• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1143-1150
• /
• 2023

The global climate crisis and the implementation of low-carbon policies have led to a growing interest in renewable energy and a growing number of related industries. Among them, solar power is attracting attention as a representative eco-friendly energy that does not deplete and does not emit pollutants or greenhouse gases. As a result, the supplement of solar power facility is increasing all over the world. However, solar power is easily affected by the environment such as geography and weather, so accurate solar power forecast is important for stable operation and efficient management. However, it is very hard to predict the exact amount of solar power using statistical methods. In addition, the conventional prediction methods have focused on only short- or long-term prediction, which causes to take long time to obtain various prediction models with different prediction horizons. Therefore, this study utilizes a many-to-many structure of a recurrent neural network (RNN) to integrate short-term and long-term predictions of solar power generation. We compare various RNN-based very short- and long-term prediction methods for solar power in terms of MSE and R² values.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.69-91
• /
• 2021

Credit Bureaus in Korea commonly use financial transaction information of the past and present time for calculating an individual's credit scores. Compared to other rating factors, the repayment history information accounts for a larger weights on credit scores. Accordingly, despite full redemption of overdue payments, late payment history is reflected negatively for the assessment of credit scores for certain period of the time. An individual with debt delinquency can be classified into two groups; (1) the individuals who have faithfully paid off theirs overdue debts(Normal Repayment), and (2) those who have not and as differences of creditworthiness between these two groups do exist, it needs to grant relatively higher credit scores to the former individuals with normal repayment. This study is designed to analyze the factors of normal repayment of Korean financial debt delinquents based on credit information of personal loan, overdue payments, redemption from Korea Credit Information Services. As a result of the analysis, the number of overdue and the type of personal loan and delinquency were identified as significant variables affecting normal repayment and among applied methodologies, neural network models suggested the highest classification accuracy. The findings of this study are expected to improve the performance of individual credit scoring model by identifying the factors affecting normal repayment of a financial debt delinquent.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1909-1917
• /
• 2021

Objective: Muscle quantity and quality can be measured with an automated system on CT. However, the effects of contrast phases on the muscle measurements have not been established, which we aimed to investigate in this study. Materials and Methods: Muscle quantity was measured according to the skeletal muscle area (SMA) measured by a convolutional neural network-based automated system at the L3 level in 89 subjects undergoing multiphasic abdominal CT comprising unenhanced phase, arterial phase, portal venous phase (PVP), or delayed phase imaging. Muscle quality was analyzed using the mean muscle density and the muscle quality map, which comprises normal and low-attenuation muscle areas (NAMA and LAMA, respectively) based on the muscle attenuation threshold. The SMA, mean muscle density, NAMA, and LAMA were compared between PVP and other phases using paired t tests. Bland-Altman analysis was used to evaluate the inter-phase variability between PVP and other phases. Based on the cutoffs for low muscle quantity and quality, the counts of individuals who scored lower than the cutoff values were compared between PVP and other phases. Results: All indices showed significant differences between PVP and other phases (p < 0.001 for all). The SMA, mean muscle density, and NAMA increased during the later phases, whereas LAMA decreased during the later phases. Bland-Altman analysis showed that the mean differences between PVP and other phases ranged -2.1 to 0.3 cm² for SMA, -12.0 to 2.6 cm² for NAMA, and -2.2 to 9.9 cm² for LAMA.The number of patients who were categorized as low muscle quantity did not significant differ between PVP and other phases (p ≥ 0.5), whereas the number of patients with low muscle quality significantly differed (p ≤ 0.002). Conclusion: SMA was less affected by the contrast phases. However, the muscle quality measurements changed with the contrast phases to greater extents and would require a standardization of the contrast phase for reliable measurement.

• 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.

• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.949-958
• /
• 2022

Objective: To investigate the feasibility of using a deep learning-based analysis of auscultation data to predict significant stenosis of arteriovenous fistulas (AVF) in patients undergoing hemodialysis requiring percutaneous transluminal angioplasty (PTA). Materials and Methods: Forty patients (24 male and 16 female; median age, 62.5 years) with dysfunctional native AVF were prospectively recruited. Digital sounds from the AVF shunt were recorded using a wireless electronic stethoscope before (pre-PTA) and after PTA (post-PTA), and the audio files were subsequently converted to mel spectrograms, which were used to construct various deep convolutional neural network (DCNN) models (DenseNet201, EfficientNetB5, and ResNet50). The performance of these models for diagnosing ≥ 50% AVF stenosis was assessed and compared. The ground truth for the presence of ≥ 50% AVF stenosis was obtained using digital subtraction angiography. Gradient-weighted class activation mapping (Grad-CAM) was used to produce visual explanations for DCNN model decisions. Results: Eighty audio files were obtained from the 40 recruited patients and pooled for the study. Mel spectrograms of "pre-PTA" shunt sounds showed patterns corresponding to abnormal high-pitched bruits with systolic accentuation observed in patients with stenotic AVF. The ResNet50 and EfficientNetB5 models yielded an area under the receiver operating characteristic curve of 0.99 and 0.98, respectively, at optimized epochs for predicting ≥ 50% AVF stenosis. However, Grad-CAM heatmaps revealed that only ResNet50 highlighted areas relevant to AVF stenosis in the mel spectrogram. Conclusion: Mel spectrogram-based DCNN models, particularly ResNet50, successfully predicted the presence of significant AVF stenosis requiring PTA in this feasibility study and may potentially be used in AVF surveillance.

• Journal of Korean Neurosurgical Society
• /
• v.67 no.1
• /
• pp.94-102
• /
• 2024

Objective : The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML). Methods : Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR). Results : We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables. Conclusion : The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.3
• /
• pp.281-301
• /
• 2024

The power cable tunnels which are part of the underground transmission line project, are constructed using the shield TBM method. The disc cutter among the shield TBM components plays an important role in breaking rock mass. Efficient tunnel construction is possible only when appropriate replacement occurs as the wear limit is reached or damage such as uneven wear occurs. A study was conducted to determine the wear conditions of disc cutter using a deep learning algorithm based on real-time measurement data of wear and rotation speed. Based on the results of full-scaled tunnelling tests, it was confirmed that measurement data was obtained differently depending on the wear conditions of disc cutter. Using real-time measurement data, an algorithm was developed to determine disc cutter wear characteristics based on a convolutional neural network model. Distributional patterns of data can be learned through CNN filters, and the performance of the model that can classify uniform wear and uneven wear through these pattern features.