Spatial objects classification using machine learning and spatial walk algorithm

Abstract This article presents a novel method for classifying spatial objects by learning node representations via walk algorithm. The findings show that considering both the attributes of and their topological relationships enables more efficient precise objects’ classification than methods only consider characteristics. emphasizes importance dependencies in data. A distinctive feature is its focus on local analysis neighborhood structure under investigation. algorithm offers defined path generation scheme, facilitating deeper understanding between objects. approach provides accurate representation essential random enhances results, as demonstrated three different scenarios. proves particularly effective context objects, where proximity limited number neighbors play significant role. exemplified planning areas development plans.