An intelligent approach for optimizing sugarcane transporting cost and logistics management

Abstract

Sugarcane transportation is one of the significant expenses of sugar production. This paper addresses sugarcane transportation costs and logistics systems to offer the mill a proper quality and quantity of sugarcane. This study aimed to optimize transportation costs and sugarcane quality to produce at the mill. A new approach, Lyrebird-based Sequence Neural Network (LbSNN), is proposed to focus specifically on optimizing transportation costs and logistics management. It involves a pre-processing function to filter out noisy data to ensure cleaner and more reliable input for further analysis. The Lyrebird optimization method is then used to perform a feature analysis, which efficiently allows the selection of the most relevant features from the dataset to improve decision-making accuracy. Consequently, the sequence neural network is designed to optimize transportation costs and ease the process of logistics management. The efficacy of the suggested approach is assessed using several performance criteria, including recall 99.9%, precision 99.9%, accuracy 99.9%, f-score 99.9% and error rate 0.1%. The outcomes demonstrate that the proposed technique effectively handles logistics and transportation problems.