Neural network based smart accelerometers for use in telecare medicine.
Sensors that perform the task of measuring the physical quantity of acceleration are discussed. Applications for such measurements and thus of accelerometers, range from early diagnosis procedures for tremor-related diseases (e.g. Parkinsons) to monitoring daily patterns of patient activity using telemetry systems. The system-level requirements in such applications are considered and two novel neural network transducer designs developed by the authors are presented which aim to satisfy such requirements. Both designs are based on a micromachined sensing element with capacitive signal pick-off. The first is an open-loop design utilising a direct inverse control strategy, whilst the second is a closed-loop design where electrostatic actuation is used as a form of feedback. Both transducers are nonlinearly compensated, capable of self-test and provide digital outputs.
Bibliogr. 27 poz.