• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권5호
• /
• pp.2732-2753
• /
• 2019

With the application of wireless sensor networks in the fields of ecological observation, defense military, architecture and urban management etc., the security problem is becoming more and more serious. Characteristics and constraint conditions of wireless sensor networks such as computing power, storage space and battery have brought huge challenges to protection research. Inspired by the danger theory in biological immune system, this paper proposes an intrusion detection model for wireless sensor networks. The model abstracts expressions of antigens and antibodies in wireless sensor networks, defines meanings and functions of danger signals and danger areas, and expounds the process of intrusion detection based on the danger theory. The model realizes the distributed deployment, and there is no need to arrange an instance at each sensor node. In addition, sensor nodes trigger danger signals according to their own environmental information, and do not need to communicate with other nodes, which saves resources. When danger is perceived, the model acquires the global knowledge through node cooperation, and can perform more accurate real-time intrusion detection. In this paper, the performance of the model is analyzed including complexity and efficiency, and experimental results show that the model has good detection performance and reduces energy consumption.

• ETRI Journal
• /
• 제44권2호
• /
• pp.300-312
• /
• 2022

Recently, public safety services have attracted significant attention for their ability to protect people from crimes. Rapid detection of dangerous situations (that is, abnormal situations where someone may be harmed or killed) is required in public safety services to reduce the time required to respond to such situations. This study proposes a novel danger detection technology based on multimodal data, which includes data from multiple sensors (for example, accelerometer, gyroscope, heart rate, air pressure, and global positioning system sensors), and multilog data, which includes contextual logs of humans and places (for example, contextual logs of human activities and crime-ridden districts) over time. To recognize human activity (for example, walk, sit, and punch), the proposed technology uses multimodal data analysis with an attitude heading reference system and long short-term memory. The proposed technology also includes multilog data analysis for detecting whether recognized activities of humans are dangerous. The proposed danger detection technology will benefit public safety services by improving danger detection capabilities.

• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.239-251
• /
• 2018

In existing cloud services, information security and privacy concerns have been worried, and have become one of the major factors that hinder the popularization and promotion of cloud computing. As the cloud computing infrastructure, the security of virtual machine systems is very important. This paper presents an immune-inspired intrusion detection model in virtual machines of cloud computing environment, denoted I-VMIDS, to ensure the safety of user-level applications in client virtual machines. The model extracts system call sequences of programs, abstracts them into antigens, fuses environmental information of client virtual machines into danger signals, and implements intrusion detection by immune mechanisms. The model is capable of detecting attacks on processes which are statically tampered, and is able to detect attacks on processes which are dynamically running. Therefore, the model supports high real time. During the detection process, the model introduces information monitoring mechanism to supervise intrusion detection program, which ensures the authenticity of the test data. Experimental results show that the model does not bring much spending to the virtual machine system, and achieves good detection performance. It is feasible to apply I-VMIDS to the cloud computing platform.

• 한국정보통신학회논문지
• /
• 제19권3호
• /
• pp.623-628
• /
• 2015

본 논문에서는 자전거 사고를 방지하기 위한 어플리케이션을 구현하였으며, 이를 위해 도플러 레이더 센서를 이용하였다. 도플러 레이더 센서는 접근하는 위험 물체를 감지하며, 어플리케이션은 위험 판단 알고리즘을 통해 사용자에게 경고 알람 서비스를 제공한다. 위험 판단 알고리즘은 감지한 전방 물체의 접근 상태와 도플러 주파수를 이용한 상대 속도를 비교하여 위험 상황을 판단한다. 또한 사고가 발생할 경우 설정된 연락처로 SMS를 발송하여 사용자의 위급 상황을 전달한다. 실험 결과 정상적으로 접근 상태와 속도를 파악하여 위험 판단을 내렸으며, 사고 발생이라 가정했을 시 설정된 연락처로 SMS 발송하는 것을 확인할 수 있었다.

• 대한조선학회지
• /
• 제11권1호
• /
• pp.27-34
• /
• 1974

This study is aimed at a validation of the vigilance simulation model which was proposed earlier (2). The model estimates a perceived danger value, an alertness level and the probability of detection at a given elapsed time of vigilance. Twenty-nine male and seven female subjects were given a simple task. They were asked to detect a number(four numbers out of six digits in the telephone directory which have the probability of occurrence in the range of 0.0010-0.0018) in six different experimental conditions, for periods of two to three hours. Analysis of the experiments showed that although the mean detection rate varied slightly in two hours, the within-subject variance and the number of cyclic performance fluctuations increased significantly. A primal factor that affects the performance seems to be the frequency of target occurrence. By curve fitting, the relation between the probability of detection and the percentages of danger event occurrence was derived; $y=0.50(1-{\varepsilon}^{-50x^2})+0.39$. Assuming the equation represents the normal detection rate(100% performance), the Relative Vigilance Performance Rating was calculated. This rating method could be a useful criterion in selecting and training of the vigilance personnel. The results show that the simulation model is a good estimator of human a performance when the probability of danger occurrence is greater than 0.0015; it gives a good reference for improving the vigilance system. Suggestions are made that (1) the validity of proposed functional equations over the extended range of danger probability be studied, (2) an analysis of the cyclic fluctuations of the alertness level be accomplished, and (3) the cost functions of detection reliability be included in any future model.

• Journal of Multimedia Information System
• /
• 제7권3호
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• 선박안전
• /
• 통권38호
• /
• pp.69-77
• /
• 2015

If we don't know the intention of altering course of a target ship when being in a head-on or a crossing situation, we may be confused about our decision making to change our course for collision avoidance and be in a danger of collision. In order to solve these problems, we need to develop an automatic detection system on altering course of a target ship for efficient collision avoidance. In this paper, we proposed an early detection system on altering course of a target ship using the steering wheel signal. This system will contribute to the reduction of collision accidents and also be used to the VTS system and the analysis of marine accidents.

• 선박안전
• /
• 통권36호
• /
• pp.71-78
• /
• 2014

If we don't know the intention of altering course of a target ship when being in a head-on or a crossing situation, we may be confused about our decision making to change our course for collision avoidance and be in a danger of collision. In order to solve these problems, we need to develop an automatic detection system on altering course of a target ship for efficient collision avoidance. In this paper, we proposed an early detection system on altering course of a target ship using the steering wheel signal. This system will contribute to the reduction of collision accidents and also be used to the VTS system and the analysis of marine accidents.

• 한국군사과학기술학회지
• /
• 제8권2호
• /
• pp.14-21
• /
• 2005

This paper describes the system for detecting the tank crew's(loader's) hand, arm, head and the upper half of the body in a danger area between the turret ceiling and the upper breech mechanism by computer vision-based method. This system informs danger of pressed to death to gunner and commander for the safety of operating mission. The camera mounted ort the top portion of the turret ceiling. The system sets search moving object from this image and detects by using change of image, laplacian operator and clustering algorithm in this area. It alarms the tank crews when it's judged that dangerous situation for operating mission. The result In this experiment shows that the detection rate maintains in $81{\sim}98$ percents.

• 디지털콘텐츠학회 논문지
• /
• 제14권4호
• /
• pp.455-462
• /
• 2013

CCTV를 이용하여 획득한 영상 내에서 다중 객체의 위험한 행위를 판단하여 사전에 미리 경고 및 긴급대책을 세워주는 감지 시스템을 제안한다. 위험한 행위의 판단여부를 위해 관심지역 및 관심지역 내에 위험지역을 설정한 후, 위험 행동 객체를 검출하여 객체의 위험지역 침범 범위에 따라 안전, 경고, 긴급 등의 위험도를 판단한다. 특히 본 연구는 위험 행동 중 교량에서 투신하는 행위를 감지하는 것을 목표로 하며 기존의 연구에서 단일객체의 행동검출에만 제한했던 연구를 여러 보행자 속에서 투신 행동하는 객체를 감지하는 것까지 확대하여 구현한다. 한 객체의 위험지역 침범의 정도에 따라 안전, 경고 및 긴급 상태로 분류하고 상황에 따라 긴급 상태로 판단되면 통합관제 센터에 즉시 알려 위험행위를 사전에 예방 할 수 있도록 한다.