• Journal of the Korean Society of Radiology
• /
• v.16 no.1
• /
• pp.25-34
• /
• 2022

Brain computed tomography (CT) is useful for brain lesion diagnosis, such as brain hemorrhage, due to non-invasive methodology, 3-dimensional image provision, low radiation dose. However, there has been numerous misdiagnosis owing to a lack of radiologist and heavy workload. Recently, object detection technologies based on artificial intelligence have been developed in order to overcome the limitations of traditional diagnosis. In this study, the applicability of a deep learning-based YOLOv5s model was evaluated for brain hemorrhage detection using brain CT images. Also, the effect of hyperparameters in the trained YOLOv5s model was analyzed. The YOLOv5s model consisted of backbone, neck and output modules. The trained model was able to detect a region of brain hemorrhage and provide the information of the region. The YOLOv5s model was trained with various activation functions, optimizer functions, loss functions and epochs, and the performance of the trained model was evaluated in terms of brain hemorrhage detection accuracy and training time. The results showed that the trained YOLOv5s model is able to provide a bounding box for a region of brain hemorrhage and the accuracy of the corresponding box. The performance of the YOLOv5s model was improved by using the mish activation function, the stochastic gradient descent (SGD) optimizer function and the completed intersection over union (CIoU) loss function. Also, the accuracy and training time of the YOLOv5s model increased with the number of epochs. Therefore, the YOLOv5s model is suitable for brain hemorrhage detection using brain CT images, and the performance of the model can be maximized by using appropriate hyperparameters.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.27-40
• /
• 2023

With the increase in the spread of smart devices and the impact of COVID-19, the consumption of media contents through smart devices has significantly increased. Along with this trend, the amount of media contents viewed through OTT platforms is increasing, that makes contents recommendations on these platforms more important. Previous contents-based recommendation researches have mostly utilized metadata that describes the characteristics of the contents, with a shortage of researches that utilize the contents' own descriptive metadata. In this paper, various text data including titles and synopses that describe the contents were used to recommend similar contents. KLUE-RoBERTa-large, a Korean language model with excellent performance, was used to train the model on the text data. A dataset of over 20,000 contents metadata including titles, synopses, composite genres, directors, actors, and hash tags information was used as training data. To enter the various text features into the language model, the features were concatenated using special tokens that indicate each feature. The test set was designed to promote the relative and objective nature of the model's similarity classification ability by using the three contents comparison method and applying multiple inspections to label the test set. Genres classification and hash tag classification prediction tasks were used to fine-tune the embeddings for the contents meta text data. As a result, the hash tag classification model showed an accuracy of over 90% based on the similarity test set, which was more than 9% better than the baseline language model. Through hash tag classification training, it was found that the language model's ability to classify similar contents was improved, which demonstrated the value of using a language model for the contents-based filtering.

• Journal of Aerospace System Engineering
• /
• v.17 no.4
• /
• pp.67-74
• /
• 2023

Recently, Urban Aircraft Mobility (UAM) has been attracting attention as a transportation system of the future, and small drones also play a role in various industries. The failure of various types of aviation systems can lead to crashes, which can result in significant property damage or loss of life. In the defense industry, where aviation systems are widely used, the failure of aviation systems can lead to mission failure. Therefore, this study proposes an anomaly detection model using deep learning technology to detect anomalies in aviation systems to improve the reliability of development and production, and prevent accidents during operation. As training and evaluating data sets, current data from aviation systems in an extremely low-temperature environment was utilized, and a deep learning network was implemented using the convolutional neural network, which is a deep learning technique that is commonly used for image recognition. In an extremely low-temperature environment, various types of failure occurred in the system's internal sensors and components, and singular points in current data were observed. As a result of training and evaluating the model using current data in the case of system failure and normal, it was confirmed that the abnormality was detected with a recall of 98 % or more.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.27-30
• /
• 2022

The plasma process, which has many advantages in terms of efficiency and environment compared to conventional process methods, is widely used in semiconductor manufacturing. Plasma Sheath is a dark region observed between the plasma bulk and the chamber wall surrounding it or the electrode. The Plasma Sheath Monitoring Sensor (PSMS) measures the difference in voltage between the plasma and the electrode and the RF power applied to the electrode in real time. The PSMS data, therefore, are expected to have a high correlation with the state of plasma in the plasma chamber. In this study, a model for predicting the state of nitrogen ions in the plasma chamber is training by a deep learning machine learning techniques using PSMS data. For the data used in the study, PSMS data measured in an experiment with different power and pressure settings were used as training data, and the ratio, flux, and density of nitrogen ions measured in plasma bulk and Si substrate were used as labels. The results of this study are expected to be the basis of artificial intelligence technology for the optimization of plasma processes and real-time precise control in the future.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.343-350
• /
• 2022

It is worth verifying the effectiveness of data integration between data with different features. This study investigated whether the data integration affects the accuracy of deep neural network (DNN), and which integration method shows the best improvement. This study used two different public datasets. One public dataset was taken in an actual farm in India. And another was taken in a laboratory environment in Korea. Leaf images were selected from two different public datasets to have five classes which includes normal and four different types of plant diseases. DNN used pre-trained VGG16 as a feature extractor and multi-layer perceptron as a classifier. Data were integrated into three different ways to be used for the training process. DNN was trained in a supervised manner via the integrated data. The trained DNN was evaluated by using a test dataset taken in an actual farm. DNN shows the best accuracy for the test dataset when DNN was first trained by images taken in the laboratory environment and then trained by images taken in the actual farm. The results show that data integration between plant images taken in a different environment helps improve the performance of deep neural networks. And the results also confirmed that independent use of plant images taken in different environments during the training process is more effective in improving the performance of DNN.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• 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.

• Korean Journal of Radiology
• /
• v.23 no.8
• /
• pp.811-820
• /
• 2022

Objective: To develop a model incorporating radiomic features and clinical factors to accurately predict acute ischemic stroke (AIS) outcomes. Materials and Methods: Data from 522 AIS patients (382 male [73.2%]; mean age ± standard deviation, 58.9 ± 11.5 years) were randomly divided into the training (n = 311) and validation cohorts (n = 211). According to the modified Rankin Scale (mRS) at 6 months after hospital discharge, prognosis was dichotomized into good (mRS ≤ 2) and poor (mRS > 2); 1310 radiomics features were extracted from diffusion-weighted imaging and apparent diffusion coefficient maps. The minimum redundancy maximum relevance algorithm and the least absolute shrinkage and selection operator logistic regression method were implemented to select the features and establish a radiomics model. Univariable and multivariable logistic regression analyses were performed to identify the clinical factors and construct a clinical model. Ultimately, a multivariable logistic regression analysis incorporating independent clinical factors and radiomics score was implemented to establish the final combined prediction model using a backward step-down selection procedure, and a clinical-radiomics nomogram was developed. The models were evaluated using calibration, receiver operating characteristic (ROC), and decision curve analyses. Results: Age, sex, stroke history, diabetes, baseline mRS, baseline National Institutes of Health Stroke Scale score, and radiomics score were independent predictors of AIS outcomes. The area under the ROC curve of the clinical-radiomics model was 0.868 (95% confidence interval, 0.825-0.910) in the training cohort and 0.890 (0.844-0.936) in the validation cohort, which was significantly larger than that of the clinical or radiomics models. The clinical radiomics nomogram was well calibrated (p > 0.05). The decision curve analysis indicated its clinical usefulness. Conclusion: The clinical-radiomics model outperformed individual clinical or radiomics models and achieved satisfactory performance in predicting AIS outcomes.

• Journal of National Security and Military Science
• /
• s.1
• /
• pp.71-111
• /
• 2003

The key lessons of the very complex modern war can be dangerously misleading to the outsiders. The efforts trying to draw lessons learned from the Iraq War (OIF : Operation Iraqi Freedom) may be biased by the view of point by Americans, because most of war episodes have been come from the Western media coverage. More serious bias can be committed thanks to the differences of warfighting doctrines and military technology between US forces and ROK forces. However, OIF-fought allied commanders and outside military experts said this campaign exemplified 21st-century warfare: swift, agile and decisive, employing overpowering technology to bring relentless violence to bear in many places at once. Even though the campaign evolved differently than anticipated, allied forces regrouped and regained the initiative remarkably quickly, thanks in large part to a new command flexibility, tied to new technology that made possible the more rapid sharing of data. These factors permitted "new air-land dynamic". The things that compel that are good sensors networked with good intelligence disseminated through a robust networking system, which then yields speed. Speed turns out to be a very important factor for conducting "Rapid Decisive Operations" relied on joint "Mass of Effects". ROK forces facing the heaviest ground threat in the world may learn more from Cold War era-typed US Army 3rd Infantry Division (3ID), which operating considerably beyond existing doctrine. 3ID flew its personnel into Kuwait to meet up with equipment already located in the region as pre-positioned stock. During OIF, the division conducted continuous offensive operations over 230km deep battlespace for 21 days. The lessons learned for ROK army to prepare tomorrow's war may be found from 3ID in its training, command and control, task organization, firepower and battlespace management, and logistics.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.67-72
• /
• 2020

The fifth generation (5G) mobile communication has an impact on the human life over the whole world, nowadays, through the artificial intelligence (AI) and the internet of things (IoT). The low latency of the 5G new radio (NR) access is implemented by the state-of-the art technologies, such as non-orthogonal multiple access (NOMA). This paper investigates a practical issue that in NOMA, for the practical channel models, such as fading channel environments, the successive interference cancellation (SIC) should be performed on the stronger channel users with low power allocation. Only if the SIC is performed on the user with the stronger channel gain, NOMA performs better than orthogonal multiple access (OMA). Otherwise, NOMA performs worse than OMA. Such the superiority requirement can be easily implemented for the channel being static or slow varying, compared to the block interval time. However, most mobile channels experience fading. And symbol by symbol channel estimations and in turn each symbol time, selections of the SIC-performing user look infeasible in the practical environments. Then practically the block of symbols uses the single channel estimation, which is obtained by the training sequence at the head of the block. In this case, not all the symbol times the SIC is performed on the stronger channel user. Sometimes, we do perform the SIC on the weaker channel user; such cases, NOMA performs worse than OMA. Thus, we can say that by what percent NOMA is better than OMA. This paper calculates analytically the percentage by which NOMA performs better than OMA in the practical mobile communication systems. We show analytically that the percentage for NOMA being better than OMA is only the function of the ratio of the stronger channel gain variance to weaker. In result, not always, but almost time, NOMA could perform better than OMA.