• 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%.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.193-198
• /
• 2008

When the existing polder levee was constructed, the river's numerical analysis decided the bank raise by applying the planned flood stage or by using the result from the sectional 1st dimensional numerical analysis. But, it was presented that there is a limitation in the 1st dimensional value analysis when the structure like the polder levee obstructs the special shaped running water flow. Therefore, in order to verify the numerical value applicability when the polder levee is constructed, this report compared each other through the 1st and 2nd dimensional numerical analysis and the mathematical principle model laboratory. In case of the polder levee construction through the numerical analysis and the mathematical principle model laboratory, it was decided that there was no big problem in the 1st dimensional numerical analysis applied design, considering the uncertainty of mathematical principle analysis though the first dimensional numerical analysis was calculated a little bigger than the second. But, after construction, it was found that the water level deviation of the 1st, 2nd occurred biggest at the place where the flow was divided into two. Also, as a result of comparing the 1st, 2nd dimensional numerical analysis with the mathematical principle model laboratory, it was confirmed that the 1st numerical analysis applied design decreased the modal safety largely, as the left side water level was calculated smaller more than 0.5m in case of the 1st dimensional numerical analysis.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.5 no.4
• /
• pp.315-320
• /
• 2004

Digital technologies have largely changed our way of life in a time-space traditional paradigm. Information Technology(IT) has become the most primary measurement in evaluation of social value. So the efficient education for IT has a big responsibility for the better living conditions. The importance of IT education continue to grow more and more. The intent of this work is to enforce the competitive power of IT education under open-education and to develop the special model of the practical IT curriculum for industry. The proposed curriculum is consisted of various modules which can be easily adapted to real world. So someone who finished IT curriculum can be re-educated the only necessary module with this developed model.

• Journal of the Korean Society of Safety
• /
• v.32 no.2
• /
• pp.132-146
• /
• 2017

Appropriate speed limits at a reasonable level in urban roads are highly important factors for efficient and safe movement. Thus, it is greatly necessary to develop the objective models or methodology based on engineering study considering factors such as traffic accident rates, roadside development levels, and roadway geometry characteristics etc. The purpose of this study is to develop the estimate model of appropriate speed limits at each road sections in urban roads using traffic information big data and field specific data and to review the effects of accident decrease. In this study, the estimate method of appropriate speed limits in directional two or more lanes of urban roads is reflecting features of actual variables in a form of adjustment factor on the basis of the maximum statutory speed limits. As a result of investigating and testing influential variables, the main variables to affect the operating speed are the function of road, the existence of median, the width of lane, the number of traffic entrance/exit path and the number of traffic signal or nonsignal at intersection and crosswalk. As a result of testing this model, when the differences are bigger between the real operating speed and the recommended speed limits using model developed in this study, the accident rate generally turns out to be higher. In case of using the model proposed in this study, it means accident rate can be lower. When the result of this study is applied, the speed limits of directional two or more lane roads in Seoul appears about 11km/h lower than the current speed limits. The decrease of average operating speed caused by the decrease of speed limits is 2.8km/h, and the decrease effect of whole accidents according to the decrease of speed is 18% at research road. In case that accident severity is considered, the accident decrease effects are expected to 17~24% in fatalities, 11~17% in seriously injured road user, 6~9% in slightly injured road user, 5~6% in property damage only accidents.

• Journal of Ocean Engineering and Technology
• /
• v.33 no.5
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• Journal of Electrochemical Science and Technology
• /
• v.13 no.4
• /
• pp.438-452
• /
• 2022

For cuboid and ellipsoid crystallites of LiFePO₄ powders, by X-ray diffraction (XRD) and microscopic (TEM) studies, it is possible to determine the anisotropic parameters of the crystallite size distribution functions. These parameters were used to describe the cathode rate capability within the model of averaging the diffusion coefficient D over the length of the crystallite columns along the [010] direction. A LiFePO₄ powder was chosen for testing the developed model, consisting of big cuboid and small ellipsoid crystallites (close to them). When analyzing the parts of big and small rate capabilities, the fitting values D = 2.1 and 0.3 nm²/s were obtained for cuboids and ellipsoids, respectively. When analyzing the results of cyclic voltammetry using the Randles-Sevcik equation and the total area of projections of electrode crystallites on their (010) plane, slightly different values were obtained, D = 0.9 ± 0.15 and 0.5 ± 0.15 nm²/s, respectively. We believe that these inconsistencies can be considered quite acceptable, since both methods of determining D have obvious sources of error. However, the developed method has a clearly lower systematic error due to the ability to actually take into account the shape and statistics of crystallites, and it is also useful for improving the accuracy of the Randles-Sevcik equation. It has also been demonstrated that the shape engineering of crystallites, among other tasks, can increase the cathode capacity by 15% by increasing their size correlation coefficients.

• Journal of Advanced Navigation Technology
• /
• v.24 no.5
• /
• pp.368-373
• /
• 2020

In order to systematically apply major technologies of the 4th Industrial Revolution to aerospace power development, an aerospace technology model is needed. The Propeller Model, which is an existing aerospace model, is a concept that operates a combination of altitude, speed, and distance, which are basic characteristics of aerospace. However, in the era of the 4th Industrial Revolution, a new model is needed because numerous technologies are used in convergence. In this paper, a jet engine model is proposed as a new aerospace technology model. Also, we propose a procedure for creating future aerospace weapon systems based on aerospace technology modeling, not on operational capability. The utilization of future battlefields and the study of the concept of advanced weapon systems in developed countries can create a new concept of weapon systems.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.5
• /
• pp.1013-1027
• /
• 2013

As the need for large-scale data analysis is rapidly increasing, Hadoop, or the platform that realizes large-scale data processing, and MapReduce, or the internal computational model of Hadoop, are receiving great attention. This paper reviews the basic concepts of Hadoop and MapReduce necessary for data analysts who are familiar with statistical programming, through examples that combine the R programming language and Hadoop.

• Korean Management Science Review
• /
• v.29 no.2
• /
• pp.143-155
• /
• 2012

The purpose of this study is to formulate and solve the scheduling problem to heat-treatment process in forging process and apply it to industries. Heat-treatment is a common process in manufacturing heavy forged products in ship engines and wind power generators. Total complete time of the schedule depends on how to group parts and assign them into heat furnace. Efficient operation of heat-treatment process increases the productivity of whole production system while scheduling the parts into heat-treatment furnace is a combinatorial problem which is known as an NP-hard problem. So the scheduling, on manufacturing site, relies on engineers' experience. To improve heat-treatment process schedule, this study formulated it into an MIP mathematical model which minimizes total complete time. Three methods were applied to example problems and the results were compared to each other. In case of small problems, optimal solutions were easily found. In case of big problems, feasible solutions were found and that feasible solutions were very close to lower bound of the solutions. ILOG OPL Studio 5.5 was used in this study.

• Journal of the Society of Naval Architects of Korea
• /
• v.41 no.5
• /
• pp.63-69
• /
• 2004

This study contains the CFD analysis to predict the flow in engine room and utilize the results as a reference for arranging smoke detectors. FLUENT, a commercial CFD code is adopted because of its good application experience in DSME(Daewoo Shipbuilding & Marine Engineering Co.. Ltd.). The target is the engine room of VLCC. which was delivered in 2002. The model for analysis includes main structure elements, ventilation ducts, main engine and other big size equipment. From the analysis results, the internal flow pattern can be observed and some guidelines for the position of smoke detectors cane be presented.