A real-time system based on artificial neural networks (ANNs) for time series prediction is proposed. For each movement the prediction errors are used both to train the ANNs and to estimate a measure of the unlikelihood of the specific gesture occurrence. The first repetition of each gesture trains the related ANNs bank and the current motion is recognized after a few successive repetitions. Neither a priori assumptions nor signal pre-processing is performed (blindness). The training is performed at the beginning and can be repeated during the running (adaptability). Each procedure is strictly physically realizable (real-time feasibility). Four gestures performed by three healthy volunteers are selected by a set of upper limb motor tasks contained in the rehabilitation scale known as Wolf motor function test (WMFT). Two accelerometers placed on the upper arm and on the forearm respectively, constitute the sensors set. Even in very challenging test settings, the proposed method shows a correct recognition rate higher than 83%.
A real-time system based on artificial neural networks (ANNs) for time series prediction is proposed. For each movement the prediction errors are used both to train the ANNs and to estimate a measure of the unlikelihood of the specific gesture occurrence. The first repetition of each gesture trains the related ANNs bank and the current motion is recognized after a few successive repetitions. Neither a priori assumptions nor signal pre-processing is performed (blindness). The training is performed at the beginning and can be repeated during the running (adaptability). Each procedure is strictly physically realizable (real-time feasibility). Four gestures performed by three healthy volunteers are selected by a set of upper limb motor tasks contained in the rehabilitation scale known as Wolf motor function test (WMFT). Two accelerometers placed on the upper arm and on the forearm respectively, constitute the sensors set. Even in very challenging test settings, the proposed method shows a correct recognition rate higher than 83%.
Gneo, M., Muscillo, R., Goffredo, M., Conforto, S., Schmid, M., D'Alessio, T. (2009). Real-time adaptive neural predictors for upper limb gestures blind recognition. In 11th International Congress of the IUPESM - Medical Physics and Biomedical Engineering World Congress (pp.536-539) [10.1007/978-3-642-03889-1-144].
Real-time adaptive neural predictors for upper limb gestures blind recognition
MUSCILLO, ROSSANA;GOFFREDO, MICHELA;CONFORTO, SILVIA;SCHMID, Maurizio;D'ALESSIO, Tommaso
2009-01-01
Abstract
A real-time system based on artificial neural networks (ANNs) for time series prediction is proposed. For each movement the prediction errors are used both to train the ANNs and to estimate a measure of the unlikelihood of the specific gesture occurrence. The first repetition of each gesture trains the related ANNs bank and the current motion is recognized after a few successive repetitions. Neither a priori assumptions nor signal pre-processing is performed (blindness). The training is performed at the beginning and can be repeated during the running (adaptability). Each procedure is strictly physically realizable (real-time feasibility). Four gestures performed by three healthy volunteers are selected by a set of upper limb motor tasks contained in the rehabilitation scale known as Wolf motor function test (WMFT). Two accelerometers placed on the upper arm and on the forearm respectively, constitute the sensors set. Even in very challenging test settings, the proposed method shows a correct recognition rate higher than 83%.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
