• Journal of Preventive Medicine and Public Health
• /
• v.41 no.4
• /
• pp.214-218
• /
• 2008

Bioterrorism events have worldwide impacts, not only in terms of security and public health policy, but also in other related sectors. Many countries, including Korea, have set up new administrative and operational structures and adapted their preparedness and response plans in order to deal with new kinds of threats. Korea has dual surveillance systems for the early detection of bioterrorism. The first is syndromic surveillance that typically monitors non-specific clinical information that may indicate possible bioterrorism-associated diseases before specific diagnoses are made. The other is infectious disease specialist network that diagnoses and responds to specific illnesses caused by intentional release of biologic agents. Infectious disease physicians, clinical microbiologists, and infection control professionals play critical and complementary roles in these networks. Infectious disease specialists should develop practical and realistic response plans for their institutions in partnership with local and state health departments, in preparation for a real or suspected bioterrorism attack.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39B no.4
• /
• pp.228-233
• /
• 2014

In recent general social surveillance systems, secure access control mechanism is needed. ONVIF establishes standards for interoperability between cameras and defines web service framework for it. In this paper we present an efficient attribute based access control mechanism for surveillance system networks which follow the ONVIF standards. It accommodates web service information security techniques and provides efficient secure access control.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.11 no.1
• /
• pp.5-14
• /
• 2008

In this paper, we propose operational concepts and technology requirements for guard and surveillance robots in military field. After surveying on current trend of guard robots, we present an operational scenario and technology requirements. To begin with, we discriminate the use of fixed type guard robots(fixed robots) and mobile guard and surveillance robots(mobile robots). Fixed robots are used for substituting daily guard by human soldier. In contrast, mobile robots are used for compensating shadow area where not to be covered by fixed type robots. To be specific, mobile robots adopt communication relays to extend operational range and sensor networks to collecting information. In addition, we present technology requirements composed of wireless communication system, platform, sensor nodes, unmanned driving technology, power supply system and IFF etc. In conclusion, in order to maximize co-operational functionality, fixed robots and mobile robots should be tightly related.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.8
• /
• pp.810-816
• /
• 2007

A security robot system named EGIS-SR is a mobile security robot through one of the new growth engine project in robotic industries. It allows home surveillance through an autonomous mobile platform using onboard cameras and wireless security sensors. EGIS-SR has many sensors to allow autonomous navigation, hierarchical control architecture to handle lots of situations in monitoring home surveillance and mighty networks to achieve unmanned security services. EGIS-SR is tightly coupled with a networked security environment, where the information of the robot is remotely connected with the remote cockpit and patrol man. It achieved an intelligent unmanned security service. The robot is a two-wheeled mobile robot and has casters and suspension to overcome a doorsill. The dynamic motion is verified through $ADAMS^{TM}$ simulation. For the main controller, PXA270 based hardware platform based on linux kernel 2.6 is developed. In the linux platform, data handling for various sensors and the localization algorithm are performed. Also, a local path planning algorithm for object avoidance with ultrasonic sensors and localization using $StarGazer^{TM}$ is developed. Finally, for the automatic charging, a docking algorithm with infrared ray system is implemented.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2003.11a
• /
• pp.406-410
• /
• 2003

DUPIC Fuel Development Facility(DFDF) is the facility to fabricate CANDU-type fuel from spent PWR fuel material without any separation of fissile elements and fission products. Unattended continuous surveillance systems for safeguards of nuclear facility result in large amounts of image and radiation data, which require much time and effort to inspect. Therefore, it is necessary to develop system that automatically pinpoints and diagnoses the anomalies from data. In this regards, this paper presents a novel concept of the continuous surveillance system that integrates visual image and radiation data by the use of neural networks. This surveillance system is operating for safeguards of the DFDF in KAERI.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• 한국정보통신설비학회:학술대회논문집
• /
• 2008.08a
• /
• pp.177-180
• /
• 2008

There are many application areas of sensor networks, such as surveillance, hospital monitoring, and home network. These are dependent on the secure operation of networks, and will have serious outcome if the networks is injured. An adversary can inject false data into the network through the compromising node. Ye et al. proposed a statistical en-route filtering scheme (SEF) to detect such false data during forwarding process. In this scheme, it is important that the choice of the threshold value since it trades off security and overhead. This paper presents an adaptive threshold value determining method in the SEF using fuzzy logic. The fuzzy logic determines a security distance value by considering the situation of the network. The Sensor network is divided into several areas by the security distance value, it can each area to uses the different threshold value. The fuzzy based threshold value can reduce the energy consumption in transmitting.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2006.07a
• /
• pp.367-367
• /
• 2006

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3991-4007
• /
• 2022

In the public healthcare, a computational system that can automatically and efficiently detect and classify falls from a video sequence has significant potential. With the advancement of deep learning, which can extract temporal and spatial information, has become more widespread. However, traditional 3D CNNs that usually adopt shallow networks cannot obtain higher recognition accuracy than deeper networks. Additionally, some experiences of neural network show that the problem of gradient explosions occurs with increasing the network layers. As a result, an enhanced three-dimensional ResNet-based method for fall detection (3D-ERes-FD) is proposed to directly extract spatio-temporal features to address these issues. In our method, a 50-layer 3D residual network is used to deepen the network for improving fall recognition accuracy. Furthermore, enhanced residual units with four convolutional layers are developed to efficiently reduce the number of parameters and increase the depth of the network. According to the experimental results, the proposed method outperformed several state-of-the-art methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.10B
• /
• pp.894-903
• /
• 2008

The position of sensors generally affects coverage, communication costs, and resource management of surveillance sensor networks. Thus we are required to place a sensor in the best location. However, it is difficult to consider that terrain and climate factors influencing sensors when sensor nodes are deployed in the real world, such as a mountain area or a downtown area. We therefore require a sensor deployment method for detecting effectively targets of interest in terms of surveillance area coverage in such environment. Thus in this paper, we analyze various environmental factors related to sensor deployment, and quantify these factors to use when we deploy sensors. By considering these quantified factors, we propose a practical and effective method for deploying sensors in terms of sensing coverage. We also demonstrate the propriety of the proposed method through implementing a sensor deployment management system according to the method.