• Journal of IKEEE
• /
• v.13 no.2
• /
• pp.140-149
• /
• 2009

Traffic anomaly detection is one of important technology that should be considered in network security and administration. In this paper, we propose an abnormal traffic detection mechanism that includes traffic monitoring and traffic analysis. We develop analytical passive monitoring system called WISE-Mon which can inspect traffic behavior. We establish a criterion by analyzing the characteristics of a traffic training set. To detect abnormal traffic, we derive a hyperplane by using Fisher linear discriminant and chi-square distribution as well as the analyzed characteristics of traffic. Our mechanism can support reliable results for traffic anomaly detection and is compatible to real-time detection. In addition, since the trend of traffic can be changed as time passes, the hyperplane has to be updated periodically to reflect the changes. Accordingly, we consider the self-learning algorithm which reflects the trend of the traffic and so enables to increase the pliability of detection probability. Numerical results are presented to validate the accuracy of proposed mechanism. It shows that the proposed mechanism is reliable and relevant for traffic anomaly detection.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.2
• /
• pp.161-165
• /
• 2014

In this paper, we proposed the fuzzy prototype pattern classifier. In the proposed classifier, each prototype is defined to describe the related sub-space and the weight value is assigned to the prototype. The weight value assigned to the prototype leads to the change of the boundary surface. In order to define the prototypes, we use Fuzzy C-Means Clustering which is the one of fuzzy clustering methods. In order to optimize the weight values assigned to the prototypes, we use the Differential Evolutionary Algorithm. We use Linear Discriminant Analysis to estimate the coefficients of the polynomial which is the structure of the consequent part of a fuzzy rule. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.117-123
• /
• 2023

To detect advanced ransomware attacks with machine learning-based models, the classification model must train learning data with high-dimensional feature space. And in this case, a 'curse of dimension' phenomenon is likely to occur. Therefore, dimensionality reduction of features must be preceded in order to increase the accuracy of the learning model and improve the execution speed while avoiding the 'curse of dimension' phenomenon. In this paper, we conducted classification of ransomware by applying three machine learning models and two feature extraction techniques to two datasets with extremely different dimensions of feature space. As a result of the experiment, the feature dimensionality reduction techniques did not significantly affect the performance improvement in binary classification, and it was the same even when the dimension of featurespace was small in multi-class clasification. However, when the dataset had high-dimensional feature space, LDA(Linear Discriminant Analysis) showed quite excellent performance.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.6
• /
• pp.662-667
• /
• 2022

Computing music similarity is an indispensable component in developing music search service. This paper focuses on learning a music similarity function in order to boost cover song identification performance. By using the probabilistic linear discriminant analysis, we construct a latent music space where the distances between cover song pairs reduces while the distances between the non-cover song pairs increases. We derive a music similarity function by testing hypothesis, whether two songs share the same latent variable or not, using the probabilistic models with the assumption that observed music features are generated from the learned latent music space. Experimental results performed on two cover music datasets show that the proposed music similarity improves the cover song identification performance.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.18 no.6
• /
• pp.1938-1944
• /
• 2004

In this study, when we make a diagnosis of constitution using QSCC Ⅱ(Questionnaire of Sasang Constitution Classification). data mining techniques are applied to seek the classification function for improving the accuracy. Data used in the analysis are the questionnaires of 1051 patients who had been treated in Dong Eui Oriental Medical Hospital and Kyung Hee Oriental Medical Hospital. The criteria for data cleansing are the response pattern in the opposite questionnaires and the positive proportion of specific questionnaires in each constitution. And the criteria for variable selection are the test of homogeneity in frequency analysis and the coefficients in the linear discriminant function. Discriminant analysis model and decision tree model are applied to seek the classification function into Sasang constitution. The accuracy in learning sample is similar in two models, the higher accuracy in test sample is obtained in discriminant analysis model.

• International Journal of Human Ecology
• /
• v.16 no.2
• /
• pp.21-31
• /
• 2015

This study explored determinants of family support that young renter households received to afford their housing costs. Microdata set of the 2014 Korea Housing Survey was used as secondary data for the study. Total 1,752,899 households headed by persons between 20 and 34 years of age and whose rental type was either Jeon-se or monthly rental with deposit in private rental units were selected as study subjects. For the data analysis, a series of discriminant analysis was conducted using IBM SPSS 21.0. Major findings were as follows. (1) Among the subjects, 28.2% were found to receive financial support from parents or other relatives. (2) To see the discriminant analysis results, a linear combination of seven household and housing characteristics (householder's gender, whether or not the householder worked in the previous week, whether or not the householders have a spouse, tenure type, structure type, location and deposit amount) could explain 44.6% of variance in young renter households' receipt of family support with a prediction accuracy of 77.2%. (3) To summarize the final discriminant model, Jeon-se renter households in location other than Incheon or Gyeonggi Province living in a unit in structure other than multifamily structure headed by younger householders that did not worked previous week or without spouse; with a greater deposit had the maximum tendency to receive family support to pay rental costs.

• Journal of the Korean Institute of Educational Facilities
• /
• v.4 no.4
• /
• pp.29-41
• /
• 1997

The objective of this paper is to construct a model to be used in deciding whether to repair or rebuild school buildings is depending on their ages and other factors. The theme of this paper is the age is the main variable but other factors such as floor, innerwall, ceiling, door, inner window of the class room, outer window of the class room, inner window of the corridor, outer window of the corridor, middle window between the classroom and the corridor, light, heater, speaker, fire protection sensor, TV monitor, and telephone status would influence the final decisions. This paper employs an experimental case study method. Using the stepwise, statistical, classification method commonly used in discriminant analysis, it evaluates 12,766 rooms of 87 different high schools in Seoul. The result of this study indicates that some critical variables influencing the final decisions are the status of TV monitor, middle window between the classroom and the corridor, light, inner window of the corridor, fire protection sensor, innerwall, speaker utensil, outer window of the class room, and door of the class room. This paper also suggests a linear discriminant function will be used for this kind of studies. Finally the paper recommends policies with respect to the variables and discriminant functions evaluated.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.2 s.308
• /
• pp.82-86
• /
• 2006

The design of a pattern recognition system generally involves the three aspects: preprocessing, feature extraction, and decision making. Among them, a feature extraction method determines an appropriate subspace of dimensionality in the original feature space of dimensionality so that it can reduce the complexity of the system and help to improve successful recognition rates. Linear transforms, such as principal component analysis, factor analysis, and linear discriminant analysis have been widely used in pattern recognition for feature extraction. This paper shows that singular value decomposition (SVD) can be applied usefully in feature extraction stage of pattern recognition. As an application, a remote sensing problem is applied to verify the usefulness of SVD. The experimental result indicates that the feature extraction using SVD can improve the recognition rate about 25% compared with that of PCA.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.101-108
• /
• 2010

In this paper, we proposed a new lazy classifier with fuzzy k-nearest neighbors approach and feature selection which is based on reconstruction error. Reconstruction error is the performance index for locally linear reconstruction. When a new query point is given, fuzzy k-nearest neighbors approach defines the local area where the local classifier is available and assigns the weighting values to the data patterns which are involved within the local area. After defining the local area and assigning the weighting value, the feature selection is carried out to reduce the dimension of the feature space. When some features are selected in terms of the reconstruction error, the local classifier which is a sort of polynomial is developed using weighted least square estimation. In addition, the experimental application covers a comparative analysis including several previously commonly encountered methods such as standard neural networks, support vector machine, linear discriminant analysis, and C4.5 trees.

• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2853-2864
• /
• 2018

Discriminant analysis predicts a class label of a new observation with an unknown label, using information from the existing labeled data. Hence, observed labels play a critical role in the analysis and we usually assume that these labels are correct. If the observed label contains an error, the data has label noise. Label noise can frequently occur in real data, which would affect classification performance. In order to resolve this, a comparative study was carried out using simulated data with label noise. In particular, we considered 4 different classification techniques such as LDA (linear discriminant analysis classifiers), QDA (quadratic discriminant analysis classifiers), KNN (k-nearest neighbour), and SVM (support vector machine). Then we evaluated each method via average accuracy using generated data from various scenarios. The effect of label noise was investigated through its occurrence rate and type (noise location). We confirmed that the label noise is a significant factor influencing the classification performance.