• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• Smart Media Journal
• /
• v.10 no.3
• /
• pp.39-47
• /
• 2021

Enhanced index tracking is a problem of optimizing the objective function to generate returns above the index based on the index tracking that follows the market return. In order to avoid problems such as large transaction costs and illiquidity, we used a method of constructing a portfolio by selecting only some of the stocks included in the index. Commonly used enhanced index tracking methods tried to find the optimal portfolio with only one objective function in all tested periods, but it is almost impossible to find the ultimate strategy that always works well in the volatile financial market. In addition, it is important to improve generalization performance beyond optimizing the objective function for training data due to the nature of the financial market, where statistical characteristics change significantly over time, but existing methods have a limitation in that there is no direct discussion for this. In order to solve these problems, this paper proposes ensemble learning that composes a portfolio by combining several objective functions and a 3-stage portfolio selection algorithm that can select a portfolio by applying criteria other than the objective function to the training data. The proposed method in an experiment using the S&P500 index shows Sharpe ratio that is 27% higher than the index and the existing methods, showing that the 3-stage portfolio selection algorithm and ensemble learning are effective in selecting an enhanced index portfolio.

• Journal of Korea Multimedia Society
• /
• v.18 no.4
• /
• pp.437-442
• /
• 2015

Voice activity detection is very important process that voice activity separated form noisy speech signal for speech enhance. Over the past few years, many studies have been made on voice activity detection, but it has poor performance in low signal to noise ratio environment or fickle noise such as car noise. In this paper, it proposed new voice activity detection algorithm using ensemble variance based on wavelet band entropy and soft thresholding method. We conduct a survey in a lot of signal to noise ratio environment of car noise to evaluate performance of the proposed algorithm and confirmed performance of the proposed algorithm.

• Journal of Korean Society of Disaster and Security
• /
• v.16 no.4
• /
• pp.129-136
• /
• 2023

A special offshore bridge with a high pylon has special structural features.Special offshore bridges have inspection blind spots that are difficult to visually inspect. To solve this problem, safety inspection methods using drones are being studied. In this study, image data of the pylon of a special offshore bridge was acquired using a drone. In addition, an artificial intelligence algorithm was developed to detect damage to the pylon surface. The AI algorithm utilized a deep learning network with different structures. The algorithm applied the stacking ensemble learning method to build a model that formed the ensemble and collect the results.

• Journal of the Korean Chemical Society
• /
• v.53 no.6
• /
• pp.653-662
• /
• 2009

Developing effective tools for predicting absorption, distribution, metabolism, excretion properties and toxicity (ADME/T) of new chemical entities in the early stage of drug design is one of the most important tasks in drug discovery and development today. As one of these attempts, support vector machines (SVM) has recently been exploited for the prediction of ADME/T related properties. However, two problems in SVM modeling, i.e. feature selection and parameters setting, are still far from solved. The two problems have been shown to be crucial to the efficiency and accuracy of SVM classification. In particular, the feature selection and optimal SVM parameters setting influence each other, which indicates that they should be dealt with simultaneously. In this account, we present an integrated practical solution, in which genetic-based algorithm (GA) is used for feature selection and grid search (GS) method for parameters optimization. hERG ion-channel inhibitor classification models of ADME/T related properties has been built for assessing and testing the proposed GA-GS-SVM. We generated 6 different models that are 3 different single models and 3 different ensemble models using training set - 1891 compounds and validated with external test set - 175 compounds. We compared single model with ensemble model to solve data imbalance problems. It was able to improve accuracy of prediction to use ensemble model.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.4
• /
• pp.173-178
• /
• 2023

As Korean literature spreads around the world, its position in the overseas publishing market has become important. As demand in the overseas publishing market continues to grow, it is essential to predict future book sales and analyze the characteristics of books that have been highly favored by overseas readers in the past. In this study, we proposed ensemble learning based prediction model and analyzed characteristics of the cumulative sales of more than 5,000 copies classified as good sellers published overseas over the past 5 years. We applied the five ensemble learning models, i.e., XGBoost, Gradient Boosting, Adaboost, LightGBM, and Random Forest, and compared them with other machine learning algorithms, i.e., Support Vector Machine, Logistic Regression, and Deep Learning. Our experimental results showed that the ensemble algorithm outperforms other approaches in troubleshooting imbalanced data. In particular, the LightGBM model obtained an AUC value of 99.86% which is the best prediction performance. Among the features used for prediction, the most important feature is the author's number of overseas publications, and the second important feature is publication in countries with the largest publication market size. The number of evaluation participants is also an important feature. In addition, text mining was performed on the four book reviews that sold the most among good-selling books. Many reviews were interested in stories, characters, and writers and it seems that support for translation is needed as many of the keywords of "translation" appear in low-rated reviews.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.71-80
• /
• 2024

In this study, a proposed ensemble learning technique aims to enhance the semantic segmentation performance of images captured by Unmanned Aerial Vehicles (UAVs). With the increasing use of UAVs in fields such as urban planning, there has been active development of techniques utilizing deep learning segmentation methods for land cover segmentation. The study suggests a method that utilizes prominent segmentation models, namely U-Net, DeepLabV3, and Fully Convolutional Network (FCN), to improve segmentation prediction performance. The proposed approach integrates training loss, validation accuracy, and class score of the three segmentation models to enhance overall prediction performance. The method was applied and evaluated on a land cover segmentation problem involving seven classes: buildings,roads, parking lots, fields, trees, empty spaces, and areas with unspecified labels, using images captured by UAVs. The performance of the ensemble model was evaluated by mean Intersection over Union (mIoU), and the results of comparing the proposed ensemble model with the three existing segmentation methods showed that mIoU performance was improved. Consequently, the study confirms that the proposed technique can enhance the performance of semantic segmentation models.

• East Asian Economic Review
• /
• v.25 no.4
• /
• pp.403-424
• /
• 2021

AdaBoost tweaks the sample weight for each training set used in the iterative process, however, it is demonstrated that it provides more correlated errors as the boosting iteration proceeds if models' accuracy is high enough. Therefore, in this study, we propose a novel way to improve the performance of the existing AdaBoost algorithm by employing heterogeneous models and a stochastic twist. By employing the heterogeneous ensemble, it ensures different models that have a different initial assumption about the data are used to improve on diversity. Also, by using a stochastic algorithm with a decaying convergence rate, the model is designed to balance out the trade-off between model prediction performance and model convergence. The result showed that the stochastic algorithm with decaying convergence rate's did have a improving effect and outperformed other existing boosting techniques.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.336-338
• /
• 1999

본 논문에서는 사회 학습의 이론의 하나인 관찰 학습 이론에 기반한 네트웍 앙상블을 위한 관찰 학습 알고리즘을 제안한다. 하나의 네트웍이 학습할 대 함께 학습되는 다른 네트웍들을 이용하여 가상 데이터를 생성하여 학습에 이용하므로써 데이터가 부족한 경우 네트웍이 과학습 되는 것을 방지고 각 네트웍의 일반화 성능을 향상시키는 동시에 앙상블의 성능도 향상시킨다. 제안된 방법을 사인 함수의 근사 문제와 중첩된 두 정규 분포의 분류 문제에 적용하고 단일 네트웍, 네트웍 위원회, Bagging 알고리즘과 비교하여 제안된 방법의 일반화 성능의 우수성을 보였다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.10a
• /
• pp.33-36
• /
• 2000

관찰학습(OLA: Observational Learning Algorithm)은 앙상블 네트워크의 각 구성 모델들이 다른 모델들을 관찰함으로써 얻어진 가상 데이터와 초기에 bo otstrap된 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 비교실험에 의하여, 보다 적은 수의 구성 모델로 동일 내지 보다 나은 성능을 나타냄이 실험적으로 검증되었다.