Yung-Cheol Byun

Intrusion detection based on clustering a data stream

In anomaly intrusion detection, how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior as a profile, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes a new clustering algorithm, which continuously models a data stream. A set of features is used to represent the characteristics of an activity. For each feature, the clusters of feature values corresponding to activities observed so far in an audit data stream are identified by the proposed clustering algorithm for data streams. As a result, without maintaining any historical activity of a user physically, new activities of the user can be continuously reflected to the on-going result of clustering.

Improved Techniques for an Iris Recognition System with High Performance

We describe in this paper efficient techniques for iris recognition system with high performance from the practical point of view. These techniques range every step for an iris recognition system from the image acquisition step to the final step, the pattern matching, and contain as follows: a method of evaluating the quality of an image in the image acquisition step and excluding it from the subsequent processing if it is not appropriate, a bisection-based Hough transform method on the edge components for detecting the center of the pupil and localizing the iris area from an eye image, an elastic body model for transforming the localized iris area into a simple coordination system, and a compact and efficient feature extraction method which is based on 2D multiresolution wavelet transform. By exploiting these techniques, we can improve the system performance in terms of computationally efficient, and more accurate and robust against noises.

Iris Recognition System Using Wavelet Packet and Support Vector Machines

In this paper, iris recognition system using wavelet packet and support vector machines is presented. It specifically uses the multiresolution decomposition of 2-D discrete wavelet packet transform for extracting the unique features from the acquired iris image. This method of feature extraction is well suited to describe the shape of the iris while allowing the algorithm to be translation and rotation invariant. The SVM approach for comparing the similarity between the similar and different irises can be assessed to have the feature’s discriminative power. We have showed that the proposed method for human iris recognition gave a way of representing iris patterns in an efficient manner and thus had advantages of saving both time and space. Thanks to the efficiency of the proposed method, it can be easily applied to the real problems.

Retrieving and exploring ontology-based human motion sequences

A framework for semantic annotation of human motion sequences is proposed in this paper. Motion capture technology is widely used for manufacturing animation but it has a significant weakness due to the lack of an industry wide standard for archiving and retrieving motion capture data. It is difficult for animators to retrieve the desired motion sequences from motion capture files as there is no semantic annotation on already captured motion data. Our goal is to improve the reusability of motion capture data. To archive our goal first, we propose a standard format for integrating different motion capture file formats. Second, we define motion ontologies that are used to annotate and semantically organize human motion sequences. This ontology-based approach provides the means for discovering and exploiting the information and knowledge surrounding motion capture data.

Anomaly intrusion detection based on clustering a data stream

In anomaly intrusion detection, how to model the normal behavior of activities performed by a user is an important issue. To extract the normal behavior as a profile, conventional data mining techniques are widely applied to a finite audit data set. However, these approaches can only model the static behavior of a user in the audit data set. This drawback can be overcome by viewing the continuous activities of a user as an audit data stream. This paper proposes a new clustering algorithm which continuously models a data stream. A set of features is used to represent the characteristics of an activity. For each feature, the clusters of feature values corresponding to activities observed so far in an audit data stream are identified by the proposed clustering algorithm for data streams. As a result, without maintaining any historical activity of a user physically, new activities of the user can be continuously reflected to the on-going result of clustering.

An Efficient Form Classification Method Using Partial Matching

In this paper, we are proposing an efficient method of classifying form that is applicable in real life. Our method will identify a small number of local regions by their distinctive images with respect to their layout structure and then by using the DP (Dynamic Programming) matching to match only these local regions. The disparity score in each local region is defined and measured to select the matching regions. Genetic Algorithm will also be applied to select the best regions of matching from the viewpoint of a performance. Our approach of searching and matching only a small number of structurally distinctive local regions would reduce the processing time and yield a high rate of classification.

Mobile-Based Luminance Measurement for Night Scenes

Summary form only given. All living things adjust their behavior according to natural light. Humans invention of artificial light has done much to enhance our night-time environment [1]. The night-time illumination is really important including wonderful lightning in metro cities and warm lightening in rural areas. Especially, the beautiful illumination in a city makes the city to live and attract tourists from all of the countries. We can easily find New York, Hong Kong, and etc. as examples of such a city. However, if not properly controlled, obtrusive light (commonly referred to as light pollution) can present serious physiological and ecological problems [2]. Therefore, the effort to minimize obtrusive light is very important for safe night-time activity.

Performance evaluation of parallel systems employing roll-forward checkpoint schemes

High performance and reliability are the main goals of parallel and distributed computing systems. To increase the performance and reliability of the systems, various checkpoint schemes have been proposed in the literature for decades. However, the lack of general analytical models has been an obstacle to compare the performance of systems employing different checkpoint schemes. This paper develops an analytical model to evaluate the relative response time of systems employing checkpoint schemes. The model has been applied to evaluate the relative response time of systems employing RFC (Roll-Forward Checkpoint), DMR-F (Double Modular Redundancy for Forward recovery), and DST (Duplex with Self-Test) schemes. The result shows the feasibility of the model developed in the paper.

Knowledge-Based Partial Matching: An Efficient Form Classification Method

An efficient method of classifying form is proposed in this paper. Our method identifies a small number of matching areas by their distinctive images with respect to their layout structure and then form classification is performed by matching only these local regions. The process is summarized as follows. First, the form is partitioned into rectangular regions along the locations of lines of the forms. The disparity in each partitioned region of the comparing form images is measured. The penalty for each partitioned area is computed by using the preprinted text, filled-in data, and the size of a partitioned area. The disparity and penalty are considered to compute the score to select final matching areas. By using our approach, the redundant matching areas are not processed and a feature vector of good quality can be extracted.

A Model of Unconstrained Digit Recognition Based on Hypothesis Testing and Data Reconstruction

We propose a model for the recognition of unconstrained digits that may be touched with neighbor ones or damaged by noises such as lines. The recognition of such digits seems to be rather paradoxical because it requires the segmentation of them into understandable units, but proper segmentation needs a priori knowledge of the units and this implies recognition capability. To break up the loop of their interdependencies, we combine two schemes, hypothesis testing and data reconstruction, motivated by the human information system. Hypothesis is set up on the basis of the information obtained from the results of the basic segmentation, and reconstruction of the information is carried out with the knowledge of a guessed digit and then testing for its validity is performed. Since our model tries to construct a guessed digit from input image it can be successful in a variety of situations such as that a digit contains strokes that do not belong to to it, that neighbor digits are touched with each other, and that there are some occluding things like lines. The recognition results of this model for 100 handwritten numeral strings belonging to NIST database and for some artificial digits damaged by line demonstrate the potential its capacity.