Urban and Rural Traffic Route Planning Method Based on Subcontrol Clustering Algorithm

Public transportation in cities and towns reflects the overall picture of a local transportation plan. Urban and rural public transportation networks play a key role in this reflection. Urban and rural transportation planning is not just a single way to achieve one-to-one integration of urban and rural transportation, but a comprehensive three-dimensional transportation planning. This study proposes a subcontrol clustering algorithm for urban and rural traffic route planning to address the challenges of integrated transportation network design. The proposed method uses the control-based [Formula: see text]-means (CB-[Formula: see text]-means) algorithm to optimize the selection of initial centroids by combining spatial density and distance metrics at the theoretical level. Specifically, the algorithm uses [Formula: see text]-nearest neighbor distance to calculate the neighborhood parameter (Eps) and iteratively optimizes the centroids based on density intensity and geometric interval. Experimental verification is based on a dataset of 350 traffic nodes, and the clustering accuracy reaches 80.33%, which is 7.78% higher than the traditional [Formula: see text]-means algorithm. The CB-[Formula: see text]-means algorithm also reduces the sum of squared errors by 55.1% (from 2693 to 1209) and the number of iterations by 51.4% (from 37 to 18). At the same time, spatial projection shows that the algorithm can effectively cluster around four centroids and identify outliers as noncritical infrastructure to achieve targeted pre-planning exclusion. Comparative analysis confirms the strong scalability of the algorithm, and parallel execution on eight computing nodes achieves a 3.7-fold acceleration. The results verify the effectiveness of the algorithm in hierarchical traffic node classification and route network optimization.