SVD-based adaptive fuzzy for generalized transportation

Abstract

This research stems from the urgent need to address the complex challenges faced in multimodal transportation within the cargo sector, particularly concerning the reduction of transportation costs and CO2 emissions. Existing transportation systems often struggle to efficiently balance economic and environmental concerns, necessitating innovative solutions. In this paper, we have introduced a novel mathematical model that integrates Singular Value Decomposition (SVD), Genetic Algorithms (GA), and the Adaptive Neural Fuzzy Inference System (ANFIS). The synergy of GA and the ANFIS forms a dynamic learning system that continually refines solutions by adapting to historical decisions and aligning with supply-demand dynamics. This integrated approach aims to optimize cost allocation and resource utilization while simultaneously minimizing CO2 emissions. Deploying the ANFIS+GA+SVD model in multimodal scenarios yields impressive results, with a minimal average percentage error (MAPE) of 0.28% for transportation costs and a remarkable coefficient of determination R2 of 0.992 for the Truck + Ship scenario. Similarly, a MAPE of 0.11% for CO2 emissions, supported by an impressive R2 of 0.989, underscores the model's accuracy. Observations of people's transportation choices in response to emission price changes reveal a significant decrease in truck usage, plummeting from 84% to below 50%. Alternative transportation methods, especially in the 3S-3 M-3 C scenario, show a substantial surge, with railways leading at a remarkable 30% increase in utilization. The combined quantity and cost comparison, utilizing the ANFIS+GA+SVD model, emphasizes the suitability of the Truck + Ship scenario for Iraq's transportation network, reinforcing the case for sustainable and efficient multimodal transportation systems.

Keywords

• Genetic algorithm
• Fuzzy neural networks
• Multimodal transportation
• SVD decomposition
• Iraq Transportation network