• 인터넷정보학회논문지
• /
• 제4권2호
• /
• pp.69-80
• /
• 2003

프로그램 행위 침입 탐지 기법은 데몬 프로그램이나 루트 권한으로 실행되는 프로그램이 발생시키는 시스템 호출들을 분석하고 프로파일을 구축하여 변형된 공격을 효과적으로 탐지한다. 본 논문에서는 베이지안 네트워크와 다중 서열 정렬을 이용하여 여러 프로세스의 시스템 호출간의 관계를 표현하고, 프로그램 행위를 모델링하여 변형된 이상 침입 행위를 분류함으로써 이상행위를 탐지한다. 제안한 기법을 UNM 데이터를 이용한 시뮬레이션을 수행하였다.

• BMB Reports
• /
• 제40권2호
• /
• pp.135-141
• /
• 2007

Conjugation of the methyl group at the fifth carbon of cytosines within the palindromic dinucleotide 5'-CpG-3' sequence (DNA methylation) is the best studied epigenetic mechanism, which acts together with other epigenetic entities: histone modification, chromatin remodeling and microRNAs to shape the chromatin structure of DNA according to its functional state. The cancer genome is frequently characterized by hypermethylation of specific genes concurrently with an overall decrease in the level of 5-methyl cytosine, the pathological implication of which to the cancerous state has been well established. While the latest genome-wide technologies have been applied to classify and interpret the epigenetic layer of gene regulation in the physiological and disease states, the epigenetic testing has also been seriously explored in clinical practice for early detection, refining tumor staging and predicting disease recurrence. This critique reviews the latest research findings on the use of DNA methylation in cancer diagnosis, prognosis and staging/classification.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.812-815
• /
• 2006

Proteins are essential agents for controlling, effecting and modulating cellular functions, and proteins with similar sequences have diverged from a common ancestral gene, and have similar structures and functions. Function prediction of unknown proteins remains one of the most challenging problems in bioinformatics. Recently, various computational approaches have been developed for identification of short sequences that are conserved within a family of closely related protein sequence. Protein function is often correlated with highly conserved motifs. Motif is the smallest unit of protein structure and function, and intends to make core part among protein structural and functional components. Therefore, prediction methods using data mining or machine learning have been developed. In this paper, we describe an approach for protein function prediction of motif-based models using data mining. Our work consists of three phrases. We make training and test data set and construct classifier using a training set. Also, through experiments, we evaluate our classifier with other classifiers in point of the accuracy of resulting classification.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.271-274
• /
• 1997

This paper presents an adaptive quantization of image sequences using the Radial Basis Function Network(RBFN) which classifies interframe image blocks. The clssification algorithm consists of two steps. Blocks are classified into NA(No Activity), SA(Small Activity), VA(Verical Activity), and HA(Horizontal Activity) classes according to edges, image activity and AC anergy distribution. RBFN is trained using the classification results of the above algorithm, which are nonlinear classification features are acquired from the complexity and variability of difference blocks. Simulation result shows that the the adaptive quantization using the RBFN method produced better results better results than that of the sorting and MLP methods.

• Genomics & Informatics
• /
• 제1권2호
• /
• pp.80-86
• /
• 2003

Human Papillomavirus (HPV) infection is known as the main factor for cervical cancer which is a leading cause of cancer deaths in women worldwide. Because there are more than 100 types in HPV, it is critical to discriminate the HPVs related with cervical cancer from those not related with it. In this paper, the risk type of HPVs using their textual explanation. The important issue in this problem is to distinguish false negatives from false positives. That is, we must find high-risk HPVs as many as possible though we may miss some low-risk HPVs. For this purpose, the AdaCost, a cost-sensitive learner is adopted to consider different costs between training examples. The experimental results on the HPV sequence database show that the consideration of costs gives higher performance. The improvement in F-score is higher than that of the accuracy, which implies that the number of high-risk HPVs found is increased.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2008년도 춘계학술대회 논문집
• /
• pp.277-280
• /
• 2008

In this work, the development of the diagnosis algorithm is carried out for identifying health and faulted conditions in three-phase induction motors. The algorithm consists of feature calculation, feature extraction, and feature classification procedures in sequence. Signals for this algorithm are acquired by current and flux sensors simultaneously, the latter is to measure the change of magnetic flux at the air-gap, This work proposes the efficient diagnosis method for induction motors by developing the powerful algorithm. The calculated features show a good linearity according to faults severities. Moreover. the final results show a good classification rate on motor conditions.

• International Journal of Contents
• /
• 제8권4호
• /
• pp.56-63
• /
• 2012

In recent decades, analyzing the activities of human brain achieved some accomplishments by using the functional Magnetic Resonance Imaging (fMRI) technique. fMRI data provide a sequence of three-dimensional images related to human brain's activity which can be used to detect instantaneous cognitive states by applying machine learning methods. In this paper, we propose a new approach for distinguishing human's cognitive states such as "observing a picture" versus "reading a sentence" and "reading an affirmative sentence" versus "reading a negative sentence". Since fMRI data are high dimensional (about 100,000 features in each sample), extremely sparse and noisy, feature selection is a very important step for increasing classification accuracy and reducing processing time. We used the Fisher Discriminant Ratio to select the most powerful discriminative features from some Regions of Interest (ROIs). The experimental results showed that our approach achieved the best performance compared to other feature extraction methods with the average accuracy approximately 95.83% for the first study and 99.5% for the second study.

• 한국동물위생학회지
• /
• 제28권1호
• /
• pp.49-69
• /
• 2005

More than 30 years have elapsed since the first report of the International Committee on Taxonomy of Viruses (ICTV) was published in 1971. Since that publication, the ICTV recognizes about 1,550 virus species, but some 30,000 virus strains and isolates are being tracked by virologists in different fields of biology. The ICTV is the 'international court' of experts that rules on names and relationships of all virus, but only to the level of species. Virus taxonomy is changing rapidly, with changes ranging from the trivial(use of italics for species names) to profound reorganization driven by the explosion of sequence information. The universal system of viral taxonomy now accepts Linnean-like classification at the levels of order, family, subfamily, genus, and species. The suffix '-virales' identifies an order, Families are identified by the suffix '-viridae' subfamilies are identified by the suffix '-virinae', and genera are identified by the suffix '-virus'. The importance of distinguishing subspecies, strains, and isolates in vaccine development, diagnostics, etc. is recognized, but these lower levels are not formally classified by ICTV. This paper mainly introduces taxonomy and classification of animal viruses on the basis of the seventh report of the ICTV edited by Van Regenmortal et al. in 2000.

• Journal of Electrical Engineering and Technology
• /
• 제12권6호
• /
• pp.2106-2117
• /
• 2017

An effective statistical feature extraction approach of data sampling of fault in the combined transmission system is presented in this paper. The proposed algorithm leads to high accuracy at minimum cost to predict fault location and fault type classification. This algorithm requires impedance measurement data from one end of the transmission line. Modal decomposition is used to extract positive sequence impedance. Then, the fault signal is decomposed by using discrete wavelet transform. Statistical sampling is used to extract appropriate fault features as benchmark of decomposed signal to train classifier. Support Vector Machine (SVM) is used to illustrate the performance of statistical sampling performance. The overall time of sampling is not exceeding 1 1/4 cycles, taking into account the interval time. The proposed method takes two steps of sampling. The first step takes 3/4 cycle of during-fault and the second step takes 1/4 cycle of post fault impedance. The interval time between the two steps is assumed to be 1/4 cycle. Extensive studies using MATLAB software show accurate fault location estimation and fault type classification of the proposed method. The classifier result is presented and compared with well-established travelling wave methods and the performance of the algorithms are analyzed and discussed.

• 정보과학회 논문지
• /
• 제44권8호
• /
• pp.842-853
• /
• 2017

스트리밍 데이터는 시간에 따라 지속적으로 생성되는 데이터 시퀀스이다. 시간이 지남에 따라 데이터의 분포 또는 컨셉이 변화할 수 있으며, 이러한 변화는 분류 모델의 성능을 저하시키는 요인이 된다. 점층적 적응적 학습 방법은 컨셉 변화의 정도에 따라 현재 분류 모델의 가중치를 조절하여 업데이트를 수행함으로써 컨셉 변화에 대한 분류 모델의 성능을 유지할 수 있게 한다. 그러나, 컨셉 변화의 정도에 맞는 적절한 가중치를 결정하기가 어렵다는 문제점이 있다. 본 논문에서는 컨셉 변화에 따른 적응적 가중치 조정에 기반한 동적 앙상블 방법을 제안한다. 실험 결과는 제안한 방법이 다른 비교 방법들에 비해 높은 성능을 보여줌을 입증한다.