• Communications for Statistical Applications and Methods
• /
• v.7 no.1
• /
• pp.327-336
• /
• 2000

We are mainly interested in hazard rate changes which are usually occur in survival times of manufactured products or patients. We may expect early failures with one hazard rate and next another hazard rate. For this type of data we apply a hazard rate change-point model and estimate the unkown time point to improve the model adequacy. We introduce change-point logistic model to the discrete time hazard rates. The MLEs are obtained routinely and we also explain the suggested model through a dataset of survival times.

• Architectural research
• /
• v.26 no.1
• /
• pp.13-20
• /
• 2024

This study is a research investigation into the properties of bubbles that affect the characteristics of foamed concrete during its production. The study examined the properties of bubbles based on the manufacturing conditions. To investigate these properties, the selected experimental factors included bead size, the length/diameter ratio of the bubble-generating tube, and compressed air. The experimental design used a design of experiments, and the test results were analyzed using analysis of variance. The foaming agent used to generate bubbles was AES (Alcohol Ethoxy Sulfate), and the method employed for bubble manufacture was the pre-foaming method. In the test results, a significant factor affecting the foaming rate of bubbles was the bead size; the highest foaming rate was observed when using 2mm beads. Bead size also primarily influenced the volume change of the aqueous solution, while other factors did not affect the foaming rate and volume change. None of the factors affected the change in bubble size, but compressed air was considered the main factor affecting bubble size and its change. The foaming rate and volume change of the aqueous solution showed a high correlation with each other. Spherical bubbles in the early stage eventually transformed into angular bubbles. Moreover, over time, it was observed that the bubble size increased.

• The Journal of Fisheries Business Administration
• /
• v.52 no.1
• /
• pp.47-63
• /
• 2021

The purpose of this study is to identify the leading price between Jeju and Wando's oliver flounder producer price and to analyze the dynamic effect of the regional producer price using the panel VAR model. In the process of analysis, it was confirmed that there are unit roots in the monthly data of Jeju and Wando's oliver flounder producer price. So, in order to avoid spurious regression, the rate change of producer price which carries out log difference was used in the analysis. As a result of the analysis, first, the panel Granger causality test showed that the influence of the change rate of producer price in oliver flounder in Jeju was slightly larger than that in Wando, but it was found that each region all leads the change rate of the producer price in oliver flounder. Second, the panel VAR estimation showed that the rate change of producer price in Jeju and Wando a month ago had a statistically significant effect on the change rate of producer price of each region. Third, the impulse response analysis indicated that other regions are affected a little more than the same region in case of the occurrence of the impact on the error terms of the change rate of produce price in Jeju and Wando oliver flounder. Fourth, the variance decomposition analysis showed that the change rate of producer price in the two regions was higher explained by Jeju compared to Wando. In conclusion, it is expected that the above results can not only be useful as basic data for the stabilization of oliver flounder producer price and the establishment of policies for easing volatility but can also help the oliver flounder industry operate its business.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.235-241
• /
• 2000

This article suggests integrated neural network models for the interest rate forecasting using change point detection. The basic concept of proposed model is to obtain intervals divided by change point, to identify them as change-point groups, and to involve them in interest rate forecasting. the proposed models consist of three stages. The first stage is to detect successive change points in interest rate dataset. The second stage is to forecast change-point group with data mining classifiers. The final stage is to forecast the desired output with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. This article is then to examine the predictability of integrated neural network models for interest rate forecasting using change-point detection.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.1283-1287
• /
• 2009

The Korean government implemented 259 road projects from 2004 to 2007, valued at $18.4 billion. Change orders of these road projects occurred 8,973 times and, subsequently, caused significant increases in the cost of the projects, approximately up to $4.2 billion (22.8% of the initial budget). These significant problems of huge change orders require a more workable control system for budget management whereas the effectiveness of the government's control is still not satisfied. However, previous approaches and studies mostly limited their analyses to simply classifying the causes of the change orders. This paper investigates the real frequency and cost impacts incurred by each cause of a change order, primarily based on 218 road projects in Korea. The paper then identifies the attributes of change orders through a survey of 204 project participants in that those sources were inevitable or avoided if properly managed. The causes of the change orders are further analyzed with analysis of variance (ANOVA) in connection with contract volume, bid award rate, the contractor's capacity to perform, and the design company's capacity. This study found that if the contract volume is smaller, then the possibility of change orders is higher. Interestingly, if the bid award rate is less than 67.5%, it signifies the highest rate of change orders. In addition, the contractors whose construction ability is assessed as the top-ranked group showed the lowest change order rates. With these results, this paper provides the preventive guidelines for reducing the likelihood of change orders.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2018.04a
• /
• pp.44-44
• /
• 2018

The seeds of soybean (Glycine max), adzuki bean (Vigna angularis), mung bean (Vigna radiata), and kidney bean (Phaseolus vulgaris L.) were examined the germination rate after 10 years of long-term storage ($-18^{\circ}C$) conservation. For soybean seeds, 2,313 accessions were examined and germination rate of 1,082 accessions was decreased with below 15% of initial germination rate. For 227 accessions of soybean, germination rate was decreased with above 15% of initial germination rate after 10 years of long-term storage, which is needed to be rejuvenated. Germination rate of 589 accessions was increased and showed no change for 415 accessions after 10 years of long-term storage. For adzuki bean seeds, 2,058 accessions were examined and germination rate of 739 accessions was decreased with below 15% of initial germination rate. For 63 accessions of adzuki bean, germination rate was decreased with above 15% of initial germination rate after 10 years of long-term storage, which is needed to be rejuvenated. Germination rate of 535 accessions was increased and showed no change for 721 accessions after 10 years of long-term storage. For mung bean seeds, 438 accessions were examined and germination rate of 139 accessions was decreased with below 15% of initial germination rate. For 5 accessions of mung bean, germination rate was decreased with above 15% of initial germination rate after 10 years of long-term storage, which is needed to be rejuvenated. Germination rate of 155 accessions was increased and showed no change for 139 accessions after 10 years of long-term storage. For kdney bean seeds, 366 accessions were examined and germination rate of 7 accessions was decreased with below 15% of initial germination rate. For 65 accessions of kidney bean, germination rate was decreased with above 15% of initial germination rate after 10 years of long-term storage, which is needed to be rejuvenated. Germination rate of 201 accessions was increased and showed no change for 93 accessions after 10 years of long-term storage.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.1
• /
• pp.23-28
• /
• 1996

In this series of two papers, adaptive code rate change schemes in DS-SSMA systems are proposed. In the proposed schemes the error correcting code rate is changed according to the channel states. Two channel states having significant effects on the bit error probability are considered: one is the effective number of users considered in Part 1, and the other is the fading environment considered in Part 2. These channel states are estimated based on retransmission requests. The criterion for the change of the code rate is to maximize the throughput under given error bound. Simulation results show that we can transmit maximum amount of information if we change the code rate based on the channel states.

• The Korean Journal of Applied Statistics
• /
• v.32 no.4
• /
• pp.561-572
• /
• 2019

We study false discovery rate segmentation (FDRSeg) and simultaneous multiscale change-point estimator (SMUCE) methods for multiscale multiple change-point estimation, and compare empirical behavior via simulation. FSRSeg is based on the control of a false discovery rate while SMUCE used for the multiscale local likelihood ratio tests. FDRSeg seems to work best if the number of change-points is large; however, FDRSeg and SMUCE methods can both provide similar estimation results when there are only a small number of change-points. As a real data application, multiple change-points estimation is done with the well-log data.

• Analytical Science and Technology
• /
• v.23 no.2
• /
• pp.109-118
• /
• 2010

Amended at the Law of indoor air quality management open a court according to the test method and excess standard of the fluid building material were changed. It used the paint and the putty in the fluid building material from this research and comparison of amended and original method it led and in about change direction of amended standard with change of the emission rate who is caused by in the amended test method and excess standard it examined. The reduction emission rate about 45% decreases in the change of test period of the paint, there was not an effect of the emission rate whom it follows in change of dry time. Also change of the emission rate whom it follows in change of application quantity the product which above $5\;mg/m^2h$ has the high emission rate the change of the emission rate is big but there was not change of the emission rate from the products of that others. The putty the emission rate about 61% decreases in case in the change of test period, there was not an effect of the emission rate whom it follows at dry time. The emission rate about 164% increased with increase of application quantity. It tried to compare two test methods, it compared in the paint and putty all current test method it was relaxed the possibility of knowing the thing there was a standard.

• 한국데이터정보과학회:학술대회논문집
• /
• 2003.10a
• /
• pp.57-72
• /
• 2003

This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.