• Review of KIISC
• /
• v.27 no.3
• /
• pp.12-19
• /
• 2017

기하급수적으로 증가하고 있는 변종 악성코드에 대응하기 위한 식별 연구가 다양화 되고 있다. 최근 연구에서는 기존 악성코드 분석 기술 (정적/동적)의 개별 사용 한계를 파악하고, 각 방식을 혼합한 하이브리드 분석으로 전환하는 추세이다. 나아가 변종 식별이 어려운 악성코드를 더욱 정확하게 식별하기 위해 기계 학습을 적용하기에 이르렀다. 이에 따라, 본 논문에서는 변종 악성코드 식별을 위해 각 연구에서 활용한 기계 학습 기술과 사용한 악성코드 특징을 중심으로 변종 악성코드 식별 연구를 분류 및 분석한다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2016.11a
• /
• pp.304-306
• /
• 2016

본 논문에서는 기계학습 방법에 기반을 둔 119 긴급 신고 전화 전사 데이터에 대한 구급, 구조, 화재 상황 분류 알고리즘을 개발하였다. 신고전화에서 빈번하게 발생하는 비정형 발화 패턴을 효율적으로 정규화하고 자연어 문장 처리 기법에서 일반적으로 사용하는 방법을 적용하여 신고전화 텍스트 데이터를 기계학습에서 사용할 수 있는 특징 벡터로 재구성하였다. 2743개의 신고전화에 대해 선형 서포트 벡터 머신을 이용하여 상황 분류를 수행한 결과, 92% 의 정확도를 얻을 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.327-329
• /
• 2023

순서 의존적 준비시간을 갖는 단일기계 생산라인에서 주어진 작업들을 효율적으로 수행하기 위해서는 최대한 동일하거나 유사한 유형의 작업물들을 연속적으로 처리하여 다음 번 작업물의 처리를 시작하기 전에 발생하는 준비시간을 최소화하여야 한다. 따라서, 대기 중인 것들 중 기계에 투입할 작업물을 적절히 선택하는 것이 중요하며, 이를 위해 작업 배정 규칙과 같은 휴리스틱을 사용할 수도 있지만, 이러한 해법들은 일반적으로 다양한 상황을 동적으로 고려하지 못하는 한계점을 갖는다. 따라서, 본 논문에서는 상용 3D 시뮬레이션 소프트웨어인 FlexSim을 사용하여 모형을 구성한 다음, 강화학습을 적용하여 대기 중인 작업물 중 최적의 후보를 선택하기 위한 작업 배정 모형을 개발하고자 한다. 세부적으로는 강화학습의 상태 및 보상을 달리 설정하면서 학습된 모형의 성능을 비교하고자 한다. 실험 결과를 통해 적절한 시뮬레이션 모형 구성과 강화학습의 파라미터 변수들을 적절히 조합하여 적절한 작업 배정 모형의 개발이 가능하다는 점을 알 수 있었다.

• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.94-102
• /
• 2016

This paper proposes a new prediction method to reduce times and labor of repetitive multi-physics simulation. To achieve exact results from the whole simulation processes, complex modeling and huge amounts of time are required. Current multi-physics analysis focuses on the simulation method itself and the simulation environment to reduce times and labor. However this paper proposes an alternative way to reduce simulation times and labor by exploiting machine learning algorithm trained with data set from simulation results. Through comparing each machine learning algorithm, Gaussian Process Regression showed the best performance with under 100 training data and how similar results can be achieved through machine-learning without a complex simulation process. Given trained machine learning algorithm, it's possible to predict the result after changing some features of the simulation model just in a few second. This new method will be helpful to effectively reduce simulation times and labor because it can predict the results before more simulation.

• Journal of KIISE
• /
• v.43 no.1
• /
• pp.80-86
• /
• 2016

A speech-act is a behavior intended by users in an utterance. Speech-act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and transformation-based learning (TBL). The user's utterance is first classified by SVM that is preferentially applied to categories with a low utterance rate in training data. Next, when an utterance has negative scores throughout the whole of the categories, the utterance is applied to the correction phase by rules. The results from our method were higher performance over the baseline system long with error-reduction.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.123-130
• /
• 2021

With the recent developments in computer technology, there has been an increasing interest in the field of machine learning. This also has led to a significant increase in real business cases of machine learning theory in various sectors. In finance, it has been a major challenge to predict the future value of financial products. Since the 1980s, the finance industry has relied on technical and fundamental analysis for this prediction. For future value prediction models using machine learning, model design is of paramount importance to respond to market variables. Therefore, this paper quantitatively predicts the stock price movements of individual stocks listed on the KOSPI market using machine learning techniques; specifically, the reinforcement learning model. The DQN and A2C algorithms proposed by Google Deep Mind in 2013 are used for the reinforcement learning and they are applied to the stock trading strategies. In addition, through experiments, an input value to increase the cumulative profit is selected and its superiority is verified by comparison with comparative algorithms.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.15-25
• /
• 2023

Extreme learning machines (ELMs) are a major analytical method in various prediction fields. ELMs can accurately predict even if the data contains noise or is nonlinear by learning the complex patterns of time series data through optimal learning. This study presents the recent trends of machine learning models that are mainly studied as tools for analyzing online time series data, along with the application characteristics using existing algorithms. In order to efficiently learn large-scale online data that is continuously and explosively generated, it is necessary to have a learning technology that can perform well even in properties that can evolve in various ways. Therefore, this study examines a comprehensive overview of the latest machine learning models applied to big data in the field of time series prediction, discusses the general characteristics of the latest models that learn online data, which is one of the major challenges of machine learning for big data, and how efficiently they can learn and use online time series data for prediction, and proposes alternatives.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.593-598
• /
• 2003

Machine learning organizes knowledge for efficient and accurate reuse. This paper is concerned with methods of concept learning from examples, which glean knowledge from a training set of preclassified ‘objects’. Ideally, training facilitates classification of novel, previously unseen objects. However, every learning system relies on processing and representation assumptions that may be detrimental under certain circumstances. We explore the biases of a well-known learning system, ID3, review improvements, and introduce some improvements of our own, each designed to yield accurate and pedagogically sound classification.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.390-392
• /
• 2022

기계학습 분야에서 모델을 학습시키려면 많은 양의 데이터가 필요하다. 최근에는 컴퓨터 비전 분야에서 데이터가 적은 환경에서 모델을 학습하는 다양한 방법들이 소개되고 있다. 하지만 대부분의 방법을 사용하기 위해서는 어느 정도 최소한의 학습 데이터가 필요하기 때문에 극심하게 데이터가 부족한 환경에서는 사용하기 어렵다. 본 논문에서는 컴퓨터 비전 분야에서 기계학습을 사용할 때 극심하게 데이터가 부족한 환경에서 시뮬레이션 도구를 활용한 인조 데이터 생성 방법을 제안한다. 실험 결과를 통해 시뮬레이션 도구를 활용하여 생성한 인조 데이터로 학습한 모델이 실제 데이터만을 학습한 모델을 대체할 수 있음을 확인하였고, F-1 점수와 정확도가 향상함을 실험적으로 확인하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.233-240
• /
• 2009

In this paper we made the serious game learning multiplication table to be evolved. The serious game is to induce the interest of the learner. This program has an interaction form which reflects the intention of the user and using this program a learner to learn the multiplication table as teacher's location are training a program that are seen as the abata and came to be that learner is smart. A study ability to be evolved used an back propagation neural networks. But we improved a study speed using divided weight table concept. The engine is studied perfectly in 60~80 times training. The learning rate increase to various non-monotonic functional form not to do a mechanical rise. And the learning rate is similar with the study ability of the human.