• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.12
• /
• pp.1588-1594
• /
• 2020

In this paper, we discuss a data balancing method for learning a neural network that generates digital holograms using a deep neural network (DNN). Deep neural networks are based on deep learning (DL) technology and use a generative adversarial network (GAN) series. The fringe pattern, which is the basic unit of a hologram to be created through a deep neural network, has very different data types depending on the hologram plane and the position of the object. However, because the criteria for classifying the data are not clear, an imbalance in the training data may occur. The imbalance of learning data acts as a factor of instability in learning. Therefore, it presents a method for classifying and balancing data for which the classification criteria are not clear. And it shows that learning is stabilized through this.

• The Journal of Society for e-Business Studies
• /
• v.26 no.1
• /
• pp.107-126
• /
• 2021

In e-commerce, rapid and accurate automatic product classification according to product information is important. Recent developments in deep learning technology have been actively applied to automatic product classification. In order to develop a deep learning model with good performance, the quality of training data and data preprocessing suitable for the model are crucial. In this study, when categories are inferred based on text product data using a deep learning model, both effects of the data preprocessing and of the selection of training data are extensively compared and analyzed. We employ our CNN model as an example of deep learning model. In the experimental analysis, we use a real e-commerce data to ensure the verification of the study results. The empirical analysis and results shown in this study may be meaningful as a reference study for improving performance when developing a deep learning product classification model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.6
• /
• pp.1227-1236
• /
• 2021

Adversarial attack, one of the attacks on deep learning classification model, is attack that add indistinguishable perturbations to input data and cause deep learning classification model to misclassify the input data. There are various adversarial attack algorithms. Accordingly, many studies have been conducted to detect adversarial attack but few studies have been conducted to classify what adversarial attack algorithms to generate adversarial input. if adversarial attacks can be classified, more robust deep learning classification model can be established by analyzing differences between attacks. In this paper, we proposed a model that detects and classifies adversarial attacks by constructing a random forest classification model with input features extracted from a target deep learning model. In feature extraction, feature is extracted from a output value of hidden layer based on class predicted by the target deep learning model. Through Experiments the model proposed has shown 3.02% accuracy on clean data, 0.80% accuracy on adversarial data higher than the result of pre-existing studies and classify new adversarial attack that was not classified in pre-existing studies.

• Journal of radiological science and technology
• /
• v.46 no.6
• /
• pp.535-542
• /
• 2023

This study aimed to implement a deep learning model that can perform quantitative quality control through ACTS software used for quantitative evaluation of ACR phantom in CT quality control and evaluate its usefulness. By changing the scanning conditions, images of three modules of the ACR phantom's slice thickness (ST), low contrast resolution (LC), and high contrast resolution (HC) were obtained and classified as ACTS software. The deep learning model used ResNet18, implementing three models in which ST, HC, and LC were learned with epoch 50 and an integrated model in which three modules were learned with Epoch 10, 30, and 50 at once. The performance of each model was evaluated through Accuracy and Loss. When comparing and evaluating the accuracy and loss function values of the deep learning models by ST, LC, and HC modules, the Accuracy and Loss of the HC model were the best with 100% and 0.0081, and in the integrated model according to the Epoch value, Accuracy and Loss with epoch 50 were the best with 96.29% and 0.1856. This paper showed that quantitative quality control is possible through a deep learning model, and it can be used as a basis and evidence for applying deep learning to the CT quality control.

• Korean Journal of Radiology
• /
• v.22 no.4
• /
• pp.612-623
• /
• 2021

Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

• Geophysics and Geophysical Exploration
• /
• v.23 no.2
• /
• pp.72-88
• /
• 2020

Recent rapid advances in computer hardware performance have led to relatively low computational costs, increasing the number of applications of machine-learning techniques to geophysical problems. In particular, deep-learning techniques are gaining in popularity as the number of cases successfully solving complex and nonlinear problems has gradually increased. In this paper, applications of seismic data denoising methods using deep-learning techniques are introduced and investigated. Depending on the type of attenuated noise, these studies are grouped into denoising applications of coherent noise, random noise, and the combination of these two types of noise. Then, we investigate the deep-learning techniques used to remove the corresponding noise. Unlike conventional methods used to attenuate seismic noise, deep neural networks, a typical deep-learning technique, learn the characteristics of the noise independently and then automatically optimize the parameters. Therefore, such methods are less sensitive to generalized problems than conventional methods and can reduce labor costs. Several studies have also demonstrated that deep-learning techniques perform well in terms of computational cost and denoising performance. Based on the results of the applications covered in this paper, the pros and cons of the deep-learning techniques used to remove seismic noise are analyzed and discussed.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• Imaging Science in Dentistry
• /
• v.51 no.3
• /
• pp.237-242
• /
• 2021

Purpose: The aim of this study was to analyse and review deep learning convolutional neural networks for detecting and diagnosing early-stage dental caries on periapical radiographs. Materials and Methods: In order to conduct this review, the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA) guidelines were followed. Studies published from 2015 to 2021 under the keywords(deep convolutional neural network) AND (caries), (deep learning caries) AND (convolutional neural network) AND (caries) were systematically reviewed. Results: When dental caries is improperly diagnosed, the lesion may eventually invade the enamel, dentin, and pulp tissue, leading to loss of tooth function. Rapid and precise detection and diagnosis are vital for implementing appropriate prevention and treatment of dental caries. Radiography and intraoral images are considered to play a vital role in detecting dental caries; nevertheless, studies have shown that 20% of suspicious areas are mistakenly diagnosed as dental caries using this technique; hence, diagnosis via radiography alone without an objective assessment is inaccurate. Identifying caries with a deep convolutional neural network-based detector enables the operator to distinguish changes in the location and morphological features of dental caries lesions. Deep learning algorithms have broader and more profound layers and are continually being developed, remarkably enhancing their precision in detecting and segmenting objects. Conclusion: Clinical applications of deep learning convolutional neural networks in the dental field have shown significant accuracy in detecting and diagnosing dental caries, and these models hold promise in supporting dental practitioners to improve patient outcomes.

• Journal of Gifted/Talented Education
• /
• v.25 no.6
• /
• pp.857-879
• /
• 2015

This study investigated the relationships among middle school students' perceptions on the roles of online tutor, their deep learning, achievement, and overall evaluation of learning experiences in the context of inquiry based online gifted mathematics and science learning. For this purpose, 249 middle school students who took online course were surveyed about their perceptions on the degree to which their tutor performed the roles as an online tutor. The students were also asked about the activities which indicate deep learning approaches and overall course experiences such as the level of satisfaction, understanding and engagement in the course. The regression analyses were conducted to examine the relationships of students' perceptions on the roles of online tutor, deep learning, achievement, and overall course experiences. The results first showed that the roles of online tutor which affects students' deep learning approach such as high-order learning, integrative learning, reflective learning were the role as a subject matter and evaluation expert. Among the sub variables of deep learning approach the variable that was related to students' overall achievement was the use of high-order learning strategy. Second, the achievement in inquiry task was related to the role of tutor as a guide of learning process and method. Third, students' overall course evaluations such as the level of satisfaction, understanding and engagement were not related to any role of tutor.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.55-60
• /
• 2020

Adaptive recommendation systems have been developed with big data processing as a system that provides services tailored to users based on user information and usage patterns. Deep learning can be used in these adaptive recommendation systems to handle big data, providing more efficient user-friendly recommendation services. In this paper, we propose a system that uses deep learning to categorize and recommend tourism types to suit the user's personality. The system was divided into three layers according to its core role to increase efficiency and facilitate maintenance. Each layer consists of the Service Provisioning Layer that real users encounter, the Recommendation Service Layer, which provides recommended services based on user information entered, and the Adaptive Definition Layer, which learns the types of tourism suitable for personality types. The proposed system is highly scalable because it provides services using deep learning, and the adaptive recommendation system connects the user's personality type and tourism type to deliver the data to the user in a flexible manner.