• Journal of KIISE:Software and Applications
• /
• v.33 no.4
• /
• pp.440-448
• /
• 2006

Self-Organizing Map (SOM) is an unsupervised learning neural network and it is used for preserving the structural relationships in the data without prior knowledge. SOM has been applied in the study of complex problems such as vector quantization, combinatorial optimization, and pattern recognition. This paper proposes a new usage of SOM as a tool for schema transformation hoping to achieve more efficient genetic process. Every offspring is transformed into an isomorphic neural network with more desirable shape for genetic search. This helps genes with strong epistasis to stay close together in the chromosome. Experimental results showed considerable improvement over previous results.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.425-429
• /
• 2018

지식 그래프는 많은 수의 개채와 이들 사이의 관계를 저장하고 있기 때문에 많은 연구에서 중요한 자원으로 활용된다. 최근에는 챗봇과 질의응답과 같은 연구에서 자연어 생성을 위한 연구에 활용되고 있다. 특히 자연어 생성에서 최근 발전 된 심층 신경망이 사용되고 있는데, 이러한 방식은 모델 학습을 위한 많은 양의 데이터가 필요하다. 즉, 심층신경망을 기반으로 지식 그래프에서 문장을 생성하기 위해서는 많은 트리플과 문장 쌍 데이터가 필요하지만 학습을 위해 사용하기엔 데이터가 부족하다는 문제가 있다. 따라서 본 논문에서는 데이터 부족 문제를 해결하기 위해 핵심어 시퀀스를 추출하여 학습하는 방법을 제안하고, 학습된 모델을 통해 트리플을 입력으로 하여 자연어 문장을 생성한다. 부족한 트리플과 문장 쌍 데이터를 대체하기 위해 핵심어 시퀀스를 추출하는 모듈을 사용해 핵심어 시퀀스와 문장 쌍 데이터를 생성하였고, 순환 신경망 기반의 인코더 - 디코더 모델을 사용해 자연어 문장을 생성하였다. 실험 결과, 핵심어 시퀀스와 문장 쌍 데이터를 이용해 학습된 모델을 이용해 트리플에서 자연어 문장 생성이 원활히 가능하며, 부족한 트리플과 문장 쌍 데이터를 대체하는데 효과적임을 밝혔다.

• Geophysics and Geophysical Exploration
• /
• v.26 no.3
• /
• pp.126-137
• /
• 2023

In this study, a recurrent neural network (RNN) was employed as a methodological approach to classify dolphin click signals derived from ocean monitoring data. To improve the accuracy of click signal classification, the single time series data were transformed into fractional domains using fractional Fourier transform to expand its features. Transformed data were used as input for three RNN models: long short-term memory (LSTM), gated recurrent unit (GRU), and bidirectional LSTM (BiLSTM), which were compared to determine the optimal network for the classification of signals. Because the fractional Fourier transform displayed different characteristics depending on the chosen angle parameter, the optimal angle range for each RNN was first determined. To evaluate network performance, metrics such as accuracy, precision, recall, and F1-score were employed. Numerical experiments demonstrated that all three networks performed well, however, the BiLSTM network outperformed LSTM and GRU in terms of learning results. Furthermore, the BiLSTM network provided lower misclassification than the other networks and was deemed the most practically appliable to field data.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.6
• /
• pp.600-605
• /
• 2020

In this paper, we propose a sound event detection method using a multi-channel multi-scale neural networks for sound sensing home monitoring for the hearing impaired. In the proposed system, two channels with high signal quality are selected from several wireless microphone sensors in home. The three features (time difference of arrival, pitch range, and outputs obtained by applying multi-scale convolutional neural network to log mel spectrogram) extracted from the sensor signals are applied to a classifier based on a bidirectional gated recurrent neural network to further improve the performance of sound event detection. The detected sound event result is converted into text along with the sensor position of the selected channel and provided to the hearing impaired. The experimental results show that the sound event detection method of the proposed system is superior to the existing method and can effectively deliver sound information to the hearing impaired.

• Review of KIISC
• /
• v.29 no.3
• /
• pp.29-36
• /
• 2019

폭발적으로 성장하는 소셜 미디어 서비스로 인해 개인간의 연결이 강화된 환경에서는 URL로써 전파되는 피싱 공격의 위험성이 크게 강조된다. 최근 텍스트 분류 및 모델링 분야에서 그 성능을 입증받은 딥러닝 알고리즘은 피싱 URL의 구문적, 의미적 특징을 각각 모델링하기에 적절하지만, 기존에 사용하는 규칙 기반 앙상블 방법으로는 문자와 단어로부터 추출되는 특징간의 비선형적인 관계를 효과적으로 융합하는데 한계가 있다. 본 논문에서는 피싱 URL의 구문적, 의미적 특징을 체계적으로 융합하기 위한 컨볼루션 신경망 기반의 퓨전 신경망을 제안하고 기계학습 방법 중 최고의 분류정확도 (0.9804)를 달성하였다. 학습 및 테스트 데이터셋으로 45,000건의 정상 URL과 15,000건의 피싱 URL을 수집하였고, 정량적 검증으로 10겹 교차검증과 ROC커브, 정성적 검증으로 오분류 케이스와 딥러닝 내부 파라미터를 시각화하여 분석하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.4
• /
• pp.826-832
• /
• 2007

A recurrent neural network has been frequently used in equalizing the channel for fast communication systems. The existing techniques, however, have mainly dealt with time-invariant chamois. The modern environments of communication systems such as mobile ones have the time-varying feature due to fading. In this paper, powerful decision feedback - recurrent neural network is used as channel equalizer for nonlinear and time-varying system, and two kinds of algorithms, such as extended Kalman filter (EKF) and sigma-point Kalman filter (SPKF), are proposed; EKF is for fast convergence and good tracing function, and SPKF for overcoming the problems which can be developed during the process of first linearization for nonlinear system EKF.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.33 no.8
• /
• pp.39-43
• /
• 2015

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1784-1789
• /
• 2021

Korean sentiment classification task is used in real-world services such as chatbots and analysis of user's purchase reviews. And due to the development of deep learning technology, neural network models with high performance are being applied. However, the neural network model is not easy to interpret what the input sentences are predicting due to which words, and recently, model interpretation methods for interpreting these neural network models have been popularly proposed. In this paper, we used the LIME algorithm among the model interpretation methods to interpret which of the words in the input sentences of the models learned with the korean sentiment classification dataset. As a result, the interpretation of the Bi-LSTM model with 85.24% performance included 25,283 words, but 84.20% of the transformer model with relatively low performance showed that the transformer model was more reliable than the Bi-LSTM model because it contains 26,447 words.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.26-30
• /
• 2022

Spiking neural network is a neural network that applies the working principle of real brain neurons. Due to the biological mechanism of neurons, it consumes less power for training and reasoning than conventional neural networks. Recently, as deep learning models become huge and operating costs increase exponentially, the spiking neural network is attracting attention as a third-generation neural network that connects convolution neural networks and recurrent neural networks, and related research is being actively conducted. However, in order to apply the spiking neural network model to the industry, a lot of research still needs to be done, and the problem of model retraining to apply a new model must also be solved. In this paper, we propose a method to minimize the cost of model retraining by extracting the weights of the existing trained deep learning model and converting them into the weights of the spiking neural network model. In addition, it was found that weight conversion worked correctly by comparing the results of inference using the converted weights with the results of the existing model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.487-490
• /
• 2019

시각과 언어 기반의 이동(VLN)은 3차원 실내 환경에서 실시간 입력 영상과 자연어 지시들을 이해함으로써, 에이전트 스스로 목적지까지 이동해야 하는 인공지능 문제이다. 이 문제는 에이전트의 영상 및 자연어 이해 능력뿐만 아니라, 상황 추론과 행동 계획 능력도 함께 요구하는 복합 지능 문제이다. 본 논문에서는 시각과 언어 기반의 이동(VLN) 작업을 위한 새로운 심층 신경망 모델을 제안한다. 제안모델에서는 입력 영상에서 합성곱 신경망을 통해 추출하는 시각적 특징과 자연어 지시에서 순환 신경망을 통해 추출하는 언어적 특징 외에, 자연어 지시에서 언급하는 장소와 랜드마크 물체들을 영상에서 별도로 탐지해내고 이들을 추가적으로 행동 선택을 위한 특징들로 이용한다. 다양한 3차원 실내 환경들을 제공하는 Matterport3D 시뮬레이터와 Room-to-Room(R2R) 벤치마크 데이터 집합을 이용한 실험들을 통해, 본 논문에서 제안하는 모델의 높은 성능과 효과를 확인할 수 있었다.