• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.308-310
• /
• 2000

관찰학습(OLA: Observational Learning Algorithm)은 앙상블 네트워크의 각 구성 모델들이 아른 모델들을 관찰함으로써 얻어진 가상 데이터와 초기에 bootstrap된 실제 데이터를 학습에 함께 이용하는 방법이다. 본 논문에서는, 초기 학습 데이터 셋을 분할하고 분할된 각 데이터 셋에 대하여 앙상블의 구성 모델들을 전문화(specialize)시키는 방법을 적용하여 기존의 관찰학습 알고리즘을 개선시켰다. 제안된 알고리즘은 bagging 및 boosting과의 비교 실험에 의하여, 보다 적은 수의 구성 모델로 동일 내지 보다 나은 성능을 나타냄이 실험적으로 검증되었다.

• Smart Media Journal
• /
• v.7 no.1
• /
• pp.16-23
• /
• 2018

In this paper, we used the Deep Neural Network (DNN) to predict the number of daily spectators of Gwangju - KIA Champions Field in order to provide marketing data for the team and related businesses and for managing the inventories of the facilities in the stadium. In this study, the DNN model, which is based on an artificial neural network (ANN), was used, and four kinds of DNN model were designed along with dropout and batch normalization model to prevent overfitting. Each of four models consists of 10 DNNs, and we added extra models with ensemble model. Each model was evaluated by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). The learning data from the model randomly selected 80% of the collected data from 2008 to 2017, and the other 20% were used as test data. With the result of 100 data selection, model configuration, and learning and prediction, we concluded that the predictive power of the DNN model with ensemble model is the best, and RMSE and MAPE are 15.17% and 14.34% higher, correspondingly, than the prediction value of the multiple linear regression model.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.2
• /
• pp.99-110
• /
• 2023

This study proposed a classification of malicious network traffic using the cyber threat framework(Mitre ATT&CK) and machine learning to solve the real-time traffic detection problems faced by current security monitoring systems. We applied a network traffic dataset called UNSW-NB15 to the Mitre ATT&CK framework to transform the label and generate the final dataset through rare class processing. After learning several boosting-based ensemble models using the generated final dataset, we demonstrated how these ensemble models classify network traffic using various performance metrics. Based on the F-1 score, we showed that XGBoost with no rare class processing is the best in the multi-class traffic environment. We recognized that machine learning ensemble models through Mitre ATT&CK label conversion and oversampling processing have differences over existing studies, but have limitations due to (1) the inability to match perfectly when converting between existing datasets and Mitre ATT&CK labels and (2) the presence of excessive sparse classes. Nevertheless, Catboost with B-SMOTE achieved the classification accuracy of 0.9526, which is expected to be able to automatically detect normal/abnormal network traffic.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.129-136
• /
• 2020

The advantages of Blockchain present the necessity of Blockchain in various fields. However, there are several disadvantages to Blockchain. Among them, the uncle block problem is one of the problems that can greatly hinder the value and utilization of Blockchain. Although the value of Blockchain may be degraded by the uncle block problem, previous studies did not pay much attention to research on uncle block. Therefore, the purpose of this study attempts to predict the occurrence of uncle block in order to predict and prepare for the uncle block problem of Blockchain. This study verifies the validity of introducing new attributes and ensemble analysis techniques for accurate prediction of uncle block occurrence. As a research method, voting, bagging, and stacking ensemble analysis techniques were employed for Ethereum's uncle block where the uncle block problem actually occurs. We used Blockchain information of Ethereum and Bitcoin as analysis data. As a result of the study, we found that the best prediction result was presented when voting and stacking ensemble techniques were applied using only Ethereum Blockchain information. The result of this study contributes to more accurately predict the occurrence of uncle block and prepare for the uncle block problem of Blockchain.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of Korean Society of Disaster and Security
• /
• v.15 no.4
• /
• pp.87-98
• /
• 2022

In recent years, frequent localized heavy rainfalls, which have a lot of rainfall in a short period of time, have been increasingly causing flooding damages. To prevent damage caused by localized heavy rainfalls, Hydrological Quantitative Precipitation Forecast (HQPF) was developed using the Local ENsemble prediction System (LENS) provided by the Korea Meteorological Administration (KMA) and Machine Learning and Probability Matching (PM) techniques using Digital forecast data. HQPF is produced as information on the impact of heavy rainfall to prepare for flooding damage caused by localized heavy rainfalls, but there is a tendency to overestimate the low rainfall intensity. In this study, we improved HQPF by expanding the period of machine learning data, analyzing ensemble techniques, and changing the process of Probability Matching (PM) techniques to improve predictive accuracy and over-predictive propensity of HQPF. In order to evaluate the predictive performance of the improved HQPF, we performed the predictive performance verification on heavy rainfall cases caused by the Changma front from August 27, 2021 to September 3, 2021. We found that the improved HQPF showed a significantly improved prediction accuracy for rainfall below 10 mm, as well as the over-prediction tendency, such as predicting the likelihood of occurrence and rainfall area similar to observation.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.5
• /
• pp.1125-1132
• /
• 2017

In a situation where the severity and frequency of drought events getting stronger and higher, many studies related to drought forecast have been conducted to improve the drought forecast accuracy. However it is difficult to predict drought events using a single model because of nonlinear and complicated characteristics of temporal behavior of drought events. In this study, in order to overcome the shortcomings of the single model approach, we first build various single models capable to explain the relationship between the meteorological drought index, Standardized Precipitation Index (SPI), and other independent variables such as world climate indices. Then, we developed a combined models using Stochastic Gradient Descent method among Ensemble Learnings.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.