• Journal of Korean Society of Rural Planning
• /
• v.12 no.4 s.33
• /
• pp.23-32
• /
• 2006

Recently, Owing to booming of leisure activities and national enforcement of 5-day workweek system, Korean government has been promoting rural tourism policy of which operating project's title is Green Rural Experience Village, Rural Traditional Theme Village, etc. In this study, ken investigation result on Green Rural Experience Village sites, an estimation model of returns by green-tourism activities was developed. The model was constructed through factor analysis and regression analysis method. Regression model developed can estimate green-tourism revenue by investment budget, homepage preengagement sales, homepage visitors, capacity of eating and drinking facilities, capacity of lodging facilities. The model developed was applied in sample villages. With these results, estimation revenue was recorded average 138.3% of survey revenue, and statistical significance was good(correlation coefficient $R^2$ = 0.8255, level of significance : 0.000), and the range of relative error was recorded largely from -7.1% to 158.6%, and average relative error was 38.3% and good. And, the model developed in this study have the critical point in aspects of insufficient data, but the results will be used in green-tourism policies and projects, and revenue estimation about each village in the present and future is limited, but in province or the whole country the application is good.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.196-212
• /
• 2014

Facial expression recognition is an important part in emotional interaction between human and machine. This paper proposes a facial expression recognition approach based on multi-classifier fusion with stacking algorithm. The kappa-error diagram is employed in base-level classifiers selection, which gains insights about which individual classifier has the better recognition performance and how diverse among them to help improve the recognition accuracy rate by fusing the complementary functions. In order to avoid the influence of the chance factor caused by guessing in algorithm evaluation and get more reliable awareness of algorithm performance, kappa and informedness besides accuracy are utilized as measure criteria in the comparison experiments. To verify the effectiveness of our approach, two public databases are used in the experiments. The experiment results show that compared with individual classifier and two other typical ensemble methods, our proposed stacked ensemble system does recognize facial expression more accurately with less standard deviation. It overcomes the individual classifier's bias and achieves more reliable recognition results.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.25 no.9
• /
• pp.506-515
• /
• 2013

The PFT (PerFluorocarbon Tracergas Technique) is of advantage to field surveys for evaluating the ventilation condition, due to its simplicity and convenience. On the other hand, it requires researchers to make some additional considerations that include uncertainties, such as the substance concentration distribution in indoor air, representativeness of a sampler, deviation of emission sources, and analysis error. In this study, the PFT and $CO_2$ tracer gas methods were applied simultaneously, to evaluate the accuracy of PFT on six ventilation conditions in the three-storied detached house. The air exchange and the outdoor air introduction a between and into zones were measured. As the results, deviations of PFT concentration distributions were observed at a sufficiently low level for an accurate determination for a house where the interior height was large, and there were relatively many partition walls. However, when a uniform airflow appeared in the indoor air, it was also validated that the indoor air would be exhausted without sufficient mixing, and consequently the measurement error of the PFT would be large.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.102-107
• /
• 2019

This paper proposes a method to improve the mass spectral detection performance of the residual gas analyzer. By improving the mode estimation method for setting the threshold value and improving the additive noise elimination method, it is possible to detect mass spectrums having low peak values of the threshold level difficult to distinguish from noise. Ion signal blocks for each mass index with noise removed by the improved method are effective for eliminating invalid ion signals based on the linear and quadratic fittings. The mass spectrum can be obtained from the quadratic fitted curves for the reconstructed ion signal block using only the valid ion signals. In addition, the resolution of the mass spectrum can be improved by correcting the error caused by the shift of the spectral peak position. To verify the performance of the proposed method, computer simulations were performed using real ion signals obtained from the residual gas analysis system under development. The simulation results show that the proposed method is valid.

• Journal of radiological science and technology
• /
• v.41 no.6
• /
• pp.603-610
• /
• 2018

This study examined the following: accuracy of the exposure conditions in the inverter device and three-phase device; output waveform over the exposure conditions; and average and standard deviation of the output waveform. After assessing whether the dose corresponding to the theoretical dose was presented, the following conclusions were obtained: 1. The accuracy of the tube voltage(kVp) and tube current(mA) exposure time(sec) was within the tolerable level prescribed in Korea's Safety Management Standards. In the error, Inverter device was large the tube voltage and exposure time, the three-phase device was large the tube current. 2. In terms of the output waveform of the exposure conditions and the average and standard deviation of the output waveform, the higher tube voltage and larger tube current resulted in greater standard deviation in pulsation. Moreover, the standard deviation of pulsation was shown to be greater in the inverter device than the three-phase device; there was also greater standard deviation in the inverter device considering the exposure time. 3. Regarding the exposure conditions over the output dose, all linearity showed the coefficient of variation which had an allowable limit of error within 0.05. Although the output dose ratio for the inverter device was 1.00~1.10 times no difference that of the three-phase device, there was almost no difference in dose ratio between the tube currents.

• Journal of The Korean Astronomical Society
• /
• v.53 no.6
• /
• pp.139-147
• /
• 2020

The sunspot area is a critical physical quantity for assessing the solar activity level; forecasts of the sunspot area are of great importance for studies of the solar activity and space weather. We developed an innovative hybrid model prediction method by integrating the complementary ensemble empirical mode decomposition (CEEMD) and extreme learning machine (ELM). The time series is first decomposed into intrinsic mode functions (IMFs) with different frequencies by CEEMD; these IMFs can be divided into three groups, a high-frequency group, a low-frequency group, and a trend group. The ELM forecasting models are established to forecast the three groups separately. The final forecast results are obtained by summing up the forecast values of each group. The proposed hybrid model is applied to the smoothed monthly mean sunspot area archived at NASA's Marshall Space Flight Center (MSFC). We find a mean absolute percentage error (MAPE) and a root mean square error (RMSE) of 1.80% and 9.75, respectively, which indicates that: (1) for the CEEMD-ELM model, the predicted sunspot area is in good agreement with the observed one; (2) the proposed model outperforms previous approaches in terms of prediction accuracy and operational efficiency.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.16 no.3
• /
• pp.115-127
• /
• 2006

The purpose of this paper is evaluation of various normalization methods and fusion algorithms in addition to pattern classification algorithms for multi-biometric systems. Experiments are performed using various normalization functions, fusion algorithms and pattern classification algorithms based on Biometric Scores Set-Releasel(BSSR1) provided by NIST. The performance results are presented by Half Total Error Rate (WTER). This study gives base data for the study on performance enhancement of multiple-biometric system by showing performance results using single database and metrics.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.2
• /
• pp.27-37
• /
• 2022

In this paper, we presents a Multiple User Multiple Input Multiple Output (MU-MIMO) test-bed system for Time Division Duplex (TDD) Long Term Evolution-Advanced (LTE-A). Using two parameters, the condition number of the channel matrix and the path gain, the MU-MIMO system could switch pre-coder to maintain target Bit Error Rate (BER) level. This paper also introduces a calibration procedure for compensating error of Radio Frequency (RF) paths of the antennas and RF transceivers. From experimental measurements, dynamic pre-coding scheme could maintain target BER, set to 10^-3, with the pre-coder set configured with Zero Forcing (ZF), Tomlinson Harashima Pre-coding (THP), Lattice Reduction (LR). The simplest pre-coder ZF is adopted in stable channel, and when path gain become less than 0.25, LR is adopted. Lastly, when condition number of channel matrix become larger than 7, THP is adopted.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.3
• /
• pp.6-16
• /
• 2022

Recent, the issue of the fourth industrial revolution triggered by technological advances has changed the automobile industry centered on internal combustion engines, and quantitative growth of the global automobile market, which has grown rapidly, has been slowing since 2015. These advances in technology are expected to develop beyond the advanced driver assistance system to autonomous driving technology. According to SAE-J3016 published by the Society of Automotive Engineers, the technology of autonomous vehicles is divided into a total of six stages according to the driver's intervention and automation level from 0 to 5. Securing safety for autonomous vehicles is important. But, research on safety evaluation theory and autonomous vehicle evaluation method based on real vehicle test is insufficient. In this study, the longitudinal distance theory equation and continuous test scenario were proposed for the test method of autonomous vehicles for fixed targets, and the real vehicle test was conducted. When comparing the theoretical values compared to the measured values, it was determined that it was reliable with a minimum error rate of 0.484% and a maximum error rate of 7.391%. Using the proposed theoretical equation, it is judged that it can be used as a safety evaluation method in an environment where real vehicle test is not possible because it can grasp the trend in the longitudinal direction in the development stage.

• Korean Journal of Agricultural Science
• /
• v.49 no.3
• /
• pp.679-690
• /
• 2022

As the supply and demand of pork has become a significant concern in Korea, controlling it has become a critical challenge for the industry. However, compared to the demand for pork, which has relatively stable consumption, it is not easy to maintain a stable supply. As the preparation of measures for a supply-demand crisis response and supply control in the pig industry has emerged as an important task, it has become necessary to establish a stable supply model and create an appropriate manual. In this study, a pork supply prediction model is constructed using reported data from the pig traceability system. Based on the derived results, a method for determining the supply-demand crisis stage using a statistical approach was proposed. From the results of the analysis, working days, African swine fever, heat wave, and Covid-19 were shown to affect the number of pigs graded in the market. A test of the performance of the model showed that both in-sample error rate and out-sample error rate were between 0.3 - 7.6%, indicating a high level of predictive power. Applying the forecast, the distribution of the confidence interval of the predicted value was established, and the supply crisis stage was identified, evaluating supply-demand conditions.