• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.770-778
• /
• 2023

Purpose: In order to reduce forklift industrial accidents, it is necessary to classify them into institutional, technical, and educational factors and conduct research on whether each factor affects disaster reduction. Method: Descriptive statistical analysis, validity analysis, reliability analysis, and multiple regression analysis were conducted using SPSS 18 program based on an offline questionnaire based on a 5-point Likert scale. Result: As a result of multiple regression analysis, it was found that institutional, technical, and educational factors, which are independent variables for disaster reduction, explain about 62.5% of the variance in disaster prevention, which is the dependent variable. The regression model verification was found to be statistically significant with F=118.775 and significance probability p<0.01. Conclusion: First, there is a need to prevent disasters by including electric forklifts weighing less than 3 tons in the inspection system. Second, there is a need to make it mandatory to install front and rear cameras and forklift line beams to prevent forklift collision disasters. Third, there is a need to conduct special training related to forklifts every year, and drivers and nearby workers need to be included in the special training for forklifts.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.392-399
• /
• 2023

This paper proposes a deep learning model to determine the region and depth of cabbage cores for robotic automation of the cabbage core removal process during the kimchi manufacturing process. In addition, rather than predicting the depth of the measured cabbage, a model was presented that simultaneously detects and classifies the area by converting it into a discrete class. For deep learning model learning and verification, RGB images of the harvested cabbage 522 were obtained. The core region and depth labeling and data augmentation techniques from the acquired images was processed. MAP, IoU, acuity, sensitivity, specificity, and F1-score were selected to evaluate the performance of the proposed YOLO-v4 deep learning model-based cabbage core area detection and classification model. As a result, the mAP and IoU values were 0.97 and 0.91, respectively, and the acuity and F1-score values were 96.2% and 95.5% for depth classification, respectively. Through the results of this study, it was confirmed that the depth information of cabbage can be classified, and that it can be used in the development of a robot-automation system for the cabbage core removal process in the future.

• Journal of The Korean Association For Science Education
• /
• v.26 no.4
• /
• pp.502-509
• /
• 2006

The purpose of this study was to analyze physics problem solving processes according to students' cognitive style in the area of 'Force and Motion' at high school level. Students who have already learned t e area of 'Force and Motion' during the first semester of the 10th grade have taken physics test and cognitive style test to choose students who have basic knowledge of physics and reflective or impulsive style. Four students who got over 19 points in the cognitive style test were selected as reflective students, and another four students who got below 12 points were selected as impulsive students. After explaining the purpose and procedure of this study, think-aloud method was introduced to the students, and the students practiced it. After that, the students solved three quantitative and qualitative problems each. Then, the questionnaire on the belief system on physics and physics problem solving and prerequisite knowledge test were also administered. By recording the students' problem solving processes, protocol was made and analyzed. After solving the problems, the students expressed their confidence, intimacy, and preference on each problem by the five point Likert scale. Impulsive students tended to succeed in solving more problems, less intimate, and more spontaneous and positive in seeking alternative solution when confronted with unacquainted problems. On the other hand, reflective students used more time in executing the problems even without planning, and used more time in solving problems and verification. Whether making effective plan or not was important rather than how much time they used in the planning step. In addition, repeating steps were more likely shown to impulsive students; they tended to be attached to their first idea.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.10-18
• /
• 2009

A moving surface vessel generates a ship wake which contains a cloud of micro-bubbles with radii ranging between $8{\sim}200{\mu}m$. Such micro-bubbles can be detected by active sonar system for more than ten minutes depending on the size and speed of the surface vessel. In this paper, a reverberation model for the ship wake is presented. The developed model consists of the acoustic scattering model due to the distribution of the micro-bubbles and the kinematic model for the moving active sonar. The acoustic scattering model is based on the volume integration, where the volume scattering strengths are obtained from the spatial distribution of micro-bubbles. Since the directivity and look-direction of active sonar are important factors for moving active sonar, the kinematic model utilizes the Euler transformation to obtain the relative motion between the global and local coordinates. In order to verify the developed model, a series of sea experiment was executed in September 2007 to obtain the spatial-temporal distribution of a bubble cloud, and analyzed to be compared with the simulation results.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.365-371
• /
• 2024

The purpose of this study was to investigate the effect of leisure satisfaction according to calligraphy activities of the elderly on self-efficacy and psychological well-being. In order to conduct this study, the researchers surveyed 306 elderly people aged 65-76 or older from late November to early December 2023 in Anyang City and Xinxiang City, Henan Province, China. In order to verify the research hypothesis, the researchers performed frequency analysis, descriptive statistics analysis, and Pearson correlation analysis using IBM SPSS Statistics 25, and then performed independent sample T-test and one-way analysis of variance (One-Way ANOVA). To verify the hypothesis through the measurement concept, related verification was conducted for Hayes PROCESS macro and Bootstrap. As a result of the study, first, there is a gender difference in leisure satisfaction, leisure satisfaction, self-efficacy, and psychological well-being, and leisure satisfaction and psychological well-being differ significantly according to age. Second, it was found that leisure satisfaction had a positive effect on self-efficacy. Third, it was found that leisure satisfaction had a positive effect on psychological well-being. Fourth, leisure satisfaction was found to have a positive effect on psychological well-being. Therefore, in order to increase the leisure satisfaction and psychological well-being of the elderly, it is necessary to carefully develop a calligraphy activity system to increase self-efficacy.

• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Annual Conference of KIPS
• /
• 2007.05a
• /
• pp.1487-1490
• /
• 2007

디지털 위성방송의 시작과 더불어 본격적인 데이터 방송의 시대가 열렸다. 데이터방송이 시작 되면서 데이터방송용 양방향 콘텐츠에 대한 수요가 급속하게 증가하고 있다. 하지만 양방향 콘텐츠 개발에 필요한 저작 도구 및 검증 시스템은 아주 초보적인 수준에 머물러 있는 것이 현실이다. 그러나 방송의 특성상 콘텐츠 상에서의 오류는 방송 사고에까지 이를 수 있는 심각한 상황이 연출 될 수 있다. 본 연구 팀은 이러한 DTV 콘텐츠 개발 요구에 부응하여, 개발자의 콘텐츠 개발 및 사업자 또는 기관에서의 콘텐츠 검증이 원활이 이루어 질수 있도록 하는 양방향 콘텐츠 검증 시스템을 개발 중이다. 양방향 콘텐츠 검증 시스템은 Java 컴파일러, 디버거, 미들웨어, 가상머신, 그리고 IDE 등으로 구성된다. 본 논문에서 제시한 자바 컴파일러는 양방향 콘텐츠 검증 시스템에서 데이터 방송용 자바 애플리케이션(Xlet)을 컴파일하여 에뮬레이팅 하거나 런타임 상에서 디버깅이 가능하도록 하는 바이너리형태의 class 파일을 생성한다. 이를 위해 Java 컴파일러는 *.java 파일을 입력으로 받아 어휘 분석과 구문 분석 과정을 거친 후 SDT(syntax-directed translation)에 의해 AST(Abstract Syntax Tree)를 생성한다. 클래스링커는 생성된 AST를 탐색하여 동적으로 로딩 되는 파일들을 연결하여 AST를 확장한다. 의미 분석과정에서는 확장된 AST를 입력으로 받아 참조된 명칭의 사용이 타당한지 등을 검사하고 코드 생성이 용이하도록 AST를 변형하고 부가적인 정보를 삽입하여 ST(Semantic Tree)를 생성한다. 코드 생성 단계에서는 ST를 입력으로 받아 이미 정해 놓은 패턴에 맞추어 Bytecode를 출력한다.ovoids에서도 각각의 점들에 대한 선량을 측정하였다. SAS와 SSAS의 직장에 미치는 선량차이는 실제 임상에서의 관심 점들과 가장 가까운 25 mm(R2)와 30 mm(R3)거리에서 각각 8.0% 6.0%였고 SAS와 FWAS의 직장에 미치는 선량차이는 25 mm(R2) 와 30 mm(R3)거리에서 각각 25.0% 23.0%로 나타났다. SAS와 SSAS의 방광에 미치는 선량차이는 20 m(Bl)와 30 mm(B2)거리에서 각각 8.0% 3.0%였고 SAS와 FWAS의 방광에 미치는 선량차이는 20 mm(Bl)와 30 mm(B2)거리에서 각각 23.0%, 17.0%로 나타났다. SAS를 SSAS나 FWAS로 대체하였을 때 직장에 미치는 선량은 SSAS는 최대 8.0 %, FWAS는 최대 26.0 %까지 감소되고 방광에 미치는 선량은 SSAS는 최대 8.0 % FWAS는 최대 23.0%까지 감소됨을 알 수 있었고 FWAS가 SSAS 보다 차폐효과가 더 좋은 것으로 나타났으며 이 두 종류의 shielded applicator set는 부인암의 근접치료시 직장과 방광으로 가는 선량을 감소시켜 환자치료의 최적화를 이룰 수 있을 것으로 생각된다.)한 항균(抗菌) 효과(效果)를 나타내었다. 이상(以上)의 결과(結果)로 보아 선방활명음(仙方活命飮)의 항균(抗菌) 효능(效能)은 군약(君藥)인 대황(大黃)의 성분(成分) 중(中)의 하나인 stilbene 계열(系列)의 화합물(化合物)인 Rhapontigenin과 Rhaponticin의 작용(作用)에 의(依)한 것이며, 이는 한의학(韓醫學) 방제(方劑) 원리(原理)인 군신좌사(君臣佐使) 이론(理論)에서 군약(君藥)이 주증(主症)에 주(主)로 작용(作用)하는 약물(藥物)이라는 것을 밝혀주는 것이라고

• Progress in Medical Physics
• /
• v.26 no.4
• /
• pp.280-285
• /
• 2015

In radiation therapy fields, a brachytherapy is a treatment that kills lesion of cells by inserting a radioisotope that keeps emitting radiation into the body. We currently verify the consistency of radiation treatment plan and dose distribution through film/screen system (F/S system), provide therapy after checking dose. When we check dose distribution, F/S systems have radiation signal distortion because there is low resolution by penumbra depending on the condition of film developed. In this study, We fabricated a $HgI_2$ Semiconductor radiation sensor for base study in order that we verify the real dose distribution weather it's same as plans or not in brachytherapy. Also, we attempt to evaluate the feasibility of QA system by utilizing and evaluating the sensor to brachytherapy source. As shown in the result of detected signal with various source-to-detector distance (SDD), we quantitatively verified the real range of treatment which is also equivalent to treatment plans because only the low signal estimated as scatters was measured beyond the range of treatment. And the result of experiment that we access reproducibility on the same condition of ${\gamma}$-ray, we have made sure that the CV (coefficient of variation) is within 1.5 percent so we consider that the $HgI_2$ sensor is available at QA of brachytherapy based on the result.

• Progress in Medical Physics
• /
• v.17 no.2
• /
• pp.105-113
• /
• 2006

This study peformed to confirm the corrected dose In different electron density materials using the superposition/FFT convolution method in radiotherapy Planning system. The experiments of the $K_2HPO_4$ diluted solution for bone substitute, Cork for lung and n-Glucose for soft tissue are very close to effective atomic number of tissue materials. The image data acquisited from the 110 KVp and 130 KVp CT scanner (Siemes, Singo emotions). The electron density was derived from the CT number (H) and adapted to planning system (Xio, CMS) for heterogeneity correction. The heterogeneity tissue phantom used for measurement dose comparison to that of delivered computer planning system. In the results, this investigations showed the CT number is highly affected in photoelectric effect in high Z materials. The electron density in a given energy spectrum showed the relation of first order as a function of H in soft tissue and bone materials, respectively. In our experiments, the ratio of electron density as a function of H was obtained the 0.001026H+1.00 in soft tissue and 0.000304H+1.07 for bone at 130 KVp spectrum and showed 0.000274H+1.10 for bone tissue in low 110 KVp. This experiments of electron density calibrations from CT number used to decide depth and length of photon transportation. The Computed superposition and FFT convolution dose showed very close to measurements within 1.0% discrepancy in homogeneous phantom for 6 and 15 MV X rays, but it showed -5.0% large discrepancy in FFT convolution for bone tissue correction of 6 MV X rays. In this experiments, the evaluated doses showed acceptable discrepancy within -1.2% of average for lung and -2.9% for bone equivalent materials with superposition method in 6 MV X rays. However the FFT convolution method showed more a large discrepancy than superposition in the low electron density medium in 6 and 15 MV X rays. As the CT number depends on energy spectrum of X rays, it should be confirm gradient of function of CT number-electron density regularly.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.