Confident COVID-19 cough prediction on imbalanced data

Julia A. Meister; Khuong An Nguyen; Zhiyuan Luo

Confident COVID-19 cough prediction on imbalanced data

Julia A. Meister, Khuong An Nguyen, Zhiyuan Luo

Research output: Contribution to conference › Other › peer-review

Abstract

COVID cough data is heavily imbalanced, and it is challenging to collect more samples. Therefore, models are biased and their predictions cannot be trusted. In this poster, we propose a confidence measure for COVID-19 cough classification.

Original language	English
Number of pages	1
Publication status	Published - 21 Nov 2022
Event	Machine Learning for Healthcare - Institute of Physics, London, United Kingdom Duration: 21 Nov 2022 → 21 Nov 2022 https://iop.eventsair.com/mlh2022/

Conference

Conference	Machine Learning for Healthcare
Abbreviated title	MLH
Country/Territory	United Kingdom
City	London
Period	21/11/22 → 21/11/22
Internet address	https://iop.eventsair.com/mlh2022/

Bibliographical note

Winner of the Best Poster Award.

Keywords

machine learning
COVID-19 classification
imbalanced data

Access to Document

2023IOPPosterFinal published version, 815 KBLicence: Unspecified

Cite this

@conference{a51108a4cb99487c83b1710851b8b165,

title = "Confident COVID-19 cough prediction on imbalanced data",

abstract = "COVID cough data is heavily imbalanced, and it is challenging to collect more samples. Therefore, models are biased and their predictions cannot be trusted. In this poster, we propose a confidence measure for COVID-19 cough classification.",

keywords = "machine learning, COVID-19 classification, imbalanced data",

author = "Meister, {Julia A.} and Nguyen, {Khuong An} and Zhiyuan Luo",

note = "Winner of the Best Poster Award.; Machine Learning for Healthcare, MLH ; Conference date: 21-11-2022 Through 21-11-2022",

year = "2022",

month = nov,

day = "21",

language = "English",

url = "https://iop.eventsair.com/mlh2022/",

}

TY - CONF

T1 - Confident COVID-19 cough prediction on imbalanced data

AU - Meister, Julia A.

AU - Nguyen, Khuong An

AU - Luo, Zhiyuan

N1 - Winner of the Best Poster Award.

PY - 2022/11/21

Y1 - 2022/11/21

N2 - COVID cough data is heavily imbalanced, and it is challenging to collect more samples. Therefore, models are biased and their predictions cannot be trusted. In this poster, we propose a confidence measure for COVID-19 cough classification.

AB - COVID cough data is heavily imbalanced, and it is challenging to collect more samples. Therefore, models are biased and their predictions cannot be trusted. In this poster, we propose a confidence measure for COVID-19 cough classification.

KW - machine learning

KW - COVID-19 classification

KW - imbalanced data

M3 - Other

T2 - Machine Learning for Healthcare

Y2 - 21 November 2022 through 21 November 2022

ER -

Confident COVID-19 cough prediction on imbalanced data

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this