Individualised Responsible Artificial Intelligence for Home-Based Rehabilitation

. 2020 Dec 22;21(1):2. doi: 10.3390/s21010002

Algorithm 2: Hybrid learning method

$t i m e_{c o m p l e t i o n} \leftarrow R e a d S e n s o r s ()$
$i m p r o v e m e n t \leftarrow P o l i n o m i a l F i t (h i s t o r y) . g e t_r a t e ()$
$b a s e l i n e \leftarrow M o s t F r e q u e n t P r e d i c t i o n ()$
$x g b_{p r e d i c t i o n} \leftarrow X G B o o s t M o d e l . p r e d i c t (t i m e_{c o m p l e t i o n})$
$k n n_{p r e d i c t i o n} \leftarrow K N N M o d e l () . p r e d i c t (t i m e_{c o m p l e t i o n})$
$c l o s e s t, f a r t h e s t \leftarrow C a l c u l a t e E u c l e d i a n D i s t a n c e ($ $x g b_{p r e d i c t i o n}, k n n_{p r e d i c t i o n}, h e a l t h y)$
if $i m p r o v e m e n t = t r u e$ then
$R e T r a i n (c l o s e s t)$ {Closer to Healthy}
else if $i m p r o v e m e n t = f a l s e$ then
$R e T r a i n (f a r t h e s t)$
else
$R e T r a i n (b a s e l i n e)$ {Steady}
end if
$u s e r S t a t e \leftarrow s t a t e C a l c u l a t i o n (s e n s o r D a t a, i m p r o v e m e n t, b a s e l i n e, f i n a l P r e d i c t i o n)$