Adaptive Optimizers for Neural Network Sperm Motility Classification

I Gede Susrama Mas Diyasa; Vaizal  Asy’ari; Ani Dijah  Rahajoe; Sayyidah  Humairah; Deshinta Arrova Dewi; Muhammad Nashif  Farid; Faikul Umam

doi:10.35882/jeeemi.v8i4.1498

I Gede Susrama Mas Diyasa Department of Information Technology, University of Pembangunan Nasional Veteran Jawa Timur, Indonesia https://orcid.org/0000-0003-2555-1282
Vaizal Asy’ari Department of Information Technology, University of Pembangunan Nasional Veteran Jawa Timur, Indonesia https://orcid.org/0009-0008-6234-5465
Ani Dijah Rahajoe Department of Information Technology, University of Pembangunan Nasional Veteran Jawa Timur, Indonesia https://orcid.org/0009-0001-0528-5127
Sayyidah Humairah Department of electrical and computer engineering, Polytechnic Faculty, University of Patras Greece https://orcid.org/0009-0004-5661-181X
Deshinta Arrova Dewi Center for Data Science and Sustainable Technologies, INTI International University, Negeri Sembilan, Malaysia https://orcid.org/0000-0003-1488-7696
Muhammad Nashif Farid Department of Data Science, University of Pembangunan Nasional Veteran Jawa Timur, Indonesia https://orcid.org/0009-0008-1656-2151
Faikul Umam Department of Informatic, Faculty of Engineering, Universitas Trunojoyo Madura, Indonesia https://orcid.org/0000-0001-8077-2825

DOI: https://doi.org/10.35882/jeeemi.v8i4.1498

Keywords: Adaptive Optimizer, Neural Network, Sperm Motility, Process Innovation, Reproductive Healthcare

Abstract

Infertility remains a major challenge in global reproductive healthcare, with abnormal sperm motility being one of the primary contributing factors to male infertility. Conventional sperm motility analysis relies heavily on manual microscopic observation, which is subjective, time-consuming, and prone to inter-operator variability. Although Computer-Aided Sperm Analysis (CASA) systems provide automated solutions, their high cost and limited accessibility restrict widespread clinical adoption. Therefore, there is a need for a lightweight and cost-effective computational approach that can automatically classify sperm motility abnormalities with high accuracy. This study proposes a machine learning framework based on a Multilayer Perceptron (MLP) neural network optimized using adaptive optimization algorithms to classify sperm motility trajectories. The model utilizes two kinematic features extracted from microscopic video tracking: mean velocity and trajectory linearity. A dataset consisting of 276 unique sperm trajectories was obtained from microscopic recordings and processed using the Trackpy library to generate motion trajectories. The dataset was divided using an 80:20 train–test split strategy to evaluate the generalization capability of the model. Four adaptive optimization algorithms were systematically evaluated, including Adagrad, Adadelta, FTRL, and Adamax. The neural network was trained for 50 epochs using binary cross-entropy as the loss function and evaluated using accuracy, per-class precision, recall, F1-score, specificity, balanced accuracy, and ROC-AUC. Experimental results demonstrate that the Adamax optimizer achieved the best performance with an accuracy of 96.43% and a perfect ROC-AUC of 1.00, outperforming Adagrad (92.86%), FTRL (69.64%), and Adadelta (67.86%). The results indicate that Adamax provides more stable convergence and better optimization behavior for dense kinematic feature spaces. These findings highlight the effectiveness of adaptive optimization techniques in improving neural network performance for automated sperm motility classification. The proposed approach offers a computationally efficient and accessible alternative for supporting clinical sperm analysis and reducing subjectivity in reproductive diagnostics

Downloads

Download data is not yet available.

References

. WHO, WHO Manual for the Laboratory Examination and Processing of Human Semen, 6th Edition. Geneva, Switzerland: World Health Organization, 2021.

. P. Choudhary, P. Dogra, and K. Sharma, "Infertility and lifestyle factors: how habits shape reproductive health," Middle East Fertil. Soc. J., vol. 30, Art. no. 14, pp. 1–9, 2025, doi: 10.1186/s43043-025-00228-7.

. A. Setiawan, I. G. S. Mas Diyasa, M. Hatta and E. Y. Puspaningrum, "Mixture gaussian V2 based microscopic movement detection of human spermatozoa," International Journal of Advances in Intelligent Informatics Vol. 6, No. 2, pp. 210-222, July 2020, doi: 10.26555/ijain.v6i2.507.

. V. Chang et al., "Gold-standard for computer-assisted morphological sperm analysis," Comput. Biol. Med., vol. 83, pp. 143–150, Apr. 2017, doi: 10.1016/j.compbiomed.2017.03.004.

. D. S. Guzick et al., “Sperm Morphology, Motility, and Concentration in Fertile and Infertile Men,” N. Engl. J. Med., vol. 345, no. 19, pp. 1388–1393, Nov. 2001, doi: 10.1056/NEJMoa003005.

. T. G. Cooper et al., "World Health Organization reference values for human semen characteristics," Hum. Reprod. Update, vol. 16, no. 3, pp. 231–245, May 2010, doi: 10.1093/humupd/dmq020.

. F. Hamzah, Z. A. Mulud, M. M. Napes, S. A. Mubarak, and R. Shafie, “Psychological Distress and Quality of Life Among Infertility Couples Undergoing Infertility Treatment in Malaysia,” J. Keperawatan Indones., vol. 28, no. 3, pp. 224–235, Nov. 2025, doi: 10.7454/jki.v28i3.1271.

. L. Bueno-Sánchez, T. Alhambra-Borrás, A. Gallego-Valadés, and J. Garcés-Ferrer, “Psychosocial Impact of Infertility Diagnosis and Conformity to Gender Norms on the Quality of Life of Infertile Spanish Couples,” Int. J. Environ. Res. Public. Health, vol. 21, no. 2, p. 158, Jan. 2024, doi: 10.3390/ijerph21020158.

. M. Rubessa et al., “High-throughput sperm assay using label-free microscopy: morphometric comparison between different sperm structures of boar and stallion spermatozoa,” Anim. Reprod. Sci., vol. 219, p. 106509, Aug. 2020, doi: 10.1016/j.anireprosci.2020.106509.

. J. Yaniz, C. Alquézar-Baeta, and J. Yagüe-Martínez, “Expanding the Limits of Computer-Assisted Sperm Analysis through the Development of Open Software,” Biology, vol. 9, no. 8, p. 207, Agustus 2020, doi: 10.3390/biology9080207.

. M. K. Panner Selvam, A. K. Moharana, S. Baskaran, R. Finelli, M. C. Hudnall, and S. C. Sikka, "Current updates on involvement of artificial intelligence and machine learning in semen analysis," Medicina, vol. 60, no. 2, p. 279, Feb. 2024, doi: 10.3390/medicina60020279.

. J. Lammers, S. Chtourou, A. Reignier, S. Loubersac, P. Barrière, and T. Fréour, “Comparison of two automated sperm analyzers using 2 different detection methods versus manual semen assessment,” J. Gynecol. Obstet. Hum. Reprod., vol. 50, no. 8, p. 102084, Oct. 2021, doi: 10.1016/j.jogoh.2021.102084.

. R. Finelli, K. Leisegang, S. Tumallapalli, R. Henkel, and A. Agarwal, “The validity and reliability of computer-aided semen analyzers in performing semen analysis: a systematic review,” Transl. Androl. Urol., vol. 10, no. 7, pp. 3069–3079, Jul. 2021, doi: 10.21037/tau-21-276.

. E. Molina and J. Parraga-Alava, “Artificial Neural Networks for Classification Tasks: A Systematic Literature Review,” Enfoque UTE, vol. 15, no. 4, pp. 1–10, Oct. 2024, doi: 10.29019/enfoqueute.1058.

. K. Qaderi, F. Sharifipour, M. Dabir, R. Shams, and A. Behmanesh, “Artificial intelligence (AI) approaches to male infertility in IVF: a mapping.review,” Eur. J. Med. Res., vol. 30, no. 1, p. 246, Apr. 2025, doi: 10.1186/s40001-025-02479-6.

. I. G. S. Mas Diyasa, W. S. J. Saputra, A. A. N. Gunawan, D. Herawati, S. Munir, and S. Humairah, “Abnormality Determination of Spermatozoa Motility Using Gaussian Mixture Model and Matching-based Algorithm,” J. Robot. Control JRC, vol. 5, no. 1, pp. 103–116, Jan. 2024, doi: 10.18196/jrc.v5i1.20686.

. J. Riordon, C. McCallum, and D. Sinton, "Deep learning for the classification of human sperm," Comput. Biol. Med., vol. 111, p. 103342, Aug. 2019, doi: 10.1016/j.compbiomed.2019.103342.

. A. H. Baksir, A. Fuad, F. Tempola, and R. Rosihan, “Fertility Prediction Using Artificial Neural Networks Using the Backpropagation Method,” JIKO J. Inform. Dan Komput., vol. 3, no. 2, pp. 107–112, Aug. 2020, doi: 10.33387/jiko.v3i2.1922.

. S. Kosuge and T. Hamagami, "Sperm Detection and Tracking Model Using HDE Transformer with Spatio-Temporal Deformable Attention for Sperm Analysis Automation," IEEE Access, vol. 13, pp. 51978–51985, 2025, doi: 10.1109/ACCESS.2025.3552792.

. O. Ogunmolu, X. Gu, S. Jiang, and N. Gans, “Nonlinear Systems Identification Using Deep Dynamic Neural Networks,” 2016, arXiv. doi: 10.48550/ARXIV.1610.01439.

. S. A. Hicks et al., “Machine Learning-Based Analysis of Sperm Videos and Participant Data for Male Fertility Prediction,” Sci. Rep., vol. 9, no. 1, p. 16770, Nov. 2019, doi: 10.1038/s41598-019-53217-y.

. WHO,.Infertility Prevalence Estimates, 1990–2021. Geneva, Switzerland: World Health Organization, 2023.

. R. Dcunha et al., “Current Insights and Latest Updates in Sperm Motility and Associated Applications in Assisted Reproduction,” Reprod. Sci., vol. 29, no. 1, pp. 7–25, Jan. 2022, doi: 10.1007/s43032-020-00408-y.

. M. Kraemer, C. Fillion, B. Martin-Pont, and J. Auger, “Factors influencing human sperm kinematic measurements by the Celltrak computer-assisted sperm analysis system,” Hum. Reprod., vol. 13, no. 3, pp. 611–619, Mar. 1998, doi: 10.1093/humrep/13.3.611.

. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.

. O. Shobayo and R. Saatchi, "Developments in Deep Learning Artificial Neural Network Techniques for Medical Image Analysis and Interpretation," Diagnostics, vol. 15, no. 9, Art. no. 1072, 2025, doi: 10.3390/diagnostics15091072.

. A. R. Pasaribu, S. Sawaluddin, S. Sitorus, and M. Syahputra, “Artificial Neural Networks Predict Covid-19 Cases in Indonesia Using the Backpropagation Method,” Leibniz J. Mat., vol. 4, no. 1, pp. 34–46, Jan. 2024, doi: 10.59632/leibniz.v4i1.388.

. B. Shi, "An Exploration of the Early Warning System for College Students' Academic Performance Based on BP Neural Network Driven by Multidimensional Data," International Journal of Web-Based Learning and Teaching Technologies, vol. 20, no. 1, pp. 1–19, 2025, doi: 10.4018/IJWLTT.384801.

F. Y. H. Ahmed, M. Al-Bahri, M. Zakarya, N. Khan, B. K. Joseph, and A. Abdullah, "Improving SpikeProp’s Training Efficiency in Spiking Neural Networks for Large Language Models Through Innovative Weight Initialization," Int. J. Comput. Intell. Syst., vol. 18, no. 1, Art. no. 286, 2025, doi: 10.1007/s44196-025-00961-x.

. E. M. S. Rochman et al., “Classification of.hypertension disease using Artificial Neural Network (ANN) backpropagation method case study in mitigating health risk: UPT Modopuro Mojokerto Health Center,” BIO Web Conf., vol. 146, p. 01083, 2024, doi: 10.1051/bioconf/202414601083.

. H. Qiu et al., “Comparative analysis of Kalman Filters, Gaussian Sum Filters, and Artificial Neural Networks for state estimation in energy management,” Energy Rep., vol. 13, pp. 4417–4440, Jun. 2025, doi: 10.1016/j.egyr.2025.03.054.

. R. Qamar and B. A. Zardari, "Artificial Neural Networks: An Overview," Mesopotamian Journal of Computer Science, vol. 2023, pp. 124–133, 2023, doi: 10.58496/MJCSC/2023/015.

. C. Liu and B. Ye, "Artificial neural network and the prospect of AGI: an argument from architecture," Discov. Artif. Intell., vol. 5, Art. no. 299, 2025, doi: 10.1007/s44163-025-00561-w.

. M. Guerra-Marín et al., "A convolutional neural network method to obtain the dynamic model parameters of a three-linear-axis Cartesian robot," Neural Comput. Appl., vol. 37, pp. 15439–15467, 2025, doi: 10.1007/s00521-025-11297-0.

. H. Taud and J. F. Mas, "Multilayer Perceptron (MLP)," in Geomatic Approaches for Modeling Land Change Scenarios, Cham: Springer, 2018, pp. 451–455, doi: 10.1007/978-3-319-60801-3_27.

. K. Danil, “Pengenalan Jenis Kelamin dalam Lingkungan Multiaksen Menggunakan Metode Multi-Layer Perceptron (MLP) dan Gated Recurrent Unit (GRU): Gender Recognition in a Multiaccent Environment Using Multi-Layer Perceptron (MLP) and Gated Recurrent Unit (GRU) Methods,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no. 3, pp. 803–811, May 2024, doi: 10.57152/malcom.v4i3.1323.

. D. Allan, T. Caswell, N. Keim, and C. van der Wel, trackpy: Trackpy v0.3.0. (Nov. 12, 2015). Zenodo. doi: 10.5281/ZENODO.34028.

. S. van der Walt, J. L. Schonberger, J. Nunez-Iglesias, F. Boulogne, J. D. Warner, N. Yager, E. Gouillart, and T. Yu, "scikit-image: image processing in Python," PeerJ, vol. 2, p. e453, Jun. 2014, doi: 10.7717/peerj.453.

. K. Dewan, T. R. Dastidar, and M. Ahmad, “Estimation of Sperm Concentration and Total Motility from Microscopic Videos of Human Semen Samples,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA: IEEE, Jun. 2018,.pp. 2380–2387. doi: 10.1109/CVPRW.2018.00307.

. F. Pedregosa et al., "Scikit-learn: Machine learning in Python," J. Mach. Learn. Res., vol. 12, pp. 2825–2830, Oct. 2011.

. J. Duchi, E. Hazan, and Y. Singer, "Adaptive subgradient methods for online learning and stochastic optimization," J. Mach. Learn. Res., vol. 12, pp. 2121–2159, Jul. 2011.

. M. D. Zeiler, "ADADELTA: An adaptive learning rate method," Dec. 22, 2012, arXiv: arXiv:1212.5701. doi: 10.48550/arXiv.1212.5701.

. H. B. McMahan et al., "Ad click prediction: a view from the trenches," in Proc. 19th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (KDD), Chicago, IL, USA, Aug. 2013, pp. 1222–1230. doi: 10.1145/2487575.2488200.

. D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," in Proc. 3rd Int. Conf. Learning Representations (ICLR), San Diego, CA, USA, May 2015. doi: 10.48550/arXiv.1412.6980.

. W. Zhao et al., “A Survey of Semen Quality Evaluation in Microscopic Videos Using Computer Assisted Sperm Analysis,” Feb. 17, 2022, arXiv: arXiv:2202.07820. doi: 10.48550/arXiv.2202.07820.

. V. Nair and G. E. Hinton, "Rectified linear units improve restricted Boltzmann machines," in Proc. 27th Int. Conf. Machine Learning (ICML), Haifa, Israel, Jun. 2010, pp. 807–814.

. M. J. Somers and J. C. Casal, “Using Artificial Neural Networks to Model Nonlinearity: The Case of the Job Satisfaction–Job Performance Relationship,” Organ. Res. Methods, vol. 12, no. 3, pp. 403–417, Jul. 2009, doi: 10.1177/1094428107309326.

. S. Sathyanarayanan, “Confusion Matrix-Based Performance Evaluation Metrics,” Afr. J. Biomed. Res., pp. 4023–4031, Nov. 2024, doi: 10.53555/AJBR.v27i4S.4345.

. S. Fatimah, “Neural Network Optimization Optimization For Medical Image Processing,” J. Komput. Indones., vol. 2, no. 1, pp. 33–40, Jun. 2023, doi: 10.37676/jki.v2i1.566.

. Elbert, M. Wulandari and J. Fat, "Optimizer Comparison In Convolutional Neural Network For Real Time Face Recognition," JurnaL EMACS (Engineering, Mathematics and Computer Science) Vol.7 No.1 January 2025: 15-24, doi: 10.21512/emacsjournal.v7i1.12058.