• Korean Journal of Radiology
• /
• v.21 no.10
• /
• pp.1165-1177
• /
• 2020

Objective: To assess the feasibility of applying a deep learning-based denoising technique to coronary CT angiography (CCTA) along with iterative reconstruction for additional noise reduction. Materials and Methods: We retrospectively enrolled 82 consecutive patients (male:female = 60:22; mean age, 67.0 ± 10.8 years) who had undergone both CCTA and invasive coronary artery angiography from March 2017 to June 2018. All included patients underwent CCTA with iterative reconstruction (ADMIRE level 3, Siemens Healthineers). We developed a deep learning based denoising technique (ClariCT.AI, ClariPI), which was based on a modified U-net type convolutional neural net model designed to predict the possible occurrence of low-dose noise in the originals. Denoised images were obtained by subtracting the predicted noise from the originals. Image noise, CT attenuation, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were objectively calculated. The edge rise distance (ERD) was measured as an indicator of image sharpness. Two blinded readers subjectively graded the image quality using a 5-point scale. Diagnostic performance of the CCTA was evaluated based on the presence or absence of significant stenosis (≥ 50% lumen reduction). Results: Objective image qualities (original vs. denoised: image noise, 67.22 ± 25.74 vs. 52.64 ± 27.40; SNR [left main], 21.91 ± 6.38 vs. 30.35 ± 10.46; CNR [left main], 23.24 ± 6.52 vs. 31.93 ± 10.72; all p < 0.001) and subjective image quality (2.45 ± 0.62 vs. 3.65 ± 0.60, p < 0.001) improved significantly in the denoised images. The average ERDs of the denoised images were significantly smaller than those of originals (0.98 ± 0.08 vs. 0.09 ± 0.08, p < 0.001). With regard to diagnostic accuracy, no significant differences were observed among paired comparisons. Conclusion: Application of the deep learning technique along with iterative reconstruction can enhance the noise reduction performance with a significant improvement in objective and subjective image qualities of CCTA images.

• Journal of the Korean Geosynthetics Society
• /
• v.21 no.2
• /
• pp.21-30
• /
• 2022

Shear strength is the most important indicator in the evaluation of rock slope stability. It is generally estimated by comparing the results of existing literature data, back analysis, experiments and etc. There are additional variables related to the state of discontinuity to consider in the shear strength of the rock slope. It is difficult to determine whether these variables exist through drilling, and it is also difficult to find an exact relationship with shear strength. In this study, the data calculated through back analysis were used. The relationship between previously considered variables was applied to deep learning and the possibility for estimating shear strength of rock slope was explored. For comparison, an existing simple linear regression model and a deep learning algorithm, a deep neural network(DNN) model, were used. Although each analysis model derived similar prediction results, the explanatory power of DNN was improved with a small differences.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.1-7
• /
• 2019

Recently, various approaches to detect network attacks using machine learning have been studied and are being applied to detect new attacks and to increase precision. However, the machine learning method is dependent on feature extraction and takes a long time and complexity. It also has limitation of performace due to learning data imbalance. In this study, we propose a method to solve the degradation of classification performance due to imbalance of learning data among the limit points of detection system. To do this, we generate data using Generative Adversarial Networks (GANs) and propose a classification method using Convolutional Neural Networks (CNNs). Through this approach, we can confirm that the accuracy is improved when applied to the NSL-KDD and UNSW-NB15 datasets.

• Imaging Science in Dentistry
• /
• v.53 no.1
• /
• pp.27-34
• /
• 2023

Purpose: The aim of this study was to clarify the influence of training with a different kind of lesion on the performance of a target model. Materials and Methods: A total of 310 patients(211 men, 99 women; average age, 47.9±16.1 years) were selected and their panoramic images were used in this study. We created a source model using panoramic radiographs including mandibular radiolucent cyst-like lesions (radicular cyst, dentigerous cyst, odontogenic keratocyst, and ameloblastoma). The model was simulatively transferred and trained on images of Stafne's bone cavity. A learning model was created using a customized DetectNet built in the Digits version 5.0 (NVIDIA, Santa Clara, CA). Two machines(Machines A and B) with identical specifications were used to simulate transfer learning. A source model was created from the data consisting of ameloblastoma, odontogenic keratocyst, dentigerous cyst, and radicular cyst in Machine A. Thereafter, it was transferred to Machine B and trained on additional data of Stafne's bone cavity to create target models. To investigate the effect of the number of cases, we created several target models with different numbers of Stafne's bone cavity cases. Results: When the Stafne's bone cavity data were added to the training, both the detection and classification performances for this pathology improved. Even for lesions other than Stafne's bone cavity, the detection sensitivities tended to increase with the increase in the number of Stafne's bone cavities. Conclusion: This study showed that using different lesions for transfer learning improves the performance of the model.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.209-224
• /
• 2024

Speaker verification is becoming popular as a method of non-face-to-face identity authentication. It involves determining whether two voice data belong to the same speaker. In cases where the criminal's voice remains at the crime scene, it is vital to establish a speaker verification system that can accurately compare the two voice evidence. In this study, to achieve this, a new speaker verification system was built using a deep learning model for Korean language. High-dimensional voice data with a high variability like background noise made it necessary to use deep learning-based methods for speaker matching. To construct the matching algorithm, the ECAPA-TDNN model, known as the most famous deep learning system for speaker verification, was selected. A large dataset of the voice data, Voxceleb, collected from people of various nationalities without Korean. To study the appropriate form of datasets necessary for learning the Korean language, experiments were carried out to find out how Korean voice data affects the matching performance. The results showed that when comparing models learned only with Voxceleb and models learned with datasets combining Voxceleb and Korean datasets to maximize language and speaker diversity, the performance of learning data, including Korean, is improved for all test sets.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.113-119
• /
• 2023

Most infrastructure structures were completed during periods of economic growth. The number of infrastructure structures reaching their lifespan is increasing, and the proportion of old structures is gradually increasing. The functions and performance of these structures at the time of design may deteriorate and may even lead to safety accidents. To prevent this repercussion, accurate inspection and appropriate repair are requisite. To this end, demand is increasing for computer vision and deep learning technology to accurately detect even minute cracks. However, deep learning algorithms require a large number of training data. In particular, label images indicating the location of cracks in the image are required. To secure a large number of those label images, a lot of labor and time are consumed. To reduce these costs as well as increase detection accuracy, this study proposed a learning structure based on mean teacher method. This learning structure was trained on a dataset of 900 labeled image dataset and 3000 unlabeled image dataset. The crack detection network model was evaluated on over 300 labeled image dataset, and the detection accuracy recorded a mean intersection over union of 89.23% and an F1 score of 89.12%. Through this experiment, it was confirmed that detection performance was improved compared to supervised learning. It is expected that this proposed method will be used in the future to reduce the cost required to secure label images.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.541-552
• /
• 2023

Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

• Journal of The Korean Association For Science Education
• /
• v.30 no.5
• /
• pp.533-543
• /
• 2010

This paper analyzed the improvement of cognitive level of the students and interactions which occurred in each step of free-topic scientific inquiry to help science teachers understand free-topic scientific inquiry better. Free-topic scientific inquiry is helpful to students with a deep strategic learning goal orientation type or a deep strategic ability goal orientation type in their transition (2B/3A) of cognitive levels. Most students have difficulties in the phase of establishing topics and hypotheses. The result says that the discussion techniques are improved through free-topic scientific inquiry, but the quality of interaction is not easily improved. The deep strategic learning goal orientation type concretizes opinion through interaction in free-topic scientific inquiry. The deep strategic ability goal orientation type are actively involve in the interaction, but they pay no attention to the process because they stick to the result. The surface strategic ability goal orientation type can not deepen a discussion due to high frequency of low level inquiry. However, the frequency of high level inquiry increases through free topic scientific inquiry operation. As a result, the characteristics of free-topic scientific inquiry were discussed and the educational implications of the progress of free-topic scientific inquiry and the organization of grouping were drawn.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.167-177
• /
• 2022

In order to obtain satellite image products using the image transmitted to the ground station after capturing the satellite images, many image pre/post-processing steps are involved. During the pre/post-processing, when converting from level 1R images to level 1G images, geometric correction is essential. An interpolation method necessary for geometric correction is inevitably used, and the quality of the level 1G images is determined according to the accuracy of the interpolation method. Also, it is crucial to speed up the interpolation algorithm by the level processor. In this paper, we proposed a lightweight CNN-based interpolation method required for geometric correction when converting from level 1R to level 1G. The proposed method doubles the resolution of satellite images and constructs a deep learning network with a lightweight deep convolutional neural network for fast processing speed. In addition, a feature map fusion method capable of improving the image quality of multispectral (MS) bands using panchromatic (PAN) band information was proposed. The images obtained through the proposed interpolation method improved by about 0.4 dB for the PAN image and about 4.9 dB for the MS image in the quantitative peak signal-to-noise ratio (PSNR) index compared to the existing deep learning-based interpolation methods. In addition, it was confirmed that the time required to acquire an image that is twice the resolution of the 36,500×36,500 input image based on the PAN image size is improved by about 1.6 times compared to the existing deep learning-based interpolation method.