• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• 품질경영학회지
• /
• 제30권4호
• /
• pp.15-25
• /
• 2002

This paper considers supplier selection process for e-business & ISO 9001 quality management system environments. Determining suitable suppliers in the electronic commerce has become a key strategic consideration. However, the nature of these decisions is usually complex and unstructured. In this paper, a Quality Estimated Supplier Selection (QESS) model is proposed to deal with the supplier selection problems in the e-business(Business to Business: B to B). In the supplier selection, quality management factors will be considered for the first time, and then price, and delivery etc. In the first level, we deal with the quality management factors such as quality management audit, product test, engineering man-power, capability index and training time etc., based on the five point scale. In the second level, a QESS model determines the final solution by considering factors such as price, production lead-time and delivery time.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 하계종합학술대회 논문집(2)
• /
• pp.459-462
• /
• 2004

In this paper, we present a reducing power consumption of a scheduling for module selection under the time constraint. A a reducing power consumption of a scheduling for module selection under the time constraint execute scheduling and allocation for considering the switching activity. The focus scheduling of this phase adopt Force-Directed Scheduling for low power to existed Force-Directed Scheduling. and it constructs the module selection RT library by in account consideration the mutual correlation of parameters in which the power and the area and delay. when it is, in this paper we formulate the module selection method as a multi-objective optimization and propose a branch and bound approach to explore the large design space of module selection. Therefore, the optimal module selection method proposed to consider power, area, delay parameter at the same time. The comparison experiment analyzed a point of difference between the existed FDS algorithm and a new FDS_RPC algorithm.

• 대한안전경영과학회지
• /
• 제5권1호
• /
• pp.69-82
• /
• 2003

The sequence which minimizes overall utility work in car assembly lines reduces the cycle time, the number of utility workers, and the risk of conveyor stopping. This study suggests mathematical formulation of the sequencing problem to minimize overall utility work, and present a genetic algorithm which can provide a near optimal solution in real time. To apply a genetic algorithm to the sequencing problem in car assembly lines, the representation, selection methods, and genetic parameters are studied. Experiments are carried out to compare selection methods such as roullette wheel selection, tournament selection and ranking selection. Experimental results show that ranking selection method outperforms the others in solution quality, whereas tournament selection provides the best performance in computation time.

• 대한산업공학회지
• /
• 제36권3호
• /
• pp.164-175
• /
• 2010

In this study, we developed a genetic algorithm to find a near optimal solution of concurrent spare parts selection for the operational time period with limited information of weapon systems purchased from overseas. Through the analysis of time profiles related with system operations, we first define the optimization goal which maintains the expected system operating rate under the budget restrictions, and the number of failures and the lead time for each spare part are used to calculate the estimated total down time of the system. The genetic algorithm for CSP selection shows that the objective function minimizes the estimated total down time of systems with satisfying the restrictions. The method provided by this study can be applied to the generalized model of CSP selection for the systems purchased from overseas without provision of their full structure and adequate information.

• 지능정보연구
• /
• 제4권1호
• /
• pp.1-10
• /
• 1998

Process planning is a very complex task and requires the dynamic informatioon of shop foor and market situations. Process plan selection is one of the main problems in the process planning. In this paper, we propose a new process plan selection model considering operation flexibility for the computer aided process planing. The model is formulated as a 0-1 integer programming considering realistic shop factors such as production volume, machining time, machine capacity, transportation time and capacity of tractors such as production volume, machining time, machine capacity, transportation time capacity of transfer device. The objective of the model is to minimize the sum of the processing and transportation time for all parts. A genetic algorithm a, pp.oach is developed to solve the model. The efficiency of the proposed a, pp.oach is verified with numerical examples.

• 한국기술혁신학회:학술대회논문집
• /
• 한국기술혁신학회 2002년도 추계학술대회
• /
• pp.45-57
• /
• 2002

Since a new entrant in the telecommunications market requires time in order to construct its own network, a requirement on the incumbent operator to implement carrier selection and pre-selection can enable a new entrant to immediately attract customers and earn revenue. Carrier selection can normally be accomplished in two ways, on a call-by-call basis or through carrel pre-selection. Call-by-call selection allows customers to choose a new entrant rather than the incumbent carrier using a specific code designated to the new carrier each time a call is made. Carrier Pre-Selection, on the other hand, allows customers directly connect to the network of one provider to have access automatically to another company's services when they pick up the phone to make certain types of calls. The carrier pre-selection option is generally considered to be a second regulatory step following the implementation of the call-by-call carrier selection option. Carrier pre-selection with the ability to override on a call-by-call basis for long distance, international, local, and fixed-to-mobile calls has now been implemented in many EU countries. This paper attempts to identify the issues in introducing CPS and to draw policy implications from other countries' experiences.

• 한국전자거래학회지
• /
• 제17권1호
• /
• pp.53-74
• /
• 2012

본 연구에서는 비즈니스 프로세스 관리(Business Process Management, BPM) 환경에서 자원의 성능에 영향을 미치게 되는 여러 요소를 고려하여 인적자원을 선택하는 방법론을 개발한다. 스케줄링에 있어서 자원의 선택 문제는 작업 수행도에 직접적인 영향을 미치기 때문에 중요한 문제로 인식되어져 왔다. 비록 많은 문제에 있어서 전통적인 자원선택 방법론이 의미를 가져왔으나, 인적자원을 다루는데 있어서는 가장 좋은 방법론이라고 볼 수 없다. 인적자원은 작업부하, 작업소요시간, 작업간 시간 등의 다양한 요소에 의해서 영향을 받는 특이한 요소이며 본 연구는 이러한 다양한 요소를 고려하여 작업자를 선택하는 방법론을 제시한다. 이를 위해서 베이지안 네트워크를 사용하며, 앞서 기술한 여러 요소들을 한꺼번에 고려하기 위한 베이지안 선택규칙(Bayesian Selection Rule, BSR)을 도입하였다. 또한, 시뮬레이션을 통해서 본 연구에서 개발된 방법론이 대기시간, 작업수행시간과 사이클 타임을 줄일 수 있음을 보였다.

• Journal of Information Processing Systems
• /
• 제2권2호
• /
• pp.67-75
• /
• 2006

In order to acquire a precise and quick response to an analytical query, proper selection of the views to materialize in the data warehouse is crucial. In traditional view selection algorithms, all relations are considered for selection as materialized views. However, materializing all relations rather than a part results in much worse performance in terms of time and space costs. Therefore, we present an improved algorithm for selection of views to materialize using the clustering method to overcome the problem resulting from conventional view selection algorithms. In the presented algorithm, ASVMRT (Algorithm for Selection of Views to Materialize using Reduced Table), we first generate reduced tables in the data warehouse using clustering based on attribute-values density, and then we consider the combination of reduced tables as materialized views instead of a combination of the original base relations. For the justification of the proposed algorithm, we reveal the experimental results in which both time and space costs are approximately 1.8 times better than conventional algorithms.

• Communications for Statistical Applications and Methods
• /
• 제25권6호
• /
• pp.591-604
• /
• 2018

The accelerated failure time (AFT) model is a linear model under the log-transformation of survival time that has been introduced as a useful alternative to the proportional hazards (PH) model. In this paper we propose variable-selection procedures of fixed effects in a parametric AFT model using penalized likelihood approaches. We use three popular penalty functions, least absolute shrinkage and selection operator (LASSO), adaptive LASSO and smoothly clipped absolute deviation (SCAD). With these procedures we can select important variables and estimate the fixed effects at the same time. The performance of the proposed method is evaluated using simulation studies, including the investigation of impact of misspecifying the assumed distribution. The proposed method is illustrated with a primary biliary cirrhosis (PBC) data set.