What does this research mean for the field?

Integrating machine learning-based predictive modeling with analytical queueing assessment provides an effective framework for optimizing workforce planning and capacity assessment in manufacturing systems. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

Develop an integrated predictive-prescriptive framework combining machine learning and queueing theory to optimize workforce planning and evaluate operational capacity in weaving manufacturing systems.

August 29, 2026ProcessesOpen Access

Data-Driven Workforce Optimization in Weaving Manufacturing Systems: An Integrated Machine Learning and Queueing Framework

View Full Paper

Ask AI

Bookmark

Authors

BKBilge Berkhan KastaciTekirdağ Namık Kemal University

Discussion

Member takes

Implication

Modeling study demonstrates accurate workforce prediction and capacity assessment in weaving manufacturing systems, highlighting the value of combining regression with queueing models.

Key Points

Develop an integrated predictive-prescriptive framework combining machine learning and queueing theory to optimize workforce planning and evaluate operational capacity in weaving manufacturing systems.
Analyzed 12 months of operational data capturing warp and weft breakage frequencies, repair durations, and workforce requirements across multiple production halls.
Trained and evaluated multiple linear regression and tree-based machine learning models—including M5P, REPTree, Random Forest, and Random Tree—using cross-validation and independent testing.
Incorporated predicted integer staffing levels into an analytical M/M/c queueing model to evaluate system utilization, expected waiting times, queue lengths, and capacity pressures.
Multiple linear regression demonstrated the highest predictive accuracy and stability among all tested algorithms (R² > 0.93).
Analytical M/M/c queueing evaluation revealed substantial hall-specific variations in capacity utilization, worker waiting times, and capacity pressure.

Cite This Study

Bilge Berkhan Kastaci (2026) studied this question.

synapsesocial.com/papers/6a9299db8e5d7d1fc0c121b1 https://doi.org/10.3390/pr14172745

View Full Paper

Ask AI

Bookmark

Implication

Modeling study demonstrates accurate workforce prediction and capacity assessment in weaving manufacturing systems, highlighting the value of combining regression with queueing models.

Data-Driven Workforce Optimization in Weaving Manufacturing Systems: An Integrated Machine Learning and Queueing Framework

Discussion

Member takes

Implication

Key Points

Cite This Study

Data-Driven Workforce Optimization in Weaving Manufacturing Systems: An Integrated Machine Learning and Queueing Framework

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider