• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.589-603
• /
• 2014

When consecutive data follows different distributions(depending on the time interval) change-point detection infers where the changes occur first and then finds further inferences for each sub-interval. In this paper, we investigate the Bayesian detection of multiple change points. Utilizing the reversible jump MCMC, we can explore parameter spaces with unknown dimensions. In particular, we consider a model where the signal is a piecewise linear function. For the Bayesian inference, we propose a new Bayesian structure and build our own MCMC algorithm. Through the simulation study and the real data analysis, we verified the performance of our method.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.05a
• /
• pp.393-398
• /
• 2007

Balance shaft has a key role in reducing a engine vibration in a vehicle and widely applied for current models. Since balance shaft module consists many sub-component and each part had its own operational characteristics, some different analysis background should be integrated into one sub-part in balance shaft module and this is the main obstacles in making a design process. Moreover, the balancing shaft rotating in high speed and such condition requires large safety factors in a design process owing to a lot of unexpected problems with the overwhelming rotation. Balance shaft is the core-component generating the intended unbalance as well as canceling the unbalance force or moment by the engine module. So, the balance shaft should meet the high fatigue resistance not to mention of NVH performance. In this paper, a design strategy focused on balance shaft is developed to build a optimal model considering a engine vibration. Putting the unbalance mass distribution as main design parameter, some candidate model is verified with structural and fatigue analysis most appropriate model is proposed here.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.1
• /
• pp.139-152
• /
• 2013

The purpose of this study is to claim the validity of tuning the architecture of neural network models for multi-class classification. A neural network model for multi-class classification is basically constructed by building a series of neural network models for binary classification. Building a neural network model, we are required to set the values of parameters such as number of hidden nodes and weight decay parameter in advance, which draws special attention as the performance of the model can be quite different by the values of the parameters. For better performance of the model, it is absolutely necessary to have a prior process of tuning the parameters every time the neural network model is built. Nonetheless, previous studies have not mentioned the necessity of the tuning process or proved its validity. In this study, we claim that we should tune the parameters every time we build the neural network model for multi-class classification. Through empirical analysis using wine data, we show that the performance of the model with the tuned parameters is superior to those of untuned models.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.3 no.3
• /
• pp.173-183
• /
• 1998

In this paper, an auto-tuning method for fuzzy controller's membership functions based on the neural network is presented. The neural network emulator offers the path which reforms the fuzzy controller's membership functions and fuzzy rule, and the reformed fuzzy controller uses for speed control of induction motor. Thus, in the case of motor parameter variation, the proposed method is superior to a conventional method in the respect of operation time and system performance. 32bit micro-processor DSP(TMS320C31) is used to achieve the high speed calculation of the space voltage vector PWM and to build the self-learning fuzzy control algorithm. Through computer simulation and experimental results, it is confirmed that the proposed method can provide more improved control performance than that PI controller and conventional fuzzy controller.

• The Journal of Korean Society for School & Community Health Education
• /
• v.14 no.2
• /
• pp.29-45
• /
• 2013

Objectives: The purpose of this study was to identify relationships between experiential activity, ego-resilience, sense of community, and school life adjustment of middle school students and to provide the basic data that can contribute to the activation of experiential activities. Methods: 2,351 middle school students of panel survey conducted by National Youth Policy Institute were used in the final analysis. The structural equation model(SEM) was carried out to analyze structural relationships between experiential activity and ego-resilience, sense of community, and school life adjustment of the youth. IBM SPSS Statistics 20.0 and IBM SPSS AMOS 20.0. were used for the analysis of all data. Results: Experiential activities had a statistically significant positive effect on ego-resilience(p<0.001), school life adjustment(p<0.05), and the sense of community (p<0.001). Especially experiential activities acted on ego-resiliency, a sense of community, school life adjustment as an important parameter. Sense of community also showed to be an important mediating role between ego-resiliency and school life adjustment. Conclusions: In order to maximize the effectiveness of experiential activities, it is necessary to build the community networking enough to take full advantage of community resources and develop various experiential activities to meet the needs of youth and social change.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.1
• /
• pp.144-152
• /
• 2013

Design is an iterative, generative, and multidisciplinary process by its nature. Iteration occurs often in most of the engineering design and development projects including construction. Design iterations cause rework, and extra efforts are required to get the optimal sequence and to manage the projects. Contrary to simple design, isolation of the generative iterations in complex design systems is very difficult, but reduction in overall iterations is possible. Design depends upon the information flow within domain and also among various design disciplines and organizations. Therefore, it is suggested that managers should be aware about the crucial iterations causing rework and optimal sequence as well. In this way, managers can handle design parameters related to such iterations pro-actively. There are a number of techniques to reduce iterations for various kinds of engineering designs. In this paper, parameter based Design Structure Matrix (DSM) is chosen. To create this DSM, a survey was performed and then partitioned using a model. This paper provides an easy approach to those companies involved in or intend to be involved in "design and build projects".

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.51 no.4
• /
• pp.163-168
• /
• 2002

This paper present a new verb efficient numerical algorithm for arcing faults detection and fault distance estimation in transmission line. It is based on the fundamental differential equations describing the transients on a transmission line before, during and alter the fault occurrence, and on the application of the "Least Error Squares Technique"for the unknown model parameter estimation. If the arc voltage estimated is a near zero, the fault is without arc, in other words the fault is permanent fault. If the arc voltage estimated has any high value, the faust is identified as an fault, or the transient fault. In permanent faults case, fault distance estimation is necessary. This paper uses the model of the arcing fault in transmission line using ZnO arrestor and resistance to be implemented within EMTP. One purpose of this study is to build a structure for modeling of arcing fault detection and fault distance estimation algorithm using Matlab programming. In this paper, This algorithm has been designed in Graphic user interface(GUI).

• Journal of the Korean Ceramic Society
• /
• v.47 no.6
• /
• pp.503-508
• /
• 2010

$Eu^{2+}$-doped $\beta$-SiAlONs ($Si_{6-z}Al_zO_zN_{8-z}:Eu_y$) are recognized as promising phosphor materials to build an white LED for lighting application due to its excellent absorption/emission efficiency in the long wave length region. In this research, the fabrication of $\beta$-SiAlON:Eu plate phosphor by sintering was investigated with fixed Eu content(y) and varied composition of the host lattice(z). The addition of the activator $Eu_2O_3$ lead to enhanced densification by forming the transient liquid phase. The refinement of a composition by the calculated lattice parameter indicated that the measured composition of the fabricated specimens is nearly same to that of designed one. The single phase $\beta$-SiAlON:Eu plate with relative density of 96.4% was achieved by addition of 2 wt% CaO, which implies the possibility of full densification by adjusting the processing variables.

• Journal of Korean Society of Steel Construction
• /
• v.14 no.1
• /
• pp.113-120
• /
• 2002

A shear connection in composite bridges with precast decks has considerable characteristics different from cast-in-place deck bridges such as shear pocket and bedding layer. Thus, it is necessary to build design basis of the shear connector in precast decks through the experiments. In order to estimate fatigue life of shear connector in precast deck bridges, push-out fatigue tests were conducted with parameter, bedding layer thickness. As a result of the tests, failure modes of shear connector were observed. Consequently, empirical S-N curve equations of stud shear connector in precast deck bridges were proposed in this paper.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.67-77
• /
• 2008

In this paper, we implemented a robust speech recognizer using the TMS320VC33 DSP. For this implementation, we had built speech and noise database suitable for the recognizer using spectral subtraction method for noise removal. The recognizer has an explicit structure in aspect that a speech signal is enhanced through spectral subtraction before endpoints detection and feature extraction. This helps make the operation of the recognizer clear and build HMM models which give minimum model-mismatch. Since the recognizer was developed for the purpose of controlling car facilities and voice dialing, it has two recognition engines, speaker independent one for controlling car facilities and speaker dependent one for voice dialing. We adopted a conventional DTW algorithm for the latter and a continuous HMM for the former. Though various off-line recognition test, we made a selection of optimal conditions of several recognition parameters for a resource-limited embedded recognizer, which led to HMM models of the three mixtures per state. The car noise added speech database is enhanced using spectral subtraction before HMM parameter estimation for reducing model-mismatch caused by nonlinear distortion from spectral subtraction. The hardware module developed includes a microcontroller for host interface which processes the protocol between the DSP and a host.