2015 15th International Conference on Intelligent Systems Design and Applications (ISDA) 2015
DOI: 10.1109/isda.2015.7489211
|View full text |Cite
|
Sign up to set email alerts
|

Determination of an optimal feature selection method based on maximum Shapley value

Abstract: We propose a novel feature selection methodology based on game theory. In this context, the players are the various feature selection methods and the characteristic function (payoff) represents the feature ranking agreement within a coalition of players. The Shapley value assigned to each feature selection method is computed and ranked from higher to lower. The best feature selection method is identified as the one having the highest Shapley value. Finally, we have performed a score fusion scheme using the Bor… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
8
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(8 citation statements)
references
References 13 publications
0
8
0
Order By: Relevance
“…The forward elimination method achieved the highest accuracy among the experimental comparison algorithms. In 2016, Mokdad et al designed a feature selection algorithm structure derived from the Shapley value [44]. First, the rank of N groups of features was obtained by N feature selection algorithms, and then the Borda Coun method was adopted to determine the ultimate feature rank.…”
Section: Related Workmentioning
confidence: 99%
“…The forward elimination method achieved the highest accuracy among the experimental comparison algorithms. In 2016, Mokdad et al designed a feature selection algorithm structure derived from the Shapley value [44]. First, the rank of N groups of features was obtained by N feature selection algorithms, and then the Borda Coun method was adopted to determine the ultimate feature rank.…”
Section: Related Workmentioning
confidence: 99%
“…Yang et al [27] used SHAP to provide an extensive analysis of the relationship between EEG features to different annotation techniques for affect recognition. Shapley values can also be used in place of feature selection metrics [28] to determine the importance of individual features and data samples. So far, few studies compare cross-dataset findings using highlevel explanations.…”
Section: Explainable Affect Recognitionmentioning
confidence: 99%
“…They presented an approach that could directly provide the ranking order of input and output variables separately. Mokdad et al (2016) proposed an optimal feature selection method based on the maximum Shapley value, and validated it by conducting experiments for a classification task based on an SVM classifier. Hur et al (2017) applied the Shapley value with random forest to analyze the influence of variables and list the priority of variables that affected classification accuracy.…”
Section: Measuring Variable Impacts Using the Shapley Valuementioning
confidence: 99%