2021
DOI: 10.1007/s44150-021-00015-8
|View full text |Cite
|
Sign up to set email alerts
|

Error Metrics and Performance Fitness Indicators for Artificial Intelligence and Machine Learning in Engineering and Sciences

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
61
0
4

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 169 publications
(66 citation statements)
references
References 115 publications
1
61
0
4
Order By: Relevance
“…Likewise, another possible application would be to use bibliometric analyzes [28] about the books that have been recovered or that have been most searched so that trend lists can be created on books and offered to recommend books to users. Finally, comment that no measures have been taken about the performance of the application in the sense that is discussed in [29,30] since the recognition functionality is a component external to the application that is simply used to combine it with others and therefore it is not possible to modify their behavior or improve it. However, as future work, it is proposed to use machine learning algorithms to create recommendations for users.…”
Section: Discussionmentioning
confidence: 99%
“…Likewise, another possible application would be to use bibliometric analyzes [28] about the books that have been recovered or that have been most searched so that trend lists can be created on books and offered to recommend books to users. Finally, comment that no measures have been taken about the performance of the application in the sense that is discussed in [29,30] since the recognition functionality is a component external to the application that is simply used to combine it with others and therefore it is not possible to modify their behavior or improve it. However, as future work, it is proposed to use machine learning algorithms to create recommendations for users.…”
Section: Discussionmentioning
confidence: 99%
“…Since this work explores the spalling phenomenon (as if a concrete mixture spalls or not), classification metrics will be adopted. Given the unique derivation of metrics, these constructs often have advantages and disadvantages; thus, it is best to utilize a series of independent metrics [ 73 ]. Three metrics are used: Area under the ROC curve (AUC), Log Loss Error (LLE), and the confusion matrix.…”
Section: Data Collection and Methodologymentioning
confidence: 99%
“…On the other hand, the ACC presents a ratio of the correct predictions to the total number of samples, respectively. All the metrics formulas are described in Table 2 [ 73 ].…”
Section: Data Collection and Methodologymentioning
confidence: 99%
“…ese include 52 specimens from Lu [36], 37 specimens from Ludwig and Nunes [37], 25 specimens from Hameed et al [38], 53 specimens from Hameed et al [39], 12 specimens from Naser and Alavi [40], 12 specimens from Ludwig et al [41], 6 specimens by Nguyen et al [42], 12 specimens by Yaseen et al [43], 19 specimens by Zhang et al [44], 39 specimens by Gong, and 4 specimens by Gandomi et al [45]. It is worth noting that the database contains a wide range of RC deep beams to improve the generativity of the model.…”
Section: Shear Strength Of Rc Deep Beams and Data Collectionmentioning
confidence: 99%