Personalized Operator Assignment Method for Fair Workload Distribution in Industry 5.0 Job Shop Scheduling

Conventional job shop scheduling approaches frequently overlook operator well-being. This work proposes Hierarchical Optimization for Dynamic Operator Assignment (HODA), a personalized assignment method that balances operator workloads by leveraging physiological operator data including age, weight, height, and heart rate. The Adaptive Neuro-Fuzzy Inference System (ANFIS) estimates each operator's energy expenditure, and the Ant Workload Balance Optimizer (AWBO) allocates tasks to minimize the variance of cumulative workloads among operators. Experimental results show that HODA outperforms two benchmark methods and is practical for industrial deployment thanks to its modular design and the widespread availability of affordable wearable devices for hearth rate monitoring. By accurately capturing the actual effort experience by operator, energy expenditure metrics provide a more reliable measure of workload than task duration alone, aligning with human-centric scheduling of Industry 5.0.