• Asia pacific journal of information systems
• /
• 제33권3호
• /
• pp.737-767
• /
• 2023

With the availability of big customer data and advances in machine learning techniques, the prediction of customer behavior at the session-level has attracted considerable attention from marketing practitioners and scholars. This study aims to predict customer purchase conversion at the session-level by employing customer profile, transaction, and clickstream data. For this purpose, we develop a multimodal deep learning fusion model with dynamic and static features (i.e., DS-fusion). Specifically, we base page views within focal visist and recency, frequency, monetary value, and clumpiness (RFMC) for dynamic and static features, respectively, to comprehensively capture customer characteristics for buying behaviors. Our model with deep learning architectures combines these features for conversion prediction. We validate the proposed model using real-world e-commerce data. The experimental results reveal that our model outperforms unimodal classifiers with each feature and the classical machine learning models with dynamic and static features, including random forest and logistic regression. In this regard, this study sheds light on the promise of the machine learning approach with the complementary method for different modalities in predicting customer behaviors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제34권4B호
• /
• pp.394-402
• /
• 2009

In this paper, we present a new analytical model for estimating the blocking performance of multi-fiber WDM networt:s with sparse and limited wavelength conversion (SLWC). The proposed model is a reduced-load approximation model that can obtain accurate estimates of blocking probability of such networks. Our model employs three new recurrence formulae to obtain the free wavelength distribution on a multi-fiber link, the free wavelength distribution after limited-range wavelength conversion and the end-to-end blocking probability of a multi-hop path, respectively. From the numerical results on the NSFNET, we demonstrate that the blocking performance of two-fiber NSFNET with three wavelength-convertible nodes, each of which translates an input wavelength to its adjacent output wavelengths, closely approximates the blocking performance of full wavelength conversion.

• Korean Journal of Mathematics
• /
• 제27권1호
• /
• pp.1-8
• /
• 2019

We will deal with an n locus model in which mutation and gene conversion are taken into consideration. Also random partitions of the number n determined by chromosomes with n loci should be investigated. The diffusion process describes the time evolution of distributions of the random partitions. In this paper, we find the probability of distribution of the diffusion process with special diffusion operator $L_1$ and we show that the average probability of genes at different loci on one chromosome can be described by the rate of gene frequency of mutation and gene conversion.

• MALSORI
• /
• 제67호
• /
• pp.167-180
• /
• 2008

This paper describes a novel spectral envelope conversion method based on Gaussian mixture model (GMM). The core of this paper is rearranging source feature vectors in input space to the transformed feature vectors in feature space for the better modeling of GMM of source and target features. The quality of statistical modeling is dependent on the distribution and the dimension of data. The proposed method transforms both of the distribution and dimension of data and gives us the chance to model the same data with different configuration. Because the converted feature vectors should be on the input space, only source feature vectors are rearranged in the feature space and target feature vectors remain unchanged for the joint pdf of source and target features using KPCA. The experimental result shows that the proposed method outperforms the conventional GMM-based conversion method in various training environment.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• 제18권4호
• /
• pp.83-87
• /
• 2004

In this paper, an electrical equivalent circuit is derived by solving system equations. A frequency characteristics graph is calculated and the characteristics curve of the linear Actuator Model System are simulated by the Matlab program The frequency characteristics of a linear actuator are analyzed on the structure of the linear Actuator Model System This paper proposed and analyzed the linear Actuator Model(LAM) by using Matlab program with linear actuator was verified computer simulation based on the energy conversion theory.

• Women's Health Nursing
• /
• 제17권4호
• /
• pp.328-336
• /
• 2011

Purpose: The purpose of this study is to develop the optimal nursing fee for nurse-midwifery center (MC) in the national health insurance system. Methods: The three methodologies used to calculate the conversion factors for the MCs in the national health insurance include cost accounting method, sustainable growth rate (SGR) model, and index model. In this study, the macro-economic indicators and the national statistics were used to estimate the conversion factors for the MCs. Results: The optimal nursing fee for the MCs in 2011 was estimated to be an increase of 57.7% by cost accounting analysis, a decrease of 17.1% by SGR model, and a decrease of 16.1% by index model. The results from SGR model and index model could had been biased due to the upswing of medical spendings in the short-term period (2008~2009). A sensitivity analysis of pre-delivery subsidy program for OB & GYN hospitals and clinics showed that the program has substantially diminished the demand for the MC services. Conclusion: More reliable methodologies to estimate nursing fees precisely are required to prove the value of nurses' services and a government subsidy program for the MC services should be followed from a social perspective.

• The Journal of the Acoustical Society of Korea
• /
• 제27권2호
• /
• pp.92-101
• /
• 2008

To dissolve the multi-layered model problems, and to complement 2-layered model's simplicity, assumed fluid-fluid-solid 3-layered model. Generally it is known that if the sediment thickness is more than 10 wavelength, the half space's influence to the in-water acoustic field could be disregarded. By tracking the maximum correlation coefficient of calculated results and experimental ones we confirmed that the requirement could be more realized. To calculate the maximum correlation coefficient we used single sensor transmission loss. On the assumption that the sediment sound velocity was 1813 m/s and frequency range 50 kHz to 120 kHz, the conversion condition was from 2.5 to 7.7 wavelength.

• 한국연소학회:학술대회논문집
• /
• 한국연소학회 1999년도 제19회 KOSCO SYMPOSIUM 논문집
• /
• pp.139-148
• /
• 1999

In oder to analyze the effect of operating conditions on pulverized coal combustion, a numerical study is conducted at the pulverized coal combustor. Eulerian approach is used for the gas phase, whereas Lagrangian approach is used for the particle phase. Turbulence is modeled using standard ${\kappa}-{\varepsilon}$ model. The description of species transport and combustion chemistry is based on the mixture fraction/probability density function(PDF) approach. Radiation is modeled using P-l model. The turbulent dispersion of particles is modeled using discrete random walk model. Swirl number of secondary air affects the flame front, particle residence time and carbon conversion. Primary/Secondary air mass ratio also affects the flame front but little affects the carbon conversion and particle residence time. Air-fuel ratio only affects the flame front due to lack of oxygen. Radiation strongly affects the flame front and gas temperature distribution because pulverized coal flame of high temperature is considered.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• 제16권1호
• /
• pp.33-39
• /
• 2005

Complex permittivities of material in a wide bandwidth are measured by using an open-ended coaxial probe. To obtain a confident complex permittivity profile, the accuracy of measured reflection coefficients and the stability of the conversion model should be guaranteed in advance. In this paper, the sensitivity of our conversion model is analyzed by employing two instruments with different uncertainties. And various factors effected on the accuracy of measured reflection coefficients are investigated in experiment.

• Journal of Ocean Engineering and Technology
• /
• 제22권2호
• /
• pp.1-6
• /
• 2008

Recently Oscillating Water Column (OWC) plants have been widely employed in wave energy conversion applications. It is necessary to investigate the chamber and optimize its shape parameters for maximizing air flow and energy conversion due to wave conditions. A 2D numerical wave tank based on a Fluent and VOF model is developed to generate the incident waves and is validated by theoretical solutions. The oscillating water column motion in the chamber predicted by the numerical method is compared with the available experimental data. Several geometric scales of the chamber are calculated to investigate the effect of the shape parameters on the oscillating water column motion and wave energy conversion.