• Journal of Wetlands Research
• /
• v.25 no.3
• /
• pp.167-175
• /
• 2023

Precipitation data is one of the essential input datasets used in various fields such as wetland management, hydrological simulation, and water resource management. In order to efficiently manage water resources using precipitation data, it is essential to secure as much data as possible by minimizing the missing rate of data. In addition, more efficient hydrological simulation is possible if precipitation data for ungauged areas are secured. However, missing precipitation data have been estimated mainly by statistical equations. The purpose of this study is to propose a new method to restore missing precipitation data using machine learning algorithms that can predict new data based on correlations between data. Moreover, compared to existing statistical methods, the applicability of machine learning techniques for restoring missing precipitation data is evaluated. Representative machine learning algorithms, Artificial Neural Network (ANN) and Random Forest (RF), were applied. For the performance of classifying the occurrence of precipitation, the RF algorithm has higher accuracy in classifying the occurrence of precipitation than the ANN algorithm. The F1-score and Accuracy values, which are evaluation indicators of the classification model, were calculated as 0.80 and 0.77, while the ANN was calculated as 0.76 and 0.71. In addition, the performance of estimating precipitation also showed higher accuracy in RF than in ANN algorithm. The RMSE of the RF and ANN algorithms was 2.8 mm/day and 2.9 mm/day, and the values were calculated as 0.68 and 0.73.

• Health Policy and Management
• /
• v.33 no.4
• /
• pp.450-456
• /
• 2023

Background: This study aims to develop a "Predictive Model for the Possibility of Collection Delinquent Health Insurance Contributions" for the National Health Insurance Service to enhance administrative efficiency in protecting and collecting contributions from livelihood-type defaulters. Additionally, it aims to establish customized collection management strategies based on individuals' ability to pay health insurance contributions. Methods: Firstly, to develop the "Predictive Model for the Possibility of Collection Delinquent Health Insurance Contributions," a series of processes including (1) analysis of defaulter characteristics, (2) model estimation and performance evaluation, and (3) model derivation will be conducted. Secondly, using the predictions from the model, individuals will be categorized into four types based on their payment ability and livelihood status, and collection strategies will be provided for each type. Results: Firstly, the regression equation of the prediction model is as follows: phat = exp (0.4729 + 0.0392 × gender + 0.00894 × age + 0.000563 × total income - 0.2849 × low-income type enrollee - 0.2271 × delinquency frequency + 0.9714 × delinquency action + 0.0851 × reduction) / [1 + exp (0.4729 + 0.0392 × gender + 0.00894 × age + 0.000563 × total income - 0.2849 × low-income type enrollee - 0.2271 × delinquency frequency + 0.9714 × delinquency action + 0.0851 × reduction)]. The prediction performance is an accuracy of 86.0%, sensitivity of 87.0%, and specificity of 84.8%. Secondly, individuals were categorized into four types based on livelihood status and payment ability. Particularly, the "support needed group," which comprises those with low payment ability and low-income type enrollee, suggests enhancing contribution relief and support policies. On the other hand, the "high-risk group," which comprises those without livelihood type and low payment ability, suggests implementing stricter default handling to improve collection rates. Conclusion: Upon examining the regression equation of the prediction model, it is evident that individuals with lower income levels and a history of past defaults have a lower probability of payment. This implies that defaults occur among those without the ability to bear the burden of health insurance contributions, leading to long-term defaults. Social insurance operates on the principles of mandatory participation and burden based on the ability to pay. Therefore, it is necessary to develop policies that consider individuals' ability to pay, such as transitioning livelihood-type defaulters to medical assistance or reducing insurance contribution burdens.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.28 no.3
• /
• pp.66-73
• /
• 2024

Stay-cable is one of the most important load carrying members in cable-stayed bridges. Monitoring structural integrity of stay-cables is crucial for evaluating the structural condition of the cable-stayed bridge. For stay-cables, tension and damping ratio are estimated based on modal properties as a measure of structural integrity. Since the monitoring system continuously measures the vibration for the long-term period, data acquisition systems should be stable and power-efficiency as the hardware system. In addition, massive signals from the data acquisition systems are continuously generated, so that automated analysis system should be indispensable. In order to fulfill these purpose simultaneously, this study presents an autonomous cable monitoring system based on domain-knowledge using IoT for continuous cable monitoring systems of cable-stayed bridges. An IoT system was developed to provide effective and power-efficient data acquisition and on-board processing capability for Edge-computing. Automated peak-picking algorithm using domain knowledge was embedded to the IoT system in order to analyze massive data from continuous monitoring automatically and reliably. To evaluate its operational performance in real fields, the developed autonomous monitoring system has been installed on a cable-stayed bridge in Korea. The operational performance are confirmed and validated by comparing with the existing system in terms of data transmission rates, accuracy and efficiency of tension estimation.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.1
• /
• pp.21-29
• /
• 2006

In this Paper a split bandwidth wideband speech coder and its highband coding method are Proposed. The coder uses a split-band approach. where the wideband input speech signal is split into two equal frequency bands from 0-4kHz and 4-8kHz. The lowband and the highband are coded respectively by the 11.8kb/s G.729 Annex E and the proposed coding method. After the LPC analysis, the highband is divided by two modes according to the properties of signals. In stationary mode. the highband signals are compressed by the mixture excitation model; CELP algorithm and W (Matching Pursuit) algorithm. The others are coded by the only CELP algorithm. We compare the performance of the new wideband speech coder with that of G.722 48kbps SB-ADPCM and G.722.2 12.85kbps in a subjective method. The simulation results show that the Performance of the proposed wideband speech coder has better than that of 48kbps G.722 and no better than that of 12.85kbps G.722.2.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.7
• /
• pp.458-467
• /
• 2010

In this paper, a new audio reproduction system was developed in which the cross-talk signals would be reasonably cancelled at an arbitrary listener position. To adaptively remove the cross-talk signals according to the listener's position, a method of tracking the listener position was employed. This was achieved using the two microphones, where the listener direction was estimated using the time-delay between the two signals from the two microphones, respectively. Moreover, room reverberation effects were taken into consideration where linear prediction analysis was involved. To remove the cross-talk signals at the left-and right-ears, the paths between the sources and the ears were represented using the KEMAR head-related transfer functions (HRTFs) which were measured from the artificial dummy head. To evaluate the usefulness of the proposed listener tracking system, the performance of cross-talk cancellation was evaluated at the estimated listener positions. The performance was evaluated in terms of the channel separation ration (CSR), a -10 dB of CSR was experimentally achieved although the listener positions were more or less deviated. A real-time system was implemented using a floating-point digital signal processor (DSP). It was confirmed that the average errors of the listener direction was 5 degree and the subjects indicated that 80 % of the stimuli was perceived as the correct directions.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.4
• /
• pp.347-357
• /
• 2003

This paper describes on the suppression of sea clutter on marine radar display using a cell-averaging CFAR(constant false alarm rate) technique, and on the analysis of radar echo signal data in relation to the estimation of ARPA functions and the detection of the shadow effect in clutter returns. The echo signal was measured using a X -band radar, that is located on the Pukyong National University, with a horizontal beamwidth of $$3.9^{\circ}$$, a vertical beamwidth of $20^{\circ}$, pulsewidth of $0.8 {\mu}s$ and a transmitted peak power of 4 ㎾ The suppression performance of sea clutter was investigated for the probability of false alarm between $l0-^0.25;and; 10^-1.0$. Also the performance of cell averaging CFAR was compared with that of ideal fixed threshold. The motion vectors and trajectory of ships was extracted and the shadow effect in clutter returns was analyzed. The results obtained are summarized as follows；1. The ARPA plotting results and motion vectors for acquired targets extracted by analyzing the echo signal data were displayed on the PC based radar system and the continuous trajectory of ships was tracked in real time. 2. To suppress the sea clutter under noisy environment, a cell averaging CFAR processor having total CFAR window of 47 samples(20+20 reference cells, 3+3 guard cells and the cell under test) was designed. On a particular data set acquired at Suyong Man, Busan, Korea, when the probability of false alarm applied to the designed cell averaging CFAR processor was 10$^{-0}$.75/ the suppression performance of radar clutter was significantly improved. The results obtained suggest that the designed cell averaging CFAR processor was very effective in uniform clutter environments. 3. It is concluded that the cell averaging CF AR may be able to give a considerable improvement in suppression performance of uniform sea clutter compared to the ideal fixed threshold. 4. The effective height of target, that was estimated by analyzing the shadow effect in clutter returns for a number of range bins behind the target as seen from the radar antenna, was approximately 1.2 m and the information for this height can be used to extract the shape parameter of tracked target..

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• (The) Research of the performance art and culture
• /
• no.18
• /
• pp.315-346
• /
• 2009

Korean 'Sin-Pa' play is a way to examine self-reliance of Korean culture and influence of Japanese culture on the Korean one in the early modern times. Although the 'Sin-Pa' play has been estimated negatively in many aspects, such an estimation can be different depending on the methodology. Therefore, I tried to explain a characteristics of the rise of 'Sin-Pa' play. While making these trials, I made efforts to reappreciate the developing process of Korean 'Sin-Pa' play and its theatrical structure and value. Particularly, I focused on structure of 'Sin-Pa' play in the context of an actual cognition of colonized Korea. Based on the 'Sin-Pa' play's repertoires I found out that one of the representative characteristics of Korean 'Sin-Pa' play is a changing process from orality to literacy. And I made attempts to uncover some ideological functions and their effects of 'Sin-Pa' play, focusing on and whose story line is usually consisted of 'provocation-pangs-defeat' while it interacted with 'provocation-pangs-penalty' of the structure of melodrama under the contemporary cultural conditions. 'Sin-Pa'' play can be considered as a performance mode to accept the Japanese value embedded in the colonized Korea since the 1910s on the one hand and to resist the overwhelming power of western culture imported through Japan on the other hand. In other words, it was closely related with the cultural-field of that period. Based on these results of this research, I tried to outline what the mode of 'Sin-Pa' was, what it reflected, and what it desired for under the influence of the contemporary cultural conditions. I analysed double qualities of 'Sin-Pa' play as a dominant narrative and/or a resistant narrative considering its relationship with the people of colonized Korea. And also I examined the place of the 'Sin-Pa' play in the history of theatre and in the history of culture.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.41 no.4
• /
• pp.250-258
• /
• 2021

This study was conducted to investigate the effect of feeding systems on feed intake, weight gain, and fawn performance (Cervus canadensis) and estimation of grazing intensity in Elk doe at pasture. A sixteen Elk doe about 236.2 kg were randomly assigned to two feeding treatments. The treatment consisted of a barn feeding system (BF) and grazing at pasture (GR), and pasture was mainly composed of tall fescue, orchard grass, and Kentucky bluegrass. The moisture content of pasture was 19.51~22.61%, which was similar during experimental periods. The crude protein content was significantly higher from June to July (p<0.05). The contents of neutral detergent fiber and acid detergent fiber ranged 53.65~60.18%, and 26.08~29.10%, respectively. There were no significant differences between feeding systems on supplementary feed intake, but the roughage and total dry matter intake showed significant differences between treatment groups (p<0.05), except for May. In August, roughage intake was dramatically decreased in the GR group due to summer environmental changes. On the other hand, the higher intake of roughage in September might be related to nutrient intake for mammals. There was no difference in body weight between treatment groups, but the fawn performance was significantly higher in the GR group (p<0.05). These results might be suggested that grazing elk doe might positively affect fawn growth. However, it is considered that BF might increase the deer weaning rate during the parturition period, since the lower weaning rate in the GR group compared to the BF group. The grazing intensity of Elk doe was increased from May to July and decreased in August, which was influenced by pasture productivity. The average grazing intensity of Elk doe was found to be 15 heads/ha, which might be controlled by supplementary feeding. Further studies needed that mixed sowing methods and fertilization management in old grazing pastures for improved pasture productivity.

• Journal of The Korean Association For Science Education
• /
• v.32 no.1
• /
• pp.160-181
• /
• 2012

The purpose of this study is to understand raters' errors in rating performance assessments of science inquiry. For this, 60 middle school students performed scientific inquiry about sound propagation and 4 trained raters rated their activity sheets. Variance components estimation for the result of the generalizability analysis for the person, task, rater design, the variance components for rater, rater by person and rater by task are about 25%. Among 4 raters, 2 raters' severity is higher than the other two raters and their severities were stabilized. Four raters' rating agreed with each other in 51 cases among the 240 cases. Through the raters' conferences, the rater error types for 189 disagreed cases were identified as one of three types; different salience, severity, and overlooking. The error type 1, different salience, showed 38% of the disagreed cases. Salient task and salient assessment components are different among the raters. The error type 2, severity, showed 25% and the error type 3, overlooking showed 31%. The error type 2 seemed to have happened when the students responses were on the borders of two levels. Error type 3 seemed to have happened when raters overlooked some important part of students' responses because she or he immersed her or himself in one's own salience. To reduce the above rater errors, raters' conference in salience of task and assesment components are needed before performing the holistic scoring of complex tasks. Also raters need to recognize her/his severity and efforts to keep one's own severity. Multiple raters are needed to prevent the errors from being overlooked. The further studies in raters' tendencies and sources of different interpretations on the rubric are suggested.