• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.281-285
• /
• 2005

Learning and evolving are two basics for data mining. As compared with classical learning theory based on objective function with minimizing training errors, the recently evolutionary computing has had an efficient approach for constructing optimal model without the minimizing training errors. The global search of evolutionary computing in solution space can settle the local optima problems of learning models. In this research, combining co-evolving algorithm into statistical learning theory, we propose an co-evolutionary computing for statistical learning theory for overcoming local optima problems of statistical learning theory. We apply proposed model to classification and prediction problems of the learning. In the experimental results, we verify the improved performance of our model using the data sets from UCI machine learning repository and KDD Cup 2000.

• 대한영상의학회지
• /
• 제83권6호
• /
• pp.1219-1228
• /
• 2022

최근 영상의학 연구 분야에서 영상 인자를 포함한 임상 예측 모형의 수요가 증가하고 있고, 특히 라디오믹스 연구가 활발하게 이루어지면서 기존의 전통적인 회귀 모형뿐만 아니라 머신러닝을 사용하는 연구들이 많아지고 있다. 본 종설에서는 영상의학 분야에서 예측 모형 연구에 사용된 통계학적 방법과 머신 러닝 방법들을 조사하여 정리하고, 각 방법론에 대한 설명과 장단점을 살펴보고자 한다. 마지막으로 예측 모형 연구에서 분석 방법 선택에서의 고려사항을 정리해 보고자 한다.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제26권3호
• /
• pp.127-146
• /
• 2023

Statistical thinking has a broad definition but focuses on the context of regression modelling in the present study. To foster students' statistical thinking within the context, teaching should no longer be seen as transfer of knowledge from teacher to students but as a process of engaging with learning activities in which they develop ownership of knowledge. This study aims at collaborative learning contexts; students were divided into small groups in order to increase opportunities for peer collaboration. Each group of students was asked to do a regression project after class. Through doing the project, they learnt to organize and connect previously accrued piecemeal statistical knowledge in an integrated manner. They could also clarify misunderstandings and solve problems through verbal exchanges among themselves. They gave a clear and lucid account of the model they had built and showed collaborative interactions when presenting their projects in front of class. A survey was conducted to solicit their feedback on how peer collaboration would facilitate learning of statistics. Almost all students found their interaction with their peers productive; they focused on the development of statistical thinking with concerted effort.

• 국제학술발표논문집
• /
• The 2th International Conference on Construction Engineering and Project Management
• /
• pp.450-458
• /
• 2007

This paper presents the results of a statistical analysis and its research findings focusing on the learning aspect in the process of international joint ventures (IJVs). The contents of this paper is derived from a sample of 96 field cases based on a proposed conceptual model of effective learning for international construction joint ventures (ICJVs). The paper presents a brief review on the conceptual model with hypotheses and summarized the key results of statistical analysis including factor and multiple regression analysis for the testing of the validity of the proposed conceptual model and its associated research hypotheses. Among other research findings, the research confirms that ICJVs provides an excellent platform of in-action learning for construction organization and suggests that good outcomes in learning could be reaped by a company who has a clear learning intent from the beginning and subsequently take corresponding learning actions during the full process of the joint venture.

• Journal of Information Processing Systems
• /
• 제8권2호
• /
• pp.241-262
• /
• 2012

An understanding of quality attributes is relevant for the software organization to deliver high software reliability. An empirical assessment of metrics to predict the quality attributes is essential in order to gain insight about the quality of software in the early phases of software development and to ensure corrective actions. In this paper, we predict a model to estimate fault proneness using Object Oriented CK metrics and QMOOD metrics. We apply one statistical method and six machine learning methods to predict the models. The proposed models are validated using dataset collected from Open Source software. The results are analyzed using Area Under the Curve (AUC) obtained from Receiver Operating Characteristics (ROC) analysis. The results show that the model predicted using the random forest and bagging methods outperformed all the other models. Hence, based on these results it is reasonable to claim that quality models have a significant relevance with Object Oriented metrics and that machine learning methods have a comparable performance with statistical methods.

• Journal of the Korean Statistical Society
• /
• 제30권2호
• /
• pp.179-192
• /
• 2001

When a statistical model has a hierarchical structure such as multilayer perceptrons in neural networks or Gaussian mixture density representation, the model includes distribution with unidentifiable parameters when the structure becomes redundant. Since the exact structure is unknown, we need to carry out statistical estimation or learning of parameters in such a model. From the geometrical point of view, distributions specified by unidentifiable parameters become a singular point in the parameter space. The problem has been remarked in many statistical models, and strange behaviors of the likelihood ratio statistics, when the null hypothesis is at a singular point, have been analyzed so far. The present paper studies asymptotic behaviors of the maximum likelihood estimator and the Bayesian predictive estimator, by using a simple cone model, and show that they are completely different from regular statistical models where the Cramer-Rao paradigm holds. At singularities, the Fisher information metric degenerates, implying that the cramer-Rao paradigm does no more hold, and that he classical model selection theory such as AIC and MDL cannot be applied. This paper is a first step to establish a new theory for analyzing the accuracy of estimation or learning at around singularities.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제9권5호
• /
• pp.161-168
• /
• 2020

스포츠 경기 결과예측은 전반적인 경기의 흐름과 승패에 영향을 미치는 변인들의 분석을 통해 팀의 전략 수립을 가능하게 해준다. 이와 같은 스포츠 경기결과 예측에 대한 연구는 주로 통계학적 기법과 기계학습 기법을 활용하여 진행되어 왔다. 승부예측 모델은 무엇보다 예측 성능이 가장 중요시된다. 그러나 최적의 성능을 보이는 예측 모델은 학습에 사용되는 데이터에 따라 다르게 나타나는 경향을 보였다. 본 논문에서는 이러한 문제를 해결하기 위해 데이터가 달라지더라도 해당 데이터에 대한 예측 시 가장 좋은 성능을 보이는 모델의 선택이 가능한 기존의 축구경기결과 예측에서 좋은 성능을 보여온 통계학적 모델과 기계학습 모델을 결합한 새로운 앙상블 모델을 제안한다. 본 논문에서 제안하는 앙상블 모델은 각 단일모델들의 경기 예측결과와 실제 경기결과를 병합한 데이터로부터 최종예측모델을 학습하여 경기 승부예측을 수행한다. 제안 모델에 대한 실험 결과, 기존 단일모델들에 비해 높은 성능을 보였다.

• 정보처리학회논문지C
• /
• 제10C권6호
• /
• pp.705-710
• /
• 2003

최근 대부분의 정보 교류가 네트워크 환경 기반에서 이루어지고 있다. 때문에 외부의 침입으로부터 시스템을 보호해 주는 네트워크 침입 탐지 기술에 대한 연구가 매우 중요한 문제로 대두되고 있다. 하지만 시스템에 대한 침입 기술은 날로 새로워지고 더욱 정교화 되고 있어 이에 대한 대비가 절실한 실정이다. 현재 대부분의 침입 탐지 시스템은 이미 알려진 외부의 침입으로부터의 경험 데이터를 이용하여 침입 유형에 효과적으로 대처하지 못하게 된다. 따라서, 본 논문에서는 통계적 학습 이론과 우도비검정 통계량을 이용하여 새로운 침입 유형까지 탐지해 낼 수 있는 변형된 통계적 학습 모형을 제안하였다. 즉, 기존의 정상적인 네트워크 사용에서 벗어나는 형태들에 대한 모형화를 통하여 시스템에 대한 침입 탐지를 수행하였다. KDD Cup-99 Task 데이터를 이용하여 정상적인 네트워크 사용을 벗어나는 새로운 침입을 제안 모형이 효과적으로 탐지함을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.420-437
• /
• 2024

There are some problems in network traffic classification (NTC), such as complicated statistical features and insufficient training samples, which may cause poor classification effect. A NTC architecture based on one-dimensional Convolutional Neural Network (CNN) and transfer learning is proposed to tackle these problems and improve the fine-grained classification performance. The key points of the proposed architecture include: (1) Model classification--by extracting normalized rate feature set from original data, plus existing statistical features to optimize the CNN NTC model. (2) To apply transfer learning in the classification to improve NTC performance. We collect two typical network flows data from Youku and YouTube, and verify the proposed method through extensive experiments. The results show that compared with existing methods, our method could improve the classification accuracy by around 3-5%for Youku, and by about 7 to 27% for YouTube.

• 한국군사과학기술학회지
• /
• 제27권3호
• /
• pp.406-415
• /
• 2024

As the equipment of the military has become more advanced and expensive, the cost of securing spare parts is also constantly increasing along with the increase in equipment assets. In particular, forecasting demand for spare parts one of the important management tasks in the military, and the accuracy of these predictions is directly related to military operations and cost management. However, because the demand for spare parts is intermittent and irregular, it is often difficult to make accurate predictions using traditional statistical methods or a single statistical or machine learning model. In this paper, we propose a model that can increase the accuracy of demand forecasting for irregular patterns of spare parts demanding by using a combination of statistical and machine learning algorithm, and through experiments on Cheonma spare parts demanding data.