• 한국정보기술학회논문지
• /
• 제17권5호
• /
• pp.47-55
• /
• 2019

최근 GPS 재밍으로 인한 피해가 증가되면서 GPS 재밍을 탐지하고 대비하기 위한 연구가 활발히 진행되고 있다. 본 논문은 다중 GPS 수신채널과 3가지 기계학습을 이용한 GPS 재밍 탐지 방법을 다루고 있다. 제안된 다중 GPS 채널은 항재밍 기능이 없는 상용 GPS 수신기와 항잡음 재밍능력만 있는 수신기, 항잡음/항기만 재밍능력이 있는 수신기로 구성되고 운용자는 각각의 수신기에 수신된 좌표를 비교하여 재밍신호의 특성을 식별할 수 있다. 본 논문에서는 신호특성이 다른 각각의 5개 재밍신호를 입력하고, 3가지 기계학습방법(AB: Adaptive Boosting, SVM: Support Vector Machine, DT: Decision Tree)을 이용하여 재밍탐지 시험을 수행하였다. 시험 결과 머신러닝 기법을 단독으로 사용하였을 때 DT 기법이 96.9% 탐지율로 가장 우수한 성능을 보였으며 이진분류기 기법에 비해 모호성 낮고 하드웨어가 단순하여 GPS 재밍탐지에 효과적임을 확인하였다. 또한, 모호성을 해결해주는 추가기법을 적용할 경우 SVM 기법을 활용할 수 있음을 확인하였다.

• 한국지반공학회논문집
• /
• 제39권4호
• /
• pp.5-17
• /
• 2023

도심지 지하굴착 공사가 대형화되면서 공사 중 안전사고에 대한 위험요인이 더욱 증가하고 있다. 이에 따라 공사현장의 위험요소를 모니터링하고 사전에 예측할 수 있는 기술이 필요하다. 굴착으로 인한 흙막이 벽체의 변형을 예측하는 방법에는 크게 경험식과 수치해석 두 가지 방법으로 분류할 수 있으며, 최근에는 인공지능 기술의 발달과 함께 머신러닝 기법을 활용한 예측 모델이 한 가지 방법으로 자리 잡고 있다. 본 연구에서는 예측력과 효율성이 우수한 부스팅 계열 알고리즘 및 앙상블 모델을 이용하여 시공 중 흙막이 벽체 변형을 예측하는 모델을 구축하였다. 지하흙막이 공사의 설계-시공-유지관리 과정에서 도출되는 자료들을 복합적으로 활용하여 데이터베이스를 구축하고, 이 자료를 토대로 학습모델을 만들고 성능을 평가하였다. 모델 성능 평가 결과, 높은 정확도로 흙막이 벽체 변형을 예측할 수 있었으며, 지반계측 자료를 학습에 활용함으로써 실제 시공과정의 특성이 반영된 예측결과를 제시할 수 있었다. 본 연구에서 구축한 예측 모델을 활용하여 시공 중 흙막이 벽체의 안정성 평가 및 모니터링에 활용할 수 있을 것으로 기대된다.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제8권3호
• /
• pp.57-67
• /
• 2018

앙상블 기법은 기계학습에서 다수의 알고리즘을 사용하여 더 좋은 성능을 내기 위해 사용하는 방법이다. 본 논문에서는 앙상블 기법에서 많이 사용되는 부스팅과 배깅에 대해 소개를 하고, 서포트벡터 회귀, 방사기저함수 네트워크, 가우시안 프로세스, 다층 퍼셉트론을 이용하여 설계한다. 추가적으로 순환신경망과 MOHID 수치모델을 추가하여 실험을 진행한다. 실험적 검증를 위해 사용하는 뜰개 데이터는 7 개의 지역에서 관측된 683 개의 관측 자료다. 뜰개 관측 자료를 이용하여 6 개의 알고리즘과의 비교를 통해 앙상블 기법의 성능을 검증한다. 검증 방법으로는 평균절대오차를 사용한다. 실험 방법은 배깅, 부스팅, 기계학습을 이용한 앙상블 모델을 이용하여 진행한다. 각 앙상블 모델마다 동일한 가중치를 부여한 방법, 차등한 가중치를 부여한 방법을 이용하여 오류율을 계산한다. 가장 좋은 오류율을 나타낸 방법은 기계학습을 이용한 앙상블 모델로서 6 개의 기계학습의 평균에 비해 61.7%가 개선된 결과를 보였다.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.543-559
• /
• 2017

Tree-based regression and classification ensembles form a standard part of the data-science toolkit. Many commonly used methods take an algorithmic view, proposing greedy methods for constructing decision trees; examples include the classification and regression trees algorithm, boosted decision trees, and random forests. Recent history has seen a surge of interest in Bayesian techniques for constructing decision tree ensembles, with these methods frequently outperforming their algorithmic counterparts. The goal of this article is to survey the landscape surrounding Bayesian decision tree methods, and to discuss recent modeling and computational developments. We provide connections between Bayesian tree-based methods and existing machine learning techniques, and outline several recent theoretical developments establishing frequentist consistency and rates of convergence for the posterior distribution. The methodology we present is applicable for a wide variety of statistical tasks including regression, classification, modeling of count data, and many others. We illustrate the methodology on both simulated and real datasets.

• Geomechanics and Engineering
• /
• 제34권6호
• /
• pp.697-726
• /
• 2023

Brittleness as an important property of rock plays a crucial role both in the failure process of intact rock and rock mass response to excavation in engineering geological and geotechnical projects. Generally, rock brittleness indices are calculated from the mechanical properties of rocks such as uniaxial compressive strength, tensile strength and modulus of elasticity. These properties are generally determined from complicated, expensive and time-consuming tests in laboratory. For this reason, in the present research, an attempt has been made to predict the rock brittleness indices from simple, inexpensive, and quick laboratory test results namely dry unit weight, porosity, slake-durability index, P-wave velocity, Schmidt rebound hardness, and point load strength index using multiple linear regression, exponential regression, support vector machine (SVM) with various kernels, generating fuzzy inference system, and regression tree ensemble (RTE) with boosting framework. So, this could be considered as an innovation for the present research. For this purpose, the number of 39 rock samples including five igneous, twenty-six sedimentary, and eight metamorphic were collected from different regions of Iran. Mineralogical, physical and mechanical properties as well as five well known rock brittleness indices (i.e., B₁, B₂, B₃, B₄, and B₅) were measured for the selected rock samples before application of the above-mentioned machine learning techniques. The performance of the developed models was evaluated based on several statistical metrics such as mean square error, relative absolute error, root relative absolute error, determination coefficients, variance account for, mean absolute percentage error and standard deviation of the error. The comparison of the obtained results revealed that among the studied methods, SVM is the most suitable one for predicting B₁, B₂ and B₅, while RTE predicts B₃ and B₄ better than other methods.

• Communications for Statistical Applications and Methods
• /
• 제25권2호
• /
• pp.199-215
• /
• 2018

Interest in $PM_{10}$ concentrations have increased greatly in Korea due to recent increases in air pollution levels. Therefore, we consider a forecasting model for next day $PM_{10}$ concentration based on the principal elements of air pollution, weather information and Beijing $PM_{2.5}$. If we can forecast the next day $PM_{10}$ concentration level accurately, we believe that this forecasting can be useful for policy makers and public. This paper is intended to help forecast a daily mean $PM_{10}$, a daily max $PM_{10}$ and four stages of $PM_{10}$ provided by the Ministry of Environment using various data mining techniques. We use seven models to forecast the daily $PM_{10}$, which include five regression models (linear regression, Randomforest, gradient boosting, support vector machine, neural network), and two time series models (ARIMA, ARFIMA). As a result, the linear regression model performs the best in the $PM_{10}$ concentration forecast and the linear regression and Randomforest model performs the best in the $PM_{10}$ class forecast. The results also indicate that the $PM_{10}$ in Seoul is influenced by Beijing $PM_{2.5}$ and air pollution from power stations in the west coast.

• 품질경영학회지
• /
• 제42권4호
• /
• pp.701-716
• /
• 2014

Purpose: In the paper, I studied success factors and measures for win-win quality management for boosting corporate competitiveness through the achievement of high quality. Methods: As such, to that end, data of companies' win-win quality management activities and Cooperation performance were gathered. Also, I had a literature review and working staffs'opinions were gathered to develop items related to trade dependence, quality cooperation, and mutual trust and cooperation. To develop the questionnaire, sufficient literature survey was conducted, and advice was sought from experts of manufacturing companies which practice Win-Win Cooperation. Results: Based on these previous researches and analysis by structural equation modeling, among trade dependence factors, overall, other factors except financial dependence and some detailed factors were found to have a relatively significant influence relation. Conclusion: The findings of this study suggest that if individual organizations can construct an effective quality improvement system and positively pursue win-win activities, it will contribute greatly to achieving high quality and improving financial performance. However, given the time and regional limits of this study, more in-depth studies need to be conducted on measures for boosting quality competitiveness through Win-Win Cooperation.

• 응용통계연구
• /
• 제30권6호
• /
• pp.851-865
• /
• 2017

최근 워너크라이라는 이름의 랜섬웨어가 전 세계적으로 큰 화두에 오르면서, 악성 소프트웨어로 인한 피해를 줄이기 위한 방법들이 재조명 되고 있다. 새로운 악성 소프트웨어가 발생했을 때 피해를 최소화하기 위해서는 해당 소프트웨어가 어떤 공격 유형을 가진 악성 소프트웨어인지 빠르게 분류할 필요가 있다. 본 연구 목적은 다양한 통계적 기법을 이용하여 악성 소프트웨어를 효과적으로 분류할 수 있는 모형을 구축하는 데 있다. 모형 적합 시 다항 로지스틱, 랜덤 포레스트, 그래디언트 부스팅, 서포트 벡터 기계 등의 기법들을 이용하였으며, 본 연구를 통해 악성 소프트웨어를 분류하는 데에 있어 중요한 역할을 하는 변수들이 존재한다는 사실을 발견하였다.

• 대한산업공학회지
• /
• 제42권4호
• /
• pp.263-269
• /
• 2016

The purpose of this study is to challenge a computational regression-type problem, that is handling large-size data, in which conventional metamodeling techniques often fail in a practical sense. To solve such problems, regression-type boosting, one of ensemble model techniques, together with bootstrapping-based re-sampling is a reasonable choice. This study suggests weight updates by the amount of the residual itself and a new error decision criterion which constructs an ensemble model of models selectively chosen by rejection limits. Through these ideas, we propose AdaBoost.RMU.R as a metamodeling technique suitable for handling large-size data. To assess the performance of the proposed method in comparison to some existing methods, we used 6 mathematical problems. For each problem, we computed the average and the standard deviation of residuals between real response values and predicted response values. Results revealed that the average and the standard deviation of AdaBoost.RMU.R were improved than those of other algorithms.

• 방사성폐기물학회지
• /
• 제19권1호
• /
• pp.75-85
• /
• 2021

Evaluating the quantitative damage to rocks through acoustic emission (AE) has become a research focus. Most studies mainly used one or two AE parameters to evaluate the degree of damage, but several AE parameters have been rarely used. In this study, several data-driven models were employed to reflect the combined features of AE parameters. Through uniaxial compression tests, we obtained mechanical and AE-signal data for five granite specimens. The maximum amplitude, hits, counts, rise time, absolute energy, and initiation frequency expressed as the cumulative value were selected as input parameters. The result showed that gradient boosting (GB) was the best model among the support vector regression methods. When GB was applied to the testing data, the root-mean-square error and R between the predicted and actual values were 0.96 and 0.077, respectively. A parameter analysis was performed to capture the parameter significance. The result showed that cumulative absolute energy was the main parameter for damage prediction. Thus, AE has practical applicability in predicting rock damage without conducting mechanical tests. Based on the results, this study will be useful for monitoring the near-field rock mass of nuclear waste repository.