• 한국멀티미디어학회논문지
• /
• 제24권5호
• /
• pp.659-666
• /
• 2021

With the continuous development of deep learning, human behavior recognition algorithms have achieved good results. However, in a multi-person recognition environment, the complex behavior environment poses a great challenge to the efficiency of recognition. To this end, this paper proposes a multi-person pose estimation model. First of all, the human detectors in the top-down framework mostly use the two-stage target detection model, which runs slow down. The single-stage YOLOv3 target detection model is used to effectively improve the running speed and the generalization of the model. Depth separable convolution, which further improves the speed of target detection and improves the model's ability to extract target proposed regions; Secondly, based on the feature pyramid network combined with context semantic information in the pose estimation model, the OHEM algorithm is used to solve difficult key point detection problems, and the accuracy of multi-person pose estimation is improved; Finally, the Euclidean distance is used to calculate the spatial distance between key points, to determine the similarity of postures in the frame, and to eliminate redundant postures.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.364-369
• /
• 2001

As the population of persons over the age of sixty-five is rapidly growing, the population of solitary senior person living at own home is growing in Japan. This situation has caused the social issue of how supports their healthy life. There have been some projects related to improve their quality of life and support their healthy life. Unfortunately mostly they focus the method of measuring vital signal and observing behavior. Nobody reports how utilize the measured data. Aim of our project is how find emergency of the aged people at home. As emergency is big different from regular life behavior, we have to recognize it. We propose concept of the human behavior model and show the some types human behavior knowledge constructed by observed human behavior model and show the some types human behavior knowledge constructed by observed human behavior. This idea is based on human having habitual life. And we discuss the possibility of finding emergency using knowledge and observed data.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.324-331
• /
• 2005

In this paper, we propose a new customer profile model based on customer behavior in Internet shopping mall. The proposed technique defines customer profile model based on customer behavior information such as click data, buy data, and interest categories. We also implement CBCPM(Customer Behavior-based Customer Profile Model) and perform extensive experiments. The experimental results show that CBCPM has higher precision, recall, and F1 than the existing customer profile model.

• 한국보건간호학회지
• /
• 제29권2호
• /
• pp.231-243
• /
• 2015

Purpose: The purpose of this study was to analyze factors affecting health promotion behavior among nursing students according to health information seeking behavior. Methods: The study design was a descriptive survey and questionnaires were collected from 240 nursing students who have studied in nursing colleges located in "J" province. Data were analyzed using frequency, percentage, mean, standard deviation, independent t-test, One-way ANOVA, $Scheff{\grave{e}}$ test, Pearson Correlation, and hierarchical multiple regression. Results: In Model I, general characteristics influenced of 17.6% of health promotion behavior factors. Health status, selection criteria and frequency of information search were statistically useful as influencing of health promotion behavior factors. In addition, in model II health information seeking behavior influenced of 18.1% of health promotion behavior factors. Conclusion: The results indicate that the health information seeking behaviors proved the influence on health promotion behavior of nursing students.

• 한국의류학회지
• /
• 제20권6호
• /
• pp.1125-1137
• /
• 1996

The author reviewed seventy papers on social psychology of clothing and fashion marketing fields, which were published in the Journal of the Korean Society of Clothing and Textiles between 1983 and 1996. The market variables and consumer behavior variables were focused on. This review showed that the market variables had been divided into three groups of variables: 1) product variables (product image and product classification): 2) brand variables (brand image and brand positioning): and 3) store variables (store image, store type, and distribution system) Consumer behavior variables have been studied on the basis of EBM Consumer Behavior Model: 1) purchasing motivation as need recognition: 2) information using as search information: 3) evaluation criteria and choice criteria as alternative evaluatioin : 4) clothing purchase, brand choice and store choice as purchase: 5) degree of wear, satisfaction and dissatisfaction as outcome: and 6) clothing discard. Variables that influence on consumer behavior, including situation variables, clothing attitude variables, personal . social variables were added to develop a variable model of clothing consumer behavior using the EBM Consumer Behavior Model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.817-828
• /
• 2018

Modern software, especially web-based software, is broadly used in various fields. Most web applications employ design patterns, such as a model-view-controller (MVC) pattern and a factory pattern as development technology, so the application can have a good architecture to facilitate maintenance and productivity. A web application, however, may have defects and developers must fix the defects when a user submits bug reports. In this paper, we propose a novel approach to improving fault traceability in web application by using software revision information and software behavior model to reduce costs and effectively handle the software defect. We also provide a case study to show effectiveness of our approach.

• Asia pacific journal of information systems
• /
• 제31권3호
• /
• pp.392-414
• /
• 2021

Social networking services (SNS) is an indispensable method in order to obtain information of the Internet participants. The study identified three variables of social media communication, sharing culture, and online trust in terms of social capital theory (SCT) and reviewed intention& behavior variables in terms of theory of planned behavior (TPB). The data were collected from 330 samples of SNS user, and were involved, and the research model uses AMOS to make confirmatory factor analysis. The findings confirmed our hypothesis that social media communication, sharing culture, and online trust affect individuals' behaviors to sharing information. This study emphasizes that not only social media communication but also sharing culture to SNS can stimulate information sharing. while previous research has predominately focused on personal cognition or social network, the study examines the integrated influence of communication, culture and trust on information sharing in SNS. In sum, by explicating the unique role of social capital, this paper aims at contributing to the continued development and success of SNS in general.

• Journal of Information Display
• /
• 제10권3호
• /
• pp.101-106
• /
• 2009

In this study, a physical OLED analog behavior model for SPICE simulation was described using the Verilog-A language. The model was presented through theoretical equations for the J-V characteristics of OLED derived according to the internalcarrier emission equation based on a diffusion model at the Schottky barrier contact, and the mobility equation based on the Pool-Frenkel model. The accuracy of this model was examined by comparing it with the results of the device simulation that was conducted.

• 한국항해항만학회지
• /
• 제31권4호
• /
• pp.309-315
• /
• 2007

We've investigated the characteristics on mariner's behavior in the collision situation through a full-mission ship handling simulator and considered that it's necessary to model the standard avoiding behavior of mariners in order to apply the obtained results more widely and effectively. Thus we described the contents of standard avoiding behavior taken by mariners in the collision situation and established the concept of the standard model based on human factors for collision avoidance in a previous study. As a following study, this paper is to propose the method of modeling on mariners' standard behavior for collision avoidance by analyzing the contents of mariner's information processing and the related factors using regression analysis. As a result, we confirmed the influence of relating factors to avoiding behavior in mariner's deciding decisions and proposed the modeling method of mariners' standard behavior for collision avoidance with a example of recognition model.

• 전기학회논문지
• /
• 제59권12호
• /
• pp.2314-2318
• /
• 2010

For human-robot interaction, a robot should recognize the meaning of human behavior. In the case of static behavior such as face expression and sign language, the information contained in a single image is sufficient to deliver the meaning to the robot. In the case of dynamic behavior such as gestures, however, the information of sequential images is required. This paper proposes behavior classification by using fuzzy classifier to deliver the meaning of dynamic behavior to the robot. The proposed method extracts feature points from input images by a skeleton model, generates a vector space from a differential image of the extracted feature points, and uses this information as the learning data for fuzzy classifier. Finally, we show the effectiveness and the feasibility of the proposed method through experiments.