• 한국어정보학회:학술대회논문집
• /
• 2016.10a
• /
• pp.134-138
• /
• 2016

정보의 양이 빠르게 증가함으로 인해 필요한 정보만을 효율적으로 얻기 위한 질의응답 시스템의 중요도가 늘어나고 있다. 그 중에서도 질의 문장에서 주어와 관계를 추출하여 정답을 찾는 지식베이스 기반 질의응답 시스템이 활발히 연구되고 있다. 그러나 기존 지식베이스 기반 질의응답 시스템은 하나의 질의 문장만을 사용하므로 정보가 부족한 단점이 있다. 본 논문에서는 이러한 단점을 해결하고자 정보검색을 통해 질의와 유사한 문장을 찾고 Recurrent Neural Encoder-Decoder에 검색된 문장과 질의를 함께 활용하여 주어와 관계를 찾는 모델을 제안한다. bAbI SimpleQuestions v2 데이터를 이용한 실험에서 제안 모델은 질의만 사용하여 주어와 관계를 찾는 모델보다 좋은 성능(정확도 주어:33.2%, 관계:56.4%)을 보였다.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.216-226
• /
• 2020

In this paper, a stacked convolutional autoencoder model is proposed in order to classify Alzheimer's disease with high accuracy in PET/CT images. The proposed model makes use of the latent space representation - which is also called the bottleneck, of the encoder-decoder architecture: The input image is sent through the pipeline and the encoder part, using stacked convolutional filters, extracts the most useful information. This information is in the bottleneck, which then uses Softmax classification operation to classify between Alzheimer's disease, Mild Cognitive Impairment, and Normal Control. Using the data from Dong-A University, the model performs classification in detecting Alzheimer's disease up to 98.54% accuracy.

• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.134-138
• /
• 2016

정보의 양이 빠르게 증가함으로 인해 필요한 정보만을 효율적으로 얻기 위한 질의응답 시스템의 중요도가 늘어나고 있다. 그 중에서도 질의 문장에서 주어와 관계를 추출하여 정답을 찾는 지식베이스 기반 질의응답 시스템이 활발히 연구되고 있다. 그러나 기존 지식베이스 기반 질의응답 시스템은 하나의 질의 문장만을 사용하므로 정보가 부족한 단점이 있다. 본 논문에서는 이러한 단점을 해결하고자 정보검색을 통해 질의와 유사한 문장을 찾고 Recurrent Neural Encoder-Decoder에 검색된 문장과 질의를 함께 활용하여 주어와 관계를 찾는 모델을 제안한다. bAbI SimpleQuestions v2 데이터를 이용한 실험에서 제안 모델은 질의만 사용하여 주어와 관계를 찾는 모델보다 좋은 성능(정확도 주어:33.2%, 관계:56.4%)을 보였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.57-60
• /
• 2021

본 논문에서는 기지 설비 중 주요 회전기기인 펌프의 이상탐지 알고리즘을 제안한다. 현재 인공지능을 활용하여 생산현장을 혁신하고자 하는 시도가 진행되고 있으나 외산 솔루션에 대한 의존도가 높은 것에 비해 국내 실정에 맞지 않는 경우가 많다. 이에 따라, 선행 연구를 통해 국내 실정에 맞는 인공지능 기술 도입이 필요하다. 본 연구에서는 VAE(Variational Auto Encoder) 알고리즘을 활용해 회전기기의 고장을 진단하는 알고리즘을 개발하였다. 본 연구 수행을 통한 회전기기의 고장 예지·진단 시스템 개발로 설비의 이상 징후 포착, 부품의 교환 시기 등 보수 일정을 예측하고 최종적으로 이를 통한 설비 가동의 효율 증대와 에너지 비용 감소의 효과를 기대한다.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.53-61
• /
• 2024

This paper presents a novel M-shaped encoder-decoder architecture for skin lesion segmentation, achieving better performance than existing approaches. The proposed architecture utilizes the left and right legs to enable multi-scale feature extraction and is further enhanced by integrating an attention module within the skip connection. The image is partitioned into four distinct patches, facilitating enhanced processing within the encoder-decoder framework. A pivotal aspect of the proposed method is to focus more on critical image features through an attention mechanism, leading to refined segmentation. Experimental results highlight the effectiveness of the proposed approach, demonstrating superior accuracy, precision, and Jaccard Index compared to existing methods

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4255-4269
• /
• 2019

This paper proposes an image generation method using a Multi Discriminator Generative Adversarial Net (MDGAN) as a next generation 2D game sprite creation technique. The proposed GAN is an Autoencoder-based model that receives three areas of information-color, shape, and animation, and combines them into new images. This model consists of two encoders that extract color and shape from each image, and a decoder that takes all the values of each encoder and generates an animated image. We also suggest an image processing technique during the learning process to remove the noise of the generated images. The resulting images show that 2D sprites in games can be generated by independently learning the three image attributes of shape, color, and animation. The proposed system can increase the productivity of massive 2D image modification work during the game development process. The experimental results demonstrate that our MDGAN can be used for 2D image sprite generation and modification work with little manual cost.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.19-27
• /
• 2020

Recently, rapid and accurate 3D models creation is required in various applications using virtual reality and augmented reality technology. In this paper, we propose an on-site learning based shape deformation method which transforms the clothed 3D human model into the shape of an input point cloud. The proposed algorithm consists of two main parts: one is pre-learning and the other is on-site learning. Each learning consists of encoder, template transformation and decoder network. The proposed network is learned by unsupervised method, which uses the Chamfer distance between the input point cloud form and the template vertices as the loss function. By performing on-site learning on the input point clouds during the inference process, the high accuracy of the inference results can be obtained and presented through experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.37-46
• /
• 2020

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.