A context-sensitive incremental learning paradigm of an ubiquitous multimodal multimedia computing system

In this paper, we proposed a context-sensitive incremental learning paradigm of an ubiquitous multimodal multimedia computing system. An ubiquitous computing environment supports a busy and mobile user´s need of being able to work on his task anytime and anywhere he wants. Along with user´s data (his profile, task, and application registry) the machine-acquired intelligence needs to be transported as well in order that the user could continue working on an intelligent environment. Machine intelligence is acquired through incremental learning. In a context-sensitive environment that has a rich selection of modalities and media for data input and output, an intelligent computing system could determine the I/O devices appropriate for the user´s setting after considering the user´s location, the noise level in the environment, and the presence or absence of other people in the vicinity. Every new setting (pre-condition scenario) produces a new I/O devices configuration (post-condition scenario) suited for the setting; each new scenario knowledge gets stored onto knowledge database. Overtime, the machine would have enough knowledge to deal with whatever context scenario that comes up.