• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.4
• /
• pp.1-7
• /
• 2001

Remotely sensed data is the most fundamental data in acquiring the GIS informations, and may be analyzed to extract useful thematic information. Multi-spectral classification is one of the most often used methods of information extraction. The actual multi-spectral classification may be performed using either supervised or unsupervised approaches. This paper analyze the effect of assigning clever initial values to image classes on the performance of parallelepiped classification algorithm, which is one of the supervised classification algorithms. First, we investigate the effect on serial computing model, then expand it on MIMD(Multiple Instruction Multiple Data) parallel computing model. On serial computing model, the performance of the parallel pipe algorithm improved 2.4 times at most and, on MIMD parallel computing model the performance improved about 2.5 times as clever initial values are assigned to image class. Through computer simulation we find that initial values of image class greatly affect the performance of parallelepiped classification algorithms, and it can be improved greatly when classes on both serial computing model and MIMD parallel computation model.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.66-74
• /
• 2008

Criticality prediction models to identify most fault-prone modules in the system early in the software development process help in allocation of resources and foster software quality improvement. Many models for identifying fault-prone modules using design complexity metrics have been suggested, but most of them are training models that need training data set. Most organizations cannot use these models because very few organizations have their own training data. This paper builds a prediction model based on a well-known supervised learning model, error backpropagation neural net, using design metrics quantifying SDL system specifications. To solve the problem of other models, this model is trained by generated virtual training data set. Some simulation studies have been performed to investigate feasibility of this model, and the results show that suggested model can be an alternative for the organizations without real training data to predict their software qualities.

• Journal of Korea Port Economic Association
• /
• v.33 no.4
• /
• pp.135-148
• /
• 2017

This study fist raises the following research question. How does the port congestion affect port operational efficiency? To answer the question, this study adopts slacks based measure data envelopment analysis (SBM-DEA) model to analyze the efficiency of port considering the congestion. As a result of the DEA-CCR(Chanres, Cooper and Rhodes) model, both Busan(2011) and Ulsan(2011) are the most efficient decision making units(DMUs). As a result of the DEA-BCC(Banker, Chanrnes, and Cooper) model, Busan(2011), Ulsan(2011), Ulsan(2012), Busan(2012), and Yeosu Gwangyang(2012) are the most efficient DMUs. As a result of SBM-DEA model, Ulsan(2012), Busan(2011), Busan(2012), Incheon(2011), and Ulsan(2011) are the most efficient DMUs considering the port congestion. The result of DEA-CCR BCC model is not identical with the result of SBM-DEA model analysis. It means the port congestion does less affect the port operational efficiency. Should the number of the vessels with the port congestion minimize, Incheon and Yeosu Gwangyang port could save lots of the port congestion cost for a total of three years.

• Journal of Biosystems Engineering
• /
• v.42 no.3
• /
• pp.190-198
• /
• 2017

Purpose: A thin-layer drying equation was developed to analyze the drying processes of soybeans (white and black beans) and investigate drying conditions by verifying the suitability of existing grain drying equations. Methods: The drying rates of domestic soybeans were measured in a drying experiment using air at a constant temperature and humidity. The drying rate of soybeans was measured at two temperatures, 50 and $60^{\circ}C$, and three relative humidities, 30, 40 and 50%. Experimental constants were determined for the selected thin layer drying models (Lewis, Page, Thompson, and moisture diffusion models), which are widely used for predicting the moisture contents of grains, and the suitability of these models was compared. The suitability of each of the four drying equations was verified using their predicted values for white beans as well as the determination coefficient ($R^2$) and the root mean square error (RMSE) of the experiment results. Results: It was found that the Thompson model was the most suitable for white beans with a $R^2$ of 0.97 or greater and RMSE of 0.0508 or less. The Thompson model was also found to be the most suitable for black beans, with a $R^2$ of 0.97 or greater and an RMSE of 0.0308 or less. Conclusions: The Thompson model was the most appropriate prediction drying model for white and black beans. Empirical constants for the Thompson model were developed in accordance with the conditions of drying temperature and relative humidity.

• Journal of Korean Academy of Nursing
• /
• v.32 no.1
• /
• pp.77-88
• /
• 2002

The purpose of this study was designed to develope and test the structural model that explains alcohol consumption behaviors among university students in Republic of Korea. The hypothetical model was constructed on the basis of the literature review and Pender's Health promotion model. Data was collected from questionnaires from 512 university students in Republic of Korea, from August to September, 2000. The reliability of instruments was adequate (Cronbach's alpha= .69-.90). Data analysis was done with SAS 6.12 for descriptive statistics and LISREL 8.13 program for covariance structural analysis. The results are as follows; 1. The overall fit of the hypothetical model to the data was moderate. Thus it was modified by male and female models. 2. The revised model has become parsimonious and had a better fit to the empirical data (male: χ2=87.21 p=.00, GFI=.97, AGFI= .94, NFI=.99, NNFI=1.0, CN=619.17, female: χ2=49.29 p=.31, GFI=.45, AGFI= .95, NFI=.99, NNFI=1.0, CN=370.02). 3. Self-efficacy was most significant factor and personality of novelty seeking, reward compensation, alcohol expectancy and drinking attitude have significant effects on male alcohol consumption behavior. 4. Personality of novelty seeking was most significant factor and personality of harm avoidance, friend influence, self-efficacies, alcohol expectancy and drinking attitude have significant effects on female alcohol consumption behavior.

• The Plant Pathology Journal
• /
• v.36 no.5
• /
• pp.406-417
• /
• 2020

Early warning services for crop diseases are valuable when they provide timely forecasts that farmers can utilize to inform their disease management decisions. In South Korea, collaborative disease controls that utilize unmanned aerial vehicles are commonly performed for most rice paddies. However, such controls could benefit from seasonal disease early warnings with a lead time of a few months. As a first step to establish a seasonal disease early warning service using seasonal climate forecasts, we developed the EPIRICE Daily Risk Model for rice blast by extracting and modifying the core infection algorithms of the EPIRICE model. The daily risk scores generated by the EPIRICE Daily Risk Model were successfully converted into a realistic and measurable disease value through statistical analyses with 13 rice blast incidence datasets, and subsequently validated using the data from another rice blast experiment conducted in Icheon, South Korea, from 1974 to 2000. The sensitivity of the model to air temperature, relative humidity, and precipitation input variables was examined, and the relative humidity resulted in the most sensitive response from the model. Overall, our results indicate that the EPIRICE Daily Risk Model can be used to produce potential disease risk predictions for the seasonal disease early warning service.

• Journal of the Korean Society of Safety
• /
• v.24 no.5
• /
• pp.63-68
• /
• 2009

The urgent VAI method development is required since "The Act of Physical Protection and Radiological Emergency that is established in 2003" requires an evaluation of physical threats in nuclear facilities and an establishment of physical protection in Korea. The VAI methodology is developed to (1) make a sabotage model by reusing existing fire/flooding/pipe break PSA models, (2) calculate MCSs and TEPSs, (3) select the most cost-effective TEPS among many TEPSs, (4) determine the compartments in a selected TEPS as vital areas, and (5) provide protection measures to the vital areas. The developed VAI methodology contains four steps, (1) collecting the internal level 1 PSA model and information, (2) developing the fire/flood/pipe rupture model based on level 1 PSA model, (3) integrating the fire/flood/pipe rupture model into the sabotage model by JSTAR, and (4) calculating MCSs and TEPS. The VAT process is performed through the VIPEX that was developed in KAERI. This methodology serves as a guide to develop a sabotage model by using existing internal and external PSA models. When this methodology is used to identify the vital areas, it provides the most cost-effective method to save the VAI and physical protection costs.

• Journal of Multimedia Information System
• /
• v.6 no.4
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.

• Journal of Biomedical Engineering Research
• /
• v.22 no.4
• /
• pp.369-375
• /
• 2001

The statistical regression model is one of the most frequently used clinical analysis methods. It has basic assumption of linearity, additivity and normal distribution of data. However, most of biological data in medical field are nonlinear and unevenly distributed. To overcome the discrepancy between the basic assumption of statistical model and actual biological data, we propose a new analytical method based on artificial neural network. The newly developed multilayer perceptron(MLP) is trained with 120 data set (60 normal, 60 patient). On applying test data, it shows the discrimination power of 0.76. The diabetic risk factors were also identified from the MLP neural network model and the logistic regression model. The signigicant risk factors identified by MLP model were post prandial glucose level(PP2), sex(male), fasting blood sugar(FBS) level, age, SBP, AC and WHR. Those from the regression model are sex(male), PP2, age and FBS. The combined risk factors can be identified using the MLP model. Those are total cholesterol and body weight, which is consistent with the result of other clinical studies. From this experiment we have learned that MLP can be applied to the combined risk factor analysis of biological data which can not be provided by the conventional statistical method.

• Journal of the Ergonomics Society of Korea
• /
• v.19 no.3
• /
• pp.23-37
• /
• 2000

Usability is one of the most important factors that affect customers' decision to purchase a product. Several studies have been conducted to model the relationship between the product design variables and the product usability. Since there could be hundreds of design variables to be considered in the model, a variable screening method is required. Traditional variable screening methods are based on expert opinions (Expert screening) in most Kansei engineering studies. Suggested in this study are statistical methods for screening important design variables by using the principal component regression(PCR), cluster analysis, and partial least squares(PLS) method. Product variables with high effect (PCR screening and PLS screening) or representative variables (Cluster screening) can be used to model the usability. Proposed variable screening methods are used to model the usability for 36 audio/visual products. The three analysis methods (PCR, Cluster, and PLS) show better model performance than the Expert screening in terms of $R^2$, the number of variables in the model, and PRESS. It is expected that these methods can be used for screening the product design variables efficiently.