• Progress in Medical Physics
• /
• v.12 no.1
• /
• pp.71-77
• /
• 2001

The region, near the edge of a radiation beam, where the dose changes rapidly according to the distance from the beam axis is known as the penumbra. There is a sharp dose gradient zone even in megavoltage photon beams due to source size, collimator, lead alloy block, other accessories, and internal scatter ray. We investigate dosimetric characteristics on penumbra regions of a standard collimator and compare to those of theoritical model for the optimal use of the system in radiotherapy. Peripheral dose distribution of 6 W Photon beams represents penumbral forming function as the depth. Also we have discussed that the peripheral dose distribution of clinical photon beams, differences between calculation dose use of emperical penumbral forming function and measurements in penumbral region. Predictions by emperical penumbral forming functions are compared with measurements in 3-dimensional water phantom and it is shown that the method is capable of reproduceing the measured peripheral dose values usually to within the statistical uncertainties of the data. The semiconductor detector and ion chamber were positioned at a dmax depth, 5cm depth, 10cm depth, and its specific ratio was determined using a scanning data. The effective penumbra, the distance from 80% to 20% isodose lines were analyzed as a function of the distance. The extent of penumbra will also expand with depth increase. Difference of measurement value and model functions value according to character of the detector show small error in dose distribution of the peripheral dose.

• The Journal of Engineering Geology
• /
• v.15 no.1
• /
• pp.67-76
• /
• 2005

This paper presents the application of a neural network for prediction of the unconfined compressive strength from physical properties and schmidt hardness number on rock samples. To investigate the suitability of this approach, the results of analysis using a neural network are compared to predictions obtained by statistical relations. The data sets containing 55 rock sample records which are composed of sandstone and shale were assembled in Daegu area. They were used to learn the neural network model with the back-propagation teaming algorithm. The rock characteristics as the teaming input of the neural network are: schmidt hardness number, specific gravity, absorption, porosity, p-wave velocity and S-wave velocity, while the corresponding unconfined compressive strength value functions as the teaming output of the neural network. A data set containing 45 test results was used to train the networks with the back-propagation teaming algorithm. Another data set of 10 test results was used to validate the generalization and prediction capabilities of the neural network.

• Journal of The Korean Association For Science Education
• /
• v.36 no.3
• /
• pp.389-397
• /
• 2016

This study aims to test the efficacy of English-based automated computer scoring models and machine translation to score Korean college students' written responses on natural selection concept items. To this end, I collected 128 pre-service biology teachers' written responses on four-item instrument (total 512 written responses). The machine translation software (i.e., Google Translate) translated both original responses and spell-corrected responses. The presence/absence of five scientific ideas and three $na{\ddot{i}}ve$ ideas in both translated responses were judged by the automated computer scoring models (i.e., EvoGrader). The computer-scored results (4096 predictions) were compared with expert-scored results. The results illustrated that no significant differences in both average scores and statistical results using average scores was found between the computer-scored result and experts-scored result. The Pearson correlation coefficients of composite scores for each student between computer scoring and experts scoring were 0.848 for scientific ideas and 0.776 for $na{\ddot{i}}ve$ ideas. The inter-rater reliability indices (Cohen kappa) between computer scoring and experts scoring for linguistically simple concepts (e.g., variation, competition, and limited resources) were over 0.8. These findings reveal that the English-based automated computer scoring models and machine translation can be a promising method in scoring Korean college students' written responses on natural selection concept items.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.35-44
• /
• 2021

In recent times, several studies have been conducted focusing on crashes occurring on the main segment of the highway. However, there is a dearth of research dealing with traffic safety relating to other highway facilities, especially ramp areas. According to the Korea Expressway Corporation's Expressway Information Service, 6,717 crashes have occurred on ramps in the five years from 2015~2019, which accounts for about 15% of all highway accidents. In this study, the simple and full safety performance functions (SPFs) were evaluated and explored using different statistical distributions (i.e., Poisson Gamma (PG) and Poisson Inverse Gaussian (PIG)) and techniques (i.e., fixed effects (FE) and random effects (RE)) to provide more accurate crash prediction models for highway ramp sections. Data on the geometric characteristics of traffic and roadways were collected from various systems and with extensive efforts using a street-view application. The results showed that the PIG models present more accurate crash predictions in general. The results also indicated that the RE models performed better than FE models for simple and full SPFs. The findings from this study offer transportation practitioners using the Korea Expressway Corporation's Expressway a dependable reference to enhance and understand traffic safety in ramp areas based on accurate crash prediction models and empirical evidence.

• Journal of the Korean GEO-environmental Society
• /
• v.12 no.4
• /
• pp.25-31
• /
• 2011

In this study, the experimental design methodology was applied to optimize 1,4-dioxane treatment in E-beam process. Main factor was mathematically described as a function of parameters 1,4-dioxane removal efficiencies(%), TOC removal efficiencies(%) modeled by the use of the central composite design(CCD) method among the response surface methodology(RSM). Concentration of 1,4-dioxane is designated as "$x_1$" and Irradiation intensity is designated as "$x_2$". The regression equation in coded unit between the 1,4-dioxane concentration and removal efficiencies(%) was $y=71.00-10.85x_1+20.67x_2+{1.53x_1}^2-{7.92x_2}^2-1.23x_1x_2$. The regression equation in coded unit between the 1,4-dioxane concentration and TOC removal efficiencies(%) was $y=44.48-13.25x_1+9.54x_2+{5.43x_1}^2-{1.35x_2}^2+4.45x_1x_2$. The model predictions agreed well with the experimentally observed results $R^2$(Adj) over 90%. Toxicity test using algae Pseudokirchneriella Subcapitata showed that the inhibition was reduced according to increasing an E-beam irradiation.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1047-1056
• /
• 2022

Sea ice, frozen sea water, in the Artic is a primary indicator of global warming. Due to its importance to the climate system, shipping-route navigation, and fisheries, Arctic sea ice prediction has gained increased attention in various disciplines. Recent advances in artificial intelligence (AI), motivated by a desire to develop more autonomous and efficient future predictions, have led to the development of new sea ice prediction models as alternatives to conventional numerical and statistical prediction models. This study aims to evaluate the performance of the two-stream convolutional long-and short-term memory (TS-ConvLSTM) AI model, which is designed for learning both global and local characteristics of the Arctic sea ice changes, for the minimum September Arctic sea ice from 2001 to 2021, and to show the possibility for an operational prediction system. Although the TS-ConvLSTM model generally increased the prediction performance as training data increased, predictability for the marginal ice zone, 5-50% concentration, showed a negative trend due to increasing first-year sea ice and warming. Additionally, a comparison of sea ice extent predicted by the TS-ConvLSTM with the median Sea Ice Outlooks (SIOs) submitted to the Sea Ice Prediction Network has been carried out. Unlike the TS-ConvLSTM, the median SIOs did not show notable improvements as time passed (i.e., the amount of training data increased). Although the TS-ConvLSTM model has shown the potential for the operational sea ice prediction system, learning more spatio-temporal patterns in the difficult-to-predict natural environment for the robust prediction system should be considered in future work.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.383-384
• /
• 2022

Following the development of technologies such as digital twin, IoT, and AI after the 4th industrial revolution, decision-making problems are being solved based on high-dimensional data analysis. This has recently been applied to the port logistics sector, and a number of studies on big data analysis, deep learning predictions, and simulations have been conducted on container terminals to improve port productivity. These high-dimensional data analysis techniques generally require a large number of data. However, the global port environment has changed due to the COVID-19 pandemic in 2020. It is not appropriate to apply data before the COVID-19 outbreak to the current port environment, and the data after the outbreak was not sufficiently collected to apply it to data analysis such as deep learning. Therefore, this study intends to present a port data augmentation method for data analysis as one of these problem-solving methods. To this end, we generate the container stowage situation of the yard through a generative adversarial neural network model in terms of container terminal operation, and verify similarity through statistical distribution verification between real and augmented data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1143-1150
• /
• 2023

The global climate crisis and the implementation of low-carbon policies have led to a growing interest in renewable energy and a growing number of related industries. Among them, solar power is attracting attention as a representative eco-friendly energy that does not deplete and does not emit pollutants or greenhouse gases. As a result, the supplement of solar power facility is increasing all over the world. However, solar power is easily affected by the environment such as geography and weather, so accurate solar power forecast is important for stable operation and efficient management. However, it is very hard to predict the exact amount of solar power using statistical methods. In addition, the conventional prediction methods have focused on only short- or long-term prediction, which causes to take long time to obtain various prediction models with different prediction horizons. Therefore, this study utilizes a many-to-many structure of a recurrent neural network (RNN) to integrate short-term and long-term predictions of solar power generation. We compare various RNN-based very short- and long-term prediction methods for solar power in terms of MSE and R² values.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.323-338
• /
• 2024

This study analyzes the Korean professional volleyball league and predict match outcomes using popular machine learning classification methods. Match data from the 2012/2013 to 2022/2023 seasons for both male and female leagues were collected, including match details. Two different data structures were applied to the models: Separating matches results into two teams and performance differentials between the home and away teams. These two data structures were applied to construct a total of four predictive models, encompassing both male and female leagues. As specific variable values used in the models are unavailable before the end of matches, the results of the most recent 3 to 4 matches, up until just before today's match, were preprocessed and utilized as variables. Logistc Regrssion, Decision Tree, Bagging, Random Forest, Xgboost, Adaboost, and Light GBM, were employed for classification, and the model employing Random Forest showed the highest predictive performance. The results indicated that while significant variables varied by gender and data structure, set success rate, blocking points scored, and the number of faults were consistently crucial. Notably, our win-loss prediction model's distinctiveness lies in its ability to provide pre-match forecasts rather than post-event predictions.

• The Journal of Dong Guk Oriental Medicine
• /
• v.6 no.2
• /
• pp.167-190
• /
• 1998

Nowadays there were two tendencies of studies about prognostic factors in stroke. One way was to define prognostic factors according to the radiological features. And the other way was to define according to the mental state, recognition, perception, motors, language, urinary&bowel incontinence etc.. The former could be objectively investigated, while the latter was difficult. The purpose of this study was to determine which variables would be predictors of stroke and which factors would be affect predictions most. The subjects of this study were 32 patients who were admitted to the Dept. of Internal Medicine, Dongguk Univ. College of Oriental Medicine whthin 48 hours from attack, Medical records were reviewed FIM, CNS, NIH stroke scale. We compared each sub-items of FIM, CNS, NIH stroke scale about mental state, recognition, perception, motors, language, urinary&bowel incontinence with MBI score at 4 weeks from admission. Also, we analyzed the correlations of sub-items and groups which devided into 5 according to independence of MBI score. And we found out the most influent factors with multiple regression analysis. The major results were as follows; 1. In mean of MBI score at 4 weeks of each groups devided low, middle, high score at mental state, recognition, perception, motors, language, urinary&bowel incontinence items, there were statistical differences in all items. 2. The mental state and lim ataxia sub-items had no significant correlations with groups divided according to independence of MBI score. All the other items were significantly correlated. 3. The most influent factors was recognition. The second was sensory and the third was bowel incontinence. 4. The most influent scales was FIM, and the second was CNS, and NlH had no statistical significancy.