IMPLEMENTATION OF YOLOv8 DEEP LEARNING FOR THE DETECTION OF ABNORMALITIES IN THE SHAPE OF BOVINE SPERMATOZOAN HEADS

Waritsin, Rizqy Khoirul (2026) IMPLEMENTATION OF YOLOv8 DEEP LEARNING FOR THE DETECTION OF ABNORMALITIES IN THE SHAPE OF BOVINE SPERMATOZOAN HEADS. Undergraduate thesis, UPN "Veteran" Jawa Timur.

	Text (Cover) Cover.pdf Download (575kB)
	Text (CHAPTER 1) CHAPTER 1.pdf Download (89kB)
	Text (CHAPTER 2) CHAPTER 2.pdf Restricted to Repository staff only until 25 July 2029. Download (738kB)
	Text (CHAPTER 3) CHAPTER 3.pdf Restricted to Repository staff only until 25 July 2029. Download (970kB)
	Text (CHAPTER 4) CHAPTER 4.pdf Restricted to Repository staff only until 24 July 2029. Download (2MB)
	Text (CHAPTER 5) CHAPTER 5.pdf Download (78kB)
	Text (DAFTAR PUSTAKA) DAFTAR PUSTAKA.pdf Download (86kB)

Abstract

Abnormalities in bovine sperm head morphology are among the factors that reduce semen quality and affect reproductive success. Manual identification is time-consuming and highly dependent on the examiner's expertise, highlighting the need for an automated detection approach. This study aims to implement the You Only Look Once version 8 (YOLOv8) architecture for detecting abnormalities in bovine sperm head morphology. Before model training, the images were preprocessed using Contrast Limited Adaptive Histogram Equalization (CLAHE) to enhance image contrast. The model was trained and evaluated using 27 experimental scenarios, consisting of three optimizers (SGD, Adam, and RMSProp), three learning rates (0.0001, 0.001, and 0.01), and three epoch settings (75, 100, and 125). The best performance was achieved using the RMSProp optimizer with a learning rate of 0.01 and 75 epochs. This configuration achieved an accuracy of 95.56%, mAP@0.5 of 91.76%, precision of 89.81%, recall of 88.38%, and an F1-score of 89.08%. These results demonstrate that YOLOv8 can effectively detect abnormalities in bovine sperm head morphology and has the potential to support automated semen quality evaluation.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Masdiyasa, I Gede Susrama	NIDN0019067008	igsusrama.if@upnjatim.ac.id
Thesis advisor	Puspaningrum, Eva Yulia	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General) > T385 Computer Graphics

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Rizqy Khoirul Waritsin

Date Deposited:

24 Jul 2026 08:08

Last Modified:

24 Jul 2026 08:34

URI:

https://repository.upnjatim.ac.id/id/eprint/58140