What are all possible ways to mitigate the risk of having a bad initial random initialization in the k$-$means algorithm? $($select all that apply$)$

Select $3$ correct answer$($s$)$

Question $12$ options:

use of k$-$means$++$ algorithm

run the algorithm multiple times and keep the one with the highest inertia

manually set the initial centroids

run the algorithm multiple times and keep the one with the lowest inertia

use of k$-$means# algorithm