• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.6
• /
• pp.983-990
• /
• 2011

Universal Soil Loss Equation (USLE) has been used to estimate potential long-term soil erosion in the fields. However, the USLE does not estimate sediment yield due to lack of module considering sediment delivery ratio (SDR) for watershed application. For that reason, the Sediment Assessment Tool for Effective Erosion Control (SATEEC) system was developed and applied to compute the sediment yield at watershed scale. However, the R factor of current SATEEC Ver. 2.1 was estimated based on 5-day antecedent rainfall, it is not related with fundamental concept of R factor. To compute R factor accurately, the energy of rainfall strikes should be considered. In this study, the R module in the SATEEC system was enhanced using formulas of Williams, Foster, Cooley, CREAMS which could consider the energy of rainfall strikes. The enhanced SATEEC system ver. 2.2 was applied to the Imha watershed and monthly sediment yield was estimated. As a result of this study, the $R^2$ and NSE values are 0.591 and 0.573 for calibration period, and 0.927 and 0.911 for validation period, respectively. The results demonstrate the enhanced SATEEC System estimates the sediment yield suitably, and it could be used to establish the detailed environmental policy standard using USLE input dataset at watershed scale.

• Journal of Veterinary Science
• /
• v.22 no.1
• /
• pp.2.1-2.10
• /
• 2021

Background: Diseases related to cerebrospinal fluid flow, such as hydrocephalus, syringomyelia, and Chiari malformation, are often found in small dogs. Although studies in human medicine have revealed a correlation with cerebrospinal fluid flow in these diseases by magnetic resonance imaging, there is little information and no standard data for normal dogs. Objectives: The purpose of this study was to obtain cerebrospinal fluid flow velocity data from the cerebral aqueduct and subarachnoid space at the foramen magnum in healthy beagle dogs. Methods: Six healthy beagle dogs were used in this experimental study. The dogs underwent phase-contrast and time-spatial labeling inversion pulse magnetic resonance imaging. Flow rate variations in the cerebrospinal fluid were observed using sagittal time-spatial labeling inversion pulse images. The pattern and velocity of cerebrospinal fluid flow were assessed using phase-contrast magnetic resonance imaging within the subarachnoid space at the foramen magnum level and the cerebral aqueduct. Results: In the ventral aspect of the subarachnoid space and cerebral aqueduct, the cerebrospinal fluid was characterized by a bidirectional flow throughout the cardiac cycle. The mean ± SD peak velocities through the ventral and dorsal aspects of the subarachnoid space and the cerebral aqueduct were 1.39 ± 0.13, 0.32 ± 0.12, and 0.76 ± 0.43 cm/s, respectively. Conclusions: Noninvasive visualization of cerebrospinal fluid flow movement with magnetic resonance imaging was feasible, and a reference dataset of cerebrospinal fluid flow peak velocities was obtained through the cervical subarachnoid space and cerebral aqueduct in healthy dogs.

• Journal of Korean society of Dental Hygiene
• /
• v.19 no.5
• /
• pp.731-742
• /
• 2019

Objectives: To analyze the association between sleep duration and the number of remaining teeth in people aged 65 years or older in order to provide basic data for improving sleep quality and developing oral health programs for teeth maintenance. Methods: The raw data for the analysis were obtained from the sixth Korean National Health and Nutrition Examination Survey (KNHANES) dataset, conducted between 2013 and 2015. The 4,340 subjects included in the study underwent oral examinations and then proceeded to answer related questions. The collected data were analyzed using SPSS (ver 23.0) program via composite samples, with the calculations for mean, standard deviation, chi-square test, and logistic return analysis being performed. Results: An analysis of the effect of sleep duration on the number of remaining teeth among people aged >65 years old showed that if the confounding variables were not corrected for, the risk of having less than 9 hours of sleep was 1.40 times higher (95% CI: 1.06-1.86). However, this was not statistically significant in models that corrected for gender, age, and other confounding variables (p>0.05). Conclusions: The association between sleep duration among the elderly with their number of remaining teeth was confirmed. Therefore, measures to improve sleep quality and oral care practices to maintain the remaining teeth in people over 65 years old should be developed.

• Computers and Concrete
• /
• v.27 no.4
• /
• pp.333-341
• /
• 2021

Steel slag, an industrial reject from the steel rolling process, has been identified as one of the suitable, environmentally friendly materials for concrete production. Given that the coarse aggregate portion represents about 70% of concrete constituents, other economic approaches have been found in the use of alternative materials such as steel slag in concrete. Unfortunately, a standard framework for its application is still lacking. Therefore, this study proposed functional model equations for the determination of strength properties (compression and splitting tensile) of steel slag aggregate concrete (SSAC), using gene expression programming (GEP). The study, in the experimental phase, utilized steel slag as a partial replacement of crushed rock, in steps 20%, 40%, 60%, 80%, and 100%, respectively. The predictor variables included in the analysis were cement, sand, granite, steel slag, water/cement ratio, and curing regime (age). For the model development, 60-75% of the dataset was used as the training set, while the remaining data was used for testing the model. Empirical results illustrate that steel aggregate could be used up to 100% replacement of conventional aggregate, while also yielding comparable results as the latter. The GEP-based functional relations were tested statistically. The minimum absolute percentage error (MAPE), and root mean square error (RMSE) for compressive strength are 6.9 and 1.4, and 12.52 and 0.91 for the train and test datasets, respectively. With the consistency of both the training and testing datasets, the model has shown a strong capacity to predict the strength properties of SSAC. The results showed that the proposed model equations are reliably suitable for estimating SSAC strength properties. The GEP-based formula is relatively simple and useful for pre-design applications.

• Journal of the Korea Convergence Society
• /
• v.11 no.12
• /
• pp.23-30
• /
• 2020

In this study, the relationship between natural gas (NG) data and gas-related environmental elements was performed using machine learning algorithms to predict the level of gas leakage risk without directly measuring gas leakage data. The study was based on open data provided by the server using the IoT-based remote control Picarro gas sensor specification. The naturel gas leaks into the air, it is a big problem for air pollution, environment and the health. The proposed method is multivariate outlier removing method based Random Forest (RF) classification for predicting risk of NG leak. After, unsupervised k-means clustering, the experimental dataset has done imbalanced data. Therefore, we focusing our proposed models can predict medium and high risk so best. In this case, we compared the receiver operating characteristic (ROC) curve, accuracy, area under the ROC curve (AUC), and mean standard error (MSE) for each classification model. As a result of our experiments, the evaluation measurements include accuracy, area under the ROC curve (AUC), and MSE; 99.71%, 99.57%, and 0.0016 for MOL_RF respectively.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.605-610
• /
• 2020

Software Defined Networking (SDN) is setting the standard for the management of networks due to its scalability, flexibility and functionality to program the network. The Distributed Denial of Service (DDoS) attack is most widely used to attack the SDN controller to bring down the network. Different methodologies have been utilized to detect DDoS attack previously. In this paper, first the dataset is obtained by Kaggle with 84 features, and then according to the rank, the 20 highest rank features are selected using Permutation Importance Algorithm. Then, the datasets are trained and tested with Convolution Neural Network (CNN) classifier model by utilizing deep learning techniques. Our proposed solution has achieved the best results, which will allow the critical systems which need more security to adopt and take full advantage of the SDN paradigm without compromising their security.

• Korean Journal of Clinical Pharmacy
• /
• v.31 no.2
• /
• pp.153-159
• /
• 2021

Background: With increasing economic evaluation studies on the treatment of or screening tools for liver diseases that cause hepatocellular carcinoma (HCC), interest in the analysis of the medical utilization and costs of HCC treatment is increasing. Therefore, we aimed to estimate the medical utilization and costs of HCC patients, and calculate the cost of main procedures for HCC treatment, including liver transplant (LT), hepatic resection (HR), radiofrequency ablation (RFA), and transarterial chemoembolization (TACE). Methods: We analyzed claim data from January to December 2018 from the Health Insurance and Review and Assessment Service-National Patient Sample (HIRA-NPS-2018) dataset, including data of patients diagnosed with HCC (Korean Standard Classification of Diseases code C22.0) who had at least one inpatient claim for HCC. Results: A total of 715 HCC patients were identified. In 2018, the yearly average medical cost per HCC patient was ₩18,460K (thousand), of which ₩14,870K was attributed to HCC. Among the total medical costs of HCC patients, the inpatient cost accounted for the largest portion of both the total medical and HCC-related costs. The major procedures of HCC treatment occurred most frequently in the order of TACE, RFA, HR, and LT. The average medical cost per treatment episode was the highest for LT (₩87,280K), followed by HR (₩10,026K), TACE (₩4,047K), and RFA (₩2,927K). Conclusion: By identifying the medical costs of HCC patients and the costs of the main procedures of HCC treatment, our results provide basic information that could be utilized for cost estimation in liver disease-related economic evaluation studies.

• The Korean Journal of Applied Statistics
• /
• v.34 no.2
• /
• pp.191-204
• /
• 2021

Visual Question Answering (VQA) and image captioning are tasks that require understanding of the features of images and linguistic features of text. Therefore, co-attention may be the key to both tasks, which can connect image and text. In this paper, we propose a model to achieve high performance for VQA by image caption generated using a pretrained standard transformer model based on MSCOCO dataset. Captions unrelated to the question can rather interfere with answering, so some captions similar to the question were selected to use based on a similarity to the question. In addition, stopwords in the caption could not affect or interfere with answering, so the experiment was conducted after removing stopwords. Experiments were conducted on VQA-v2 data to compare the proposed model with the deep modular co-attention network (MCAN) model, which showed good performance by using co-attention between images and text. As a result, the proposed model outperformed the MCAN model.

• Journal of the Korea Convergence Society
• /
• v.13 no.3
• /
• pp.33-41
• /
• 2022

In this article, we proposed to predict natural gas (NG) leakage levels through feature selection based on a factor analysis (FA) of the integrating the Korean Meteorological Agency data and natural gas leakage data for considering complex factors. The paper has been divided into three modules. First, we filled missing data based on the linear interpolation method on the integrated data set, and selected essential features using FA with OrdinalEncoder (OE)-based normalization. The dataset is labeled by K-means clustering. The final module uses four algorithms, K-nearest neighbors (KNN), decision tree (DT), random forest (RF), Naive Bayes (NB), to predict gas leakage levels. The proposed method is evaluated by the accuracy, area under the ROC curve (AUC), and mean standard error (MSE). The test results indicate that the OrdinalEncoder-Factor analysis (OE-F)-based classification method has improved successfully. Moreover, OE-F-based KNN (OE-F-KNN) showed the best performance by giving 95.20% accuracy, an AUC of 96.13%, and an MSE of 0.031.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4439-4455
• /
• 2021

Compared with two-stage object detection algorithms, one-stage algorithms provide a better trade-off between real-time performance and accuracy. However, these methods treat the intermediate features equally, which lacks the flexibility to emphasize meaningful information for classification and location. Besides, they ignore the interaction of contextual information from different scales, which is important for medium and small objects detection. To tackle these problems, we propose an image pyramid network based on dual attention mechanism (DAIPNet), which builds an image pyramid to enrich the spatial information while emphasizing multi-scale informative features based on dual attention mechanisms for one-stage object detection. Our framework utilizes a pre-trained backbone as standard detection network, where the designed image pyramid network (IPN) is used as auxiliary network to provide complementary information. Here, the dual attention mechanism is composed of the adaptive feature fusion module (AFFM) and the progressive attention fusion module (PAFM). AFFM is designed to automatically pay attention to the feature maps with different importance from the backbone and auxiliary network, while PAFM is utilized to adaptively learn the channel attentive information in the context transfer process. Furthermore, in the IPN, we build an image pyramid to extract scale-wise features from downsampled images of different scales, where the features are further fused at different states to enrich scale-wise information and learn more comprehensive feature representations. Experimental results are shown on MS COCO dataset. Our proposed detector with a 300 × 300 input achieves superior performance of 32.6% mAP on the MS COCO test-dev compared with state-of-the-art methods.