Dear Edy Budiman Ummul Hairah
I read your article
Comparison of linear and vector data normalization techniques in decision making for learning quota assistance
My comments
1- In page 1 you say “It should also be noted that if the normalization technique is not suitable for the decision problem or the method chosen, the best decision solution may be missed”
And how do you know if the normalization technique is suitable or not for the method chosen?
2- I believe that norm methods don’t scale values ate the same magnitude, as you say, all values are different, however, what is preserved is the original proportion in each criterion. And what is the recommended solution? As I understand that is just what you are looking for.
3- In page 2 “there will be an explosion of criteria and alternatives and scaling them into dimensionally more difficult units”
Why there should be a relation between normalization and number of criteria and alternatives?
4- On page 6 “The ability to remove scales is a basic rule that when normalizing identical data with different units or scales, the same result is obtained”.
Remove scales? Removing from where?
Same result is obtained? Are you sure? Normally, this is not the case
5- In page 6, “it is necessary to check the symmetry of the normalized values when comparing the cost and benefit criteria”
Could you please explain the meaning of this? What symmetry?
6 – Page 6 “A292 is the best ranking alternative to vector normalization while A292 is the best alternative to linear normalization”
This is incorrect as per figure 5.
A292 is the second-best alternative for linear and the eighth for vector
7- “To keep the maximum initial information concerning the initial attribute values and other criterion values, it is necessary to check the symmetry of the normalized values when comparing the cost and benefit criteria”
Could you explain this?
These are my comments
Hope they can help you
Nolberto Munier
- Badges
- Science topic
- Similar topics
- Mathematics