• 한국컴퓨터정보학회논문지
• /
• 제14권10호
• /
• pp.159-166
• /
• 2009

자연면역 시스템은 여러 신체 부위에서 다양한 기능으로 외부침입에 민감하게 대응할 뿐만 아니라 기존에 감염된 정보를 기억하는 기능을 수행한다. 그러나 자연 면역 시스템의 원리를 적용한 컴퓨터 보안 시스템에서는 자연면역 시스템이 갖는 기능을 충분히 제공하지 못하는 문제점이 있다. 이 논문에서는 자연면역 시스템의 네거티브 셀렉션을 적용한 항체와 임의의 비정상 시스템 콜 시퀀스를 선택하여 유전자 알고리즘을 적용한 항체를 결합하여 자연면역 시스템과 유사한 기능을 제공하는 하이브리드 모델을 제안한다. 제안된 모델은 긍정적 결함과 부정적 결함을 줄이기 위해 임의의 비정상 시스템 콜 시퀀스를 이용한다. 실험에 사용된 데이터는 UNM(University of New Maxico)에서 제공된 샌드메일 데이터이며 실험 결과 제안 모델은 기존 네거티브 셀렉션보다 비정상 시스템 콜을 정상 시스템 콜로 판정하는 부정적 결함이 평균 0.55% 낮게 나타났다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.185-188
• /
• 2001

According as many people use a computer newly, damage of computer virus and hacking is rapidly increasing by the crucial users. To block hacking that is intrusion of a person's computer and the computer virus that destroys data, a study for intrusion-detection of system and virus detection using a biological immune system is in progress. In this paper, we make a model of positive selection and negative selection of self-recognition process that is ability of T-cytotoxic cell that plays an important part in biological immune system. So we embody a self-nonself distinction algorithm in computer. To prove the efficacy of self-recognition algorithm, we use simulations by a cell change and a string change of self file.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.211-216
• /
• 2006

The Constrained Linear Spectral Unmixing(CLSU) is investigated for sub-pixel image processing, Its result is the abundance map which mean fractions of endmember existing in a mixed pixel. Compared to the Linear Spectral Unmixing using least square method, CLSU uses the NNLS (Non-Negative Least Square) algorithm to guarantee that the estimated fractions are constrained. But, CLSU gets Into difficulty in image processing due to select endmember at a user's disposition. In this study, endmember selection optimization method using entropy in the error-image analysis is proposed. In experiments which is used hyperion image, it is shown that our method can select endmember number than CLSU based on unsupervised endemeber selection.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 춘계 학술대회 학술발표 논문집
• /
• pp.229-232
• /
• 2003

나날이 발전하는 인터넷 기반의 네트워크 환경에서 보안의 중요성은 아무리 강조해도 지나치지 않다. 바이러스와 해킹 기술의 발전 속도는 항상 방어자의 능력을 앞지르고 있으며, 공격자들의 능력과 무관한 해킹 툴의 보급은 누구나가 해커가 될 수 있도록 하는데 일조하고 있다. 이제 더 이상 해킹과 바이러스로부터 안전지대는 없다고 해도 과언이 아니다. 이에 본 논문에서는 일정한 환경에서의 침입에 대해 학습을 하여 그 침입을 탐지할 수 있는 디텍터를 생성할 수 있는 알고리즘을 제안한다. 공격 유형의 수에 비해 적은, 그러나 인공 면역계의 T 세포 형성과정인 부정선택을 이용한 학습알고리즘을 기반으로 생성된 디텍터들은 상대적으로 다양한 공격의 침입을 탐지한다. 이의 유효성을 시뮬레이션을 이용하여 확인한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권6호
• /
• pp.2996-3011
• /
• 2017

With rapid growth of web technology and dissemination of smart devices, social networking service(SNS) is widely used. As a result, huge amount of data are generated from SNS such as Twitter, and sentiment analysis of SNS data is very important for various applications and services. In the existing sentiment analysis based on the $Na{\ddot{i}}ve$ Bayes algorithm, a same number of attributes is usually employed to estimate the weight of each class. Moreover, uncountable and meaningless attributes are included. This results in decreased accuracy of sentiment analysis. In this paper two methods are proposed to resolve these issues, which reflect the difference of the number of positive words and negative words in calculating the weights, and eliminate insignificant words in the feature selection step using Multinomial $Na{\ddot{i}}ve$ Bayes(MNB) algorithm. Performance comparison demonstrates that the proposed scheme significantly increases the accuracy compared to the existing Multivariate Bernoulli $Na{\ddot{i}}ve$ Bayes(BNB) algorithm and MNB scheme.

• International Journal of Contents
• /
• 제3권1호
• /
• pp.1-8
• /
• 2007

The distributions of the minimum correlated F-variable arises in many applied statistical problems including simultaneous analysis of variance (SANOVA), equality of variance, selection and ranking populations, and reliability analysis. In this paper, negative binomial sampling technique is employed to derive the distributions of the minimum of chi-square variables and hence the distributions of the minimum correlated F-variables. The work presented in this paper is divided in two parts. The first part is devoted to develop some combinatorial identities arised from the negative binomial sampling. These identities are constructed and justified to serve important purpose, when we deal with these distributions or their characteristics. Other important results including cumulants and moments of these distributions are also given in somewhat simple forms. Second, the distributions of minimum, chisquare variable and hence the distribution of the minimum correlated F-variables are then derived within the negative binomial sampling framework. Although, multinomial theory applied to order statistics and standard transformation techniques can be used to derive these distributions, the negative binomial sampling approach provides more information regarding the nature of the relationship between the sampling vehicle and the probability distributions of these functions of chi-square variables. We also provide an algorithm to compute the percentage points of the distributions. The computation methods we adopted are exact and no interpolations are involved.

• The Plant Pathology Journal
• /
• 제30권2호
• /
• pp.195-199
• /
• 2014

Apple stem pitting virus (ASPV), of the Foveavirus genus in the family Betaflexiviridae, is one of the most common viruses of apple and pear trees. To examine variability of the coat protein (CP) gene from ASPV, eight isolates originating from 251 apple trees, which were collected from 22 apple orchards located in intensive apple growing areas of the North Gyeongsang and North Jeolla Provinces in Korea, were sequenced and compared. The nucleotide sequence identity of the CP gene of eight ASPV isolates ranged from 77.0 to 97.0%, while the amino acid sequence identity ranged from 87.7 to 98.5%. The N-terminal region of the viral CP gene was highly variable, whereas the C-terminal region was conserved. Genetic algorithm recombination detection (GARD) and single breakpoint recombination (SBP) analyses identified base substitutions between eight ASPV isolates at positions 54 and 57 and position 771, respectively. GABranch analysis was used to determine whether the eight isolates evolved due to positive selection. All values in the GABranch analysis showed a ratio of substitution rates at non-synonymous and synonymous sites (dNS/dS) below 1, suggestive of strong negative selection forces during ASPV CP history. Although negative selection dominated CP evolution in the eight ASPV isolates, SLAC and FEL tests identified four possible positive selection sites at codons 10, 22, 102, and 158. This is the first study of the ASPV genome in Korea.

• 대한의용생체공학회:의공학회지
• /
• 제39권2호
• /
• pp.69-79
• /
• 2018

The present study proposes an algorithm that can discriminate between normal subjects and paroxysmal atrial fibrillation (PAF) patients, which is conducted using electrocardiogram (ECG) without PAF events. For this, time-domain features and random forest classifier are used. Time-domain features are obtained from Poincare plot, Lorenz plot of ${\delta}RR$ interval, and morphology analysis. Afterward, three features are selected in total through feature selection. PAF patients and normal subjects are classified using random forest. The classification result showed that sensitivity and specificity were 81.82% and 95.24% respectively, the positive predictive value and negative predictive value were 96.43% and 76.92% respectively, and accuracy was 87.04%. The proposed algorithm had an advantage in terms of the computation requirement compared to existing algorithm, so it has suggested applicability in the more efficient prediction of PAF.

• 한국지능시스템학회논문지
• /
• 제11권9호
• /
• pp.801-806
• /
• 2001

최근 컴퓨터의 사용이 보편화되면서 악의적 사용자에 의해 발생하는 컴퓨터 바이러스와 해킹에 의한 피해가 급속히 증가하고 있다. 남의 컴퓨터에 침입하는 해킹이나 데이터를 파괴하는 컴퓨터 바이러스에 의한 피해를 막기 위해 최근에 생명체의 면역시스템의 특징을 이용해 인공면역계를 구성해 시스템 침입탐지와 바이러스 탐지 및 치료에 대한 연구가 활발히 진행 중에 있다. 생체 면역계는 외부에서 침입해 세포나 장기에 피해를 주는 물질인 항원을 스스로 자기세포와 구분해 인식, 제거하는 기능이 있다. 이러한 면역계의 특징인 항원을 인식하는 기능은 자기세포의 확실한 인식을 가지고 있는 상태에서 다른 물질을 구분하는 자기/비자기(self/non-self) 인식방법으로 볼 수 있다. 본 논문에서는 생체 면역계에서 세포독성 T세포의 생성과정의 하나인 Positive Selection을 모델링하여 침입에 의한 데이터 변경과 바이러스에 의한 데이터 감염 등을 탐지할 때 가장 중요한 요소인 자기-인식 알고리즘을 구현하였다. 제안한 알고리즘은 큰 파일에서의 Detection을 구성하기 용이한 점을 가지며 극소변경과 블록변경에 대한 자기인식률을 통해 알고리즘을 유효성을 검증한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.115.1-115
• /
• 2001

According as many people use a computer newly, damage of computer virus and hacking is rapidly increasing by the crucial users. A computer virus is one of program on computer and has abilities of self reproduction and destruction like a virus of biology. And hacking is to rob a person´s data in a intruded computer and to delete data in a person´s computer from the outside. To block hacking that is intrusion of a person´s computer and the computer virus that destroys data, a study for intrusion-detection of system and virus detection using a biological immune system is in progress. In this paper, we make a mood of positive selection and negative selection of self-recognition process that is ability of ...