Commissariat &#xc0; L'&#xc9;nergie Atomique Et Aux &#xc9;nergies Alternatives

Movea

Florence Gris

Pierre Jallon

A device identifying a cyclic movement type of a physical system from a set of possible cyclic movements types includes: a movement sensor providing an observation data sequence concerning the physical system; a storage storing at least one statistical hidden-state Markov model; and a computer programmed to analyze the observation data sequence and select one cyclic movement type based on the stored statistical model. The storage includes least one statistical hidden-state Markov model for each possible cyclic movement type and the computer is programmed to analyze compatibility of the observation data sequence with each possible cyclic movement type based on the statistical model associated with this cyclic movement type. The computer is further programmed to provide a sequence of hidden states of the statistical model associated with the selected cyclic movement type, based on the observation data sequence and the statistical model associated with the selected cyclic movement type.

Device and method for identifying a cyclic movement and corresponding computer program

A method for configuring a device for detecting a situation from a set of situations where a physical system comprises the following steps: reception of a learning sequence corresponding to a given situation of the physical system; determination of parameters of a hidden-state Markov statistical model recorded in the detection device and relating to the given situation, on the basis of a prior initialization of these parameters. The prior initialization comprises the following steps: determination of a plurality of probability distributions from the learning sequence; distribution of the probability distributions between the various hidden states of the statistical model in question by global optimization of a function of adaptation of these probability distributions to the various hidden states and to impossible transition constraints; and initialization of the parameters of the statistical model in question using given representative probability distributions for each hidden state of the statistical model in question.

Growing community of inventors

Tullins, France

Florence Gris