• 대한건축학회논문집:구조계
• /
• 제35권11호
• /
• pp.155-162
• /
• 2019

The construction industry is the highest safety accident causing industry as 28.55% portion of all industries' accidents in Korea. In particular, falling is the highest accidents type composed of 60.16% among the construction field accidents. Therefore, we analyzed the factors of major disaster affecting the fall accident and then derived feature importances by considering various variables. We used data collected from Korea Occupational Safety & Health Agency (KOSHA) for learning and predicting in the proposed model. We have an effort to predict the degree of occupational fall accidents by using the machine learning model, i.e., Adaboost, short for Adaptive Boosting. Adaboost is a machine learning meta-algorithm which can be used in conjunction with many other types of learning algorithms to improve performance. Decision trees were combined with AdaBoost in this model to predict and classify the degree of occupational fall accidents. HyOperpt was also used to optimize hyperparameters and to combine k-fold cross validation by hierarchy. We extracted and analyzed feature importances and affecting fall disaster by permutation technique. In this study, we verified the degree of fall accidents with predictive accuracy. The machine learning model was also confirmed to be applicable to the safety accident analysis in construction site. In the future, if the safety accident data is accumulated automatically in the network system using IoT(Internet of things) technology in real time in the construction site, it will be possible to analyze the factors and types of accidents according to the site conditions from the real time data.

• 한국BIM학회 논문집
• /
• 제10권4호
• /
• pp.22-31
• /
• 2020

Shop drawing tasks conducted after finishing coordinated or engineering design have great influences on the quality and cost of a project. However, despite the development of commercial BIM applications, shop drawings have mainly produced manually in certain engineering fields. Incorrect shop drawings with human errors have occurred various problems such as cost overrun, time delay and reworks. An automated shop drawing publishing from BIM is expected to resolve these problems. Despite attempts for automate shop drawing production, the field of mechanical, electrical and plumbing (MEP) is yet regarded challenging due to complexity of components and connection. In this research, we develop a process for automated producing 3D MEP shop drawings in BIM environment as following steps: to analyze conventional MEP shop drawing process, to identify detailed process that can be automated, to classify existing MEP objects and assign codes usable in BIM, and to develop an application. The validation of automated process is conducted against 10 clean room projects in which MEP is more complex and its cost is higher than other projects in terms of productivity and workers' satisfaction. Results show that the number of manpower for shop drawing is reduced by 30%, and the working time is shortened by 31%. Personal opinions of involved practitioners is interpreted as positive as the average rate of agrement on practicability, easy-to-use and necessary retouch tasks is around 66%.

• 한국추진공학회지
• /
• 제24권6호
• /
• pp.69-77
• /
• 2020

액체 핀틀 추력기의 성능해석을 위해 준 일차원 다상 반응유동 해석코드를 개발하였다. 해석코드의 주요모델로서 다상 유동장, 액적의 기화, 다상 연소, 액체 막냉각 등의 모델들을 적용하였다. 액적기화 모델은 Abramzon의 기화모델을 적용하였으며 연소 모델은 flamelet 모델을 적용하였다. 막냉각 효과는 Shine의 모델을 적용하였다. 각 모델을 사용하여 산소-질소의 Sod shock 튜브, n-decane 액적기화, 케로신 다상연소, 막냉각 길이를 계산하여 선행 연구자의 결과와 비교 검증하였다.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• 대기
• /
• 제31권5호
• /
• pp.489-510
• /
• 2021

In this paper, we propose an algorithm for detecting convective initiation (CI) using GEO-KOMPSAT-2A/advanced meteorological imager data. The algorithm identifies clouds that are likely to grow into convective clouds with radar reflectivity greater than 35 dBZ within the next two hours. This algorithm is developed using statistical and qualitative analysis of cloud characteristics, such as atmospheric instability, cloud top height, and phase, for convective clouds that occurred on the Korean Peninsula from June to September 2019. The CI algorithm consists of four steps: 1) convective cloud mask, 2) cloud object clustering and tracking, 3) interest field tests, and 4) post-processing tests to remove non-convective objects. Validation, performed using 14 CI events that occurred in the summer of 2020 in Korean Peninsula, shows a total probability of detection of 0.89, false-alarm ratio of 0.46, and mean lead-time of 39 minutes. This algorithm can be useful warnings of rapidly developing convective clouds in future by providing information about CI that is otherwise difficult to predict from radar or a numerical prediction model. This CI information will be provided in short-term forecasts to help predict severe weather events such as localized torrential rainfall and hail.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.294-302
• /
• 2022

Detection of fake news is a complex and a challenging task. Generation of fake news is very hard to stop, only steps to control its circulation may help in minimizing its impacts. Humans tend to believe in misleading false information. Researcher started with social media sites to categorize in terms of real or fake news. False information misleads any individual or an organization that may cause of big failure and any financial loss. Automatic system for detection of false information circulating on social media is an emerging area of research. It is gaining attention of both industry and academia since US presidential elections 2016. Fake news has negative and severe effects on individuals and organizations elongating its hostile effects on the society. Prediction of fake news in timely manner is important. This research focuses on detection of fake news spreaders. In this context, overall, 6 models are developed during this research, trained and tested with dataset of PAN 2020. Four approaches N-gram based; user statistics-based models are trained with different values of hyper parameters. Extensive grid search with cross validation is applied in each machine learning model. In N-gram based models, out of numerous machine learning models this research focused on better results yielding algorithms, assessed by deep reading of state-of-the-art related work in the field. For better accuracy, author aimed at developing models using Random Forest, Logistic Regression, SVM, and XGBoost. All four machine learning algorithms were trained with cross validated grid search hyper parameters. Advantages of this research over previous work is user statistics-based model and then ensemble learning model. Which were designed in a way to help classifying Twitter users as fake news spreader or not with highest reliability. User statistical model used 17 features, on the basis of which it categorized a Twitter user as malicious. New dataset based on predictions of machine learning models was constructed. And then Three techniques of simple mean, logistic regression and random forest in combination with ensemble model is applied. Logistic regression combined in ensemble model gave best training and testing results, achieving an accuracy of 72%.

• Journal of Radiation Protection and Research
• /
• 제47권3호
• /
• pp.152-157
• /
• 2022

Background: The hemi-body electron beam irradiation (HBIe^-) technique has been proposed for the treatment of mycosis fungoides. It spares healthy skin using an electron shield. However, shielding electrons is complicated owing to electron scattering effects. In this study, we developed a thimble-like head bolus shield that surrounds the patient's entire head to prevent irradiation of the head during HBIe^-. Materials and Methods: The feasibility of a thimble-like head bolus shield was evaluated using a simplified Geant4 Monte Carlo (MC) simulation. Subsequently, the head bolus was manufactured using a three-dimensional (3D) printed mold and Ecoflex 00-30 silicone. The fabricated head bolus was experimentally validated by measuring the dose to the Rando phantom using a metal-oxide-semiconductor field-effect transistor (MOSFET) detector with clinical configuration of HBIe^-. Results and Discussion: The thimble-like head bolus reduced the electron fluence by 2% compared with that without a shield in the MC simulations. In addition, an improvement in fluence degradation outside the head shield was observed. In the experimental validation using the inhouse-developed bolus shield, this head bolus reduced the electron dose to approximately 2.5% of the prescribed dose. Conclusion: A thimble-like head bolus shield for the HBIe^- technique was developed and validated in this study. This bolus effectively spares healthy skin without underdosage in the region of the target skin in HBIe^-.

• Design & Manufacturing
• /
• 제16권1호
• /
• pp.55-61
• /
• 2022

As meters become digital and smart, energy data such as electricity, gas, heat, and water can be accurately and efficiently measured with a smart meter, providing consumers with data on energy used, so that real-time demand response and energy management services can be utilized. Although it is developing from a simple metering system to a smart metering industry to create a high value-added industry fused with ICT, illegal counterfeiting of electronic meters is causing problems in intelligent crimes such as manipulation and hacking of SW. The meter not only allows forgery of the meter data through arbitrary manipulation of the SW, but also leaves a fatal error in the metering performance, so that the OIML requires the validation of the SW from the authorized institution. In order to solve this problem, a quantitative confirmation device was developed in order to eradicate the act of cheating the fuel oil quantity through encoder pulse operation and program modulation, etc. In order to prevent the act of deceiving the lubricator, a device capable of checking pulse forgery was developed, manufactured, and verified. In addition, the performance of the device was verified by conducting an experiment on the meter being used in the actual field. It is judged that the developed quantitative confirmation device can be applied to other flow meters other than lubricators, and in this case, accurate measurement can be induced.

• 아태비즈니스연구
• /
• 제12권4호
• /
• pp.163-178
• /
• 2021

Purpose - The purpose of this study is to develop a tool to measure the corporate social responsibility activities of tourism and hotel companies using ISO26000 and to verify its reliability and validity. Design/Methodology/Approach - This study is the development of a tool for evaluating social responsibility activities of tourism and hotel companies. For this, as the first stage filer research, 4 experts developed the questions based on ISO26000. And 12 experts (academia, industry) were surveyed by Delphi to evaluate suitability. Finally, the validity and reliability of the development tool were verified for a total of 55 incumbents and related persons. Research Results - For the development of a tool for measuring social responsibility activities of tourism and hotel companies, based on the standard draft of ISO26000, questions that fit 7 core areas were composed (60 questions). In addition, a Delphi survey was conducted on a panel of 12 experts, and a total of 45 questions were derived. Finally, as a result of an exploratory factor analysis of 55 field experts, 20 items consisting of 6 factors were finally confirmed as a measuring tool for social responsibility activities of tourism and hotel companies. Research implications or originality - It is significant for the first development of a social responsibility activity scale suitable for the situation of tourism and hotel companies by applying ISO26000. This will raise awareness of the importance of social responsibility activities in the tourism industry environment, and will help tourism companies to develop a positive awareness of social responsibility activities and to prepare effective implementation strategies.

• Geomechanics and Engineering
• /
• 제28권5호
• /
• pp.521-529
• /
• 2022

This research work deals with the development of air pluviation method for preparing uniform sand specimens for conducting large scale laboratory testing. Simulating real field conditions and to get reliable results, air pluviation method is highly desirable. This paper presents a special technique called air pluviation or sand raining technique for achieving uniform relative density. The apparatus is accompanied by a hopper, shutters with different orifice sizes and numbers and set of sieves. Before using this apparatus, calibration curves are drawn for relative density against different height of fall (H) and shutter sizes. From these calibration curves, corresponding to the desired relative density of 60%, the shutter size of 13mm and height of fall of 457.2 mm, are selected and maintained throughout the pluviation process. The density obtained from the mobile pluviator is then verified using the Dynamic Cone Penetrometer (DCP) test where the soil is poured in the box using defined shutter size and fall height. The results obtained from the DCP test are averaged as 60±0.5 which was desirable. The mobile pluviator used in this research is also capable of obtaining relative densities up to 90%. The instrument is validated using experimental and numerical approach. In numerical study, Plaxis 3D software is used in which the soil mass is defined by 10-Node tetrahedral elements and 6-Node plate is used to simulate plate behavior in the validation phase. The results obtained from numerical approach were compared with that of experimental one which showed very close correlation.