• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.2
• /
• pp.311-316
• /
• 2016

Network intrusion detection system based on machine learning method such as artificial neural network is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features, which guarantees accuracy and efficienty, from generally used many features to detect network intrusion requires extensive computing resources. In this paper, we deal with a optimal feature selection problem to determine 6 denial service attacks and normal usage provided by NSL-KDD data. We propose a optimal feature selection algorithm. Proposed algorithm is based on the multi-start local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In order to evaluate the performance of our proposed algorithm, comparison with a case of all 41 features used against NSL-KDD data is conducted. In addtion, comparisons between 3 well-known machine learning methods (multi-layer perceptron., Bayes classifier, and Support vector machine) are performed to find a machine learning method which shows the best performance combined with the proposed feature selection method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.4
• /
• pp.370-380
• /
• 2002

This paper proposes an ATR (Automatic Target Recognition) algorithm for identifying non-occluded and occluded military vehicles in natural FLIR (Forward Looking InfraRed) images. After segmenting a target, a radial function is defined from the target boundary to extract global shape features. Also, to extract local shape features of upper region of a target, a distance function is defined from boundary points and a line between two extreme points. From two functions and target contour, four global and four local shape features are proposed. They are much more invariant to translation, rotation and scale transform than traditional feature sets. In the experiments, we show that the proposed feature set is superior to the traditional feature sets with respect to the similarity-transform invariance and recognition performance.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.16-29
• /
• 1995

Choosing initial codevectors in the LBG algorithm controls the performance of a codebook, because it only guarantees a locally optimal codebook. In this paper, we propose the decision method of initial codevectors by a decision radius which takes for feature vectors DC, low frequency, medium frequency and high frequency terms generated by a DCT. The more the decision radius is increased in order to decide initial codevectors, the more the number of membership vectors and the standard deviation for distance among the initial codevectors are increased. To obtain improved performance for a codebook, the decision radius for DC term is required above 0.9 of the membership rate and those for low frequency, medium frequency and high frequency terms under 0.6 of it.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.9
• /
• pp.753-763
• /
• 1990

This paper proposes a new current control strategy for current regulated VSI-PWM lnverter. The conventional hysteresis control method has good dynamic response, but the switching frequency in lower region are high because it does not optimise switching patterns. Proposed current control strategy can optimize switching patterns. As regulater, three level comparator are used, the output of comparator select appropriate inverter output voltage vectors via switching table stored in EPROM. The simulation and experimental results in comparison to conventional hysteresis strategy are presented and discussed.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.22-23
• /
• 2018

본 논문에서는 그래프 간 정합을 이용한 포인트 클라우드 시퀀스 압축 기법을 제안한다. 우선, 그래프를 활용하여 포인트 클라우드 시퀀스의 시변하는 기하학적 구조를 표현하고, 그래프로부터 웨이블릿 변환을 사용하여 추출한 특징 벡터를 매칭하는 방법으로 인접 프레임 간 움직임 예측을 수행한다. 그리고 움직임 예측을 통해 얻은 움직임 벡터 중 정합 점수가 높은 소수의 움직임 벡터를 보간하여 프레임 전체의 움직임 필드를 얻는다. 최종적으로 움직임 정보를 활용하여 얻은 예측 프레임과 타겟 프레임의 차이를 선택적 엔트로피 부호화 방식으로 코딩하여 포인트 클라우드 시퀀스 압축을 수행한다. 실험 결과 제안하는 기법이 3D 포인트 클라우드 시퀀스를 효과적으로 압축함을 확인할 수 있다.

• Annual Conference of KIPS
• /
• 2016.10a
• /
• pp.599-602
• /
• 2016

고속철도 산업의 핵심 요소 중 하나인 선로전환기는 열차의 진로를 제어해주는 부품으로, 해당 설비의 노후화를 조기에 탐지하여 적절한 시기에 선로전환기를 교체하는 것은 안정적인 철도운영에서 매우 중요하다. 본 논문에서는 선로전환기의 작동 시 발생하는 전류 신호를 이용하여 선로전환기의 노후화를 탐지하는 시스템을 제안한다. 제안하는 시스템은 선로전환기로부터 전류 신호를 취득한 후, 주파수 도메인의 특징인 SK값으로 변환하여 특징벡터를 추출하고, PCA를 이용하여 SK벡터의 차원 축소와 동시에 중요한 특징들만을 선택한다. 마지막으로, 선로전환기의 노후화를 탐지하는 문제를 이진 클래스 문제로 해석하여, 기계학습의 대표적 모델인 SVM을 이용하여 선로전환기의 노후화 여부를 탐지한다. 실제 국내에서 운행 중인 선로전환기의 전류 신호를 취득하여 실험한 결과, 선로전환기의 노후화 상황을 안정적으로 탐지함을 확인하였다.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.409-416
• /
• 2013

Attention is one of important cognitive functions in human affecting on the selectional concentration of relevant events and ignorance of irrelevant events. The discrimination of attentional and inattentional status is the first step to manage human's attentional capability using computer assisted device. In this paper, we newly combine the non-linear recurrence pattern analysis and spectrum analysis to effectively extract features(total number of 13) from the electroencephalographic signal used in the input to classifiers. The performance of diverse types of attention-inattention classifiers, including supporting vector machine, back-propagation algorithm, linear discrimination, gradient decent, and logistic regression classifiers were evaluated. Among them, the support vector machine classifier shows the best performance with the classification accuracy of 81 %. The use of spectral band feature set alone(accuracy of 76 %) shows better performance than that of non-linear recurrence pattern feature set alone(accuracy of 67 %). The support vector machine classifier with hybrid combination of non-linear and spectral analysis can be used in later designing attention-related devices.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.6
• /
• pp.654-662
• /
• 2010

In this paper, we suggest an advanced algorithm, to recognize pedestrian/non-pedestrian using second-stage cascade method, which applies Adaboost algorithm to make a strong classification from weak classifications. First, we extract two feature vectors: (i) Histogram of Oriented Gradient (HOG) which includes gradient information and differential magnitude; (ii) Curvature-HOG which is based on four different curvature features per pixel. And then, a strong classification needs to be obtained from weak classifications for composite recognition method using both HOG and curvature-HOG. In the proposed method, we use one feature vector and one strong classification for the first stage of recognition. For the recognition-failed image, the other feature and strong classification will be used for the second stage of recognition. Based on our experiment, the proposed algorithm shows higher recognition rate compared to the traditional method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.97-102
• /
• 2019

There are many difficulties to define because there is no systematic classification and analysis method using accurate criteria or numerical values for creative people. In order to solve this problem, this study attempts to analyze how to distinguish creative people and what kind of personality they have when distinguishing creative people. In this study, I first survey the Big 5 personality trait, classify and analyze the data set using the data mining tool WEKA, and then analyze the data set related to the creativity The goal is to analyze the features using various machine learning techniques. I use seven feature selection algorithms, select feature groups classified by feature selection algorithms, apply them to machine learning algorithms to find out the accuracy, and derive the results.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.133-136
• /
• 2002

본 연구에서는 뉴우턴법과 모멘트를 이용한 수정된 고정점 알고리즘의 독립성분분석기법을 이용한 영상의 특징추출을 제안하였다. 여기서 뉴우턴법은 엔트로피 최적화로부터 유도된 기법으로 그 계산을 간략화하여 역혼합행렬의 빠른 경신을 위함이고, 모멘트는 접선을 구하는 과정에서 함수의 기울기변화 계산에서 발생하는 발진을 줄여 좀 더 빠른 학습을 위함이다. 제안된 기법을 13개 자연영상들로부터 선택된 12×12 픽셀(pixel)의 10,000개 패치를 대상으로 시뮬레이션 한 결과, 추출된 16×16픽셀의 160개 독립성분 기저벡터 각각은 자연영상들에 포함된 공간적인 주파수 특성과 방향성을 가지는 경계 특성이 잘 드러나는 국부적인 특징들임을 확인할 수 있었다. 또한 모멘트의 이용으로 개선된 특징추출을 얻을 수 있었다.