2016
DOI: 10.1016/j.trac.2016.04.021
|View full text |Cite
|
Sign up to set email alerts
|

Quality performance metrics in multivariate classification methods for qualitative analysis

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
27
0
1

Year Published

2017
2017
2023
2023

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 102 publications
(29 citation statements)
references
References 34 publications
1
27
0
1
Order By: Relevance
“…Classification performance was evaluated on the basis of a set of indices. The most common parameters are summarized next although other possibilities exist: Precision of a class represents the capability of a classification model to not include samples of other classes in the considered class (it is the ratio between the samples of the g ‐th class correctly classified and the total number of samples assigned to that class). Sensitivity of a class is the ability of the model to correctly recognize samples belonging to that class. Specificity of a class describes the ability of the model to reject samples of all other classes in the considered class. Accuracy is the ratio of correctly assigned samples (it can be defined for a class alone or for the overall model considering the correctly assigned samples in all classes) over the total number of samples. Class non‐error rate (NER) is the average of the specificity and sensitivity of the class, whereas the model NER is the average of all class sensitivities. Class error rate (ER) or, just class error, is the complement of the NER (ER = 1‐NER). …”
Section: Methodssupporting
confidence: 80%
“…Classification performance was evaluated on the basis of a set of indices. The most common parameters are summarized next although other possibilities exist: Precision of a class represents the capability of a classification model to not include samples of other classes in the considered class (it is the ratio between the samples of the g ‐th class correctly classified and the total number of samples assigned to that class). Sensitivity of a class is the ability of the model to correctly recognize samples belonging to that class. Specificity of a class describes the ability of the model to reject samples of all other classes in the considered class. Accuracy is the ratio of correctly assigned samples (it can be defined for a class alone or for the overall model considering the correctly assigned samples in all classes) over the total number of samples. Class non‐error rate (NER) is the average of the specificity and sensitivity of the class, whereas the model NER is the average of all class sensitivities. Class error rate (ER) or, just class error, is the complement of the NER (ER = 1‐NER). …”
Section: Methodssupporting
confidence: 80%
“…To quantify the classification results, we evaluated multiple measures including the individual class accuracy, individual class precision, overall accuracy, balanced accuracy, and balanced precision ( Cuadros-Rodriguez et al, 2016 ) based on the predicted and diagnosis labels. Different measures reflect the results from different angles.…”
Section: Methodsmentioning
confidence: 99%
“…To evaluate the classification performance for each method, we computed the accuracy, sensitivity, and specificity according to the predicted label of the testing data [31], and then recorded the mean and standard deviation of each metric across different runs for a comprehensive comparison between different methods. Furthermore, we also performed a two-sample t-test on the classification accuracy to compare the performance between our CNN fusion method and any single-modal method.…”
Section: Methodsmentioning
confidence: 99%