Artificial Immune Systems for Anomaly Detection in Ambient Assisted Living Applications

Author(s):  
Sebastian Bersch ◽  
Djamel Azzi ◽  
Rinat Khusainov ◽  
Ifeyinwa E. Achumba

This paper makes a case for the use of Artificial Immune Systems (AIS) in the area of Ambient Assisted Living (AAL) for anomaly detection and long term monitoring. A brief literature review of some of the solutions developed for AAL and the use of AIS in other fields of research is presented. The authors advocate the use of AIS in AAL based on their unique features and their ability to address problems specific to the long term monitoring of people. An improved method for the optimisation of detector generation for AIS, which uses a novel intelligent seeding technique, is presented. The new seeding technique is compared with two other detector seeding methods. The simulation results are presented showing an improvement in the classification accuracy and warranting current and future work.

2020 ◽  
Vol 68 (4) ◽  
pp. 790-803
Author(s):  
Danijela Protić

Introduction/purpose: The artificial immune system is a computational model inspired by the biological or human immune system. Of particular interest in artificial immune systems is the way the human body reacts to new pathogens and adapts to remain immune for a long period after a disease has been combated, which refers to the recognition of known malicious attacks and the way the immune system identifies self-cells not to be reacted to, which refers to the anomaly detection. Methods: Negative selection, positive selection, clonal selection, immune networks, danger theory, and dendritic cell algorithm are presented. Results: A variety of algorithms and models related to artificial immune systems and two classification principles are presented; one based on the detection of a particular attack and the other based on anomaly detection. Conclusion: Artificial immune systems are often used in intrusion detection since they are accurate and fast. Experiments show that the models can be used in both known attack and anomaly detection. Eager machine learning classifiers show better results in the decision, which is an advantage if runtime is not a significant parameter. Dendritic cell and negative selection algorithms show better results for real-time detection.


Author(s):  
Barbara S. Minsker ◽  
Charles Davis ◽  
David Dougherty ◽  
Gus Williams

Kerntechnik ◽  
2018 ◽  
Vol 83 (6) ◽  
pp. 513-522 ◽  
Author(s):  
U. Hampel ◽  
A. Kratzsch ◽  
R. Rachamin ◽  
M. Wagner ◽  
S. Schmidt ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document