Learning using an artificial immune system
Journal of Network and Computer Applications - Special issue on intelligent systems: design and applications. Part 2
Communications of the ACM
ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Embryonics: Artificial Cells Driven by Artificial DNA
ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Biowatch: A Giant Electronic Bio-Inspired Watch
EH '01 Proceedings of the The 3rd NASA/DoD Workshop on Evolvable Hardware
Self-Nonself Discrimination in a Computer
SP '94 Proceedings of the 1994 IEEE Symposium on Security and Privacy
A Sense of Self for Unix Processes
SP '96 Proceedings of the 1996 IEEE Symposium on Security and Privacy
IEEE Transactions on Evolutionary Computation
A comparative study on self-tolerant strategies for hardware immune systems
ICARIS'06 Proceedings of the 5th international conference on Artificial Immune Systems
An adaptive self-tolerant algorithm for hardware immune system
ICES'05 Proceedings of the 6th international conference on Evolvable Systems: from Biology to Hardware
| Hi-index | 0.00 |
A simple robot control system is used to demonstrate bioinspired fault tolerance techniques; a multi-layered hardware immune system is used for fault detection and an embryonic array for fault avoidance. The acquired layer of the immune system monitors system behaviour for unusual activity (normal behaviour is learnt during an unsupervised teaching period). An non-learning innate layer is then employed to localise the fault if possible. The embryonic array allows simple, robust reconfiguration to avoid the fault; as many faults as spare cells can be accommodated. The complete system, including the learning algorithm, is implemented on a Virtex FPGA. Results showing the appropriate response to different types of faults are given.