http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
오상훈 한국콘텐츠학회 2018 International Journal of Contents Vol.14 No.4
EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users’ implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.
오상훈 한국콘텐츠학회 2018 International Journal of Contents Vol.14 No.4
Among many UNESCO world heritage sites in Korea, “Historic Village: Hahoe” is adjacent to Nakdong River and it is imperative to monitor the water level near the village in a bid to forecast floods and prevent disasters resulting from floods.. In this paper, we propose a recurrent neural network with multiple hidden layers to predict the water level near the village. For training purposes on the proposed model, we adopt the sixth-order error function to improve learning for rare events as well as to prevent overspecialization to abundant events. Multiple hidden layers with recurrent and crosstalk links are helpful in acquiring the time dynamics of the relationship between rainfalls and water levels. In addition, we chose hidden nodes with linear rectifier activation functions for training on multiple hidden layers. Through simulations, we verified that the proposed model precisely predicts the water level with high peaks during the rainy season and attains better performance than the conventional multi-layer perceptron.
오상훈 한국콘텐츠학회 2003 한국콘텐츠학회논문지 Vol.3 No.2
포유류 동물의 시각피질 세포에 나타나는 특징은 크게 단순특징을 추출하는 simple cell과 복잡한 특징에 반응하는 complex cell로 구분된다. 특히, 하위 계층의 세포들은 단순특징을 추출하며, 상위 계층으로 갈수록 복합특징을 추출하는 세포들이 존재한다. 이 연구에서는 입력영상에 독립성분분석을 적용하여 complex cell에 대응하는 복잡한한 특징을 추출하였다. 이 결과는 시각피질 세포의 정보처리에 대한 방식에 대한 이해를 기반으로 시각정보처리 알고리즘을 개발하는 데 기여할 것이다. Neurons in the mammalian visual cortex can be dassified into the two main categories of simple cells and complex cells based on their response properties. Here, we find the complex features corresponding to the response of complex cells by applying the unsupervised independent component analysis network to input images. This result will be helpful to elucidate the information processing mechanism of neurons in primary visual cortex.
Subject Independent Classification of Implicit Intention Based on EEG Signals
오상훈 한국콘텐츠학회 2016 International Journal of Contents Vol.12 No.3
Brain computer interfaces (BCI) usually have focused on classifying the explicitly-expressed intentions of humans. In contrast, implicit intentions should be considered to develop more intelligent systems. However, classifying implicit intention is more difficult than explicit intentions, and the difficulty severely increases for subject independent classification. In this paper, we address the subject independent classification of implicit intention based on electroencephalography (EEG) signals. Among many machine learning models, we use the support vector machine (SVM) with radial basis kernel functions to classify the EEG signals. The Fisher scores are evaluated after extracting the gamma, beta, alpha and theta band powers of the EEG signals from thirty electrodes. Since a more discriminant feature has a larger Fisher score value, the band powers of the EEG signals are presented to SVM based on the Fisher score. By training the SVM with 1-out of-9 validation, the best classification accuracy is approximately 65% with gamma and theta components.
디지털 자원의 웹 아카이빙을 위한 납본 프로세스 개발 및 기능 설계
오상훈,최영선 한국정보관리학회 2008 정보관리학회지 Vol.25 No.4
국립중앙도서관에서 인쇄 출판물을 대상으로 운영 중인 납본체계와는 달리 웹 아카이빙인 OASIS (Online Archiving & Searching Internet Sources)는 웹 사이트, 웹 자원 등의 온라인 디지털 자원을 대상으로 자원 수집, 관리 및 보존하기 위한 과정이 필요하다. 이에 본 논문에서는 웹 아카이빙을 위한 디지털 자원 납본 프로세스를 개발하기 위해 디지털 자원 납본 주체와 대상을 정의하였고, 납본 프로세스를 위한 단계별 정의와 기능을 명시하였다. 또한 디지털 납본 시스템 구성을 위한 업무 흐름도와 단위 업무에 따른 기능 정의와 정보 흐름을 위한 구조를 제시하였다. The National Library of Korea is administering a legal deposit system for the printed- publications. Whereas, OASIS(Online Archiving & Searching Internet Sources) has to design a system to collect, manage and preserve web sites and web resources for Web Archiving. The purpose of this study is to develop a digital deposit process for digital resources. As a result, this study defines the subjects and objects for digital deposits, and describes the definitions and the functions according to digital deposit steps. Also, this study designs the data flow diagram and proposes the function definitions on unit works and the structure for the flow of information.