• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.173-198
• /
• 2020

For a long time, many studies have been conducted on predicting the success of campaigns for customers in academia, and prediction models applying various techniques are still being studied. Recently, as campaign channels have been expanded in various ways due to the rapid revitalization of online, various types of campaigns are being carried out by companies at a level that cannot be compared to the past. However, customers tend to perceive it as spam as the fatigue of campaigns due to duplicate exposure increases. Also, from a corporate standpoint, there is a problem that the effectiveness of the campaign itself is decreasing, such as increasing the cost of investing in the campaign, which leads to the low actual campaign success rate. Accordingly, various studies are ongoing to improve the effectiveness of the campaign in practice. This campaign system has the ultimate purpose to increase the success rate of various campaigns by collecting and analyzing various data related to customers and using them for campaigns. In particular, recent attempts to make various predictions related to the response of campaigns using machine learning have been made. It is very important to select appropriate features due to the various features of campaign data. If all of the input data are used in the process of classifying a large amount of data, it takes a lot of learning time as the classification class expands, so the minimum input data set must be extracted and used from the entire data. In addition, when a trained model is generated by using too many features, prediction accuracy may be degraded due to overfitting or correlation between features. Therefore, in order to improve accuracy, a feature selection technique that removes features close to noise should be applied, and feature selection is a necessary process in order to analyze a high-dimensional data set. Among the greedy algorithms, SFS (Sequential Forward Selection), SBS (Sequential Backward Selection), SFFS (Sequential Floating Forward Selection), etc. are widely used as traditional feature selection techniques. It is also true that if there are many risks and many features, there is a limitation in that the performance for classification prediction is poor and it takes a lot of learning time. Therefore, in this study, we propose an improved feature selection algorithm to enhance the effectiveness of the existing campaign. The purpose of this study is to improve the existing SFFS sequential method in the process of searching for feature subsets that are the basis for improving machine learning model performance using statistical characteristics of the data to be processed in the campaign system. Through this, features that have a lot of influence on performance are first derived, features that have a negative effect are removed, and then the sequential method is applied to increase the efficiency for search performance and to apply an improved algorithm to enable generalized prediction. Through this, it was confirmed that the proposed model showed better search and prediction performance than the traditional greed algorithm. Compared with the original data set, greed algorithm, genetic algorithm (GA), and recursive feature elimination (RFE), the campaign success prediction was higher. In addition, when performing campaign success prediction, the improved feature selection algorithm was found to be helpful in analyzing and interpreting the prediction results by providing the importance of the derived features. This is important features such as age, customer rating, and sales, which were previously known statistically. Unlike the previous campaign planners, features such as the combined product name, average 3-month data consumption rate, and the last 3-month wireless data usage were unexpectedly selected as important features for the campaign response, which they rarely used to select campaign targets. It was confirmed that base attributes can also be very important features depending on the type of campaign. Through this, it is possible to analyze and understand the important characteristics of each campaign type.

• Korean Journal of Remote Sensing
• /
• v.33 no.2
• /
• pp.111-123
• /
• 2017

The phycocyanin pigment (PC) is a marker for cyanobacterial presence in eutrophic inland water. Accurate estimation of low PC concentration in turbid inland water is challenging due to the optical complexity and criticalforissuing an early warning of potentialrisks of cyanobacterial bloom to the public. To monitor cyanobacterial bloom in eutrophic inland waters, an approach is proposed to partition non-water absorption coefficient from measured reflectance and to retrieve absorption coefficient of PC with the aim of improving the accuracy in remotely estimated PC, in particular for low concentrations. The proposed inversion model retrieves absorption spectra of PC ($a_{pc}({\lambda})$) with $R^2{\geq}0.8$ for $a_{pc}(620)$. The algorithm achieved more accurate Chl-a and PC estimation with $0.71{\leq}R^2{\leq}0.85$, relative root mean square error (rRMSE) ${\leq}39.4%$ and mean relative error(RE) ${\leq}78.0%$ than the widely used semi-empirical algorithm for the same dataset. In particular, low PC ($PC{\leq}50mg/m^3$) and low PC: Chl-a ratio values of for all datasets used in this study were well predicted by the proposed algorithm.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.23 no.6
• /
• pp.489-495
• /
• 2011

Fossil fuel energy has become a worldwide environmental issue due to its effect on global warming and depletion in its supply. Therefore, the interest in developing alternative energy source has been rising. Ocean energy, especially, has gained strength as an alternative energy source for its unlimited supply with low secondary risks. Among all the ocean energy, the west coast of Korea holds the field of large-scale energy development because of its distinctive tidal range. Tidal power plant construction at the sea may expedite multi development effects such as bridge roles, tourism resource effects and adjustability of flood inundation at the inner bay. This study introduces the validity of tidal power plant construction at Garilim Bay in west coast of Korea by examining anticipated hydraulic characteristics using EFDC model. Through EFDC numerical simulations, the feasibility of Garolim Bay as a tidal power plant field has been proved. And the most effective tidal power plant construction would be to install hydraulic turbine in the west side of bay entrance where ebb current is stronger, and install water gate in the east side of bay entrance where the flood current is superior.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.41-43
• /
• 2022

In order to prevent and block infectious diseases caused by the recent COVID-19 pandemic, non-contact biometric information acquisition and analysis technology is attracting attention. The invasive and attached biometric information acquisition method accurately has the advantage of measuring biometric information, but has a risk of increasing contagious diseases due to the close contact. To solve these problems, the non-contact method of extracting biometric information such as human fingerprints, faces, iris, veins, voice, and signatures with automated devices is increasing in various industries as data processing speed increases and recognition accuracy increases. However, although the accuracy of the non-contact biometric data acquisition technology is improved, the non-contact method is greatly influenced by the surrounding environment of the object to be measured, which is resulting in distortion of measurement information and poor accuracy. In this paper, we propose a context-based bio-signal modeling technique for the interpretation of personalized information (image, signal, etc.) for bio-information analysis. Context-based biometric information modeling techniques present a model that considers contextual and user information in biometric information measurement in order to improve performance. The proposed model analyzes signal information based on the feature probability distribution through context-based signal analysis that can maximize the predicted value probability.

• Journal of Environmental Policy
• /
• v.12 no.3
• /
• pp.21-47
• /
• 2013

The aim is to analysis landslide vulnerability in Inje, Korea, using GCI(Geospatial Correlative Integration) and probability rainfalls based on geographic information system (GIS). In order to achieve this goal, identified indicators influencing landslides based on literature review. We include indicators of exposure to climate(rainfall probability), sensitivity(slope, aspect, curvature, geology, topography, soil drainage, soil material, soil thickness and soil texture) and adaptive capacity(timber diameter, timber type, timber density and timber age). All data were collected, processed, and compiled in a spatial database using GIS. Karisan-ri that had experienced 470 landslides by Typhoon Ewinia in 2006 was selected for analysis and verification. The 50% of landslide data were randomly selected to use as training data, while the other 50% being used for verification. The probability of landslides for target years (1 year, 3 years, 10 years, 50 years, and 100 years) was calculated assuming that landslides are triggered by 3-day cumulative rainfalls of 449 mm. Results show that number of slope has comparatively strong influence on landslide damage. And inclination of $25{\sim}30^{\circ}C$, the highest correlation landslide. Improved previous landslide vulnerability methodology by adopting GCI. Also, vulnerability map provides meaningful information for decision makers regarding priority areas for implementing landslide mitigation policies.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.19 no.2
• /
• pp.14-26
• /
• 2016

This study analyzed the correlation between the standardized precipitation index(SPI) and forest fire occurrences using monthly accumulative rainfall data since 1970 and regional fire occurrence data since 1991. To understand the relationship between the SPI and forest fire occurrences, the correlations among the SPI of nine main observatory weather stations including Seoul, number of fire occurrences, and log of fire occurrences were analyzed. We analyzed the correlation of SPI with fire occurrences in the 1990s and 2000s and found that in the 1990s, the SPI of 3 months showed high correlation in Gyeonggi, Gangwon, and Chungnam, while the SPI of 6 months showed high correlation in Chungbuk, and the SPI of 12 months showed high correlation in Gyeongnam, Gyenongbuk, Jeonnam, and Jeonbuk. In the 2000s, the SPI of 6 months showed high correlation with the fire frequency in Gyeonggi, Chungnam, Chungbuk, Jeonnam, and Jeonbuk, whereas the fire frequency in western Gangwon was highly correlated with the SPI of 3 months and, in eastern Gangwon, Gyeongnam, and Gyenongbuk, with the SPI of 1 month. In the 1990s, distinct differences in the drought condition between the SPI of 3 months and 12 months in the northern and southern regions of Korean Peninsula were found, whereas the differences in both the SPI of 1 month and 6 months were found in the Baekdudaegan region except western Gangwon since the 2000s. Therefore, this study suggests that we can develop a model to predict forest fire occurrences by applying the SPI of 1-month and 6-month data in the future.

• Journal of the Korea Concrete Institute
• /
• v.23 no.3
• /
• pp.295-301
• /
• 2011

Recently, the use of UHPC made of superplasticizers, silica fume, and steel fibers has been increasing worldwide. Although UHPC has a very high strength as well as an excellent durability performance due to its dense microstructures, earlyage cracks may occur due to the high heat of hydration and autogenous shrinkage caused by low W/B and high unit cement content. The early-age shrinkage cracking of UHPC can be controlled by using the shrinkage reducers and expansive admixtures having autogenous shrinkage compensation effect. In this paper, ultrasonic pulse velocity of UHPC containing shrinkage reducers and expansive agents was measured to predict its stiffness change. Also, the effect of shrinkage reducers and expansive agents on the autogenous shinkage of UHPC was investigated through the shrinkage test of UHPC specimens. Furthermore, the material coefficients of autogenous shrinkage prediction model were determined using the autogenous shrinkage values of UHPC with age. Consequently, the test results showed that, by adding shrinkage reducers and expansive agents, the stiffness of UHPC was rapidly developed at early-ages and the autogenous shrinkage was considerably reduced.

• The korean journal of orthodontics
• /
• v.37 no.3 s.122
• /
• pp.171-181
• /
• 2007

Objective: The present study was aimed at an analytical formulation of the micro-implant related torque as a function of implant size, i.e. the diameter and length, screw size, and the bony resistance at the implant to bone interface. Methods: The resistance at the implant to cancellous bone interface $(S_{can})$ was assumed to be in the range of 1.0-2.5 MPa. Micro-implant model of Absoanchor (Dentos Inc. Daegu, Korea) was used in the course of the analysis. Results: The results showed that the torque was a strong function of diameter, length, and the screw height. As the diameter increased and as the screw size decreased, the torque index decreased. However the strength index was a different function of the implant and bone factors. The whole Absoanchor implant models were within the safe region when the resistance at the implant/cancellous bone $(=S_{can})$ was 1.0 or less. Conclusion: For bone with $S_{can}$ of 1.5 MPa, the cervical diameter should be greater than 1.5 mm if micro-implant models of 12 mm long are to be placed. For $S_{can}$ of 2.0 MPa, micro-implant models of larger cervical diameter than 1.5 mm were found to be safe only if the endosseous length was less than 8 mm.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.5
• /
• pp.113-120
• /
• 2020

Safety accidents, called industrial accidents in construction work, are causing a lot of casualties, property damage and social controversy in the event of an accident, causing the construction to lose public confidence. The risk of safety accidents at construction sites may continue to increase as the construction of high-rise, large-scale, and multi-purpose complex buildings has increased in recent years. In particular, the most frequently constructed apartment construction among reinforced concrete buildings is designed and constructed with a wall-like structure with no beams for each floor, while the lower floors are made of lamen with columns and beams. As a result, the transfer beam or transfer slab to withstand the upper load is installed on the upper part of the Ramen structure, so the system Dongbari, which is installed as a temporary material during concrete laying construction, may collapse at any time during plowing and curing. The purpose of this study is to apply IT convergence technology to prevent the collapse of the system Dongbari during concrete installation, and to apply many of the variables that may occur during construction on a case-by-case basis to check the stability of the system Dongbari and to propose a model of the anti-conducting prediction system.

• Journal of Korea Water Resources Association
• /
• v.47 no.11
• /
• pp.1051-1060
• /
• 2014

This study is attempted to realize an improved computation performance by combining the MPI (Message Passing Interface) Technique, a standard model of the parallel programming in the distributed memory environment, with the DHM(Diffusion Hydrodynamic Model), a inundation analysis model. With parallelizing inundation model, it compared with the existing calculation method about the results of applications to complicate and required long computing time problems. In addition, it attempted to prove the capability to estimate inundation extent, depth and speed-up computing time due to the flooding in protected lowlands and to validate the applicability of the parallel model to the actual flooding analysis by simulating based on various inundation scenarios. To verify the model developed in this study, it was applied to a hypothetical two-dimensional protected land and a real flooding case, and then actually verified the applicability of this model. As a result of this application, this model shows that the improvement effectiveness of calculation time is better up to the maximum of about 41% to 48% in using multi cores than a single core based on the same accuracy. The flood analysis model using the parallel technique in this study can be used for calculating flooding water depth, flooding areas, propagation speed of flooding waves, etc. with a shorter runtime with applying multi cores, and is expected to be actually used for promptly predicting real time flood forecasting and for drawing flood risk maps etc.