A frame work for classifying physiological tremor variants employing principal component analysis

Tremor, the most common form of movement disorder is an often impairment condition which affects a person´s ability to maintain mental and physical stability. There are quite lot of efforts to diagnose, lay a frame work for identification and classification of these disorders. There are expensive, non optimal methods employed to detect physiological and enhanced physiological tremors in neurological patients and still there are continued efforts to benchmark and correctly diagnose them. The main aim of this work was to develop a prototype for tremor data acquisition and to analyse parameters of tremor signal through MEMS sensors and MSP430 Microcontroller in real time. Instrument allows clinicians to noninvasively record precise, human tremor data via wearable MEMS sensor. Two types of tremors variants Physiological tremor and Enhanced Physiological tremor were recorded and evaluated. This framework is proposed from 900 samples under each tremor class and a classification procedure is proposed employing Principal Component Analysis.