GPS and Acceleration Data in Multimode Trip Data Recognition Based on Wavelet Transform Modulus Maximum Algorithm

Abstract

The GPS-based travel survey is an emerging data collection method in transportation planning. The survey's application in trip mode detection has been explored in many studies. Most research on trip mode detection methods based on GPS data has been developed and tested with data collected from European and American countries. The methods cannot be easily adapted to Asian countries such as China, India, and Japan, which have much higher population densities, more complex road networks, and highly mixed travel modes during daily commuting. Furthermore, for trip segment division in multimode travel, existing algorithms use travel time and distance thresholds that are highly dependent on local travel behavior and lack universality across traffic environments. This paper proposes an innovative framework for detecting trip modes in complex urban environments. First, a smartphone application, GPSurvey, was developed to collect passive GPS trace data. Then a wavelet transform modulus maximum algorithm was developed for trip segment division. The algorithm has outstanding capabilities for identifying singularity features of a signal; this factor suits the task of detecting mode changes in a complex traffic environment. A neural network module was developed for mode detection on the basis of cell phone GPS location and acceleration data. The results indicate that the proposed method has promising performance. The average absolute detection error of mode transfer time was within 1 min, and the accuracy for detecting all modes was greater than 85%.