Analysis of sequential ruminal temperature sensor data from dairy cows to identify cow subgroups by clustering and predict calving through supervised machine learning
Journal of Reproduction and Development · 2023
DOI: 10.1262/jrd.2022-107 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Reproduction and Development, 2023. Verfasst von Eri Furukawa und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Theriogenology, Graduate School of Veterinary Medicine, Hokkaido University, Sapporo, Hokkaido 060-0818, Japan. Hauptthemen laut MEDLINE: Parturition, Body Temperature. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
The present study investigated the applicability of a calving prediction model based on supervised machine learning of ruminal temperature (RT) data in dairy cows. The existence of cow subgroups for prepartum RT changes was also examined, and the predictive performance of the model was compared among these subgroups. RT data were collected from 24 Holstein cows at 10 min intervals using an RT sensor system. The average hourly RT was calculated and data were expressed as residual RTs (rRT = actual RT - mean RT for the same time on the previous three days). The mean rRT decreased beginning at approximately 48 h before calving to a low of -0.5°C at 5 h before calving. However, two cow subgroups were identified: cows with a late and small rRT decrease (Cluster 1, n = 9) and those with an early and large rRT decrease (Cluster 2, n = 15). A calving prediction model was developed using five features extracted from the sensor data (indicative of prepartum rRT changes) through a support vector machine. Cross-validation showed that calving within 24 h was predicted with a sensitivity of 87.5% (21/24) and precision of 77.8% (21/27). A significant difference in sensitivity was observed between Clusters 1 and 2 (66.7 vs. 100%, respectively), while none was observed for precision. Therefore, the model based on RT data with supervised machine learning has the potential to efficiently predict calving, although improvements for specific cow subgroups are required.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratory of Theriogenology, Graduate School of Veterinary Medicine, Hokkaido University, Sapporo, Hokkaido 060-0818, Japan.
- Laboratory of Theriogenology, Faculty of Veterinary Medicine, Hokkaido University, Sapporo, Hokkaido 060-0818, Japan.
- The Better Co., Ltd., Tokyo 161-0034, Japan.
- uLikeKorea Co., Inc., Seoul 05839, Republic of Korea.
- Laboratory of Animal Breeding and Reproduction, Research Faculty of Agriculture, Hokkaido University, Sapporo, Hokkaido 060-8589, Japan.
- Global Station for Food, Land and Water Resources, Global Institution for Collaborative Research and Education, Hokkaido University, Sapporo, Hokkaido 060-8589, Japan.
Zitieren
APA
Furukawa, E., Yanagawa, Y., Matsuzaki, A., Kim, H., Bai, H., Takahashi, M., Katagiri, S., & Higaki, S. (2023). Analysis of sequential ruminal temperature sensor data from dairy cows to identify cow subgroups by clustering and predict calving through supervised machine learning. Journal of Reproduction and Development. https://doi.org/10.1262/jrd.2022-107
Vancouver
Furukawa E, Yanagawa Y, Matsuzaki A, Kim H, Bai H, Takahashi M, et al. Analysis of sequential ruminal temperature sensor data from dairy cows to identify cow subgroups by clustering and predict calving through supervised machine learning. Journal of Reproduction and Development. 2023. doi:10.1262/jrd.2022-107
BibTeX
@article{Furukawa2023,
author = {Furukawa, Eri and Yanagawa, Yojiro and Matsuzaki, Akira and Kim, Heejin and Bai, Hanako and Takahashi, Masashi and Katagiri, Seiji and Higaki, Shogo},
title = {Analysis of sequential ruminal temperature sensor data from dairy cows to identify cow subgroups by clustering and predict calving through supervised machine learning},
journal = {Journal of Reproduction and Development},
year = {2023},
doi = {10.1262/jrd.2022-107}
}
EUVIMED