• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.257-260
• /
• 2007

In this paper addresses the low-level behavior of fuzzy control and the high-level behavior selector for Autonomous Mobile Robots (AMRs) based on a Fuzzy Artificial Immune Network. The sensing information that comes from ultrasonic sensors is the antigen it, and stimulates antibodies. There are many possible combinations of actions between action-patterns and external situations. The question is how to handle the situations to decide the proper action. We propose a fuzzy artificial immune network to solve the above problem. and the computer simulation for an AMR action selector shows the usefulness of the proposed action selector.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2083-2089
• /
• 2007

In this paper addresses the low-level behavior of fuzzy control and the high-level behavior selector for Autonomous Mobile Robots(AMRs) based on a Fuzzy Artificial Immune Network. The sensing information that comes from ultrasonic sensors is the antigen it, and stimulates antibodies. There are many possible combinations of actions between action-patterns and external situations. The question is how to handle the situations to decide the proper action. We propose a fuzzy artificial immune network to solve the above problem. and the computer simulation for an AMR action selector shows the usefulness of the proposed action selector.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.03a
• /
• pp.373-379
• /
• 1999

This pqer investigates the subject of intrusion detection over networks. Existing network-based IDS's are categorised into three groups and the overall architecture of each group is summarised and assessed. A new methodology to this problem is then presented, which is inspired by the human immune system and based on a novel artificial immune model. The architecture of the model is presented and its characteristics are compared with the requirements of network-based IDS's. The paper concludes that this new approach shows considerable promise for future network-based IDS's.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.229-232
• /
• 2003

나날이 발전하는 인터넷 기반의 네트워크 환경에서 보안의 중요성은 아무리 강조해도 지나치지 않다. 바이러스와 해킹 기술의 발전 속도는 항상 방어자의 능력을 앞지르고 있으며, 공격자들의 능력과 무관한 해킹 툴의 보급은 누구나가 해커가 될 수 있도록 하는데 일조하고 있다. 이제 더 이상 해킹과 바이러스로부터 안전지대는 없다고 해도 과언이 아니다. 이에 본 논문에서는 일정한 환경에서의 침입에 대해 학습을 하여 그 침입을 탐지할 수 있는 디텍터를 생성할 수 있는 알고리즘을 제안한다. 공격 유형의 수에 비해 적은, 그러나 인공 면역계의 T 세포 형성과정인 부정선택을 이용한 학습알고리즘을 기반으로 생성된 디텍터들은 상대적으로 다양한 공격의 침입을 탐지한다. 이의 유효성을 시뮬레이션을 이용하여 확인한다.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.159-166
• /
• 2009

A nature immunity system responds sensitively to an external invasion with various functions in a lot of bodies, besides it there is a function to remember information to have been currently infected. we propose a hybrid model similar to immune system which combine with the antibody which applied genetic algorithm as select antibody and the arbitrary abnormal system call sequence that applied negative selection of a nature immunity system. A proposed model uses an arbitrary abnormal system Kol sequence in order to reduce a positive defect and a negative defect. Data used to experiment are send mail data processed UNM (University of New Maxico). The negative defect that an experiment results proposal model judged system call more abnormal than the existing negative selection to normal system call appeared 0.55% low.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04b
• /
• pp.923-926
• /
• 2002

인공면역시스템을 이용한 침입탐지시스템 개발을 위해 적용한 동적클론선택(Dynamic Clonal Selection) 알고리즘과 그의 문제점을 소개하고 개선된 동적클론선택 알고리즘을 제안한다. 개선된 동적클론선택 알고리즘은 정상행위를 비정상행위로 판단하는 기억 탐지 자들을 제거함으로써 기존에 동적클론선택 알고리즘이 안고 있던 오류를 감소시키는 방안을 제시한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3B
• /
• pp.311-317
• /
• 2009

The traditional network anomaly detection systems execute the threshold-based detection without considering dynamic network environments, which causes false positive and limits an effective resource utilization. To overcome the drawbacks, we present the adaptive network anomaly detection model based on artificial immune system (AIS) in centralized network. AIS is inspired from human immune system that has learning, adaptation and memory. In our proposed model, the interaction between dendritic cell and T-cell of human immune system is adopted. We design the main components, such as central node and router node, and define functions of them. The central node analyzes the anomaly information received from the related router nodes, decides response policy and sends the policy to corresponding nodes. The router node consists of detector module and responder module. The detector module perceives the anomaly depending on learning data and the responder module settles the anomaly according to the policy received from central node. Finally we evaluate the possibility of the proposed detection model through simulation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.72-78
• /
• 2006

It is essential for robot to have the sensing and communication abilities in the swarm robot system. In general, as the number of robot goes on increasing, the limitation of communication capacity and information overflow occur in global communication system. Therefore a local communication is more effective than global one. In this paper, we propose the novel method for determining the optimal communication radius through the analyzing of the information propagation based on local communication. And we also propose a method of cooperative strategies and group behavior of swarm robot based on artificial immune system.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2008.10a
• /
• pp.236-246
• /
• 2008

We consider the Inventory Routing problem(IRP) for the vending machine operating system. An artificial immune system(AIS) is introduced to solve the IRP. The IPR is an rolling wave planning. The previous solution of IRP is one of good initial solution of current IRP. We introduce an Artificial Immune system with memory cell (AISM) which store previous solution in memory cell and use an initial solution for current problem. Experiment results shows that AISM reduced calculations time in relatively less demand uncertainty.

• IE interfaces
• /
• v.20 no.4
• /
• pp.458-468
• /
• 2007

Artificial immune systems (AIS) are one of natural computing inspired by the natural immune system. The fault detection, the pattern recognition, the system control and the optimization are major application area of artificial immune systems. This paper gives a concept of artificial immune systems and useful techniques as like the clonal selection, the immune network theory and the negative selection. A concise survey on the optimization problem based on artificial immune systems is generated. The overall performance of artificial immune systems for the optimization problem is discussed.