• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.9-10
• /
• 2019

본 논문은 구동장치의 진동에서 특징 데이터를 추출하고 인공신경망에 학습을 시킨 후, 구동 장치의 결함을 분류하는 시스템을 구현하였다. 딥러닝 기술을 이용함으로써 특정 장치에 종속되지 않고 학습할 데이터의 특징에 따라 쉽게 변경 가능하다. 또한, 실제 적용될 현장에서 발생할 수 있는 예측외의 진동 환경에 유연하게 대처하기 위해 딥러닝 모델 중 CNN을 적용한 시스템을 설계하였으며, 본 연구팀의 이전 연구에서 제안된 DNN 기반의 진단시스템을 학습데이터의 환경과 다른 처리배제가 필요한 진동 환경에서 비교 실험하여 제안된 시스템이 새로운 환경적응 성능향상에 대하여 우수한 결과를 얻었음을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.20 no.8
• /
• pp.10-18
• /
• 2020

Among various contents industry, this study especially focused on music industry and tried to develop a prediction model for music box office using deep learning. The deep learning prediction model designed to predict music chart-in period based on 17 variables -singer power, singer influence, featuring singer power, featuring singer influence, number of participating singers, gender of participating singers, lyric writer power, composer power, arranger power, production agency power, distributing agency power, title track, LIKEs on streaming platform, comments on streaming platform, pre-promotion article, teaser-video view, first-week performance. Additionally we conducted a linear regression analysis to sort out factors, and tried to compare the prediction performance between the original DNN prediction model and the DNN model made of sorted out factors.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.348-350
• /
• 2021

When predicting the concentration of fine dust using deep learning, there is a problem that the characteristics of a high concentration of 81㎍/m³ or more are not well reflected in the prediction model. In this paper, a comparison through predictive performance was conducted to confirm the results of reflecting the characteristics of fine dust in the high concentration area according to the deep learning algorithm. As a result of performance evaluation, overall, similar levels of results were shown, but the RNN model showed higher accuracy than other models at concentrations of "very bad" based on AQI. This confirmed that the RNN algorithm reflected the characteristics of the high concentration better than the DNN and LSTM algorithms.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.452-455
• /
• 2022

4차 산업혁명의 확산으로 의학계에서도 딥러닝 기술을 이용한 질병의 치료결과 예측 연구가 활발하다. 이와 관련, 일부 연구에서 국소적인 환자 데이터의 활용으로 인해 도출된 연구 결과의 일반화가 어려웠으며 예측률 제고를 위해 특정 딥러닝 알고리즘을 중심으로 한 실험이 추진되어 다양한 알고리즘별 예측률의 비교·분석 결과를 제시하는 연구도 미흡하였다. 이에, 건강보험심사평가원의 대규모 진료 정보와 다종의 알고리즘을 제공하는 AutoML을 이용, 사망률이 높은 80대·90대 노령자 대상 폐암 진단 후 84개월간의 사망률을 예측하는 Decision Tree 등 5개 알고리즘별 모델을 생성하고 이를 활용, 사망률의 예측 성능을 비교하고 사망률에 영향을 미치는 요인에 대한 분석 결과를 도출하였다.

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.

• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1061-1070
• /
• 2021

In this manuscript, we tried to improve the performance of the FC-DenseNet by applying an attention gate for the classification of cropping areas. The attention gate module could facilitate the learning of a deep learning model and improve the performance of the model by injecting of spatial/spectral weights to each feature map. Crop classification was performed in the onion and garlic regions using a proposed deep learning model in which an attention gate was added to the skip connection part of FC-DenseNet. Training data was produced using various PlanetScope satellite imagery, and preprocessing was applied to minimize the problem of imbalanced training dataset. As a result of the crop classification, it was verified that the proposed deep learning model can more effectively classify the onion and garlic regions than existing FC-DenseNet algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.614-617
• /
• 2021

법률 문서는 일반 사용자가 이해하기 어려운 용어로 이루어져 있고 특히 장문의 문서가 많아 법률시스템에 종사하는 종사자들 또한 많은 양의 문서를 읽기가 어려운 현실이다. 이에 문서 요약 방법중 딥러닝 기반의 사전학습 모델을 적용한 추출요약기반, 생성요약 방법론과 딥러닝 이전의 핵심문장 추출 방법론을 비교하여 법률용어의 요약성능에 대한 비교 평가를 수행하고자 하며 추후 연구과제로 법률문서에 특화된 요약 모델을 만들어보고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.686-688
• /
• 2020

본 논문에서는 U-Net 모델을 이용하여 정교하고 반복되는 패턴을 가진 인쇄물에 대한 비지도 학습을 통한 딥러닝 기반 이상치탐지(Anomaly Detection) 방법을 제안하였다. 인쇄물(카드)의 비정상 패턴 검출을 위하여 촬영한 영상으로부터 카드 영역을 분리한 이미지로 구성된 Dataset을 구축하였고 정상 이미지와 동일한 이미지를 출력하기 위해, 정상 이미지와 마스크 이미지 쌍의 Training dataset을 U-Net으로 학습하였다. Test dataset의 이미지를 입력으로 넣어 생성된 마스크 결과를 원본 마스크 이미지와 비교하여 이상 여부를 판단하는 본 논문의 방법이 정상, 비정상 인쇄물을 잘 구분하는 것을 확인하였다. 또한 정상과 비정상 이미지 각각을 학습한 지도학습 기반 CNN 분류 방법을 입력 영상과 복원 영상 간의 복원 오차를 비교하여 객체의 이상 여부를 판별하는 본 논문의 방법과 비교 평가하였다. 본 논문을 통해 U-Net을 사용하여 별도로 데이터에 대한 label 취득 없이 이상치를 검출할 수 있음을 확인할 수 있었다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.513-524
• /
• 2022

Recently, detecting damages of civil infrastructures from digital images using deep learning technology became a very popular research topic. In order to adapt those methodologies to the field, it is essential to explain robustness of deep learning models. Our research points out that the existing pixel-based deep learning model evaluation metrics are not sufficient for detecting cracks since cracks have linear appearance, and proposes a new evaluation methodology to explain crack segmentation deep learning model more rationally. Specifically, we design, implement and validate a methodology to generate tolerance buffer alongside skeletonized ground truth data and prediction results to consider overall similarity of topology of the ground truth and the prediction rather than pixel-wise accuracy. We could overcome over-estimation or under-estimation problem of crack segmentation model evaluation through using our methodology, and we expect that our methodology can explain crack segmentation deep learning models better.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.203-210
• /
• 2022

As more and more research and companies use health care data, efforts are being made to vitalize health care data worldwide. However, the system and format used by each institution is different. Therefore, this research established a basic model to classify text data onto multiple institutions according to the type of the future by establishing a basic model to classify the types of medical records of the EEG Report. For EEG Report classification, four deep learning-based algorithms were compared. As a result of the experiment, the ANN model trained by vectorizing with One-Hot Encoding showed the highest performance with an accuracy of 71%.