• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.6
• /
• pp.417-424
• /
• 2021

Algal bloom is an ongoing issue in the management of freshwater systems for drinking water supply, and the chlorophyll-a concentration is commonly used to represent the status of algal bloom. Thus, the prediction of chlorophyll-a concentration is essential for the proper management of water quality. However, the chlorophyll-a concentration is affected by various water quality and environmental factors, so the prediction of its concentration is not an easy task. In recent years, many advanced machine learning algorithms have increasingly been used for the development of surrogate models to prediction the chlorophyll-a concentration in freshwater systems such as rivers or reservoirs. This study used a light gradient boosting machine(LightGBM), a gradient boosting decision tree algorithm, to develop an ensemble machine learning model to predict chlorophyll-a concentration. The field water quality data observed at Daecheong Lake, obtained from the real-time water information system in Korea, were used for the development of the model. The data include temperature, pH, electric conductivity, dissolved oxygen, total organic carbon, total nitrogen, total phosphorus, and chlorophyll-a. First, a LightGBM model was developed to predict the chlorophyll-a concentration by using the other seven items as independent input variables. Second, the time-lagged values of all the input variables were added as input variables to understand the effect of time lag of input variables on model performance. The time lag (i) ranges from 1 to 50 days. The model performance was evaluated using three indices, root mean squared error-observation standard deviation ration (RSR), Nash-Sutcliffe coefficient of efficiency (NSE) and mean absolute error (MAE). The model showed the best performance by adding a dataset with a one-day time lag (i=1) where RSR, NSE, and MAE were 0.359, 0.871 and 1.510, respectively. The improvement of model performance was observed when a dataset with a time lag up of about 15 days (i=15) was added.

• Journal of Cadastre & Land InformatiX
• /
• v.46 no.2
• /
• pp.43-55
• /
• 2016

This study estimated land prices using instance-based learning. A k-nearest neighbor method was utilized among various instance-based learning methods, and the 10 distance metrics including Euclidean distance were calculated in k-nearest neighbor estimation. One distance metric prediction which shows the best predictive performance would be normally chosen as final estimate out of 10 distance metric predictions. In contrast to this practice, an ensemble technique which combines multiple predictions to obtain better performance was applied in this study. We applied the gradient boosting algorithm, a sort of residual-fitting model to our data in ensemble combining. Sales price data of farm lands in Haenam-gun, Jeolla Province were used to demonstrate advantages of instance-based learning as well as an ensemble technique. The result showed that the ensemble prediction was more accurate than previous 10 distance metric predictions.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.171-177
• /
• 2021

Through the rapid developments in machine learning, there have been diverse utilization approaches not only in industrial fields but also in daily life. Implementations of machine learning on financial data, also have been of interest. Herein, we employ machine learning algorithms to store sales data and present future applications for fintech enterprises. We utilize diverse missing data processing methods to handle missing data and apply gradient boosting machine learning algorithms; XGBoost, LightGBM, CatBoost to predict the future revenue of individual stores. As a result, we found that using median imputation onto missing data with the appliance of the xgboost algorithm has the best accuracy. By employing the proposed method, fintech enterprises and customers can attain benefits. Stores can benefit by receiving financial assistance beforehand from fintech companies, while these corporations can benefit by offering financial support to these stores with low risk.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.201-222
• /
• 2023

As the e-Commerce gets increased based on the platform, a lot of small and medium sized sellers have tried to develop the more effective strategies to maximize the profit. In order to increase the profitability, it is quite important to make the strategic decisions based on the range of promotion, discount rate and categories of products. This research aims to develop the business intelligence application which can help sellers of e-Commerce platform make better decisions. To decide whether or not to promote, it is needed to predict the level of increase in sales after promotion. I n this research, we have applied the various machine learning algorithm such as MLP(Multi Layer Perceptron), Gradient Boosting Regression, Random Forest, and Linear Regression. Because of the complexity of data structure and distinctive characteristics of product categories, Random Forest and MLP showed the best performance. It seems possible to apply the proposed approach in this research in support the small and medium sized sellers to react on the market changes and to make the reasonable decisions based on the data, not their own experience.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.13 no.3
• /
• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• 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
• /
• v.32 no.6
• /
• 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.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.321-335
• /
• 2021

Particulate matter (PM10 and PM2.5 with a diameter less than 10 and 2.5 ㎛, respectively) can be absorbed by the human body and adversely affect human health. Although most of the PM monitoring are based on ground-based observations, they are limited to point-based measurement sites, which leads to uncertainty in PM estimation for regions without observation sites. It is possible to overcome their spatial limitation by using satellite data. In this study, we developed machine learning-based retrieval algorithm for ground-level PM10 and PM2.5 concentrations using aerosol parameters from Geostationary Ocean Color Imager (GOCI) satellite and various meteorological parameters from a numerical weather prediction model during January to December of 2019. Gradient Boosted Regression Trees (GBRT) and Light Gradient Boosting Machine (LightGBM) were used to estimate PM concentrations. The model performances were examined for two types of feature sets-all input parameters (Feature set 1) and a subset of input parameters without meteorological and land-cover parameters (Feature set 2). Both models showed higher accuracy (about 10 % higher in R2) by using the Feature set 1 than the Feature set 2. The GBRT model using Feature set 1 was chosen as the final model for further analysis(PM10: R2 = 0.82, nRMSE = 34.9 %, PM2.5: R2 = 0.75, nRMSE = 35.6 %). The spatial distribution of the seasonal and annual-averaged PM concentrations was similar with in-situ observations, except for the northeastern part of China with bright surface reflectance. Their spatial distribution and seasonal changes were well matched with in-situ measurements.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.1
• /
• 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.

• Journal of Korean Society on Water Environment
• /
• v.37 no.5
• /
• 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.