No abstract

No abstract

No abstract

Cognitive radios are intelligent mobile systems with self-adaptivity. Existing frameworks mainly focus on the radio aspects of system designs such as dynamic spectrum access and reduction of bit error rate. However, besides the radio aspects, cognitive radios also leverage other environmental data such as GPS location, system time, and user preferences. The authors propose an adaptive reasoning and learning framework (ARALF) for cognitive radio systems such that this gap between spectrum data and other environment data is bridged. The framework has a novel reasoning and learning mechanism that combines case-based reasoning and rule-based reasoning. Adaptivity and mobility are seamlessly blended into the framework so that users of cognitive radios are completely unaware of unexpected jitters due to environment changes.

No abstract