Loading…
Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning
Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult Optim...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Default Article |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/2134/11955162.v1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1818167687711293440 |
|---|---|
| author | Hannah Jowitt Jérôme Durussel Raphael Brandon Mark King |
| author_facet | Hannah Jowitt Jérôme Durussel Raphael Brandon Mark King |
| author_sort | Hannah Jowitt (8101628) |
| collection | Figshare |
| description | Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult OptimEye S5 wearable device was collected from both national and international level fast bowlers (n = 35) in both training and matches, at various intensities. A machine-learning based approach was used to develop the algorithm. Outputs were compared with over 20,000 manually recorded events. A high Matthews correlation coefficient (r = 0.945) showed very good agreement between the automatically detected bowling deliveries and manually recorded ones. The algorithm was found to be both sensitive and specific in training (96.3%, 98.3%) and matches (99.6%, 96.9%), respectively. Rare falsely classified events were typically warm-up deliveries or throws preceded by a run. Inertial sensors data processed by a machine-learning based algorithm provide a valid tool to automatically detect bowling events, whilst also providing the opportunity to look at performance metrics associated with fast bowling. This offers the possibility to better monitor bowling workloads across a range of intensities to mitigate injury risk potential and maximise performance. |
| format | Default Article |
| id | rr-article-11955162 |
| institution | Loughborough University |
| publishDate | 2020 |
| record_format | Figshare |
| spelling | rr-article-119551622020-02-26T00:00:00Z Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning Hannah Jowitt (8101628) Jérôme Durussel (283782) Raphael Brandon (8548812) Mark King (1258182) Algorithm GPS workload Sport Sciences Human Movement and Sports Sciences Curriculum and Pedagogy Cricket fast bowlers are at a high risk of injury occurrence, which has previously been shown to be correlated to bowling workloads. This study aimed to develop and test an algorithm that can automatically, reliably and accurately detect bowling deliveries. Inertial sensor data from a Catapult OptimEye S5 wearable device was collected from both national and international level fast bowlers (n = 35) in both training and matches, at various intensities. A machine-learning based approach was used to develop the algorithm. Outputs were compared with over 20,000 manually recorded events. A high Matthews correlation coefficient (r = 0.945) showed very good agreement between the automatically detected bowling deliveries and manually recorded ones. The algorithm was found to be both sensitive and specific in training (96.3%, 98.3%) and matches (99.6%, 96.9%), respectively. Rare falsely classified events were typically warm-up deliveries or throws preceded by a run. Inertial sensors data processed by a machine-learning based algorithm provide a valid tool to automatically detect bowling events, whilst also providing the opportunity to look at performance metrics associated with fast bowling. This offers the possibility to better monitor bowling workloads across a range of intensities to mitigate injury risk potential and maximise performance. 2020-02-26T00:00:00Z Text Journal contribution 2134/11955162.v1 https://figshare.com/articles/journal_contribution/Auto_detecting_deliveries_in_elite_cricket_fast_bowlers_using_microsensors_and_machine_learning/11955162 CC BY-NC-ND 4.0 |
| spellingShingle | Algorithm GPS workload Sport Sciences Human Movement and Sports Sciences Curriculum and Pedagogy Hannah Jowitt Jérôme Durussel Raphael Brandon Mark King Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title | Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title_full | Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title_fullStr | Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title_full_unstemmed | Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title_short | Auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| title_sort | auto detecting deliveries in elite cricket fast bowlers using microsensors and machine learning |
| topic | Algorithm GPS workload Sport Sciences Human Movement and Sports Sciences Curriculum and Pedagogy |
| url | https://hdl.handle.net/2134/11955162.v1 |