Self-Managing systems are a significant feature inAutonomic Computing which is required for system reliability and performance in a changing environment. The work described in this book chapter is concerned with self-healing systems; systems that can detect and analyse issues with their behavior and performance, and fixe or reconfigure as appropriate. These processes should occur in real-time to restore the desired functionality as soon as possible. The system should ideally maintain functionality during the healing process which occurs at runtime. Adaptive neural networks are proposed as a solution to some of these challenges; monitoring the system and environment, mapping a suitable solution and adapting the system accordingly. A novel application of a modified Pipelined Recurrent Neural Network is proposed in this chapter with experiments aimed to assess its applicability to online.
CITATION STYLE
Ai-Jumeily, D., Al-Zawi, M., Hussain, A. J., & Dobre, C. (2014). Adaptive pipelined neural network structure in self-aware internet of things. Studies in Computational Intelligence, 546, 111–136. https://doi.org/10.1007/978-3-319-05029-4_5
Mendeley helps you to discover research relevant for your work.