DR-XGBoost: An XGBoost model for field-road segmentation based on dual feature extraction and recursive feature elimination

The study of patterns of crowd flows represents an emerging and expanding research field. The most straightforward and efficient approach to investigate the patterns of crowd flows is to concentrate on traffic flow. However, assessments of simple point-to-point movement frequently lack universal validity, and little research has been conducted on the regularity of nighttime movement. Due to the suspension of public transportation at night, taxi orders are critical in capturing the features of nighttime crowd flows in a tourism city. Using Haikou as an example, this paper proposes a mixed Geogrid Spatio-temporal model (MG-STM) for the tourism city in order to address the challenges. Firstly, by collecting the pick-up/drop-off/in-out flow of crowds, this research uses DCNMF dimensionality reduction to extract semi-supervised spatio-temporal variation features and the K-Means clustering method to determine the cluster types of nighttime crowd flows’ changes in each geogrid. Secondly, by constructing a mixed-evaluation model based on LJ1-01 nighttime light data, crowd flows’ clusters, and land use data in geogrid-based regions, the pattern of nighttime crowd flows in urban land use areas is successfully determined. The results suggest that MG-STM can estimate changes in the number of collective flows in various regions of Haikou effectively and appropriately. Moreover, population density of land use areas shows a high positive correlation with the lag of crowd flows. Each 5% increase in population density results in a 30-min delay in the peak of crowd flows. The MG-STM will be extremely beneficial in developing and implementing systems for criminal tracking and pandemic prevention.

As a core component of automated logistics systems, delivery robots hold significant application value in the field of unmanned delivery. This research addresses the robot path planning problem, aiming to enhance delivery efficiency and reduce operational costs through systematic improvements to the RIME optimization algorithm. Through in-depth analysis, we identified several major drawbacks in the standard RIME algorithm for path planning: insufficient global exploration capability in the initial stages, a lack of diversity in the hard RIME search mechanism, and oscillatory phenomena in soft RIME step size adjustment. These issues often lead to undesirable phenomena in path planning, such as local optima traps, path redundancy, or unsmooth trajectories. To address these limitations, this study proposes the Multi-Strategy Controlled Rime Algorithm (MSRIME), whose innovation primarily manifests in three aspects: first, it constructs a multi-strategy collaborative optimization framework, utilizing an infinite folding Fuch chaotic map for intelligent population initialization to significantly enhance the diversity of solutions; second, it designs a cooperative mechanism between a controlled elite strategy and an adaptive search strategy that, through a dynamic control factor, autonomously adjusts the strategy activation probability and adaptation rate, expanding the search space while ensuring algorithmic convergence efficiency; and finally, it introduces a cosine annealing strategy to improve the step size adjustment mechanism, reducing parameter sensitivity and effectively preventing path distortions caused by abrupt step size changes. During the algorithm validation phase, comparative tests were conducted between two groups of algorithms, demonstrating their significant advantages in optimization capability, convergence speed, and stability. Further experimental analysis confirmed that the algorithm’s multi-strategy framework effectively suppresses the impact of coordinate and dimensional differences on path quality during iteration, making it more suitable for delivery robot path planning scenarios. Ultimately, path planning experimental results across various Building Coverage Rate (BCR) maps and diverse application scenarios show that MSRIME exhibits superior performance in key indicators such as path length, running time, and smoothness, providing novel technical insights and practical solutions for the interdisciplinary research between intelligent logistics and computer science.

Feature deformation network with multi-range feature enhancement for agricultural machinery operation mode identification