Elevators are the main means of transport in buildings. A malfunction of an elevator in operation may cause in convenience to users. Furthermore, fatal accidents, such as injuries and death, may occur to the passengers also. Therefore, it is important to prevent failure before accidents happen. In related studies, preventive measures are proposed through analyzing failures, and the lifespan of elevator components. However, these methods are limited to existing an elevator model and its surroundings, including operating conditions and installed environments. Vibration occurs when the elevator is operated. Experts have classified types of faults, which are symptoms for malfunctions (failures), via analyzing vibration. This study proposes an artificial intelligent model for classifying faults automatically with deep learning algorithms through elevator vibration data, hereby preventing failures before they occur. In this study, the vibration data of six elevators are collected. The proposed methodology in this paper removes "the measurement error data" with incorrect measurements and extracts operating sections from the input datasets for proceeding deep learning models. As a result of comparing the performance of training five deep learning models, the maximum performance indicates Accuracy 97% and F1 Score 97%, respectively. This paper presents an artificial intelligent model for detecting elevator fault automatically. The users’ safety and convenience may increase by detecting fault prior to the fatal malfunctions. In addition, it is possible to reduce manpower and time by assisting experts who have previously classified faults.

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

North Korea continues to upgrade and display its long-range rocket launchers to emphasize its military strength. Recently Republic of Korea kicked off the development of anti-artillery interception system similar to Israel’s “Iron Dome”, designed to protect against North Korea’s arsenal of long-range rockets. The system may not work smoothly without the function assigning interceptors to incoming various-caliber artillery rockets. We view the assignment task as a dynamic weapon target assignment (DWTA) problem. DWTA is a multistage decision process in which decision in a stage affects decision processes and its results in the subsequent stages. We represent the DWTA problem as a Markov decision process (MDP). Distance from Seoul to North Korea’s multiple rocket launchers positioned near the border, limits the processing time of the model solver within only a few second. It is impossible to compute the exact optimal solution within the allowed time interval due to the curse of dimensionality inherently in MDP model of practical DWTA problem. We apply two reinforcement-based algorithms to get the approximate solution of the MDP model within the time limit. To check the quality of the approximate solution, we adopt Shoot-Shoot-Look(SSL) policy as a baseline. Simulation results showed that both algorithms provide better solution than the solution from the baseline strategy.

MRI는 인체에 수소 밀도에 따른 재현성의 차이가 상대적으로 기존의 영상 장비들에 비교하여 큰 차이가 있으므로 임상 에서 이를 증명하고 문제 발견 시 이를 보완하는 것이 딥러닝 알고리즘은 매우 중요하다. 따라서 본 연구에서는 현재 특수 의료장비에서 권하는 미국 방사선 의학회(American College of Radiology, ACR)의 두부 전용 MRI 팬텀을 사용하여 영상 품질기준에 현재 임상 적용되고 있는 딥러닝 알고리즘 방법을 적용하여 딥러닝 알고리즘 적용 전후 변화를 평가해 보고자 하였다. 연구 결과 분해능을 측정하는 항목인 고대조도 공간 분해능과 같이 해상도와 관련된 영상 품질은 분해능은 개선되었음을 알 수 있었고, 그뿐만 아니라 위치의 정확도 역시도 기존에 딥러닝 알고리즘의 적용 전 영상과 통계적으로 차이가 있었다. 또한 딥러닝 알고리즘의 강도 차이에도 영상 간 차이는 없었다. 이러한 결과는 특수의료장비 영상품질관리 규정에 적용되고 있는 ACR 팬텀의 평가 기준에 부합 하나, 딥러닝 알고리즘 적용 전후 차이가 통계적으로 있었으며, 이러 한 차이가 재현성과 관련하여 추후에 조금 더 관련된 연구기 필요할 것으로 사료된다.

경추 MRI는 연부 조직에 대한 대조도와 분해능이 우수하여 경추 부위의 퇴행성 질환 및 추간공의 협착, 척수염, 추간판 탈출증 등의 신경 질환 검사에 특히 이용되고 있다. 그러나 경추 MRI 검사는 신경 질환에 의한 배경 신호 강도가 증가되어 SNR이 감소하고 이를 보상하기 위해 여기 횟수가 증가되어 검사 시간이 길어지는 단점이 있다. 교통사고나 낙상을 원인으 로 경추 MRI 검사를 진행할 시 검사 시간이 길어 호흡과 질환의 통증에 의한 움직임 등을 최소화해야 최적의 영상을 획득 할 수 있어 환자의 적극적인 협조가 요구되며 적정한 검사 시간의 단축을 통해 인공물이 없는 진단 가능한 영상을 만들어 낼 수 있다. 최근 개발된 SwiftMR 인공지능 소프트웨어는 경추 MRI 검사 시간을 획기적으로 줄일 수 있다. T2 시상면, T2 축상면, T1 시상면, T1 축상면 SwiftMR 영상의 SNR은 목뼈 몸통 223.82 ± 30.82, 척수 273.03 ± 32.38, 가시돌 기 및 가로돌기 378.61 ± 27.64로 측정되었다. 고속스핀 에코 기법의 SNR은 목뼈 몸통 116.51 ± 11.46, 척수 182.1 ± 22.24, 가시돌기 및 가로돌기 227.79 ± 35.55로 측정되었다. 고속스핀에코 기법의 CNR은 182.12 ± 13.24, SwiftMR 기법 CNR은 346.8 ± 41.84로 측정되었다. 고속스핀에코와 SwiftMR 인공지능 소프트웨어가 적용된 영상을 통해 화질 선명도, 신호 강도의 균일성, 목뼈 몸통 주변의 인공물의 관찰자 간 병변에 대한 일치성 평가는 K값이 0.87로 평가되었다. 연구 결과를 통해 경추 MRI 검사에 SwiftMR 인공지능 기법을 적용함으로써 검사 시간을 단축할 수 있으며, 환자의 불편을 최소화하고 진단 가능한 질 좋은 영상 정보를 제공할 수 있을 것으로 사료된다.

Este estudio aborda el aprendizaje de la pronunciación en español como una tercera lengua por parte de los hablantes nativos de coreano en los EEUU. Específicamente, profundiza en las características de sus pronunciaciones, las perspectivas desde las que se pueden entender las pronunciaciones y los puntos que los investigadores de L3 deben tener en cuenta para examinar sus pronunciaciones. Para ello, primero este estudio presenta modelos sobre la percepción y producción de L2, así como modelos sobre la morfosintaxis de L3. Luego, aplica los principios principales de los modelos a las situaciones y características del aprendizaje que muestran los estudiantes coreanos de español en los EEUU. Por último, con base en los fundamentos teóricos y sus características del aprendizaje, hace sugerencias para estudios empíricos que examinen la pronunciación de español como L3. Este estudio puede ser útil para los estudiantes coreanos de español como L3 y sus padres, profesores de español e investigadores de L3. Además, algunas sugerencias de este estudio se pueden aplicar a los estudiantes coreanos de español como L3 que viven en Corea y países angloparlantes que no sean los EEUU.

본 논문은 초등학교 현장에서 교사와 학생들에게 계몽편의 내용 중 자연 현상의 음양론과 천지인 삼원의 효율적인 교수학습 방안을 현대에 알맞은 교 수법으로 제시하려고 한다. 이에 본 연구에서는 초등학생을 교육대상으로 음 양오행과 천지인 삼원의 체계적인 수업 설계를 구성하고 교수학습 방안을 제 시하여 교사에게는 교수법을, 학생들에게는 노래와 그림을 통해 음양오행을 쉽게 이해하도록 하는 학습 방안 연구를 목적으로 한다. 본 연구의 구성은 교안과 노래 악보, 율동 설명, 유튜브(YouTube) QR코드와 URL, 그림자료로 시각적, 청각적 교육이 가능하도록 하였다. 음양오행과 천지 인 삼원의 이론적 설명과 학교 교육에서 음양오행과 천지인 삼원을 쉽게 지 도하기 위한 효율적인 교수학습모형을 초등학교 교수법에 맞추어 질적인 교 수학습 방안을 제시하였다. 수업마다 활용할 수 있는 노래악보와 율동설명이 있으며, 음원과 율동이 유튜브에 업로드 되어 URL을 클릭하거나 QR코드를 핸드폰으로 찍으면 바로 볼 수 있도록 구성하였다. 또한 각 주제에 맞는 그 림들은 지도하는 교사와 수업을 받는 학생들 모두에게 교육적 가치가 있다 고 본다. 음양오행 관련 가사를 만들고, 노래 반주에 맞추어 8곡의 음반을 제작하였 다. 8곡 중 5곡은 율동 동영상을 촬영하여 초등학생들이 신체 활동을 통해 학 습 주제를 몸으로 익힐 수 있도록 유튜브(YouTube)에 업로드 하였으며, 나머 지 3곡은 그림을 보며 노래하도록 유튜브(YouTube)에 업로드 하였다. 유튜브 (YouTube) QR코드와 URL을 논문에 넣었으며, 유튜브 URL은 클릭하면 바로 연 결되고, QR코드는 핸드폰을 사용하여 QR코드스캔으로 사진 찍으면 웹브라우 저로 바로 연결이 되어 터치만 하면 유튜브(YouTube) 동영상을 시청할 수 있 도록 하였다. 본 연구를 통해 동양적 철학에 내재 되어 있는 역사나 사상, 철학적인 내용 들이 교육과정에 반영되고 학습자의 습득이 용이하도록 설계되어 전통문화와 의 연계적인 교육 체계가 운영될 수 있기를 바란다.

This paper investigates Korean EFL students’ learning (de)motivation factors according to the level of students’ English learning motivation. A total of 41 undergraduate students reflected on their past ten years of English learning experiences and submitted autobiographic essays with ‘motigraph,’ marking their annual changes of English learning motivation from 0 to 10. The data were analyzed with Grounded Theory. The findings revealed that the factors that increased or decreased English learning motivation were different according to students’ level of motivation. Students with low-level motivation were influenced by their teacher or parents, while those with high-level motivation were influenced by their past L2 learning experiences perceived positively by themselves. In both groups, the factors of emotional experiences caused by negative L2 learning experiences were the main reasons for demotivation. This paper emphasizes the importance of subjective appraisal in maintaining students’ L2 learning motivation and recovering from the state of demotivation.

Purpose: The aim of this study investigated the transition experience of novice nurses working in a tertiary hospital, focusing on the difference between nursing school education and clinical nursing practice. Methods: The data were collected through an unstructured, in-depth interview with 14 recently employed nurses from October 2020 to January 2021. The data were analyzed by qualitative content analysis. Results: The main theme of the transition experience perceived by new graduate nurses was confirmed as ‘reality shock’. In the process of identifying the main themes, five categories, sixteen sub- categories, and sixty-two concepts were derived. The five categories were, ‘Clinical field different from school education setting’, ‘Nursing school education in need of change’, ‘Strengths and limitations of clinical training in schools and hospitals’, ‘Difficulty in establishing relationships and communicating’, and ‘struggling to stand alone’. Conclusion: To minimize the reality shock experienced by novice nurses, nursing schools should innovate their traditional teaching methods based on the changing characteristics of the novice nurses and the clinical environment. In nursing practice, hospitals should grant more time to the nurses for adaptation and diversify mentoring programs comparable to internships for novice nurses.

The SLA 3d printer is the first of the commercial 3D printer. The 3D printed output is printed hanging on the bed that move to the upper position. Sandblasted bed is used to prevent layer shift. If sandblasting is wrong, the 3D printed output is layer shifted. For this reason, 3D printer manufacturing companies inspect the bed surface. However, the sandblasted surface has variety of irregular shapes and craters, so it is difficult to establish a quality control standard. To solve problems, this paper presents a standardized sandblasting histogram and threshold. We present a filter that can increase the classification rate.

For a plastic diffusion lens to uniformly diffuse light, it is important to minimize deformation that may occur during injection molding and to minimize deformation. It is essential to control the injection molding condition precisely. In addition, as the number of meshes increases, there is a limitation in that the time required for analysis increases. Therefore, We applied machine learning algorithms for faster and more precise control of molding conditions. This study attempts to predict the deformation of a plastic diffusion lens using the Decision Tree regression algorithm. As the variables of injection molding, melt temperature, packing pressure, packing time, and ram speed were set as variables, and the dependent variable was set as the deformation value. A total of 256 injection molding analyses were conducted. We evaluated the prediction model's performance after learning the Decision Tree regression model based on the result data of 256 injection molding analyses. In addition, We confirmed the prediction model's reliability by comparing the injection molding analysis results.

The sorption/adsorption behavior of radionuclides, usually occurring at the solid-water interface, is considered to be one of the primary reactions that can hinder the migration of radiotoxic elements contained in the spent nuclear fuel. In general, various physicochemical properties such as surface area, cation exchange capacity, type of radionuclides, solid-to-liquid ratio, aqueous concentration, etc. are known to provide a significant influence on the sorption/adsorption characteristics of target radionuclides onto the mineral surfaces. Therefore, the distribution coefficient, Kd, inherently shows a conditiondependent behavior according to those highly complicated chemical reactions at the solid-water interfaces. Even though a comprehensive understanding of the sorption behavior of radionuclides is significantly required for reliable safety assessment modeling, the number of the chemical thermodynamic model that can precisely predict the sorption/adsorption behavior of radionuclides is very limited. The machine-learning based approaches such as random forest, artificial neural networks, etc. provide an alternative way to understand and estimate complicated chemical reactions under arbitrarily given conditions. In this respect, the objective of this study is to predict the sorption characteristics of various radionuclides onto major bentonite minerals, as backfill materials for the HLW repository, in terms of the distribution coefficient by using a machine-learning based computational approach. As a background dataset, the sorption database previously established by the JAEA was employed for random forest machine learning calculation. Moreover, the hyperparameters such as the number of decision trees, the number of variables to divide each node, and random seed numbers were controlled to assess the coefficient of determination, R2, and the final calculation result. The result obtained in this study indicates that the distribution coefficients of various radionuclides onto bentonite minerals can be reliably predicted by using the machine learning model and sorption database.

Since radon was detected in mattresses of famous bed furniture brands in 2018, the nuclear safety and security commission (NSSC) announced the radiation safety management act in April 2021 to protect the public health and environment. This act stipulates the safety management of radiation that can be encountered in the natural environment such as the notification of radioactivity concentration of source materials, process by-products, the installation and operation of radioactive monitors. In this study, a model was established to predict radioactive exposure dose from radioactive materials such as radon and uranium detected in consumer products such as bed mattresses, pillows, shower, bracelets and masks in order to identify major radioactive substances that largely affect the exposure dose. A period of seven years from 2014 to 2020 was investigated for the source materials and exposure doses of consumer products containing naturally occurring radioactive materials (NORMs). We analyzed these using machine learning models such as classification and regression tree (CART), Random Forest and TreeNet. Index development and verification were performed to evaluate the predictive performance of the models. Overall, predictive performance was highest when Random Forest or TreeNet was used for each consumer product. Thoron had a great influence on the internal exposure dose of bedding, clothing and mats. Uranium had a great influence on the internal exposure dose of other consumer products except whetstones. When the number of data is very small or the missing value rate is high, it is difficult to expect accurate predictive performance even with machine learning techniques. If we significantly reduce the missing value rate of data or use the limit of detection value instead of missing values, we can build a model with more accurate predictive performance.

The spent fuel safety information delivered from the consignor to the disposal facility operator directly affects the operation and safety of the disposal facility. Therefore, the operator of a disposal facility must perform data quality management to increase data reliability, and anomaly detection is a representative method among quality control methods. We propose a quality control method to detect anomalies using XGBoost, known for its excellent performance, prevention of overfitting, and fast training speed. First, we select significant variables such as release burnup, enrichment, and amount U from the spent fuel safety information and train models for each variable using only normal data. A model trained using only normal data generates a small error for a normal pattern and a large error for an abnormal pattern. Then, when the data error exceeds a set threshold, the data is determined as an anomaly. In this paper, we implement the XGBoost models using virtual spent fuel information and optimize the hyperparameter of XGBoost using a simulated annealing method for high accuracy. The optimized XGBoost models show high accuracy in a normal input and provide a stable prediction value even in an abnormal input. In addition, we perform anomaly detection by including defect input in the data to validate the presented method. The proposed method shows the result of effectively classifying normal values and anomalies.