EUVIMEDEUVIMED entdecken
Crossref

Predicting Multi-KPI Warehouse Dynamics: A Simulation-Based Evaluation of Fuzzy-Integrated Neural Architectures

Mohamed Amine Frikha

International Journal of Advanced Computer Science and Applications · 2026 · 17 (9)

DOI: 10.14569/ijacsa.2026.0170934 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Computer Science and Applications, 2026. Verfasst von Mohamed Amine Frikha. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Warehouse order fulfillment is governed by complex, nonlinear interactions among order arrivals, picking workload, congestion, replenishment, labor, equipment, and dispatch capacity. This study proposes a simulation-based predictive framework that compares a global multilayer perceptron (MLP) with a fuzzy-integrated modular architecture comprising three regime-specific local neural networks. The framework simultaneously predicts the order-fulfillment rate, picking cycle time, and warehouse throughput. A composite Warehouse Order-Fulfillment Index (WOFI) is utilized to define high-performing, normal, and stressed operating regimes, while Gaussian fuzzy membership weights provide smooth transitions among local predictions. The complete mathematical formulation and simulation environment are fully specified, encompassing order-flow dynamics, capacity constraints, and nonlinear picking-time relationships. Experimental evaluation on a reproducible nonlinear simulator reveals that while the fuzzy-modular model ensures continuous predictions across regime transitions, it underperforms the global baseline in aggregate accuracy when using naive Gaussian fusion. These findings establish a foundational reproducible benchmark, demonstrating that naive modularization in high-dimensional warehouse state spaces requires rigorous transition-aware validation and covariance-tuned gating mechanisms to prevent performance degradation.

Zitieren

APA

Frikha, M. A. (2026). Predicting Multi-KPI Warehouse Dynamics: A Simulation-Based Evaluation of Fuzzy-Integrated Neural Architectures. International Journal of Advanced Computer Science and Applications, 17(9). https://doi.org/10.14569/ijacsa.2026.0170934

Vancouver

Frikha MA. Predicting Multi-KPI Warehouse Dynamics: A Simulation-Based Evaluation of Fuzzy-Integrated Neural Architectures. International Journal of Advanced Computer Science and Applications. 2026;17(9). doi:10.14569/ijacsa.2026.0170934

BibTeX
@article{Frikha2026,
  author = {Frikha, Mohamed Amine},
  title = {Predicting Multi-KPI Warehouse Dynamics: A Simulation-Based Evaluation of Fuzzy-Integrated Neural Architectures},
  journal = {International Journal of Advanced Computer Science and Applications},
  year = {2026},
  volume = {17},
  number = {9},
  doi = {10.14569/ijacsa.2026.0170934}
}
Kostenlos starten →