• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.325-345
• /
• 2023

In the rapidly evolving domain of e-commerce, our study presents a cohesive approach to enhance customer satisfaction prediction from online reviews, aligning methodological innovation with practical insights. We integrate the RFE-SHAP feature selection with LDA topic modeling to streamline predictive analytics in e-commerce. This integration facilitates the identification of key features-specifically, narrowing down from an initial set of 28 to an optimal subset of 14 features for the Random Forest algorithm. Our approach strategically mitigates the common issue of overfitting in models with an excess of features, leading to an improved accuracy rate of 84% in our Random Forest model. Central to our analysis is the understanding that certain aspects in review content, such as quality, fit, and durability, play a pivotal role in influencing customer satisfaction, especially in the clothing sector. We delve into explaining how each of these selected features impacts customer satisfaction, providing a comprehensive view of the elements most appreciated by customers. Our research makes significant contributions in two key areas. First, it enhances predictive modeling within the realm of e-commerce analytics by introducing a streamlined, feature-centric approach. This refinement in methodology not only bolsters the accuracy of customer satisfaction predictions but also sets a new standard for handling feature selection in predictive models. Second, the study provides actionable insights for e-commerce platforms, especially those in the clothing sector. By highlighting which aspects of customer reviews-like quality, fit, and durability-most influence satisfaction, we offer a strategic direction for businesses to tailor their products and services.

• ETRI Journal
• /
• v.36 no.1
• /
• pp.1-11
• /
• 2014

In this paper, we propose a distributed synchronization algorithm for wireless mesh networks based on orthogonal frequency division multiple access. For time and frequency synchronization, a node requests its neighbor nodes for a change of fast Fourier transform starting points, transmission times, and carrier frequencies needed for synchronization. The node also updates its own time and frequency elements through simple formulas based on request messages received from neighbor nodes using a guard interval and a cyclic prefix. This process with the cooperation of neighbor nodes leads to a gradual synchronization of all nodes in the network. Through a performance comparison with a conventional scheme, we obtain simulation results indicating that the proposed scheme outperforms the conventional scheme in random topologies and a grid topology.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.15 no.8 s.101
• /
• pp.924-930
• /
• 2005

Sound absorptive materials have good performance in high frequency range, not at low frequencies. Therefore it has been great challenge to develop a sound absorbing structure that is good at low frequency. We propose to use a Helmholtz resonator array panel for this purpose. A Helmholtz resonator is one of noise control elements widely used in many practical applications. The resonator is a simple structure composed of a rigid-walled cavity with a neck, but it has very high performance at resonance frequency. This paper discusses the sound absorption of Helmholtz resonator array panels at normal and random incidence. First, various experimental results are introduced and studied. Secondly, we theoretically predict the absorptive characteristics of the resonator away panel. The theoretical approach is based on the Fourier analysis for a periodic absorber. We believe that this method can be used to design a panel for low frequency noise control.

• Korean Management Science Review
• /
• v.17 no.2
• /
• pp.175-187
• /
• 2000

The stochastic vehicle routing problem (VRP) is a problem of growing importance since it includes a reality that the deterministic VRP does not have. The stochastic VRP arises whenever some elements of the problem are random. Common examples are stochastic service quantities and stochastic travel times. The solution methodologies for the stochastic VRP are very intricate and regarded as computationally intractable. Even heuristics are hard to develope and implement. On possible way of solving it is to apply a solution for the deterministic VRP. This paper presents a performance evaluation of four simple heuristic for the deterministic VRP is a stochastic environment. The heuristics are modified to consider the time window constraints. The computational results show that some of them perform very well in different cases of the stochastic VRP.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1995.10a
• /
• pp.672-675
• /
• 1995

Because of a sudden growth of the research of fatigue failure, recent machines or structures have been designed by damage tolerance design in many fields. Consequently, it is the most primary factor to clarity the specific character of fatique failure in the design of machines or structures considering reliability. A statistical analysis is required to analyze the outcome of an experiment or a life estimate by reason of that fatigue failure contains lots of random elements. Reliability analysis which has tukenn the place of the existing analyses in the consideration of the uncertainty of a material, is a very efficient way. Even reliability analysis, however, is not a perfect way to analyses the uncertainties of all the materials. This thesis would refer to a newly conceived data analysis that the coefficient of a system could cause the ambiguity of the relationship of an input and output.

• IE interfaces
• /
• v.25 no.3
• /
• pp.309-318
• /
• 2012

Forecasting probability or likelihood of technology development success has been a crucial factor for critical decisions in technology management such as R&D project selection and go or no-go decision of new product development (NPD) projects. This paper proposes an analytic network process (ANP) approach to forecasting of technology development success. Reviewing literature on factors affecting technology development success has constructed the ANP model composed of four criteria clusters : R&D characteristics, R&D competency, technological characteristics, and technological environment. An alternative cluster comprised of two elements, success and failure is also included in the model. The working of the proposed approach is provided with the help of a case study example of MRAM (magnetic random access memory) technology.

• Structural Engineering and Mechanics
• /
• v.8 no.4
• /
• pp.401-410
• /
• 1999

A method of optimum design based on reliability for antenna structures is presented in this paper. By constructing the equivalent event, the formula is derived for calculating the reliability of reflector accuracy of antenna under the action of random wind load. The optimal model is developed, in which the cross sectional areas of member are treated as design variables, the structure weight as objective function, the reliability of reflector accuracy and the strength or stability of structural elements as constraints. The improved accelerated convergence gradient algorithm developed by the author is used. The design results show that the method in this paper is feasible and effective.

• Journal of Biomedical Engineering Research
• /
• v.8 no.2
• /
• pp.171-176
• /
• 1987

Wiener filtering method was applied to the dual energy imaging procedure in digital radiography(D.R.). A linear scanning photodiode arrays with 1024 elements(0.6mm H 1.3mm pixel size) were used to obtain chest images in 0.7 sec. For high energy image acquisition, X-ray tube was set at 140KVp, 100mA with a rare-earth phosphor screen. Low energy image was obtained with X-ray tube setting at 70KVp, 150mA. These measured dual energy images are represented in the vector matrix notation as a linear discrete model including the additive random noise. Then, the object images are restored in the minimum mean square error sense using Wiener filtering method in the transformed domain. These restored high and low energy images are used for computation of the basis image decomposition. Then the basis images are linearly combined to produce bone or tissue selective images. Using this process, we could improve the signal to noise ratio characteristics in the material selective images.

• Journal of the Korean Society for Railway
• /
• v.11 no.1
• /
• pp.75-80
• /
• 2008

Human factors still play a significant part in many railway accidents. It is well blown that SPAD (Signal Passed at Danger) remains as the single most cause of railway accidents. In this study a stochastic model is developed to quantify SPAD human reliability. This model provides closed-form mathematical expressions into which multiple factors affecting the reliability of man-machine systems can be incorporated. Two basic elements are combined to form the framework for modeling: random signal occurrence and transient human performance characteristics.

• Journal of the Korean housing association
• /
• v.14 no.1
• /
• pp.77-86
• /
• 2003

The purpose of this study is to set up a model of affective evaluation to structurally and systematically analyse subjective affective expressions of human beings with regard to the residential environment and to analyse the correlation between affective responses of residents and physical elements by positively applying the model to the evaluation of outdoor space of apartment complexes as an area of study on evaluation of residential environment. The area for evaluation was limited to three apartment complexes situated in Daegu, and the subjects for evaluation were also limited to a group of residents(housewives) living at the three apartment complexes. The research method is summarized as follows. 214 affective words(adjective phrases) expressing outdoor space of apartments were selected from literature on random sampling basis, and reduced to 25 ones through factor analysis. Then, these 25 words were systematized by an affective evaluating scale with 7 categories of meaning. The evaluation was conducted with 324 homemakers living at the apartment complexes selected for evaluation from September 29, 2000 to October 5, 2000. SPSSWIN, a statistical program was used for analysis.