• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.3
• /
• pp.58-64
• /
• 2021

As the number of registered vehicles increases, traffic congestion will worsen worse, which may act as an inhibitory factor for urban social and economic development. Through accurate traffic flow prediction, various AI techniques have been used to prevent traffic congestion. This paper uses the data from a VDS (Vehicle Detection System) as input variables. This study predicted traffic flow in five levels (free flow, somewhat delayed, delayed, somewhat congested, and congested), rather than predicting traffic flow in two levels (free flow and congested). The Catboost model, which is a machine-learning algorithm, was used in this study. This model predicts traffic flow in five levels and compares and analyzes the accuracy of the prediction with other algorithms. In addition, the preprocessed model that went through RandomizedSerachCv and One-Hot Encoding was compared with the naive one. As a result, the Catboost model without any hyper-parameter showed the highest accuracy of 93%. Overall, the Catboost model analyzes and predicts a large number of categorical traffic data better than any other machine learning and deep learning models, and the initial set parameters are optimized for Catboost.

• The Journal of the Korea Contents Association
• /
• v.15 no.7
• /
• pp.106-116
• /
• 2015

Recently, growing up in social and economic development, the lifestyle of Koreans brought many changes in the form of leisure activity and influenced a lot in leisure. In particular, the establishment of the five-day work week increased the leisure time and became popular with family activities. Accordingly, the base of the leisure population expanding, people have an interest in the new way of leisure and the desire is increasing. Camping culture that increasingly take place in the tent camping now is changing into a cultural center to enjoy the camping SUV vehicle. The desire of consumers for the design of the unique exterior and interior caravan increasingly appearing as a major requirement. In this study, we propose a caravan design development strategies to meet the needs of such customers. First analyzes the hypothesis set and to identify the Overview of the caravan, and optimization of use and the problem of the user. Proceed with the design map analysis through classification of the caravan design registered in the KIPO, and proceed to the market research and patented technology to identify and to proceed with the caravan design development strategies for the various products.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.4
• /
• pp.667-675
• /
• 2016

The goal of this study is to be used as baseline data for transportation demand management. At the present time the number of registered car and householding car is increasing, so there is a need to analyze the car ownership pattern through household car hold status. Also, it is necessary to analyze the factor of increasing car. The research is proceeded with classifying as the household which is holding private cars or holding passenger cars and non passenger cars based on the result of the research of the household travel survey data. The result of this study is shown as follows. According to car ownership pattern, there are more households holding passenger cars only when they are holding less than 2 cars. Otherwise there are more households holding passenger car and non passenger car when they are holding more than 3 cars. Using the Ordered Logit Model, there are more differences in factors affects holding cars by variables of housing type and household properties.

• Journal of Hydrogen and New Energy
• /
• v.23 no.6
• /
• pp.634-639
• /
• 2012

The contribution levels of emissions from the heavy-duty vehicles have been continuously increased. Among the exhaust emissions, NOx (nitric oxides) have a ratio of 73.2% and particle matters have a proportion of 61.8% in the heavy-duty vehicles. Also, natural gas vehicles have the 78.9% of total registered local buses in Korea. Therefore, the investigation on emission characteristics of heavy-duty vehicles using CNG and diesel fuel according to the various driving cycles was carried out in this study. In order to analyze the emission characteristics, the five kinds of buses by using CNG and diesel fuels with a after-treatment devices (DPF, p-DPF) was used and five test driving schedules were applied for analysis of emission characteristics in a chassis dynamometer. To analyze the exhaust emission, the exhaust emission and PM analyzers were used. From this study, it is revealed that diesel buses with after-treatment had reduced emission of CO, HC, PM but NOx. Also, NMHC emission of CNG bus have a higher level and NOx level was similar with diesel buses. In addition, emissions in NIER06 with slow average speed shows lowest levels compared to other test modes.

• Journal of Convergence for Information Technology
• /
• v.10 no.5
• /
• pp.111-116
• /
• 2020

Recently, many safety accidents involving children shuttle buses take place. Without a teacher for help, a safety accident occurs when the driver can't see a child who is getting off in the blind spot of both frontside and backside. A deep learning-based smart mirror allows user authentication and provides various services. Especially, It can be a role of helper for children, and prevent accidents that can occur when drivers or assistant teachers do not see them. User authentication is carried out with children's face registered in advance. Safety accidents can be prevented by an approximate sensor and a camera in frontside and backside of the bus. This study suggests a way of checking out whether children are missed in the process of getting in and out of the bus, designs a system that reduce blind spots in the front and back of the vehicle, and builds a safety system that provide various services using GPS.

• Journal of Ocean Engineering and Technology
• /
• v.32 no.4
• /
• pp.287-295
• /
• 2018

This paper presents the results of an exploration of the ferromanganese crusts of Western Pacific Seamount registered by the Korean government. This area has been surveyed with a deep-sea camera and crust samples have been acquired by deep-sea dredging since 2013. On October 18-19, 2017, a united research team from KIOST and KRISO explored two blocks, OSM11 and OSM07, on the seamount using Hemire ROV. A precise survey was conducted on the ferromanganese crusts and sediments covering the slope/top of OSM11 and the middle flat area of OSM07. Rock samples were collected with precise positioning, and HD videos were recorded for 7 hours. This paper discusses the technical issues of this exploration in terms of (1) how to deal with an emergency situation during an electric power blackout, (2) the improvement of the thruster power by adding cooling plugs to the housings of the thruster amplifiers, (3) the relative motion of the depressor by changing the fixing method of the cable terminator, which affects the service life of the cable, (4) a sampling technique for the steep slope of the seamount, (5) integrated navigation under a USBL blackout, and (6) a 3-dimensional image mosaic for visualizing the distribution state of the crusts.

• Journal of Home Health Care Nursing
• /
• v.12 no.1
• /
• pp.41-69
• /
• 2005

Purpose: This study was performed to evaluate the outcomes of the home care nursing program conducted jointly by thirty two catholic churches and C hospital in Seoul. Method: The subjects included 173 patients who registered for the program during a 4 month-period from November 1, 2004 to February 28, 2005 and received home care services for more than 4 times and 32 professional nurses participating in the program. Using the concept of medical outcome study (MOS), the structure, process, outcome elements were analyzed. Result: 1) A Catholic homecare nursing center and nurses of the C hospital played a central role in providing nursing care, and each church operated its own vehicle from its own office. Home care nurse's job satisfaction was 2.8 out of total score of 4. The major illness was cerebrovascular disease including stroke followed by skeletomuscular disease including degenerative arthritis cancer, and diabetes. Among reasons for accessing the home care nursing program, hypertension management was most prevalent. More than half of the registration was done through catholic churches. Most people who referred the patient to the program was through the church. Most patients received home care nursing 1-2 times a week for 30 to 60 minutes in average and the most frequent type of service provided was basic nursing. 3) The most frequent reason for terminating home care services was death. The change in PPS(Palliative Performance Scale) level from the time of registration and after 4 visits was the same in 45%, decreased in 30%, and improved in 25%. Patient satisfaction was very high, showing 3.4 out of total score of 4. Conclusion: These results proved that the home care nursing program was highly appreciated by subjects and nurses were providing professional care. Thus the two parties involved in the program were actively supporting the program to fulfill their mission. However, several areas needed to be improved such as relating with local community, relating with family doctor, and issue of improving the working conditions for home care nurses.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.8
• /
• pp.1139-1145
• /
• 2018

According to the prosecutors' office's statistics for 2014, 53% of a bicycle users have experienced theft. The reason for the high rate of bicycle stolen in Korea is that there is no bicycle management system. This is because they do not use bicycle numbers to manage bikes like cars do. Most people do not know if they have a VIN(Vehicle Identification Number) on their bike. If the buyer registers the bicycle in the bicycle management blockchain system, anyone can view the information registered in the chain, so that if the bicycle number is filled in, the bicycle can be identified. In addition, when an accident occurs, blockchain will record what kind of equipment it is replacing, like an automobile, to manage all the information about the bicycle. In this way, consumers can inquire whether they have a history of accident when they make a second-hand transaction. In this paper, we propose a method to construct bicycle management system using bicycle VIN.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.46 no.3
• /
• pp.183-190
• /
• 2020

Objectives: The purpose of this retrospective epidemiological study was to determine the etiology and pattern of maxillofacial injuries in a pediatric population. Materials and Methods: Data for pediatric maxillofacial trauma patients aged 12 years and younger who were registered at the Department of Pediatric and Preventive Dentistry, Dr. R. Ahmed Dental College and Hospital, Kolkata, India, were reviewed and examined. Patients who were treated between October 2016 and September 2018 were analyzed according to age, sex, cause of injury, frequency and site of facial fractures, and soft tissue injuries. The chi-square tests were carried out for statistical analyses with a significance level of 5%. Results: Of 232 patients with a mean age of 6.77±3.25 years, there were 134 males (57.8%) and 98 females (42.2%). The overall male to female ratio was 1.39:1. The most common causes of injuries were falls (56.5%) and motor vehicle accidents (16.8%). Incidence of falls decreased significantly with age (P<0.001). Dentoalveolar injuries (61.6%) and soft tissue injuries (57.3%) were more common than facial fractures (42.7%). Mandibular fractures (82.8%) were the most common facial fractures, and perioral or lip injuries were the most prevalent injuries in our patient population. There was a positive association between facial fractures and soft tissue injury (P<0.01) (odds ratio 0.26; confidence interval 0.15-0.46). Conclusion: Falls were the leading cause of maxillofacial trauma in our sample of children, and the most common site of fractures was the mandible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.6
• /
• pp.211-221
• /
• 2019

The death toll for every 10,000 cars registered in Korea is 1.4, which is still the lowest among OECD members, and the need for rescue and response systems is emerging. In response, the company is developing a vehicle ICT-based emergency rescue system (e-Call) that can handle accidents such as rapid and accurate life saving by automatically sending accident detection and related information to the central center in the event of a traffic accident. However, ordinary citizens are negative about the installation and cost of e-Call services. To solve these problems, various introduction and operation methods of e-Call were proposed for activation of terminal distribution. In addition, the effect of introducing e-Call was analyzed by predicting the penetration rate of e-Call terminals. Analysis shows that 463 to 926 deaths and 3,335 to 6,66.9 billion won will be saved in 10 years after the introduction of e-Call terminals.