• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.11
• /
• pp.435-442
• /
• 2018

Outlier detection means to detect data samples that deviate significantly from the distribution of normal data. Most outlier detection methods calculate an outlier score that indicates the extent to which a data sample is out of normal state and determine it to be an outlier when its outlier score is above a given threshold. However, since the range of an outlier score is different for each data and the outliers exist at a smaller ratio than the normal data, it is very difficult to determine the threshold value for an outlier score. Further, in an actual situation, it is not easy to acquire data including a sufficient amount of outliers available for learning. In this paper, we propose a clustering-based outlier detection method by constructing a model representing a normal data region using only normal data and performing binary classification of outliers and normal data for new data samples. Then, by dividing the given normal data into chunks, and constructing a clustering model for each chunk, we expand it to the ensemble method combining the decision by the models and apply it to the streaming data with dynamic changes. Experimental results using real data and artificial data show high performance of the proposed method.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.377-380
• /
• 2022

An application called an app can be downloaded and used on mobile devices. Among them, Android-based apps have the disadvantage of being implemented on an open source basis and can be exploited by anyone, but unlike iOS, which discloses only a small part of the source code, Android is implemented as an open source, so it can analyze the code. However, since anyone can participate in changing the source code of open source-based Android apps, the number of malicious codes increases and types are bound to vary. Malicious codes that increase exponentially in a short period of time are difficult for humans to detect one by one, so it is efficient to use a technique to detect malicious codes using AI. Most of the existing malicious app detection methods are to extract Features and detect malicious apps. Therefore, three ways to select the optimal feature to be used for learning after feature extraction are proposed. Finally, in the step of modeling with optimal features, ensemble techniques are used in addition to a single model. Ensemble techniques have already shown results beyond the performance of a single model, as has been shown in several studies. Therefore, this paper presents a plan to select the optimal feature and implement a learning model for Android app-based malicious code detection.

• Wind and Structures
• /
• v.4 no.5
• /
• pp.441-454
• /
• 2001

Conical vortices on roof corners of a prismatic low-rise building have been investigated by using the PIV(Particle Image Velocimetry) technique. The Reynolds number based on the free stream velocity and model height was $5.3{\times}10^3$. Mean and instantaneous vector fields for velocity, vorticity, and turbulent kinetic energy were measured at two vertical planes and for two different flow angles of $30^{\circ}$ and $45^{\circ}$. The measurements provided a clear view of the complex flow structures on roof corners such as a pair of counter rotating conical vortices, secondary vortices, and tertiary vortices. They also enabled accurate and easy measurement of the size of vortices. Additionally, we could easily locate the centers of the vortices from the ensemble averaged velocity fields. It was observed that the flow angle of a $30^{\circ}$ produces a higher level of vorticity and turbulent kinetic energy in one of the pair of vortices than does the $45^{\circ}$ flow angle.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.20 no.6
• /
• pp.126-131
• /
• 2012

Tire force is one of important parameters which determine vehicle dynamics. However, it is hard to measure tire force directly through sensors. Not only the sensor is expensive but also installation of sensors on harsh environments is difficult. Therefore, estimation algorithms based on vehicle dynamic models are introduced to estimate the tire forces indirectly. In this paper, an estimation system for estimating lateral force and states is suggested. The state-space equation is constructed based on the 3-DOF bicycle model. Extended Kalman Filter, Unscented Kalman Filter and Ensemble Kalman Filter are used for estimating states on the nonlinear system. Performance of each algorithm is evaluated in terms of RMSE (Root Mean Square Error) and maximum error.

• International Journal of Fluid Machinery and Systems
• /
• v.9 no.3
• /
• pp.265-276
• /
• 2016

Energy systems working coherently in different conditions may not have a specific design which can provide optimal performance. A system working for a longer period at lower efficiency implies higher energy consumption. In this effort, a methodology demonstrated by a jet pump design and optimization via numerical modeling for fluid dynamics and implementation of an evolutionary algorithm for the optimization shows a reduction in computational costs. The jet pump inherently has a low efficiency because of improper mixing of primary and secondary fluids, and multiple momentum and energy transfer phenomena associated with it. The high fidelity solutions were obtained through a validated numerical model to construct an approximate function through surrogate analysis. Pareto-optimal solutions for two objective functions, i.e., secondary fluid pressure head and primary fluid pressure-drop, were generated through a multi-objective genetic algorithm. For the jet pump geometry, a design space of several design variables was discretized using the Latin hypercube sampling method for the optimization. The performance analysis of the surrogate models shows that the combined surrogates perform better than a single surrogate and the optimized jet pump shows a higher performance. The approach can be implemented in other energy systems to find a better design.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2009.05a
• /
• pp.27-31
• /
• 2009

홍수피해를 예방할 수 있는 대책에는 여러 가지 방법이 있으나 비구조물적인 방법 중에서 대표적인 것이 홍수예경보이다. 이에 합리적인 설계홍수량 산정을 위해 하천유역에서 강우-유출과정의 정확한 해석과 유출예측은 수자원의 효율적인 활용과 하천의 이수, 치수를 위한 수문학적 해석에 있어서 매우 중요하며, 이를 위해서는 강우로부터 정도 높은 유출량 예측이 요구된다. 뿐만 아니라 하천범람 등의 재해로부터 인명과 재산을 보호하기 위한 홍수예경보 시스템의 구축이 필요하다. 홍수예경보 시스템의 효율적인 관리를 위해서는 실시간 홍수예측(Real-time Flood Prediction)기법의 개발이 필요하다. 홍수유출모형에 있어 공간적 변화특성과 평균 강우량의 공간분포를 반영할 수 있는 분포형 매개변수 모형(Distributed-Parameter Model)인 분포형 모델을 대상으로 앙상블 칼만필터(Ensemble Kalman Filter, EnKF) 이론을 적용하여 비선형시스템에서 오차를 포함한 반응을 실시간으로 처리하여 불확실성을 정량적으로 감소시켜 홍수유출을 예측하는데 그 목적이 있다. 하천유역특성을 이용한 홍수유출예측을 위하여 비선형시스템에서의 앙상블 칼만필터 기법을 적용한 분포형 모형을 이용하여 더욱 정밀한 홍수유출을 예측하게 되고 향후 홍수예경보모형으로서 적정 유역분할 규모를 결정해주는 근거를 제시할 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.160-160
• /
• 2017

본 연구는 앙상블 칼만필터(Ensemble Kalman Filter)를 통해 인공위성 기반 토양수분 자료를 수문모형에 동화하여 단위 격자에 대한 수문인자를 산출하고자 한다. 수문모형은 Variable Infiltration Capacity(VIC) model을 대상으로 수행하였으며, 시범 유역으로는 소양강댐 유역을 선정하였다. 입력자료는 2007년 이후 8년간 자료를 수집하였으며, 2007-2010년 관측 유량 자료를 사용하여 모형을 보정하고, 2011-2014년 자료를 통하여 검증하였다. Isolated-Speciation Particle Swarm Optimization(ISPSO) 기법을 통하여 매개변수를 추정하였고, 보정기간 뿐 아니라 검증 기간에 대해서도 높은 모형효율성계수를 얻을 수 있었다. VIC 모형 자료 동화 대상 자료로는 AMSR2 위성 토양 수분 자료, 지상관측 토양수분 보간자료 및 조건부합성방법을 통한 위성/지점 융합 토양수분을 선정하였다. 위성 토양 수분 자료는 값을 과대 추정하는 경향이 있었으며, 지상관측 보간 자료는 유량이 큰 사상에 대한 첨두 유량을 과소 추정하는 경향을 보였다. 인공위성자료와 지상 자료를 합성한 조건부합성기법 토양수분자료는 더 정확한 추정이 가능하여 모의의 정확도가 향상되었다. 본 연구를 통해서 미계측 유역에 대해 격자별 수문기상인자 정보를 제공할 수 있으며, 데이터베이스를 구축하여 다양한 수문분석에 기초자료로 활용될 수 있을 것이다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.67-75
• /
• 2022

Recently, e-learning has been attracting significant attention due to COVID-19. However, while e-learning has many advantages, it has disadvantages as well. One of the main disadvantages of e-learning is that it is difficult for teachers to continuously and systematically monitor learners. Although services such as personalized e-learning are provided to compensate for the shortcoming, systematic monitoring of learners' concentration is insufficient. This study suggests a method to evaluate the learner's concentration by applying machine learning techniques. In this study, emotion and gaze data were extracted from 184 videos of 92 participants. First, the learners' concentration was labeled by experts. Then, statistical-based status indicators were preprocessed from the data. Random Forests (RF), Support Vector Machines (SVMs), Multilayer Perceptron (MLP), and an ensemble model have been used in the experiment. Long Short-Term Memory (LSTM) has also been used for comparison. As a result, it was possible to predict e-learners' concentration with an accuracy of 90.54%. This study is expected to improve learners' immersion by providing a customized educational curriculum according to the learner's concentration level.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.8
• /
• pp.89-97
• /
• 2022

The e-commerce market faces significant credit risks due to the complexity of the industry and information asymmetries. Therefore, credit risk has started to stymie the growth of e-commerce. However, there is no reliable system for evaluating the creditworthiness of e-commerce companies. Therefore, this paper constructs a credit risk evaluation index system that comprehensively considers the online and offline behavior of online retail enterprises, including 15 indicators that reflect online credit risk and 15 indicators that reflect offline credit risk. This paper establishes an integration method based on a fuzzy integral support vector machine, which takes the factor analysis results of the credit risk evaluation index system of online retail enterprises as the input and the credit risk evaluation results of online retail enterprises as the output. The classification results of each sub-classifier and the importance of each sub-classifier decision to the final decision have been taken into account in this method. Select the sample data of 1500 online retail loan customers from a bank to test the model. The empirical results demonstrate that the proposed method outperforms a single SVM and traditional SVMs aggregation technique via majority voting in terms of classification accuracy, which provides a basis for banks to establish a reliable evaluation system.

• ETRI Journal
• /
• v.45 no.3
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.