Umeå University's logo

umu.sePublications
Operational message
There are currently operational disruptions. Troubleshooting is in progress.
Change search
Link to record
Permanent link

Direct link
Prorok, Kalle
Publications (3 of 3) Show all publications
Karbalaie, A., Strong, A., Nordström, T., Schelin, L., Selling, J., Grip, H., . . . Häger, C. (2026). Beyond self-reports after anterior cruciate ligament injury: machine learning methods for classifying and identifying movement patterns related to fear of re-injury. Journal of Sports Sciences, 44(3), 342-356
Open this publication in new window or tab >>Beyond self-reports after anterior cruciate ligament injury: machine learning methods for classifying and identifying movement patterns related to fear of re-injury
Show others...
2026 (English)In: Journal of Sports Sciences, ISSN 0264-0414, E-ISSN 1466-447X, Vol. 44, no 3, p. 342-356Article in journal (Refereed) Published
Abstract [en]

Anterior cruciate ligament (ACL) tears are prevalent career-ending sports injuries. A barrier to successful return to activity is fear of re-injury. Evaluating psychological readiness is however limited to insufficient self-reported assessments. We developed machine learning models using biomechanical data from standardized rebound side hops (SRSH) to objectively classify fear levels post-ACL reconstruction (ACLR) and identify key biomechanical variables. Sixty individuals with ACLR and 47 controls performed up to 10 side hops per leg. Kinematic and kinetic data were collected using motion capture and force platforms. ACLR participants were classified (Tampa Scale for Kinesiophobia-17) as HIGH-FEAR (n = 32) or LOW-FEAR (n = 28). Analyses involved 1D convolutional neural networks (1D CNN) and logistic regression. Integrated gradients identified influential movement variables. The 1-D CNN distinguished HIGH-FEAR versus LOW-FEAR ACLR individuals in agreement with Tampa Scale scores, achieving a mean accuracy of 75.6% (F₁ Score = 0.76, Matthews Correlation Coefficient = 0.52), which was 8.6% better than logistic regression. Influential variables included trunk tilt, hip flexion/extension, and ankle supination/pronation. Machine learning from biomechanics can identify movement linked to fear of re-injury post-ACLR, potentially informing personalised rehabilitation to mitigate fear and enhance recovery.

Place, publisher, year, edition, pages
Routledge, 2026
Keywords
Artificial intelligence, biomechanics, kinesiophobia, knee, machine learning integration, rehabilitation
National Category
Physiotherapy Orthopaedics Sport and Fitness Sciences
Research subject
physiotherapy
Identifiers
urn:nbn:se:umu:diva-246049 (URN)10.1080/02640414.2025.2578584 (DOI)001598870300001 ()001598870300001 (PubMedID)2-s2.0-105019696230 (Scopus ID)
Funder
Swedish Research Council, 2017-00892Swedish Research Council, 2022-00774Konung Gustaf V:s och Drottning Victorias FrimurarestiftelseRegion Västerbotten, RV966109Region Västerbotten, RV967112
Available from: 2025-10-31 Created: 2025-10-31 Last updated: 2026-02-02Bibliographically approved
Drewes, F. & Prorok, K. (2021). AI för dokumentgenerering.
Open this publication in new window or tab >>AI för dokumentgenerering
2021 (Swedish)Report (Other academic)
Abstract [sv]

Den här rapporten ger en kortfattad introduktion till metoder och några praktiska resultat från ett AI-texthanteringsprojekt i samarbete mellan Trafikverket, Umeå universitet och Sweco. Tester har gjorts för att extrahera information (geografiska orter, sammanfattningar, frågor och svar) från dokument. Även dokumentgenerering, projektets ursprungliga fokus, har adresserats. Där var målet att automatiskt skapa texter för utvalda syften, något som visade sig vara svårt i nuläget då de existerande metoderna är begränsade och samtidigt mycket krävande på datorkraft. Till rapporten hör några förenklade kodexempel där läsaren själv kan testköra och förhoppningsvis lära sig från lite olika fall.Rapporten är indelad i fyra delar: En icke teknisk översikt för allmänt intresserade, en mer detaljerad beskrivning av resultaten, en del om begrepp och metoder för speciellt intresserade samt en del om implementation för programmerare.

Publisher
p. 45
Keywords
dokumentgenerering, artificiell intelligens
National Category
Natural Language Processing
Research subject
computational linguistics
Identifiers
urn:nbn:se:umu:diva-219548 (URN)
Projects
Framtagande av AI-verktyg för effektivare dokumentgenerering vid väg- och järnvägsplanering
Funder
Swedish Transport Administration, TRV 2020/16433
Available from: 2024-01-16 Created: 2024-01-16 Last updated: 2025-02-07Bibliographically approved
Rönnbäck, S., Westerberg, S. & Prorok, K. (2009). CSE+: path planning amid circles. In: IEEE International Conference on Robots and Agents: . Paper presented at 4th International Conference on Robots and Agents, Wellington, New Zealand, 10-12 february 2009 (pp. 447-452). IEEE conference proceedings
Open this publication in new window or tab >>CSE+: path planning amid circles
2009 (English)In: IEEE International Conference on Robots and Agents, IEEE conference proceedings, 2009, p. 447-452Conference paper, Published paper (Refereed)
Abstract [en]

This paper presents a method for obstacle avoidance and path-finding amid circular objects. The input data are circles and the output is a sequence of circles. The output circles represent a possible path, to a target, for a holonomic mobile robot. The method uses a solution to the Apollonius Tangency problem to find the maximum spanning circles amid the input circles. The radii of the circles can be set by desired clearance to nearby obstacles, from sensor parameters, or model parameters from extracted features. The method is intuitive and rather easily implemented and suits well for mobile robots, especially mobile robots with circular shape. It can be implemented with a depth-first approach where the target bearing angle is used as criteria in a divide and conquer step. The method was tested on sensor data registered by a laser range finder.

Place, publisher, year, edition, pages
IEEE conference proceedings, 2009
National Category
Robotics and automation
Identifiers
urn:nbn:se:umu:diva-19735 (URN)10.1109/ICARA.2000.4803947 (DOI)000269688000040 ()2-s2.0-66149166020 (Scopus ID)978-1-4244-2712-3 (ISBN)978-1-4244-2713-0 (ISBN)
Conference
4th International Conference on Robots and Agents, Wellington, New Zealand, 10-12 february 2009
Note

CSE plus: path planning amid circles

Available from: 2009-03-27 Created: 2009-03-10 Last updated: 2025-02-09Bibliographically approved
Organisations

Search in DiVA

Show all publications