Data mining techniques to analyze the factors influencing active commuting to school

Abstract

The health benefits of active commuting to school in children and adolescents have been widely researched in the last few years, and it is currently of interest to detect the factors that could influence active commuting in a positive or a negative way. In this study, data mining techniques were applied to a sample of 6979 students aged 5–20 years old from south-eastern Spain to analyze what factors influenced their commuting behavior. Several data mining techniques, such as association rules, decision trees, and cluster analyses, were used to examine these influences. The results proved that active commuting could be influenced by several factors. The main factor seemed to be the distance to school; a threshold between 1100 and 1600 m was the distance at which students changed from an active to a passive mode of commuting. We also detected that specific meteorological conditions could influence active commuting in some way. Finally, some factors such as older ages and living in urban areas (as opposed to rural areas) were associated with active modes of commuting. These results prove that data mining techniques are appropriate to further the knowledge in the active commuting field.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 19 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.