VehicleSense: Transportation Mode Detection Using Sound Data with an Acceleromter-based Trigger System

Abstract

A new transportation mode recognition system for smartphones, VehicleSense that is widely applicable to mobile context-aware services is proposed. VehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured while being on candidate transportations in a unique way. To attain the high energy efficiency, VehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the built-in microphone of smartphones. Further, to attain the high accuracy and the low latency, VehicleSense manipulates the sampled sound with non-linear filters that are shown to lead to substantial performance improvement. Our 186-hour log of sound and accelerometer data collected by seven different Android smartphone models confirms that VehicleSense shows 98.2% of recognition accuracy with only 0.6 seconds of latency, while consuming only about 26.1 mW on average for all day monitoring.