Motif Mining and Unsupervised Representation Learning for BirdCLEF 2022

Autor: Miyaguchi, Anthony, Yu, Jiangyue, Cheungvivatpant, Bryan, Dudley, Dakota, Swain, Aniketh

Publikováno v: CEUR-WS Vol-3180 (2022) 2159-2167

We build a classification model for the BirdCLEF 2022 challenge using unsupervised methods. We implement an unsupervised representation of the training dataset using a triplet loss on spectrogram representation of audio motifs. Our best model perform

Externí odkaz: http://arxiv.org/abs/2206.04805

Identifying and characterizing disease subpopulations that most benefit from polygenic risk scores.

Autor: Isgut M; Department of Bioinformatics, Georgia Institute of Technology, Atlanta, GA, 30332, USA.; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA., Giuste F; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA., Gloster L; Department of Bioinformatics, Georgia Institute of Technology, Atlanta, GA, 30332, USA.; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA., Swain A; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA., Choi K; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA., Hornback A; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA. ahornback6@gatech.edu., Deshpande SR; Advanced Cardiac Therapies and Heart Transplant Program, Children's National Hospital, Washington, DC, 20010, USA., Wang MD; School of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, 30322, USA. maywang@gatech.edu.

Publikováno v: Scientific reports [Sci Rep] 2024 Sep 27; Vol. 14 (1), pp. 22124. Date of Electronic Publication: 2024 Sep 27.