• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• Atmosphere
• /
• v.32 no.3
• /
• pp.235-246
• /
• 2022

A large number of MJO skill metrics and process-oriented MJO simulation metrics have been developed by previous studies including the MJO Working Group and Task Force. To assess models' successes and shortcomings in the MJO simulation, a standardized set of diagnostics with the additional set of dynamics-oriented diagnostics are applied. The Global Coupled (GC) model developed for the operation of the climate prediction system is used with the comparison between the GC2 and GC3.1. Two GC models successfully capture three-dimensional dynamic and thermodynamic structure as well as coherent eastward propagation from the reference regions of the Indian Ocean and the western Pacific. The low-level moisture convergence (LLMC) ahead of the MJO deep convection, the low-level westerly and easterly associated with the coupled Rossby-Kelvin wave and the upper-level divergence are simulated successfully. The GC3.1 model simulates a better three-dimensional structure of MJO and thus reproduces more realistic eastward propagation. In GC2, the MJO convection following the LLMC near and east of the Maritime Continent is much weaker than observation and has an asymmetric distribution of both low and upper-level circulation anomalies. The common shortcomings of GC2 and GC3.1 are revealed in the shorter MJO periods and relatively weak LLMC as well as convective activity over the western Indian Ocean.

• Journal of Korean Society on Water Environment
• /
• v.39 no.1
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.107-116
• /
• 2024

Copper Filter Dryer (CFD) are responsible for removing impurities from the circulation of refrigerant in refrigeration and cooling systems to maintain clean refrigerant, and defects in CFD can lead to product defects such as leakage and reduced lifespan in refrigeration and cooling systems, making quality assurance essential. In the quality inspection stage, human inspection and defect judgment methods are traditionally used, but these methods are subjective and inaccurate. In this paper, YOLOv7 object detection algorithm was used to detect defects occurring during the CFD Shaft pipe and welding process to replace the existing quality inspection, and the detection performance of F1-Score 0.954 and 0.895 was confirmed. In addition, the cause of defects occurring during the welding process was analyzed by analyzing the sensor data corresponding to the Timestamp of the defect image. This paper proposes a method for manufacturing quality assurance and improvement by detecting defects that occur during CFD process and analyzing their causes.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.5 no.3
• /
• pp.245-254
• /
• 2000

This study was conducted to investigate the community structure and distributional pattern of meiobenthos in the deep sea bottoms of northeastern Pacific during July 1998. The faunal samples were collected using the multiple corer at ten stations; eight stations along the transects from 5$^{\circ}$N to 12$^{\circ}$N, and two stations in the Preservation Zone and Impact Zone of the KODOS (Korea Deep Ocean Study) area. The organic carbon content in sediments ranged from 0.79 to 1.76 mg cm$^{-3}$, and higher concentration appeared at stations in lower latitudes than 8$^{\circ}$N. The most abundant meiobenthos was nematodes and followed by foraminiferans; these two taxa comprised more than 70% of the total abundance at all stations. The most abundant meiobenthos occurred with mesh size of 0.063 nm. The maximum density of meiobenthos was 442 ind./10 cm$^2$ at station N5, and the density gradually decreased toward station N8 where the minimum density of 92 md./10 cm$^2$ was found. More than 60% of meiobenthos were distributed at surface sediment layer within 1.0 cm, and the peak abundance was found at 0-0.25 cm layer. The latitudinal distribution pattern of meiobenthos in the study area seemed to be related with the primary productivity of the surface water that is also connected to the water circulation pattern of the Pacific Ocean near the Equator, diverging at latitude of 8$^{\circ}$N and conversing at 5$^{\circ}$N.

• Economic and Environmental Geology
• /
• v.39 no.1 s.176
• /
• pp.27-38
• /
• 2006

To understand the geologic and hydrogeochemical controls on the occurrence of high fluoride concentrations in bedrock groundwaters of South Korea, we examined a total of 367 hydrochemistry data obtained from deep groundwater wells (avg. depth=600 m) that were drilled fur exploitation of hot springs. The fluoride concentrations were generally very high (avg. 5.65mg/L) and exceeded the Drinking Water Standard (1.5 mg/L) in $72\%$ of the samples. A significant geologic control of fluoride concentrations was observed: the highest concentrations occur in the areas of granitoids and granitic gneiss, while the lowest concentrations in the areas of volcanic and sedimentary rocks. In relation to the hydrochemical facies, alkaline $Na-HCO_3$ type waters had remarkably higher F concentrations than circum-neutral to slightly alkaline $Ca-HCO_3$ type waters. The prolonged water-rock interaction occurring during the deep circulation of groundwater in the areas of granitoids and granitic gneiss is considered most important for the generation of high F concentrations. Under such condition, fluoride-rich groundwaters are likely formed through hydrogeochemical processes consisting of the removal of Ca from groundwater via calcite precipitation and/or cation exchange and the successive dissolution of plagioclase and F-bearing hydroxyl minerals (esp. biotite). Thus, groundwaters with high pH and very high Na/Ca ratio within granitoids and granitic gneiss are likely most vulnerable to the water supply problem related to enriched fluorine.

• Journal of Chest Surgery
• /
• v.36 no.8
• /
• pp.559-565
• /
• 2003

By improving the flow pattern in Fontan circuit, total cavopulmonary connection (TCPC) could result in a better outcome than atriopulmonary connection Fontan operation. For the patients with impaired hemodynamics after atriopulmonary Fontan connection, conversion to TCPC can be expected to bring hemodynamic and functional improvement. We studied the results of the revision of the previous Fontan connection to TCPC in patients with failed Fontan circulation. Material and method: From October1979 to June 2002, eight patients who had failed Fontan circulation, underwent revision of previous Fontan operation to TCPC at Yonsei University Hospital. Intracardiac anomalies of the patients were tricuspid atresia (n=4) and other functional single ventricles (n=4). Mean age at TCPC conversion was 14.0$\pm$7.0 years (range, 4.6~26.2 years) and median interval between initial Fontan operation and TCPC was 7.5 years (range, 2.4~14.3 years). All patients had various degree of symptoms and signs of right heart failure. NYHA functional class was 111 or IV in six patients. Paroxysmal atrial fibrillation (n:f), cyanosis (n=2), intraatrial thrombi (n=2), and protein losing enteropathy (PLE) (n=3) were also combined. The previous Fontan operation was revised to extracardiac conduit placement (n=7) and intraatrial lateral tunnel (n=1). Result: There was no operative death. Major morbidities included deep sternal infection (n=1), prolonged pleural effusion over two weeks (n=1), and temporary junctional lachyarrhythrnia (n=1). Postoperative central venous Pressure was lower than the preoperative value (17.9$\pm$3.5 vs. 14.9$\pm$1.0, p=0.049). Follow-up was complete in all patients and extended to 50,1 months (mean, 30.3$\pm$ 12.8 months). There was no late death. All patients were in NYHA class 1 or 11. Paroxysmal supraventricular tachycardia developed in a patient who underwent conversion to intraatrial lateral tunnel procedure, PLE was recurred in two patients among three patients who had had PLE before the convertsion. There was no newly developed PLE. Conclusion: Hemodynamic and functional improvement could be expected for the patients with Fontan circulatory failure after atriopulmonary connection by revision of their previous circulation to TCPC. The conversion could be performed with low risk of morbidity and mortality.

• Journal of Biomedical Engineering Research
• /
• v.19 no.3
• /
• pp.279-284
• /
• 1998

Deep hypothermic circulatory arrest(DHCA), in which systemic temperatures of 2$0^{\circ}C$ or less are used to allow temporary cessation of the circulation, is an useful adjunct in cardiac surgery. Because man in natural circumstances is never exposed to the extreme hypothermic condition, however, one of the controversial aspects is appropriate blood gas management($\alpha$STAT versus PH-STAT) during DHCA. This study aims to compare $\alpha$STAT with PH-STAT management for control of blood gases in experimental cardiopulmonary bypass(CPB) circuits with a membrane oxygenator. Fourteen young pigs were assigned to one of two strategies of gas manipulation. After a median sternotomy, CPB was established. Core cooling was initiated and continued until nasopharyngeal temperature fell below 2$0^{\circ}C$. The flow rate was set at 2,500 ml/min. Once their temperatures were below 2$0^{\circ}C$, the animals were subjected to circulatory arrest for 40mins. During cooling, blood gas was maintained according to either $\alpha$$\alpha$STAT or pH-STAT strategies. After DHCA, the body was rewarmed to normal body temperature. Arterial blood gases were measured before the onset of CPB, before cooling, before DHCA, at the point of 27$^{\circ}C$ during re-warming, on completion of re-warming. Cooling time was significantly shorter in $\alpha$-STAT than PH-STAT strategy, while there was no significant differences in rewarming time between two groups. Carbon dioxide was added between 5.5 and 3.0% in PH-STAT, while no carbon dioxide was added in $\alpha$STAT management. Amounts of oxygen administration were gradually lowered as temperature decreased. In this way, criteria of PH, PaCO, and PaO adjustments were satisfied in both $\alpha$STAT and PH-STAT management groups.

• Journal of Korean Society of Environmental Engineers
• /
• v.36 no.4
• /
• pp.286-294
• /
• 2014

The purpose of this study is to investigate the effects of applying density current generator (hereafter referred to as DCG to large lakes on the operating conditions of DCG, de-stratification, water quality improvement and inhibition of algae occurrence. As a result of a survey conducted to derive the optimum operating parameters of DCG in a condition to minimize eco-toxicity, the following conclusions were obtained. During the survey period, a marked stratification appeared in September to October 2011 and May 2012. At this time, the average depth of water to form thermocline was found to be $5{\pm}2$ m, so the location of discharge port for the operation of DCG was determined to be about 5 m below from the surface. To minimize the adverse effects of benthos and obtain the effect of water mixture at the time of water circulation, the mixing ratio of surface water and deep water was designed to be 3:1 by means of ecotoxicological assessment on the DCG operating characteristics. To select the appropriate operating hours for DCG, DCG was operated by 12 hr, 24 hr, 36 hr and 48 hr. As its result, the formation of thermocline did not occur during the operation of 36 hr. Also, It was effected that start reoperating from 3rd day after stop 2days under the condition of operated during 36 hr with calculated power consumption. Under the above conditions, the results of DO and water temperature analysis during the operation of DCG showed that the stratification, which was distinct previously, appeared to be weak, and relatively lower levels than those before operation were found as a result of water quality analysis on COD and chlorophyll-a, which leads to the conclusion that the water body is maintained at a stable condition due to the circulation of water by the occurrence of density current resulting from the operation of DCG.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.61-68
• /
• 2010

A magnetotelluric (MT) survey has been performed to delineate deeply extended fracture systems at the geothermal field in Seokmo Island, Korea. To assist interpretation of the MT data, geological surveying and well logging of existing wells were also performed. The surface geology of the island shows Cretaceous and Jurassic granite in the north and Precambrian schist in the south. The geothermal regime has been found along the boundary between the schist and Cretaceous granite. Because of the deep circulation along the fracture system, geothermal gradient of the target area exceeds $45^{\circ}C/km$, which is much higher than the average geothermal gradient in Korea. 2D and 3D inversions of MT data clearly showed a very conductive anomaly, which is interpreted as a fracture system bearing saline water that extends at least down to 1.5 km depth and is inclined eastwards. After drilling down to the depth of 1280 m, more than 4000 tons/day of geothermal water overflowed with temperature higher than $70^{\circ}C$. This water showed very similar chemical composition and temperature to those from another existing well, so that they can be considered to have the same origin; i.e. from the same fracture system. A new geothermal project for combined heat and power generation was launched in 2009 in Seokmo Island, based on the survey. Additional geophysical investigations including MT surveys to cover a wider area, seismic reflection surveys, borehole surveys, and well logging of more than 20 existing boreholes will be conducted.