2000
DOI: 10.1016/s0957-4174(99)00045-7
|View full text |Cite
|
Sign up to set email alerts
|

Validation of intelligent systems: a critical study and a tool

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
11
0
1

Year Published

2003
2003
2019
2019

Publication Types

Select...
5
4
1

Relationship

0
10

Authors

Journals

citations
Cited by 37 publications
(12 citation statements)
references
References 24 publications
0
11
0
1
Order By: Relevance
“…We have also carried out a validation against the problem, since we can count on standard references: the available catalogues with classified spectra, and the human experts that have collaborated in this development (Mosqueira-Rey and Moret-Bonillo, 2000). Table 4 shows a comparison between the three developed automatic classification systems (Experts Systems, Fuzzy Logic and Artificial Neural Networks) and the two human experts.…”
Section: Discussion and Resultsmentioning
confidence: 99%
“…We have also carried out a validation against the problem, since we can count on standard references: the available catalogues with classified spectra, and the human experts that have collaborated in this development (Mosqueira-Rey and Moret-Bonillo, 2000). Table 4 shows a comparison between the three developed automatic classification systems (Experts Systems, Fuzzy Logic and Artificial Neural Networks) and the two human experts.…”
Section: Discussion and Resultsmentioning
confidence: 99%
“…After the test cases are sorted based on GI, the first 25 test cases are selected by the tool. Eighteen (18) of the 20 inserted errors were correctly detected at different iterations and through different test cases. This indicates a failure rate of 10% where MAVERICK was not able to detect an existing error.…”
Section: ) Errors Inserted In Implementation and Knowledge Basementioning
confidence: 96%
“…An external validation consists in determining "whether this is the right model" according to the requirements, while an internal validation consists of checking "whether the model is right", whether it accomplishes what is expected of it. Internal validation is sometimes called model verification [6].…”
Section: Validationmentioning
confidence: 99%