• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.51-61
• /
• 2008

Most of Korea's 15 local airports, with the exception Jeju, Gimpo and Gimhae airports, have been several billion Won in the red each year. It has been reported that one of the causes of the poor financial performance is inaccurate air traffic demand predictions. Under the situation, the entry of low-cost carrier air service using turbo-prop airplanes into the domestic airlines market gets a wide range of support, which is expected to promote the convenience of consumers and help to activate local airports. In this study, the authors (1) suggest a high-speed transport demand model among existing airlines, Korea Train Express (KTX) and low-cost carrier air service; (2) try to make low-cost air carrier demand predictions for a route between Seoul and Daegu through a stated-preference survey; and (3), examine possible effectiveness of selected policy measures by establishing an estimation model. First, fare has a strong influence for mode choice between high-speed transport modes when considering the entry of low-cost carrier air service between Seoul and Daegu. Even low-cost carrier air service fare is set at 38,000 won, which is considerably low compared with that of KTX, in the regions where the total travel time is the same for both low-cost carrier air service and KTX, the probability of selecting low-cost carrier air service is 0.1, which shows little possibility of modal change between high speed transportation means. It is suggested that the fare of low-cost air service between Seoul and Daegu should be within the range of from of 38,000 to 44,000 Won; if it is higher, the demand is likely to be lower than expected.

• Journal of Bio-Environment Control
• /
• v.10 no.1
• /
• pp.36-41
• /
• 2001

This experiment was carried out to investigate temperature distribution in the double layer plastic greenhouse and chilling injury to watermelons grown during a cold season. Temperatures on eastern and western sides were about 6.2% and 14.7%, respectively, lower than that of central section in a south-north oriented greenhouse. Daily mean temperature in the northern part was about 1-2$^{\circ}C$ higher than that in the southern part of the greenhouse. In terms of vertical temperature distribution inside the greenhouse, temperature at ground surface was approximately 1$^{\circ}C$ lower during the day and 0.5$^{\circ}C$ higher during the night than that in the upper part, 2m from the ground surface. Leaf mould medium kept higher ground temperatures as compared to sandy soil, red clay soil, and in the northern and southern sides as compared to the central part of the greenhouse. A symptom of chilling injury on leaves was upward curling, followed by chlorosis and necrosis. A severe symptom of chilling injury to plants was the breakdown of vascular bundles. Root growth was more susceptible than stem or leaf growth to low temperatures. At 3$0^{\circ}C$, main and lateral roots grew vigorously, while lateral root growth was inhibited at 22$^{\circ}C$ and root growth was stopped at 14$^{\circ}C$ and 6$^{\circ}C$. Small and puffy fruits with dark green surface were produced at low temperatures. In cold season cultivation of watermelons, it is suggested that plants be transplanted in the central part and train to sides of the greenhouse in order to reduced chilling injuries.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.7
• /
• pp.221-228
• /
• 2020

Part-of-Speech (POS) tagged corpus is a collection of electronic text in which each word is annotated with a tag as the corresponding POS and is widely used for various training data for natural language processing. The training data generally assumes that there are no errors, but in reality they include various types of errors, which cause performance degradation of systems trained using the data. To alleviate this problem, we propose a novel method for detecting errors in the existing POS tagged corpus using the classifier of XGBoost and cross-validation as evaluation techniques. We first train a classifier of a POS tagger using the POS-tagged corpus with some errors and then detect errors from the POS-tagged corpus using cross-validation, but the classifier cannot detect errors because there is no training data for detecting POS tagged errors. We thus detect errors by comparing the outputs (probabilities of POS) of the classifier, adjusting hyperparameters. The hyperparameters is estimated by a small scale error-tagged corpus, in which text is sampled from a POS-tagged corpus and which is marked up POS errors by experts. In this paper, we use recall and precision as evaluation metrics which are widely used in information retrieval. We have shown that the proposed method is valid by comparing two distributions of the sample (the error-tagged corpus) and the population (the POS-tagged corpus) because all detected errors cannot be checked. In the near future, we will apply the proposed method to a dependency tree-tagged corpus and a semantic role tagged corpus.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.197-206
• /
• 2010

High-quality and low-price digital printing devices are nowadays abused to print or forge official documents and bills. Identifying color laser printers will be a step for media forensics. This paper presents a new method to identify color laser printers with printed color images. Since different printer companies use different manufactural systems, printed documents from different printers have little difference in visual. Analyzing this artifact, we can identify the color laser printers. First, high-frequency components of images are extracted from original images with discrete wavelet transform. After calculating the gray-level co-occurrence matrix of the components, we extract some statistical features. Then, these features are applied to train and classify the support vector machine for identifying the color laser printer. In the experiment, total 2,597 images of 7 printers (HP, Canon, Xerox DCC400, Xerox DCC450, Xerox DCC5560, Xerox DCC6540, Konica), are tested to classify the color laser printer. The results prove that the presented identification method performs well with 96.9% accuracy.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.55-64
• /
• 2013

Due to the popularization of digital high-performance capturing equipments and the emergence of powerful image-editing softwares, it is easy for anyone to make a high-quality counterfeit money. However, the probability of detecting a counterfeit money to the general public is extremely low. In this paper, we propose a counterfeit money detection algorithm using a general purpose scanner. This algorithm determines counterfeit money based on the different features in the printing process. After the non-local mean value is used to analyze the noises from each money, we extract statistical features from these noises by calculating a gray level co-occurrence matrix. Then, these features are applied to train and test the support vector machine classifier for identifying either original or counterfeit money. In the experiment, we use total 324 images of original money and counterfeit money. Also, we compare with noise features from previous researches using wiener filter and discrete wavelet transform. The accuracy of the algorithm for identifying counterfeit money was over 94%. Also, the accuracy for identifying the printing source was over 93%. The presented algorithm performs better than previous researches.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.706-714
• /
• 2012

The Korea Meteorological Administration provided the recent four-years records of weather dataset for our very short-term heavy rainfall prediction. We divided the dataset into three parts: train, validation and test set. Through feature selection, we select only important features among 72 features to avoid significant increase of solution space that arises when growing exponentially with the dimensionality. We used a differential evolution algorithm and two classifiers as the fitness function of evolutionary computation to select more accurate feature subset. One of the classifiers is Support Vector Machine (SVM) that shows high performance, and the other is k-Nearest Neighbor (k-NN) that is fast in general. The test results of SVM were more prominent than those of k-NN in our experiments. Also we processed the weather data using undersampling and normalization techniques. The test results of our differential evolution algorithm performed about five times better than those using all features and about 1.36 times better than those using a genetic algorithm, which is the best known. Running times when using a genetic algorithm were about twenty times longer than those when using a differential evolution algorithm.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.2
• /
• pp.55-63
• /
• 2018

In order to support the load of the train with enough stiffness, a study on an effective method for the characterization of the stiffness of the compacted subgrade is required. In this study, the crosshole-type dynamic cone penetrometer (CDCP) is used for the stiffness characterization of the subgrade along the depth. For the application of the CDCP test, three points of compacted subgrades are selected as the study sites. For the study sites, CDCP test, in-situ density test, and light falling weight deflectometer (LFWD) test are conducted. As the results of CDCP tests, shear wave velocity profiles are obtained by using the travel times and the travel distances of the shear waves along the depth. In addition, maximum shear modulus ($G_{max}$) profiles are estimated by using the density of the subgrades and the shear wave velocity profiles. The averaged maximum shear moduli at each testing point are highly correlated with the dynamic deflection moduli ($E_{vd}$) determined by LFWD tests. Therefore, a reliable stiffness characterization of the subgrade can be conducted by using CDCP tests. In addition, because CDCP characterizes the stiffness of the subgrade along the depth rather than a representative value, CDCP test may be effectively used for the stiffness characterization of the subgrade.

• Journal of Korean Society of Transportation
• /
• v.23 no.2
• /
• pp.75-82
• /
• 2005

To relieve congestion in the current system of intercity transportation, the Korea decided in 1990 to construct a high-speed railroad between Seoul and Busan and it is now in operation. This new mode of transportation significantly cut travel time between major cities and a trip from Seoul to the southeastern port of Busan. Since the KTX opening, average daily passenger numbers on both the Gyeongbu and Honam lines have increased about 1.3 fold over 2003 levels. As of December 2004, the KTX trains are carrying about 81,000 people a day. On KTX routes, the daily number of airline passengers dropped. Express long-distance bus traffic also dropped by 20% to 30%, while that on short-distance routes (100km or less) increased by about 20%. These figures clearly indicate that the Korean transportation network is becoming railroad-centric. However, the number of KTX passengers is fewer than anticipated possibly due to the Korean economic downturn and the operation of the KTX will leave many existing Saemaul and Mugunghwa train sets idle, which will be put into operation for areas, not covered by the KTX. When all the existing major lines have been electrified, more high-speed rail services will be phased in using direct connections to maximize operational efficiency. And also, the dual management by KTX and conventional rail will be regarded as the promotion of the benefit of the public.

• Journal of The Korean Association For Science Education
• /
• v.39 no.4
• /
• pp.535-544
• /
• 2019

In order to find out whether the traditional mass media in our society are sufficiently functioning as a vehicle of providing scientific information to the public outside the school education, public perception of science articles in mass media and scientific terms used in high frequency in science articles have been examined. To investigate the public perception on science articles, a questionnaire was constructed about the usefulness, importance, access frequency, and understanding of science articles. The questionnaires were conducted in areas with high flow populations such as train stations or subway stations. A total of 425 responses were used for analysis. In order to extract high frequency scientific terms used in science articles, two television companies and two newspapers were designated as target media, and their texts on science articles reported over the last 17 years were collected to investigate the frequency of scientific terms used. Based on the frequency, we conducted the self-report comprehension test for the top 100 scientific terms. The results of this study show that the public in our society has relatively high perception of the importance and usefulness of science articles, however, reading and understanding the articles seems to be somewhat difficult. In addition, the scientific terminology used in science articles has a high degree of comprehension for those of higher education, natural sciences majors, and men. In addition, scientific terms with high understanding degree were characterized according to gender, age, educational background, and field of major.

• The Journal of the Korea Contents Association
• /
• v.19 no.10
• /
• pp.685-697
• /
• 2019

The study aimed to analyze the structure of China's passenger railway network in the years of 2008, 2013, and 2018, respectively. At the same time, it tried to investigate its derivative impact on the patterns of Chinese urban network. The analytical tool was based on the NetMiner4.0. In order to measure network characteristics of China's passenger railway network, it primarily focused on the degree centrality, betweenness centrality, and closeness centrality. First of all, the higher degree centralities, with a few exceptions, were observed in BeiJing, ShangHai, GuangZhou, WuHan, XiAn, ChengDu, HaErBin, and ShenYang over a decade. In contrast, the higher betweenness centralities were recorded in cities of higher development potential including WuLuMuQi, GuiYang, ShenYang, and KunMing. The closeness centrality analyses confirmed the fact that most metropoles like BeiJing, ShangHai, and GuangZhou kept the highest train accessibility during the same research period. At the same time, the opening up of a new stretch of high speed railway network has consecutively strengthened connectivity between BeiJing and TianJin. Owing to unprecedented development of railway traffic and its extensive operations, this study believes that Chinese major cities, without interruption, would pursue a series of urban policy alternatives geared towards railway stations-oriented networking and competitively try to extend their network ranges.