• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2005.11a
• /
• pp.199-202
• /
• 2005

TV OSD(On Screen Display) 메뉴 자동검증 시스템에서 다국적 언어의 문자 인식은 표준패턴의 구조적 분석이 쉽지 않을 뿐만 아니라 학습패턴 집합의 규모와 특징의 수가 증가함으로 인하여 특징추출 및 인식 과정에서 방대한 계산량이 요구된다. 이에 본 연구에서는 학습 데이터에 포함되는 다량의 특징 집합으로부터 인식에 필요한 효과적인 특징을 선별함으로써 패턴 분류기의 효율성을 개선하기 위한 방법론을 고찰한다. 이를 위하여 수정된 형태의 Adaboost 기법을 제안하고 이를 적용한 실험 결과로부터 그 유용성을 고찰한다. 제안된 알고리즘은 초기의 특징 집합을 취약한 성능을 갖는 다수의 분류기(classifier)로서 고려하며, 이로부터 반복학습을 통하여 개선된 분류기를 점진적으로 선별해 나가게 된다. 학습의 원리는 주어진 학습패턴 집합에 기초하여 일종의 교사학습(supervised learning) 방식으로 이루어진다. 각 패턴에 할당된 가중치 값은 각 단계에서 산출되는 분류결과에 따라 적응적으로 수정되어 반복학습이 진행됨에 따라 점차 보완적 성능을 갖는 분류기를 선택할 수 있게 한다. 즉, 주어진 각 학습패턴에 대하여 초기에 균등한 가중치가 부여되며, 반복학습의 각 단계에서 적용되는 분류기의 출력을 분석하여 오분류된 패턴의 가중치 분포를 증가시켜 나간다. 본 연구에서는 실제 응용으로서 OSD 메뉴검증 시스템을 대상으로 제안된 이론을 적용하고 그 타당성을 평가한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.2
• /
• pp.366-373
• /
• 2017

In this paper, we propose a variable weighted average (VWA) learning method in order to improve the performance of the fuzzy ART neural network that has been developed by Grossberg. In a conventional method, the Fast Commit Slow Recode (FCSR), when an input pattern falls in a category, the representative pattern of the category is updated at a fixed learning rate regardless of the degree of similarity of the input pattern. To resolve this issue, a variable learning method proposes reflecting the distance between the input pattern and the representative pattern to reduce the FCSR's category proliferation issue and improve the pattern recognition rate. However, these methods still suffer from the category proliferation issue and limited pattern recognition rate due to inevitable excessive learning created by use of fuzzy AND. The proposed method applies a weighted average learning scheme that reflects the distance between the input pattern and the representative pattern when updating the representative pattern of a category suppressing excessive learning for a representative pattern. Our simulation results show that the newly proposed variable weighted average learning method (VWA) mitigates the category proliferation problem of a fuzzy ART neural network by suppressing excessive learning of a representative pattern in a noisy environment and significantly improves the pattern recognition rates.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.77-86
• /
• 2005

In this paper, we designed a learning algorithm of LVQ that extracts classification errors and learns ones and improves classification performance. The proposed LVQ learning algorithm is the learning Networks which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVQ. To extract pattern vectors which cause classification errors, we proposed the error-cause condition, which uses that condition and constructed the pattern vector space which consists of the input pattern vectors that cause the classification errors and learned these pattern vectors , and improved performance of the pattern classification. To prove the performance of the proposed learning algorithm, the simulation is performed by using training vectors and test vectors that are Fisher' Iris data and EMG data, and classification performance of the proposed learning method is compared with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional classification.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.05a
• /
• pp.56-62
• /
• 2004

In the case that we do not have enough number of training patterns because of limitation such as time consuming, economic problem, and so on, we geneterate a new patterns using the brain-style Information processing algorithm, that is, supervised and unsupervised learning methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.287-292
• /
• 2007

본 연구에서는 동적 수신호 패턴에 대한 효과적인 인식을 위하여, 특징추출 단계와 패턴 분류 단계의 두 모듈로 이루어지는 복합형 신경망 모델을 제안한다. 특징추출 모듈을 위하여 고유의 특징표현 기법과 3차원 수용영역 구조의 CNN 모델을 제안한다. 이는 3차원 형식의 데이터로 표현되는 수신호 패턴으로부터 특징점의 공간적 변이뿐만 아니라 시간적 변이에 강인한 특징추출 기능을 제공한다. 패턴 분류 모듈에서는 효율적인 학습과 인식 기능을 위하여 수정된 구조의 GFMM 모델을 제안한다. 또한 학습패턴의 빈도를 고려한 활성화 특성과 학습 방법을 정의함으로써 기존의 GFMM 모델이 갖는 단점인 학습결과가 학습순서에 종속되는 특성과 비정상적 패턴 및 노이즈 패턴에 민감한 현상을 개선한다.

• The Journal of the Acoustical Society of Korea
• /
• v.12 no.6
• /
• pp.21-27
• /
• 1993

계층형 신경망은 패턴 분류를 위해 사용되어 왔다. 이것은 주어진 교사패턴들의 학습으로 원하는 입력-출력 간의 매핑을 할 수 있기 때문이다. 신경망은 타겟ㅌ트 패턴이 입력 패턴의 카테고리에 일치할 때 타겟트 패턴을 학습하므로서 사후 확률을 근사화할 수 있다. 그리고 입력 공간을 부분 공간으로 나누어 학습 데이터들의 비율로서 만든 타겟트 벡터들로 학습한 신경망은 확률밀도 함수를 나타낼 수 있다. 본 연구에서는 역전파 학습법을 이용한 계층형 NN 과 코드북으로서 사후 확률과 확률밀도함수의 측정방법을 제안하였다. VQ 로 추정한 사후확률고 확률밀도함수를 이용하여 학습이 필요없는 RBF network 의 일종인 PNN으로 모음 인식을 수행 하였다. 인식 실험에서 PNN 의 결과는 역전파 학습법을 이용항 3층 신경망과 VQ 의 평균 인식율과 비교되었다. VQ-PNN의 인식율이 다른 것보다 우수하게 나타났다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.285-301
• /
• 2023

Due to the increasing demand and importance of non-face-to-face education, open online learning platforms are getting interests both domestically and internationally. These platforms exhibit different characteristics from online courses by universities and other educational institutions. In particular, students engaged in these platforms can receive more learner autonomy, and the development of tools to assist learning is required. From the past, researchers have attempted to utilize process mining to understand realistic study behaviors and derive learning patterns. However, it has a deficiency to employ it to the open online learning platforms. Moreover, existing research has primarily focused on the process model perspective, including process model discovery, but lacks a method for the process pattern and instance perspectives. In this study, we propose a method to identify learning patterns within an open online learning platform using process mining techniques. To achieve this, we suggest three different viewpoints, e.g., model-level, variant-level, and instance-level, to comprehend the learning patterns, and various techniques are employed, such as process discovery, conformance checking, autoencoder-based clustering, and predictive approaches. To validate this method, we collected a learning log of machine learning-related courses on a domestic open education platform. The results unveiled a spaghetti-like process model that can be differentiated into a standard learning pattern and three abnormal patterns. Furthermore, as a result of deriving a pattern classification model, our model achieved a high accuracy of 0.86 when predicting the pattern of instances based on the initial 30% of the entire flow. This study contributes to systematically analyze learners' patterns using process mining.

• Journal of radiological science and technology
• /
• v.30 no.4
• /
• pp.419-426
• /
• 2007

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize taste(bitter, sweet, sour and salty) pattern vectors. The signal intensity of taste are used to compose the input pattern vectors. The SOM(Self Organizing Maps) algorithm for taste pattern recognition is used to learn initial reference vectors and the ot-star learning algorithm is used to determine the class of the output neurons of the sunclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ(Learning Vector Quantization) algorithm. The pattern vectors are classified into subclasses by neurons in the subclass layer, and the weights between subclass layer and output layer are learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors, the proposed algorithm is simulated with ones of the conventional LVQ, and it is confirmed that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.5 s.43
• /
• pp.95-103
• /
• 2006

In this paper, the input pattern vectors are extracted and the learning algorithms is designed to recognize EEG pattern vectors. The frequency and amplitude of alpha rhythms and beta rhythms are used to compose the input pattern vectors. And the algorithm for EEG pattern recognition is used SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of the subclass layer. The weights of the proposed algorithm which is between the input layer and the subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights between subclass layer and output layer is learned to classify the classified subclass, which is enclosed a class. To classify the pattern vectors of EEG, the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.6
• /
• pp.69-80
• /
• 2004

This paper proposes a method to learn action patterns of opponent characters for intelligent characters. For learning action patterns, intelligent characters learn the past actions as well as the current actions of opponent characters. Therefore, intelligent characters react more properly than ones without the knowledge on action patterns. In addition, this paper proposes a method to learn moving actions whose fitness is hard to evaluate. To evaluate the performance of the proposed algorithm, we experiment with four repeated action patterns in a game similar to real games. The results show that intelligent characters learn the optimal actions for action patterns and react properly against to random action opponent characters. The proposed method can be applied to various games in which characters confront each other, e.g. massively multiple of line games.