• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.6
• /
• pp.603-611
• /
• 2020

This study collected and analyzed transportation card data in order to better understand the operation and usage of city buses in Ulsan Metropolitan City in Korea. The analysis used quantitative and qualitative indicators according to the characteristics of the data, and also the categories were classified as general status, operational status, and satisfaction. The existing city bus survey method has limitations in terms of survey scale and in the survey process itself, which incurs various types of errors as well as requiring a lot of time and money to conduct. In particular, the bus means indicators calculated using transportation card data were analyzed to compensate for the shortcomings of the existing operational status survey methods that rely entirely on site surveys. The city bus index calculated by using the transportation card data involves quantitative operation status data related to the user, and this results in the advantage of being able to conduct a complete survey without any data loss in the data collection process. We took the transportation card data from the entire city bus network of Ulsan Metropolitan City on Wednesday April 3, 2019. The data included information about passenger numbers/types, bus types, bus stops, branches, bus operators, transfer information, and so on. From the data analysis, it was found that a total of 234,477 people used the city bus on the one day, of whom 88.6% were adults and 11.4% were students. In addition, the stop with the most passengers boarding and alighting was Industrial Tower (10,861 people), A total of 20,909 passengers got on and off during the peak evening period of 5 PM to 7 PM, and 13,903 passengers got on and off the No. 401 bus route. In addition, the top 26 routes in terms of the highest number of passengers occupied 50% of the total passengers, and the top five bus companies carried more than 70% of passengers, while 62.46% of the total routes carried less than 500 passengers per day. Overall, it can be said that this study has great significance in that it confirmed the possibility of replacing the existing survey method by analyzing city bus use by using transportation card data for Ulsan Metropolitan City. However, due to limitations in the collection of available data, analysis was performed only on one matched data, attempts to analyze time series data were not made, and the scope of analysis was limited because of not considering a methodology for efficiently analyzing large amounts of real-time data.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.3
• /
• pp.247-262
• /
• 2022

In domestic tunnels, it is mandatory to install CCTVs in tunnels longer than 200 m which are also recommended by installation of a CCTV-based automatic accident detection system. In general, the CCTVs in the tunnel are installed at a low height as well as near by the moving vehicles due to the spatial limitation of tunnel structure, so a severe perspective effect takes place in the distance of installed CCTV and moving vehicles. Because of this effect, conventional CCTV-based accident detection systems in tunnel are known in general to be very hard to achieve the performance in detection of unexpected accidents such as stop or reversely moving vehicles, person on the road and fires, especially far from 100 m. Therefore, in this study, the region of interest is set up and a new concept of inverse perspective transformation technique is introduced. Since moving vehicles in the transformed image is enlarged proportionally to the distance from CCTV, it is possible to achieve consistency in object detection and identification of actual speed of moving vehicles in distance. To show this aspect, two datasets in the same conditions are composed with the original and the transformed images of CCTV in tunnel, respectively. A comparison of variation of appearance speed and size of moving vehicles in distance are made. Then, the performances of the object detection in distance are compared with respect to the both trained deep-learning models. As a result, the model case with the transformed images are able to achieve consistent performance in object and accident detections in distance even by 200 m.

• Korean Journal of Mineralogy and Petrology
• /
• v.35 no.3
• /
• pp.367-376
• /
• 2022

This study is a preliminary step to understand the reaction between various liquids and zeolite in the subduction zone environment. Stilbite, NaCa₄(Al₉Si₂₇)O₇₂·28(H₂O), was selected and high pressure study was conducted on compressional behavior by the pressure-transmitting medium (PTM). Water and NaHCO₃ solution that can exist in the subduction zone was used as PTM, and samples were pressurized from ambient to a maximum of 2.5 GPa. Below 1.0 GPa, both experiments show a low linear compressibility in the range of 0.001 to 0.004 GPa^-1 and a high bulk modulus of 220(1) GPa. This is presumably because the structure of the stilbite becomes very dense due to insertion of water molecules or cations into the channel. On the other hand, at 1.0 GPa or higher, the trends of the two experiments are different. In the water run, the linear compressibility of the c-axis is increased to 0.006(1) GPa^-1. In the NaHCO₃ run, the linear compressibility of the b- and c-axis is increased to 0.006(1) GPa^-1. The bulk modulus after 1.0 GPa shows values of 40(1) and 52(7) GPa in water and NaHCO₃ run, respectively, confirming that stilbite becomes more compressible than that before 1.0 GPa. It is caused by the migration of cations and water molecules inside the channel, as the water molecules in the PTM start to freeze and stop to insert toward the channel at 1.0 GPa or more. In the NaHCO₃ run, it is assumed that the distribution of extra-framework species inside the structure is changed by substitution of the Na⁺ cation. It can be expected from tendency of the relative intensity ratio of the (001) and (020) peaks which show a different from that of the water run.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.307-325
• /
• 2023

Due to the prolonged COVID-19 pandemic, the frequency of people who are tired of living indoors visiting nearby mountains and national parks to relieve depression and lethargy has exploded. There is a place where thousands of people who came out of nature stop walking and breathe and rest, that is the mineral spring. Even in mountains or national parks, there are about 600 mineral springs that can be found occasionally in neighboring parks or trails in the metropolitan area. However, due to irregular and manual water quality tests, people drink mineral water without knowing the test results in real time. Therefore, in this study, we intend to develop a model that can predict the quality of the spring water in real time by exploring the factors affecting the quality of the spring water and collecting data scattered in various places. After limiting the regions to Seoul and Gyeonggi-do due to the limitations of data collection, we obtained data on water quality tests from 2015 to 2020 for about 300 mineral springs in 18 cities where data management is well performed. A total of 10 factors were finally selected after two rounds of review among various factors that are considered to affect the suitability of the mineral spring water quality. Using AutoML, an automated machine learning technology that has recently been attracting attention, we derived the top 5 models based on prediction performance among about 20 machine learning methods. Among them, the catboost model has the highest performance with a prediction classification accuracy of 75.26%. In addition, as a result of examining the absolute influence of the variables used in the analysis through the SHAP method on the prediction, the most important factor was whether or not a water quality test was judged nonconforming in the previous water quality test. It was confirmed that the temperature on the day of the inspection and the altitude of the mineral spring had an influence on whether the water quality was unsuitable.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.123-138
• /
• 2017

Since the stock market is driven by the expectation of traders, studies have been conducted to predict stock price movements through analysis of various sources of text data. In order to predict stock price movements, research has been conducted not only on the relationship between text data and fluctuations in stock prices, but also on the trading stocks based on news articles and social media responses. Studies that predict the movements of stock prices have also applied classification algorithms with constructing term-document matrix in the same way as other text mining approaches. Because the document contains a lot of words, it is better to select words that contribute more for building a term-document matrix. Based on the frequency of words, words that show too little frequency or importance are removed. It also selects words according to their contribution by measuring the degree to which a word contributes to correctly classifying a document. The basic idea of constructing a term-document matrix was to collect all the documents to be analyzed and to select and use the words that have an influence on the classification. In this study, we analyze the documents for each individual item and select the words that are irrelevant for all categories as neutral words. We extract the words around the selected neutral word and use it to generate the term-document matrix. The neutral word itself starts with the idea that the stock movement is less related to the existence of the neutral words, and that the surrounding words of the neutral word are more likely to affect the stock price movements. And apply it to the algorithm that classifies the stock price fluctuations with the generated term-document matrix. In this study, we firstly removed stop words and selected neutral words for each stock. And we used a method to exclude words that are included in news articles for other stocks among the selected words. Through the online news portal, we collected four months of news articles on the top 10 market cap stocks. We split the news articles into 3 month news data as training data and apply the remaining one month news articles to the model to predict the stock price movements of the next day. We used SVM, Boosting and Random Forest for building models and predicting the movements of stock prices. The stock market opened for four months (2016/02/01 ~ 2016/05/31) for a total of 80 days, using the initial 60 days as a training set and the remaining 20 days as a test set. The proposed word - based algorithm in this study showed better classification performance than the word selection method based on sparsity. This study predicted stock price volatility by collecting and analyzing news articles of the top 10 stocks in market cap. We used the term - document matrix based classification model to estimate the stock price fluctuations and compared the performance of the existing sparse - based word extraction method and the suggested method of removing words from the term - document matrix. The suggested method differs from the word extraction method in that it uses not only the news articles for the corresponding stock but also other news items to determine the words to extract. In other words, it removed not only the words that appeared in all the increase and decrease but also the words that appeared common in the news for other stocks. When the prediction accuracy was compared, the suggested method showed higher accuracy. The limitation of this study is that the stock price prediction was set up to classify the rise and fall, and the experiment was conducted only for the top ten stocks. The 10 stocks used in the experiment do not represent the entire stock market. In addition, it is difficult to show the investment performance because stock price fluctuation and profit rate may be different. Therefore, it is necessary to study the research using more stocks and the yield prediction through trading simulation.

• Journal of Preventive Medicine and Public Health
• /
• v.31 no.1 s.60
• /
• pp.139-156
• /
• 1998

Diving related disease including decompression sickness is an important occupational health problem and diving fishermen remain a fairly hazardous occupation in Korea. To prevent diving related disease, we investigate diving patterns, incidence of diving related diseases, and contributing factors of 433 diving fishermen of three coast interviewing and mailing questionnaire in 1996. Mean age of divers was 39.7 years, ranged from 24 to 58 years, 92.8% of these were male, and 58.4% of divers were high school graduates. Mean duration of work as a diver was 12.9 years, ranged from 2 to 40 years. It was found that 70.4% of divers were using hookah system, 22.2% of helmet, and only 2.5% SCUBA. About half of them have learned diving skills from other divers. The peak season of diving was from April to June and mean working days were 20.3 days per month during the peak season. On the average, the divers dived 5-6 times, ranged from 1 to 10 times a day with 51.1 minutes of diving time, ranged from 20 to 120 minutes, at 30 m or 40 m in depth, and 35.5 minute of interval on surface. Most divers ascended slowly making decompression stop, yet the decompression profile used was not based on any scientific knowledge except for their own experiences. It appeared that each diving system had slightly different diving patterns. There were 282(65.0%) divers that suffered from DCS in 1995 and 31.2% of divers were given recompression therapy at a medical facility since they worked as diving fishermen. Skin and musculoskeletal complaints were common symptoms of DCS and 39% of divers experienced a voiding difficulty. In univariate analysis, females have an increased frequency of DCS(93% vs 66% for males). Old age, long duration of work, helmet diving, diving time, diving depth, repetitive diving, and blow up were all contributing factors to DCS. It was found that most diving patterns exceed no decompression limit and did not use the standard decompression table. This suggests that most of divers are at high risk of developing diving related disease with prolonged dives and lengthy repetitive diving in deep depth. Considering the diving patterns and economic aspect of professional diving, the incidence of DCS among diving fishermen in Korea will not decrease in the near future. These findings suggest that periodical health surveillance for divers, and education of health and safety are important for reducing the risk of diving related disease in the population of diving fishermen.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.17 no.2
• /
• pp.31-36
• /
• 2013

Purpose: Measure gastric emptying time (GET: Gastric Emptying Time) is a non-invasive and quantitative evaluation methods, mainly by endoscopic or radiological examination confirmed no mechanical obstruction in patients with symptoms of congestion is checked. Such tests are not common gastric emptying time measured esophageal cancer patients (who underwent esophagectomy) patients after surgery for gastric emptying time was measured test. And the period of time for more than one year after the gastric emptying time measurement was performed. By comparing the two kinds of tests in the chest cavity after surgery as the evaluation of gastrointestinal function tests evaluate the usefulness of GET, and will evaluate the characteristics of the image. Materials and Methods: 93 patients who underwent esophagectomy with gastric emptying time measurement of subject tests immediately after surgery and after 1 year or longer were twice. Preparation of the patient before the test is more than 12 hours of overnight fasting is important, in addition to the medicine or to stop smoking, and diabetes insulin injections should be early in the morning is ideal to test. Generally labeled with $^{99m}Tc-DTPA$ resin which is used to make steamed egg, seaweed and fermented milk with a high viscosity after eating, three hours in the standing position was measured. Evaluation of gastric emptying curves on the way intragastric radioactivity level by 50% the time (half-time [T1/2]) was calculated, based on the half-life was divided into three steps: over 180 minutes was defined as delayed gastric emptying, within 180minutes was defined as intermediate gastric emptying and when all the radioisotopes were dumped into the jejunum as soon as swallowed, was defined as rapid gastric emptying. Results: Gastric emptying time of a typical images stomach of antrum and fundus additional images appear stronger over time move on to the small intestine. but esophageal cancer who underwent esophagectomy side of the thoracic cavity showed a strong image. Immediately after surgery, the half-time (T1/2) of rapid gastric emptying appeared to 12.9%, intermediate gastric emptying appeared to 52.7%, delay gastric emptying appeared to 34.4%. After more than a year the results of the half-life after surgery, 67% of rapid gastric emptying to intermediate gastric emptying was changed, 69% of delay gastric emptying to intermediate gastric emptying changed. Intermediate gastric emptying worse in patients rapid gastric emptying and the delay gastric emptying is 24% in the case. Conclusion: Esophagectomy for esophageal cancer who underwent half-time measurement test (T1/2) rapid gastric emptying and delay gastric emptying are the result of the comparison over time, changes were observed intermediate gastric emptying. Mainly seeing of gastric emptying time measurement in the esophagus instead of thoracic cavity to check the evaluation of gastrointestinal function can be useful even means. And segmentation criteria and narrow time interval of checking if more accurate information and analysis of the clinical diagnosis and evaluation seems to be done.

• Proceedings of the KOR-BRONCHOESO Conference
• /
• 1972.03a
• /
• pp.5-6
• /
• 1972

Noise and air pollution, which accompany the development of industry and the increase of population, contribute to the deterioration of urban environment. The air pollution level of Seoul has gradually increased and the city residents are suffering from a high pollution of noise. If no measures were taken against pollution, the amount of emission of pollutant into air would be 36.7 thousand tons per year per square kilometer in 1975, three times more than that of 1970, and it would be the same level as that of United States in 1968. The main sources of air pollution in Seoul are the exhaust has from vehicles and the combustion of bunker-C oil for heating purpose. Thus, it is urgent that an exhaust gas cleaner should be instaled to every car and the fuel substituted by less sulfur-contained-oil to prevent the pollution. Transportation noise (vehicular noise and train noise) is the main component of urban noise problem. The average noise level in downtown area is about 75㏈ with maximum of 85㏈ and the vehicular homing was checked 100㏈ up and down. Therefore, the reduction of the number of bus-stop the strict regulation of homing in downtown area and a better maintenance of car should be an effective measures against noise pollution in urban areas. Within the distance of 200 metres from railroad, the train noise exceeds the limit specified by the pollution control law in Korea. Especially, the level of noise and steam-whistle of train as measured by the ISO evaluation can adversely affect the community activities of residents. To prevent environmental destruction, many developed countries have taken more positive action against worsening pollution and such an action is now urgently required in this country.