• 한국병원경영학회지
• /
• 제17권2호
• /
• pp.21-33
• /
• 2012

Purpose : This study aims to suggest application of patients DB to hospital marketing by performing market segmentation and selecting target market. Consequently help to establish suited strategy of marketing. Method : 14,072 patients hospitalized in a University Medical Center were recruited into this study. In order to classify the customer groups, cluster analysis was used with RFM(Recency, Frequency, Monetary) model, and 1-way ANOVA verified the differences among groups. And then, sociodemographical status, healthcare utilization and diagnosis(ICD-10) of each group were compared to draw a marketing strategy. Results : Four groups were classified through clustering analysis, and'high use and high profit' and'low use and high profit' groups were selected as a target market. The features of target market were as follows, the female proportion was high; used a private room; hospitalized through the emergency room; had operation; length of stay was long; had many comorbidity and cooperative treatment. There was difference in each feature of target market: as for the'high use and high profit' group, many patients were diagnosed with 'certain infectious and parasitic diseases'; and as for the'low use and high profit'group, the proportion of patients who purchased'industrial accident compensation insurance'and'auto insurance'was relatively high; many patients were diagnosed with'Injury, poisoning and certain other consequences of external causes'. Conclusion : It is needed to establish'positioning' strategy by monitoring and communicating with'high use and high profit' group. And for the case of'low use and high profit' group, it is necessary to make a follow-up management and lead them to have a medical check-up.

• 한국조사연구학회지:조사연구
• /
• 제9권1호
• /
• pp.69-85
• /
• 2008

층화는 표본설계 단계에서 예비정보를 활용하는 대표적인 방법으로 대부분의 전국 단위의 표본설계에서 널리 활용된다. 층화의 효율을 극대화시키기 위해서는 조사목적에 부합되는 적절한 층화변수를 선택하는 것이 매우 중요하다. 하나의 표본을 통해 여러 개의 관심변수를 동시에 조사하는 다목적조사에서 다변량 층화변수가 있을 때 층화 전략을 세우는 것은 매우 복잡한 양상을 띤다. 본 연구에서는 관심변수의 수가 매우 많은 다목적조사를 위한 층화전략을 다룬다. 층화를 위해 구체적으로 사용하는 통계적 도구는 요인분석과 군집분석 등의 다변량 통계기법인데, 먼저 요인분석을 통해 적절한 층화변수들을 선정한 후 그 변수들을 이용하여 군집분석을 통해 층화를 하는 전략을 소개한다. 본 연구에서는 구체적으로 해양수산부의 어업비계통생산량조사를 위한 표본설계에서의 층화과정을 다룬다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제48권3호
• /
• pp.329-352
• /
• 2009

The purpose of this study was to investigate the effects of small group cooperative communicative activities on the strategies for estimating measurement. To do this, two research questions were set as follow: First, are there any differences between strategies employed by students in the experimental group and the control group before and after the estimating measurement activities? Second, are there any differences between strategies employed by students in different ability levels(upper, middle, lower) of pre-estimating measurement test in the experimental group? The research results were drawn from the investigation as below: First, the strategical change of before and after the estimating measurement tasks in the experimental group was quite noticeable. Unlike the small strategical change in the control group, small group cooperative communicative learning resulted in a decrease of simple memorization and guessing strategies and an increase of refined strategies such as the standard strategy, clustering, unit load and so on. Second, mathematical communicative activities in a small group cooperative learning showed that the students in the upper level of pre-estimating measurement test used more refined strategies and the students in the lower level used simple memorization and guessing strategy more frequently. And through interaction in small group, students could have chances to recognize error of strategies and to modify and learn strategies. In conclusion, small group cooperative activities allowed students to have chances to communicate mathematically and it is a efficient way of helping students learn estimating measurement strategies.

• 전기전자학회논문지
• /
• 제13권1호
• /
• pp.71-76
• /
• 2009

As one of the most important requirements for wireless sensor networks, prolonging network lifetime can be realized by minimizing energy consumption in cluster heads as well as sensor nodes. While most of the previous researches have focused on the energy of sensor nodes, we devote our attention to cluster heads because they are most dominant source of power consumption in the cluster-based sensor networks. Therefore, we seek to minimize energy consumption by minimizing the maximum(MINMAX) energy dissipation at each cluster heads. This work requires energy-efficient clustering of the sensor nodes while satisfying given energy constraints. In this paper, we present a constraint satisfaction modeling of cluster-based routing in a heterogeneous sensor networks because mixed integer programming cannot provide solutions to this MINMAX problem. Computational experiments show that substantial energy savings can be obtained with the MINMAX algorithm in comparison with a minimum total energy(MTE) strategy.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권1호
• /
• pp.48-55
• /
• 2005

Mobility of an indoor wheeled robot is affected by adhesion force that is related to various floor conditions. When the adhesion force between driving wheels and floor decreases suddenly, the robot begins slip. In order to overcome this slip problem, optimal slip velocity must be decided for stable movement of wheeled robot. First of all, this paper shows that conventional PI control can not be applied to a wheeled robot of the light weight. Secondly, proposed fuzzy logic is applied to the Takagi-Sugeno model for the configuration of fuzzy sets. For the design of Takagi-Sugeno model and fuzzy rule, proposed algorithm uses FCM(Fuzzy c-mean clustering method) algorithm. In additionally, this algorithm adjusts the driving torque for restraining re-slip. The proposed fuzzy logic controller(FLC) is pretty useful with prevention of the slip phenomena for the controller performance in the re-adhesion control strategy, These procedures are implemented using a Pioneer 2-DXE wheeled robot parameter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권7호
• /
• pp.1293-1310
• /
• 2011

A simple modification of well known Low Energy Adaptive Clustering Hierarchy (LEACH) protocol is proposed to exploit cooperative diversity. Instead of selecting a single cluster-head, we propose M cluster-heads in each cluster to obtain a diversity of order M. The cluster-heads gather data from all the sensor nodes within the cluster using same technique as LEACH. Cluster-heads transmit gathered data cooperatively towards the destination or higher order cluster-head. We propose a code combining based cooperative diversity protocol which is similar to coded cooperation that maximizes the performance of the proposed cooperative LEACH protocol. The implementation of the proposed cooperative strategy is analyzed. We develop the upper bounds on bit error rate (BER) and frame error rate (FER) for our proposal. Space time block codes (STBC) are also a suitable candidate for our proposal. In this paper, we argue that the STBC performs worse than the code combining cooperation.

• 산경연구논집
• /
• 제5권1호
• /
• pp.17-25
• /
• 2014

Purpose - Nowadays, the innovative design concept is being implemented in product design. In order to satisfy market trends and the demand for quality, designers should employ customer satisfaction questionnaires and analyze them with various experimental processes. Research design, data, and methodology - These methodologies would help designers have a better understanding of their customers and judge the market size and clustering validity, by diverse product strategies, for dealing with the rapid change prevailing in the market today. Results - By considering the innovative design with regard to telephones as an experimental case, the study investigates and demonstrates how the product can benefit from market-oriented and customized management concepts, when creative design ability is utilized for developing the product. Conclusions - Along with the benefit of having an innovative product value, the product can stimulate progress inthe development of the enterprise management, which has emerged as the main issue in the area of social and economic development in every developed country.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.30-32
• /
• 2005

Mobility of an indoor wheeled robot is affected by adhesion force that is related to various floor conditions. When the adhesion force between driving wheels and floor decreases suddenly, the robot begins slip. In order to overcome this slip problem, optimal slip velocity must be decided for stable movement of wheeled robot. First of all, this paper shows that conventional PI control can not be applied to a wheeled robot of the light weight. Secondly, proposed fuzzy logic is applied to the Takagi-Sugeno model for the configuration of fuzzy sets. For the design of Takagi-Sugeno model and fuzzy rule, proposed algorithm uses FCM(Fuzzy c-mean clustering method) algorithm. The proposed fuzzy logic controller(FLC) is pretty useful with prevention of the slip phenomena for the controller performance in the re-adhesion control strategy.

• 한국통신학회논문지
• /
• 제35권5A호
• /
• pp.417-422
• /
• 2010

본 논문에서는 무선 센서 네트워크상에서 QoS를 보장하면서 노드들의 에너지 효율을 최대화하는 다중 계층 클러스터링 기법을 제안하였다. 제안된 방법의 가장 큰 특징은 지정된 시간 내 도착성과 데이터 전송의 신뢰성 등 요구되는 QoS를 만족시키면서 노드들의 분산된 에너지 소모를 통해 전체 네트워크 수명을 증가 시킨다는데 있다. 시뮬레이션을 통해 제안된 기법은 센서 네트워크상에서 가능한 에너지를 절감하면서 데이터 패킷들의 시간 내 도착을 보장할 수 있다는 것을 확인 하였다.

• 산업공학
• /
• 제25권2호
• /
• pp.229-240
• /
• 2012

Conventional research on customer relationship management(CRM) in general has focused on the effects of individual customer's satisfaction, retention and profit management. However, corporate customers are more profitable than individual customers because of high volume and frequent transactions between companies. In this article, a prototype for a corporate customer relationship management is developed in the postal service. First, the frequency and amount of customers' usage were examined, and thereby the corporate customer rating scheme was established to provide customized service. Second, five different types of usage patterns were determined using clustering analysis. In addition, we presented the rationales behind the five types of patterns. Third, RFM(recency, frequency, monetary) analysis was performed, and then action plans were developed to increase sales. Finally, the prototype software was developed to automatically perform the above analysis using MS Excel program.