TrailSense: A Crowdsensing System for Detecting Risky Mountain Trail Segments with Walking Pattern Analysis

摘要: Trail surface information is critical in preventing from the mountain accidents such as falls and slips. In this paper, we propose a new mobile crowdsensing system that automatically infers whether trail segments are risky to climb by using sensor data collected multiple hikers’ smartphones. We extract cyclic gait-based features walking motion train machine learning models, results then aggregated for robust classification. evaluate our with two real-world datasets. First, 14 climbers which includes 13 segments. The average accuracy of individuals approximately 80%, but after clustering results, can accurately identify all an additional dataset five different trails, have 10 total. Our show model trained one be used other trail, documents generalizability system.