| lab website | https://strokeinnovationlab.ca |
| google scholar | https://scholar.google.ca/citations?user=qzhk98YAAAAJ&hl=en |
| podcast | https://www.stroke.fm/ |
| Personal site and blog | https://www.ncrit.org/posts/index.html |
RE: https://sigmoid.social/@neuroccm/115681232644280133
Hi folks, interview with founder and maker of intervals.Icu is up on Velo Health , please subscribe, comment, like!
Learn about how this awesome platform was developed and what’s coming in the future https://youtu.be/cw06Ko3NJLM?si=c1nLCPMKCvqPXPxH
#cycling #gravel #fitness #running
Hey folks! intervals.icu
- one of the Best platforms for metrics and analysis of your fitness
- this community of #tech #medicine #ML #programming #fitness #wellness #cyclists #gravel #cycling #runners #foamed #MedEd is keen on wellness, fitness
-I had the distinct privilege of interviewing the founder and developer of this platform Mr. David Tinker, we get into #fitness #cycling #programming #backendDevelopment
Velo Health Podcast:
https://podcasts.apple.com/gb/podcast/velo-health/id1859510634
https://open.spotify.com/show/31XA0zxf3eoy9LdWQgqD9P?si=b0b4c06ed7414ba4
🎂 Happy Birthday, Callsheet! 🎂
Original announcement:
https://www.caseyliss.com/2023/8/7/callsheet
1-year recap:
https://www.caseyliss.com/2024/7/13/callsheet-renewals-approach
Thanks to everyone who has tried the app, a huge thank you to everyone who has subscribed, and an immense thank you to anyone who has subscribed at the bonus levels! 💙
Super stoked for year number two!
Attached: 1 image Catbells Ridge from Keswick #silentSunday #landscapePhotography #Fotografie #photography
This study assesses deep learning models for audio classification in a clinical setting with the constraint of small datasets reflecting real-world prospective data collection. We analyze CNNs, including DenseNet and ConvNeXt, alongside transformer models like ViT, SWIN, and AST, and compare them against pre-trained audio models such as YAMNet and VGGish. Our method highlights the benefits of pre-training on large datasets before fine-tuning on specific clinical data. We prospectively collected two first-of-their-kind patient audio datasets from stroke patients. We investigated various preprocessing techniques, finding that RGB and grayscale spectrogram transformations affect model performance differently based on the priors they learn from pre-training. Our findings indicate CNNs can match or exceed transformer models in small dataset contexts, with DenseNet-Contrastive and AST models showing notable performance. This study highlights the significance of incremental marginal gains through model selection, pre-training, and preprocessing in sound classification; this offers valuable insights for clinical diagnostics that rely on audio classification.
Casey Liss