• Communications for Statistical Applications and Methods
• /
• 제6권2호
• /
• pp.383-395
• /
• 1999

This study is concerned with the evaluation of predictive ability of classification models with ordered multiple categories. If categories can be ordered or ranked the spread of misclassification should be considered to evaluate the performance of the classification models using loss rate since the apparent error rate can not measure the spread of misclassification. Since loss rate is known to underestimate the true loss rate the bootstrap method were used to estimate the true loss rate. thus this study suggests the method to evaluate the predictive power of the classification models using loss rate and the bootstrap estimate of the true loss rate.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1996년도 가을 학술발표회 논문집
• /
• pp.29-36
• /
• 1996

A procedure for the predictive control for structural vibration control in building subject to wind loads is presented. The building motions are modeled by the first mode of the response. Wind velocities are generated by the simulation using power spectral density function. Predictive control algorithm is the discrete-time formulation and that is developed as a control strategy that computes the control signal which makes the predicted process output equal to a desired process output. Results on the reduction of the dynamic response and control effectiveness of the algorithm are presented and discussed.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 1999년도 전력전자학술대회 논문집
• /
• pp.489-492
• /
• 1999

This paper proposes a control method for three-phase voltage-source PWM converters using only a single current sensor in the DC link. A predictive current controller for the voltage-source PWM converter is used so that all phase currents can be reconstructed in a switching period although one or two of active vectors are applied only for a short time. Compensation of the 2 step delays is also included. In this paper single sensor current control using predictive state observer will be discussed, and investigated experimentally.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2015년도 전력전자학술대회 논문집
• /
• pp.63-64
• /
• 2015

The control of IPMSM(Interior Permanent Magnet Synchronous Motor) for electric vehicle is important to track torque reference depended on accelerator. This paper executes IPMSM control applied the predictive current control which has good dynamic characteristic and, compare PI control with predictive current control to verify dynamic characteristic through simulation.

• 조명전기설비학회논문지
• /
• 제28권6호
• /
• pp.40-44
• /
• 2014

In this paper, maximum power is the lowering device using the facility's energy use and peak load electricity through analyzing attitude should like to make it reduce its power base rate. Simulator to manage the demand for power, a maximum electric power base power from electronic watt-hour meters by a device's signal, predictive power, the current power by computing the goal of power for less than Maximum peak power and peak shift, so that you can manage, and peak York, which role you want a cut Metal heat treatment result which analyzes the data, demand for electricity company over the years of analyzing the characteristics of each load, and effects and Reducing power consumption device every month identified seven Sequence control to the load system and successful power control is about showing that the defined goals.

• 대한간호학회지
• /
• 제27권4호
• /
• pp.796-806
• /
• 1997

The majority of studies on breastfeeding consists of descriptive correlational studies identifying the incidence and correlates of breastfeeding. The theory of planned behavior has been shown to yield great predictive power for behavioral goals over which individuals have only limited control such as improving school grades and weight loss. The purpose of this study was to test the "theory of planned behavior" in the prediction of breastfeeding of mothers who delivered vaginally, One hundred mothers who delivered vaginally in one general hospital in Seoul and one general hospital and three private hospitals in Taejeon participated in this study. The instruments used for data collection in this study were developed by the researchers following the guidelines suggested by Ajzen & Fishbein(1980) and Ajzen & Madden(1986). The instruments included measurement of attitude, subjective norm, perceived behavioral control and intention. The collected data were analyzed using descriptive statistics, Pearson product moment correlation, hierachical multiple regression and logistic regression. The results are as follows ; 1. Intention to breastfeed correlated significantly with attitude, subjective norm and perceived behavioral control. Both attitude and subjective norm did not make a significant contribution to the prediction of intention, but the addition of perceived behavioral control to the regression equation greatly improved the model's predictive power, increasing the R²from .05 to .52. 2. Intention to breastfeed alone had a significant predictive effect on actual breastfeeding, resulting in a regression coefficient of .16(X²=8 60, p<.01), but when perceived behavioral control was added to the equation, intention was not a significant predictive variable and only perceived behavioral control showed significant predictive power on actual breastfeeding, resulting in a regression coefficient of .12(X²=4.69, p<.05). In sum, breastfeeding behavior lent only partial support to the second version of the theory of planned behavior, and because perceived behavioral control had a strong effect on intention to breastfeed and actual breastfeeding, It would be desirable to develop nursing intervention programs which focus on strengthening the perceived behavioral control for the promotion of breastfeeding.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 A
• /
• pp.295-299
• /
• 1996

When the current of a power converter is controlled with a digital controller, it generally shows the error due to execution time delay. The error may be considerable in such systems as active power filters wherein the current varies steeply even in steady state, as well as in transients. Therefore, it is of particular importance to compensate the time delay effect in a digitally-controlled active power filter. This paper introduces a modification of so-called predictive current control, by taking the control time delay into consideration. The results of simulation and experiment with a 10 kVA active power filter prototype show considerable improvement in current tracking capability, validating the proposed current control method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.416-418
• /
• 1997

Stable power source and fast control response are important for the generator excitation system. To stabilize the control of excitation circuit the PI controller for excitation current has been used. But the response of the system with this conventional control technique is very poor, especially in transient response with a predictive current control, the response of the excitation system can be improved. In this study, it is verified by the PSIM simulation.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2019년도 추계학술대회
• /
• pp.180-181
• /
• 2019

This paper proposes a method for improving the power quality of PMSG-based wind energy conversion system based on model predictive control in DC Microgrid. The MPC has a fast dynamic response. However, a large torque ripple deteriorating power quality is generated by a large and fixed switching period. On the other hand, the proposed method improves the power quality by setting the sampling time having zero torque error. The validity of the proposed method is verified through PSIM simulation.

• International journal of advanced smart convergence
• /
• 제7권4호
• /
• pp.75-83
• /
• 2018

Predictive IoT Sensor Algorithm is a technique of data science that helps computers learn from existing data to predict future behaviors, outcomes, and trends. This algorithm is a cloud predictive analytics service that makes it possible to quickly create and deploy predictive models as analytics solutions. Sensors and computers collect and analyze data. Using the time series prediction algorithm helps to predict future temperature. The application of this IoT in industrial environments like power plants and factories will allow organizations to process much larger data sets much faster and precisely. This rich source of sensor data can be networked, gathered and analyzed by super smart software which will help to detect problems, work more productively. Using predictive IoT technology - sensors and real-time monitoring - can help organizations exactly where and when equipment needs to be adjusted, replaced or how to act in a given situation.