Message Boards Message Boards

Predicting COVID-19 using cough sounds classification

POSTED BY: Siria Sadeddin
10 Replies

Congratulations! Your post was highlighted on the Wolfram's official social media channels. Thank you for your contribution. We are looking forward to your future posts.

POSTED BY: Moderation Team
Posted 3 years ago

The API and the webform have both been upgraded to reflect Siria's improved model. A 90%|10% train|test split was used.

results

POSTED BY: Renay Oshop

oh wow, where is this data from?

POSTED BY: Siria Sadeddin

OMG thank you Renay! Of Couse this is still dummy because of the limited amount of data but if we could collect thousands of records can become a thing :D

POSTED BY: Siria Sadeddin
Posted 3 years ago

I think that would be great. Curation of data might be an issue, though.

POSTED BY: Renay Oshop
Posted 3 years ago
 api=CloudObject[https://www.wolframcloud.com/obj/renay.oshop/CovidCoughClassifierAPI];
URLExecute[api, {"mp3" -> File["filepathtomp3"]}]
POSTED BY: Renay Oshop

I have made a little change on the model, this I think will generalize better the Coughs for this task. ;)

POSTED BY: Siria Sadeddin
Posted 3 years ago

Thank you! I operationalized this into a web form in case anyone wants to see it in action. https://wolfr.am/SGd0jvLu Uses mp3 files as input. For entertainment only.

POSTED BY: Renay Oshop

Can you post a WebAPI link? (So the classifier can be used in scripts, WL or other programming languages.)

POSTED BY: Anton Antonov

enter image description here -- you have earned Featured Contributor Badge enter image description here Your exceptional post has been selected for our editorial column Staff Picks http://wolfr.am/StaffPicks and Your Profile is now distinguished by a Featured Contributor Badge and is displayed on the Featured Contributor Board. Thank you!

POSTED BY: Moderation Team
Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
Attachments
Remove
or Discard

Group Abstract Group Abstract