• 지능정보연구
• /
• 제18권1호
• /
• pp.125-141
• /
• 2012

본 연구는 최근 그 중요성이 한층 높아지고 있는 침입탐지시스템(IDS, Intrusion Detection System)의 침입탐지모형을 개선하기 위한 방안으로 유전자 알고리즘에 기반한 새로운 통합모형을 제시한다. 본 연구의 제안모형은 서로 상호보완적 관계에 있는 이분류 모형인 로지스틱 회귀분석(LOGIT, Logistic Regression), 의사결정나무(DT, Decision Tree), 인공신경망 (ANN, Artificial Neural Network), 그리고 SVM(Support Vector Machine)의 예측결과에 적절한 가중치를 부여해 최종 예측결과를 산출하도록 하였는데, 이 때 최적 가중치의 탐색을 위한 방법으로는 유전자 알고리즘을 사용한다. 아울러, 본 연구에서는 1차적으로 오탐지율을 최소화하는 최적의 모형을 산출한 뒤, 이어 비대칭 오류비용 개념을 반영해 오탐지로 인해 발생할 수 있는 전체 비용을 최소화할 수 있는 최적 임계치를 탐색, 최종적으로 가장 비용 효율적인 침입탐지모형을 도출하고자 하였다. 본 연구에서는 제안모형의 우수성을 확인하기 위해, 국내 한 공공기관의 보안센서로부터 수집된 로그 데이터를 바탕으로 실증 분석을 수행하였다. 그 결과, 본 연구에서 제안한 유전자 알고리즘 기반 통합모형이 인공신경망이나 SVM만으로 구성된 단일모형에 비해 학습용과 검증용 데이터셋 모두에서 더 우수한 탐지율을 보임을 확인할 수 있었다. 비대칭 오류비용을 고려한 전체 비용의 관점에서도 단일모형으로 된 비교모형에 비해 본 연구의 제안모형이 더 낮은 비용을 나타냄을 확인할 수 있었다. 이렇게 실증적으로 그 효과가 검증된 본 연구의 제안 모형은 앞으로 보다 지능화된 침입탐지시스템을 개발하는데 유용하게 활용될 수 있을 것으로 기대된다.

• Communications for Statistical Applications and Methods
• /
• 제17권5호
• /
• pp.679-688
• /
• 2010

Lee (2010) developed a confidence interval for the difference of binomial proportions in two doubly sampled data subject to false-positive errors. The confidence interval seems to be adequate for a general double sampling model subject to false-positive misclassification. However, in many applications, the false-positive error rates could be the same. On this note, the construction of asymptotic confidence interval is considered when the false-positive error rates are common. The coverage behaviors of nine likelihood based confidence intervals are examined. It is shown that the confidence interval based Rao score with the expected information has good performance in terms of coverage probability and expected width.

• 전자공학회논문지B
• /
• 제31B권3호
• /
• pp.115-122
• /
• 1994

The problems in back-propagation(BP) generally are learning speed and misclassification due to lacal minimum. In this paper, to solve these problems, the classical modified methods of BP are reviewed and an extension of the BP to compensate the sigmoide-prime function around the extremity where the actual output of a unit is close to zero or one is proposed. The proposed method is not onlu faster than the conventional methods in learning speed but has an advantage of setting variables easily because it shows good classification results over the vast and uncharted space about the variations of learning rate, etc.. And it is simple for hardware implementation.

• Journal of Ecology and Environment
• /
• 제36권1호
• /
• pp.89-94
• /
• 2013

Diatoms have become an integral part of the UK's freshwater monitoring strategy over the past two decades, mostly in response to increasingly stringent European Union (EU) legislation. The use of diatoms is based on strong correlations between diatom assemblages and environmental variables, and from knowledge of the "expected" (= "reference") state of each river. The nationwide overview of the ecological health of rivers this gives allows those stretches of rivers which fail to meet EU criteria to be identified. This, in turn, allows appropriate remediation measures to be planned. Because diatom assemblages vary in space and time, even within a single water body, effective use of diatoms requires a consistent approach in order to minimise uncertainty. This includes the use of methods which comply with European Standards, a training and accreditation scheme for analysts, and a suite of quality assurance methods. Those aspects of uncertainty that cannot be readily controlled have been quantified and all estimates of ecological status are accompanied by the appropriate "confidence of class" and "risk of misclassification". This, in turn, helps planners prioritise those locations which are most likely to benefit from remediation.

• Journal of Nutrition and Health
• /
• 제28권8호
• /
• pp.791-799
• /
• 1995

Agreement between open question and closed question on portion size of a food frequency questionnaire was assessed for the influence by the restricted choices in closed question on estimated nutrient intakes and agreement of ranking individuals. Dietary intakes of 361 subjects in a rural country, Yang-pyeung Gun were obtained using a interview method. The results are as follows ; 1) Nutrients intakes calculated from closed question on portion size were lower than those calculated from open question on portion size. 2) For most nutrients the percentage of Korean RDA were significantly lower with closed question than open question. 3) Correlation coefficient of nutrient intakes and food intakes obtained by two methods were higher than 0.6 for all nutrients and food items. 4) For each nutrient, misclassification into extreme quartiles was less than 1 percent. 5) These data indicate that closed question on portion size can provide the corresponding information as open question if food frequency questionnarie is used for the ranking of individuals.

• 대한음성학회지:말소리
• /
• 제56호
• /
• pp.195-206
• /
• 2005

Discrimination between speech and music is important in many multimedia applications. In this paper, focusing on the spectral change characteristics of speech and music, we propose a new method of speech/music discrimination based on cepstral distance. Instead of using cepstral distance between the frames with fixed interval, the minimum of cepstral distances among neighbor frames is employed to increase discriminability between fast changing music and speech. And, to prevent misclassification of speech segments including short pause into music, short pause segments are excluded from computing cepstral distance. The experimental results show that proposed method yields the error rate reduction of$68\%$, in comparison with the conventional approach using cepstral distance.

• 대한음성학회지:말소리
• /
• 제48호
• /
• pp.93-105
• /
• 2003

Since telephone channel has bandlimited frequency characteristics, speech signal over the telephone channel shows degraded speech quality. In this paper, we propose an algorithm using neural network to reconstruct wideband speech from its narrowband version. Although single neural network is a good tool for direct mapping, it has difficulty in training for vast and complicated data. To alleviate this problem, we modularize the neural networks based on appropriate clustering of the acoustic space. We also introduce fuzzy computing to compensate for probable misclassification at the cluster boundaries. According to our simulation, the proposed algorithm showed improved performance over the single neural network and conventional codebook mapping method in both objective and subjective evaluations.

• 한국콘텐츠학회논문지
• /
• 제9권1호
• /
• pp.123-130
• /
• 2009

일반적으로 다층퍼셉트론을 패턴인식 문제에 적용할 경우 클래스 당 하나의 출력 노드를 배정하고, 이 출력 노드의 인덱스가 입력 패턴의 클래스를 뜻하도록 한다. 이 논문에서는 이와 달리 다층퍼셉트론의 성능 향상을 위하여 클래스 당 출력노드 수를 증가시키는 방법을 제안한다. 두 개의 클래스 문제를 대상으로 클래스 발생확률이 동일하고 각 클래스 내에서 출력노드가 균일분포를 지닌다는 가정 하에, 이 방법의 효용성을 확률론적인 유도를 통하여 증명하였다. 그리고, 50개의 고립단어 인식의 시뮬레이션으로 출력노드를 증가 시킬 경우 성능이 향상됨을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제15권3호
• /
• pp.355-364
• /
• 1994

The most important requirement for the controller of a prosthetic arm is that it has a high fidelity discriminator where the motion control may be performed open loop using EMG signals as a control source. Therefore, it is very effective method to reduce the influence of misclassification of classifier for the total system performance. This paper presents the new function discrimination method which combines MLP classifier and frizzy filter by stages for the requirement. The major advantage of MLP is a consistent learning capability for the easy adaptation to environments. The fuzzy filter uses all informations of MLP outputs and prior EMG activity informations which increase as the experience increases. That property is superior to one which uses maximum output of MLP in view of information amounts and quality. Simulation result shows that proposed method is superior to the probabilistic model, MLP model and the combined model of both in the respect of discrimination quaity.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.273-276
• /
• 1996

We propose a new method to extract valid lines from a visual image. Unsupervised clustering method is used to assign each line to any of the line groups according to its orientation. During the low-level image processing we use an adaptive threshold method to reduce human supervision and to automate the processing sequence. To reduce the misclassification rate and to suppress the superiors line support regions at the clustering stage, the adaptive threshold method is consistently applied. Performing principal component analysis on each line support region provides an efficient method of obtaining line equation. Finally we adopt the theory of robust statistics to guarantee the quality of each extracted line and to eliminate the lines of poor quality. We present the experimental results to verify our method. With the proposed method, one can extract the lines according to the internal orientation similarities and integrate the whole process into one adaptive procedure.