Akademik Veri Yönetim Sistemi
ADVANCED INTELLIGENT SYSTEMS, 2025 (SCI-Expanded, Scopus)
Sperm motility, a critical factor in diagnosing male infertility, requires computer-based solutions due to the limitations of manual evaluation methods. This studyintroduces the Hi-LabSpermTracking dataset, comprising 66 videos (60 seach, 10 fps) collected from 14 patients and meticulously annotated by experts.Unlike similar datasets, these uninterrupted, long-duration videos enable con-tinuous tracking of individual sperm cells, each assigned a unique ID throughoutthe video, supporting both sperm detection and tracking tasks. Experimentalevaluations employ you only look once v8 (YOLOv8), real-time detectiontransformer, and simple online and realtime tracking with a deep associationmetric across three scenarios. In Scenario I (sperm detection), the YOLOv8nmodel achieves 98.9% mAP50 and 97.9% F1-score. In Scenario II (spermtracking), performance metrics include 83.88% mAP50, 87.63% F1-score,72.27% higher order tracking accuracy (HOTA), and 77.88% multiple objecttracking accuracy (MOTA). Scenario III simulates real-world challenges by separatingtraining and testing videos. Ensemble methods are applied, with the proposedmean ensemble achieving superior results: 86.55% mAP50, 87.87% F1-score,66.66% HOTA, and 76.42% MOTA. The Hi-LabSpermTracking dataset enablesrobust sperm tracking research, while the mean ensemble method amplifiesaccuracy by uniting model strengths.RESEARCH ARTICLEwww.advintellsyst.comAdv. Intell. Syst. 2025, 2500115 2500115 (1 of 24) © 2025 The Author(s). Advanced Intelligent Systems published by Wiley-VCH GmbH