• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.161-168
• /
• 2019

Recently, video equipments such as CCTV, which is spreading rapidly, is being used as a means to monitor and cope with abnormal situations in almost governments, companies, and households. However, in most cases, since recognizing the abnormal situation is carried out by the monitoring person, the immediate response is difficult and is used only for post-analysis. In this paper, we present the results of the development of video surveillance system that automatically recognizing the abnormal situations and sending such events to the smartphone immediately using the latest deep learning technology. The proposed system extracts skeletons from the human objects in real time using Openpose library and then recognizes the human behaviors automatically using deep learning technology. To this end, we reconstruct Openpose library, which developed in the Caffe framework, on Darknet framework to improve real-time processing. We also verified the performance improvement through experiments. The system to be introduced in this paper has accurate and fast behavioral recognition performance and scalability, so it is expected that it can be used for video surveillance systems for various applications.

• Journal of the HCI Society of Korea
• /
• v.12 no.4
• /
• pp.45-55
• /
• 2017

In recent years, some service providers have introduced chatbot agents to provide engagement in the healthcare field. However, current research on chatbot agents is still limited to designing various chatbot identities for healthcare services. By contrast, this study aims to investigate how various agent identities affect users' perceptions and behaviors differently. We developed three chatbot agents with different identities: a doctor (an individual), a hospital (an institution), and a virtual agent (a machine). Then, we recruited 36 users and divided them into three groups, each using a different chatbot agent. They were asked to track their behaviors and review advice from the chatbot agent for six days. Post-hoc surveys and interviews were conducted in order to investigate users' perceptions. The findings are as follows: participants felt more trusting and intimate with the doctor and hospital agents than with the virtual agent. Many of the participants preferred the hospital agent due to its higher reliability. However, all three agents did not lead the participants to change their behaviors. This study contributes to providing practical guidelines for designing chatbots in the healthcare field by studying users' perceptions and behaviors depending on chatbot identities.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.5
• /
• pp.101-107
• /
• 2009

In this paper, we describe a method of detecting emergency situation using images from surveillance cameras and propose a mobile robot tracking system for detailed examination of that situation. We are able to track a few persons and recognize their actions by an analyzing image sequences acquired from a fixed camera on all sides of buildings. When emergency situation is detected, a mobile robot moves and closely examines the place where the emergency is occurred. In order to recognize actions of a few persons using a sequence of images from surveillance cameras images, we need to track and manage a list of the regions which are regarded as human appearances. Interest regions are segmented from the background using MOG(Mixture of Gaussian) model and continuously tracked using appearance model in a single image. Then we construct a MHI(Motion History Image) for a tracked person using silhouette information of region blobs and model actions. Emergency situation is finally detected by applying these information to neural network. And we also implement mobile robot tracking technology using the distance between the person and a mobile robot.

• Journal of Science and Technology Studies
• /
• v.1 no.2 s.2
• /
• pp.399-422
• /
• 2001

Models for human cognition currently discussed in cognitive science cannot be appropriate ones. The symbolic model of the traditional artificial intelligence works for reasoning and problem-solving tasks, but doesn't fit for pattern recognition such as letter/sound cognition. Connectionism shows the contrary phenomena to those of the traditional artificial intelligence. Connectionist systems has been shown to be very strong in the tasks of pattern recognition but weak in most of logical tasks. Brooks' situated action theory denies the. notion of representation which is presupposed in both the traditional artificial intelligence and connectionism and suggests a subsumption model which is based on perceptions coming from real world. However, situated action theory hasn't also been well applied to human cognition so far. In emphasizing those characteristics of models I refer those models 'left-brain model', 'right-brain model', and 'robot model' respectively. After I examine those models in terms of substantial items of cognitions- mental state, mental procedure, basic element of cognition, rule of cognition, appropriate level of analysis, architecture of cognition, I draw three arguments of embodiment. I suggest a way of unifying those existing models by examining their theoretical compatability which is found in those arguments.

• Journal of the Korean Society of Earth Science Education
• /
• v.14 no.1
• /
• pp.21-32
• /
• 2021

The recognition for future global environment was studied targeting the university students who will be grown as general public composing our society in this study. The rate recognizing as the complex space of natural objects and artifacts is very low for non-science majored university students. Also, the rate recognizing global environment change from now to the future as negative. The environment recognition should be changed as that the university students can imagine the human live together with the nature in the image of future global environment. The environment education find out and practice the method that human can co-exist together to the direction of co-exist with the nature. Also, the rate internalizing future global environment as the space the human amends for non-science majored university students. This result is interpreted as shown the point of view that the global environment can be improved by the human activity, and it suggests the direction of environment education the university should supply. The environment education direction should be converted from the eduction of environment or the eduction from environment to the education for environment. The opportunity for global environment education should be provided to all university students without the discrimination on the major in the university education course. Sustainable global environment eduction is necessary for our son and daughter live on the earth continuously.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1396-1398
• /
• 2015

BCI (Brain Computer Interface)는 사람의 두뇌와 컴퓨터를 연결하는 '뇌-컴퓨터 인터페이스'를 나타내는 것이며 EEG(Electroencephalogram)을 주로 분석하여 인간의 행동이나 의도를 파악한다. 본 논문에서는 EEG를 이용한 행동인식의 하나로 졸음을 판단하는 방법을 제안한다. 제안방법에서는 MindWave를 이용하여 얻은 실험 데이터를 FFT를 이용하여 1초 단위로 스펙트럼을 분석하여 High-Alpha 영역의 시간에 따른 데이터 변화 패턴을 분석하여 졸음을 판단한다. 실험 결과, 100%의 최고 성능을 얻을 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.580-582
• /
• 2022

본 본문은 영상을 통해 반려동물의 행동과 감정을 인식하는 연구이다. 이러한 연구는 반려동물과 인간의 삶을 향상시키는데 도움을 줄 수 있다. 제안된 시스템의 유용성은 실험을 통해 검증하였고, 어느 정도 의미 있는 결과를 얻을 수 있었다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.3
• /
• pp.11-21
• /
• 2011

The development of computer-based modeling system has allowed the operationalization of cognitive science issues. Human cognition has become one of most interesting research subjects in artificial intelligence to emulate human mentality and behavior. This paper introduces a methodology well-suited for designing the intelligent system of human cognition. The research investigates how to elicit and represent cognitive knowledge obtained from individual city-dwellers through the application of fuzzy relational theory to personal construct theory. Crucial to this research is to implement formally and process interpretatively the psychological cognition of urbanites who interact with their environment in order to offer useful advice on urban problem. What is needed is a techniques to analyze cognitive structures which are embodiments of this perceptive knowledge for human being.

• Management & Information Systems Review
• /
• v.35 no.1
• /
• pp.207-233
• /
• 2016

Currently mobile messenger industry, based on mobile application, is growing. And it has aroused innovative change, offering services in various forms beyond the form simply sharing messengers. Also because messenger securities are becoming personalized and intelligent, the importance of more diverse mobile applications' securities is increasing. This study carries out the empirical study of the causal relationship that the factors of using application services influence on security recognition and security Intention of mobile securities, and consequentially impact upon protection of personal information of users. In order that, we present the research model which prime variables of SDT, which emphasized on natural immanent motivation of human, applied to. To verify the research model of this study empirically, we conducted a survey targeting the public and university students which have ever used mobile messenger applications. With this, we desire to contribute to emphasizing the significance of individual messenger security and playing a positive role to develop security guide for consumers. The path analysis results are as follows. First, perceived autonomy has a positive effect on both security awareness and security intention. Second, perceived competence has a positive effect on security intention. Third, perceived relatedness has a positive effect on both security awareness and security intention. Last, security awareness and security intention. have a positive effect on privacy protection behavior. Through emphasizing the importance of the security of the messenger of individuals and contribute to a positive role for development of the necessary security guidelines to consumers.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.525-530
• /
• 2010

Currently, most context-aware services are built by developers. Some researchers argued that services should be defined by end users, who understand their own needs best. We view that the significance of enabling the user to define his/her personalized services will multiply as our living spaces grow smarter. This paper introduces a novel method called CASPER, which is capable of deriving personalized services from the log of user's activities of daily living. CASPER can generate useful services that even the user may not perceive, mining causality of events in the log. We present the algorithm of CASPER in detail and discuss the result of an experiment which we conducted as a proof of concept.