# An analysis of pacing profiles in sprint kayak racing using functional principal components and hidden Markov models

**Authors:** Harry Estreich, Nicola Bullock, Mark Osborne, Edgar Santos-Fernandez, Paul Pao-Yen Wu, Matteo Vandoni, Matteo Vandoni, Matteo Vandoni, Matteo Vandoni

PMC · DOI: 10.1371/journal.pone.0326375 · PLOS One · 2025-07-02

## TL;DR

This study uses advanced statistical models to analyze how sprint kayakers adjust their race pacing over their careers.

## Contribution

The novel approach combines functional principal components and hidden Markov models to categorize and track pacing profiles in kayak racing.

## Key findings

- The first four principal components explained 90.77% of the variation in 500m races and 78.80% in 1000m races.
- Pacing characteristics like dropoff and kick were identified as key components influencing race profiles.
- An athlete’s pacing profile changes as they mature, with development pathway athletes showing a higher dropoff trend.

## Abstract

This study analysed sprint kayak pacing profiles in order to categorise and compare an athlete’s race profile throughout their career. We used functional principal component analysis of normalised velocity data for 500m and 1000m races to quantify pacing. The first four principal components explained 90.77% of the variation over 500m and 78.80% over 1000m. These principal components were then associated with unique pacing characteristics with the first component defined as a dropoff in velocity and the second component defined as a kick. All other defined characteristics were a variation of these two, i.e., late kick. We then applied a Hidden Markov model to categorise each profile over an athlete’s career, using the PC scores, into different types of race profiles. This model included age and event type and identified a trend for a higher dropoff in development pathway athletes. Using the four different race profile types, four athletes had all their race profiles throughout their careers analysed. It was identified that an athlete’s pacing profile changes throughout their career as an athlete matures. This information provides coaches, practitioners and athletes with expectations as to how pacing profiles change across the course of an athlete’s career.

## Full-text entities

- **Genes:** KRT6B (keratin 6B) [NCBI Gene 3854] {aka CK-6B, CK6B, K6B, KRTL1, PC2, PC4}, CBX8 (chromobox 8) [NCBI Gene 57332] {aka PC3, RC1}, PCSK1 (proprotein convertase subtilisin/kexin type 1) [NCBI Gene 5122] {aka BMIQ12, NEC1, PC1, PC1/3, PC3, SPC3}, CBX4 (chromobox 4) [NCBI Gene 8535] {aka NBP16, PC2}
- **Diseases:** stroke (MESH:D020521), HMM (MESH:D004195), fatigue (MESH:D005221), fPC (MESH:C566443), Athlete D (MESH:D001265)
- **Chemicals:** HMM (-)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC12221036/full.md

## Figures

7 figures with captions in the complete paper: https://tomesphere.com/paper/PMC12221036/full.md

## References

27 references — full list in the complete paper: https://tomesphere.com/paper/PMC12221036/full.md

---
Source: https://tomesphere.com/paper/PMC12221036