Byung Do Chung

Design for a tandem AGV system with two-load AGVs

Abstract The tandem AGV system is obtained by partitioning all workstations into multiple zones. Then, a single vehicle is assigned to each zone. In this paper, we present an analytical model to design a tandem AGV system with two-load AGVs. The analytical model is obtained by performing a design procedure which consists of two steps, ‘selection of feasible zones’ and ‘selection of final guide path.’ A numerical example is presented to show the design procedure.

A hybrid genetic algorithm with two-stage dispatching heuristic for a machine scheduling problem with step-deteriorating jobs and rate-modifying activities

Abstract This article is concerned with a single machine scheduling problems that integrate by step-deterioration along with multiple rate-modifying activities (RMAs). The actual processing time of a job is defined by a step function of its starting time and a specific deterioration threshold. The starting rate of the actual processing time of jobs is restored through the application of RMAs, which recover the original processing time. In this scheduling environment, we simultaneously determine the schedule of step-deteriorating jobs and the number and positions of RMAs to minimize the makespan. We derive a mixed integer programming model to obtain the optimal solution and propose a hybrid genetic algorithm with a two-stage dispatching heuristic represented by a simple chromosome. The performance of the proposed genetic algorithm (GA) is compared with GAs with two types of chromosome representations using randomly generated test instances.

User Satisfaction and Retention of Mobile Telecommunications Services in Korea

Abstract Since the introduction of smartphones in South Korea, users have shown quick and positive responses to them. This study explores issues in user satisfaction and develops strategies for user retention of a specific mobile telecommunications service provider in Korea. We presented a face-to-face questionnaire to 4398 participants representing nationwide characteristics of Korean users. Mobile telecommunications services and features were divided into two factors based on benefit segmentation and were analyzed with user profiling. Users’ responses to mobile telecommunications services were characterized as “Fundamental services and functions,” which meet users’ basic and traditional expectations for a smartphone as a communication and media tool, and “Cost and monetary benefits,” which mobile telecommunications providers offer to attract users. Based on the scores for those two factors, we divided respondents into five groups and addressed their characteristics in terms of demographic features, subscription duration, and factors that influence user satisfaction. The results of our analysis suggest strategies mobile communications providers can develop for each segment to promote high satisfaction and increase user retention. To improve satisfaction levels, relatively more efforts need to be invested in the fundamental services and functions.

Incorporating receiver operating characteristics into naive Bayes for unbalanced data classification

Naive Bayesian classification has been widely used in data mining area because of its simplicity and robustness to missing values and irrelevant attributes. However, naive Bayes classifiers sometimes show poor performance due to their unrealistic assumption that all attributes are equally important and conditionally independent of each other. In this research, we dispense with the former assumption by proposing a new attribute weighting method. The proposed method considers each attribute as a single classifier and measures its discriminating ability using the area under an ROC curve (AUC). Each AUC value is then used to weight the corresponding attribute. In addition, we try to reduce the complexity of classification models by selecting high AUC attributes. Using 20 real datasets from the machine learning repository at UC Irvine (UCI), we conduct a numerical experiment to show that the proposed method is an improvement over standard naive Bayes classification and existing weighting methods.

Affinely Adjustable Robust Model for Multiperiod Production Planning Under Uncertainty

Demand forecasting is an important factor in production planning, but future demand is not easy to forecast in practice. We consider a multiperiod, multiproduct production planning problem under demand uncertainty with constrains for raw materials, manufacturing capacity, and inventory. Under the assumption that probability distribution of demand is not available, two types of robust optimization models are proposed. First, a robust counterpart is developed to determine the here-and-now decision. Next, an affinely adjustable robust counterpart is developed to determine the wait-and-see decisions by approximating a robust solution with a linear decision rule. The robust models find an optimal solution that is always feasible and less sensitive against all realized demand within a given uncertainty set, in order to minimize production, procurement, inventory, and lost sales costs even in the worst case. Numerical studies demonstrated that, without knowing probability distribution of future demand, the affinely adjustable robust counterpart approach could outperform the robust counterpart and deterministic model in terms of the average cost, the standard deviation of the realized cost, and the worst-case scenario cost. The proposed method is much better than the others, especially when penalty cost due to lost sales is high and unknown demand is left skewed.

Effects of Perceived Usability and Aesthetics on Emotional Responses in Different Contexts of Use

In understanding user experience issues, it is necessary to consider contextual features in user interaction with an application. The present study aims to examine the differences among applications with difference contexts of use (perceived type: interaction styles based on use purposes) in terms of the relationships between user perception (perceived usability and perceived aesthetics) and emotion (valence and arousal). A study was performed using 15 existing websites from various domains. From the responses of participants, the relationships between perceived usability and emotional valence were found to differ according to perceived type, but those between perceived aesthetics and emotional valence were not. On the other hand, sufficient reliability for the arousal items was not secured. Through the meaningful categorization of arousal into two factors (negative and positive), significant differences in the relationships between perceived usability/aesthetics and emotional arousal could be found. Implications of the findings are discussed in the connection of contextual/design features, perceptual characteristics, and emotional responses in the development of interactive applications.

A robust optimization approach for an artillery fire-scheduling problem under uncertain threat

Abstract In this study, the determination of an artillery firing sequence is considered in order to minimize the enemy threat to friendly forces prior to the conclusion of the firing operation. A deterministic model and robust counterpart are developed to deal with the deterministic and uncertain enemy threat levels, respectively. In both cases, the optimal strategy is demonstrated to be firing based on the threat removal rate per unit time. Moreover, a two-phase approach is developed based on the concept of cardinality-constrained uncertainty. In this approach, the firing sequence is determined in the first phase and then, in the second phase, the robustness of the uncertain factors is adjusted by using the modified problem to evaluate the total threat exposure of friendly units to the enemy. A set of problems is generated and tested using the proposed model and strategy. The results of numerical experiments demonstrate that the proposed strategy outperforms conventional fire-scheduling approaches. Additionally, the price of robustness is considered by adjusting the value of uncertain factors.

Lessons from the history of Samsung’s SCM innovations: focus on the TQM perspective

The purpose of this paper is to provide some lessons learned from the implementation of supply chain management (SCM) innovation in the Samsung Group, arguably the most successful globaliser in South Korea. Our case study allows direct observation of the field, which would be particularly suitable for approaching several managerial functions combined together towards successful SCM performance. There have been some distinguished factors of success such as innovation-oriented leadership and culture, customer-focused product innovation and globalisation, speed-focusing strategy, and closed-loop sales and operations planning and Six Sigma. The experiences in a single company may not fully cover those that could have been made in other successful firms. However, it is expected that Samsung’s success in SCM innovation caused several meaningful ramifications for those interested and the results of this work provide useful implications in this respect.