HIGHLIGHTS
- What: Methods: Here the authors propose a self-calibrating random forest (RF) model which can be pre-trained on data from many users, then one-shot calibrated on a new user and_(2) self-calibrate in an unsupervised and autonomous way to adapt to varying arm positions. The authors aim to develop a simple, explainable, robust, parallelisable, and computationally efficient model, which at the same time, can generalise well to arm positions and requires minimal training data from the target user. The authors first prove the inherent superior generalisability of a basic RF model to various arm . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.