Improving Outcome Prediction for Traumatic Brain Injury From Imbalanced Datasets Using RUSBoosted Trees on Electroencephalography Spectral Power

Autor: Nor Safira Elaina Mohd Noor, Haidi Ibrahim, Muhammad Hanif Che Lah, Jafri Malin Abdullah

Publikováno v: IEEE Access, Vol 9, Pp 121608-121631 (2021)

Reliable prediction of traumatic brain injury (TBI) outcomes based on machine learning (ML) that is derived from quantitative electroencephalography (EEG) features has renewed interest in recent years. Nevertheless, the approach has suffered from imb

Externí odkaz: https://doaj.org/article/5c60d9455ad14af69f61de1d9c41af8d

Centroid-aware local discriminative metric learning in speaker verification

Autor: Wei Li, Bao-Gang Hu, Joseph Razik, Feiyue Huang, Kekai Sheng, Weiming Dong

Publikováno v: Pattern Recognition
Pattern Recognition, Elsevier, 2017, 72 (c), pp.176-185. ⟨10.1016/j.patcog.2017.07.007⟩
Pattern Recognition, 2017, 72 (c), pp.176-185. ⟨10.1016/j.patcog.2017.07.007⟩

International audience; We propose a new mechanism to pave the way for efficient learning against class-imbalance and improve representation of identity vector (i-vector) in automatic speaker verification (ASV). The insight is to effectively exploit

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c71106fa723582a268d3b24d7963da7
https://hal-univ-tln.archives-ouvertes.fr/hal-01769892/file/LDSV.pdf