• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권1호
• /
• pp.81-98
• /
• 2013

Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.194-202
• /
• 2019

Reliability analysis of the components frequently starts with the data that manufacturer provides. If enough failure data are collected from the field operations, the reliability should be recomputed and updated on the basis of the field failure data. However, when the failure time record for a component contains only a few observations, all statistical methodologies are limited. In this case, where the failure records for multiple number of identical components are available, a valid alternative is combining all the data from each component into one data set with enough sample size and utilizing the useful information in the censored data. The ROK Navy has been operating multiple Patrol Killer Guided missiles (PKGs) for several years. The Korea Multi-Function Control Console (KMFCC) is one of key components in PKG combat system. The maintenance record for the KMFCC contains less than ten failure observations and a censored datum. This paper proposes a Bayesian approach with a Dirichlet mixture model to estimate failure time density for KMFCC. Trends test for each component record indicated that null hypothesis, that failure occurrence is renewal process, is not rejected. Since the KMFCCs have been functioning under different operating environment, the failure time distribution may be a composition of a number of unknown distributions, i.e. a mixture distribution, rather than a single distribution. The Dirichlet mixture model was coded as probabilistic programming in Python using PyMC3. Then Markov Chain Monte Carlo (MCMC) sampling technique employed in PyMC3 probabilistically estimated the parameters' posterior distribution through the Dirichlet mixture model. The simulation results revealed that the mixture models provide superior fits to the combined data set over single models.

• 한국통신학회논문지
• /
• 제29권1C호
• /
• pp.65-71
• /
• 2004

본 논문은 주성분분석(PCA, Principle Component Analysis) 혹은 독립성분분석(ICA, Independent Principle Component Analysis)를 이용하여 HMM(Hidden Markov Model) 파라메타의 차수를 감소시킴으로써 MLLR(Maximum Likelihood Linear Regression) 화자 적응 알고리즘을 개선하였다. 데이터의 특징을 잘 나타내는 PCA와 ICA를 통해 모델 mixture component의 상관관계를 줄이고 상대적으로 데이터의 분포가 적은 축을 삭제함으로써 추정해야 하는 적응 파라메타의 수를 줄였다. 기존의 MLLR 알고리즘은 SI(Speaker Independent)모델 보다 좋은 인식성능을 나타내기 위해 30초 이상의 적응 데이터가 요구되었고, 반면 제안한 알고리즘은 적응 파라메타의 수를 감소시킴으로써 10초 이상의 적응데이터가 요구되었다. 또한, 36차의 HMM 파라메타는 기존의 MLLR 알고리즘과 비슷한 인식성능을 나다내는 10차의 주성분이나 독릭성분을 사용함으로써 MLLR 알고리즘에서 적응파라메타를 추정할 때 요구되는 연산량을 1/167로 감소시켰다.

• 인터넷정보학회논문지
• /
• 제9권6호
• /
• pp.165-177
• /
• 2008

멀티 에이전트 강화학습에서 중요한 이슈 중의 하나는 자신의 성능에 영향을 미칠 수 있는 다른 에이전트들이 존재하는 동적 환경에서 어떻게 최적의 행동 정책을 학습하느냐 하는 것이다. 멀티 에이전트 강화 학습을 위한 기존 연구들은 대부분 단일 에이전트 강화 학습기법들을 큰 변화 없이 그대로 적용하거나 비록 다른 에이전트에 관한 별도의 모델을 이용하더라도 현실적이지 못한 가정들을 요구한다. 본 논문에서는 상대 에이전트에 대한 나이브 베이지안 기반의 행동 정책 모델을 소개한 뒤, 이것을 이용한 강화 학습 방법을 설명한다. 본 논문에서 제안하는 멀티 에이전트 강화학습 방법은 기존의 멀티 에이전트 강화 학습 연구들과는 달리 상대 에이전트의 Q 평가 함수 모델이 아니라 나이브 베이지안 기반의 행동 정책 모델을 학습한다. 또한, 표현력은 풍부하나 학습에 시간과 노력이 많이 요구되는 유한 상태 오토마타나 마코프 체인과 같은 행동 정책 모델들에 비해 비교적 간단한 형태의 행동 정책 모델은 이용함으로써 학습의 효율성을 높였다. 본 논문에서는 대표적인 적대적 멀티 에이전트 환경인 고양이와 쥐게임을 소개한 뒤, 이 게임을 테스트 베드 삼아 실험들을 전개함으로써 제안하는 나이브 베이지안 기반의 정책 모델의 효과를 분석해본다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제22권1호
• /
• pp.124-130
• /
• 2009

Estimating genetic interaction effects in animal genomics would be one of the most challenging studies because the phenotypic variation for economically important traits might be largely explained by interaction effects among multiple nucleotide sequence variants under various environmental exposures. Genetic improvement of economic animals would be expected by understanding multi-locus genetic interaction effects associated with economic traits. Most analyses in animal breeding and genetics, however, have excluded the possibility of genetic interaction effects in their analytical models. This review discusses a historical estimation of the genetic interaction and difficulties in analyzing the interaction effects. Furthermore, two recently developed methods for assessing genetic interactions are introduced to animal genomics. One is the restricted partition method, as a nonparametric grouping-based approach, that iteratively utilizes grouping of genotypes with the smallest difference into a new group, and the other is the Bayesian method that draws inferences about the genetic interaction effects based on their marginal posterior distributions and attains the marginalization of the joint posterior distribution through Gibbs sampling as a Markov chain Monte Carlo. Further developing appropriate and efficient methods for assessing genetic interactions would be urgent to achieve accurate understanding of genetic architecture for complex traits of economic animals.

• Journal of Communications and Networks
• /
• 제16권1호
• /
• pp.81-91
• /
• 2014

This paper proposes hidden-node aware grouping (HAG) algorithm to enhance the performance of institute of electrical and electronics engineers (IEEE) 802.15.4 networks when they undergo either severe collisions or frequent interferences by hidden nodes. According to the degree of measured collisions and interferences, HAG algorithm dynamically transforms IEEE 802.15.4 protocol between a contention algorithm and a contention-limited one. As a way to reduce the degree of contentions, it organizes nodes into some number of groups and assigns each group an exclusive per-group time slot during which only its member nodes compete to grab the channel. To eliminate harmful disruptions by hidden nodes, especially, it identifies hidden nodes by analyzing the received signal powers that each node reports and then places them into distinct groups. For load balancing, finally it flexibly adapts each per-group time according to the periodic average collision rate of each group. This paper also extends a conventional Markov chain model of IEEE 802.15.4 by including the deferment technique and a traffic source to more accurately evaluate the throughput of HAG algorithm under both saturated and unsaturated environments. This mathematical model and corresponding simulations predict with 6%discrepancy that HAG algorithm can improve the performance of the legacy IEEE 802.15.4 protocol, for example, even by 95% in a network that contains two hidden nodes, resulting in creation of three groups.

• Spatial Information Research
• /
• 제2권1호
• /
• pp.47-51
• /
• 1994

본 연구의 목적은 토지자원의 유효한 개발과 관리를 위해 원격탐사 자료 및 지상자료를 이용하여 토지피복(이용)의 예측 모형을 정립하고 실제로 제주도 지역에 적용하여 그 실증을 거치는 것이었다. 본 모형은 계절분석(multi-date processing)및 다중 분석(multi-file proces-sing)기법을 채택하고 Markov의 확률 이전 계산법 및 판별 함수(discriminant function)계산법으로 부터 합성 출현시킨 공간적/시간적 토지 이용 투영방법을 채택하였다. 판별 함수 계산법은 토지피복(이용)변화상의 최다 경향치를 산출 하기 위해 제주도 경관 평면(Iandscape plane)전지역의 각 화소(pixel)에 적용되고, 확율 이전 계산법은 특정 미래 시간 간극상에서 상이한 토지피복(이용)으로 변화하는 이들 화소의 수량을 결정한다. 본합성 모형은 이렇게 토지피복 변화상(공간적)과 그 화소의 수량(정량적)을 결합하여 경관 평면상에서 미래의 토지피복 예측을 가능케 하는 것이다.

• 전자공학회논문지S
• /
• 제35S권2호
• /
• pp.1-9
• /
• 1998

ATM was adopted as the switching and multiplexing technique for BISDN which aims at transmitting traffics with various characteristics in a unified network. To construct these ATM networks, the most important aspect is the design of the switching system with high performance and different service capabilities. In this paepr, we analyze the performance of an input and output queueing switch with preemptive priority which is considered to be most suitable for ATM networks. For the analysis of an input queue, we model each input queue as two separate virtual input queues for each priority class and we approximage them asindependent Geom/Geom/1 queues. And we model a virtual HOL queue which consists of HOL cells of all virtual input queues which have the same output address to obtain the mean service time at each virtual input queue. For the analysis of an output quque, we obtain approximately the arrival process into the output queue from the state of the virtual HOL queue. We use a Markov chain method to analyze these two models and obtain the maximum throughput of the switch and the mean queueing delay of cells. and analysis results are compared with simulation to verify that out model yields accurate results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1579-1602
• /
• 2020

In the design of production system, buffer capacity allocation is a major step. Through polymorphism analysis of production capacity and production capability, this paper investigates a buffer allocation optimization problem aiming at the multi-stage production line including unreliable machines, which is concerned with maximizing the system theoretical production rate and minimizing the system state entropy for a certain amount of buffers simultaneously. Stochastic process analysis is employed to establish Markov models for repairable modular machines. Considering the complex structure, an improved vector UGF (Universal Generating Function) technique and composition operators are introduced to construct the system model. Then the measures to assess the system's multi-state reliability and structural complexity are given. Based on system theoretical production rate and system state entropy, mathematical model for buffer capacity optimization is built and optimized by a specific genetic algorithm. The feasibility and effectiveness of the proposed method is verified by an application of an engine head production line.

• 응용통계연구
• /
• 제22권1호
• /
• pp.115-127
• /
• 2009

The purpose of statistical analyses of array-CGH experiment data is to divide the whole genome into regions of equal copy number, to quantify the copy number in each region and finally to evaluate its significance of being different from two. Several statistical procedures have been proposed which include the circular binary segmentation, and a Gaussian based local regression for detecting break points (GLAD) by estimating a piecewise constant function. We propose in this note a penalized spline regression and its simultaneous confidence band(SCB) approach to evaluate the statistical significance of regions of genetic gain/loss. The region of which the simultaneous confidence band stays above 0 or below 0 can be considered as a region of genetic gain or loss. We compare the performance of the SCB procedure with GLAD and hidden Markov model approaches through a simulation study in which the data were generated from AR(1) and AR(2) models to reflect spatial dependence of the array-CGH data in addition to the independence model. We found that the SCB method is more sensitive in detecting the low level copy number alterations.