• 지적과 국토정보
• /
• 제46권2호
• /
• pp.43-55
• /
• 2016

본 연구는 사례 기반 학습(instance-based learning)의 논리를 활용하여 지가를 추정하였다. 다양한 사례 기반 학습 기법 중 k-최근린법을 이용하였으며, k-최근린법 적용시 유사성을 측정하는 거리척도는 유클리디안 거리를 비롯해 문헌에 비교적 자주 등장하는 10개의 거리척도를 사용하였다. 본 연구에서는 k-최근린법에 의한 10 종류의 예측값 중 가장 우수한 성능을 보이는 1개의 예측값을 최종 가격으로 선택하는 대신, 이들 예측값들을 병합하는 앙상블(ensemble) 기법의 논리를 적용하여 최종 예측값을 결정하였다. 앙상블 기법 중 일종의 잔차 적합 모형인 경사 부스팅 앨고리듬을 적용하여 최종 가격을 정하였다. 본 연구에서는 이러한 사례 기반 학습과 앙상블 기법의 이점을 실증적으로 제시하기 위해 전라남도 해남군 소재 농지를 사례로 하여 가격을 추정하였으며, k-최근린법에 의한 10 종류의 예측값보다 앙상블 기법에 의한 가격이 보다 정확한 것을 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제25권2호
• /
• pp.171-177
• /
• 2021

최근 머신러닝의 발전에 따라 일상생활과 산업에서 기술을 적용하는 사례들이 많아지고 있다. 금융 데이터와 머신러닝 기법을 활용한 연구 또한 활발하게 이루어지고 있다. 본 논문은 이러한 동향에 따라 상점 매출 데이터에 머신러닝 기법을 접목해 매출 예측 모델을 구축, 핀테크 산업에서의 활용 방안을 제시한다. 다양한 결측치 처리 기법을 적용하고 그래디언트 부스팅 기반의 머신러닝 기법인 XGBoost, LightGBM, CatBoost를 사용하여 각 모델의 상점 매출예측 성능을 비교한다. 연구 결과, 단일대체법 중 중앙값 대체법을 사용한 데이터셋에 XGBoost를 활용해 예측을 진행한 모델의 성능이 가장 우수했다. 연구를 통해 얻은 모델을 이용하여 상점의 매출 예측을 진행함으로서 핀테크 기업의 고객 상점들은 대출금을 상환하기 전 금융 보조를 받는 근거로, 핀테크 기업은 상환 가능성이 높은 우수 상점에 금융 상품을 제공하는 등 기업과 고객 모두에게 긍정적인 방향으로 활용할 수 있다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권3호
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.537-538
• /
• 2023

본 논문에서는 사람에게서 나타나는 생체 특성과 흡연여부의 상관관계 분석을 위해 랜덤 포레스트와 그래디언트 부스팅 트리의 두 가지 기계학습 알고리즘을 사용하였다. 연구에 사용된 데이터는 국민건강보험공단에서 제공하고 Kaggle에서 취합하여 정리한 건강검진 정보를 사용하였다. 분류 모델의 학습에 있어 혈청 정보가 높은 관계성을 보일 것으로 예상하였으나, 실제 결과는 성별이 가장 큰 영향을 끼치는 것으로 확인되었다.

• Computers and Concrete
• /
• 제32권6호
• /
• pp.607-613
• /
• 2023

The objective of this work is to determine the compressive strength of geopolymer concrete utilizing four distinct machine learning approaches. These techniques are known as gradient boosting machine (GBM), generalized linear model (GLM), extremely randomized trees (XRT), and deep learning (DL). Experimentation is performed to collect the data that is then utilized for training the models. Compressive strength is the response variable, whereas curing days, curing temperature, silica fume, and nanosilica concentration are the different input parameters that are taken into consideration. Several kinds of errors, including root mean square error (RMSE), coefficient of correlation (CC), variance account for (VAF), RMSE to observation's standard deviation ratio (RSR), and Nash-Sutcliffe effectiveness (NSE), were computed to determine the effectiveness of each algorithm. It was observed that, among all the models that were investigated, the GBM is the surrogate model that can predict the compressive strength of the geopolymer concrete with the highest degree of precision.

• 대한원격탐사학회지
• /
• 제37권2호
• /
• pp.321-335
• /
• 2021

미세먼지 (PM10) 및 초미세먼지 (PM2.5)는 인체에 흡수 가능하여 호흡기 질환 및 심장 질환과 같이 인체건강에 악영향을 미치며, 심각할 경우 조기 사망에 영향을 줄 수 있다. 전 세계적으로 현장관측기반의 모니터링을 수행하고 있지만 미 관측지역에 대한 대기질 분포의 공간적인 한계점이 존재하여 보다 광범위한 지역에 대한 지속적이고 정확한 모니터링이 필요한 상황이다. 위성기반 에어로졸 정보를 사용함으로써 이러한 현장 관측자료의 한계점을 극복할 수 있다. 따라서 본 연구에서는 다양한 위성 및 모델자료를 활용하여 2019년도에 대해 한 시간 단위의 지상 PM10 및 PM2.5 농도를 추정하였다. GOCI 위성의 관측영역을 포함하는 동아시아 지역에 대해 트리 기반 앙상블 방법을 사용하는 Boosting 기법인 GBRTs (Gradient Boosted Regression Trees)와 LightGBM (Light Gradient Boosting Machine)을 활용하여 모델을 구축하였다. 또한, 기상변수 및 토지피복변수의 사용유무에 따른 모델의 성능을 비교하기 위해 두 가지 festure set으로 나누어 테스트하였다. 두 기법 모두 주요 변수인 AOD (Aerosol Optical Depth), SSA (Single Scattering Albedo), DEM (Digital Eelevation Model), DOY (Day of Year), HOD (Hour of Day)와 기상변수 및 토지피복변수를 함께 사용한 Feature set 1을 사용하였을 때 높은 정확도를 보였다. Feature set 1에 대해 GBRT 모델이 LightGBM에 비해서약 10%의 정확도 향상을 보였다. 가장 정확도가 높았던 기상 및 지표면 변수를 포함한 Feature set1을 사용한 GBRT기반 모델을 최종모델로 선정하였으며 (PM10: R2 = 0.82 nRMSE = 34.9%, PM2.5: R2 = 0.75 nRMSE = 35.6%), 계절별 및 연평균 PM10 및 PM2.5 농도에 대한 공간적인 분포를 확인해본 결과, 현장관측자료와 비슷한 공간 분포를 보였으며, 국가별 농도 분포와 계절에 따른 시계열 농도 패턴을 잘 모의하였다.

• 전기학회논문지
• /
• 제65권1호
• /
• pp.142-149
• /
• 2016

This paper proposes a method to detect LP(License Plate) of vehicles in indoor and outdoor parking lots. In restricted environment, there are many conventional methods for detecting LP. But, it is difficult to detect LP in natural and complex scenes with background clutters because several patterns similar with text or LP always exist in complicated backgrounds. To verify the performance of LP text detection in natural images, we apply MB-LGP feature by combining with ensemble machine learning algorithm in purpose of selecting optimal features of small number in huge pool. The feature selection is performed by adaptive boosting algorithm that shows great performance in minimum false positive detection ratio and in computing time when combined with cascade approach. MSER is used to provide initial text regions of vehicle LP. Throughout the experiment using real images, the proposed method functions robustly extracting LP in natural scene as well as the controlled environment.

• 한국물환경학회지
• /
• 제37권5호
• /
• pp.335-343
• /
• 2021

Water quality prediction is essential for the proper management of water supply systems. Increased suspended sediment concentration (SSC) has various effects on water supply systems such as increased treatment cost and consequently, there have been various efforts to develop a model for predicting SSC. However, SSC is affected by both the natural and anthropogenic environment, making it challenging to predict SSC. Recently, advanced machine learning models have increasingly been used for water quality prediction. This study developed an ensemble machine learning model to predict SSC using the XGBoost (XGB) algorithm. The observed discharge (Q) and SSC in two fields monitoring stations were used to develop the model. The input variables were clustered in two groups with low and high ranges of Q using the k-means clustering algorithm. Then each group of data was separately used to optimize XGB (Model 1). The model performance was compared with that of the XGB model using the entire data (Model 2). The models were evaluated by mean squared error-ob servation standard deviation ratio (RSR) and root mean squared error. The RSR were 0.51 and 0.57 in the two monitoring stations for Model 2, respectively, while the model performance improved to RSR 0.46 and 0.55, respectively, for Model 1.

• Safety and Health at Work
• /
• 제10권4호
• /
• pp.452-460
• /
• 2019

Background: Monitoring and control of PM_2.5 are being recognized as key to address health issues attributed to PM_2.5. Availability of low-cost PM_2.5 sensors made it possible to introduce a number of portable PM_2.5 monitors based on light scattering to the consumer market at an affordable price. Accuracy of light scatteringe-based PM_2.5 monitors significantly depends on the method of calibration. Static calibration curve is used as the most popular calibration method for low-cost PM_2.5 sensors particularly because of ease of application. Drawback in this approach is, however, the lack of accuracy. Methods: This study discussed the calibration of a low-cost PM_2.5-monitoring device (PMD) to improve the accuracy and reliability for practical use. The proposed method is based on construction of the PM_2.5 sensor network using Message Queuing Telemetry Transport (MQTT) protocol and web query of reference measurement data available at government-authorized PM monitoring station (GAMS) in the republic of Korea. Four machine learning (ML) algorithms such as support vector machine, k-nearest neighbors, random forest, and extreme gradient boosting were used as regression models to calibrate the PMD measurements of PM_2.5. Performance of each ML algorithm was evaluated using stratified K-fold cross-validation, and a linear regression model was used as a reference. Results: Based on the performance of ML algorithms used, regression of the output of the PMD to PM_2.5 concentrations data available from the GAMS through web query was effective. The extreme gradient boosting algorithm showed the best performance with a mean coefficient of determination (R²) of 0.78 and standard error of 5.0 ㎍/㎥, corresponding to 8% increase in R² and 12% decrease in root mean square error in comparison with the linear regression model. Minimum 100 hours of calibration period was found required to calibrate the PMD to its full capacity. Calibration method proposed poses a limitation on the location of the PMD being in the vicinity of the GAMS. As the number of the PMD participating in the sensor network increases, however, calibrated PMDs can be used as reference devices to nearby PMDs that require calibration, forming a calibration chain through MQTT protocol. Conclusions: Calibration of a low-cost PMD, which is based on construction of PM_2.5 sensor network using MQTT protocol and web query of reference measurement data available at a GAMS, significantly improves the accuracy and reliability of a PMD, thereby making practical use of the low-cost PMD possible.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.31-31
• /
• 2023

During December 2022, the northeast monsoon, which dominates the south and the Gulf of Thailand, had significant rainfall that impacted the lower southern region, causing flash floods, landslides, blustery winds, and the river exceeding its bank. The Golok River, located in Narathiwat, divides the border between Thailand and Malaysia was also affected by rainfall. In flood management, instruments for measuring precipitation and water level have become important for assessing and forecasting the trend of situations and areas of risk. However, such regions are international borders, so the installed measuring telemetry system cannot measure the rainfall and water level of the entire area. This study aims to predict 72 hours of water level and evaluate the situation as information to support the government in making water management decisions, publicizing them to relevant agencies, and warning citizens during crisis events. This research is applied to machine learning (ML) for water level prediction of the Golok River, Lan Tu Bridge area, Sungai Golok Subdistrict, Su-ngai Golok District, Narathiwat Province, which is one of the major monitored rivers. The eXtreme Gradient Boosting (XGBoost) algorithm, a tree-based ensemble machine learning algorithm, was exploited to predict hourly water levels through the R programming language. Model training and testing were carried out utilizing observed hourly rainfall from the STH010 station and hourly water level data from the X.119A station between 2020 and 2022 as main prediction inputs. Furthermore, this model applies hourly spatial rainfall forecasting data from Weather Research and Forecasting and Regional Ocean Model System models (WRF-ROMs) provided by Hydro-Informatics Institute (HII) as input, allowing the model to predict the hourly water level in the Golok River. The evaluation of the predicted performances using the statistical performance metrics, delivering an R-square of 0.96 can validate the results as robust forecasting outcomes. The result shows that the predicted water level at the X.119A telemetry station (Golok River) is in a steady decline, which relates to the input data of predicted 72-hour rainfall from WRF-ROMs having decreased. In short, the relationship between input and result can be used to evaluate flood situations. Here, the data is contributed to the Operational support to the Special Water Resources Management Operation Center in Southern Thailand for flood preparedness and response to make intelligent decisions on water management during crisis occurrences, as well as to be prepared and prevent loss and harm to citizens.