• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.27-35
• /
• 2021

With the development of the Internet, various IT technologies such as IoT, Cloud, etc. have been developed, and various systems have been built in countries and companies. Because these systems generate and share vast amounts of data, they needed a variety of systems that could detect threats to protect the critical data contained in the system, which has been actively studied to date. Typical techniques include anomaly detection and misuse detection, and these techniques detect threats that are known or exhibit behavior different from normal. However, as IT technology advances, so do technologies that threaten systems, and these methods of detection. Advanced Persistent Threat (APT) attacks national or companies systems to steal important information and perform attacks such as system down. These threats apply previously unknown malware and attack technologies. Therefore, in this paper, we propose a hybrid intrusion detection system that combines anomaly detection and misuse detection to detect unknown threats. Two detection techniques have been applied to enable the detection of known and unknown threats, and by applying machine learning, more accurate threat detection is possible. In misuse detection, we applied Classification based on Association Rule(CBA) to generate rules for known threats, and in anomaly detection, we used One-Class SVM(OCSVM) to detect unknown threats. Experiments show that unknown threat detection accuracy is about 94%, and we confirm that unknown threats can be detected.

• Journal of the Korean Society for information Management
• /
• v.33 no.2
• /
• pp.33-59
• /
• 2016

This study examined the factors affecting the performance of automatic classification for the domestic conference papers based on machine learning techniques. In particular, In view of the classification performance that assigning automatically the class labels to the papers in Proceedings of the Conference of Korean Society for Information Management using Rocchio algorithm, I investigated the characteristics of the key factors (classifier formation methods, training set size, weighting schemes, label assigning methods) through the diversified experiments. Consequently, It is more effective that apply proper parameters (${\beta}$, ${\lambda}$) and training set size (more than 5 years) according to the classification environments and properties of the document set. and If the performance is equivalent, I discovered that the use of the more simple methods (single weighting schemes) is very efficient. Also, because the classification of domestic papers is corresponding with multi-label classification which assigning more than one label to an article, it is necessary to develop the optimum classification model based on the characteristics of the key factors in consideration of this environment.

• Journal of KIISE:Software and Applications
• /
• v.32 no.8
• /
• pp.781-788
• /
• 2005

LDA (Linear Discriminant Analysis) is a data discrimination technique that seeks transformation to maximize the ratio of the between-class scatter and the within-class scatter While it has been successfully applied to several applications, it has two limitations, both concerning the underfitting problem. First, it fails to discriminate data with complex distributions since all data in each class are assumed to be distributed in the Gaussian manner; and second, it can lose class-wise information, since it produces only one transformation over the entire range of classes. We propose three extensions of LDA to overcome the above problems. The first extension overcomes the first problem by modeling the within-class scatter using a PCA mixture model that can represent more complex distribution. The second extension overcomes the second problem by taking different transformation for each class in order to provide class-wise features. The third extension combines these two modifications by representing each class in terms of the PCA mixture model and taking different transformation for each mixture component. It is shown that all our proposed extensions of LDA outperform LDA concerning classification errors for handwritten digit recognition and alphabet recognition.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.113-119
• /
• 2007

This article deals mainly with two objectives viz, 1) the potentiality of very high-resolution(VHR) multi-spectral and pan chromatic QuickBird satellite data in resources mapping over moderate resolution satellite data (IRS LISS III) and 2) the advantages of using object oriented classification method of eCognition software in land use and land cover analysis over the ISODATA classification method. These VHR data offers widely acceptable metric characteristics for cartographic updating and increase our ability to map land use in geometric detail and improve accuracy of local scale investigations. This study has been carried out in the Sukkalampatti mini-watershed, which is situated in the Eastern Ghats of Tamil Nadu, India. The eCognition object oriented classification method succeeded in most cases to achieve a high percentage of right land cover class assignment and it showed better results than the ISODATA pixel based one, as far as the discrimination of land cover classes and boundary depiction is concerned.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1167-1175
• /
• 2018

Microarray data plays an essential role in diagnosing and detecting cancer. Microarray analysis allows the examination of levels of gene expression in specific cell samples, where thousands of genes can be analyzed simultaneously. However, microarray data have very little sample data and high data dimensionality. Therefore, to classify microarray data, a dimensional reduction process is required. Dimensional reduction can eliminate redundancy of data; thus, features used in classification are features that only have a high correlation with their class. There are two types of dimensional reduction, namely feature selection and feature extraction. In this paper, we used k-means algorithm as the clustering approach for feature selection. The proposed approach can be used to categorize features that have the same characteristics in one cluster, so that redundancy in microarray data is removed. The result of clustering is ranked using the Relief algorithm such that the best scoring element for each cluster is obtained. All best elements of each cluster are selected and used as features in the classification process. Next, the Random Forest algorithm is used. Based on the simulation, the accuracy of the proposed approach for each dataset, namely Colon, Lung Cancer, and Prostate Tumor, achieved 85.87%, 98.9%, and 89% accuracy, respectively. The accuracy of the proposed approach is therefore higher than the approach using Random Forest without clustering.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.1-7
• /
• 2003

Internal defects such as browning of the flesh and blackening and rot of the ovary of pear can be easily developed because of the inadequate environmental conditions during the storage and distribution of fruit. The quality assurance system for the agricultural product is to be settled in Korea. All defected agricultural products should be excluded prior to the distribution to enhance the commercial values. However, early stage on-line defect detection of agricultural product is very difficult and even more difficult in a case of the internal defects. The goal of this research is to develop a system that can detect and classify internal defects of agricultural produce on-line using VIS/NIR transmittance spectroscopy. And Shingo pear, which is one of the famous species of Korean pear, was used for the experiment. Soft independence modeling of class analogy (SIMCA) algorithm was employed to analyze the transmittance spectroscopic data qualitatively. On-line classification system was constructed and classification model was developed and validated. As a result, the correct classification rate (CCR) using the developed classification model was 96.1 ％.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.628-631
• /
• 1988

This paper describes a fingerprint classification on the basis of feature points(whorl, core) and feature vector and uses a syntactic approach to identify the shape of flow line around the core. Fingerprint image is divided into 8 by 8 subregions and fingerprint region is separated from background. For each subregion of fingerprint region, the dominant ridge direction is obtained to use the slit window quantized in 8 direction and relaxation is performed to correct ridge direction code. Feature points(whorl, core, delta) are found from the ridge direction code. First classification procedure divides the types of fingerprint into 4 class based on whorl and cores. The shape of flow line around the core is obtained by tracing for the fingerprint which has one core or two core and is represented as string. If the string is acceptable by LR(1) parser, feature vector is obtained from feature points(whorl, core, delta) and the shape of flow line around the core. Feature vector is used hierarchically and linearly to classify fingerprint again. The experiment resulted in 97.3 percentages of sucessful classification for 71 fingerprint impressions.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.4
• /
• pp.332-339
• /
• 2014

Face classification has wide applications in security and surveillance. However, this technique presents various challenges caused by pose, illumination, and expression changes. Face recognition with long-distance images involves additional challenges, owing to focusing problems and motion blurring. Multiple frames under varying spatial or temporal settings can acquire additional information, which can be used to achieve improved classification performance. This study investigates the effectiveness of multi-frame decision-level fusion with photon-counting linear discriminant analysis. Multiple frames generate multiple scores for each class. The fusion process comprises three stages: score normalization, score validation, and score combination. Candidate scores are selected during the score validation process, after the scores are normalized. The score validation process removes bad scores that can degrade the final output. The selected candidate scores are combined using one of the following fusion rules: maximum, averaging, and majority voting. Degraded facial images are employed to demonstrate the robustness of multi-frame decision-level fusion in harsh environments. Out-of-focus and motion blurring point-spread functions are applied to the test images, to simulate long-distance acquisition. Experimental results with three facial data sets indicate the efficiency of the proposed decision-level fusion scheme.

• Journal of Korean Society for Atmospheric Environment
• /
• v.9 no.3
• /
• pp.207-215
• /
• 1993

In order to statistically predict $O_3$ levels in Seoul, the study used the TMS (telemeted air monitoring system) data from the Department of Environment, which have monitored at 20 sites in 1989 and 1990. Each data in each site was characterized by 6 major criteria pollutants ($SO_2, TSP, CO, NO_2, THC, and O_3$) and 2 meteorological parameters, such as wind speed and wind direction. To select proper variables and to determine each pollutant's behavior, univariate statistical analyses were extensively studied in the beginning, and then various applied statistical techniques like cluster analysis, regression analysis, and expert system have been intensively examined. For the initial study of high level $O_3$ prediction, the raw data set in each site was separated into 2 group based on 60 ppb $O_3$ level. A hierarchical cluster analysis was applied to classify the group based on 60 ppb $O_3$ into small calsses. Each class in each site has its own pattern. Next, multiple regression for each class was repeatedly applied to determine an $O_3$ prediction submodel and to determine outliers in each class based on a certain level of standardized redisual. Thus, a prediction submodel for each homogeneous class could be obtained. The study was extended to model $O_3$ prediction for both on-time basis and 1-hr after basis. Finally, an expect system was used to build a unified classification rule based on examples of the homogenous classes for all of sites. Thus, a concept of high level $O_3$ prediction model was developed for one of $O_3$ alert systems.

• The korean journal of orthodontics
• /
• v.21 no.1 s.33
• /
• pp.171-183
• /
• 1991

This investigation was designed to categorize Angle's class II malocclusion groups through analyzing horizontal and vertical components of craniofacial skeleton in Angle's class II malocclusion. The material selected for this study consisted in standard lateral cephalogram of two hundred and twenteen children, eighty eight boys and one hundred twenty four girls, aged 6 through 18 years, having Angle's class II malocclusion. On the basis of findings of this study, the following results were obtained. 1. In horizontal skeletal classifications, 16 groups were classified according to FMN-A-B, SE-FMN-A, Ba-SE-Me, Ba-Se/Ra P. The sequences that have relatively high frequency are as follows: a) Horizontal Group 16 b) Horizontal Group 12 c) Horizontal Group 13 d) Horizontal Group 9 & 15 2. In vertical skeletal classification, 8 groups were classified according to the PMV/PP, PMV/Occ. P. PMV/Mn. P. The sequences that relatively high frequency are as follows; a) Vertical Group A b) Vertical Group D c) Vertical Group C d) Vertical Group H 3. In vertical and horizontal skeletal classifications, the sequence that relatively high frequency are as follows; a) Group13-A b) Group16-A & 9-A c) Group12-A & 15-A d) Group16-C