• 한국정보통신학회논문지
• /
• 제19권1호
• /
• pp.35-40
• /
• 2015

본 논문은 유전 알고리즘 기반 귀납적 학습 환경 하에서 메타 학습법을 이용한 다중 분류기 시스템의 구축에 관한 것이다. 메타 학습법을 이용한 다중 분류기 시스템의 구축에서 분류기는 일반 분류기와 메타 분류기로 구성된다. 메타 분류기는 사례에 대한 일반 분류기의 분류 결과에 학습 알고리즘을 적용하여 얻어진다. 분류시스템의 의사 결정과정에서 메타 분류기의 역할은 일반 분류기의 분류 결과를 평가하여 최종 의사 결정 과정에의 참여 여부를 결정하는 것이다. 분류 시스템은 분류기의 분류 결과가 옳은 것으로 평가된 결과들만 취합하여 이를 바탕으로 최종 분류 결과를 도출해 낸다. 메타 학습법이 다중 분류기 시스템의 성능에 미치는 영향을 다수의 사례 집합을 이용하여 평가하였다.

• 지능정보연구
• /
• 제3권2호
• /
• pp.83-91
• /
• 1997

DELVAUX is an inductive learning environment that learns Bayesian classification rules from a set o examples. In DELVAUX, a genetic a, pp.oach is employed to learn the best rule-set, in which a population consists of rule-sets and rule-sets generate offspring by exchanging some of their rules. We have explored a meta-learning a, pp.oach in the DELVAUX learning environment to improve the classification performance of the DELVAUX system. The meta-learning a, pp.oach learns the bias of a classifier so that it can evaluate the prediction made by the classifier for a given example and thereby improve the overall performance of a classifier system. The paper discusses the meta-learning a, pp.oach in details and presents some empirical results that show the improvement we can achieve with the meta-learning a, pp.oach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권8호
• /
• pp.2067-2081
• /
• 2024

Recently, image analysis research has been actively conducted due to the accumulation of big image data and the development of deep learning. Image analytics research has different characteristics from other data such as data size, real-time, image quality diversity, structural complexity, and security issues. In addition, a large amount of data is required to effectively analyze images with deep-learning models. However, in many fields, the data that can be collected is limited, so there is a need for meta learning based image analysis technology that can effectively train models with a small amount of data. This paper presents a comprehensive survey of meta-learning-based object-tracking techniques. This approach comprehensively explores object tracking methods and research that can achieve high performance in data-limited situations, including key challenges and future directions. It provides useful information for researchers in the field and can provide insights into future research directions.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제24권3호
• /
• pp.175-199
• /
• 2021

The Science Writing Heuristic (SWH) approach is described as an immersive argument-based science inquiry focusing particularly on learning through epistemic practices. In the literature, several previous studies indicate how academic achievement is positively influenced by the SWH. In addition to these previous studies, several meta-syntheses of qualitative data have been conducted on this particular topic. With these literatures in mind, a quantitative meta-analysis was conducted with ten studies (N = 724) to examine the effectiveness of the SWH on student achievement in Turkey. To present a thoroughly detailed report, this study also examined the following moderators: grade level, subject area, school location, intervention length, and report source. Overall, this study found that in Turkey, the SWH classrooms performed better in academic achievement tests than traditional lecture-based classrooms. Additionally, the SWH is more likely to be effective regardless of grade levels, subject areas, and school locations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• 시스템엔지니어링학술지
• /
• 제19권2호
• /
• pp.18-31
• /
• 2023

Exploring artificial intelligence and machine learning for nuclear safety has witnessed increased interest in recent years. To contribute to this area of research, a machine learning model capable of accurately predicting nuclear power plant response with minimal computational cost is proposed. To develop a robust machine learning model, the Best Estimate Plus Uncertainty (BEPU) approach was used to generate a database to train three models and select the best of the three. The BEPU analysis was performed by coupling Dakota platform with the best estimate thermal hydraulics code RELAP/SCDAPSIM/MOD 3.4. The Code Scaling Applicability and Uncertainty approach was adopted, along with Wilks' theorem to obtain a statistically representative sample that satisfies the USNRC 95/95 rule with 95% probability and 95% confidence level. The generated database was used to train three models based on Recurrent Neural Networks; specifically, Long Short-Term Memory, Gated Recurrent Unit, and a hybrid model with Long Short-Term Memory coupled to Convolutional Neural Network. In this paper, the System Engineering approach was utilized to identify requirements, stakeholders, and functional and physical architecture to develop this project and ensure success in verification and validation activities necessary to ensure the efficient development of ML meta-models capable of predicting of the nuclear power plant response.

• 정보처리학회논문지B
• /
• 제11B권1호
• /
• pp.77-82
• /
• 2004

강화학습에서 temporal-credit 할당 문제 즉, 에이전트가 현재 상태에서 어떤 행동을 선택하여 상태전이를 하였을 때 에이전트가 선택한 행동에 대해 어떻게 보상(reward)할 것인가는 강화학습에서 중요한 과제라 할 수 있다. 본 논문에서는 조합최적화(hard combinational optimization) 문제를 해결하기 위한 새로운 메타 휴리스틱(meta heuristic) 방법으로, greedy search뿐만 아니라 긍정적 반응의 탐색을 사용한 모집단에 근거한 접근법으로 Traveling Salesman Problem(TSP)를 풀기 위해 제안된 Ant Colony System(ACS) Algorithms에 Q-학습을 적용한 기존의 Ant-Q 학습방범을 살펴보고 이 학습 기법에 다양화 전략을 통한 상태전이와 TD-오류를 적용한 학습방법인 Ant-TD 강화학습 방법을 제안한다. 제안한 강화학습은 기존의 ACS, Ant-Q학습보다 최적해에 더 빠르게 수렴할 수 있음을 실험을 통해 알 수 있었다.

• 한국과학교육학회지
• /
• 제32권8호
• /
• pp.1295-1317
• /
• 2012

There has been disagreement on the importance of definitions in science education. Yager (1983) believes that one crisis in science education was due to the considerable emphasis upon the learning of definitions. Hobson (2004) disagrees with physics textbooks that do not provide general definition on energy. Some textbooks explain that "there is no completely satisfactory definition of energy" or they can only "struggle to define it." In general, imprecise definitions in textbooks (Bauman, 1992) and inaccuracies in definition provided by teachers (Galili & Lehavi, 2006) may cause alternative conceptions. Besides, there are at least four challenges in defining physical concepts: precision, circularity, context and completeness in knowledge. These definitional problems that have been discussed in The Feynman Lectures, may impede the learning of physical concepts. A meta-study approach is employed to examine about five hundreds journal papers that may discuss definitions in physics, problems in defining physical concepts and how they may result in alternative conceptions. These journal papers are mainly selected from journals such as American Journal of Physics, International Journal of Science Education, Journal of Research in Science Teaching, Physics Education, The Physics Teachers, and so on. There are also comparisons of definitions with definitions from textbooks, Dictionaries of Physics, and English Dictionaries. To understand the nature of alternative conception, Lee et al. (2010) have suggested a theoretical framework to describe the learning issues by synthesizing cognitive psychology and science education approaches. Taking it a step further, this study incorporates the challenges in semantics and epistemology, proposes that there are at least four variants of alternative conceptions. We may coin the term, 'alternative definitions', to refer to the commonly available definitions, which have these four problems in defining physics concepts. Based on this study, alternative definitions may result in at least four variants of alternative conceptions. Note that these four definitional problems or challenges in definitions cannot be easily resolved. Educators should be cognizant of the four variants of alternative conceptions which can arise from alternative definitions. The concepts of alternative definitions can be useful and possibly generalized to science education and beyond.

• 시스템엔지니어링학술지
• /
• 제18권2호
• /
• pp.75-93
• /
• 2022

Machine learning (ML) data-driven meta-model is proposed as a surrogate model to reduce the excessive computational cost of the physics-based model and facilitate the real-time prediction of a nuclear power plant's transient response. To forecast the transient response three machine learning (ML) meta-models based on recurrent neural networks (RNNs); specifically, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and a sequence combination of Convolutional Neural Network (CNN) and LSTM are developed. The chosen accident scenario is a control element assembly withdrawal at power concurrent with the Loss Of Offsite Power (LOOP). The transient response was obtained using the best estimate thermal hydraulics code, MARS-KS, and cross-validated against the Design and control document (DCD). DAKOTA software is loosely coupled with MARS-KS code via a python interface to perform the Best Estimate Plus Uncertainty Quantification (BEPU) analysis and generate a time series database of the system response to train, test and validate the ML meta-models. Key uncertain parameters identified as required by the CASU methodology were propagated using the non-parametric Monte-Carlo (MC) random propagation and Latin Hypercube Sampling technique until a statistically significant database (181 samples) as required by Wilk's fifth order is achieved with 95% probability and 95% confidence level. The three ML RNN models were built and optimized with the help of the Talos tool and demonstrated excellent performance in forecasting the most probable NPP transient response. This research was guided by the Systems Engineering (SE) approach for the systematic and efficient planning and execution of the research.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (2)
• /
• pp.551-553
• /
• 1999

This paper explores the utility of a new classifier fusion approach to discrimination. Multiple classifier fusion, a popular approach in the field of pattern recognition, uses estimates of each individual classifier's local accuracy on training data sets. In this paper we investigate the effectiveness of fusion methods compared to individual algorithms, including the artificial neural network and k-nearest neighbor techniques. Moreover, we propose an efficient meta-classifier architecture based on an approximation of the posterior Bayes probabilities for learning the oracle.