• The Journal of the Korea Contents Association
• /
• v.18 no.8
• /
• pp.525-535
• /
• 2018

If the frequency of a particular class is excessively higher than the frequency of other classes in the classification problem, data imbalance problems occur, which make machine learning distorted. Corporate bankruptcy prediction often suffers from data imbalance problems since the ratio of insolvent companies is generally very low, whereas the ratio of solvent companies is very high. To mitigate these problems, it is required to apply a proper sampling technique. Until now, oversampling techniques which adjust the class distribution of a data set by sampling minor class with replacement have popularly been used. However, they are a risk of overfitting. Under this background, this study proposes ROSE(Random Over Sampling Examples) technique which is proposed by Menardi and Torelli in 2014 for the effective corporate bankruptcy prediction. The ROSE technique creates new learning samples by synthesizing the samples for learning, so it leads to better prediction accuracy of the classifiers while avoiding the risk of overfitting. Specifically, our study proposes to combine the ROSE method with SVM(support vector machine), which is known as the best binary classifier. We applied the proposed method to a real-world bankruptcy prediction case of a Korean major bank, and compared its performance with other sampling techniques. Experimental results showed that ROSE contributed to the improvement of the prediction accuracy of SVM in bankruptcy prediction compared to other techniques, with statistical significance. These results shed a light on the fact that ROSE can be a good alternative for resolving data imbalance problems of the prediction problems in social science area other than bankruptcy prediction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.1
• /
• pp.55-65
• /
• 2017

This study was conducted to investigate the mediating effects of coping on the impact of life stress on depression, subjective well-being and psychological well-being in nursing students. Self-report questionnaires were used to collect data from 147 nursing students. Data were analyzed using descriptive statistics, Pearson's correlation coefficient and hierarchical multiple regression. Nursing students who had a higher level of depression had a higher level of life stress, as well as a higher frequency of avoidance coping. Conversely, those who had a higher level of subjective well-being and psychological well-being had a lower level of life stress, as well as a lower frequency of avoidance coping. There were also significant positive correlations between psychological well-being and problem solving coping. The results showed that avoidance coping partially mediated the effects of life stress on depression, subjective well-being and psychological well-being. The results suggest that it is necessary to offer stress management programs to reduce avoidance coping, with additional consideration of life stress and coping strategies, to prevent depression and improve well-being among nursing students.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.607-615
• /
• 2016

This study concerns the transmission of energy and data using induced electromotive force. Due to the requirements of weapon systems, most arms are kept in an armory for a very long time before being used. During this time, the reserve battery, which serves mostly as a power supply for the electronic fuze, can be degraded, thus causing problems when it is actually needed. We attempt to solve the various problems associated with the old fuze system caused by long-term storage by using the 'induction power' transmitted from another device just before its operation, instead of using 'built-in power'. We tried to find the best carrier frequency to communicate with the system by induced electromotive force. Also, we changed the communication method for transmitting the 'induction power' from 'FM/AM modulation' to 'Duty ratio modulation', which can transmit a large amount of data in a short time. Through experiments, it was demonstrated that the induction coil can replace the reserve fuze's battery without any problem, thus confirming the possibility of using an induction coil as the power supply source of the electronic fuze.

• Journal of the Korean Geophysical Society
• /
• v.6 no.3
• /
• pp.165-177
• /
• 2003

The purpose of this paper is to analyze the behavior and to study the safety evaluation of the Unmun Dam located in Cheongdo-Gun of GyeongBuk Province, Korea. For this purpose, soil analyses including boring data, geophysical surveys were conducted. In this paper, especially many geophysical methods were adopted to configure out the subsurface situation of dam. Applied geophysical methods were: 1) electric resistivity survey, 2) high frequency magnetotelluric (HFMT) survey, 3) ground penetrating radar (GPR) survey, 4) seismic refraction survey, 5) seismic cross-hole tomography survey, and 6) high frequency impedance (ZHF) survey. Each of geophysical surveys were analyzed and joint analyses between geophysical surveys were also performed to deduce the more reliable subsurface information of Dam by using the features and characteristics of each geophysical survey. Since many defects, such as gravel and weathered rock blocks in the dam core, and lots of amounts of leakage, by boring analyses were found, reinforcement by compaction grouting system (CGS) has been conducted in some range of dam. Some geophysical data and data of geotechnical gauges were also used to confirm the effects of reinforcement. Electric resistivity, EM, GPR, ZHF, seismic refraction and seismic tomography surveys show that left side of dam is weak, which means the possibility of existence of gravel, rock block, water and cavities in the core of dam. This result coincides with the boring data. Especially, electric survey after reinforcement shows that even the right side of the dam has been deformed by the strong pressure during the reinforcement itself. As a conclusion, some problems in the dam found. Especially, the dam near spillway shows the high possibility of leakage. It should be pointed out that only the left side of he dam has not a leakage problem. As a whole, the dam has problems of weakness, because of unsatisfactory construction. It is strongly recommended that highly intensive monitoring is required.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.250-254
• /
• 2002

Intergranular corrosion of austenitic stainless steels is a conventional and momentous problem during welding and high temperature use. One of the major reasons for such intergranular corrosion is so-called sensitization, i.e., chromium depletion due to chromium carbide precipitation at grain boundaries. Conventional methods for preventing sensitization of austenitic stainless steels include reduction of carbon content in the material, stabilization of carbon atoms as non-chromium carbides by the addition of titanium, niobium or zirconium, local solution-heat-treatment by laser beam, etc. These methods, however, are not without drawbacks. Recent grain boundary structure studies have demonstrated that grain boundary phenomena strongly depend on the crystallographic nature and atomic structure of the grain boundary, and that grain boundaries with coincidence site lattices are immune to intergranular corrosion. The concept of "grain boundary design and control", which involves a desirable grain boundary character distribution, has been developed as grain boundary engineering. The feasibility of grain boundary engineering has been demonstrated mainly by thermomechanical treatments. In the present study, a thermomechanical treatment was tried to improve the resistance to the sensitization by grain boundary engineering. A type 304 austenitic stainless steel was pre-strained and heat-treated, and then sensitized, varying the parameters (pre-strain, temperature, time, etc.) during the thermomechanical treatment. The grain boundary character distribution was examined by orientation imaging microscopy. The intergranular corrosion resistance was evaluated by electrochemical potentiokinetic reactivation and ferric sulfate-sulfuric acid tests. The sensitivity to intergranular corrosion was reduced by the thermomechanical treatment and indicated a minimum at a small roll-reduction. The frequency of coincidence-site-lattice boundaries indicated a maximum at a small strain. The ferric sulfate-sulfuric acid test showed much smaller corrosion rate in the thermomechanically-treated specimen than in the base material. An excellent intergranular corrosion resistance was obtained by a small strain annealing at a relatively low temperature for long time. The optimum parameters created a uniform distribution of a high frequency of coincidence site lattice boundaries in the specimen where corrosive random boundaries were isolated. The results suggest that the thermomechanical treatment can introduce low energy segments in the grain boundary network by annealing twins and can arrest the percolation of intergranular corrosion from the surface.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2
• /
• pp.121-128
• /
• 2003

Acoustic Echo Cancellation(m) is very active research topic having many applications like teleconference and hands-free communication and it employs Double Talk Detector(DTD) to indicate whether the near-end speaker is active or not. However. the DTD is very sensitive to the variation of acoustical environment and it sometimes provides wrong information about the near-end speaker. In this paper, we are focusing on the development of robust DTD algorithm which is a basic building block for reliable AEC system. The proposed AEC system consists of delayless subband AEC and narrow-band DTD. Delayless subband AEC has proven to have excellent performance of echo cancellation with a low complexity and high convergence speed. In addition, it solves the signal delay problem in the existing subband AEC. On the other hand, the proposed narrowband DTD is operating on low frequency subband. It can take most advantages from the narrow subband such as a low computational complexity due to the down-sampling and the reliable DTD decision making procedure because of the low-frequency nature of the subband signal. From the simulation results of the proposed narrowband DTD and wideband DTD, we confirm that the proposed DTD outperforms the wideband DTD in a sense of removing possible false decision making about the near-end speaker activity.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.7
• /
• pp.76-84
• /
• 2013

In the passive emitter localization using instantaneous TDOA (time difference of arrival) and FDOA (frequency difference of arrival) measurements, the estimation accuracy can be improved by collecting additional measurements. To achieve this goal, it is required to increase the number of the sensors. However, in electronic warfare environment, a large number of sensors cause the loss of military strength due to high probability of intercept. Also, the additional processes should be considered such as the data link and the clock synchronization between the sensors. Hence, in this paper, the passive localization of a stationary emitter is presented by using the successive TDOA and FDOA measurements from two moving sensors. In this case, since an independent pair of sensors is added in the data set at every instant of measurement, each pair of sensors does not share the common reference sensor. Therefore, the QCLS (quadratic correction least squares) methods cannot be applied, in which all pairs of sensor should include the common reference sensor. For this reason, a Gauss-Newton algorithm is adopted to solve the non-linear least square problem. In addition, to show the performance of the proposed method, we compare the RMSE (root mean square error) of the estimates with CRLB (Cramer-Rao lower bound) and derived the CEP (circular error probable) planes to analyze the expected estimation performance on the 2-dimensional space.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.15 no.1
• /
• pp.17-37
• /
• 1987

The purpose of this study is to establish more rational and practical planning theory for amusement park. It analyze and consider the fluctuation of people who come and use the Tong-Ch'on amusement park. The results drawn from this reserch work are as follows; 1. The main visitors of the Tong-Ch'on amusement park are students in their twenties and thirties, and people whose incomes are below 300,000 Won a month. The purpose of visit is for a rest rather than for amusement and user prefer summer, while the user is so rare in wintertime. Those phenomena observed are somewhat different from the real purpose of a amusement park which is on purpose to make profits by offering entertainments to the users. So planner should pay attention to the three points. They are varieties, seasonable diversification and fantastic character of facilties, in the amusement park. 2. The access time of the Tong-Ch'on amusement park was 41 minutes, the use frequency was 4 times a year and resident time was 164 minutes. The relationship of the three factors are as follows; log Y(F) =1.7832-0.0277(A.T) R$^2$=0.75 Y(R. F)=31.8885+3.3217(A.T) R$^2$=0.53 Y(R. T)=224.8959-87.8309 1og(F) R$^2$=0.38 F;Use frequency(time/year) A.T;Access Time(minute) R.T;Resident Time(minute) 3. In the choice of space, there were much differences according to tole user's age, job, degree of education, companion type and purpose of use. 4. There are considerable correlation between use fluctuation and some factors. The factors are season(summer, winter) as a time, temperature, cloud amount, duration of sunshine, weather(rainy-day) as a climate and a day of the week(weekday, holiday) as a social system. The important variables are temperature, cloud amount, duration of sunshine and a day of the week(weekday, holiday) to estimate the user of amusementpark. 5. 1 can reduce the following two types of regression models. 1) log$\sub$e/ Y1 = 6.9114 + 0.l135 TEM + 0.00002 SUN -0.4068W1 + 0.4316 W3 (R$^2$= 0.94) 2) log$\sub$e/ Y2 = 7.2069 + 0.l177 TEM - 0.0990 CLO + 0.4880 W3 (R$^2$=0.95) Y; Number of User TEM; Temperature CLO; Amount of cloud SUN; Duration of Sunshine W1; Weekday W3; Holiday Those model is in order to estimate the user for management of Tong-Ch'on amusement park and use on the computation of facility sloe for reconstruction. Besides the amusement park, city park and outdoor recreation area could estimate of user through this method. But, I am not sure about the regression models because I did not apply the regression models to the other amusement park, city Park or outdoor recreation area. Therefore, I think that this problem needs to be studied on in the future.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.37 no.1
• /
• pp.28-42
• /
• 2009

In the wake of categorizing the design changes occurred during the period from 2004 till the first half of 2006 in Choongcheong province area, based on purpose and reason of design changes identified by the Korea National Housing Corp, it included 11 types such as the image of the apartment complex, scenic elements, consideration by the user, prevention of the defect, constructability, site conditions, incompatibility between the activities, superordinate standard, prevention of civic complaints, design details and others, along with 47 subordinate elements. And the evaluation intended to identify the corelation between the number and time of design change approval, frequency and scale of design change by type and the cost variations indicated that; firstly, enhancing the image of the apartment complex proved to be the main reason for design changes, accounting for 22% in terms of frequency and 54.9% in terms of cost variation. Secondly, the higher the increase in cost by design change aimed at improving the image of the complex, the lower the decrease in cost by design change for uncertain reasons, dubbed the inverse proportional relations, indicating that the design changes for uncertain reasons were mostly aimed at reducing the construction cost. Thirdly, with regard to the number of design change approval and the time of the initial approval, twice or less and 90 days or less before completion of the construction work, respectively, accounted for $52{\sim}53%$, indicating the design change deliberation and approval tended to have been carried out collectively in the form of ex post facto approval, which seemed to be attributable to the attempt of reducing the construction cost or budget problem, as a result of comparing with the cases in which the cost was reduced.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.48 no.1
• /
• pp.77-83
• /
• 2011

In this thesis, 50W Doherty amplifier was designed and implemented for Beyond 3G's repeater and base-station. Auxiliary amplifier of doherty amplifier was implemented by Gate bias control circuit. Though gate bias control circuit solved auxiliary's bias problem, output characteristics of doherty amplifier was limited. To enhance the output characteristic relativize Drain control circuit And To improve power efficiency make 3-way Doherty power amplifier. therefore, 3-way GDCD (Gate and Drain bias Control Doherty) power amplifier is embodied to drain bias circuit for General Doherty power amplifier. The 3-way GDCD power amplifier composed of matching circuit with chip capacitor and micro strip line using FR4 dielectric substance of specific inductive capacity(${\varepsilon}r$) 4.6, dielectric substance height(H) 30 Mills, and 2.68 Mills(2 oz) of copper plate thickness(T). Experiment result satisfied specification of amplifier with gains are 57.03 dB in 2.11 ~ 2.17 GHz, 3GPP frequency band, PEP output is 50.30 dBm, W-CDMA average power is 47.01 dBm, and ACLR characteristics at 5MHz offset frequency band station is -40.45 dBc. Especially, 3-way DCHD power amplifier showed excellence efficiency performance improvement in same ACLR than general doherty power amplifier.