• Korean Journal Plant Pathology
• /
• v.14 no.4
• /
• pp.331-338
• /
• 1998

To develop the model for prediction of potato late blight progress, the relationship between severity index of potato late blight transformed by the logit and Gompit transformation function and cumulative severity value (CSV) processing weather data during growing period in Taegwallyeong alpine area, 1975 to 1992 were examined. When logistic model and Gompertz model were compared by determining goodness of fit for progressive degree of late blight using CSV as independent variable, the coefficients of determination were higher as 0.742 in the logistic model than 0.680 in the Gompertz model. Parameters in logistic model were composed of progressive rate and initial value of logistic model. Initial value was calculated in -3.664. The progressive rate of potato late blight was 0.137 in cv. Superior, 0.136 in cv. Irish Cobbler, and 0.070 in cv. Jopung without fungicide sprays. According to in crease of the number of spray times the progressive rate was lowered, was 0.020 in cv. Superior under the conventional program of fungicide sprays, 10 times sprays during cropping season. Equation of progressive rate, b1=0.0088 ACSV-0.033 (R2=0.976), was written by examining the relationship between the parameters of progressive rate of late blight and the average CSV (ACSV) quantifing weather information. By estimating parameters of logistic function, model able to describe the late blight progress of potato, cv. Superior was formulated in Y=4/(1+39.0·exp((0.0088 ACSV-0.033)·CSV).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.12
• /
• pp.5963-5980
• /
• 2017

Image scrambling is an important technology in information hiding, where the Arnold transformation is widely used. Several researchers have proposed the application of $H{\acute{e}}non$ map in square image scrambling, and certain improved technologies require scrambling many times to achieve a good effect without resisting chosen-plaintext attack although it can be directly applied to non-square images. This paper presents a non-square image scrambling algorithm, which can resist chosen-plaintext attack based on a chaotic two-dimensional Sine Logistic modulation map and $H{\acute{e}}non$ map (2D-SLHM). Theoretical analysis and experimental results show that the proposed algorithm has advantages in terms of key space, efficiency, scrambling degree, ability of anti-attack and robustness to noise interference.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.30-35
• /
• 2010

This paper presents a quality enhancement of images by using a histogram equalization based on the symmetric logistic function. The histogram equalization is a simple and effective spatial processing method that it enhances the quality by adjusting the brightness of image. The logistic function that is a sigmoidal nonlinear transformation function, is applied to non-linearly enhance the brightness of the image according to its intensity level frequency. We propose a flexible and symmetrical logistic function by only using the intensity with maximum frequency in an histogram and the total number of pixels. The proposed function decreases the computation load of an exponential function in the traditional logistic function. The proposed method has been applied for equalizing 5 images with a different resolution and histogram distribution. The experimental results show that the proposed method has the superior enhancement performances compared with the source images and the traditional global histogram equalization, respectively.

• Journal of the military operations research society of Korea
• /
• v.6 no.2
• /
• pp.129-149
• /
• 1980

In medical follow-up, equipment lifetesting, various military situations, and other fields, one often desires to calculate survival probability as a function of time, p(t). If the observer is able to record the time of occurrence of the event of interest (called a 'death'), then an empirical, non-parametric estimate may simply by obtained from the fraction of survivors after various elapsed times. The estimation is more complicated when the data are truncated, i.e., when the observer loses track of some individuals before death occurs. The product-limit method of Kaplan and Meier is one way of estimating p(t) when the mechanism causing truncation is independent of the mechanism causing death. This paper proposes jackknife estimators of logistic trans-formation and compares it to the product-limit method. A computer simulation is used to generate the times of death and truncation from a variety of assumed distributions.

• Korean Journal Plant Pathology
• /
• v.14 no.2
• /
• pp.150-156
• /
• 1998

To develop a model for prediction of turnip mosaic virus(TuMV) disease progress of Chinese cabbage based on weather information and number of TuMV vector aphids trapped in Taegwallyeong alpine area, data were statistically processed together. As the variables influenced on TuMV disease progress, cumulative portion(CPT) above 13$^{\circ}C$ in daily average temperature was the most significant, and solar radiation, duration of sunshine, vector aphids and cumulative temperature above $0^{\circ}C$ were significant. When logistic model and Gompertz model were compared by detemining goodness of fit for TuMV disease progress using CPT as independent variable, regression coefficient was higher in the logistic model than in the Gompertz model. Epidemic parameters, apparent infection rate and initial value of logistic model, were estimated by examining the relationship between disease proportion linearized by logit transformation equation, In(Y/Yf-Y) and CPT. Models able to describe the progression of TuMV disease were formulated in Y=100/(1+128.4 exp(-0.013.CPT.(-1(1/(1+66.7.exp(-0.11.day). Calculated disease progress from the model was in good agreement with investigated actual disease progress showing high significance of the coefficient of determination with 0.710.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.2
• /
• pp.403-410
• /
• 2014

Binary logistic regression analysis is a statistical technique that explains binary response variable by quantitative or qualitative explanatory variables. In the binary logistic regression model, the probability that the response variable equals, say 1, one of the binary values is to be explained as a transformation of linear combination of explanatory variables. This is one of big barriers that non-statisticians have to overcome in order to understand the model. In this study, an educational tool is developed that explains the need of the binary logistic regression analysis using Excel VBA. More precisely, this tool explains the problems related to modeling the probability of the response variable equal to 1 as a linear combination of explanatory variables and then shows how these problems can be solved through some transformations of the linear combination.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.39-47
• /
• 2021

This study was conducted to propose a product planning prediction model using logistic regression algorithm to predict seasonal factors and rapidly changing product trends. First, we collected unstructured data of consumers in portal sites and online markets using web crawling, and analyzed meaningful information about products through preprocessing for transformation of standardized data. The datasets of 11,200 were analyzed by Logistic Regression to analyze consumer satisfaction, frequency analysis, and advantages and disadvantages of products. The result of analysis showed that the satisfaction of consumers was 92% and the defective issues of products were confirmed through frequency analysis. The results of analysis on the use satisfaction, system efficiency, and system effectiveness items of the developed product planning prediction program showed that the satisfaction was high. Defective issues are very meaningful data in that they provide information necessary for quickly recognizing the current problem of products and establishing improvement strategies.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1991.10a
• /
• pp.357-365
• /
• 1991

Military material-supply problem is one of the most important logistic problems under conscription system. Formally, two approaches were followed lowed to this problem. (1) Needs for material per soldier is estimated by past experience. The total demand for the material is estimated by multiplication of this coefficient and the number of soldiers given in the governmental programme. (2) The total demand for the material is estimated by the forcast based on the past statistics. The material supply system based on these estimates, however, relies too much on past statistics ;lack of flexibility is feared to adapt itself to changes in conscription programme, life-time of materials and so on. In this paper, the author has followed new approach : The conscription system itself is a linear input-output system, in which sequences of enlistment and dischargement are regarded as input and output. And the sequencial demands for the material are related by another linear transformation to the former sequences. In this regard z-transformation is applied to construct to transfer functions associated with this system. With these transfer functions, methods are established to determine the material demand corresponding to conscription programme and life-time distribution. Numerical methods by computers are also prepared.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.203-226
• /
• 2021

Purpose The purpose of this study is to enhance the accuracy score of personal credit scoring using the convolutional neural networks and secure the transparency of the deep learning model using eXplainalbe Artifical Inteligence(XAI) technique. Design/methodology/approach This study built a classification model by using the convolutional neural networks(CNN) and applied a methodology that is transformation of numerical data to imaged data to apply CNN on personal credit data. Then layer-wise relevance propagation(LRP) was applied to model we constructed to find what variables are more influenced to the output value. Findings According to the empirical analysis result, this study confirmed that accuracy score by model using CNN is highest among other models using logistic regression, neural networks, and support vector machines. In addition, With the LRP that is one of the technique of XAI, variables that have a great influence on calculating the output value for each observation could be found.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.6
• /
• pp.2441-2445
• /
• 2015

Background: Several risk factors leading to malignant transformation of hydatidiform moles have been described previously. Many studies showed that prophylactic chemotherapy for high risk hydatidiform moles could significantly decrease the incidence of malignancy. Thus, it is essential to discover a breakthrough to determine patients with high risk malignancy so that prophylactic chemotherapy can be started as soon as possible. Objectives: Development of a scoring system of risk factors as a predictor of hydatidiform mole malignant transformation. Materials and Methods: This research is a case control study with hydatidiform mole and choriocarcinoma patients as subjects. Multiple logistic regression was used to analyze the data. Odds ratios (OR), attributable at risk (AR : OR-1) and risk index ($ARx{\beta}$) were calculated for develoipment of a scoring system of malignancy risk. The optimal cut-off point was determined using receiver operating characteristic (ROC) curve. Results: This study analyzed 34 choriocarcinoma cases and 68 benign hydatidiform mole cases. Four factors significantly increased the risk of malignancy, namely age ${\geq}35$ years old (OR:4.41, 95%CI:1.07-16.09, risk index 5); gestational age ${\geq}$ 12weeks (OR:11.7, 95%CI:1.8-72.4, risk index 26); uterine size greater than the gestational age (OR:10.2, 95%CI:2.8-36.6, risk index 21); and histopathological grade II-III (OR:3.4, 95%CI:1.1-10.6, risk index 3). The lowest and the highest scores for the risk factors were zero and 55, respectively. The best cut-off point to decide high risk malignancy patients was ${\geq}31$. Conclusions: Malignant transformation of hydatidiform moles can be predicted using the risk scoring by analyzing the above four parameters. Score ${\geq}31$ implies high risk patients so that prophylactic chemotherapy can be promptly administered for prevention.