• Journal of the Korean Statistical Society
• /
• v.26 no.2
• /
• pp.277-288
• /
• 1997

For the analysis of survival data including covariates whose effects vary in time, the multiprocess discount survival model is proposed. The parameter vector modeling the time-varying effects of covariates is to vary between time intervals and its evolution between time intervals depends on the perturbation of the next time interval. The recursive estimation of the parameter vector can be obtained at the end of each time interval. The retrospective estimation of the survival function and the forecasting of the survival function of individuals of the specific covariates also can be obtained based on the information gathered until the end of the time interval.

• Journal of Korean Society for Quality Management
• /
• v.12 no.2
• /
• pp.2-5
• /
• 1984

Periodic replacement model with minimal repair at failure is extended to the case where quantity purchases are possible. A recursive relationship among replacement intervals is obtained, which shows that replacement intervals are an increasing sequence due to the inventory carrying cost. Using the relationship, a procedure is given for determining how many units to purchase on each order and when to replace each unit after it has begun operating so as to minimize the total cost per unit time over an infinite time span. The problem can be simplified if equal replacement intervals are assumed, and the solution is very close to the solution of the unconstrained problem.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.29 no.11
• /
• pp.74-81
• /
• 2015

In the measurement of atmospheric static electric field, it is important to know characteristics of corona discharges caused at the tip of test electrode. This paper presents the fundamental data of DC corona discharges that occurred at the tip of a needle-shaped electrode placed in the homogeneous background electric field which simulates the atmospheric static field under thundercloud. The major characteristics of interest for this purpose are the polarity effect of corona discharges and the magnitudes and time intervals of corona current pulses. The experimental set-up consists of the plate-to-plate configuration with a needle-shaped protrusion, DC power supply, and voltage and current measuring devices. As a result of experiments, the polarity dependence of corona pulses is significantly pronounced. The time intervals between successive corona pulses in the negative polarity is much longer than those in the positive polarity. The time intervals for both polarities is drastically decreased as the applied electric field is increased. Also the magnitudes of the positive corona pulses are slightly changed with an increase in applied electric field, but those of the negative corona pulses are linearly increased with increasing the applied electric fields.

• The Korean Journal of Emergency Medical Services
• /
• v.22 no.3
• /
• pp.47-54
• /
• 2018

Purpose: The purpose of this study was to present evidence for quality management based on analysis of patient transportation and response intervals among emergency medical squads. Methods: The chi-square test was used to determine whether mental status and patient assessment affected direct medical control and hospital destination. One way analysis of variance was used to compare response intervals depending on mental status and patient assessment using data drawn from 1172 prehospital care reports. Results: There was a statistically significant relationship between mental status and direct medical control (p<.001); there was a statistically significant relationship between patient assessment and hospital destination (p=.011). However, there was no statistically significant relationship between mental status and hospital destination. The interval from arrival at the patient's side to departure from the scene showed a statistically significant difference (p<.001, p<.001), however, it took the longest time (16.8 minutes) in unresponsive patients. It showed a statistically significant difference (p<.001) in the interval from arrival at patient's side to departure from the scene depending on patient assessment; however, it took the longest time (9.6 minutes) in emergency patients. Conclusion: There was call for direct medical control based on patient assessment; however, patient transportation and response intervals were not appropriate.

• Smart Structures and Systems
• /
• v.21 no.2
• /
• pp.187-194
• /
• 2018

This paper focuses on the $H_{\infty}$ filter design problem for offshore steel jacket platforms. Its objective is to design a full-order state observer for offshore platforms in presence of unknown disturbances. To make the method more practical, it is assumed that the measured variables are available at discrete-time instants with time-varying sampling time intervals. By modelling the sampling intervals as a bounded time-varying delay, the estimation error system is expressed as a time-delay system. As a result, the addressed problem can be transformed to the problem of stability of dynamic error between the system and the state estimator. Then, based on the Lyapunov-Krasovskii Functional (LKF), a stability criterion is obtained in the form of Linear Matrix Inequalities (LMIs). According to the stability criterion, a sufficient condition on designing the state estimator gain is obtained. In the end, the proposed method is applied to an offshore platform to show its effectiveness.

• Journal of Information Processing Systems
• /
• v.2 no.1
• /
• pp.23-27
• /
• 2006

This paper presents a feature selection technique based on distributional differences for efficient machine learning. Initial training data consists of data including many features and a target value. We classified them into positive and negative data based on the target value. We then divided the range of the feature values into 10 intervals and calculated the distribution of the intervals in each positive and negative data. Then, we selected the features and the intervals of the features for which the distributional differences are over a certain threshold. Using the selected intervals and features, we could obtain the reduced training data. In the experiments, we will show that the reduced training data can reduce the training time of the neural network by about 40%, and we can obtain more profit on simulated stock trading using the trained functions as well.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.6
• /
• pp.1122-1129
• /
• 2007

For a system with multiple real-time tasks of different deadlines, it is very difficult to find the optimal checkpoint interval because of the complexity in considering the scheduling of tasks. In this paper, we determine the optimal checkpoint interval for multiple real-time tasks that are scheduled by RM(Rate Monotonic) algorithm. Faults are assumed to occur with Poisson distribution. Checkpoints are inserted in the execution of task with equal distance in the same task, but different distances in other tasks. When faults occur, rollback to the latest checkpoint and re-execute task after the checkpoint. We derive the equation of maximum slack time for each task, and determine the number of re-executable checkpoint intervals for fault recovery. The equation to check the schedulibility of tasks is also derived. Based on these equations, we find the probability of all tasks executed within their deadlines successfully. Checkpoint intervals which make the probability maximum is the optimal.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.7
• /
• pp.875-882
• /
• 2014

In this paper, we propose a new parameter estimation method that can deal with the data of multiple time intervals simultaneously. If there are common modes in the multiple time intervals, it is possible to create a new polynomial by summing the coefficients of the prediction error polynomials of each time interval. By calculating the roots of the new polynomial, it is possible to estimate the common modes that exist in each time interval. The accuracy of the proposed parameter estimation method has been proven by using appropriate test signals.

• Bulletin of the Korean Mathematical Society
• /
• v.52 no.2
• /
• pp.483-504
• /
• 2015

This paper is devoted to solving a multidimensional backward stochastic differential equation with a general time interval, where the generator is uniformly continuous in (y, z) non-uniformly with respect to t. By establishing some results on deterministic backward differential equations with general time intervals, and by virtue of Girsanov's theorem and convolution technique, we prove a new existence and uniqueness result for solutions of this kind of backward stochastic differential equations, which extends the results of [8] and [6] to the general time interval case.

• Clinical and Experimental Reproductive Medicine
• /
• v.49 no.4
• /
• pp.270-276
• /
• 2022

Objective: The present study assessed the biological characteristics of human spermatozoa at different time intervals (0, 1, 1.5, and 2 hours) after incubation at 37℃. Methods: Twenty-five normozoospermic semen samples were incubated at 37℃. Incubation was performed at four time intervals of 0 (after liquefaction), 1, 1.5, and 2 hours. The samples were evaluated for sperm parameters at each time interval. Results: The rate of sperm progressive motility decreased at 1.5 hours compared to 0 hours as well as 2 hours compared to 1 hour and 0 hours. The rate of non-motile spermatozoa also decreased after 2 hours compared to after 0 hours. No significant changes were observed in sperm viability (p=0.98) and non- progressive motility (p=0.48) at any time intervals. Abnormal sperm morphology increased at 1.5 hours of incubation time (p<0.001). No significant changes were observed in DNA fragmentation at 1 hour compared to 0 hours (median [interquartile range]: 19.5 [4] vs. 19 [4]), as well as at 1.5 hours compared to 1 hour (20 [5]). However, a significant increase in DNA fragmentation was observed at 1.5 hours compared to 0 hours. The mitochondrial membrane potential decreased remarkably after 1 hour of incubation time. No significant differences were observed in the acrosome reaction or malonaldehyde levels at any time point (p=0.34 and p=0.98, respectively). Conclusion: The incubation of normozoospermic samples before use in assisted reproductive technology should be less than 1.5 hours to minimize the destructive effects of prolonged incubation time on general and specific sperm parameters.