinear controller. The educational system is controlled by 586 PC using Turbo C program. The sensor array is composed of 20 optical sensors. The nonlinear controller consists of nonlinear control algorithm and control board included SCR, FET and phase controller. The A/D converter is used to show the height of ring position to analog for an education purpose. The control signal calculated from the nonlinear control of algorithm send control board through 8 bit D/A convertor. Experiment results are given to verify that Proposed nonlinear controller is useful in on line control of the educational system.al system.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1038-1048
• /
• 2021

We propose an end-to-end neural coreference resolution for the Korean language that uses an attention mechanism to point to the same entity. Because Korean is a head-final language, we focused on a method that uses a pointer network based on the head. The key idea is to consider all nouns in the document as candidates based on the head-final characteristics of the Korean language and learn distributions over the referenced entity positions for each noun. Given the recent success of applications using bidirectional encoder representation from transformer (BERT) in natural language-processing tasks, we employed BERT in the proposed model to create word representations based on contextual information. The experimental results indicated that the proposed model achieved state-of-the-art performance in Korean language coreference resolution.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.540-543
• /
• 2021

본 논문에서는 Multi-Head Attention 대신 Spatial Gating Unit을 사용하는 GMLP[1]에 작은 Attention 신경망을 추가한 모델을 구성하여 뉴스와 위키피디아 데이터로 사전학습을 실시하고 한국어 다운스트림 테스크(감성분석, 개체명 인식)에 적용해 본다. 그 결과, 감성분석에서 Multilingual BERT보다 0.27%높은 Accuracy인 87.70%를 보였으며, 개체명 인식에서는 1.6%높은 85.82%의 F1 Score를 나타내었다. 따라서 GMLP가 기존 Transformer Encoder의 Multi-head Attention[2]없이 SGU와 작은 Attention만으로도 BERT[3]와 견줄만한 성능을 보일 수 있음을 확인할 수 있었다. 또한 BERT와 추론 속도를 비교 실험했을 때 배치사이즈가 20보다 작을 때 BERT보다 1에서 6배 정도 빠르다는 것을 확인할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.3-7
• /
• 2019

자연어 표상은 자연어가 가진 정보를 컴퓨터에게 전달하기 위해 표현하는 방법이다. 현재 자연어 표상은 학습을 통해 고정된 벡터로 표현하는 것이 아닌 문맥적 정보에 의해 벡터가 변화한다. 그 중 BERT의 경우 Transformer 모델의 encoder를 사용하여 자연어를 표상하는 기술이다. 하지만 BERT의 경우 학습시간이 많이 걸리며, 대용량의 데이터를 필요로 한다. 본 논문에서는 빠른 자연어 표상 학습을 위해 의미 정보와 BERT를 결합한 개념 언어 모델을 제안한다. 의미 정보로 단어의 품사 정보와, 명사의 의미 계층 정보를 추상적으로 표현했다. 실험을 위해 ETRI에서 공개한 한국어 BERT 모델을 비교 대상으로 하며, 개체명 인식을 학습하여 비교했다. 두 모델의 개체명 인식 결과가 비슷하게 나타났다. 의미 정보가 자연어 표상을 하는데 중요한 정보가 될 수 있음을 확인했다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.543-545
• /
• 2019

본 논문은 최신 한국어 의존 구문 분석 모델(Korean dependency parsing model)들과 다양한 앙상블 모델(ensemble model)들을 결합하여 그 성능을 분석한다. 단어 표현은 미리 학습된 워드 임베딩 모델(word embedding model)과 ELMo(Embedding from Language Model), Bert(Bidirectional Encoder Representations from Transformer) 그리고 다양한 추가 자질들을 사용한다. 또한 사용된 의존 구문 분석 모델로는 Stack Pointer Network Model, Deep Biaffine Attention Parser와 Left to Right Pointer Parser를 이용한다. 최종적으로 각 모델의 분석 결과를 앙상블 모델인 Bagging 기법과 XGBoost(Extreme Gradient Boosting) 이용하여 최적의 모델을 제안한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.367-368
• /
• 2023

최근 챗봇 시스템은 급격한 발전과 함께 사용자와 자연스러운 대화를 할 수 있는 인공지능 기술의 필요성이 대두되고 있다. 기존의 챗봇 시스템은 대화 상황을 충분히 이해하지 못하거나, 학습된 데이터를 벗어나는 문장에 대한 일관성 있는 응답을 제공하지 못하는 한계가 있다. 본 논문에서는 GPT-3와 KoBERT를 활용하여 사용자의 감정 상태를 파악하고 해당 감정을 고려한 일관성 있는 대화를 제공하는 감정 분석 기반 챗봇 시스템을 제안한다. 이를 바탕으로 긍정적인 대화를 이어 나가는데 초점을 두어 자연스러운 대화가 가능할 것으로 기대된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.81-83
• /
• 2023

GIT의 커밋 메시지를 소프트웨어 유지보수 활동 세 가지로 분류하는 연구를 분석하고 정확도를 높일 수 있는 모델들을 분석하였고 관련 모델 중 커밋메시지와 변경된 소스를 같이 활용하는 연구들은 변경된 소스를 분석하기 위해 도구들을 대부분 활용하는데 대부분 특정 언어만 분류할 수 있는 한계가 있다. 본 논문에서는 소스 변경 데이터를 추출할 때 언어의 제약을 없애기 위해 GPT를 이용해 변경된 소스의 요약을 추출하는 과정을 추가함으로써 언어 제약의 한계를 극복할 수 있는 개선된 모델에 관한 연구를 진행하였다. 향후 본 연구 모델의 구현 및 검증을 진행하고 이를 이용해 프로젝트 진행에 활용할 수 있는 솔루션 개발 연구까지 확정해 나갈 예정이다.

• The Journal of Society for e-Business Studies
• /
• v.27 no.1
• /
• pp.15-28
• /
• 2022

Due to recent expansion of online market such as clothing, utilizing customer review has become a major marketing measure. User review has been used as a tool of analyzing sentiment of customers. Sentiment analysis can be largely classified with machine learning-based and lexicon-based method. Machine learning-based method is a learning classification model referring review and labels. As research of sentiment analysis has been developed, multi-modal models learned by images and video data in reviews has been studied. Characteristics of words in reviews are differentiated depending on products' and customers' categories. In this paper, sentiment is analyzed via considering review data and metadata of products and users. Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Self Attention-based Multi-head Attention models and Bidirectional Encoder Representation from Transformer (BERT) are used in this study. Same Multi-Layer Perceptron (MLP) model is used upon every products information. This paper suggests a multi-modal sentiment analysis model that simultaneously considers user reviews and product meta-information.

• Phonetics and Speech Sciences
• /
• v.12 no.4
• /
• pp.63-71
• /
• 2020

Speech recognition is one of the areas actively commercialized using deep learning and machine learning techniques. However, the majority of speech recognition systems on the market are developed on data with limited diversity of speakers and tend to perform well on typical adult speakers only. This is because most of the speech recognition models are generally learned using a speech database obtained from adult males and females. This tends to cause problems in recognizing the speech of the elderly, children and people with dialects well. To solve these problems, it may be necessary to retain big database or to collect a data for applying a speaker adaptation. However, this paper proposes that a new end-to-end speech recognition method consists of an acoustic augmented recurrent encoder and a transformer decoder with linguistic prediction. The proposed method can bring about the reliable performance of acoustic and language models in limited data conditions. The proposed method was evaluated to recognize Korean elderly and children speech with limited amount of training data and showed the better performance compared of a conventional method.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.613-626
• /
• 2022

Guaranteeing the quality and integrity of structural health monitoring (SHM) data is very important for an effective assessment of structural condition. However, sensory system may malfunction due to sensor fault or harsh operational environment, resulting in multiple types of data anomaly existing in the measured data. Efficiently and automatically identifying anomalies from the vast amounts of measured data is significant for assessing the structural conditions and early warning for structural failure in SHM. The major challenges of current automated data anomaly detection methods are the imbalance of dataset categories. In terms of the feature of actual anomalous data, this paper proposes a data anomaly detection method based on data-level and deep learning technique for SHM of civil engineering structures. The proposed method consists of a data balancing phase to prepare a comprehensive training dataset based on data-level technique, and an anomaly detection phase based on a sophisticatedly designed network. The advanced densely connected convolutional network (DenseNet) and Transformer encoder are embedded in the specific network to facilitate extraction of both detail and global features of response data, and to establish the mapping between the highest level of abstractive features and data anomaly class. Numerical studies on a steel frame model are conducted to evaluate the performance and noise immunity of using the proposed network for data anomaly detection. The applicability of the proposed method for data anomaly classification is validated with the measured data of a practical supertall structure. The proposed method presents a remarkable performance on data anomaly detection, which reaches a 95.7% overall accuracy with practical engineering structural monitoring data, which demonstrates the effectiveness of data balancing and the robust classification capability of the proposed network.