• 복식
• /
• 제63권2호
• /
• pp.1-13
• /
• 2013

The purpose of this study is to examine how the features of network in the Internet fashion community affect the diffusion of fashion information to members in the online community with other variables (informative features, consumer features). Communities that actively exchange fashion information among their members were selected for the social network analysis and hypothesis verification. As a result, we found that a few information activists influenced most of the information receivers in the network features of fashion communities. Also, we found that the informative features (usefulness, reliability), consumer features (NFC, innovation) as well as the network features (connectivity, power), have a significant influence on the diffusion of Internet fashion information which verified the importance of the network features in the study on the Internet.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2002년도 추계학술대회 논문집
• /
• pp.53-58
• /
• 2002

본 논문은 감성공학 데이터의 지속적인 지표화를 위해 과정의 자동화를 제안하며 자동 지표화가 문서의 자동 요약과 유사하다는 점에 착안하여 문서 자동분류, 정보유형 추출, 특성언어 추출 및 문장 재구성이라는 단계별 기술의 기초가 되는 정보유형 및 핵심어, 그리고 특성표현을 통한 정보문 추출 방법에 대해 연구하였다. 감성공학 코퍼스 분석을 통한 본 연구는 감성공학 분야에서의 지식 관리 시스템과 자동 요약 시스템에 활용될 수 있다.

• 한국정보처리학회논문지
• /
• 제3권3호
• /
• pp.439-448
• /
• 1996

형태 인식에서 유익한 특징정보의 선정 및 추출이 대단히 중요한 역할을 한다. 본 논문은 유익한 특징정보의 선정과 신경망의 학습을 동시에 수행할 수 있는 알고리 즘을 기술한다. 알고리즘은 근본적으로 반복적으로 수행되는 세 단계로 구성되어 있는데, 이들은 학습, 연결자 제거, 그리고 입력 신경세포 제거이다. 초기 학습을 실행한후, 먼저 적은 절대값을 갖는 연결자들이 제거 된다. 그런 후, 내부 계층 신경 세포들과 은 숫자의 결자들을 갖는 입력 신경세포들이 제거된다. 이 과정은 제거된 입력 신경세포들에 상응하는 특징정보들을 제외시키는 것과 동일하다. 만약, 에러값이 증가 하면, 연결자 제거 및 입력 신경세포 제거 과정의 반복으로 구성된 신경망의 재학습을 실행한다. 그 결과, 알고리즘은 다른 공간계로의 변환없이 특징정보 추출 공간내에서 중요한 특징들을 선정하게 된다. 또한, 즉징정보 선정인 형태 분류 관점에서의 성능과 긴밀하게 연결되어 수행되므로, 선정 된 특징정보들은 형태 분류에 가장 좋은 정보를 제공한다. 이 알고리즘은 불필요 또는 그다지 중요하지 않은 정보의 추출로 인한 경제 적 손실을 피할수 있게 한다. 더구나, 마지막에 얻어진 신경망은 인식 성능에 저해 요인이 될 수있는 불필요한 파라미터들, 즉 가중 연결자 및 바이어스를 포함하지 않는다. 응용결과,, 본 알고리즘은 가장 좋은 정보를 갖는 특징들만을 남기며, 성능 저하를 일으 키지 않으면서도 특징 벡터의 차원을 현저하게 줄였다.

• 한국IT서비스학회지
• /
• 제11권sup호
• /
• pp.139-152
• /
• 2012

In the medical web forum, people share medical experience and information as patients and patents' families. Some people search medical information written in non-expert language and some people offer words of comport to who are suffering from diseases. Medical web forums play a role of the informative support and the emotional support. We propose the automatic classification model of articles in the medical web forum into the information support and emotional support. We extract text features of articles in web forum using text mining techniques from the perspective of linguistics and then perform supervised learning to classify texts into the information support and the emotional support types. We adopt the Support Vector Machine (SVM), Naive-Bayesian, decision tree for automatic classification. We apply the proposed model to the HealthBoards forum, which is also one of the largest and most dynamic medical web forum.

• International Journal of Computer Science & Network Security
• /
• 제21권12호
• /
• pp.143-148
• /
• 2021

The article considers the training of specialists in education in the conditions of distance learning. It is lights up the advantages of distance learning and determined the characteristic features of distance learning of students training in the implementation of these technologies in the educational process. The article focuses on the main aspects of computerization of studies as a technological breach in methodology, organization and practical realization of educational process and informative culture of a teacher. Information technologies are intensive involved in life of humanity, educational process of schools and higher educational establishments. Intercommunication is examined between the processes of informatization of the society and education.

• 산경연구논집
• /
• 제10권8호
• /
• pp.7-15
• /
• 2019

Purpose - This study aims to examine the influence of social network service (SNS) on the brand image of infant food products; highlight the effects of brand image on the purchasing and word-of-mouth intention; and explore the effects of the purchasing intention on the word-of-mouth intention. Research design, data, and methodology - Based on previous studies, it was found that the fundamental SNS characteristics for infant food products are reliability, interactivity, and informative. Using AMOS 22.0 and structural equation modeling (SEM), 288 questionnaires were surveyed as a statistical method for examining the proposed hypotheses. Results - The analysis shows that reliability and informative have significant impacts on brand image, whereas interactivity does not. Again, the effect of brand image of infant food products on the purchase and word-of-mouth intention is statistically significant. However, the results differ across the "working housewife" and the "full-time housewife" groups. The connection between reliability and brand image was found to be statistically significant in this study. Conclusions - This study analyzes the effects of SNS characteristics on the brand image of infant food products and the effect of the brand image on purchase and word-of-mouth intentions, and provides practical implications for the same.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.173-188
• /
• 2013

In Facial Expression Recognition Systems (FERS), only particular regions of the face are utilized for discrimination. The areas of the eyes, eyebrows, nose, and mouth are the most important features in any FERS. Applying facial features descriptors such as the local binary pattern (LBP) on such areas results in an effective and efficient FERS. In this paper, we propose an automatic facial expression recognition system. Unlike other systems, it detects and extracts the informative and discriminant regions of the face (i.e., eyes, nose, and mouth areas) using Haar-feature based cascade classifiers and these region-based features are stored into separate image files as a preprocessing step. Then, LBP is applied to these image files for facial texture representation and a feature-vector per subject is obtained by concatenating the resulting LBP histograms of the decomposed region-based features. The one-vs.-rest SVM, which is a popular multi-classification method, is employed with the Radial Basis Function (RBF) for facial expression classification. Experimental results show that this approach yields good performance for both frontal and near-frontal facial images in terms of accuracy and time complexity. Cohn-Kanade and JAFFE, which are benchmark facial expression datasets, are used to evaluate this approach.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.59-62
• /
• 2007

본 논문에서는 불균형 및 Under-sampling된 바이오 데이터에 대하여 클래스 구분력이 없는 특징의 소거를 통해 이후 이어질 FLDA 둥 다양한 방법론올 적용할 수 있는 방법을 제안하고자 한다. 제안하는 알고리즘은 평균과 분산을 통해 클래스의 형태를 결정하는 기존 방법론의 문제점을 회피할 수 있는 방법을 제공하며, 클래스 구분력에 중점을 두어 특정을 선별하였을 경우 선별된 특정들의 상관 계수가 높은 문제를 극복할 수 있도록 한다. 이에 따라 알고리즘이 선택한 특정집합은 서로의 특징에 대해 상관계수가 낮으며, 클래스의 구분력이 높은 특정을 갖게 된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권10호
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.