• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.5
• /
• pp.505-511
• /
• 2023

In the present study, a deep learning model was established to predict the motion response of small fishing vessels. Hydrodynamic performances were evaluated for two small fishing vessels for the dataset of deep learning model. The deep learning model of the Long Short-Term Memory (LSTM) which is one of the recurrent neural network was utilized. The input data of LSTM model consisted of time series of six(6) degrees of freedom motions and wave height and the output label was selected as the time series data of six(6) degrees of freedom motions. The hyperparameter and input window length studies were performed to optimize LSTM model. The time series motion response according to different wave direction was predicted by establised LSTM. The predicted time series motion response showed good overall agreement with the analysis results. As the length of the time series increased, differences between the predicted values and analysis results were increased, which is due to the reduced influence of long-term data in the training process. The overall error of the predicted data indicated that more than 85% of the data showed an error within 10%. The established LSTM model is expected to be utilized in monitoring and alarm systems for small fishing vessels.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.11-18
• /
• 2022

De novo drug design is the process of developing new drugs that can interact with biological targets such as protein receptors. Traditional process of de novo drug design consists of drug candidate discovery and drug development, but it requires a long time of more than 10 years to develop a new drug. Deep learning-based methods are being studied to shorten this period and efficiently find chemical compounds for new drug candidates. Many existing deep learning-based drug design models utilize recurrent neural networks to generate a chemical entity represented by SMILES strings, but due to the disadvantages of the recurrent networks, such as slow training speed and poor understanding of complex molecular formula rules, there is room for improvement. To overcome these shortcomings, we propose a deep learning model for SMILES string generation using variational autoencoders with self-attention mechanism. Our proposed model decreased the training time by 1/26 compared to the latest drug design model, as well as generated valid SMILES more effectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.201-211
• /
• 2022

According to the recent change in the cybersecurity paradigm, research on anomaly detection methods using machine learning and deep learning techniques, which are AI implementation technologies, is increasing. In this study, a comparative study on data preprocessing techniques that can improve the anomaly detection performance of a GRU (Gated Recurrent Unit) neural network-based intrusion detection model using NGIDS-DS (Next Generation IDS Dataset), an open dataset, was conducted. In addition, in order to solve the class imbalance problem according to the ratio of normal data and attack data, the detection performance according to the oversampling ratio was compared and analyzed using the oversampling technique applied with DCGAN (Deep Convolutional Generative Adversarial Networks). As a result of the experiment, the method preprocessed using the Doc2Vec algorithm for system call feature and process execution path feature showed good performance, and in the case of oversampling performance, when DCGAN was used, improved detection performance was shown.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.771-781
• /
• 2019

We propose the VS³-NET model to solve the task of question answering questions with machine-reading comprehension that searches for an appropriate answer in a given context. VS³-NET is a model that trains latent variables for each question using variational inferences based on a model of a simple recurrent unit-based sentences and self-matching networks. The types of questions vary, and the answers depend on the type of question. To perform efficient inference and learning, we introduce neural question-type models to approximate the prior and posterior distributions of the latent variables, and we use these approximated distributions to optimize a reparameterized variational lower bound. The context given in machine-reading comprehension usually comprises several sentences, leading to performance degradation caused by context length. Therefore, we model a hierarchical structure using sentence encoding, in which as the context becomes longer, the performance degrades. Experimental results show that the proposed VS³-NET model has an exact-match score of 76.8% and an F1 score of 84.5% on the SQuAD test set.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.674-679
• /
• 2017

In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.712-715
• /
• 1997

In image jacobian based visual servoing, generally, inverse jacobian should be calculated by complicated coordinate transformations. These are required excessive computation and the singularity of the image jacobian should be considered. This paper presents a visual servoing to control the pose of the robotic manipulator for tracking and grasping 3-D moving object whose pose and motion parameters are unknown. Because the object is in motion tracking and grasping must be done on-line and the controller must have continuous learning ability. In order to estimate parameters of a moving object we use the kalman filter. And for tracking and grasping a moving object we use a fuzzy inference based reinforcement learning algorithm of dynamic recurrent neural networks. Computer simulation results are presented to demonstrate the performance of this visual servoing

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.47-50
• /
• 2017

문서 요약은 입력 문서가 가진 주제를 유지하면서 크기가 축약된 새로운 문서를 생성하는 것이다. 문서 요약의 방법론은 크게 추출 요약과 추상 요약으로 구분된다. 추출 요약의 경우 결과가 문서 전체를 충분히 대표하지 못하거나 문장들 간의 호응이 떨어지는 문제점이 있다. 최근에는 순환 신경망 구조의 모델을 이용한 추상 요약이 활발히 연구되고 있으나, 이러한 방법은 입력이 길어지는 경우 정보가 누락된다는 문제점을 가지고 있다. 본 논문에서는 이러한 단점들을 해소하기 위해 추출 요약으로 입력 문서의 중요한 일부 문장들을 선별하고 이를 추상 요약의 입력으로 사용했을 때의 성능 변화를 관찰한다. 추출 요약을 통해 원문 대비 30%까지 문서를 요약한 후 요약을 생성했을 때, ROUGE-1 0.2802, ROUGE-2 0.1294, ROUGE-L 0.3254의 성능을 보였다.

• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.321-323
• /
• 2016

최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.892-895
• /
• 2017

본 논문에서는 비분할 비디오로부터 이 비디오에 담긴 사람의 행동을 효과적으로 탐지해내기 위한 심층 신경망 모델을 제안한다. 일반적으로 비디오에서 사람의 행동을 탐지해내는 작업은 크게 비디오에서 행동 탐지에 효과적인 특징들을 추출해내는 과정과 이 특징들을 토대로 비디오에 담긴 행동을 탐지해내는 과정을 포함한다. 본 논문에서는 특징 추출 과정과 행동 탐지 과정에 이용할 심층 신경망 모델을 제시한다. 특히 비디오로부터 각 행동별 시간적, 공간적 패턴을 잘 표현할 수 있는 특징들을 추출해내기 위해서는 C3D 및 I-ResNet 합성곱 신경망 모델을 이용하고, 시계열 특징 벡터들로부터 행동을 자동 판별해내기 위해서는 양방향 BI-LSTM 순환 신경망 모델을 이용한다. 대용량의 공개 벤치 마크 데이터 집합인 ActivityNet 비디오 데이터를 이용한 실험을 통해, 본 논문에서 제안하는 심층 신경망 모델의 성능과 효과를 확인할 수 있었다.