• Journal of Broadcast Engineering
• /
• v.13 no.1
• /
• pp.92-98
• /
• 2008

Network data modeling is a essential research for the evaluation for intrusion detection systems performance, network modeling and methods for analyzing network data. In network data modeling, real data from the network must be analyzed and the modeled data must be efficiently composed to reflect a sufficient amount of the original data. In this parer the useful elements of real network data were quantified from packets captured from a huge network. Futhermore, a statistical analysis method was used to find the most effective element for efficiently classifying the modeled data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4204-4222
• /
• 2015

Cloud is the latest buzz word in the internet community among developers, consumers and security researchers. There have been many attacks on the cloud in the recent past where the services got interrupted and consumer privacy has been compromised. Denial of Service (DoS) attacks effect the service availability to the genuine user. Customers are paying to use the cloud, so enhancing the availability of services is a paramount task for the service provider. In the presence of DoS attacks, the availability is reduced drastically. Such attacks must be detected and prevented as early as possible and the power of computational approaches can be used to do so. In the literature, machine learning techniques have been used to detect the presence of attacks. In this paper, a novel approach is proposed, where intelligent rule based feature selection and classification are performed for DoS attack detection in the cloud. The performance of the proposed system has been evaluated on an experimental cloud set up with real time DoS tools. It was observed that the proposed system achieved an accuracy of 98.46% on the experimental data for 10,000 instances with 10 fold cross-validation. By using this methodology, the service providers will be able to provide a more secure cloud environment to the customers.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• Journal of IKEEE
• /
• v.18 no.1
• /
• pp.1-7
• /
• 2014

In this paper, we suggest an improved Viola-Jones detection framework for the efficient feature selection and the fast rejection method of the sub-window. Our object detector has low computational complexity because it rejects sub-windows until specific threshold. Owing to using same framework, detection performance is same with the existing Viola-Jones detector. We measure the number of average feature calculation about MIT-CMU test set. As a result of the experiment, the number of average feature calculation is reduced to 45.5% and the detection speed is improved about 58.5% compared with the previous algorithm.

• Journal of the Korean Society of Safety
• /
• v.20 no.4 s.72
• /
• pp.130-137
• /
• 2005

Decision tree algorithm is one of the data mining techniques, which conducts grouping or prediction into several sub-groups from interested groups. This technique can analyze a feature of type on groups and can be used to detect differences in the type of industrial accidents. This paper uses C4.5 algorithm for the feature analysis. The data set consists of 24,887 features through data selection from total data of 25,159 taken from 2 year observation of industrial accidents in Korea For the purpose of this paper, one target value and eight independent variables are detailed by type of industrial accidents. There are 222 total tree nodes and 151 leaf nodes after grouping. This paper Provides an acceptable level of accuracy(%) and error rate(%) in order to measure tree accuracy about created trees. The objective of this paper is to analyze the efficiency of the C4.5 algorithm to classify types of industrial accidents data and thereby identify potential weak points in disaster risk grouping.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.4
• /
• pp.413-420
• /
• 2019

The purpose of the present study is to develop a model for predicting hypercholesterolemia using an integrated set of body fat mass variables based on machine learning techniques, beyond the study of the association between body fat mass and hypercholesterolemia. For this study, a total of six models were created using two variable subset selection methods and machine learning algorithms based on the Korea National Health and Nutrition Examination Survey (KNHANES) data. Among the various body fat mass variables, we found that trunk fat mass was the best variable for predicting hypercholesterolemia. Furthermore, we obtained the area under the receiver operating characteristic curve value of 0.739 and the Matthews correlation coefficient value of 0.36 in the model using the correlation-based feature subset selection and naive Bayes algorithm. Our findings are expected to be used as important information in the field of disease prediction in large-scale screening and public health research.

• Journal of Digital Convergence
• /
• v.11 no.11
• /
• pp.343-349
• /
• 2013

Rough set theory comes to derive optimal rules through the effective selection of features from the redundancy of lots of information in data mining using the concept of equivalence relation and approximation space in rough set. The reduction of attributes is one of the most important parts in its applications of rough set. This paper purports to define a information-theoretic measure for determining the most important attribute within the association of attributes using rough entropy. The proposed method generates the effective reduct set and formulates the core of the attribute set through the elimination of the redundant attributes. Subsequently, the control rules are generated with a subset of feature which retain the accuracy of the original features through the reduction.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.11-21
• /
• 2020

Cardio-cerebrovascular diseases (CCD) account for 24% of the causes of death to Koreans and its proportion is the highest except cancer. Currently, the risk of the cardiovascular disease for domestic patients is based on the Framingham risk score (FRS), but accuracy tends to decrease because it is a foreign guideline. Also, it can't score the risk of cerebrovascular disease. CCD is hard to predict, because it is difficult to analyze the features of early symptoms for prevention. Therefore, proper prediction method for Koreans is needed. The purpose of this paper is validating IG-MLP (Information Gain - Multilayer Perceptron) evaluation based feature selection method using CCD data with simulation. The proposed method uses the raw data of the 4^th ~ 7^th of The Korea National Health and Nutrition Examination Survey (KNHANES). To select the important feature of CCD, analysis on the attributes using IG-MLP are processed, finally CCD prediction ANN model using optimize feature set is provided. Proposed method can find important features of CCD prediction of Koreans, and ANN model could predict more accurate CCD for Koreans.