• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권1호
• /
• pp.385-405
• /
• 2019

High Efficiency Video Coding (HEVC) enables significantly improved compression performance relative to existing standards. However, the advance also requires high computational complexity. To accelerate the intra prediction mode decision, a minimum risk Bayesian classification framework is introduced. The classifier selects a small number of candidate modes to be evaluated by a rate-distortion optimization process using the sum of absolute Hadamard transformed difference (SATD). Moreover, the proposed method provides a loss factor that is a good trade-off model between computational complexity and coding efficiency. Experimental results show that the proposed method achieves a 31.54% average reduction in the encoding run time with a negligible coding loss of 0.93% BD-rate relative to HEVC test model 16.6 for the Intra_Main common test condition.

• 품질경영학회지
• /
• 제46권1호
• /
• pp.39-74
• /
• 2018

Purpose: For more than 30 years, robust parameter design (RPD), which attempts to minimize the process bias (i.e., deviation between the mean and the target) and its variability simultaneously, has received consistent attention from researchers in academia and industry. Based on Taguchi's philosophy, a number of RPD methodologies have been developed to improve the quality of products and processes. The primary purpose of this paper is to review and discuss existing RPD methodologies in terms of the three sequential RPD procedures of experimental design, parameter estimation, and optimization. Methods: This literature study composes three review aspects including experimental design, estimation modeling, and optimization methods. Results: To analyze the benefits and weaknesses of conventional RPD methods and investigate the requirements of future research, we first analyze a variety of experimental formats associated with input control and noise factors, output responses and replication, and estimation approaches. Secondly, existing estimation methods are categorized according to their implementation of least-squares, maximum likelihood estimation, generalized linear models, Bayesian techniques, or the response surface methodology. Thirdly, optimization models for single and multiple responses problems are analyzed within their historical and functional framework. Conclusion: This study identifies the current RPD foundations and unresolved problems, including ample discussion of further directions of study.

• 한국정보과학회논문지:컴퓨팅의 실제 및 레터
• /
• 제14권5호
• /
• pp.527-531
• /
• 2008

스캐너를 이용해 스캔한 데이타는 오차를 포함하고 있으며, 이러한 오차는 통계적인 성질을 갖는 경우가 많다. 이러한 이유에서 통계적인 방법은 오차 처리를 위해 매우 효과적인 방법이며, 최근 많은 연구가 이루어지고 있다. 이러한 통계적인 방법 중 대표적인 방법인 점 추정 방법은 데이타의 여러 성질을 나타내지 못하고 단지 확률이 최대가 되는 부분의 성질만을 나타내는 한계가 있으며, 이러한 한계로 인하여 오버피팅 문제가 발생하게 된다. 이러한 한계를 극복하고 오버피팅 문제를 해결하기 위해서 본 논문에서는 변분 베이지안 방법을 이용한다. 점집합의 오차를 제거하기 위해 지역적 근사곡면을 사용하고, 높이함수를 이용해서 근사곡면을 나타낸다. 변분 베이지안 방법을 사용하여 오차가 제거된 근사곡면을 구하고, 주어진 점들을 근사곡면으로 매핑하여 오차를 제거한다. 제시된 방법은 계량적 실험과 실제 스캔된 자료를 이용한 실험을 통하여 검증된다.

• Journal of the Korean Statistical Society
• /
• 제29권4호
• /
• pp.435-441
• /
• 2000

Ko(1998, 1999) proposed certain flexible two-stage plans that could be served as one-step interim analysis in on-going clinical trials. The proposed Plans are optimal simultaneously in both a Bayes and a Neyman-Pearson sense. The Neyman-Pearson interpretation is that average expected sample size is being minimized, subject just to the two overall error rates $\alpha$ and $\beta$, respectively of first and second kind. The Bayes interpretation is that Bayes risk, involving both sampling cost and wrong decision losses, is being minimized. An example of this correspondence are given by using a binomial setting.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.361-364
• /
• 1997

Bayesian MAP-EM approaches have been quite useful or tomographic reconstruction in that they can stabilize the instability of well-known ML-EM approaches, and can incorporate a priori information on the underlying emission object. However, MAP reconstruction algorithms with expressive priors often suffer from the optimization problem when their objective unctions are nonquadratic. In our previous work [1], we showed that the use of deterministic annealing method greatly reduces computational burden or optimization and provides a good solution or nonquadratic objective unctions. Here, we further investigate the convergence of the deterministic annealing algorithm; our experimental results show that, while the solutions obtained by a simple quenching algorithm depend on the initial conditions, the estimates converged via deterministic annealing algorithm are consistent under various initial conditions.

• 전자통신동향분석
• /
• 제34권4호
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• 한국지능시스템학회논문지
• /
• 제21권3호
• /
• pp.395-400
• /
• 2011

본 논문에서는 얼굴 표정에서 나타나는 동적인 정서상태 변화를 고려한 얼굴 영상 기반 정서 인식 연구를 제안한다. 본 연구는 얼굴 영상 기반 정서적 특징 검출 및 분석 단계와 정서 상태 분류/인식 단계로 구분할 수 있다. 세부 연구의 구성 중 첫 번째는 Facial Action Units (FAUs)과 결합한 Active Shape Model (ASM)을 이용하여 정서 특징 영역 검출 및 분석기법의 제안이며, 두 번째는 시간에 따른 정서 상태의 동적 변화를 고려한 정확한 인식을 위하여 Hidden Markov Model(HMM) 형태의 Dynamic Bayesian Network를 사용한 정서 상태 분류 및 인식기법의 제안이다. 또한, 최적의 정서적 상태 분류를 위한 HMM의 파라미터 학습 시 Harmony Search (HS) 알고리즘을 이용한 휴리스틱 최적화 과정을 적용하였으며, 이를 통하여 동적 얼굴 영상 변화를 기반으로 하는 정서 상태 인식 시스템을 구성하고 그 성능의 향상을 도모하였다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.246-246
• /
• 2023

Multi-purpose dams are operated accounting for both physical and socioeconomic factors. This study aims to evaluate the utility of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River. In this study, the Gated Recurrent Unit (GRU) algorithm is applied to predict hourly water level of the dam reservoirs over 2002-2021. The hyper-parameters are optimized by the Bayesian optimization algorithm to enhance the prediction skill of the GRU model. The GRU models are set by the following cases: single dam input - single dam output (S-S), multi-dam input - single dam output (M-S), and multi-dam input - multi-dam output (M-M). Results show that the S-S cases with the local dam information have the highest accuracy above 0.8 of NSE. Results from the M-S and M-M model cases confirm that upstream dam information can bring important information for downstream dam operation prediction. The S-S models are simulated with altered outflows (-40% to +40%) to generate the simulated water level of the dam reservoir as alternative dam operational scenarios. The alternative S-S model simulations show physically inconsistent results, indicating that our deep learning algorithm-based model is not explainable for multi-purpose dam operation patterns. To better understand this limitation, we further analyze the relationship between observed water level and outflow of each dam. Results show that complexity in outflow-water level relationship causes the limited predictability of the GRU algorithm-based model. This study highlights the importance of socioeconomic factors from hidden multi-purpose dam operation processes on not only physical processes-based modeling but also aritificial intelligence modeling.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• 제어로봇시스템학회논문지
• /
• 제20권3호
• /
• pp.277-288
• /
• 2014

This article reviews various state estimation methods for nonlinear systems, particularly with a perspective of a process control engineer. Nonlinear state estimation methods can be classified into the following two categories: stochastic approaches and deterministic approaches. The current review compares the Bayesian approach, which is mainly a stochastic approach, and the MHE (Moving Horizon Estimation) approach, which is mainly a deterministic approach. Though both methods are reviewed, emphasis is given to the latter as it is particularly well-suited to highly nonlinear systems with slow sampling rates, which are common in chemical process applications. Recent developments in underlying theories and supporting numerical algorithms for MHE are reviewed. Thanks to these developments, applications to large-scale and complex chemical processes are beginning to show up but they are still limited at this point owing to the high numerical complexity of the method.