Evaluation of Highway Transportation Service Quality Based on Big Data

The rapid advancement of transportation systems has led to an increased emphasis on evaluating and improving the quality of highway travel services. With the proliferation of big data technologies, there is a growing opportunity to leverage large-scale data analytics for comprehensive service quality assessment. This paper explores a novel methodology that integrates neural networks and genetic algorithms to evaluate highway travel service quality, addressing the complexities and challenges posed by the modern transportation landscape. In response to the shortcomings of random initialization of BP neural network parameters, this paper first proposes improvements to genetic algorithms from various perspectives. The enhanced genetic algorithm is then employed for optimizing the initial parameters of the BP network, followed by the training of the BP network to construct the final network used for evaluating the quality of public transportation services. The outcomes of this study are expected to drive advancements in transportation management strategies, fostering a more efficient, safe, and user-centric highway travel experience. The fusion of big data analytics, neural networks, and genetic algorithms opens avenues for continuous improvement and innovation in the realm of transportation services, ultimately benefiting both travelers and service providers alike.