| dc.creator |
ÖZTÜRK, Muhammed Maruf |
|
| dc.date |
2022-01-01T00:00:00Z |
|
| dc.identifier |
ed63bb30-8ddf-465d-b74b-5b498ef6ab9c |
|
| dc.identifier |
10.1080/0952813x.2021.1871664 |
|
| dc.identifier |
https://avesis.sdu.edu.tr/publication/details/ed63bb30-8ddf-465d-b74b-5b498ef6ab9c/oai |
|
| dc.description |
Software effort estimation (SEE) is a software engineering problem that requires robust predictive models. To establish robust models, the most feasible configuration of hyperparameters of regression methods is searched. Although only a few works, which include hyperparameter optimisation (HO), have been done so far for SEE, there is not any comprehensive study including deep learning models. In this study, a feed-forward deep neural network algorithm (FFDNN) is proposed for software effort estimation. The algorithm relies on a binary-search-based method for finding hyperparameters. FFDNN outperforms five comparison algorithms in the experiment that uses two performance parameters. The results of the study suggest that: 1) Employing traditional methods such as grid and random search increases tuning time remarkably. Instead, sophisticated parameter search methods compatible with the structure of regression method should be developed; 2) The performance of SEE is enhanced when associated hyperparameter search method is devised according to the essentials of chosen deep learning approach; 3) Deep learning models achieve in competitive CPU time compared to the tree-based regression methods such as CART_DE8. |
|
| dc.language |
eng |
|
| dc.rights |
info:eu-repo/semantics/closedAccess |
|
| dc.title |
A tuned feed-forward deep neural network algorithm for effort estimation |
|
| dc.type |
info:eu-repo/semantics/article |
|