• Knowledge Management Research
• /
• v.16 no.4
• /
• pp.69-87
• /
• 2015

Given the huge number of data produced by its users, SNS is a great source of customer insights. Since viral trends in SNS reflect customers' direct feedback, companies can draw out highly meaningful business insights when such data is effectively analyzed and managed. However, while the importance of understanding SNS big data keeps growing, the methods for analyzing atypical data such as SNS postings for business insights over product has not been well studied. This study aims to demonstrate the way to exploit topic modeling method to support marketing strategy generation and therefore leverage business process. First, we conducted topic modeling analysis for twitter data of Apple and Samsung smartphones. Then we comparatively examined the analysis results to draw meaningful market insights about each smartphone product. Finally, we draw out a strategic marketing recommendation for each smartphone brand based on the findings.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1995.04a
• /
• pp.891-895
• /
• 1995

This paper describes a solid modeling system based on a systematic description of techniques for analyzing and understanding on engineering drawings. Main stress is placed on clarifying the difference between the drawing understanding and the drawing recognition. The former, in which we feel major interest, is intrinsically a difficult problem because it inherent contains combinatorial search to require more than polynomial time. Actually, understanding drawings is regarded as a process to recover the information lost in projection 3-D objects to 2-D drawings. But, solid modeling by automatic understanding of the given drawings is one of the promising approach, which is described precisely in the text. Reviewing the studies performed so far, we summarize the future direction of the project and inevitable open problems left.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2007.05a
• /
• pp.260-264
• /
• 2007

Many load modeling concepts have been proposed in the past. Efforts of load modeling may be summarized into three approaches ; the first one is to find an aggregation of various different load components scattered and distributed in an area. The second one is to find parameters to represent load from field tests, if any. And the third one is how to present the load of motor components could be represented. This paper proposes a system identification of combined load modeling to cover the second approach. In this paper, an improved method of system identification is suggested for the combined load model (dynamic and static load model) in which parameters of the equivalent induction motor. polynomial type load and their compositions.

• Journal of the Korean Society of Combustion
• /
• v.15 no.3
• /
• pp.15-24
• /
• 2010

The purpose of this study is to assess approaches to modeling coal gasification and combustion in general purpose CFD codes. Coal gasification and combustion involve complex multiphase flows and chemical reactions with strong influences of turbulence and radiation. CFD codes would treat coal particles as a discrete phase and gas species are considered as a continuous phase. An approach to modeling coal reaction in $FLUENT^{(R)}$, selected in this study as a typical commercial CFD code, was evaluated including its devolatilization, gas phase reactions, and char oxidation, turbulence, and radiation submodels. CFD studies in the literature were reviewed to show the uncertainties and limitations of the results. Therefore, the CFD analysis gives useful information, but the results should be carefully interpreted based on understandings on the uncertainties associated with the modelings of coal gasification and combustion.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.11a
• /
• pp.162-163
• /
• 2011

This paper presents the system dynamics methodology for modeling and control the production/inventory system. Under system dynamics point of view, we can apply some production/inventory policies as if we use the control laws for dynamics systems, then the behavior of system is analyzed and evaluated to improve the performance of production/inventory system. We also utilize the hybrid modeling method for the dynamic of production system with the combination of Matlab/Simulink and Matlab/Sateflow. Finally, the numerical simulation results are carried out in Matlab/Simulink environment and compare with the results from other works. It is shown that our approach can obtain some good performances (such as operational cost, stability of inventory, customer service level).

• Proceedings of the KIEE Conference
• /
• 2006.11a
• /
• pp.282-284
• /
• 2006

In this paper, Static load models are developed using measurement based approach which is fundamental for on-line load modeling. The measurement data can be acquired from PMU(phasor measurement units). On the assumption that we have on-line measurement data, a scheme which is for Static load model capable to apply SCADA/EMS is developed. The Least Squares criterion is used for minimizing between measured and simulated data. In this manner, On-line Static load modeling algorithm can be developed. In this paper, a scheme that simple Static load model is applied for On-line load modeling is studied.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.3-8
• /
• 2001

Regarding current rapid innovations and applications of information and telecommunication technologies as well as economical requirements, modeling and simulation (M&S) plays an increasingly important role for the planning, development and operation of high-tech products and systems. M&S has to seen as a key technology for multi-facetted analysis of complex systems during their life-cycles. For reasons as accuracy, credibility and cost-effectiveness, the selection of adequate and effective M&S techniques and tools is of significant importance. Regarding these aspects, this paper summarizes the basic methodological modeling approach for effective product and system modeling. In addition, besides a classification of different basic architectures and taxonomies combining knowledge-processing and simulation techniques, the paper describes some practical implementations and experiences.

• The Journal of Information Systems
• /
• v.28 no.4
• /
• pp.271-291
• /
• 2019

Purpose The purpose of this study is to propose a methodology to derive positive keywords and negative keywords through deep learning to classify reviews into positive reviews and negative ones, and then refine the results of topic modeling using these keywords. Design/methodology/approach In this study, we extracted topic keywords by performing LDA-based topic modeling. At the same time, we performed attention-based deep learning to identify positive and negative keywords. Finally, we refined the topic keywords using these keywords as filters. Findings We collected and analyzed about 6,000 English reviews of Gyeongbokgung, a representative tourist attraction in Korea, from Tripadvisor, a representative travel site. Experimental results show that the proposed methodology properly identifies positive and negative keywords describing major topics.

• The Journal of Korean Association of Computer Education
• /
• v.10 no.2
• /
• pp.101-113
• /
• 2007

In this paper, we present an object-based modeling and language for an object-oriented spatio-temporal database system. For handling the structure of spatio-temporal objects and the spatio-temporal operators, we propose the two layers of data modeling: a spatio-temporal object model (STOM) and an spatio_temporal internal description model (STIM). We then propose STOQL, a spatio-temporal object-oriented query language. STOQL provides an integrated mechanism for the graphical display of spatial objects and the retrieval of spatio-temporal and aspatial objects.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.8 no.3
• /
• pp.42-51
• /
• 1999

An experimental modeling of cutting and structural dynamics and the on-line detection of malfunction process is substantial not only for the investigation of the static and dynamic characteristics of cutting process but also for the analytic realization of diagnostic systems. In this regard, We have discussed on the comparative assessment of two recursive time series modeling algorithms that can represent the machining process and detect the abnormal machining behaviors in precision round shape machining such as turning, drilling and boring in mold and die making. In this study, simulation and experimental work were performed to show the malfunctioned behaviors. For this purpose, two new recursive approach (REIVM, RLSM) were adopted fur the on-line system identification and monitoring of a machining process, we can apply these new algorithm in real process for the detection of abnormal machining behaviors such as chipping, chatter, wear and round shape lobe waviness.