• Communications for Statistical Applications and Methods
• /
• 제26권6호
• /
• pp.591-610
• /
• 2019

Deep Learning is one of the machine learning methods to find features from a huge data using non-linear transformation. It is now commonly used for supervised learning in many fields. In particular, Convolutional Neural Network (CNN) is the best technique for the image classification since 2012. For users who consider deep learning models for real-world applications, Keras is a popular API for neural networks written in Python and also can be used in R. We try examine the parameter estimation procedures of Deep Neural Network and structures of CNN models from basics to advanced techniques. We also try to figure out some crucial steps in CNN that can improve image classification performance in the CIFAR10 dataset using Keras. We found that several stacks of convolutional layers and batch normalization could improve prediction performance. We also compared image classification performances with other machine learning methods, including K-Nearest Neighbors (K-NN), Random Forest, and XGBoost, in both MNIST and CIFAR10 dataset.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.165-165
• /
• 2023

Streamflow prediction is a critical task in water resources management and essential for planning and decision-making purposes. However, the streamflow prediction is challenging due to the complexity and non-linear nature of hydrological processes. The transfer learning is a powerful technique that enables a model to transfer knowledge from a source domain to a target domain, improving model performance with limited data in the target domain. In this study, we apply the transfer learning using the Informer model, which is a state-of-the-art deep learning model for streamflow prediction. The model was trained on a large-scale hydrological dataset in the source basin and then fine-tuned using a smaller dataset available in the target basin to predict the streamflow in the target basin. The results demonstrate that transfer learning using the Informer model significantly outperforms the traditional machine learning models and even other deep learning models for streamflow prediction, especially when the target domain has limited data. Moreover, the results indicate the effectiveness of streamflow prediction when knowledge transfer is used to improve the generalizability of hydrologic models in data-sparse regions.

• 대한원격탐사학회지
• /
• 제39권5_4호
• /
• pp.1111-1123
• /
• 2023

원격탐사 영상을 이용한 지표 속성의 변화를 모니터링 하기 위해서 딥러닝(deep learning) 모델을 이용한 의미론적 영상 분할 방법이 최근에 널리 사용되고 있다. 대표적인 의미론적 영상 분할 딥러닝 모델인 UNet 모델을 비롯하여 다양한 종류의 UNet 기반의 딥러닝 모델들의 성능 향상을 위해서는 학습 데이터셋의 크기가 충분해야 한다. 학습 데이터셋의 크기가 커지면 이를 처리하는 하드웨어 요구 사항도 커지고 학습에 소요되는 시간도 크게 증가되는 문제점이 발생한다. 이런 문제를 해결할 수 있는 방법인 전이학습은 대규모의 학습 데이터 셋이 없어도 모델 성능을 향상시킬 수 있는 효과적인 방법이다. 본 논문에서는 UNet 기반의 딥러닝 모델들을 대표적인 사전 학습 모델(pretrained model)인 VGG19 모델 및 ResNet50 모델과 결합한 세 종류의 전이학습 모델인 UNet-ResNet50 모델, UNet-VGG19 모델, CBAM-DRUNet-VGG19 모델을 제시하고 이를 건물 추출에 적용하여 전이학습 적용에 따른 정확도 향상을 분석하였다. 딥러닝 모델의 성능이 학습률의 영향을 많이 받는 점을 고려하여 학습률 설정에 따른 각 모델별 성능 변화도 함께 분석하였다. 건물 추출 결과의 성능 평가를 위해서 Kompsat-3A 데이터셋, WHU 데이터셋, INRIA 데이터셋을 사용하였으며 세 종류의 데이터셋에 대한 정확도 향상의 평균은 UNet 모델 대비 UNet-ResNet50 모델이 5.1%, UNet-VGG19 모델과 CBAM-DRUNet-VGG19 모델은 동일하게 7.2%의 결과를 얻었다.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.364-373
• /
• 2022

Image morphing methods make seamless transition changes in the image and mask the meaningful information attached to it. This can be detected by traditional machine learning algorithms and new emerging deep learning algorithms. In this research work, scope of different Hybrid learning approaches having combination of Deep learning and Machine learning are being analyzed with the public dataset CASIA V1.0, CASIA V2.0 and DVMM to find the most efficient algorithm. The simulated results with CNN (Convolution Neural Network), Hybrid approach of CNN along with SVM (Support Vector Machine) and Hybrid approach of CNN along with Random Forest algorithm produced 96.92 %, 95.98 and 99.18 % accuracy respectively with the CASIA V2.0 dataset having 9555 images. The accuracy pattern of applied algorithms changes with CASIA V1.0 data and DVMM data having 1721 and 1845 set of images presenting minimal accuracy with Hybrid approach of CNN and Random Forest algorithm. It is confirmed that the choice of best algorithm to find image forgery depends on input data type. This paper presents the combination of best suited algorithm to detect image morphing with different input datasets.

• 한국정보시스템학회지:정보시스템연구
• /
• 제32권4호
• /
• pp.149-162
• /
• 2023

Purpose In the textile industry, fabric defects significantly impact product quality and consumer satisfaction. This research seeks to enhance defect detection by developing a transformer-based deep learning image segmentation model for learning high-dimensional image features, overcoming the limitations of traditional image classification methods. Design/methodology/approach This study utilizes the ZJU-Leaper dataset to develop a model for detecting defects in fabrics. The ZJU-Leaper dataset includes defects such as presses, stains, warps, and scratches across various fabric patterns. The dataset was built using the defect labeling and image files from ZJU-Leaper, and experiments were conducted with deep learning image segmentation models including Deeplabv3, SegformerB0, SegformerB1, and Dinov2. Findings The experimental results of this study indicate that the SegformerB1 model achieved the highest performance with an mIOU of 83.61% and a Pixel F1 Score of 81.84%. The SegformerB1 model excelled in sensitivity for detecting fabric defect areas compared to other models. Detailed analysis of its inferences showed accurate predictions of diverse defects, such as stains and fine scratches, within intricated fabric designs.

• The Korean Journal of Physiology and Pharmacology
• /
• 제24권1호
• /
• pp.89-99
• /
• 2020

Although microscopic analysis of tissue slides has been the basis for disease diagnosis for decades, intra- and inter-observer variabilities remain issues to be resolved. The recent introduction of digital scanners has allowed for using deep learning in the analysis of tissue images because many whole slide images (WSIs) are accessible to researchers. In the present study, we investigated the possibility of a deep learning-based, fully automated, computer-aided diagnosis system with WSIs from a stomach adenocarcinoma dataset. Three different convolutional neural network architectures were tested to determine the better architecture for tissue classifier. Each network was trained to classify small tissue patches into normal or tumor. Based on the patch-level classification, tumor probability heatmaps can be overlaid on tissue images. We observed three different tissue patterns, including clear normal, clear tumor and ambiguous cases. We suggest that longer inspection time can be assigned to ambiguous cases compared to clear normal cases, increasing the accuracy and efficiency of histopathologic diagnosis by pre-evaluating the status of the WSIs. When the classifier was tested with completely different WSI dataset, the performance was not optimal because of the different tissue preparation quality. By including a small amount of data from the new dataset for training, the performance for the new dataset was much enhanced. These results indicated that WSI dataset should include tissues prepared from many different preparation conditions to construct a generalized tissue classifier. Thus, multi-national/multi-center dataset should be built for the application of deep learning in the real world medical practice.

• 드라이브 ㆍ 컨트롤
• /
• 제19권4호
• /
• pp.104-109
• /
• 2022

For autonomous driving research using AI, datasets collected from road environments play an important role. In other countries, various datasets such as CityScapes, A2D2, and BDD have already been released, but datasets suitable for the domestic road environment still need to be provided. This paper analyzed and verified the dataset reflecting the Korean driving environment. In order to verify the training dataset, the class imbalance was confirmed by comparing the number of pixels and instances of the dataset. A similar A2D2 dataset was trained with the same deep learning model, ConvNeXt, to compare and verify the constructed dataset. IoU was compared for the same class between two datasets with ConvNeXt and mIoU was compared. In this paper, it was confirmed that the collected dataset reflecting the driving environment of Korea is suitable for learning.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• pp.273-280
• /
• 2022

Along with the advancement of deep learning technology, securing high-quality dataset for verification of developed technology is emerging as an important issue, and developing robust deep learning models to the domestic road environment is focused by many research groups. Especially, unlike expressways and automobile-only roads, in the complex city driving environment, various dynamic objects such as motorbikes, electric kickboards, large buses/truck, freight cars, pedestrians, and traffic lights are mixed in city road. In this paper, we built our dataset through multi camera-based processing (collection, refinement, and annotation) including the various objects in the city road and estimated quality and validity of our dataset by using YOLO-based model in object detection. Then, quantitative evaluation of our dataset is performed by comparing with the public dataset and qualitative evaluation of it is performed by comparing with experiment results using open platform. We generated our 2D dataset based on annotation rules of KITTI/COCO dataset, and compared the performance with the public dataset using the evaluation rules of KITTI/COCO dataset. As a result of comparison with public dataset, our dataset shows about 3 to 53% higher performance and thus the effectiveness of our dataset was validated.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.114-121
• /
• 2019

This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in 'tfrecords' format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.

• 한국전자통신학회논문지
• /
• 제15권1호
• /
• pp.85-92
• /
• 2020

심층학습은 많은 양의 데이터셋을 학습에 활용하여 객체 분류, 검출, 분할 등의 영상 분석에 탁월한 성능을 나타내고 있다. 본 논문에서는 데이터셋의 종류가 다양한 얼굴 표정인식 데이터셋들을 활용하여 학습 데이터셋의 특성이 심층학습 성능에 영향을 줄 수 있음을 확인하고, 각 학습 데이터셋에 적합한 심층학습 모델의 구성 요소를 설정하는 방법을 제안한다. 제안하는 방법은 심층학습 모델의 성능에 영향을 주는 구성 요소인 활성함수, 그리고 최적화 알고리즘을 유전 알고리즘을 이용하여 선정한다. CK+, MMI, KDEF 데이터셋에 대해서 널리 활용되고 있는 심층학습 모델의 각 구성 요소별 다양한 알고리즘을 적용하여 성능을 비교 분석하고, 유전 알고리즘을 적용하여 최적의 구성 요소를 선정할 수 있음을 시뮬레이션을 통하여 확인한다.