IDENTIFIKASI ABNORMALITAS MOTILITAS SPERMATOZOA MENGGUNAKAN ALGORITMA REGRESI LOGISTIK

Karim, Mohammad Daniel Sulthonul (2025) IDENTIFIKASI ABNORMALITAS MOTILITAS SPERMATOZOA MENGGUNAKAN ALGORITMA REGRESI LOGISTIK. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010059-cover.pdf Download (1MB)
	Text (Bab 1) 20081010059-bab1.pdf Download (154kB)
	Text (Bab 2) 20081010059-bab2.pdf Restricted to Registered users only until February 2027. Download (524kB)
	Text (Bab 3) 20081010059-bab3.pdf Restricted to Registered users only until February 2027. Download (1MB)
	Text (Bab 4) 20081010059-bab4.pdf Restricted to Registered users only until February 2027. Download (605kB)
	Text (Bab 5) 20081010059-bab5.pdf Download (107kB)
	Text (Daftar Pustaka) 20081010059-daftarpustaka.pdf Download (205kB)
	Text (Lampiran) 20081010059-lampiran.pdf Restricted to Registered users only Download (213kB)

Abstract

Spermatozoa motility is a crucial indicator in determining male fertility quality. Manual assessment of motility abnormalities often requires significant time and effort, necessitating a more efficient and accurate automated approach. This study aims to identify spermatozoa motility abnormalities using the logistic regression algorithm, utilizing microscopic video data analyzed with the TrackPy library for trajectory tracking. The analysis process includes data acquisition, spermatozoa detection in each frame, sperm trajectory creation, and trajectory classification into normal or abnormal categories. The logistic regression model was trained using a dataset derived from spermatozoa trajectories classified based on average velocity and trajectory linearity parameters. The study tested scenarios on videos with various frame rates: 15 fps, 24 fps, and 30 fps. Results show that the logistic regression method achieved accuracies of 81% for videos at 15 fps, 91% at 24 fps, and 95% at 30 fps. As a comparison, the Support Vector Machine (SVM) algorithm achieved an accuracy of 89% for videos at 30 fps. This study demonstrates that the logistic regression algorithm provides superior performance in classifying spermatozoa motility abnormalities, particularly for videos with higher frame rates.

Item Type:

Thesis (Undergraduate)

Contributors:

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

Subjects:

Q Science > QA Mathematics > QA76.87 Neural computers

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Mohammad Daniel Sulthonul Karim

Date Deposited:

04 Feb 2025 08:54

Last Modified:

04 Feb 2025 08:54

URI:

https://repository.upnjatim.ac.id/id/eprint/34515