Constructing and Exploring a Predictive Model for 100-Meter Sprint Segmented Data

DOI

10.2991/978-94-6463-540-9_18How to use a DOI?

Keywords

100-meter Sprint; Segmented Data; Random Forest; Sequence Characteristics

Abstract

In a 100-meter race, segmented data every 10 meters is crucial for studying an athlete’s performance. Although there are currently two ways - official provision and video analysis - to obtain segmented data, both have significant drawbacks, making it very difficult to obtain segmented data at present. To address this issue, this study created a relevant dataset, defined the corresponding input sequences, and constructed a satisfactory prediction model based on Random Forests to predict these segmented data. Users only need to input data at any position and in any quantity within the sequence to obtain accurate segmented data every 10 meters. In addition, this paper also explored the model to a certain extent, and summarized the characteristics of input sequences that contribute to the generation of high-quality prediction results: the quantity of known data should be as large as possible; the distribution of known data should be as dispersed as possible; the positions of known data should be as close as possible to each 10-meter; and the positions of known data within the first 50 meters are more favorable than those in the latter 50 meters. Under these guidelines, users of the model can better utilize it to obtain satisfactory prediction results.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yunhao Cui
PY  - 2024
DA  - 2024/10/16
TI  - Constructing and Exploring a Predictive Model for 100-Meter Sprint Segmented Data
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 154
EP  - 164
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_18
DO  - 10.2991/978-94-6463-540-9_18
ID  - Cui2024
ER  -