A Bio-Inspired Data-Driven Hybrid Optimization Framework for Task Unit Partition in Cruise Itinerary Planning.

Area of Science:

• Operations Research
• Data Science
• Bio-inspired Computing

Background:

• Cruise tourism faces challenges in personalized itinerary planning due to resource constraints and limitations of traditional clustering methods.
• Existing methods struggle to balance passenger preferences with venue capacities, impacting planning quality and operational efficiency.

Purpose of the Study:

• To propose a novel bio-inspired, data-driven hybrid optimization framework for cruise itinerary planning.
• To enhance the operational efficiency and service quality of cruise tourism through intelligent passenger segmentation and resource allocation.

Main Methods:

• Integration of Genetic Balanced Clustering Algorithm (GBCA) for multi-objective passenger grouping.
• Utilizing Kernel Principal Component Analysis (KPCA) for preference data feature extraction.
• Employing an improved Adaptive Spiral Flying Sparrow Search Algorithm (ASFSSA) for hyperparameter optimization.
• Implementing Kernel Extreme Learning Machine (KELM) for predicting itinerary planning quality.

Main Results:

• The proposed framework significantly outperforms conventional methods in cruise itinerary planning.
• Achieved at least a 40% improvement in segmentation quality.
• Demonstrated superior convergence speed and stability in simulated cruise scenarios.

Conclusions:

• The developed framework offers a scalable and intelligent solution for resource-constrained scheduling problems in cruise tourism.
• Highlights the effectiveness of bio-inspired, data-driven methodologies in engineering optimization.
• Enables dynamic venue capacity allocation based on group preferences for maximized benefits, load balance, and fairness.