• 한국컴퓨터정보학회논문지
• /
• 제21권4호
• /
• pp.73-80
• /
• 2016

Most fault prediction models have class imbalance problems because training data usually contains much more non-fault class modules than fault class ones. This imbalanced distribution makes it difficult for the models to learn the minor class module data. Data imbalance is much higher when severity-based fault prediction is used. This is because high severity fault modules is a smaller subset of the fault modules. In this paper, we propose severity-based models to solve these problems using the three sampling methods, Resample, SpreadSubSample and SMOTE. Empirical results show that Resample method has typical over-fit problems, and SpreadSubSample method cannot enhance the prediction performance of the models. Unlike two methods, SMOTE method shows good performance in terms of AUC and FNR values. Especially J48 decision tree model using SMOTE outperforms other prediction models.

• IEIE Transactions on Smart Processing and Computing
• /
• 제3권1호
• /
• pp.19-27
• /
• 2014

Compressive sensing is an emerging sampling technique which enables sampling a signal at a much lower rate than the Nyquist rate. In this paper, we propose a novel framework based on Kronecker compressive sensing that provides multi-resolution image reconstruction capability. By exploiting the relationship of the sensing matrices between low and high resolution images, the proposed method can reconstruct both high and low resolution images from a single measurement vector. Furthermore, post-processing using BM3D improves its recovery performance. The experimental results showed that the proposed scheme provides significant gains over the conventional framework with respect to the objective and subjective qualities.

• 한국통신학회논문지
• /
• 제21권11호
• /
• pp.2942-2953
• /
• 1996

This paper studies the effect of intersymbol interference due to sampling-time jitter on the worst-case bit error probability in a digital modultation over an additive white Gaussian noise channel, with the squared-root raised-cosine filters in the transmitter and the receiver. It derives approximation formulas using the Taylor series approximations. the principal results of this paper is the relationship between the worst-casse bit error probability, the degree of jitter, the roll factor of the raised cosine filter, and other quantities. Numerical results show, as expected, that the intersymbol interference decreases as the roll-off factor increases and the jitter decreases. They also show that the approximation formulas are accurate for smally intersymbol interference, i.e., for large roll-noise ratio $E_{b/}$ $N_{0}$.leq.7 dB and begin to lose accuracy for larger signal-to-noise ratio.o.o.

• 대한기계학회논문집A
• /
• 제26권9호
• /
• pp.1859-1865
• /
• 2002

In the conventional sliding mode control technique, a priori knowledge of the bound of external disturbances or/and parameter uncertainties is required to assure control robustness. This, however, may not be easy to obtain in practical situation. This work presents a novel methodology, a sliding mode controller with perturbation estimator, which offers a robust control performance without a priori knowledge about the perturbations (disturbances and parameter uncertainties). The proposed technique is featured by an integrated average value of the imposed perturbation over a certain sampling period. In order to demonstrate the effectiveness of the proposed methodology, a two-link robotic system is adopted and its position control performance is evaluated. In addition, a comparative work between the conventional technique and the proposed one is undertaken.

• Wind and Structures
• /
• 제6권5호
• /
• pp.403-418
• /
• 2003

This paper presents an extensive analysis of the short term, unsteady wind loading on a low-rise building. The building is located in a rural environment and only the specific situation of wind flow orthogonal to the long face of the structure is considered. The data is analysed using conventional analysis and less traditional methods such as conditional sampling and wavelet analysis. The nature of the flow field over the building is found to be highly unsteady and complex. Fluctuating pressures on the windward wall are shown to a large extent to be caused by the fluctuations in the upstream flow, whereas extreme pressures on the roof are as a result of high intensity small scale flow structures. On the roof of the building a significant amount of energy is shown to exist at frequencies above 1 Hz.

• 제어로봇시스템학회논문지
• /
• 제8권1호
• /
• pp.1-4
• /
• 2002

We studied the technique which can control the real system without additional hardware drivers using virtual machine driver operated on the windows operating system. We showed the feasibility of the proposed scheme under the error and the delay of a sampling time on the multi task processing through the load test of the experiment using graphic user interface.

• 대한산업공학회지
• /
• 제34권3호
• /
• pp.328-336
• /
• 2008

This research proposes a method for economic-statistical design of adaptive moving average (A-MA) charts. The basic idea of the A-MA chart is to accumulate previous samples selectively in order to increase the sensitivity. The A-MA chart is a kind of adaptive chart such as the variable sampling size (VSS) chart. A major advantage of the A-MA chart over the VSS chart is that it is easy to maintain rational subgroups by using the fixed sampling size. A steady state cost rate function is constructed based on Lorenzen and Vance (1986) model. The cost rate function is optimized with respect to five design parameters. Computational experiments show that the A-MA chart is superior to the VSS chart as well as to the Shewhart $\bar{X}$ chart in the economic-statistical sense.

• 응용통계연구
• /
• 제25권4호
• /
• pp.641-650
• /
• 2012

Spatial time series data can be viewed as a set of time series simultaneously collected at a number of spatial locations. This paper studies Bayesian inferences in a spatial time bilinear model with a Gibbs sampling algorithm to overcome problems in the numerical analysis techniques of a spatial time series model. For illustration, the data set of mumps cases reported from the Korea Center for Disease Control and Prevention monthly over the years 2001~2009 are selected for analysis.

• Steel and Composite Structures
• /
• 제2권6호
• /
• pp.429-440
• /
• 2002

A finite strip method is developed for fatigue reliability analysis of steel highway bridges. Flat shell strips are employed to model concrete slab and steel girders, while a connection strip is formed using penalty function method to take into account eccentricity of girder top flange. At each sampling point with given slab thickness and modulus ratio, a finite strip analysis of the bridge under fatigue truck is performed to calculate stress ranges at fatigue-prone detail, and fatigue failure probability is evaluated following the AASHTO approach or the LEFM approach. After the failure probability is integrated over all sampling points, fatigue reliability of the bridge is determined.

• 산업경영시스템학회지
• /
• 제5권7호
• /
• pp.1-7
• /
• 1982

This thesis deals with the method of Work Sampling to compare production activity due to change of productivity, workmen's productivity environment, nonproductivity of machine and plant when there is a process before and after change of work environments. So, this study takes $x^2$ - test to discover significant change of process, and obtains Proper observation number due to ratio difference-test over change of productivity before and after process change. Therefore, this thesis represent statistically effective results between two periods before and after process change.