• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.239-247
• /
• 2015

Recently, various research studies on frontal collision and rear-ender which occur more frequently compared to others are underway as the public interest on them is growing. This study analyzes scientifically the relationship between effective impact speed and injury incidence for vehicle crash accident reconstruction and presents a relevant model formula. Because real vehicle experiments have certain limitations such as possible injuries, this study efforts to collect and analyze as many materials as possible to substitute real vehicle experiments, including data from various collision tests and human experiments. As a result, this study present a threshold in which head-on collisions and rear impacts do not cause injuries under 7 km/h of effective impact speed, and suggests a model formula showing that injury extent is linearly proportional to effective impact speed through collision speed and amount of plastic deformation. In conclusion, a model formula for estimating effective impact speed and injury incidence newly proposed in this study is expected to be used as a minimum standard of judgment in disputes on the injury extent of passenger in head-on collisions and rear impacts. Furthermore its availability in terms of technological analysis in legal arguments is expected to be very high if this study will be enhanced by referring to scientific analyses of various real accidents so as to apply it in various types of collision accidents.

• Journal of Biomedical Engineering Research
• /
• v.39 no.5
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.7
• /
• pp.843-856
• /
• 2023

The global surge in maritime traffic has resulted in an increased number of ship collisions, leading to significant economic, environmental, physical, and human damage. The causes of these maritime accidents are multifaceted, often arising from a combination of crew judgment errors, negligence, complexity of navigation routes, weather conditions, and technical deficiencies in the vessels. Given the intricate nuances and contextual information inherent in each incident, a methodology capable of deeply understanding the semantics and context of sentences is imperative. Accordingly, this study utilized the SentenceBERT model to analyze maritime safety tribunal decisions over the last 20 years in the Busan Sea area, which encapsulated data on ship collision incidents. The analysis revealed important keywords potentially responsible for these incidents. Cluster analysis based on the frequency of specific keyword appearances was conducted and visualized. This information can serve as foundational data for the preemptive identification of accident causes and the development of strategies for collision prevention and response.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.47-56
• /
• 2020

The stock index is used not only as an economic indicator for a country, but also as an indicator for investment judgment, which is why research into predicting the stock index is ongoing. The task of predicting the stock price index involves technical, basic, and psychological factors, and it is also necessary to consider complex factors for prediction accuracy. Therefore, it is necessary to study the model for predicting the stock price index by selecting and reflecting technical and auxiliary factors that affect the fluctuation of the stock price according to the stock price. Most of the existing studies related to this are forecasting studies that use news information or macroeconomic indicators that create market fluctuations, or reflect only a few combinations of indicators. In this paper, this we propose to present an effective combination of the news information sentiment analysis and various macroeconomic indicators in order to predict the US Dow Jones Index. After Crawling more than 93,000 business news from the New York Times for two years, the sentiment results analyzed using the latest natural language processing techniques BERT and NLTK, along with five macroeconomic indicators, gold prices, oil prices, and five foreign exchange rates affecting the US economy Combination was applied to the prediction algorithm LSTM, which is known to be the most suitable for combining numeric and text information. As a result of experimenting with various combinations, the combination of DJI, NLTK, BERT, OIL, GOLD, and EURUSD in the DJI index prediction yielded the smallest MSE value.

• Journal of the Korean GEO-environmental Society
• /
• v.13 no.12
• /
• pp.91-98
• /
• 2012

In this paper, the behavior of offshore wind turbine(OWT) foundation which is modeled by using existing design method and FEM is compared. When the same type of foundation is designed under the same sea and ground condition, the behavior characteristics with each model are compared. As a result, the member forces between apparent fixity and distributed spring type foundation which consider the ground stiffness are not different markedly, while fixed-base type foundation shows relatively lower member forces, which results in smaller safety margin. In other words, considering ground stiffness is reasonable because soil-pile interaction affects significantly on the analysis result. A case study with a monopile shows significant errors between p-y and FEM model at the head and tip of the pile. Also, it shows that the errors at the tip with diameter increase of the pile is larger. Thus, considering ground characteristics and engineering judgment are necessary in practice. A comparison of reliability analysis between tripod and monopile type foundation on the same condition shows larger probability of failure in monopile type and it indicates that the safety margin of monopile type can be lower.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.3
• /
• pp.52-60
• /
• 2018

In the automobile industry, in order to increase the fuel efficiency and conform to the safety regulations, it is necessary to make the vehicles as light as possible. Therefore, it is crucial to manufacture dual phase steels, complex phases steels, MS steels, TRIP steels, and TWIP from high strength steels with a tensile strength of 700Mpa or more. In order to apply ultra-high tensile strength steel to the body, the welding process is essential. Resistance spot welding, which is advantageous in terms of its cost, is used in more than 80% of cases in body welding. It is generally accepted that ultra-high tensile strength steel has poor weldability, because its alloy element content is increased to improve its strength. In the case of the resistance spot welding of ultra-high tensile steel, it has been reported that the proper welding condition area is reduced and interfacial fracture and partial interfacial fracture occur in the weld zone. Therefore, research into the welding quality judgment that can predict the defect and quality in real time is being actively conducted. In this study, the dynamic resistance of the weld was monitored using the secondary circuit process variables detected during resistance spot welding, and the factors necessary for the determination of the welding quality were extracted from the dynamic resistance pattern. The correlations between the extracted factors and the weld quality were analyzed and a regression analysis was carried out using highly correlated pendulums. Based on this research, a regression model that can be applied to the field was proposed.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.1
• /
• pp.12-22
• /
• 2013

Construction industry throughout the construction projects life cycle using BIM is able to manage information. Among them, BIM-based quantity take-off is directly connected to the data of the construction business as an important management element that is essential for one of the management factors of feasibility study and economic analysis. In addition, the result of BIM-based quantity take-off can be varied depending on modeler, so the exact guideline for BIM modeling is necessary. The BIM-based quantity take-off in terms of reliability and accuracy of the information is very important. Therefore, this study verified the BIM modeling of the apartment interior materials using both separate object and composite object was validated the quantitative comparison of the difference in BIM-based quantity take-off for accuracy & reliability judgment of BIM-based quantity take-off and realistic & desirable suggestion of BIM modeling way. As the result of this study, it is preferable to model various interior materials to use separate object for the purpose of correct BIM-based quantity take-off, but the realistic way of the BIM modeling using both separate object and composite object jointly was verified in order to judge BIM-based quantity take-off in terms of work productivity.

• Journal of Korean Society of Transportation
• /
• v.32 no.5
• /
• pp.554-566
• /
• 2014

An objective of VMS(Variable Message Signs) is to make transportation system effective specifically for driver's path selection. The traffic solutions including a VMS problem can be modeled through Game Theory, however, the majority of the studies can not model various driver's response according to VMS information in game theory. So, this paper tries to analyze a driver's response according to VMS traffic informations through evolutionary game theory. We apply a behavior characteristics of driver to evolutionary game theory, then finds drivers are only accepting in case of the biggest pay-off, and if a traffic flow finds a balance over time, ratio of accepting information is converged as an evolutionary stable state gradually. Consequently, the strategy of the other drivers such as traffic problems can not be predicted accurately. In case, drivers repeat between groups and reasonable judgment by the experience, we expect that VMS can provide strategic information through evolutionary game theory.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.113-120
• /
• 2018

Angiography and CT angiography are used widely for the examination of vascular diseases, but the diagnosis of such diseases is made mostly by the subjective judgment of the inspector. This paper proposes a method for detecting the suspicious regions of stenosis and aneurysm in the inner surfaces of 3D blood vessel models reconstructed from medical images. Initially, the 3D curve-skeletons of the blood vessel models and the contours at the nodes of the curve-skeletons were generated. Next, the 3D curve-skeletons were divided into a set of branches and the areas of normal contours of nodes located in each branch were calculated. The nodes whose contours contain suspicious regions were detected by taking into account the average area, maximum and minimum areas, and the area difference between the adjacent normal contours. The diagnosis of stenosis and aneurysm can be supported by properly visualizing the suspicious regions detected. The suspicious regions of the disease were identified by implementing and testing it using several data sets of human blood vessels, highlighting the usefulness of the proposed method.

• Journal of the Korean Society of Safety
• /
• v.25 no.6
• /
• pp.34-39
• /
• 2010

The purpose of this study is to suggest objective evaluation model as a plan to utilize as opportunity in establishing judgment standard of mutual inspection criteria and to upgrade inspection ability by reviewing and analyzing level of danger and importance in advance based on inspection results of inspection institutions regarding tower cranes used in construction fields. Tower crane is a mechanical device transporting construction supplies and heavy materials to places over 20~150M high from the ground for the period ranging from a short time of 2~3 months to two years after being installed in construction sites in vicinity of buildings or structures and is an important facility indispensable for construction sites. However, since use period after installation is short and professional technical ability of technicians working on-site about of tower crane is poor, systematic and quantitative safety management is not carried out As a part of researches on procedure of RBI(Risk Based Inspection) possible to apply to Knowledge Based System based on knowledge and experiences of experts as well as to tower cranes for solving these problems, quantitative RPN(Risk Priority Number) was applied to RPN utilizing technique of FMEA(Failure Mode and Effect Analyses). When general RBI 80/20 Rule was applied parts with high level of risks were found out as wire rope, hoist up/down safety device, reduction gear, and etc. However, since there are still many insufficient parts as risk analyses of tower crane were not established, it is necessary for experts with sufficient experiences and knowledge to supplement active RBI techniques and continuous researches on tower cranes by sharing and setting up data base of important information with this study as a starting point.