Linguistic description of human body posture using fuzzy logic and several levels of abstraction

A remarkable characteristic of the human brain is its capability to create abstract models of the real world. Natural language is the main tool that we use to manage these abstractions. In this paper we describe a measurement device that represents the data of sensors using concepts defined at different levels of abstraction and produces its output in natural language. The ultimate goal of this work is to investigate possibilities of creating instruments capable of communicating their results to human beings using Natural Language. We present an experimental prototype that uses accelerometers to obtain information about the posture of the user. We use two well known objects: the pendulum and the Rubik´s cube, to establish a sequence of metaphors that end, at the highest level of abstraction, with a linguistic description of the temporal sequence of the user postures.