http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Binary Harmony Search 알고리즘을 이용한 Unsupervised Nonlinear Classifier 구현
이태주(Tae-Ju Lee),박승민(Seung-Min Park),고광은(Kwang-Eun Ko),성원기(Won-Ki Sung),심귀보(Kwee-Bo Sim) 한국지능시스템학회 2013 한국지능시스템학회논문지 Vol.23 No.4
본 논문을 통해서 우리는 최적화 알고리즘인 binary harmony search (BHS) 알고리즘을 이용하여 unsupervised nonlinear classifier를 구현하는 방안을 제시하였다. 패턴인식을 위한 기계학습이나 뇌파 신호의 분석 과정과 같이 벡터로 표현되는 특징들을 분류하는데 있어 다양한 알고리즘들이 제시되었다. 교사 학습기반의 분류 방식으로는 support vector machine과 같은 기법이 사용되어왔고, 비교사 학습 방법을 통한 분류 기법으로는 fuzzy c-mean (FCM)과 같은 알고리즘들이 사용되어 왔다. 그러나 기존에 사용해 왔던 분류 방법들은 비선형 데이터 분류에 적용하기 힘들거나 교사 학습을 적용하기 위해서 사전정보를 필요로 하는 문제점이 있다. 본 논문에서는 경험적 접근을 통해 공간상에 분포된 벡터 사이의 기하학적 거리를 최소로 만드는 벡터 집합을 선택하고 이를 하나의 클래스로 간주하는 방법을 적용한 분류법을 제시하였다. 비교 대상으로 FCM과 artificial neural network (ANN) 기반의 self-organizing map (SOM)을 제시하였다. 시뮬레이션에는 KEEL machine learing dataset을 사용하였고 그 결과, 제안된 방식이 기존 알고리즘에 비해 더 나은 우수성을 지니고 있음을 확인하였다. In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.
Deep Belief Network를 이용한 뇌파의 음성 상상 모음 분류
이태주(Tae-Ju Lee),심귀보(Kwee-Bo Sim) 제어로봇시스템학회 2015 제어·로봇·시스템학회 논문지 Vol.21 No.1
In this paper, we found the usefulness of the deep belief network (DBN) in the fields of brain-computer interface (BCI), especially in relation to imagined speech. In recent years, the growth of interest in the BCI field has led to the development of a number of useful applications, such as robot control, game interfaces, exoskeleton limbs, and so on. However, while imagined speech, which could be used for communication or military purpose devices, is one of the most exciting BCI applications, there are some problems in implementing the system. In the previous paper, we already handled some of the issues of imagined speech when using the International Phonetic Alphabet (IPA), although it required complementation for multi class classification problems. In view of this point, this paper could provide a suitable solution for vowel classification for imagined speech. We used the DBN algorithm, which is known as a deep learning algorithm for multi-class vowel classification, and selected four vowel pronunciations:, /a/, /i/, /o/, /u/ from IPA. For the experiment, we obtained the required 32 channel raw electroencephalogram (EEG) data from three male subjects, and electrodes were placed on the scalp of the frontal lobe and both temporal lobes which are related to thinking and verbal function. Eigenvalues of the covariance matrix of the EEG data were used as the feature vector of each vowel. In the analysis, we provided the classification results of the back propagation artificial neural network (BP-ANN) for making a comparison with DBN. As a result, the classification results from the BP-ANN were 52.04%, and the DBN was 87.96%. This means the DBN showed 35.92% better classification results in multi class imagined speech classification. In addition, the DBN spent much less time in whole computation time. In conclusion, the DBN algorithm is efficient in BCI system implementation.
Binary Harmony Search 기반의 EEG 채널 그룹화를 이용한 다중 자극에 반응하는 뇌파 신호의 특성 연구
이태주(Tae-Ju Lee),박승민(Seung-Min Park),심귀보(Kwee-Bo Sim) 제어로봇시스템학회 2013 제어·로봇·시스템학회 논문지 Vol.19 No.8
This paper proposed a novel method for an analysis feature of an Electroencephalogram (EEG) at all channels simultaneously. In a BCI (Brain-Computer Interface) system, EEGs are used to control a machine or computer. The EEG signals were weak to noise and had low spatial resolution because they were acquired by a non-invasive method involving, attaching electrodes along with scalp. This made it difficult to analyze the whole channel of EEG signals. And the previous method could not analyze multiple stimuli, the result being that the BCI system could not react to multiple orders. The method proposed in this paper made it possible analyze multiple-stimuli by grouping the channels. We searched the groups making the largest correlation coefficient summation of every member of the group with a BHS (Binary Harmony Search) algorithm. Then we assumed the EEG signal could be written in linear summation of groups using concentration parameters. In order to verify this assumption, we performed a simulation of three subjects, 60 times per person. From the simulation, we could obtain the groups of EEG signals. We also established the types of stimulus from the concentration coefficient. Consequently, we concluded that the signal could be divided into several groups. Furthermore, we could analyze the EEG in a new way with concentration coefficients from the EEG channel grouping.