• The Korean Journal of Ecology
• /
• v.26 no.4
• /
• pp.203-208
• /
• 2003

Losses in the dry weight of leaf litter from six tree species were studied during 16 months on the forest floor in temperate deciduous forest of Mt. Cheonma in the vicinity of Seoul in Korea by using litter bag method. The decomposition rate of each leaf litter varies with each species. After 16 months elapsed, the leaf litter of Acer pseudo-sieboidianum showed the highest decomposition constant (0.82) as Olson´s decomposition constant, while that of Pinus densiflora showed the lowest decomposition constant (0.33). The decomposition constant of Quercus mongolica, Q. serrata, Betula ermani and Carpinus laxiflora showed 0.43, 0.37, 0.66 and 0.75, respectively. The decomposition constant of leaf litter was considered with temperature and precipitation which accumulated daily during each term of litter bag collection. The decomposition constant of leaf litter showed closely positive correlation with daily accumulative temperature and precipitation. The relationships between decomposition constant and the daily accumulative temperature and precipitation at each period of litter bag collection were analyzed through multi-regression analysis. The correlation coefficients as a result of multi-regression analysis in Q. mongolica, Q. serrata, P densiflora, B. ermani, C. laxiflorais and A. pseudo-sieboldianum were 0.83, 0.81, 0.69, 0.77, 0.77 and 0.62, respectively. The precipitation showed higher effect, about 10 times, on the leaf litter decomposition than the daily accumulative temperature.

• Journal of Power System Engineering
• /
• v.13 no.5
• /
• pp.76-81
• /
• 2009

The fatalities of pedestrian account for about 21.2% of all fatalities at 2007 year in Korea. To reconstruct exactly the accident, it is important to calculate the throw distance of pedestrian in car to pedestrian accident. The frontal shape of SUV vehicle is dissimilar to passenger car and bus, so the trajectory and throw distance of pedestrian by SUV vehicle is not the same of passenger car and bus. The influencing on it can be classified into the factors of vehicle and pedestrian, and road factor. It was analyzed by PC-CRASH for simulation, and SPSS s/w was used for regression analysis. From the simulation results, the maximum impact energy of multi-body of pedestrian was occurred to that of torso body at the same time. And the throw distance increased with the increasing of impact velocity, and decreased with the increasing of impact offset. Also it decreased with the increasing of velocity of pedestrian at accident, and the throw distance of wet road was longer than that of dry road. Finally, the regression analysis model of SUV(Nissan Pathfinder type)vehicle in car to pedestrian accident was as follows; $$disti_i=-0.87-0.11offseti_i+0.69speed_i-4.27height_i+0.004walk_i+0.63wet_i+{\epsilon}_i$$.

• Health Policy and Management
• /
• v.30 no.3
• /
• pp.355-365
• /
• 2020

Background: This study is aimed to verify individual and regional-level factors affecting the depression of Koreans and to develop social programs for improving the depressive status. Methods: This study used individual-level variables from the Korean Community Health Survey (2018) and used the e-regional index of the Korean Statistical Information Service as the regional-level variable. A multi-level logistic regression was executed to identify individual and regional-level variables that were expected to affect the extent of depressive symptoms and to draw the receiver operating characteristic curve to compare the volume of impact between variables from both levels. Results: The results of the multi-level logistic regression analysis in regards to individual-level factors showed that older age, female gender, a lower income level, a lower education level, not having a spouse, the practice of walking, the consumption of breakfast higher levels of stress, and having high blood pressure or diabetes were associated with a greater increase in depressive symptoms. In terms of regional factors, areas with fewer cultural facilities and fewer car registration had higher levels of depressive symptoms. The comparison of area under the curve showed that individual factors had a greater influence than regional factors. Conclusion: This study showed that while both, individual and regional-level factors affect depression, the influence of the latter was relatively weaker as compared to the first. In this sense, it is necessary to develop programs focused on the individual, such as social prescribing at the local or community-level, rather than the city and nation-level approach that are currently prevalent.

• Journal of Mechanical Science and Technology
• /
• v.17 no.6
• /
• pp.816-824
• /
• 2003

In this study, variations of cutting performance with pulse time, open circuit voltage, wire speed and dielectric fluid pressure were experimentally investigated in Wire Electrical Discharge Machining (WEDM) process. Brass wire with 0.25 mm diameter and AISI 4140 steel with 10 mm thickness were used as tool and work materials in the experiments. The cutting performance outputs considered in this study were surface roughness and cutting speed. It is found experimentally that increasing pulse time, open circuit voltage, wire speed and dielectric fluid pressure increase the surface roughness and cutting speed. The variation of cutting speed and surface roughness with cutting parameters is modeled by using a regression analysis method. Then, for WEDM with multi-cutting performance outputs, an optimization work is performed using this mathematical models. In addition, the importance of the cutting parameters on the cutting performance outputs is determined by using the variance analysis (ANOVA).

• Wind and Structures
• /
• v.8 no.3
• /
• pp.163-178
• /
• 2005

Wind-induced mean and dynamic interference effects of tall buildings are studied in detail by a series of wind tunnel tests in this paper. Interference excitations of several types of upwind structures of different sizes in different upwind terrains are considered. Comprehensive interference characteristics are investigated by artificial neural networks and correlation analysis. Mechanism of the wakes vortex-induced resonance is discussed, too. Measured results show significant correlations exist in the distributions of the interference factors of different configurations and upwind terrains and, therefore, a series of relevant regression equations are proposed to simplify the complexity of the multi-parameter wind induced interference effects between two tall buildings.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.5
• /
• pp.209-216
• /
• 2024

Real estate market prices are determined by various factors, including macroeconomic variables, as well as the influence of a variety of unstructured text data such as news articles and social media. News articles are a crucial factor in predicting real estate transaction prices as they reflect the economic sentiment of the public. This study utilizes sentiment analysis on news articles to generate a News Sentiment Index score, which is then seamlessly integrated into a real estate price prediction model. To calculate the sentiment index, the content of the articles is first summarized. Then, using AI, the summaries are categorized into positive, negative, and neutral sentiments, and a total score is calculated. This score is then applied to the real estate price prediction model. The models used for real estate price prediction include the Multi-head attention LSTM model and the Vector Auto Regression model. The LSTM prediction model, without applying the News Sentiment Index (NSI), showed Root Mean Square Error (RMSE) values of 0.60, 0.872, and 1.117 for the 1-month, 2-month, and 3-month forecasts, respectively. With the NSI applied, the RMSE values were reduced to 0.40, 0.724, and 1.03 for the same forecast periods. Similarly, the VAR prediction model without the NSI showed RMSE values of 1.6484, 0.6254, and 0.9220 for the 1-month, 2-month, and 3-month forecasts, respectively, while applying the NSI led to RMSE values of 1.1315, 0.3413, and 1.6227 for these periods. These results demonstrate the effectiveness of the proposed model in predicting apartment transaction price index and its ability to forecast real estate market price fluctuations that reflect socio-economic trends.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.5
• /
• pp.297-304
• /
• 2020

In this study, the prediction method was reviewed to process a cylindrical plate forming using machine learning as a data-driven approach by roll bending equipment. The calculation of the forming variables was based on the analysis using the mechanical relationship between the material properties and the roll bending machine in the bending process. Then, by applying the finite element analysis method, the accuracy of the deformation prediction model was reviewed, and a large number data set was created to apply to machine learning using the finite element analysis model for deformation prediction. As a result of the application of the machine learning model, it was confirmed that the calculation is slightly higher than the linear regression method. Applicable results were confirmed through the machine learning method.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.499-510
• /
• 2016

It is very important to select relevant variables in regression models for survival analysis. In this paper, we introduce a penalized variable-selection procedure in multi-level frailty models based on the "frailtyHL" R package (Ha et al., 2012). Here, the estimation procedure of models is based on the penalized hierarchical likelihood, and three penalty functions (LASSO, SCAD and HL) are considered. The proposed methods are illustrated with multi-country/multi-center bladder cancer survival data from the EORTC in Belgium. We compare the results of three variable-selection methods and discuss their advantages and disadvantages. In particular, the results of data analysis showed that the SCAD and HL methods select well important variables than in the LASSO method.

• The Research Journal of the Costume Culture
• /
• v.24 no.6
• /
• pp.803-816
• /
• 2016

The purposes of this study were to investigate the influences of channel assessments on the usage of multi-channels by product types, and the differences in the usage of multi-channels among product types in buying decision making process for fashion products. Data were collected from 510 consumers in their 20s to 50s with purchasing experiences through multi-channel distribution system and living in Seoul and Kyunggi province; 491 were analyzed after deleting incomplete questionnaires. Factor analysis, multiple regression analysis and one-way ANOVA were used for statistical analysis by using SPSS 18.0. The results were as follows: 5 factors were extracted for channel assessment: utility, accuracy, risk, price benefit and sharing information. Price benefits, utility and sharing information for online channel tended to influence positively on the usage of online channel and online+offline channels. Accuracy and low perceived risk of offline influenced positively on offline and on+offline channel usages. The usage levels of on-line and off-line channels for cosmetics were significantly lower than the usage levels for clothes and accessories on information search, evaluation of alternatives, and purchase stages. Significant differences were also found in the usage levels of multi-channels (on+off-line) on information search and evaluation of alternatives stages. The usage levels of the multi-channels for clothes were the highest followed by those of accessories and cosmetics in order.