• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.91-94
• /
• 2021

As deep learning technologies becoming developed, realistic fake videos synthesized by deep learning models called "Deepfake" videos became even more difficult to distinguish from original videos. As fake news or Deepfake blackmailing are causing confusion and serious problems, this paper suggests a novel model detecting Deepfake videos. We chose Residual Convolutional Neural Network (Resnet50) as an extraction model and Long Short-Term Memory (LSTM) which is a form of Recurrent Neural Network (RNN) as a classification model. We adopted cosine similarity with hinge loss to train our extraction model in embedding the features of Deepfake and original video. The result in this paper demonstrates that temporal features in the videos are essential for detecting Deepfake videos.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.212-215
• /
• 2021

본 논문에서는 딥러닝의 CNN(Convolution Neural Network) 학습을 통하여 악성코드를 실행시키지 않고서 악성코드 변종을 패밀리 그룹으로 분류하는 방법을 연구한다. 먼저 데이터 전처리를 통해 3가지의 서로 다른 방법으로 악성코드 이미지와 메타데이터를 생성하고 이를 CNN으로 학습시킨다. 첫째, 악성코드의 byte 파일을 8비트 gray-scale 이미지로 시각화하는 방법이다. 둘째, 악성코드 asm 파일의 opcode sequence 정보를 추출하고 이를 이미지로 변환하는 방법이다. 셋째, 악성코드 이미지와 메타데이터를 결합하여 분류에 적용하는 방법이다. 이미지 특징 추출을 위해서는 본고에서 제안한 CNN을 통한 학습 방식과 더불어 3개의 Pre-trained된 CNN 모델을 (InceptionV3, Densnet, Resnet-50) 사용하여 전이학습을 진행한다. 전이학습 시에는 마지막 분류 레이어층에서 본 논문에서 선택한 데이터셋에 대해서만 학습하도록 파인튜닝하였다. 결과적으로 가공된 악성코드 데이터를 적용하여 9개의 악성코드 패밀리로 분류하고 예측 정확도를 측정해 비교 분석한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.873-876
• /
• 2020

매실의 병충해 이미지를 Tensorflow hub에서 제공하는 Resnet50모델에 Transfer Learning기법을 이용하여 학습시키고, 학습된 모델을 Flask를 이용하여 연동시킨다. 이렇게 완성된 웹앱은 사용자가 매실의 이미지를 업로드 하면, 어떤 병충해를 가지고 있는 지 알려주며, 사용자는 얻은 결과를 통해 육안으로 구분하기 어려운 병충해의 정보를 얻어 매실이 손상이 가는 것을 예방할 수 있다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.97-99
• /
• 2021

As the aging society continues in recent years, interest in dementia is increasing. Among them, Alzheimer's disease is a degenerative brain disease that accounts for the largest percentage of all dementia patients, with the medical community currently not offering clear prevention and treatment for Alzheimer's disease, and the importance of early treatment and early prevention is emphasized. In this paper, we intend to find the most efficient activation function by combining various activation functions centering on convolutional neural networks using MRI datasets of normal people and patients with Alzheimer's disease. In addition, it is intended to be used as a dementia classification modeling suitable for the medical field in the future through Alzheimer's dementia classification modeling.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.999-1009
• /
• 2019

The importance of high-resolution sea ice maps of the Arctic Ocean is increasing due to the possibility of pioneering North Pole Routes and the necessity of precise climate prediction models. In this study,sea ice classification algorithms for two deep learning models were examined using Sentinel-1 A/B SAR data to generate high-resolution sea ice classification maps. Based on current ice charts, three classes (Open Water, First Year Ice, Multi Year Ice) of training data sets were generated by Arctic sea ice and remote sensing experts. Ten sea ice classification algorithms were generated by combing two deep learning models (i.e. Simple CNN and Resnet50) and five cases of input bands including incident angles and thermal noise corrected HV bands. For the ten algorithms, analyses were performed by comparing classification results with ground truth points. A confusion matrix and Cohen's kappa coefficient were produced for the case that showed best result. Furthermore, the classification result with the Maximum Likelihood Classifier that has been traditionally employed to classify sea ice. In conclusion, the Convolutional Neural Network case, which has two convolution layers and two max pooling layers, with HV and incident angle input bands shows classification accuracy of 96.66%, and Cohen's kappa coefficient of 0.9499. All deep learning cases shows better classification accuracy than the classification result of the Maximum Likelihood Classifier.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.49 no.2
• /
• pp.131-139
• /
• 2022

This study aimed to evaluate the effectiveness of deep convolutional neural networks (CNNs) for diagnosis of interproximal caries in pediatric intraoral radiographs. A total of 500 intraoral radiographic images of first and second primary molars were used for the study. A CNN model (Resnet 50) was applied for the detection of proximal caries. The diagnostic accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and area under ROC curve (AUC) were calculated on the test dataset. The diagnostic accuracy was 0.84, sensitivity was 0.74, and specificity was 0.94. The trained CNN algorithm achieved AUC of 0.86. The diagnostic CNN model for pediatric intraoral radiographs showed good performance with high accuracy. Deep learning can assist dentists in diagnosis of proximal caries lesions in pediatric intraoral radiographs.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.461-467
• /
• 2020

In the field of nuclear medicine, errors are sometimes generated because the assessment of the uniformity of gamma cameras relies on the naked eye of the evaluator. To minimize these errors, we created an artificial intelligence model based on CNN algorithm and wanted to assess its usefulness. We produced 20,000 normal images and partial cold region images using Python, and conducted artificial intelligence training with Resnet18 models. The training results showed that accuracy, specificity and sensitivity were 95.01%, 92.30%, and 97.73%, respectively. According to the results of the evaluation of the confusion matrix of artificial intelligence and expert groups, artificial intelligence was accuracy, specificity and sensitivity of 94.00%, 91.50%, and 96.80%, respectively, and expert groups was accuracy, specificity and sensitivity of 69.00%, 64.00%, and 74.00%, respectively. The results showed that artificial intelligence was better than expert groups. In addition, by checking together with the radiological technologist and AI, errors that may occur during the quality control process can be reduced, providing a better examination environment for patients, providing convenience to radiologists, and improving work efficiency.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.623-625
• /
• 2021

Rubber o-rings are produced by conventional injection molding methods. In this case, products that are not normally molded are determined to be defective. However, if images acquired during image-based reading are read as original, there is a problem of poor accuracy. We have thus learned from convolutional neural networks using adaptive binarization and Convex Hull algorithms by extracting only rubber oring parts from the original images through pre-processing. During the test process, it was confirmed that the defect detection performance of the learning method applied pre-processing was better than the standard suggested.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.451-452
• /
• 2023

최근 CNN 이 다양한 산업에 확산되고 있으며, IoT 기기 및 엣지 컴퓨팅에 적합한 경량 모델에 대한 연구가 급증하고 있다. 본 논문에서는 CNN 모델의 파라미터 비트 연산을 위한 자동화 프레임워크를 제안하고, 파라미터 비트와 모델 정확도 사이의 관계를 실험 및 연구한다. 제안된 프레임워크는 하위 n- bit 를 0 으로 설정하여 정보 손실 발생시킴으로써 ImageNet 데이터셋으로 사전 학습된 CNN 모델의 파라미터와 정확도의 강인성을 비트 단위로 체계적으로 실험할 수 있다. 우리는 비트 연산을 수행한 파라미터로 InceptionV3, InceptionResnetV2, ResNet50, Xception, DenseNet121, MobileNetV1, MobileNetV2 모델의 정확도를 평가한다. 실험 결과는 성능이 낮은 모델일수록 파라미터와 정확도 간의 강인성이 높아 성능이 좋은 모델보다 정확도를 유지하는 비트 수가 적다는 것을 보여준다.