• Computational Structural Engineering
• /
• v.35 no.1
• /
• pp.25-34
• /
• 2022

• Journal of Intelligence and Information Systems
• /
• v.9 no.3
• /
• pp.23-47
• /
• 2003

Traditional studies for customer relationship management (CRM) generally focus on static CRM in a specific time frame. The static CRM and customer behavior knowledge derived could help marketers to redirect marketing resources fur profit gain at that given point in time. However, as time goes, the static knowledge becomes obsolete. Therefore, application of CRM to an online retailer should be done dynamically in time. Customer-based analysis should observe the past purchase behavior of customers to understand their current and likely future purchase patterns in consumer markets, and to divide a market into distinct subsets of customers, any of which may conceivably be selected as a market target to be reached with a distinct marketing mix. Though the concept of buying-behavior-based CRM was advanced several decades ago, virtually little application of the dynamic CRM has been reported to date. In this paper, we propose a dynamic CRM model utilizing data mining and a Monitoring Agent System (MAS) to extract longitudinal knowledge from the customer data and to analyze customer behavior patterns over time for the Internet retailer. The proposed model includes an extensive analysis about a customer career path that observes behaviors of segment shifts of each customer: prediction of customer careers, identification of dominant career paths that most customers show and their managerial implications, and about the evolution of customer segments over time. furthermore, we show that dynamic CRM could be useful for solving several managerial problems which any retailers may face.

• Journal of Industrial Technology
• /
• v.10
• /
• pp.3-8
• /
• 1990

This paper presents a linear state feedback control approach to the stabilization of discrete-time uncertain systems with bounded uncertain parameters. The approach is based on the LQ(linear quadratic) regulator theory and Lyapunov's stability analysis. Asymptotically stable behavior is guaranteed in the presence of parameter uncertainties, and the upper bound of the performance index is determined.

• Korean Journal of Community Nutrition
• /
• v.18 no.5
• /
• pp.429-441
• /
• 2013

This study was conducted to examine the interrelations among snack preference, purchasing behavior and intake of fifth and sixth grade students in elementary schools in Gyeongnam province. Frequency of snack intake was the highest in those who reported 'once a day' (45.6%) snack habit. Longer-time television viewers also showed higher frequency of snack intake than shorter-time viewers. Thirty-three percent of students purchased snacks by themselves and the frequency of snack purchasing had a significant positive relationship with TV watching time (p < 0.01). The main reason, place and time of eating snacks were 'hunger' (79.2%), their home environment (50.9%) and 'after school hours' (89.7%). The favorite snack was 'ice cream' and, this snack habit was significantly different by gender of the child (p < 0.01) and TV watching time (p < 0.01). 'Milk and dairy products' scored highest (3.47) in snack intake frequency among longer-time TV viewers (> 2hr) compared to shorter-time TV viewers and this difference was statistically significant (p < 0.001). The snack preference score was correlated positively (r = 0.454) with the intake frequency for snack and its explanation power ($R^2$) was 20.5%. With regard to snack purchase behaviors, the scores of 'checking the expiration date' and 'comparing the price with similar products' were high (in what group?). Female students (p < 0.001) and shorter-time TV viewers (< 2hr) (p < 0.01) had a more reasonable purchasing behavior. The total score of preference was significantly higher (p < 0.05) in shorter-timeTV viewers (< 2hr). In the correlation between snack purchasing behaviors and intake frequency, attractiveness (r = 0.208, p < 0.001) and preference (r = 0.330, p < 0.001) showed significant positive correlations. The result of regression analysis, preference only was selected ($R^2$= 0.108).

• Management Science and Financial Engineering
• /
• v.8 no.2
• /
• pp.1-20
• /
• 2002

This paper presents a model that analyzes the impact of uncertainties in demand and processing times on the production lead time of a Kanban system. We consider the waste associated with under-production as well as over-production when we measure the production lead time. We set up an optimization model to minimize the production lead time. A simple heuristic procedure is developed to determine solutions in terms of the size of containers and the number of Kanban cards. In addition, we numerically examine the behavior of the optimal Kanban system.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.11
• /
• pp.503-510
• /
• 1986

A new algorithm based on the concept of prediction error minimization is suggested to estimate the time varying delay in discrete processes. In spite of the existence of the stochastic noise, this algorithm can estimate time varying delay accurately. Computation time of this algorithm is far less than that of the previous extended parameter methods. With the use of this algorithm, generalized minimum variance control shows good control behavior in simulations.

• Journal of the Chungcheong Mathematical Society
• /
• v.33 no.4
• /
• pp.445-468
• /
• 2020

A long-time behavior of global solutions for a dispersive-dissipative equation with time-dependent damping terms is investigated under null Dirichlet boundary condition. By virtue of an appropriate new Lyapunov function and the Lojasiewicz-Simon inequality, we show that any global bounded solution converges to a steady state and get the rate of convergence as well, when damping coefficients are integrally positive and positive-negative, respectively. Moreover, under the assumptions on on-off or sign-changing damping, we derive an asymptotic stability of solutions.

• Applied Chemistry for Engineering
• /
• v.10 no.5
• /
• pp.690-695
• /
• 1999

An experimental study for mesophase pitch prepared from coal tar pitch has been carried out to clarify the rheological behaviors in the molten state. The apparent viscosity, shear stress, shear rate, Qunoline insoluble(QI), and softening point(SP) change were investigated especially. The conditions to increase mesophase content during polymerization were heat treatment time of 5 hrs, catalyst concentration of 3% and reaction temperature of $420^{\circ}C$. Apparent viscosity change with increase in temperature of pitches was different according to the heat treatment conditions and apparent viscosity increased with increasing heat treatment temperature, heat treatment time, contents of mesophase, on the contrary, fluidity is decreased. Rheological behavior of molten mesophase pitches at about $270^{\circ}C$ showed Newtonian behavior below $375^{\circ}C$ and non-Newtonian behavior above $270^{\circ}C$, the flow behavior was analyzed with Casson model.

• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.219-229
• /
• 1990

The compression creep behavior of grains when loaded depends not only on load but also on duration of load application. The most common methods of studying the load-time characteristics of agricultural products is by employing rheological models such as Burger's model. However it is sometimes not sufficient to describe the viscoelastic behavior of grains to be Burger's model. For this reason, this study was conducted to develop the rheological model which represented the creep compliance response of the rough rice kernel and was a function of initial stress applied and time. The effects of the initial stress applied and the moisture content on the compression creep behavior of the rough rice kernel were analyzed. The results were obtained from the study as follows: 1. Since the viscoelastic behavior of the rough rice kernel was nonlinear, the transient and steady state creep compliance was satisfactorily modelled as follows: $$J({\sigma},t)=A{\sigma}^B[C+Dt-exp(-Ft)]$$ But, for the every stress applied, the compression creep behavior of the samples tested can be well described by Burger's model respectively. 2. The creep compliance, the instantaneous elastic strain, the retarded elastic strain and the viscous strain of the sample tested generally increased in magnitude with increasing the applied initial stress and the moisture content used in the tests. At low moisture content, the creep compliance for the Japonica-type rough rice kernel Was a little higher than those for Indica-type and at high moisture content, vice versa at high moisture content. 3. The retardation times of the samples had not an uniform tendency by the initial stress and the moisture content. The retardation times ranged from 0.66 to 6.76 seconds, and the creep progressed from transient to steady state at a relatively high rate. 4. The less viscous strain than the instantaneous elastic strain for the samples tested indicated that rough rice kernel behaved as a viscoelastic body characterized by elasticity than viscosity.

• Fashion & Textile Research Journal
• /
• v.7 no.6
• /
• pp.624-632
• /
• 2005

The purpose of this study was to examine the consumers' purchasing behavior of budget-priced cosmetics according to the shopping orientation. Questionnaires used for this study were composed of 57 questions including 21 questions about cosmetic shopping orientation, 32 questions about budget-priced cosmetic purchasing behavior and four questions about demographic variables. Questionnaires were administrated to 20 to 49 aged 317 women who have shopping experience on budget-priced cosmetics. Data were analyzed by using factor analysis, cluster analysis, ANOVA, ${\chi}^2$-test, correlation, crosstabulation analysis, and scheffe test utilizing SPSS/WIN. The results were as follows. First, shopping orientation of cosmetics were classified into 5 factors: 'interest and impulsive purchasing tendency', 'price-oriented purchasing tendency', 'ration-oriented purchasing tendency', 'famous brand-oriented purchasing tendency' and 'brand royalty- oriented purchasing tendency'. According to the shopping orientation of cosmetics, the respondents were classified into 4 groups: 'passive shopping group', 'rational shopping group', 'active shopping group', 'neutral shopping group'. Second, when comparing each group's purchasing behavior of budget-priced cosmetics with shopping orientation of cosmetics, there was not significant difference in one time purchasing cost and the number of shop visits. In case of demographic variables concerning purchasing behavior of budget-priced cosmetics, there was significant differences in one time purchasing cost according to age, level of education and employment status. The number of shop visits had also difference according to age, level of education and monthly family income. Based on these results, marketing strategies for demographic characteristics of target market rather than the shopping orientation are needed.