• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• pp.80-87
• /
• 2024

This paper focuses on improving accuracy in constrained computing settings by employing the ReLU (Rectified Linear Unit) activation function. The research conducted involves modifying parameters of the ReLU function and comparing performance in terms of accuracy and computational time. This paper specifically focuses on optimizing ReLU in the context of a Multilayer Perceptron (MLP) by determining the ideal values for features such as the dimensions of the linear layers and the learning rate (Ir). In order to optimize performance, the paper experiments with adjusting parameters like the size dimensions of linear layers and Ir values to induce the best performance outcomes. The experimental results show that using ReLU alone yielded the highest accuracy of 96.7% when the dimension sizes were 30 - 10 and the Ir value was 1. When combining ReLU with the Adam optimizer, the optimal model configuration had dimension sizes of 60 - 40 - 10, and an Ir value of 0.001, which resulted in the highest accuracy of 97.07%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.3
• /
• pp.188-193
• /
• 2011

In this letter, we have derived another exact performance analysis for the OADF(opportunistic adaptive decode-and-forward) relay systems over Rayleigh fading channels. Based on error-events at relay nodes, the received instantaneous SNR(signal-to-noise ratio) is presented and its PDF(probability density function) is expressed as a more tractable form in which the number of summations and the length of each summation are specified. Then, exact average error rate, outage probability, and average channel capacity are obtained as general forms. Simulation results are finally presented to validate that the proposed analytical expressions can be a unified frame work covering all Rayleigh fading channel conditions. Furthermore, it is confirmed that OADF schemes can outperform the other schemes on the average error rate, outage probability, and average channel capacity.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.15 no.4
• /
• pp.131-137
• /
• 2007

In this study, the biodegradation test on lignocellulose under sulfate reducing conditions was carried out. In particular, the interaction between cellulose and lignin was investigated with various g-cellulose/g-lignin (C/L) ratios: 42.15, 4.59, 2.51, 1.14 and 0.7. It was shown that the rate of cellulose degradation decreased in proportion to the lignin content. Assuming first order degradation kinetics, the consequences of competitive inhibition were graphically shown for different C/L ratios. The relation between cellulose reduction rate and C/L ratio was expressed by logarithm function with a determination coefficient of 0.97. Lignocellulose reduction rate was also described as a logarithm function of C/L ratio showing a inhibition effect by lignin. In the mean time, the rate of lignin decomposition was higher at C/L ratio of 2.51 and 1.14 compared with C/L ratios of 4.59 and 0.7, indicating that excessive extra carbon source is not appropriate for lignin biodegradation.

• Journal of Ecology and Environment
• /
• v.40 no.2
• /
• pp.125-135
• /
• 2016

Background: The objectives of this study were to establish a swimming capability model for largemouth bass using the FishXing (version 3) program, and to determine the swimming speed and feasibility of fish passage through a waterway tunnel. This modeling aimed to replicate the waterway tunnel connecting the Andong and Imha Reservoirs in South Korea, where there is a concern that largemouth bass may be able to pass through this structure. As largemouth bass are considered an invasive species, this spread could have repercussions for the local environment. Results: Flow regime of water through the waterway tunnel was calculated via the simulation of waterway tunnel operation, and the capability of largemouth bass to pass through the waterway tunnel was then estimated. The swimming speed and distance of the largemouth bass had a positive linear function with total length and negative linear function with the flow rate of the waterway tunnel. The passing rate of small-size largemouth bass (10-30 cm) was 0%at a flow of $10m^3/s$ due to rapid exhaustion from prolonged upstream swimming through the long (1.952 km) waterway tunnel. Conclusions: The results of FishXing showed that the potential passing rate of large size largemouth bass (>40 cm) through the waterway tunnel was greater than 10%; however, the passage of largemouth bass was not possible because of the mesh size ($3.4{\times}6.0cm$) of the pre-screening structures at the entrance of the waterway tunnel. Overall, this study suggests that the spread of largemouth bass population in the Imha Reservoir through the waterway tunnel is most likely impossible.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.993-1004
• /
• 2017

A stratified sampling method is generally used with a sample selected using the same sample weight in each stratum in order to improve the accuracy of the sampling survey estimation. However, the weight should be adjusted to reflect the response rate if the response rate is affected by the value of the variable of interest. It may be also more effective to adjust the weights by subdividing the stratum rather than using the same weight if the variable of interest has a linear relationship with the continuous auxiliary variables. In this study, we propose a method to increase the accuracy of estimation using an informative sampling design technique when the response rate is an exponential function of the variable of interest and the variable of interest has a linear relationship with the auxiliary variable. Simulation results show the superiority of the proposed method.

• Health Policy and Management
• /
• v.5 no.1
• /
• pp.132-160
• /
• 1995

This study purported to acquire information necessary to improve the management of general hospitals. It tried to determine major indices which represent managerial performance of general hospitals and to identify the managerial characteristics of general hospitals which affect the major financial indices. Eighty-eight hospitals were chosen from 188 hospitals which were subject to standardization audit by the Korean Hospital Association. The results of a discriminant analysis are summarized as followings. First, when a single index was used to measure managerial performance of the sample hospitals, the ration of net profit to total capital was the best index and its discriminant power was 58.14%. The ratio of the number of boardmen((M. D.) and average daily medical cost were highly related to this index. Second, when two indices were used, income growth rte and the ration of net profit to total capital had the highest discriminant distinction ability. Their discriminant power was 61.9%. In this case, the ratio of the number of boardmen(M. D.) was significantly and highly related to the indices. Third, when all three indices-income growth rate, the ration of net profit to total capital and quick ratio - were used together, a discriminant function was statistically insignificant. Therefore, using all three indices was not useful in measuring managerial performance of the sample hospitals. In conclusion, using two indices-income growth rate and the ration of net profit to total capital-was better in measuring manegerial performance of general hospitals than using a single index. The independent variable which affected these indices was the ration of the number of boardmen. The discriminant function was : $D_{GI}=2.77+4.832\times(the ratio of the number of boardmen)$ *G=growth index(income growth rate) *I=profit index(the ration of net profit to total capital)

• Korean Journal of Acupuncture
• /
• v.19 no.2
• /
• pp.41-49
• /
• 2002

Objectives : The aim of the present study is to observe effects of acupuncture related with the nerve system, Inferior mesenteric nerve activity(IMNA) was examined on BL60 acupuncture closely connected with the bladder and HT8 with little tied. Materials and methods : Acupunctures were performed during 100 seconds after stabilization. IMNA was measured by micromanipulator, preamplifier, mean arterial pressure(MAP) and heart rate were observed by blood pressure transducer, 4-channel transducer amplifier in anesthetized rat. Results : On BL60 acupuncture, the heart rate was not significantly decreased but IMNA, MAP were significantly decreased and Maximum peak of IMNA was increased during inserted acupuncture, decreased after ejected acupuncture respectively. On HT8 acupuncture, IMNA was decreased during acupuncture than before acupuncture but the others did not showed signigicant difference. Conclusions : Our results demonstrated a meridian interaction between BL60 acupoint in the bladder channel and Inferior mesenteric sympathetic nerve related to the bladder. This fact suggest that BL60 acupuncture have effect on the bladder through the nerve system. Meanwhile, IMNA was decreased during HT8 acupuncture. This result is supposed HT8 to have not meridian function but acupoint function by another mechanism. It needs to be closely examined other meridians and nerve by the optimal approaching method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1266-1273
• /
• 2013

The purpose of this study was to analysis the effect of form of outsole - complex function double rocker sole(CDR) vs. negative-heel rocker sole (NR) - on energy consumption and heart rate intensity during gait. 11 women, who had no medical history on musculoskeletal disease and surgery within 3 years prior to study, were participated. The walking energy cost per time (WECt) during 35minutes, heart rate intensity, and total calorie consumption were compared by using pair t-test. The WECt and total calorie consumption were found to be significantly higher(p<.05) in CDR than NR. However, there was no difference in HRi. Based on the present study, CDR shoe may have significant implications in shoe prescription for people who want to increase energy consumption.

• Journal of Environmental Health Sciences
• /
• v.47 no.2
• /
• pp.175-181
• /
• 2021

Objectives: The correlation between the size of a leak hole, the volume of the leakage, and the range of influence was investigated for a hydrochloric acid tank-lorry. Methods: For the case of a tank-lorry chemical accident, KORA (Korea Off-site Risk Assessment Supporting Tool) was used to predict the leak rate and the range of influence according to the size of the leak hole. The correlation was studied using R. Results: As a result of analyzing the leak rate change according to the leak hole size in a 35% hydrochloric acid tank-lorry, as the size of the leak hole increased from 1 to 100 mm, the leak rate increased from 0.008 to 83.94 kg/sec, following the power function. As a result of calculating the range of influence under conditions ranging from 1 to 100 mm in size and 10 to 60 minutes of leakage time, it was found that the range spanned from a minimum of 5.4 m to a maximum of 307.9 m. As a result of multiple regression analysis using R, the quadratic function model best explained the correlation between the size of the leak hole, the leak time, and the range of influence with an adjected coefficient of determination of 0.97 and a root mean square error of 22.33. Conclusion: If a correlation database for the size of a leak hole is accumulated for various substances and under various conditions, the amount of leakage and the range of influence can easily be calculated, facilitating field response activities.