Advances in artificial immune systems

Dasgupta,

doi:10.1109/ci-m.2006.248056

Cited by 125 publications

(153 citation statements)

References 4 publications

Supporting

Mentioning

150

Contrasting

Unclassified

Order By: Relevance

“…Population-based algorithms apply negative selection and clonal selection theory, while network-based algorithms apply the concept of immune network theory [19]. One of the reasons to apply the AIS rather than other algorithms is that it needs only positive examples, and the patterns learned can be clearly examined.…”

Section: Related Studiesmentioning

confidence: 99%

Negative selection algorithm for dengue outbreak detection

Mousavi

Bakar

Zainudin

et al. 2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:Dengue is a critical communicable and vector-borne disease and is becoming a serious concern in Malaysia. It is important to have an early detection system that could provide immediate action, such as the control of dengue transmission at a specific location. However, the available strategy and action may give long-term effects to the community since inaccurate decision making or prediction may lead to other circumstances. Moreover, the need to have a system that can detect the outbreak in a reasonable amount of time is critical. In this study, a nature-inspired computing technique, the artificial immune system (AIS), is used for dengue outbreak detection. One of the variants of the AIS algorithms, called the negative selection algorithm (NSA), has been widely applied in anomaly detection and fault detection. This study aims to employ the NSA for dengue outbreak detection.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Negative selection algorithm for dengue outbreak detection

Mousavi

Bakar

Zainudin

et al. 2013

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…For action selection, the IAIN controller may select one output action, using arbitration, but may not combine more than one action to achieve the desired result. Turn left with angle θ A 2 Turn right with angle θ A 3 Go straight forward A 4 Go straight backward During simulation, each robot has a state that is considered to be a B-cell and its behaviors are considered to be the antibodies. The main objective of the robot-team is to deliver the rod to the target area, within Rτ distance range, and as a result any behavior that leads otherwise needs to be avoided as much as possible.…”

Section: Modeling the Primary Immune System Memory Responsementioning

confidence: 99%

“…Take applications on the field of robotics for example. Dasgupta and Nino, in their book, surveyed robotics research inspired by Artificial Immune Networks up to 2009 [3]. Among research done on autonomous robots there were a few robots that utilized a mechanism called Immunoid to collect various amount of garbage from a constantly changing environment [4].…”

Section: Fig 1 Generation Of Memory Cells In the Artificialmentioning

confidence: 99%

Novel Implementation of the Artificial Immune System Memory

Meshref¹

2016

IJCA

View full text Add to dashboard Cite

During the past decade, there were many approaches that made use of the concepts of artificial immune system. By reviewing the literature, it was found that the research on the artificial immune memory design was sparse and only a few researchers attempted to embark upon issues related to it. This proposed research introduces a novel model that serves as an artificial memory for the artificial immune system. The proposed research design approaches this goal by modeling the primary immune memory response using an idiotopic artificial immune network. As well, the secondary immune memory response is modeled by using a hetero-associative memory network. The two models were tested and the results showed considerable resemblance with the primary and secondary immune memory system behavior. The testing results showed that the developed memory models achieved 100% recognition rates for the tested patterns. Even after adding noise to the input data, the overall memory model showed acceptable recognition rate of 87.5% for 25% noise, and 68.7% recognition rate for 50% noise. Therefore, the designed primary and secondary artificial immune memory model achieve significant potential in representing the behavior of the original immune system memory.

show abstract

“…doi:10.1016/j.eswa.2010.07.087 comparing to a newly activated B-cell (Carter, 2000). The novel characteristics of the immune system have inspired the development of artificial immune systems for various applications (Dasgupta, 2006;Hart & Timmis, 2008). The major application areas include data mining (Freitas & Timmis, 2007), pattern recognition (Watkins, Timmis, & Boggess, 2004;Zhong, Zhang, Gong, & Li, 2007), fault diagnosis (Dasgupta, KrishnaKumar, Wong, & Berry, 2004;Taylor & Corne, 2003), and medical classification problems (Polat, Gunes, & Tosun, 2006).…”

Section: Introductionmentioning

confidence: 99%