• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.121-121
• /
• 2020

Varying dominant processes, including Tropical Cyclone (TC) and non-TC rainfall events, have been known to drive the occurrence of precipitation in South Korea. With the changes in the pattern of the Earth's climate due to anthropogenic activities, nonstationarity or changes in the magnitude and frequency of these dominant processes have been separately observed for the past decades and are expected to continue in the coming years. These changes often cause unprecedented hydrologic events such as extreme flooding which pose a greater risk to the society. This study aims to take into account a more reliable future climate condition with two dominant processes. Diverse statistical models including the hidden markov chain, K-nearest neighbor algorithm, and quantile mappings are utilized to mimic future rainfall events based on the recorded historical data with the consideration of the varying effects of TC and non-TC events. The data generated is then utilized to the hydrologic model to conduct a flood frequency analysis. Results in this study emphasize the need to consider the nonstationarity of design rainfalls to fully grasp the degree of future flooding events when designing urban water infrastructures.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.150-152
• /
• 2022

In this work, we propose a model that considers the behavior and synaptic plasticity of sensory neurons based on Liquid Time-constant Network (LTC). The neuron connection structure was experimented with four types: the increasing number of neurons, the decreasing number, the decreasing number, and the decreasing number. In this study, we experimented using a time series prediction dataset to see if the performance of the changed model improved compared to LTC. Experimental results show that the application of modeling of sensory neurons does not always bring about performance improvements, but improves performance through proper selection of learning rules depending on the type of dataset. In addition, the connective structure of neurons showed improved performance when it was less than four layers.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.822-835
• /
• 2023

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder-decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.9
• /
• pp.4049-4054
• /
• 2014

Background: Race and ethnicity are significant factors in predicting survival time of breast cancer patients. In this study, we applied advanced statistical methods to predict the survival of White non-Hispanic female breast cancer patients, who were diagnosed between the years 1973 and 2009 in the United States (U.S.). Materials and Methods: Demographic data from the Surveillance Epidemiology and End Results (SEER) database were used for the purpose of this study. Nine states were randomly selected from 12 U.S. cancer registries. A stratified random sampling method was used to select 2,000 female breast cancer patients from these nine states. We compared four types of advanced statistical probability models to identify the best-fit model for the White non-Hispanic female breast cancer survival data. Three model building criterion were used to measure and compare goodness of fit of the models. These include Akaike Information Criteria (AIC), Bayesian Information Criteria (BIC), and Deviance Information Criteria (DIC). In addition, we used a novel Bayesian method and the Markov Chain Monte Carlo technique to determine the posterior density function of the parameters. After evaluating the model parameters, we selected the model having the lowest DIC value. Using this Bayesian method, we derived the predictive survival density for future survival time and its related inferences. Results: The analytical sample of White non-Hispanic women included 2,000 breast cancer cases from the SEER database (1973-2009). The majority of cases were married (55.2%), the mean age of diagnosis was 63.61 years (SD = 14.24) and the mean survival time was 84 months (SD = 35.01). After comparing the four statistical models, results suggested that the exponentiated Weibull model (DIC= 19818.220) was a better fit for White non-Hispanic females' breast cancer survival data. This model predicted the survival times (in months) for White non-Hispanic women after implementation of precise estimates of the model parameters. Conclusions: By using modern model building criteria, we determined that the data best fit the exponentiated Weibull model. We incorporated precise estimates of the parameter into the predictive model and evaluated the survival inference for the White non-Hispanic female population. This method of analysis will assist researchers in making scientific and clinical conclusions when assessing survival time of breast cancer patients.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.14 no.3
• /
• pp.509-521
• /
• 1994

This study is an effort to develop computer simulation model that produce precipitation patterns from stochastic model. A stochastic model is formulated for the process of daily precipitation with considering the sequences of wet and dry days and the precipitation amounts on wet days. This study consists of 2 papers and the process of precipitation occurrence is modelled by an alternate renewal process (ARP) in paper (I). In the ARP model for the precipitation occurrence, four discrete distributions, used to fit the wet and dry spells, were as follows; truncated binomial distribution (TBD), truncated Poisson distribution (TPD), truncated negative binomial distribution (TNBD), logarithmic series distribution (LSD). In companion paper (II) the process of occurrence is developed by Markov chain. The amounts of precipitation, given that precipitation has occurred, are described by a Gamma. Pearson Type-III, Extremal Type-III, and 3 parameter Weibull distribution. Daily precipitation series model consists of two models, A-Wand A-G model, by combining the process of precipitation occurrence and a continuous probability distribution on the precipitation of wet days. To evaluate the performance of the simulation model, output from the model was compared with historical data of 7 stations in the Nakdong and Seomjin river basin. The results of paper (1) show that it is possible to design a model for the synthetic generation of IX)int precipitation patterns.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2484-2496
• /
• 2000

High speed switches have been developing to interconnect a large number of nodes. It is important to analyze the switch performance under various conditions to satisfy the requirements. Queueing analysis, in general, has the intrinsic problem of large state space dimension and complex computation. In fact, The petri net is a graphical and mathematical model. It is suitable for various applications, in particular, manufacturing systems. It can deal with parallelism, concurrence, deadlock avoidance, and asynchronism. Currently it has been applied to the performance of computer networks and protocol verifications. This paper presents a framework for modeling and analyzing ATM switch using stochastic activity networks (SANs). In this paper, we provide the ATM switch model using SANs to extend easily and an approximate analysis method to apply A TM switch models, which significantly reduce the complexity of the model solution. Cell arrival process in output-buffered Queueing A TM switch with finite buffer is modeled as Markov Modulated Poisson Process (MMPP), which is able to accurately represent real traffic and capture the characteristics of bursty traffic. We analyze the performance of the switch in terms of cell-loss ratio (CLR), mean Queue length and mean delay time. We show that the SAN model is very useful in A TM switch model in that the gates have the capability of implementing of scheduling algorithm.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.313-324
• /
• 2008

A sentence reduction is the information compression process which removes extraneous words and phrases and retains basic meaning of the original sentence. Most researches in the sentence reduction have required a large number of lexical and syntactic resources and focused on extracting or removing extraneous constituents such as words, phrases and clauses of the sentence via the complicated parsing process. However, these researches have some problems. First, the lexical resource which can be obtained in loaming data is very limited. Second, it is difficult to reduce the sentence to languages that have no method for reliable syntactic parsing because of an ambiguity and exceptional expression of the sentence. In order to solve these problems, we propose the sentence reduction method which uses templates and POS(part of speech) information without a parsing process. In our proposed method, we create a new sentence using both Sentence Reduction Templates that decide the reduction sentence form and Grammatical POS-based Reduction Rules that compose the grammatical sentence structure. In addition, We use Viterbi algorithms at HMM(Hidden Markov Models) to avoid the exponential calculation problem which occurs under applying to Sentence Reduction Templates. Finally, our experiments show that the proposed method achieves acceptable results in comparison to the previous sentence reduction methods.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.35-44
• /
• 2000

In this paper, we propose a new trajectory model for characterizing segmental features and their interaction based upon a general framework of hidden Markov models. Each segment, a sequence of vectors, is represented by a trajectory of observed sequences. This trajectory is obtained by applying a new design matrix which includes transitional information on contiguous frames, and is characterized as a polynomial regression function. To apply the trajectory to the segmental HMM, the frame features are replaced with the trajectory of a given segment. We also propose the likelihood of a given segment and the estimation of trajectory parameters. The obervation probability of a given segment is represented as the relation between the segment likelihood and the estimation error of the trajectories. The estimation error of a trajectory is considered as the weight of the likelihood of a given segment in a state. This weight represents the probability of how well the corresponding trajectory characterize the segment. The proposed model can be regarded as a generalization of a conventional HMM and a parametric trajectory model. The experimental results are reported on the TIMIT corpus and performance is show to improve significantly over that of the conventional HMM.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.917-929
• /
• 2017

Korean income data obtained from Korea Labor Panel Survey shows excessive zeros, which may not be properly explained by the Tobit model. In this paper, we analyze the data using a zero-inflated Tobit model to incorporate excessive zeros. A zero-inflated Tobit model consists of two stages. In the first stage, individuals with 0 income are divided into two groups: genuine zero group and random zero group. Individuals in the genuine zero group did not participate labor market since they have no intention to do so. Individuals in the random zero group participated labor market but their incomes are very low and truncated at 0. In the second stage, the Tobit model is assumed to a subset of data combining random zeros and positive observations. Regression models are employed in both stages to obtain the effect of explanatory variables on the participation of labor market and the income amount. Markov chain Monte Carlo methods are applied for the Bayesian analysis of the data. The proposed zero-inflated Tobit model outperforms the Tobit model in model fit and prediction of zero frequency. The analysis results show strong evidence that the probability of participating in the labor market increases with age, decreases with education, and women tend to have stronger intentions on participating in the labor market than men. There also exists moderate evidence that the probability of participating in the labor market decreases with socio-economic status and reserved wage. However, the amount of monthly wage increases with age and education, and it is larger for married than unmarried and for men than women.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.25 no.6
• /
• pp.394-404
• /
• 2013

In the present study, the characteristics of spectral peakedness parameter $Q_p$, bandwidth parameter ${\varepsilon}$, and spectral width parameter ${\nu}$ were analyzed as a first step to define the swell waves quantitatively. For the analysis, the joint probability density function of significant wave heights and peak periods were newly developed. The MCMC(Markov Chain Monte Carlo) simulations have been performed to generate the significant wave heights and peak periods from the developed probability density functions. Applying the simulated significant wave heights and peak periods to the theoretical wave spectrum models, the spectral shapes parameters were obtained and analyzed. Among the spectral shape parameters, only the spectral peakedness parameter $Q_p$, is shown to be independent with the significant wave height and peak wave period. It also best represents the peakedness of the spectral shape, and henceforth $Q_p$ should be used to define the swell waves with a wave period. For the field verification of the results, wave data obtained from Hupo port and Ulleungdo were analyzed and results showed the same trend with the MCMC simulation results.