Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Comparative Performance Analysis of YOLOv10-Based Models with CBAM and SPPFCSPC for Body Condition Score Assessment in Beef Cattle

Tropical Animal Science Journal · Vol. 48 No. 5 (2025) · hlm. 402–411

DOI
10.5398/tasj.2025.48.5.402
ISSN
2615-787X, 2615-790X
Terbit
2025-08-27
Penerbit
Bogor Institute of Agriculture
Bahasa
en
Lisensi
creativecommons.org/licenses/by-sa/4.0/

Abstrak

Body condition score assessment serves as a critical metric for evaluating the health, nutritional status, and overall well-being of beef cattle, playing a pivotal role in herd management and productivity optimization. Traditional manual BCS assessment methods are inherently subjective, labor-intensive, and impractical for large-scale operations, thereby necessitating an automated and data-driven approach. This study investigates the performance of YOLOv10-based deep learning models, incorporating the convolutional block attention module (CBAM) and spatial pyramid pooling-fast cross-stage partial connections (SPPFCSPC) to enhance feature extraction, classification accuracy, and computational efficiency in BCS estimation. A total of 432 annotated images representing five BCS categories (1–5) were used for model training and evaluation. The models were assessed using precision, recall, and F1 Score, with expert-labeled ground truth ensuring robustness. Results show that the YOLOv10x variant achieved the highest classification accuracy of 88.2%, highlighting its superior detection capability. YOLOv10m exhibited a balanced trade-off between accuracy and computational efficiency, achieving an F1 Score of 79.2%. The integration of CBAM improved precision but slightly reduced recall, whereas SPPFCSPC enhanced recall at the expense of increased computational complexity. Notably, YOLOv10n achieved the fastest inference time of 1.0 ms but with a lower accuracy of 82.4%, underscoring the trade-off between model depth and real-time applicability. These findings validate the effectiveness of attention-based and multi-scale feature learning strategies for improving the automation of BCS classification in beef cattle.

Kata kunci

Jaringan kolaborasi para penulis

24 penulis · 72 tautan kepenulisan bersama · 36 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universitas Gadjah Mada
  • National Research and Innovation Agency
  • IPB University
  • University of Brawijaya
  • Sebelas Maret University
  • Pusat Penelitian dan Pengembangan Peternakan
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Ahmat Endang Two SulfiarUniversitas Gadjah Mada2
H. MaulanaUniversitas Gadjah Mada2
Alek IbrahimNational Research and Innovation Agency2
N NgadiyonoUniversitas Gadjah Mada2
I Gede Suparta BudisatriaUniversitas Gadjah Mada2
Panjono PanjonoUniversitas Gadjah Mada2
Siti AndarwatiUniversitas Gadjah Mada2
T NugrohoSebelas Maret University1
Amalina Nur WahyuningtyasIPB University1
Epi TaufikIPB University1
Mochammad Sriduresta SoenarnoIPB University1
PanjonoAfiliasi tidak diketahui1
Budi GuntoroUniversitas Gadjah Mada1
Sigit BintaraUniversitas Gadjah Mada1
Lusia Komala WidiastutiUniversitas Gadjah Mada1
Atien PriyantiPusat Penelitian dan Pengembangan Peternakan1
Rifal MaulanaUniversitas Gadjah Mada1
Aryogi AryogiNational Research and Innovation Agency1
Agus WibowoAfiliasi tidak diketahui1
Regita Aisyah NirmalaUniversitas Gadjah Mada1
P. PanjonoUniversitas Gadjah Mada1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OpenAlex API (jurnal SINTA, ADR 0048) https://openalex.org/S4210227096, pertama di-harvest 19 Nov 2026, terakhir terlihat 19 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/"><dc:title xml:lang="en">Comparative Performance Analysis of YOLOv10-Based Models with CBAM and SPPFCSPC for Body Condition Score Assessment in Beef Cattle</dc:title><dc:creator>Fajar Ariadi</dc:creator><dc:creator>Febriani Utaminingrum</dc:creator><dc:creator>Bayu Andri Atmoko</dc:creator><dc:subject>body condition score</dc:subject><dc:subject>beef cattle</dc:subject><dc:subject>YOLOv10</dc:subject><dc:subject>CBAM</dc:subject><dc:subject>attention mechanism</dc:subject><dc:subject>multi-scale feature extraction</dc:subject><dc:subject>model efficiency</dc:subject><dc:description xml:lang="en">Body condition score assessment serves as a critical metric for evaluating the health, nutritional status, and overall well-being of beef cattle, playing a pivotal role in herd management and productivity optimization. Traditional manual BCS assessment methods are inherently subjective, labor-intensive, and impractical for large-scale operations, thereby necessitating an automated and data-driven approach. This study investigates the performance of YOLOv10-based deep learning models, incorporating the convolutional block attention module (CBAM) and spatial pyramid pooling-fast cross-stage partial connections (SPPFCSPC) to enhance feature extraction, classification accuracy, and computational efficiency in BCS estimation. A total of 432 annotated images representing five BCS categories (1–5) were used for model training and evaluation. The models were assessed using precision, recall, and F1 Score, with expert-labeled ground truth ensuring robustness. Results show that the YOLOv10x variant achieved the highest classification accuracy of 88.2%, highlighting its superior detection capability. YOLOv10m exhibited a balanced trade-off between accuracy and computational efficiency, achieving an F1 Score of 79.2%. The integration of CBAM improved precision but slightly reduced recall, whereas SPPFCSPC enhanced recall at the expense of increased computational complexity. Notably, YOLOv10n achieved the fastest inference time of 1.0 ms but with a lower accuracy of 82.4%, underscoring the trade-off between model depth and real-time applicability. These findings validate the effectiveness of attention-based and multi-scale feature learning strategies for improving the automation of BCS classification in beef cattle.</dc:description><dc:publisher>Bogor Institute of Agriculture</dc:publisher><dc:date>2025-08-27</dc:date><dc:type>info:eu-repo/semantics/article</dc:type><dc:format>application/pdf</dc:format><dc:identifier>https://doi.org/10.5398/tasj.2025.48.5.402</dc:identifier><dc:identifier>10.5398/tasj.2025.48.5.402</dc:identifier><dc:source>Tropical Animal Science Journal; Vol 48 No 5 (2025); 402-411</dc:source><dc:source>2615-787X</dc:source><dc:source>2615-790X</dc:source><dc:language>en</dc:language><dc:relation>https://journal.ipb.ac.id/tasj/article/download/63469/31373</dc:relation><dc:rights>https://creativecommons.org/licenses/by-sa/4.0/</dc:rights></oai_dc:dc>