• Journal of the Korean Society of Food Science and Nutrition
• /
• v.44 no.6
• /
• pp.854-861
• /
• 2015

This study investigated the association between breakfast frequency (0~2 times, 3~6 times, and 7 times per week) and awareness of general school life (physical activity, relationships with teachers and friends, rule compliance, study attitudes, study records, and overall school life) in high school students (boys 146 and girls 155) in the Yongin region. Awareness of physical activity was higher in girls (77.4%) than in boys (65.1%). Rule compliance showed a significant difference in girls (P<0.01), whereas boys did not show any difference. Percentage of 'effective' awareness of study attitudes was 24.0% and 44.5% in boys and girls, respectively. Awareness of study records in girls showed significant difference (0~2 times 37.5%, 3~6 times 30.4%, and 7 times 52.2%) (P<0.05), whereas boys did not show any difference. Awareness of overall school life showed a significant difference in both boys (P<0.05) and girls (P<0.01). Association between breakfast frequency and general school life in boys was as follows: awareness of overall school life had the highest positive value (+0.185) (P<0.05) and relationships with teachers had the second (+0.168) (P<0.05). Girls also showed the highest positive value (+0.323) (P<0.01) for awareness of overall school life, which occurred in the following order: rule compliance (+0.316) (P<0.01)> awareness of study attitudes (+0.267) (P<0.01)> relationships with friends (+0.215) (P<0.01). In conclusion, high school students showed a high positive association between breakfast frequency and general school life, particularly in girls. Therefore, effective nutrition education programs in connection with national policy and school support are highly required to provide healthy breakfast and school life to high school students.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.792-798
• /
• 2007

In this paper, we propose a hierarchical fuzzy-rough classification method based on statistical information for maximizing the performance of pattern classification and reducing the number of rules without learning approaches such as neural network, genetic algorithm. In the proposed method, statistical information is used for extracting the partition intervals of antecedent fuzzy sets at each layer on hierarchical fuzzy-rough classification systems and rough sets are used for minimizing the number of fuzzy if-then rules which are associated with the partition intervals extracted by statistical information. To show the effectiveness of the proposed method, we compared the classification results(e.g. the classification accuracy and the number of rules) of the proposed with those of the conventional methods on the Fisher's IRIS data. From the experimental results, we can confirm the fact that the proposed method considers only statistical information of the given data is similar to the classification performance of the conventional methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10b
• /
• pp.130-132
• /
• 2001

신경망을 이용한 추천 기술은 항목이나 사용자간의 가중치를 학습할 수 있고, 자료 유형에 상관없이 데이터 처리가 용이하다. 또한 최근 연구를 통해서 그 우수성이 입증되고 있다. 그러나 사용자간의 상관관계로 추천하는 사용자 신경망 모델과 항목간의 상관관계로 추천하는 항목 신경망 모델이 서로 다른 관점으로 다른 선호도를 제시한 경우에 선택한 모델의 선호도에 따라 시스템의 성능이 좌우된다. 그러므로 효율적이고 성능이 우수한 추천 시스템을 위해 사용자와 항목 신경망 모델의 통합 방법을 제안한다. 두 모델 사이에 우선 순위를 결정하여 통합하는 순차적 통합 방법과 두 모델을 동시에 고려하는 병렬적 통합방법을 제안한다. 그러나 두 통합 방법은 선호도 예측 기준에 있어서 정적이고, 문제에 대한 적응성이 없다. 그러므로 신경망(퍼셉트론, 다층 퍼셉트론)을 이용한 통합 방법을 제안한다. 또한 퍼지의 소속함수를 이용하여 퍼지 추론를 적용한 통합 방법을 제안하고, 패턴 인식 분야에서 사용하는 BKS 방법을 적응하여 두 신경망 모델을 통합하여 실험한다. 본 논문에서는 사용자와 항목 신경망 모델을 통합함으로써 기존의 추천 기술인 연관 규칙과 단일 신경망 모델을 이용한 추천보다 우수함을 보이고 있다.

• Annual Conference on Human and Language Technology
• /
• 2012.10a
• /
• pp.40-44
• /
• 2012

어휘가 갖는 의미적 중의성은 자연어의 특성 중 하나로 자연어 처리의 정확도를 떨어트리는 요인으로, 이러한 중의성을 해소하기 위해 언어적 규칙과 다양한 기계 학습 모델을 이용한 연구가 지속되고 있다. 의미적 중의성을 가지고 있는 동형이의어의 의미분별을 위해서는 주변 문맥이 가장 중요한 자질이 되며, 자질 정보를 추출하기 위해 사용하는 문맥 창의 크기는 중의성 해소의 성능과 밀접한 연관이 있어 신중히 결정되어야 한다. 본 논문에서는 의미분별과정에 필요한 문맥을 가변적인 크기로 사용하는 가변길이 윈도우 방식을 제안한다. 세종코퍼스의 형태의미분석 말뭉치로 학습하여 12단어 32,735문장에 대해 실험한 결과 용언의 경우 평균 정확도 92.2%로 윈도우를 고정적으로 사용한 경우에 비해 향상된 결과를 보였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.1
• /
• pp.14-24
• /
• 2002

In this paper, a design of the pulsewidth-modulation(PWM) neural network with both retrieving and learning function is proposed. In the designed PWM neural system, the input and output signals of the neural network are represented by PWM signals. In neural network, the multiplication is one of the most commonly used operations. The multiplication and summation functions are realized by using the PWM technique and simple mixed-mode circuits. Thus, the designed neural network only occupies the small chip area. By applying some circuit design techniques to reduce the nonideal effects, the designed circuits have good linearity and large dynamic range. Moreover, the delta learning rule can easily be realized. To demonstrate the learning capability of the realized PWM neural network, the delta learning nile is realized. The circuit with one neuron, three synapses, and the associated learning circuits has been designed. The HSPICE simulation results on the two learning examples on AND function and OR function have successfully verified the function correctness and performance of the designed neural network.

• Journal of KIISE:Software and Applications
• /
• v.32 no.1
• /
• pp.1-9
• /
• 2005

In this paper we propose a modified fuzzy min-max neural network model for pattern classification and discuss the usefulness of the model. We define a new hypercube membership function which has a weight factor to each of the feature within a hyperbox. The weight factor makes it possible to consider the degree of relevance of each feature to a class during the classification process. Based on the proposed model, a knowledge extraction method is presented. In this method, a list of relevant features for a given class is extracted from the trained network using the hyperbox membership functions and connection weights. Ft)r this purpose we define a Relevance Factor that represents a degree of relevance of a feature to the given class and a similarity measure between fuzzy membership functions of the hyperboxes. Experimental results for the proposed methods and discussions are presented for the evaluation of the effectiveness and feasibility of the proposed methods.

• Annual Conference on Human and Language Technology
• /
• 1999.10d
• /
• pp.60-75
• /
• 1999

품사 태깅은 자연 언어 처리의 가장 기본이 되는 부분으로 상위 자연 언어 처리 부분인 구문 분석, 의미 분석의 전처리로 사용되고, 독립된 응용으로 언어의 정보를 추출하거나 정보 검색 등의 응용에 사용되어 진다. 품사 태깅은 크게 통계에 기반한 방법, 규칙에 기반한 방법, 이 둘을 모두 이용하는 혼합형 방법 등으로 나누어 연구되고 있다. 포항공대 자연언어처리 연구실의 자연 언어 처리 엔진(SKOPE)의 품사 태깅 시스템 POSTAG는 미등록어 추정이 강화된 혼합형 품사 태깅 시스템이다 본 시스템은 형태소 분석기, 통계적 품사 태거, 에러 수정 규칙 후처리기로 구성되어 있다. 이들은 각각 단순히 직렬 연결되어 있는 것이 아니라 형태소 접속 테이블을 기준으로 분석 과정에서 형태소 접속 그래프를 생성하고 처리하면서 상호 밀접한 연관을 가진다. 그리고, 미등록어용 패턴사전에 의해 등록어와 동일한 방법으로 미등록어를 처리함으로써 효율적이고 강건한 품사 태깅을 한다. 한편, POSTAG에서 사용되는 태그세트와 한국전자통신연구원(ETRI)의 표준 태그세트 간에 양방향으로 태그세트 매핑을 함으로써, 표준 태그세트로 태깅된 코퍼스로부터 POSTAC를 위한 대용량 학습자료를 얻고 POSTAG에서 두 가지 태그세트로 품사 태깅 결과 출력이 가능하다. 본 시스템은 MATEC '99'에서 제공된 30000어절에 대하여 표준 태그세트로 출력한 결과 95%의 형태소단위 정확률을 보였으며, 태그세트 매핑을 제외한 POSTAG의 품사 태깅 결과 97%의 정확률을 보였다.

• Journal of KIISE:Software and Applications
• /
• v.33 no.8
• /
• pp.692-702
• /
• 2006

In this study, a weighted fuzzy min-max (WFMM) neural network model for pattern classification is proposed. The model has a modified structure of FMM neural network in which the weight concept is added to represent the frequency factor of feature values in a learning data set. First we present in this paper a new activation function of the network which is defined as a hyperbox membership function. Then we introduce a new learning algorithm for the model that consists of three kinds of processes: hyperbox creation/expansion, hyperbox overlap test, and hyperbox contraction. A weight adaptation rule considering the frequency factors is defined for the learning process. Finally we describe a feature analysis technique using the proposed model. Four kinds of relevance factors among feature values, feature types, hyperboxes and patterns classes are proposed to analyze relative importance of each feature in a given problem. Two types of practical applications, Fisher's Iris data and Cleveland medical data, have been used for the experiments. Through the experimental results, the effectiveness of the proposed method is discussed.

• Journal of Intelligence and Information Systems
• /
• v.18 no.2
• /
• pp.1-17
• /
• 2012

The Smartphone, one of essential mobile devices widely used recently, can be very effectively applied to capture knowledge on the spot by jointly applying the pervasive functionality of cloud computing. The process of knowledge capturing can be also effectively automated if the topic of knowledge is automatically identified. Therefore, this paper suggests an interdisciplinary approach to automatically acquire knowledge on the spot by combining technologies of text mining-based topic identification and cloud computing-based Smartphone. The Smartphone is used not only as the recorder to record knowledge possessor's dialogue which plays the role of the knowledge source, but also as the sensor to collect knowledge possessor's context data which characterize specific situations surrounding him or her. The support vector machine, one of well-known outperforming text mining algorithms, is applied to extract the topic of knowledge. By relating the topic and context data, a business rule can be formulated, and by aggregating the rule, the topic, context data, and the dictated dialogue, a set of knowledge is automatically acquired.

• Journal of Internet Computing and Services
• /
• v.7 no.3
• /
• pp.169-178
• /
• 2006

In this paper, we define the large word sets which are noble variations the large item sets in mining association rules, and improve the accuracy for NaiveBayes based on the defined large word sets. In order to use them, a document is divided into the several paragraphs, and then each paragraph can be transformed as the transaction by extracting words in it. The proposed method was implemented by using Al:Categorizer framework and its accuracies were measured by the experiments for reuter-21578 data set. The results of the experiments show that the proposed method improves the accuracy of the conventional NaiveBayes.