• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.65 no.3
• /
• pp.204-209
• /
• 2016

It is difficult to establish accurate modeling of PV power system because of various uncertainty. However, it is important work to modeling of PV for fault diagnosis. This paper proposes modeling and fault diagnosis method using correlation analysis and ELM(Extreme Learning Machine). Rather than using total data, we select optimal time interval with higher corelation between PV power and solar irradiation. Also, we use average value during 60 minute to avoid rapid variation of PV power. To show the effectiveness of the proposed method, we performed various experiments by dataset.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.8
• /
• pp.55-61
• /
• 2010

In this paper, we proposed selective extraction method of frequency information and PCA-ELM based diagnosis system for three-phase induction motors. As the first step for diagnosis procedure, DFT is performed to transform the acquired current signal into frequency domain. And then, frequency components are selected according to discriminate order calculated by variance As the next step, feature extraction is performed by principal component analysis (PCA). Finally, we used the classifier based on Extreme Learning Machine (ELM) with fast learning procedure. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.18-30
• /
• 2022

Predicting remaining useful life (RUL) becomes significant to implement prognostics and health management of industrial systems. The relevant studies have contributed to creating RUL prediction models and validating their acceptable performance; however, they are confined to drive reasonable preventive maintenance strategies derived from and connected with such predictive models. This paper proposes a data-driven preventive maintenance method that predicts RUL of industrial systems and determines the optimal replacement time intervals to lead to cost minimization in preventive maintenance. The proposed method comprises: (1) generating RUL prediction models through learning historical process data by using machine learning techniques including random forest and extreme gradient boosting, and (2) applying the system failure time derived from the RUL prediction models to the Weibull distribution-based minimum-repair block replacement model for finding the cost-optimal block replacement time. The paper includes a case study to demonstrate the feasibility of the proposed method using an open dataset, wherein sensor data are generated and recorded from turbofan engine systems.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.745-760
• /
• 2021

Prediction of a stock price has been a subject of interest for a long time in financial markets, and thus, many studies have been conducted in various directions. As the efficient market hypothesis introduced in the 1970s acquired supports, it came to be the majority opinion that it was impossible to predict stock prices. However, recent advances in predictive models have led to new attempts to predict the future prices. Here, we summarize past studies on the price prediction by evaluation measures, and predict the direction of stock prices of Samsung Electronics, LG Chem, and NAVER by applying various machine learning models. In addition to widely used technical indicator variables, accounting indicators such as Price Earning Ratio and Price Book-value Ratio and outputs of the hidden Markov Model are used as predictors. From the results of our analysis, we conclude that no models show significantly better accuracy and it is not possible to predict the direction of stock prices with models used. Considering that the models with extra predictors show relatively high test accuracy, we may expect the possibility of a meaningful improvement in prediction accuracy if proper variables that reflect the opinions and sentiments of investors would be utilized.

• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.97-117
• /
• 2021

Predicting term deposit subscriptions is one of representative financial marketing in banks, and banks can build a prediction model using various customer information. In order to improve the classification accuracy for term deposit subscriptions, many studies have been conducted based on machine learning techniques. However, even if these models can achieve satisfactory performance, utilizing them is not an easy task in the industry when their decision-making process is not adequately explained. To address this issue, this paper proposes an explainable scheme for term deposit subscription forecasting. For this, we first construct several classification models using decision tree-based ensemble learning methods, which yield excellent performance in tabular data, such as random forest, gradient boosting machine (GBM), extreme gradient boosting (XGB), and light gradient boosting machine (LightGBM). We then analyze their classification performance in depth through 10-fold cross-validation. After that, we provide the rationale for interpreting the influence of customer information and the decision-making process by applying Shapley additive explanation (SHAP), an explainable artificial intelligence technique, to the best classification model. To verify the practicality and validity of our scheme, experiments were conducted with the bank marketing dataset provided by Kaggle; we applied the SHAP to the GBM and LightGBM models, respectively, according to different dataset configurations and then performed their analysis and visualization for explainable term deposit subscriptions.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.390-399
• /
• 2022

Cyber security and resilience are phrases that describe safeguards of ICTs (information and communication technologies) from cyber-attacks or mitigations of cyber event impacts. The sole purpose of Risk models are detections, analyses, and handling by considering all relevant perceptions of risks. The current research effort has resulted in the development of a new paradigm for safeguarding services offered online which can be utilized by both service providers and users. customers. However, rather of relying on detailed studies, this approach emphasizes task selection and execution that leads to successful risk treatment outcomes. Modelling intelligent CSGs (Cyber Security Games) using MLTs (machine learning techniques) was the focus of this research. By limiting mission risk, CSGs maximize ability of systems to operate unhindered in cyber environments. The suggested framework's main components are the Threat and Risk models. These models are tailored to meet the special characteristics of online services as well as the cyberspace environment. A risk management procedure is included in the framework. Risk scores are computed by combining probabilities of successful attacks with findings of impact models that predict cyber catastrophe consequences. To assess successful attacks, models emulating defense against threats can be used in topologies. CSGs consider widespread interconnectivity of cyber systems which forces defending all multi-step attack paths. In contrast, attackers just need one of the paths to succeed. CSGs are game-theoretic methods for identifying defense measures and reducing risks for systems and probe for maximum cyber risks using game formulations (MiniMax). To detect the impacts, the attacker player creates an attack tree for each state of the game using a modified Extreme Gradient Boosting Decision Tree (that sees numerous compromises ahead). Based on the findings, the proposed model has a high level of security for the web sources used in the experiment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.581-588
• /
• 2017

This study was conducted to determine which factors would predict metabolic syndrome (MetS) perception and exercise by applying a machine learning classifier, or Extreme Gradient Boosting algorithm (XGBoost) from July 2014 to December 2015. Data were obtained from the Korean Community Health Survey (KCHS), representing different community-dwelling Korean adults 19 years and older, from 2009 to 2013. The dataset includes 370,430 adults. Outcomes were categorized as follows based on the perception of MetS and physical activity (PA): Stage 1 (no perception, no PA), Stage 2 (perception, no PA), and Stage 3 (perception, PA). Features common to all questionnaires for the last 5 years were selected for modeling. Overall, there were 161 features, categorical except for age and the visual analogue scale (EQ-VAS). We used the Extreme Boosting algorithm in R programming for a model to predict factors and achieved prediction accuracy in 0.735 submissions. The top 10 predictive factors in Stage 3 were: age, education level, attempt to control weight, EQ mobility, nutrition label checks, private health insurance, EQ-5D usual activities, anti-smoking advertising, EQ-VAS, education in health centers for diabetes, and dental care. In conclusion, the results showed that XGBoost can be used to identify factors influencing disease prevention and management using healthcare bigdata.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.1
• /
• pp.95-107
• /
• 2017

In this study, a preliminary study was undertaken for development of a tunnel incident automatic detection system based on a machine learning algorithm which is to detect a number of incidents taking place in tunnel in real time and also to be able to identify the type of incident. Two road sites where CCTVs are operating have been selected and a part of CCTV images are treated to produce sets of training data. The data sets are composed of position and time information of moving objects on CCTV screen which are extracted by initially detecting and tracking of incoming objects into CCTV screen by using a conventional image processing technique available in this study. And the data sets are matched with 6 categories of events such as lane change, stoping, etc which are also involved in the training data sets. The training data are learnt by a resilience neural network where two hidden layers are applied and 9 architectural models are set up for parametric studies, from which the architectural model, 300(first hidden layer)-150(second hidden layer) is found to be optimum in highest accuracy with respect to training data as well as testing data not used for training. From this study, it was shown that the highly variable and complex traffic and incident features could be well identified without any definition of feature regulation by using a concept of machine learning. In addition, detection capability and accuracy of the machine learning based system will be automatically enhanced as much as big data of CCTV images in tunnel becomes rich.