Machine Learning-Based Process Improvement in Optical Module Manufacturing Through Predictive Analytics
Received: 17 June 2025 | Revised: 27 August 2025 and 14 September 2025 | Accepted: 16 September 2025 | Online: 20 November 2025
Corresponding author: Busaba Phruksaphanrat
Abstract
This study aimed to enhance the optical module manufacturing process using Machine Learning (ML) by enabling early defect detection. The traditional step-by-step testing workflow (OPA, LOPT, OTSM, and OSET) results in excessive retesting cycles, increasing production time, and reducing overall efficiency. A structured method was employed, including data preparation, statistical hypothesis testing (t-test and F-test) for feature selection, and comparative evaluation across multiple ML models. Two prediction strategies were investigated: (i) a step-by-step model that predicts the outcome at each test stage, and (ii) a cross-step model that directly predicts the final OSET outcome from early-stage OPA data. The results show that the step-by-step prediction with XGBoost increased the total yield from 48.5% to 98.1%. Meanwhile, the cross-step prediction using Random Forest, leveraging early-stage OPA data, further improved the yield to 98.9%. In a real-world implementation involving 100 optical modules, the ML-based process reduced retesting from 53 units to only 3, saving approximately 795 minutes (13.25 hours) of testing time per batch while maintaining the same number of finished goods. These results demonstrate that ML-based predictive analytics can significantly improve process efficiency, minimize unnecessary retesting, reduce tester load, and accelerate production throughput without compromising product quality.
Keywords:
machine learning, optical module manufacturing, process improvement, predictive analytics, industrial AIDownloads
References
A. Affandi and O. AL-Rusaini, ''Implementation of Fiber Optic Communication System Using Developed Computer Program,'' IOSR Journal of Electrical and Electronics Engineering, vol. 11, no. 3, pp. 122–142, May 2016.
U. J. Umoga et al., ''Exploring the potential of AI-driven optimization in enhancing network performance and efficiency,'' Magna Scientia Advanced Research and Reviews, vol. 10, no. 1, pp. 368–378, Feb. 2024. DOI: https://doi.org/10.30574/msarr.2024.10.1.0028
M. I. H. Okfie and S. Mishra, ''Anomaly Detection in IIoT Transactions using Machine Learning: A Lightweight Blockchain-based Approach,'' Engineering, Technology & Applied Science Research, vol. 14, no. 3, pp. 14645–14653, Jun. 2024. DOI: https://doi.org/10.48084/etasr.7384
M. Zeng and C. Chen, ''Design of High-speed Data Transmission System Based on Fiber-PCIE,'' Frontiers in Business, Economics and Management, vol. 7, no. 3, pp. 84–89, Feb. 2023. DOI: https://doi.org/10.54097/fbem.v7i3.5397
H. Bichri, A. Chergui, and M. Hain, ''Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets,'' International Journal of Advanced Computer Science and Applications, vol. 15, no. 2, 2024. DOI: https://doi.org/10.14569/IJACSA.2024.0150235
B. Gerald, ''A Brief Review of Independent, Dependent and One Sample t-test,'' International Journal of Applied Mathematics and Theoretical Physics, vol. 4, no. 2, p. 50, 2018. DOI: https://doi.org/10.11648/j.ijamtp.20180402.13
R. Odek and G. Opuodho, ''F-test and P-values: A synopsis,'' Journal of Management and Science, vol. 13, no. 2, pp. 59–61, June 2023. DOI: https://doi.org/10.26524/jms.13.22
H. A. Salman, A. Kalakech, and A. Steiti, ''Random Forest Algorithm Overview,'' Babylonian Journal of Machine Learning, vol. 2024, pp. 69–79, June 2024. DOI: https://doi.org/10.58496/BJML/2024/007
A. Natekin and A. Knoll, ''Gradient boosting machines, a tutorial,'' Frontiers in Neurorobotics, vol. 7, no. 21, pp. 1–21, 2013. DOI: https://doi.org/10.3389/fnbot.2013.00021
Z. A. Ali, Z. H. Abduljabbar, H. A. Tahir, A. B. Sallow, and S. M. Almufti, ''eXtreme Gradient Boosting Algorithm with Machine Learning: a Review,'' Academic Journal of Nawroz University, vol. 12, no. 2, pp. 320–334, May 2023. DOI: https://doi.org/10.25007/ajnu.v12n2a1612
R. Qamar and B. A. Zardari, ''Artificial Neural Networks: An Overview,'' Mesopotamian Journal of Computer Science, vol. 2023, pp. 124–133, Aug. 2023. DOI: https://doi.org/10.58496/MJCSC/2023/015
C. Y. J. Peng, K. L. Lee, and G. M. Ingersoll, ''An Introduction to Logistic Regression Analysis and Reporting,'' The Journal of Educational Research, vol. 96, no. 1, pp. 3–14, Sept. 2002. DOI: https://doi.org/10.1080/00220670209598786
H. H. Patel and P. Prajapati, ''Study and Analysis of Decision Tree Based Classification Algorithms,'' International Journal of Computer Sciences and Engineering, vol. 6, no. 10, pp. 74–78, Oct. 2018. DOI: https://doi.org/10.26438/ijcse/v6i10.7478
A. P. Wibawa et al., ''Naïve Bayes Classifier for Journal Quartile Classification,'' International Journal of Recent Contributions from Engineering, Science & IT (iJES), vol. 7, no. 2, June 2019, Art. no. 91. DOI: https://doi.org/10.3991/ijes.v7i2.10659
P. Cunningham and S. J. Delany, ''K-Nearest Neighbour Classifiers - A Tutorial,'' ACM Computing Surveys, vol. 54, no. 6, pp. 1–25, July 2022. DOI: https://doi.org/10.1145/3459665
M. M. Abdulrazzaq, I. F. Yaseen, S. A. Noah, and M. A. Fadhil, ''Multi-Level of Feature Extraction and Classification for X-Ray Medical Image,'' Indonesian Journal of Electrical Engineering and Computer Science, vol. 10, no. 1, pp. 154–167, Apr. 2018. DOI: https://doi.org/10.11591/ijeecs.v10.i1.pp154-167
H. Dong, R. Liu, and A. W. Tham, ''Accuracy Comparison between Five Machine Learning Algorithms for Financial Risk Evaluation,'' Journal of Risk and Financial Management, vol. 17, no. 2, Jan. 2024, Art. no. 5. DOI: https://doi.org/10.3390/jrfm17020050
E. J. Michaud, Z. Liu, and M. Tegmark, ''Precision Machine Learning,'' Entropy, vol. 25, no. 1, Jan. 2023, Art. no. 175. DOI: https://doi.org/10.3390/e25010175
D. M. W. Powers, ''Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation,'' Journal of Machine Learning Technologies, vol. 2, no. 1, pp. 2229–3981, 2011.
M. Sokolova, N. Japkowicz, and S. Szpakowicz, ''Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation,'' in AI 2006: Advances in Artificial Intelligence, vol. 4304, A. Sattar and B. Kang, Eds. Springer Berlin Heidelberg, 2006, pp. 1015–1021 DOI: https://doi.org/10.1007/11941439_114
M. Majnik and Z. Bosnić, ''ROC analysis of classifiers in machine learning: A survey,'' Intelligent Data Analysis, vol. 17, no. 3, pp. 531–558. DOI: https://doi.org/10.3233/IDA-130592
Y. Lee and Y. Roh, ''An Expandable Yield Prediction Framework Using Explainable Artificial Intelligence for Semiconductor Manufacturing,'' Applied Sciences, vol. 13, no. 4, Feb. 2023, Art. no. 2660. DOI: https://doi.org/10.3390/app13042660
A. Polenta, S. Tomassini, N. Falcionelli, P. Contardo, A. F. Dragoni, and P. Sernani, ''A Comparison of Machine Learning Techniques for the Quality Classification of Molded Products,'' Information, vol. 13, no. 6, May 2022, Art. no. 272. DOI: https://doi.org/10.3390/info13060272
Downloads
How to Cite
License
Copyright (c) 2025 Nattapon Wongngern, Busaba Phruksaphanrat
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
