• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.27 no.2
• /
• pp.71-86
• /
• 2022

The water quality index (WQI) has been widely used to evaluate marine water quality. The WQI in Korea is categorized into five classes by marine environmental standards. But, the WQI calculation on huge datasets is a very complex and time-consuming process. In this regard, the current study proposed machine learning (ML) based models to predict WQI class by using water quality datasets. Sihwa Lake, one of specially-managed coastal zone, was selected as a modeling site. In this study, adaptive boosting (AdaBoost) and tree-based pipeline optimization (TPOT) algorithms were used to train models and each model performance was evaluated by metrics (accuracy, precision, F1, and Log loss) on classification. Before training, the feature importance and sensitivity analysis were conducted to find out the best input combination for each algorithm. The results proved that the bottom dissolved oxygen (DO_Bot) was the most important variable affecting model performance. Conversely, surface dissolved inorganic nitrogen (DIN_Sur) and dissolved inorganic phosphorus (DIP_Sur) had weaker effects on the prediction of WQI class. In addition, the performance varied over features including stations, seasons, and WQI classes by comparing spatio-temporal and class sensitivities of each best model. In conclusion, the modeling results showed that the TPOT algorithm has better performance rather than the AdaBoost algorithm without considering feature selection. Moreover, the WQI class for unknown water quality datasets could be surely predicted using the TPOT model trained with satisfactory training datasets.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.179-188
• /
• 2023

Recently, fake news disguises the form of news content and appears whenever important events occur, causing social confusion. Accordingly, artificial intelligence technology is used as a research to detect fake news. Fake news detection approaches such as automatically recognizing and blocking fake news through natural language processing or detecting social media influencer accounts that spread false information by combining with network causal inference could be implemented through deep learning. However, fake news detection is classified as a difficult problem to solve among many natural language processing fields. Due to the variety of forms and expressions of fake news, the difficulty of feature extraction is high, and there are various limitations, such as that one feature may have different meanings depending on the category to which the news belongs. In this paper, emotional change patterns are presented as an additional identification criterion for detecting fake news. We propose a model with improved performance by applying a convolutional neural network to a fake news data set to perform analysis based on content characteristics and additionally analyze emotional change patterns. Sentimental polarity is calculated for the sentences constituting the news and the result value dependent on the sentence order can be obtained by applying long-term and short-term memory. This is defined as a pattern of emotional change and combined with the content characteristics of news to be used as an independent variable in the proposed model for fake news detection. We train the proposed model and comparison model by deep learning and conduct an experiment using a fake news data set to confirm that emotion change patterns can improve fake news detection performance.

• 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.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.2
• /
• pp.61-68
• /
• 2024

The majority of high-speed railway bridges along the domestic Gyeongbu and Honam lines feature a PSC-box type structure with a span length ranging from 35 to 40m, which typically exhibits a first bending natural frequency of approximately 4 to 5Hz. When KTX high-speed trains transverse these bridges at speeds ranging from 290 to 310km/h, the vibration induced by the trains approaches the first bending natural frequency of the bridge. Furthermore, with the upcoming operation of a EMU-320 high-speed train and the anticipated increase in the speeds of these high-speed trains, there is a need to analyze the dynamic response of high-speed railway bridges. For this, based on measured responses from actual railway bridges, a numerical model was constructed using a numerical model updating technique. The dynamic response of the updated numerical model exhibited a strong agreement with the measured response from the actual railway bridges. Subsequently, this updated model was utilized to analyze the dynamic response characteristics of the bridges when KTX and EMU-320 trains operate at increased speeds. The maximum vertical displacement and acceleration at the mid-span of the bridges were also compared to those specified in the railway design standard with the increasing speed of KTX and EMU-320.

• Korean Journal of Radiology
• /
• v.22 no.6
• /
• pp.983-993
• /
• 2021

Objective: To investigate the image quality of ultralow-dose CT (ULDCT) of the chest reconstructed using a cycle-consistent generative adversarial network (CycleGAN)-based deep learning method in the evaluation of pulmonary tuberculosis. Materials and Methods: Between June 2019 and November 2019, 103 patients (mean age, 40.8 ± 13.6 years; 61 men and 42 women) with pulmonary tuberculosis were prospectively enrolled to undergo standard-dose CT (120 kVp with automated exposure control), followed immediately by ULDCT (80 kVp and 10 mAs). The images of the two successive scans were used to train the CycleGAN framework for image-to-image translation. The denoising efficacy of the CycleGAN algorithm was compared with that of hybrid and model-based iterative reconstruction. Repeated-measures analysis of variance and Wilcoxon signed-rank test were performed to compare the objective measurements and the subjective image quality scores, respectively. Results: With the optimized CycleGAN denoising model, using the ULDCT images as input, the peak signal-to-noise ratio and structural similarity index improved by 2.0 dB and 0.21, respectively. The CycleGAN-generated denoised ULDCT images typically provided satisfactory image quality for optimal visibility of anatomic structures and pathological findings, with a lower level of image noise (mean ± standard deviation [SD], 19.5 ± 3.0 Hounsfield unit [HU]) than that of the hybrid (66.3 ± 10.5 HU, p < 0.001) and a similar noise level to model-based iterative reconstruction (19.6 ± 2.6 HU, p > 0.908). The CycleGAN-generated images showed the highest contrast-to-noise ratios for the pulmonary lesions, followed by the model-based and hybrid iterative reconstruction. The mean effective radiation dose of ULDCT was 0.12 mSv with a mean 93.9% reduction compared to standard-dose CT. Conclusion: The optimized CycleGAN technique may allow the synthesis of diagnostically acceptable images from ULDCT of the chest for the evaluation of pulmonary tuberculosis.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.4
• /
• pp.305-330
• /
• 2023

Unlike NATM tunnels, Shield TBM tunnels have split linings. Therefore, the stress distribution of the lining is different even if the lining is under the same load. Representative methods for analyzing the stress generated in lining in Shield TBM tunnels include Non-joint Mode that does not consider connections and a 2-ring beam-spring model that considers ring-to-ring joints and segment connections. This study is an analysis method by Break-joint Mode. However, we do not consider the structural role of segment lining connections. The effectiveness of the modeling is verified by analyzing behavioral characteristics against vibration loads by modeling with segment connection interfaces to which vertical stiffness and shear stiffness, which are friction components, are applied. Unlike the Non-joint mode, where the greatest stress occurs on the crown for static loads such as earth pressure, the stress distribution caused by contact between segment lining and friction stiffness produced the smallest stress in the crown key segment where segment connections were concentrated. The stress distribution was clearly distinguished based on segment connections. The results of static analysis by earth pressure, etc., produced up to seven times the stress generated in Non-joint mode compared to the stress generated by Break-joint Mode. This result is consistent with the stress distribution pattern of the 2-ring beam-spring model. However, as for the stress value for the train vibration load, the stress of Break-joint Mode was greater than that of Non-joint mode. This is a different result from the static mechanics concept that a segment ring consisting of a combination of short members is integrated in the circumferential direction, resulting in a smaller stress than Non-joint mode with a relatively longer member length.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.69-88
• /
• 2022

One of the characteristics of South Korea's economic structure is that it is highly dependent on exports. Thus, many businesses are closely related to the global economy and diplomatic situation. In addition, small and medium-sized enterprises(SMEs) specialized in exporting are struggling due to the spread of COVID-19. Therefore, this study aimed to develop a model to forecast exports for next year to support SMEs' export strategy and decision making. Also, this study proposed a strategy to recommend promising export countries of each item based on the forecasting model. We analyzed important variables used in previous studies such as country-specific, item-specific, and macro-economic variables and collected those variables to train our prediction model. Next, through the exploratory data analysis(EDA) it was found that exports, which is a target variable, have a highly skewed distribution. To deal with this issue and improve predictive performance, we suggest a separated learning method. In a separated learning method, the whole dataset is divided into homogeneous subgroups and a prediction algorithm is applied to each group. Thus, characteristics of each group can be more precisely trained using different input variables and algorithms. In this study, we divided the dataset into five subgroups based on the exports to decrease skewness of the target variable. After the separation, we found that each group has different characteristics in countries and goods. For example, In Group 1, most of the exporting countries are developing countries and the majority of exporting goods are low value products such as glass and prints. On the other hand, major exporting countries of South Korea such as China, USA, and Vietnam are included in Group 4 and Group 5 and most exporting goods in these groups are high value products. Then we used LightGBM(LGBM) and Exponential Moving Average(EMA) for prediction. Considering the characteristics of each group, models were built using LGBM for Group 1 to 4 and EMA for Group 5. To evaluate the performance of the model, we compare different model structures and algorithms. As a result, it was found that the separated learning model had best performance compared to other models. After the model was built, we also provided variable importance of each group using SHAP-value to add explainability of our model. Based on the prediction model, we proposed a second-stage recommendation strategy for potential export countries. In the first phase, BCG matrix was used to find Star and Question Mark markets that are expected to grow rapidly. In the second phase, we calculated scores for each country and recommendations were made according to ranking. Using this recommendation framework, potential export countries were selected and information about those countries for each item was presented. There are several implications of this study. First of all, most of the preceding studies have conducted research on the specific situation or country. However, this study use various variables and develops a machine learning model for a wide range of countries and items. Second, as to our knowledge, it is the first attempt to adopt a separated learning method for exports prediction. By separating the dataset into 5 homogeneous subgroups, we could enhance the predictive performance of the model. Also, more detailed explanation of models by group is provided using SHAP values. Lastly, this study has several practical implications. There are some platforms which serve trade information including KOTRA, but most of them are based on past data. Therefore, it is not easy for companies to predict future trends. By utilizing the model and recommendation strategy in this research, trade related services in each platform can be improved so that companies including SMEs can fully utilize the service when making strategies and decisions for exports.

• Journal of the Korean Geophysical Society
• /
• v.3 no.4
• /
• pp.269-280
• /
• 2000

Rail vibration in city zone is becoming a serious environmental problem. In order to make a reduction plan for rail vibration, the research was conducted in which many experiments to measure actual rail vibration along the railroad through the central Deajeon area. A digital vibration level meter was used to measure rail vibration. Vibration levels of Z-axis were measured at every second for the duration of the train passing. The measuring station was placed at every 5m for the distance of 55m. A total of 353 different sets of vibration level were obtained. The signals were processed to get $L_{10}$ value and analyzed in terms of distance, train velocity, and number of trains. As a result, it has been found that rail vibration exceed the allowable vibraton limit of 60 dB, at the point of 25 m far from the railroad center, which is regulated by the las of vibration and noise. Train velocity was found to affect a little for vibration level within the zone. It was also found that a trench installed along a railroad could reduce vibration level up to approximately 10 percent. A model test was conducted to investigate the influence of the location and size of trench, on the transfer of vibration. A heavy steel ball was used to generate vibrations. On the basis obtained from this study, it could be concluded that the application of distance-attenuation and the installment of a trench along railroad could be applied as a reduction plan for rail vibration. Because limitions might exist to depend on the effect of distance attenuation, trenchs excavated along a railroad might be suggested as the most efficient solution to reduce railroad vibration.

• Journal of Korean Society of Forest Science
• /
• v.98 no.4
• /
• pp.435-443
• /
• 2009

The purpose of this study is to construct user satisfaction model using factor analysis and regression analysis through survey on various factors which decide users' satisfaction index of OK-SUNG Recreation Forest located in Gumi-city, Kyungbuk (newly opened on Dec, 26, 2007) and to suggest the right operation plans referring to the studies on existing recreation forests. The research results are as follows; The using behavior of recreation forests reported similar pattern to existing researches such as companion pattern, duration of status, ages and costs. The result of construction regression model after dividing of using behavior of recreation forests into two sections, which are physical sector and mental sector, showed that recreation environmental factor and inner recreation factor influenced more highly on satisfaction index. This result showed that the recreation factor, which is for obtaining mental satisfaction and friendship among companions, nature friendly factor and environmental factor more highly influence on the satisfaction index and the existing studies also support this result. Therefore, in order to offer higher standard recreation opportunities to the users, there needs consideration not only concerning experience facilities, walks and paths up a mountain, but also concerning the harmony between nature and facilities. In addition, in order to offer comfort and stableness in body and mind to users, it is necessary to educate and train the staff to offer better service and to maintain the facilities of recreation forest peaceful and calm.

• The Journal of Society for e-Business Studies
• /
• v.13 no.3
• /
• pp.121-135
• /
• 2008

Railroad logistics transporting freight by train takes charge of 10 or 20 percent of domestic cargos. Railroad logistics users such as transport companies including shippers or Inland Container Depot(ICD) use electronic document(EDI or XML) or input data through WEB to process railroad logistics business. However, as business environments evolving into e-business, it is required to upgrade the legacy railroad logistics process. As the increase of using ebXML-based schema format, it is also needed to improve the electronic documents based on DTD format into those of XML schema format. This study deals with information standard for railroad logistics to improve the railroad logistics business. To this purpose railroad business processes were re-defined through the standard business process modeling methodology. Information model was also derived by defining railroad logistics activities from business process model. And Business Information Entities(BIEs) were defined to design new electronic documents according to the extracted information model. An improved system architecture for railroad logistics was proposed as well. The results of this study will provide an effective and flexible business flow to railroad logistics business.