• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.179-196
• /
• 2021

With the spread of untact culture resulting from the Covid-19 pandemic, the size of the car camping market has expanded to minimize contact with others. As a result, SUVs have exceeded sales of sedans, and sales of recreational vehicles (RVs) have increased by 101% compared to the same period last year. Despite the explosive increase in demand for car camping, research on car camping has not matched this increase. Therefore, in this study, we intended to conduct a study focused on car camping users. According to a survey of Naver's famous car camping cafe, it was difficult to find articles, maps, and websites with car camping places. Analysis of car camping websites showed that most only post information about the camping itself, so details of car camping places were not available. Furthermore, according to a survey derived from related prior studies and literature surveys, most users urged solutions to the problem of unauthorized garbage dumping in the car camping locations. In addition, car camping users wanted to receive information on amenities near the car camping places. Therefore, we aimed to establish a car camping website that provides basic information on car camping places and nearby convenience facilities. Moreover, to solve the problem of garbage dumping, we provided a category wherein users can post pictures of clean camping campaigns. We also developed a business model utilizing the certification process of clean camping. The business model is designed with a structure wherein car camping users are rewarded through the clean camping certification process. Compensation for clean camping certification was proposed to be provided through partnerships with domestic automakers, Korea Tourism Organization, and Small Business Market Promotion Agency.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.35-56
• /
• 2023

With the development of information and communication technology, numerous reviews are continuously posted on websites, which causes information overload problems. Therefore, users face difficulty in exploring reviews for their decision-making. To solve such a problem, many studies on review helpfulness prediction have been actively conducted to provide users with helpful and reliable reviews. Existing studies predict review helpfulness mainly based on the features included in the review. However, such studies disable providing the reason why predicted reviews are helpful. Therefore, this study aims to propose a methodology for applying eXplainable Artificial Intelligence (XAI) techniques in review helpfulness prediction to address such a limitation. This study uses restaurant reviews collected from Yelp.com to compare the prediction performance of six models widely used in previous studies. Next, we propose an explainable review helpfulness prediction model by applying the XAI technique to the model with the best prediction performance. Therefore, the methodology proposed in this study can recommend helpful reviews in the user's purchasing decision-making process and provide the interpretation of why such predicted reviews are helpful.

• Information Systems Review
• /
• v.22 no.1
• /
• pp.59-72
• /
• 2020

Artificial Intelligence is establishing itself as a familiar tool from an intractable concept. In this trend, financial sector is also looking to improve the problem of existing system which includes Fraud Detection System (FDS). It is being difficult to detect sophisticated cyber financial fraud using original rule-based FDS. This is because diversification of payment environment and increasing number of electronic financial transactions has been emerged. In order to overcome present FDS, this paper suggests 3 types of artificial intelligence models, Generative Adversarial Network (GAN), Deep Neural Network (DNN), and Convolutional Neural Network (CNN). GAN proves how data imbalance problem can be developed while DNN and CNN show how abnormal financial trading patterns can be precisely detected. In conclusion, among the experiments on this paper, WGAN has the highest improvement effects on data imbalance problem. DNN model reflects more effects on fraud classification comparatively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.11
• /
• pp.6565-6575
• /
• 2014

Hamilton's Markov-switching model [5] was extended to the simultaneous equations model. A framework for an instrumental variable interpretation of full information maximum likelihood (FIML) by Hausman [4] can be used to deal with the problem of simultaneous equations based on the Hamilton filter [5]. A comparison of the proposed FIML Markov-switching model with the LIML Markov-switching models [1,2,3] revealed the LIML Markov-switching models to be a special case of the proposed FIML Markov-switching model, where all but the first equation were just identified. Moreover, the proposed Markov-switching model is a general form in simultaneous equations and covers a broad class of models that could not be handled previously. Excess sensitivity of marginal propensity to consume with big shocks, such as housing bubble bursts in 2008, can be determined by applying the proposed model to Campbell and Mankiw's consumption function [6], and allowing for the possibility of structural breaks in the sensitivity of consumption growth to income growth.

• 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%.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• Knowledge Management Research
• /
• v.24 no.3
• /
• pp.95-125
• /
• 2023

As the aviation industry has rapidly been grown, there are more factors for customers to consider when choosing an airline. In response, airlines are trying to increase customer value by providing high-quality services and differentiated experiential value. While early customer value research centered on utilitarian value, which is the trade-off between cost and benefit in terms of utility for products and services, the importance of experiential value has recently been emphasized. However, experiential value needs to be studied in a specific context that fully represents customer preferences because what constitutes customer value changes depending on the product or service context. In addition, customer value has an important influence on customers' decision-making, so it is necessary for airlines to accurately understand what constitutes customer value. In this study, we collected customer reviews and ratings from Skytrax, a website specializing in airlines, and utilized the BERTopic technique to derive factors of customer value. The results revealed nine factors that constitute customer value in airlines, and six of them are related to customer satisfaction. This study proposes a new methodology that enables a granular understanding of customer value and provides airlines with specific directions for improving service quality.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2006.11a
• /
• pp.478-482
• /
• 2006

The domestic enterprises in order to secure the freshness location of market from the international competition which is keen are propelling a price and a quality high position strategy steadily. It is put in competitive situation with the overseas enterprises and even from construction industry it follows in construction market opening and there is not another idea to the research the management strategies, directions and focus competitive elements of the enterprise against, what it sees consequently and to rise to the priority where the competitive power reinforcement of the enterprise is important, it becomes. Competitive power of like this enterprise for a reinforcement the technique which induces a big interest 6 Sigma is technique from the many companies. 6 sigma preceding researches of manufacturing and service industry the fact that it is accomplished with the object which will carry most. The research which relates with construction industry is staying to an introduction of 6 sigma the investigation phase, the actual introduction introduces and "S" construction there is not only a possibility against the application result of having a limit because it is applying. It is like that but like referring to a minute description for the international competitive power security which it follows in the change which market environment is sudden 6 sigma the introduction will judge, indispensability development of the logical propriety against hereupon and it will reach and it verifies the question investigation for to lead, 6 sigma of the construction companies it confirms the application possibility and presents the propulsion model as 6 sigma the fact that overcoming the limit characteristic of that introduction application as objective of sample research means it will do.

• Journal of Technologic Dentistry
• /
• v.34 no.1
• /
• pp.1-9
• /
• 2012

Purpose: The purpose of this study was to investigate the transmittance differences of pressable ceramic core due to thickness within the visible light spectrum. Methods: 36 specimens were divided into 2 groups (0.6mm, 0.8mm) which have each 3 specimens. The size of specimens was 10mm high and 10mm wide. The transmittance of specimens are measured by spectrophotometer Model Cary 500 that can measure infrared-ray, visible wave and ultraviolet-ray. Results: The results shows that there was no significant difference between specimen's thickness(0.6mm, 0.8mm) and transmittance. Conclusion: The individual's color perception is personal and there are numerous factors that influence on it. In general, human eye can perceive the color of thing only within visible light spectrum but in this experiment through spectrophotometer there was no big difference between specimen's thickness(0.6mm, 0.8mm) and transmittance. To sum up, The most important factors were a layed porcelain structure and its thickness rather than core thickness in the porcelain crown. Also, When making all ceramic core with dead pulp (nervous treatment tooth) when used as a restorative esthetic think is more efficient to improve.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.1
• /
• pp.38.2-38.2
• /
• 2011

In general, solar filaments are divided into two parts; one spine and several barbs. Barbs are seen as if they protrudes from the spine. Until now there are many controversies about the structures of a barb and spine. Recently, New Solar Telescope was installed at Big Bear Solar Observatory. Its clear aperture is about 1.6m and it is the largest telescope among ground-based solar telescopes. Fast Imaging Solar Spectrograph (FISS) developed by SNU and KASI was also installed in a vertical optical table in Coude room of the 1.6m NST. It is simultaneously able to record two lines; $H{\alpha}$ and Ca II 8542A lines. On 2010 July 29, we observed a portion of a solar filament located in northern hemisphere with FISS and it had a well-developed barb. And we also observed a potion of a spine. In order to analyze the data, we used the cloud model and obtained physical quantities of the solar filament. Temperature of the solar lament ranged between 4500K and 12000K and non-thermal velocity ranged between 3km/s and 6.5km/s. By comparing physical quantities of a barb and spine, we try to understand these structures of the solar filament.