Brian Horsak's Avatar

Brian Horsak

@bhorsak.bsky.social

Endowed Professor for Applied Biomechanics and Rehabilitation Research at the St. Pรถlten University of Applied Sciences, Austria #MachineLearning #VirtualReality #OpenSim #GaitBiomechanis

70 Followers  |  56 Following  |  6 Posts  |  Joined: 06.02.2024
Posts Following

Posts by Brian Horsak (@bhorsak.bsky.social)

Decoding Gait Signatures: Exploring Individual Patterns in Pathological Gait Using Explainable AI This study explores the application of machine learning (ML) to derive and analyze individual gait patterns (i.e., gait signatures) from ground reaction force data. This study leverages three datasets...

Our latest research ๐——๐—ฒ๐—ฐ๐—ผ๐—ฑ๐—ถ๐—ป๐—ด ๐—š๐—ฎ๐—ถ๐˜ ๐—ฆ๐—ถ๐—ด๐—ป๐—ฎ๐˜๐˜‚๐—ฟ๐—ฒ๐˜€: ๐—˜๐˜…๐—ฝ๐—น๐—ผ๐—ฟ๐—ถ๐—ป๐—ด ๐—œ๐—ป๐—ฑ๐—ถ๐˜ƒ๐—ถ๐—ฑ๐˜‚๐—ฎ๐—น ๐—ฃ๐—ฎ๐˜๐˜๐—ฒ๐—ฟ๐—ป๐˜€ ๐—ถ๐—ป ๐—ฃ๐—ฎ๐˜๐—ต๐—ผ๐—น๐—ผ๐—ด๐—ถ๐—ฐ๐—ฎ๐—น ๐—š๐—ฎ๐—ถ๐˜ ๐˜‚๐˜€๐—ถ๐—ป๐—ด ๐—˜๐˜…๐—ฝ๐—น๐—ฎ๐—ถ๐—ป๐—ฎ๐—ฏ๐—น๐—ฒ ๐—”๐—œ has been published in IEEE Access @ @embs.org section ๐Ÿ‘‰ doi.org/10.1109/ACCE...

#GaitAnalysis #Biomechanics #AI #ML #XAI #GaitSignature #BiomechSky

25.12.2024 22:17 โ€” ๐Ÿ‘ 9    ๐Ÿ” 4    ๐Ÿ’ฌ 2    ๐Ÿ“Œ 2

Corrected link here: doi.org/10.1016/j.jb...

13.03.2024 10:56 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0


โšก๐Ÿšซ Caution: Be cautions when using variability-based metrics based on markerless data. The higher inter-trial variability could potentially lead to misleading results.

13.03.2024 10:55 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

โœ… ๐Ÿ“‰ Mitigation Strategies: Do not trust single waveforms, use avareged ones and make sure you have enough data to calculate robust mean waveforms.

13.03.2024 10:55 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

Here are the key findings ๐ŸŽฏ ๐Ÿ“Š :

โฌ† ๐Ÿ“ˆ Increased Inter-Trial Variability: the markerless system exhibited an increase in inter-trial variability of up to 22%. It seems that the markerless pose estimation pipelines introduce additional variability in kinematic data ontop of the natural variability.

13.03.2024 10:55 โ€” ๐Ÿ‘ 0    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0

I am very happy to share our lastest study with #OpenCap, a markerless mocap solution based on smartphones. We evaluated the inter-trial variability between markerless and marker-based data. Our paper was just recently accepted and can be found here: lnkd.in/dsFufy8F

13.03.2024 10:53 โ€” ๐Ÿ‘ 1    ๐Ÿ” 0    ๐Ÿ’ฌ 4    ๐Ÿ“Œ 0

.

07.02.2024 22:03 โ€” ๐Ÿ‘ 1    ๐Ÿ” 0    ๐Ÿ’ฌ 0    ๐Ÿ“Œ 0