• Journal of Korean Society for Quality Management
• /
• v.44 no.2
• /
• pp.221-244
• /
• 2016

Purpose: This research reviews the papers, published in the Journal of the Korean Society for Quality Control (KSQC) and the Journal of the Korean Society for Quality Management (KSQM) since 1965, in the area of statistical methods. The literature review is performed in the four fields of the statistical methods and we categorize the published articles into the several sub-areas in each field. Methods: The reviewed articles are classified into the four main categories: probability model and estimation, Bayesian analysis and non-parametric analysis, regression and time series analysis, and application of data analysis. We examine the contents and relationships of the published articles of the several sub-areas in each category. Results: We summarize the reviewed papers in the chronological road-maps for each sub-area, and outline the relations of the connected papers. Some comments on the contents and the contributions of the reviewed papers are also provided in this paper. Conclusion: Various issues are employed and published on the research of the application statistical methods for past 50 years, and many worthy works are achieved in the theory and application areas of statistical methods for improving quality in the manufacturing and service industries. The future direction of the research in the statistical quality management methods also can be explored by the contents of this research.

• Journal of the Korea Institute of Building Construction
• /
• v.14 no.6
• /
• pp.631-637
• /
• 2014

Recently, following the application of modular housing techniques to not only residential sector, but also to business sector, the scope of modular housing market b expanding. In the case of other developed countries, such markets are entering into the maturity stage, though the market in Korea is not fully formed yet. Thus, it is difficult to check its trend to estimated mid- to long-term prospects of the market. In this context, the study predicted demand of the modular housing market by using a non-linear prediction model based on time series analysis. To get the prospects for the modular housing market, the quantity of housing supply was estimated based on the estimated quantity of newly built housings, and assumed that a portion of the supplied quantity would be the demand for modular housings. Based on the assumption of demand for modular housings, several scenarios were analyzed and the prospects of the modular housing market was obtained by utilizing the non-linear prediction model.

• International Journal of Reliability and Applications
• /
• v.12 no.1
• /
• pp.15-39
• /
• 2011

This paper deals with the reliability analysis of a complex system with three possibilities at the time of repair. The considered system consists of two subsystems A and Bin series configuration (1-out-of-2: F). Subsystem A has n units which are connected in series whereas subsystem B consists of n units in parallel configuration. The configuration of subsystem A is of 1-out-of-n: F whereas subsystem B is of k-out-of-n: D and k+1-out-of-n: F nature. System has three states: Good, degraded and failed. Supplementary variable technique has been used for mathematical formulation of the model. Laplace transform is being utilized to solve the mathematical equation. Reliability, Availability, M.T.T.F., Busy Period and Cost effectiveness of the system have been computed. The repairs from state $S_7$ to $S_0$, $S_8$ to $S_0$, $S_9$ to $S_0$ and $S_{11}$ to $S_0$ have two types namely exponential and general. Joint probability distribution of repair rate from $S_7$ to $S_0$, $S_8$ to $S_0$, $S_9$ to $S_0$ and $S_{11}$ to $S_0$ is computed by Gumbel-Hougaard family of copula. Some particular cases of the system have also been derived to see the practical importance of the model.

• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.179-201
• /
• 2004

Online traffic flow modeling is attracting more attention due to intelligent transport systems and technologies. The flow-density relation plays an important role in traffic flow modeling and provides a basic way to illustrate traffic flow behavior under different traffic flow and traffic density conditions. Until now the research effort has focused mainly on the shape of the relation. The time series of the relation has not been identified clearly, even though the time series of the relation reflects the upstream/downstream traffic conditions and should be considered in the traffic flow modeling. In this paper the flow-density relation is analyzed dynamically and interpreted as a states diagram. The dynamic flow-density relation is quantified by applying fuzzy logic. The quantified dynamic flow-density relation builds the basis for online application of a macroscopic traffic flow model. The new approach to online modeling of traffic flow applying the dynamic flow-density relation alleviates parameter calibration problems stemming from the static flow-density relation.

• Smart Structures and Systems
• /
• v.26 no.5
• /
• pp.619-629
• /
• 2020

Solar towers, which often has a large aspect ratio and low fundamental natural frequency, were extremely prone to large amplitude of wind-induced vibrations, especially Vortex-Induced Vibration (VIV). A tiny Tuned Mass Damper (TMD) with conveniently adjustable eddy current damping was specially designed and manufactured for elastic wind tunnel tests of a solar tower. A series of numerical simulations by using the COMSOL software were conducted to determine three key parameters, including the thickness of the back iron plate and the conductive plate (T_b and T_c), the distance between the magnet and the conductive plate (T_d). Based on the results of numerical simulations, a tiny TMD was manufactured and its structural parameters were experimentally identified. The optimized values of the tiny TMD can be conveniently realized. The tiny TMD was installed at the top of the elastic test model of a 243-meter-high solar tower, and a series of wind tunnel tests were carried out to examine the effectiveness of the TMD in suppressing wind-induced responses of the test model. The results showed that the wind-induced responses could be obviously reduced by the TMD, especially in the cross-wind direction. The cross-wind RMS and peak responses at the critical wind velocity can be reduced by about 86% and 75%, respectively. However, the maximum reduction of the responses at the design wind velocity is about 45%, obviously less than that at the critical wind velocity.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.15 no.3
• /
• pp.219-225
• /
• 1982

Four heat conduction models were examined for defatted soy-protein curds in order to get the 'intrinsic' thermal conductivity of soy-protein. As the result of examination, the 'intrinsic', thermal conductivities of soy-protein, frozen and unfrozen states, were determined on the basis of series model to be 0.488 W/m.K and 0.300 W/m.K, respectively. By using the 'intrinsic' thermal conductivity values of soybean protein and the series model, the effective thermal conductivity of soybean curds, with and without fat, at frozen and unfrozen states, was predicted satisfactorily, The temperature dependency of the effective thermal conductivity of soybean curd was mostly observed to correlate with the thermal conductivity of water and ice.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.680-685
• /
• 2017

The emergence of online media and their data has enabled data-driven methods to solve challenging and complex tasks such as rumor classification problems. Recently, deep learning based models have been shown as one of the fastest and the most accurate algorithms to solve such problems. These new models, however, either rely on complete data or several days-worth of data, limiting their applicability in real time. In this study, we go beyond this limit and test the possibility of super early rumor detection via recurrent neural networks (RNNs). Our model takes in social media streams as time series input, along with basic meta-information about the rumongers including the follower count and the psycholinguistic traits of rumor content itself. Based on analyzing millions of social media posts on 498 real rumors and 494 non-rumor events, our RNN-based model detected rumors with only 30 initial posts (i.e., within a few hours of rumor circulation) with remarkable F1 score of 0.74. This finding widens the scope of new possibilities for building a fast and efficient rumor detection system.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.61-73
• /
• 2016

We consider the wild bootstrap Ljung-Box (LB) test for autocorrelation in residuals of fitted multivariate time series models. The asymptotic chi-square distribution under the IID assumption is traditionally used for the LB test; however, size distortion tends to occur in the usage of the LB test, due to the conditional heteroskedasticity of financial time series. In order to overcome such defects, we propose the wild bootstrap LB test for autocorrelation in residuals of fitted vector autoregressive and error correction models. The simulation study and real data analysis are conducted for finite sample performance.

• Water for future
• /
• v.21 no.1
• /
• pp.77-86
• /
• 1988

The main objective of this paper is to study the application of runs to the analysis of hydrologic data. The stochastic structure of annual hydrologic data is investigated using the statistical properties of run-length for various truncation levels. Observed relative frequencies of run-length at each station are copared with the calculated and approched to the calculated. Also, it can be shown to estimate the durations of wet and dry years by the probabilities of run-length for a given truncation level. Annual precipitation data were obtained from the stations where have relatively long records, and stream flow data were generated by Markov model. The results of hypothesis test with run-lengths show independence of annual hydrologic series and Markov model can be applied to generate annual stream flow at Hyunpung, Waekwan and Gyuam.

• Journal of Computational Design and Engineering
• /
• v.2 no.3
• /
• pp.157-164
• /
• 2015

This paper discusses an optimization-based approach for the design of a product platform for industrial three-axis linear-type robots, which are widely used for handling objects in manufacturing lines. Since the operational specifications of these robots, such as operation speed, working distance and orientation, weight and shape of loads, etc., will vary for different applications, robotic system vendors must provide various types of robots efficiently and effectively to meet a range of market needs. A promising step toward this goal is the concept of a product platform, in which several key elements are commonly used across a series of products, which can then be customized for individual requirements. However the design of a product platform is more complicated than that of each product, due to the need to optimize the design across many products. This paper proposes an optimization-based fundamental framework toward the design of a product platform for industrial three-axis linear-type robots; this framework allows the solution of a complicated design problem and builds an optimal design method of fundamental features of robot frames that are commonly used for a wide range of robots. In this formulation, some key performance metrics of the robot are estimated by a reducedorder model which is configured with beam theory. A multi-objective optimization problem is formulated to represent the trade-offs among key design parameters using a weighted-sum form for a single product. This formulation is integrated into a mini-max type optimization problem across a series of robots as an optimal design formulation for the product platform. Some case studies of optimal platform design for industrial three-axis linear-type robots are presented to demonstrate the applications of a genetic algorithm to such mathematical models.