• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.243-246
• /
• 2018

최근 사용자 발화를 이해하고 그에 맞는 피드백을 생성할 수 있는 대화 시스템의 중요성이 증가하고 있다. 따라서 사용자 의도를 파악하기 위한 화행 분석은 대화 시스템의 필수적인 요소이다. 최근 많이 연구되는 심층 학습 기법은 모델이 데이터로부터 자질들을 스스로 추출한다는 장점이 있다. 발화 자체의 연속성과 화자간 상호 작용을 포착하기 위하여 CNN에 RNN을 결합한 CNN-RNN을 제안한다. 본 논문에서 제안한 계층 구조 어텐션 매커니즘 기반 CNN-RNN을 효과적으로 적용한 결과 워드 임베딩을 추가한 조건에서 가장 높은 성능인 91.72% 정확도를 얻었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.533-539
• /
• 2019

This study proposes a malware classification model that can handle arbitrary length input data using the Microsoft Malware Classification Challenge dataset. We are based on imaging existing data from malware. The proposed model generates a lot of images when malware data is large, and generates a small image of small data. The generated image is learned as time series data by Dynamic RNN. The output value of the RNN is classified into malware by using only the highest weighted output by applying the Attention technique, and learning the RNN output value by Residual CNN again. Experiments on the proposed model showed a Micro-average F1 score of 92% in the validation data set. Experimental results show that the performance of a model capable of learning and classifying arbitrary length data can be verified without special feature extraction and dimension reduction.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.49-59
• /
• 2022

In this paper, we designed a new enzyme function prediction model PSCREM based on a study that compared and evaluated CNN and LSTM/GRU models, which are the most widely used deep learning models in the field of predicting functions and structures using protein sequences in 2020, under the same conditions. Sequence evolution information was used to preserve detailed patterns which would miss in CNN convolution, and the relationship information between amino acids with functional significance was extracted through overlapping RNNs. It was referenced to feature map production. The RNN family of algorithms used in small CNN-RNN models are LSTM algorithms and GRU algorithms, which are usually stacked two to three times over 100 units, but in this paper, small RNNs consisting of 10 and 20 units are overlapped. The model used the PSSM profile, which is transformed from protein sequence data. The experiment proved 86.4% the performance for the problem of predicting the main classes of enzyme number, and it was confirmed that the performance was 84.4% accurate up to the sub-sub classes of enzyme number. Thus, PSCREM better identifies unique patterns related to protein function through overlapped RNN, and Overlapped RNN is proposed as a novel methodology for protein function and structure prediction extraction.

• Transactions of Materials Processing
• /
• v.33 no.3
• /
• pp.214-230
• /
• 2024

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.2
• /
• pp.389-396
• /
• 2019

In this paper, various architectures of deep neural networks were applied for sound event detection and their performances were compared using a common audio database. The FNN, CNN, RNN and CRNN were implemented using hyper-parameters optimized for the database as well as the architecture of each neural network. Among the implemented deep neural networks, CRNN performed best at all testing conditions and CNN followed CRNN in performance. Although RNN has a merit in tracking the time-correlations in audio signals, it showed poor performance compared with CNN and CRNN.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.129-143
• /
• 2023

In the era of big data, the field of artificial intelligence is showing remarkable growth, and in particular, the image classification learning methods by deep learning are becoming an important area. Various studies have been actively conducted to further improve the performance of CNNs, which have been widely used in image classification, among which a representative method is the Convolutional Recurrent Neural Network (CRNN) algorithm. The CRNN algorithm consists of a combination of CNN for image classification and RNNs for recognizing time series elements. However, since the inputs used in the RNN area of CRNN are the flatten values extracted by applying the convolution and pooling technique to the image, pixel values in the same phase in the image appear in different order. And this makes it difficult to properly learn the sequence of arrangements in the image intended by the RNN. Therefore, this study aims to improve image classification performance by proposing a novel hybrid method of CNN and RNN applying the concepts of encoder and decoder. In this study, the effectiveness of the new hybrid method was verified through various experiments. This study has academic implications in that it broadens the applicability of encoder and decoder concepts, and the proposed method has advantages in terms of model learning time and infrastructure construction costs as it does not significantly increase complexity compared to conventional hybrid methods. In addition, this study has practical implications in that it presents the possibility of improving the quality of services provided in various fields that require accurate image classification.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.177-183
• /
• 2022

Recently, interesting of home training is getting bigger due to COVID-19. Accordingly, research on applying HAR(human activity recognition) technology to home training has been conducted. However, existing paper of HAR proposed static activity instead of dynamic activity. In this paper, the deep learning model where dynamic exercise posture can be analyzed and the accuracy of the user's exercise posture can be shown is proposed. Fitness images of AI-hub are analyzed by blaze pose. The experiment is compared with three types of deep learning model: RNN(recurrent neural network), LSTM(long short-term memory), CNN(convolution neural network). In simulation results, it was shown that the f1-score of RNN, LSTM and CNN is 0.49, 0.87 and 0.98, respectively. It was confirmed that CNN is more suitable for human activity recognition than other models from simulation results. More exercise postures can be analyzed using a variety learning data.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.151-154
• /
• 2018

본 논문에서는 CNN Seq2Seq 구조를 이용해 한국어 대화 시스템을 개발하였다. 기존 Seq2Seq는 RNN 혹은 그 변형 네트워크에 데이터를 입력하고, 입력이 완료된 후의 은닉 층의 embedding에 기반해 출력열을 생성한다. 우리는 CNN Seq2Seq로 입력된 발화에 대해 출력 발화를 생성하는 대화 모델을 학습하였고, 그 성능을 측정하였다. CNN에 대해서는 약 12만 발화 쌍을 이용하여 학습하고 1만 발화 쌍으로 실험하였다. 평가 결과 제안 모델이 기존의 RNN 기반 모델에 비해 우수한 결과를 보였다.

• Journal of Sensor Science and Technology
• /
• v.32 no.3
• /
• pp.174-179
• /
• 2023

Bulk trailers, used for the transportation of powdered materials, such as cement and fly ash, are crucial in the construction industry. The speedy exhaustion of powdered materials stored in the tank of bulk trailers is relevant to improving transportation efficiency and reducing transportation costs. The exhaust time can be reduced by developing an automatic control system to replace the manual exhaust operation. The instantaneous or accumulated exhausts of powdered materials must be measured for automatic control of the bulk trailer exhaust system. Accordingly, we previously proposed a recurrent neural network (RNN) model that estimated the instantaneous exhaust based on low-cost pressure sensor signals without an expensive flowmeter for powders. Although our previous study utilized only an RNN model, models such as multilayer perceptron (MLP) and convolutional neural network (CNN) are also widely utilized for time-series estimation. This study compares the performance of three neural network models (MLP, CNN, and RNN) in estimating instantaneous and accumulated exhausts. In terms of the instantaneous exhaust estimation, the difference in the performance of neural network models was insignificant (that is, 8.64, 8.62, and 8.56% for the MLP, CNN, and RNN, respectively, in terms of the normalized root mean squared error). However, in the case of the accumulated exhaust, the performance was excellent in the order of CNN (1.67%), MLP (2.03%), and RNN (2.20%).