• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.6
• /
• pp.289-294
• /
• 2014

In the recent enterprises and are utilizing the CRM using data mining techniques and new marketing plan. However, data mining techniques are necessary expertise, general public access is difficult, it will be subject to constraints of time and space. in this paper, in order to solve this problem, we have proposed a Mobile CRM applying the data mining method. Thus, to analyze the structure of an existing CRM system, and defines the data flow and format. Also, define the process of the system, was designed sales trend analysis algorithm and customer sales recommendation algorithm using data mining techniques. Evaluation of the proposed system, through the test scenario to ensure proper operation, it was carried out the comparison and verification with the existing system. Results of the test, the value of existing programs and data matches to verify the reliability and use queries the proposed statistical tables to reduce the analysis time of data, it was verified rapidity.

• Earthquakes and Structures
• /
• v.17 no.2
• /
• pp.175-189
• /
• 2019

The aim of the study is to show the results of complex shaking table experimental investigation focused on the response of two models of cylindrical steel tanks under mining tremors and moderate earthquakes, including the aspects of diagnosis of structural damage. Firstly, the impact and the sweep-sine tests have been carried out, so as to determine the dynamic properties of models filled with different levels of liquid. Then, the models have been subjected to seismic and paraseismic excitations. Finally, one fully filled structure has been tested after introducing two different types of damages, so as to verify the method of damage diagnosis. The results of the impact and the sweep-sine tests show that filling the models with liquid leads to substantial reduction in natural frequencies, due to gradually increasing overall mass. Moreover, the results of sweep-sine tests clearly indicate that the increase in the liquid level results in significant increase in the damping structural ratio, which is the effect of damping properties of liquid due to its sloshing. The results of seismic and paraseismic tests indicate that filling the tank with liquid leads initially to considerable reduction in values of acceleration (damping effect of liquid sloshing); however, beyond a certain level of water filling, this regularity is inverted and acceleration values increase (effect of increasing total mass of the structure). Moreover, comparison of the responses under mining tremors and moderate earthquakes indicate that the power amplification factor of the mining tremors may be larger than the seismic power amplification factor. Finally, the results of damage diagnosis of fully filled steel tank model indicate that the forms of the Fourier spectra, together with the frequency and power spectral density values, can be directly related to the specific type of structural damage. They show a decrease in the natural frequencies for the model with unscrewed support bolts (global type of damage), while cutting the welds (local type of damage) has resulted in significant increase in values of the power spectral density for higher vibration modes.

• Information Systems Review
• /
• v.20 no.1
• /
• pp.81-98
• /
• 2018

ERP supports the automation and integration of business processes of enterprises and records voluminous data about the business activities of enterprises. The academe and business enterprises are focusing on process mining, which improves the performance of business processes and strengthens compliance. However, these studies focused on analysis of the business process of large companies, which adopts foreign ERP, such as SAP ERP or Oracle ERP. In comparison with foreign ERP, domestic ERP lags behind in terms of logging and managing of event data. Therefore, the application of process mining to domestic ERP is a challenging task. The present study aims to analyze domestic ERP based on process mining to overcome this challenge. This study discusses the lessons learned from a case study in a Korean cosmetics manufacturing company. Our results are expected to strengthen the competitiveness of Korean small and medium-sized enterprises that adopt domestic ERP and realize the outcomes of the large investment of the Korean government on the ERP implementation of enterprises.

• IE interfaces
• /
• v.12 no.4
• /
• pp.551-556
• /
• 1999

In this paper, we compare the performance of three data mining classification algorithms(neural network, decision tree, logistic regression) in consideration of various characteristics of categorical input and output data. $2^{4-1}$. 3 fractional factorial design is used to simulate the comparison situation where factors used are (1) the categorical ratio of input variables, (2) the complexity of functional relationship between the output and input variables, (3) the size of randomness in the relationship, (4) the categorical ratio of an output variable, and (5) the classification algorithm. Experimental study results indicate the following: decision tree performs better than the others when the relationship between output and input variables is simple while logistic regression is better when the other way is around; and neural network appears a better choice than the others when the randomness in the relationship is relatively large. We also use Taguchi design to improve the practicality of our study results by letting the relationship between the output and input variables as a noise factor. As a result, the classification accuracy of neural network and decision tree turns out to be higher than that of logistic regression, when the categorical proportion of the output variable is even.

• Asia pacific journal of information systems
• /
• v.12 no.1
• /
• pp.139-158
• /
• 2002

As the telecommunication market becomes mature in Korea, severe competition has already begun on the market. While service providers struggled for the last couple of years to acquire as many new customers as possible, nowadays they are making more efforts on retaining the current customers. The churn management by analyzing customers' demographic and transactional data becomes one of the key customer retention strategies which most companies pursue. However, the customer data analysis has still remained at the basic level in the industry, even though it has considerable potential as a tool for understanding customer behavior. This paper develops several churn prediction models using data mining techniques such as logistic regression, decision trees, and neural networks. For model-building, real data were used which were collected from one of the major telecommunication companies in Korea. This paper explores various ways of comparing model performance, while the hit ratio was mainly focused in the previous research. The comparison criteria used in this study include gain ratio, Kolmogorov-Smirnov statistics, distribution of the predicted values, and explanation ability. This paper also suggest some guidance for model selection in applying data mining techniques.

• Journal of Korea Water Resources Association
• /
• v.47 no.2
• /
• pp.207-221
• /
• 2014

Recently, due to global warming, climate change has affected short time concentrated local rain and unexpected heavy rain which is increasingly causing life and property damage. Therefore, this paper studies the characteristic of localized heavy rain and flash flood in Nakdong basin study area by applying Data Mining method to predict flood and constructing water level predicting model. For the verification neural network from Data Mining method and hydraulic flood routing was used for flood from July 1989 to September 1999 in Nakdong point and Iseon point was used to compare flood level change between observed water level and SAM (Slope Area Method). In this research, the study area was divided into three cases in which each point's flood discharge, water level was considered to construct the model for hydraulic flood routing and neural network based on artificial intelligence which can be made from simple input data used for comparison analysis and comparison evaluation according to actual water level and from the model.

• Geomechanics and Engineering
• /
• v.36 no.3
• /
• pp.205-215
• /
• 2024

Manually mapping fractures in construction stone mines is challenging, time-consuming, and hazardous. In this method, there is no physical access to all points. In contrast, digital image processing offers a safe, cost-effective, and fast alternative, with the capability to map all joints. In this study, two methods of detecting the trace of discontinuities using image processing in construction stone mines are presented. To achieve this, we employ two modified Hough transform algorithms and the degree of neighborhood technique. Initially, we introduced a method for selecting the best edge detector and smoothing algorithms. Subsequently, the Canny detector and median smoother were identified as the most efficient tools. To trace discontinuities using the mentioned methods, common preprocessing steps were initially applied to the image. Following this, each of the two algorithms followed a distinct approach. The Hough transform algorithm was first applied to the image, and the traces were represented through line drawings. Subsequently, the Hough transform results were refined using fuzzy clustering and reduced clustering algorithms, along with a novel algorithm known as the farthest points' algorithm. Additionally, we developed another algorithm, the degree of neighborhood, tailored for detecting discontinuity traces in construction stones. After completing the common preprocessing steps, the thinning operation was performed on the target image, and the degree of neighborhood for lineament pixels was determined. Subsequently, short lines were removed, and the discontinuities were determined based on the degree of neighborhood. In the final step, we connected lines that were previously separated using the method to be described. The comparison of results demonstrates that image processing is a suitable tool for identifying rock mass discontinuity traces. Finally, a comparison of two images from different construction stone mines presented at the end of this study reveals that in images with fewer traces of discontinuities and a softer texture, both algorithms effectively detect the discontinuity traces.

• Ocean and Polar Research
• /
• v.32 no.4
• /
• pp.337-350
• /
• 2010

This study conducted sedimentological and geophysical surveys for 3 years (2006-2008) in southern Gyeonggi Bay, Korea to elucidate temporal changes in subaqueous dune morphology on a sand ridge trending northeast to southwest that has been excavated by marine sand mining. The sand ridge (~20 m in height, ~2 km in width and 3~4 km in length) has a steep slope on the NW side and a gentle slope on the SE side, creating an asymmetric profile. Large (10~100 m in length) and very large (>100 m in length) dunes occurring on the SE side of the ridge show a northeastward asymmetrical shape, whereas dunes on the NW side destroyed by marine sand mining display a southwestward asymmetry. The comparison between Flemming (1988)'s correlation and the height-length correlation of this study indicates that tidal current and availability of sand sediment are major controlling factors to the development and maintenance of dunes. Depth and sedimentary characteristics (grain size) are not likely to be major controlling factors, but indirectly influence dune growth by hydrological and sedimentary processes. The length and the height of dunes decrease toward the southeastern trough away from the crest of the ridge. These features result from the decrease of tidal current and sediment availability. The length and the height of dunes on the southeast side decrease gradually over time. This is a result of the interaction between tidal current and the decrease in sediment availability due to sediment extraction by marine sand mining. Marine sand mining has destroyed the dunes directly, causing irregular shapes of shorter length and lower height. The coarse fraction of suspended sediments is transported and deposited very close to the sand pit. By contrast, relatively fine sediments are transported by the tidal current and deposited over a wide range by the settling-lag effect, resulting in a decrease of sediment grain size in the area where suspended sediments are deposited. In addition, marine sand mining, decreases the height of dunes. Therefore, morphological and sedimentological characteristics of dunes around the sand pits will be significantly changed by future sand mining activities.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.3
• /
• pp.173-183
• /
• 2019

This study aims to utilize big data contents of news and social media for developing a corporate strategy of multinational enterprises and their global decision-making through the data mining technique, especially text mining. In this paper, the data of 2 news media (BBC and CNN) and 2 social media (Facebook and Twitter) were collected for the three global leading Korean companies (Samsung, Hyundai Motor Company, and LG) from April, 2018 to April, 2019. The findings of this paper have shown that traditional news media and also modern social media have become devastating tools to extract global trends or phenomena for businesses. Moreover, this presents that a company can adopt a two-track strategy through two different types of media by deriving the key issues or trends from news media channels and also grasping consumers' sentiments, preference or issues of interest such as battery or design from social media. In addition, analyzing the texts of those media and understanding the association rules greatly contribute to the comparison between two different types of media channels to see the difference. Lastly, this provides meaningful and valuable data empowered insights to find a future direction comprehensively and develop a global strategy for sustainability of business.

• Geomechanics and Engineering
• /
• v.8 no.3
• /
• pp.441-460
• /
• 2015

A new theoretical approach for analysis of stress around a tensioned anchor in rock is presented in this paper. The solution has been derived for semi-infinite elastic rock and anchor and for plane strain conditions. The method considers both the anchor head bearing plate and its grouted bond length embedded in depth. The solution of the tensioned rock anchor problem is obtained by superimposing the solutions of two simpler but fundamental problems: A distributed load applied at a finite portion (bearing plate area) of the rock surface and a distributed shear stress applied at the anchor-rock interface along the bond length. The solution of the first problem already exists and the solution of the shear stress distributed along the bond length is found in this study. To acquire a deep understanding of the stress distribution around a tensioned anchor in rock, an illustrative example is solved and stress contours are drawn for stress components. In order to verify the results obtained by the proposed solution, comparisons are made with finite difference method (FDM) results. Very good agreements are observed for the teoretical results in comparison with FDM.