• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.48-54
• /
• 2019

This paper proposed a method of validation data augmentation for improving the grading accuracy of diabetic macular edema (DME) using deep learning. The data augmentation technique is basically applied in order to secure diversity of data by transforming one image to several images through random translation, rotation, scaling and reflection in preparation of input data of the deep neural network (DNN). In this paper, we apply this technique in the validation process of the trained DNN, and improve the grading accuracy by combining the classification results of the augmented images. To verify the effectiveness, 1,200 retinal images of Messidor dataset was divided into training and validation data at the ratio 7:3. By applying random augmentation to 359 validation data, $1.61{\pm}0.55%$ accuracy improvement was achieved in the case of six times augmentation (N=6). This simple method has shown that the accuracy can be improved in the N range from 2 to 6 with the correlation coefficient of 0.5667. Therefore, it is expected to help improve the diagnostic accuracy of DME with the grading information provided by the proposed DNN.

• 한국가시화정보학회지
• /
• 제19권1호
• /
• pp.68-73
• /
• 2021

In this study, the detection of rubber o-ring defects was carried out using k-fold cross validation and Support Vector Machine (SVM) algorithm. The data process was carried out in 3 steps. First, we proceeded with a frame alignment to eliminate unnecessary regions in the learning and secondly, we applied gray-scale changes for computational reduction. Finally, data processing was carried out using image augmentation to prevent data overfitting. After processing data, SVM algorithm was used to obtain normal and defect detection accuracy. In addition, we applied the SVM algorithm through the k-fold cross validation method to compare the classification accuracy. As a result, we obtain results that show better performance by applying the k-fold cross validation method.

• 응용통계연구
• /
• 제24권5호
• /
• pp.871-881
• /
• 2011

In this paper we propose a logistic regression method to estimate the survival function and the median survival time in interval-censored data. The proposed method is motivated by the data augmentation technique with no sacrifice in augmenting data. In addition, we develop a cross validation criterion to determine the size of data augmentation. We compare the proposed estimator with other existing methods such as the parametric method, the single point imputation method, and the nonparametric maximum likelihood estimator through extensive numerical studies to show that the proposed estimator performs better than others in the sense of the mean squared error. An illustrative example based on a real data set is given.

• Journal of information and communication convergence engineering
• /
• 제16권3호
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.485-492
• /
• 2018

In this paper, we propose facial expression recognition using CNN (Convolutional Neural Network), one of the deep learning technologies. The proposed structure has general classification performance for any environment or subject. For this purpose, we collect a variety of databases and organize the database into six expression classes such as 'expressionless', 'happy', 'sad', 'angry', 'surprised' and 'disgusted'. Pre-processing and data augmentation techniques are applied to improve training efficiency and classification performance. In the existing CNN structure, the optimal structure that best expresses the features of six facial expressions is found by adjusting the number of feature maps of the convolutional layer and the number of nodes of fully-connected layer. The experimental results show good classification performance compared to the state-of-the-arts in experiments of the cross validation and the cross database. Also, compared to other conventional models, it is confirmed that the proposed structure is superior in classification performance with less execution time.

• 한국컴퓨터정보학회논문지
• /
• 제26권4호
• /
• pp.21-28
• /
• 2021

본 연구는 기존 편평발 측정을 위해 사용되던 다양한 방법의 한계를 보완할 수 있는 새로운 측정 방법으로 전이학습을 적용한 딥러닝 기반 편평발 분류 방법론을 제안한다. 편평발 88장, 정상발 88장으로 이루어진 총 176장의 이미지 데이터를 활용하여, 적은 데이터로도 우수한 예측 모델을 생성할 수 있는 데이터 증폭 기술과 사전학습 모델인 VGG16 구조를 활용하는 전이학습 기술을 적용하여 제안 모델의 학습을 진행하였다. 제안 모델의 우수성을 확인하기 위하여 기본 CNN 기반 모델과 제안 방법론의 예측 정확도를 비교하는 실험을 수행하였다. 기본 CNN 모델의 경우 훈련 정확도는 77.27%, 검증 정확도는 61.36%, 그리고 시험 정확도는 59.09%로 나타났으며, 제안 모델의 경우 훈련 정확도는 94.32%, 검증 정확도는 86.36%, 그리고 시험 정확도는 84.09%로 나타나 기본 CNN 모델에 비해 제안 모델의 정확도가 큰 폭으로 향상된 것을 확인하였다.

• 한국기계가공학회지
• /
• 제19권7호
• /
• pp.7-15
• /
• 2020

Recently, the fourth industrial revolution has been presented as a new paradigm and additive manufacturing (AM) has become one of the most important topics. For this reason, process monitoring for each cross-sectional layer of additive metal manufacturing is important. Particularly, deep learning can train a machine to analyze, optimize, and repair defects. In this paper, image classification is proposed by learning images of defects in the metal cross sections using the convolution neural network (CNN) image labeling algorithm. Defects were classified into three categories: crack, porosity, and hole. To overcome a lack-of-data problem, the amount of learning data was augmented using a data augmentation algorithm. This augmentation algorithm can transform an image to 180 images, increasing the learning accuracy. The number of training and validation images was 25,920 (80 %) and 6,480 (20 %), respectively. An optimized case with a combination of fully connected layers, an optimizer, and a loss function, showed that the model accuracy was 99.7 % and had a success rate of 97.8 % for 180 test images. In conclusion, image labeling was successfully performed and it is expected to be applied to automated AM process inspection and repair systems in the future.

• 터널과지하공간
• /
• 제29권3호
• /
• pp.184-196
• /
• 2019

본 연구에서는 화강암 시편에서 수압 파쇄법에 의해 생성된 미세균열의 3차원 형상을 X-ray CT 영상과 딥러닝을 이용하여 추출하였다. 실험으로 생성된 미세균열은 X-ray CT 영상 상에서 일반적인 영상처리방법으로는 추출하기 매우 어렵고 육안으로만 관찰이 가능한 형태를 지닌다. 하지만 본 연구에서 제안한 합성곱 신경망(Convolutional neural network) 기반 인코더-디코더(Encoder-Decoder) 구조의 딥러닝 모델을 통해 미세균열을 정량적으로 추출할 수 있었다. 특히 픽셀 단위의 미세균열 추출을 위해 인코딩 과정에서 소실되는 정보를 디코딩 과정으로 직접 전달하는 디코더 모델을 제안하였다. 또한, 딥러닝 기반 신경망 학습에 필요한 데이터의 수를 증가시키기 위해 이미지의 분할(Division), 회전(Rotation), 그리고 반전(Flipping) 등으로 데이터를 생성하는 영상 증대 방법을 적용하였으며 이때 최적의 조합을 확인하였다. 최적의 영상 학습 데이터 증대 방법을 적용하였을 때 검증 데이터뿐만 아니라 테스트 데이터에서의 성능 향상을 확인하였다. 학습 데이터의 원본 개수가 딥러닝 기반 신경망의 균열 추출 성능에 미치는 영향을 확인하고 딥러닝 기술을 사용하여 성공적으로 미세균열을 추출하였다.

• 대한임베디드공학회논문지
• /
• 제15권4호
• /
• pp.197-204
• /
• 2020

The ImageNet dataset is a large scale dataset and contains various natural scene images. In this paper, we propose a convolutional neural network (CNN)-based weighted ensemble technique for the ImageNet classification task. First, in order to fuse several models, our technique uses weights for each model, unlike the existing average-based ensemble technique. Then we propose an algorithm that automatically finds the coefficients used in later ensemble process. Our algorithm sequentially selects the model with the best performance of the validation set, and then obtains a weight that improves performance when combined with existing selected models. We applied the proposed algorithm to a total of 13 heterogeneous models, and as a result, 5 models were selected. These selected models were combined with weights, and we achieved 3.297% Top-5 error rate on the ImageNet test dataset.

• 대한방사선기술학회지:방사선기술과학
• /
• 제45권1호
• /
• pp.41-47
• /
• 2022

The purpose of this study is to apply a deep learning model that can distinguish lung perfusion and lung ventilation images in nuclear medicine, and to evaluate the image classification ability. Image data pre-processing was performed in the following order: image matrix size adjustment, min-max normalization, image center position adjustment, train/validation/test data set classification, and data augmentation. The convolutional neural network(CNN) structures of VGG-16, ResNet-18, Inception-ResNet-v2, and SE-ResNeXt-101 were used. For classification model evaluation, performance evaluation index of classification model, class activation map(CAM), and statistical image evaluation method were applied. As for the performance evaluation index of the classification model, SE-ResNeXt-101 and Inception-ResNet-v2 showed the highest performance with the same results. As a result of CAM, cardiac and right lung regions were highly activated in lung perfusion, and upper lung and neck regions were highly activated in lung ventilation. Statistical image evaluation showed a meaningful difference between SE-ResNeXt-101 and Inception-ResNet-v2. As a result of the study, the applicability of the CNN model for lung scintigraphy classification was confirmed. In the future, it is expected that it will be used as basic data for research on new artificial intelligence models and will help stable image management in clinical practice.