• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.2
• /
• pp.800-816
• /
• 2018

In recent years, video surveillance research has been able to recognize various behaviors of pedestrians and analyze the overall situation of objects by combining image analysis technology and deep learning method. Human Activity Recognition (HAR), which is important issue in video surveillance research, is a field to detect abnormal behavior of pedestrians in CCTV environment. In order to recognize human behavior, it is necessary to detect the human in the image and to estimate the pose from the detected human. In this paper, we propose a novel approach for 2D Human Pose Estimation based on object detection using RGB-D information. By adding depth information to the RGB information that has some limitation in detecting object due to lack of topological information, we can improve the detecting accuracy. Subsequently, the rescaled region of the detected object is applied to ConVol.utional Pose Machines (CPM) which is a sequential prediction structure based on ConVol.utional Neural Network. We utilize CPM to generate belief maps to predict the positions of keypoint representing human body parts and to estimate human pose by detecting 14 key body points. From the experimental results, we can prove that the proposed method detects target objects robustly in occlusion. It is also possible to perform 2D human pose estimation by providing an accurately detected region as an input of the CPM. As for the future work, we will estimate the 3D human pose by mapping the 2D coordinate information on the body part onto the 3D space. Consequently, we can provide useful human behavior information in the research of HAR.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• 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.

• Asian Journal for Public Opinion Research
• /
• v.1 no.3
• /
• pp.217-231
• /
• 2014

This study begins with a review of commonly discussed dimensions of public risk perception that may influence public opinion toward risks. Factors that have been revealed by the literature to have substantial impact on risk perception, such as demographic background, trust, and media environment, are also discussed. Meanwhile, we evaluate two well-known research models in the realm of risk analysis: 1) the psychometric paradigm, and 2) the social amplification of risk framework (SARF). Based on a literature review, this study suggests that, besides the psychological and social approach, models of risk perception and risk communication research should shift to a more comprehensive one by considering the interrelations between laypeople and the environment. This study proposes a research model from the perspective of social cognitive theory (SCT) as a potential framework for future studies: 1) in the societal environment, individuals' risk perception and information seeking behavior, which is determined by risk perception will be influenced by trust in regulators and interpersonal trust; 2) in the media environment, individuals' risk perception and information seeking behavior will be influenced by individuals' perceived information characteristics. Knowledge about risk accumulated through information seeking will change risk perception in a longitudinal process.

• Journal of Digital Convergence
• /
• v.16 no.3
• /
• pp.225-236
• /
• 2018

Organizations continue to invest in the security of information technology as a means to be more competitive than others in their industry do. However, there is a relatively lack of interest in the information security compliance of employees who implement information security technologies and policies of organization. This study finds mechanisms for enhancing security compliance by applying theory of planned behavior, justice theory, and motivation theory in information security field. We use structural equation modeling to verify the research hypotheses, and conducted a survey on the employees of organization with information security policy. The results showed that organizational justice, sanction, and organizational identification affect the factors of the planned behavior theory and affect the employee's compliance intention. As a result, this research suggested directions for strategic approach for enhancing employee's compliance intention on organization's security policy.

• Journal of Information Technology Applications and Management
• /
• v.17 no.2
• /
• pp.175-185
• /
• 2010

The primary objective of this paper is to examine post acceptance behavior model in UCC services. Based on the relevant literature reviews, this study posits six characteristics, that is, expectation confirmation, perceived usefulness, perceived enjoyment, satisfaction, and continuance intention as key variables to describe the post acceptance behavior model in UCC services. Then we constructed a research model and hypotheses about relationship between these variables. A total 286 usable survey responses of UCC service users have been employed in the analysis. The empirical results of this study are summarized as follows. Firstly, expectation confirmation has a positive effect on the perceived usefulness, perceived enjoyment, and satisfaction. Secondly, perceived enjoyment has a positive effect on the satisfaction. Lastly, perceived usefulness, perceived enjoyment, and satisfaction have a positive effect on the continuance intention. These results will be helpful for the UCC services sector to further develop service delivery strategies for strengthening the ongoing relationship with customers. Finally, some possible limits of the present research and future directions for such research were discussed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.17 no.5
• /
• pp.75-88
• /
• 2012

This study examines the relationship among servicescape, information technology, employee's job satisfaction, affective commitment and service performance. Empirical research is conducted to statistically test the model using SEM and empirically confirms followings: (a) positive effect of servicescape and IT on both of job satisfaction and affective commitment, which, in turn, positively influences on service behavior, (b) positive effect of affective commitment and service behavior on service recovery, and (c) significant indirect effect of job satisfaction on service recovery meditated by service behavior. Results suggest that there are direct and indirect effects on service performance of servicescape and information technology through job satisfaction and affective commitment. This paper is concluded with the summarized result and contribution of this study, managerial implication of the research findings, and further research issues.

• Journal of Korean Library and Information Science Society
• /
• v.42 no.3
• /
• pp.105-126
• /
• 2011

The purpose of this research is to investigate the information behavior of Korean college students as related to their process of learning activities, and to provide the essential data for improving the service quality of Korean academic libraries. To the end, discussed in details are (1) classifying the everyday learning activities of college students into six types and finding out the special features of their information needs and seeking behavior, (2) figuring out the meanings and use-patterns of academic libraries in their everyday learning, and (3) developing the variables influencing their library use behavior and testing the relationship between such variables and library use behavior. The data were collected through a survey with 290 college students, and analyzed for both frequency test and Chi-square test for the discussion.

• The Journal of Information Systems
• /
• v.17 no.2
• /
• pp.73-94
• /
• 2008

Knowledge is a fundamental assets, therefore, the ability to create, acquire, integrate, and share knowledge has emerged as a fundamental organizational capability(Sambamurthy and Subramani, 2005). This apaper reports the results of an empirical study investigating the factors of acceptance and the moderating role of resistance in Knowledge Management Systems(KMS). The research model is based on the theory of planned behavior(TPB) and technology acceptance model(TAM). It includes the perceived usefulness instead of attitude, subjective norm, perceived behavior control and intention of acceptance of KMS. Also, three external variables namely task-technology fit, organizational support, and perceived rewards are added. In the research model, all hypothrses of the baseline model and the moderating effects of resistance were found to be significant. The authors also of fred several implications based chi the findings.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.44-50
• /
• 2017

To understand whether Falling, which is one of the causes of injuries, occurs, various behavior recognition research is proceeding. However, in most research recognize only the fact that Falling has occurred and provide the service. As well as the occurrence of the Falling, the risk varies greatly based on the type of Falling and the situation before and after the Falling. Therefore, when Falling occurs, it is necessary to infer the user's current situation and provide appropriate services. In this paper, we propose to base on Fog Computing and Cloud Computing to design Context-aware System using analysis of behavior data and process sensor data in real-time. This system solved the problem of increase latency and server overload due to large capacity sensor data.

• The Journal of Information Systems
• /
• v.23 no.4
• /
• pp.197-219
• /
• 2014

Despite of continuous efforts to crack down on piracy using penalties and regulations, this unauthorized piracy market is still enormous. Since the moral hazard about this phenomenon is pervasive and continually upsets the major intellectual property markets, an alternative plan is required. The purpose of this study is to provide an objective insight for factors that affect people's digital video piracy behavior. The following two research propositions were the focus: what psychological factors affect piracy behavior and how are these factors related to one another? In order to accomplish the research aims, we reviewed literatures on the current state of piracy in South Korea, characteristics of digital contents, studies on criminal psychology and behavioral theories. Previous research in the fields of criminal theory indicated that neutralization, a form of rationalization, would help explain digital piracy intentions. Thus, this study developed a model that explains effects of neutralization techniques and tested the possibility of an integrated model with other behavioral theory such as TPB and TIB. Empirical results of the study(368 sample collected) showed that all the factors in TPB including Attitude to Piracy(+), Subjective Norm(-), Perceived Behavioral Control(+) had a significant impact on Piracy Intention. Moreover, two neutralization techniques, Condemn the Condemners(+) and Appeal to Higher Loyalties(+), had a significant effect on Piracy Intention. In addition, Past Behavior had strong impacts on Attitude(+), Perceived Behavioral Control(+) and Piracy Intention(+). In terms of Expected Profit, it had an impact on Attitude to Piracy positively. These findings suggest implications for protecting the current intellectual property markets, with many stakeholders in movies and media industries. There are some limitations as followed: first, the study did not consider other neutralization techniques, low level of deterrence and the other expected results despite the possibility of their effects. Second, the study needs improvements through longitudinal research because the cross-sectional research could not rule out the alternative explanations.