Bootstrap aggregating decision tree for motion classification based on a textile-integrated and wearable sensorarray

In this work a system for instant classification of motion patterns is presented. It is based on a non-contact magnetic induction monitoring device, which is textile-integrated, wearable, and able to measure pulse and respiratory activity. The proposed classificator is based on a decision tree algorithm generated by bootstrap aggregating. Its accurate classification performance is validated with the help of a data set comprising five exemplary motion patterns. Furthermore, the dependance of the misclassification error on the input sample length is investigated.