Research Article
Detecting Shilling Attacks with Automatic Features from Multiple Views
Algorithm 2
Feature extraction.
| Input:Setmd, Setfs, Setas, DRg, SDAEopts, crate | |
| output: fea | |
| 1for each md∈Setmd do | |
| 2for each fs%∈Setfs do | |
| 3for each as%∈Setas do | |
| 4DRa = getAttackProfiles(DRg, md, fs%, as%) | |
| 5 | |
| 6end for | |
| 7end for | |
| 8end for | |
| 9 [R, P, M]=preprocessingData(DR) | |
| 10SDAE=SDAESetup(SDAEopts) | |
| 11Fea_R=SDAElearn(SDAE,R,crate) | |
| 12Fea_P=SDAElearn(SDAE,P,crate) | |
| 13Fea_M=SDAElearn(SDAE,M,crate) | |
| 14Fea_SDAE=FeaUnion(Fea_R,Fea_P,Fea_M) | |
| 15Fea=PCA(Fea_SDAE) | |
| 16return Fea, DR |