• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.26-37
• /
• 2017

The study is to develop safety performance functions(SPFs) for urban intersections using random effects Tobit regression model and to analyze correlations between crashes and factors. Also fixed effects Tobit regression model was estimated to compare and analyze model validation with random effects model. As a result, AADT, speed limits, number of lanes, land usage, exclusive right turn lanes and front traffic signal were found to be significant. For comparing statistical significance between random and fixed effects model, random effects Tobit regression model of total crash rate could be better statistical significance with $R^2_p$ : 0.418, log-likelihood at convergence: -3210.103, ${\rho}^2$: 0.056, MAD: 19.533, MAPE: 75.725, RMSE: 26.886 comparing with $R^2_p$ : 0.298, log-likelihood at convergence: -3276.138, ${\rho}^2$: 0.037, MAD: 20.725, MAPE: 82.473, RMSE: 27.267 for the fixed model. Also random effects Tobit regression model of injury crash rate has similar results of model statistical significant with random effects Tobit regression model.

• Korean Chemical Engineering Research
• /
• v.57 no.6
• /
• pp.781-789
• /
• 2019

There are frequent accidents by chemicals during laboratory experiments and pilot plant and reactor operations. It is necessary to find and comprehend relevant information to prevent accidents before starting synthesis experiments. In the process design stage, reaction information is also necessary to prevent runaway reactions. Although there are various sources available for synthesis information, including the Internet, it takes long time to search and is difficult to choose the right path because the substances used in each synthesis method are different. In order to solve these problems, we propose an intelligent synthetic path search system to help researchers shorten the search time for synthetic paths and identify hazardous intermediates that may exist on paths. The system proposed in this study automatically updates the database by collecting information existing on the Internet through Web scraping and crawling using Selenium, a Python package. Based on the depth-first search, the path search performs searches based on the target substance, distinguishes hazardous chemical grades and yields, etc., and suggests all synthetic paths within a defined limit of path steps. For the benefit of each research institution, researchers can register their private data and expand the database according to the format type. The system is being released as open source for free use. The system is expected to find a safer way and help prevent accidents by supporting researchers referring to the suggested paths.

• Journal of The Korean Association For Science Education
• /
• v.39 no.4
• /
• pp.563-571
• /
• 2019

The purpose of this study is to analyze the safety contents presented in high school science textbooks of the 2015 revised national science curriculum. For these, we found safety contents in the inquiries and appendices of 63 science textbooks: integrated science, science inquiry experiment, physics I, II, chemistry I, II, biology I, II, and earth science I, II. We analyzed these safety contents using six safety factors based on the seven standards for safety education. The main results are as follows: First, 81(46.0%) inquiries among 176 curriculum inquiries contain safety contents, and these contents are mainly found in chemistry textbooks, and the least in 'science inquiry experiment' textbooks. Second, safety contents are found the most in 'laboratory safety rule', followed by 'safety symbol' and 'usage of protection equipment'. Third, the safety contents of appendices are mainly in 'laboratory safety rule' and 'accident treatment'. Based on these results of this study, it is concluded that these textbooks have problems; that there is a big difference in describing safety contents in each textbook; that these safety contents are not presented in detail and that the educational effect is reduced. Furthermore, the safety symbol is not standardized. We also discussed ways to improve the safety contents of science textbooks.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.7
• /
• pp.870-874
• /
• 2018

In the worst maritime accidents, people should abandon ship, but ship structures are narrow and complex and operation takes place on rough seas, so escape is not easy. In particular, passengers on cruise ships are untrained and varied, making evacuation prospects worse. In such a case, the evacuation management of the crew plays a very important role. If a rescuer enters a ship at distress and conducts rescue activities, which zones represent the most effective entry should be examined. Generally, crew and rescuers take the shortest route, but if an accident occurs along the shortest route, it is necessary to select the second-best alternative. To solve this situation, this study aims to calculate evacuation routes using Q-Learning of Reinforcement Learning, which is a machine learning technique. Reinforcement learning is one of the most important functions of artificial intelligence and is currently used in many fields. Most evacuation analysis programs developed so far use the shortest path search method. For this reason, this study explored optimal paths using reinforcement learning. In the future, machine learning techniques will be applicable to various marine-related industries for such purposes as the selection of optimal routes for autonomous vessels and risk avoidance.

• Journal of Navigation and Port Research
• /
• v.47 no.3
• /
• pp.120-127
• /
• 2023

Maritime pilots are always exposed to unpredictable risks present in the marine environment because they are boarding ships through pilot ladders or accommodation ladders at sea. Since the pilot plays an important role in securing the safety of a ship entering or departing from a port, an injury to the pilot substantially affects the overall safety of the ship. The purpose of this study is to analyze pilot injuries and predict accidents. For this purpose, pilot injury cases are analyzed and potential situations are identified through a survey. Pilot injuries are also predicted. The survey was analyzed using the IPA (Importance-Performance Analysis) methodology, and the binomial distribution and Poisson distribution were used to predict injury trends. As a result of the study, 316.8 nearmiss occurred per pilot injury, and if the current accident management system is maintained, the probability of pilot injury occurring within 3 months is 64.4%. Based on the research results, the need for a management system to prevent pilot injuries and reinforcement of maintenance and installation for pilot ladders was suggested.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.245-250
• /
• 2017

Flash floods is defined as the flooding of intense rainfall over a relatively small area that flows through river and valley rapidly in short time with no advance warning. So that it can cause damage property and casuality. This study is to establish the flash-flood warning system using 38 accident data, reported from the National Disaster Information Center and Land Surface Model(TOPLATS) between 2009 and 2012. Three variables were used in the Land Surface Model: precipitation, soil moisture, and surface runoff. The three variables of 6 hours preceding flash flood were reduced to 3 factors through factor analysis. Decision tree, random forest, Naive Bayes, Support Vector Machine, and logistic regression model are considered as big data methods. The prediction performance was evaluated by comparison of Accuracy, Kappa, TP Rate, FP Rate and F-Measure. The best method was suggested based on reproducibility evaluation at the each points of flash flood occurrence and predicted count versus actual count using 4 years data.

• Journal of the Korean Society of Radiology
• /
• v.1 no.3
• /
• pp.35-40
• /
• 2007

The purpose of this study was to investigate in S city of Chung-Nam using direction radiation Cervical spine among patient enforcing AP view, lateral view, total 113 subjects(40-year-old low)by target examine and got following as: 1) Distribution of age 14~40 years old 57 men (50.4%), woman 56subjects(49.6%)be, and age group 30~40year old 80subjects(70.8 %), 20~29year old 27subjects(23.9%). 2) It appeared most by 81subjects(71.7%) that can not know cause though traffic accident, misstep, cause ignorantness were investigated to revealed by the chronic 87subjects(77%) appeared by thing which statistical significance is with occurrence cause. 3) 20 Among whole 113subjects 20~29years old 27 subjects(23.9%), 30~40years old 80 subjects(70.8%) manifestationacute form of a disease, the chronic all high distributionsee. 4) This investigator left shoulder region pain among 39 subjects whole 113 subjects (left to direction that could know that is each main pain in 34.5 %), cervical vertebral portion upside 31 subjects(27.4%), both shoulder region pain 20 subjects(17.7%), and becomes left side scoliosis 62 subjects(54.9%)by the most frequencies appear. 5) Appeared antespondylolisthesis by all curve 48 subjects(42.5 %) in curve direction and at Systolic blood pressure from 160mmHg to all 19 subjects (before total 69 subjects (61.0 %) at 16.8 %), Diastolic blood pressures curve 31 subjects(27.4 %) by 100 mmHg appear.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.49-59
• /
• 2023

There are various items in the safety and health standards of the manufacturing industry, but they can be divided into work-related diseases and musculoskeletal diseases according to the standards for sickness and accident victims. Musculoskeletal diseases occur frequently in manufacturing and can lead to a decrease in labor productivity and a weakening of competitiveness in manufacturing. In this paper, to detect the musculoskeletal harmful factors of manufacturing workers, we defined the musculoskeletal load work factor analysis, harmful load working postures, and key points matching, and constructed data for Artificial Intelligence(AI) learning. To check the effectiveness of the suggested dataset, AI algorithms such as YOLO, Lite-HRNet, and EfficientNet were used to train and verify. Our experimental results the human detection accuracy is 99%, the key points matching accuracy of the detected person is @AP0.5 88%, and the accuracy of working postures evaluation by integrating the inferred matching positions is LEGS 72.2%, NECT 85.7%, TRUNK 81.9%, UPPERARM 79.8%, and LOWERARM 92.7%, and considered the necessity for research that can prevent deep learning-based musculoskeletal diseases.

• Transactions of the KSME C: Technology and Education
• /
• v.5 no.2
• /
• pp.135-143
• /
• 2017

The domestic unique research reactor, HANARO (Hi-flux Advanced Neutron Application ReactOr), has been constructed with the open-pool, the core is submerged in, for the multi-purpose neutron application. The reactor has a primary cooling system to remove the fission heat from the core and its connected fluidic systems. Since the works are required at the reactor pool top as a characteristic of the research reactor, the radiation shall be minimized with the operation of the hot water layer system to avoid unnecessary radiation exposure on the workers during work at the pool top. Moreover, the pool water management system is connected to the reactor pool to maintain the pool temperature below $50^{\circ}C$ to minimize the uprising radioactive gas or impurity from the colder pool bottom. For the efficient flow rate of the PWMS, the thermal capacity of heat exchanger is selected with 260 kW in the normal operation condition. In this paper, the modeling is formulated to figure out whether or not each pool temperature maintains below the temperature limit and the calculation results show that the designed PWMS heat exchanger has enough capacity with the design margin regardless of the reactor operation mode.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.25 no.5
• /
• pp.542-549
• /
• 2019

Maritime accidents, such as the collision of a fishing boat in Incheon's Yeongheung Island, result in several casualties and property damage, even if they occur just once. To prevent such accidents, the Incheon Metropolitan Government is implementing safety management policies; further, they will provide ship collision warning services to prevent collisions on WAVE (Wireless Access in Vehicular Environment) communication-based ship safety operation pilot projects. However, to realize these objectives, a service standardization method is required that defines specific service types, configurations, and systems, which should be prepared based on user requirement analyses. In this study, a standardization method of WAVE communication-based collision warning service was developed by analyzing the requirements of the vessel operators subject to the services and related authorities. This will help improve the quality of service, ensuring professionalism and reliability through continuous improvement and efforts for standardization, as well as data derived from demonstration projects. Therefore, it is expected to help prevent maritime accidents to a considerable extent.