Travel Behavior Characterization Using Raw Accelerometer Data Collected from Smartphones

Abstract

In this paper, we compare different algorithms for the recognition of transportation modes based on features extracted from the accelerometer data. The performance and effectiveness of the transportation mode classifiers presented is evaluated and their accuracy is discussed. The data set used for training and testing algorithms was collected by a group of volunteers in the city of Valencia in 2013; an Android application designed for the recording of trips and transportation modes application was installed on their smartphones. This application collected GPS readings each 10-12 seconds and accelerometer data at 1Hz. While GPS data was only used for the validation of trips for the training of the algorithms, accelerometer readings were used entirely for their training. Results show the high performance of Recurrent Neural Networks in recognizing travel modes using accelerometer data.

Automatic Trip Detection with the Dutch Mobile Mobility Panel: Towards Reliable Multiple-Week Trip Registration for Large Samples

“…Most studies report an average accuracy between 70 and 80 percent (Biljecki et al, 2013). Reported success rates for automatic mode detection are beyond 80 percent in several studies (e.g., Gong et al, 2012;Shin et al, 2015;Rasmussen et al, 2015;Nitsche et al, 2014) and in some cases even beyond 90 percent (e.g., Feng and Timmermans, 2013;Ferrer and Ruiz, 2014). The difference in predicted accuracy depends not only on the algorithm, but also on the number of identified transportation modes, type of input variables, urban setting, and data used to validate the algorithms.…”

“…Various methods have been used to detect modes. In general, a training set is used to let a mathematical algorithm "learn" to recognize the correct mode, e.g., by Bayesian belief networks Timmermans, 2013, Xiao et al, 2015) recurrent neural networks (Ferrer and Ruiz, 2014), and Markov chains (Nitsche et al, 2014). In some cases, geographical context data is added to improve the mode detection algorithm.…”

Driving Behaviour Style Study with a Hybrid Deep Learning Framework Based on GPS Data

“…Dong et al [38] proposed an autoencoder regularized deep neural network combining supervised and unsupervised learning. Ferrer and Ruiz [20] were using data extracted from GPS and GIS, compared five classification models including Decision Tree, Bayesian Network, Random Forest, Naïve Bayesian and Neural Network to identify travel patterns. In recent years, there is a growing body of evidence to suggest that competitive learning outperforms traditional clustering methods.…”

“…Zheng et al [18] have suggested that the new social transportation field should focus on traffic analytics with big data using data mining, machine learning, and crowdsourcing mechanisms. Smartphone-based travel surveys are generally conducted using personal devices and navigation apps; they offer a key benefit in reducing both the cost of data collection and that of distributing and retrieving the hardware [19][20][21]. Most navigation applications utilize the mobile device, built-in GPS, to provide real-time location, route, traffic, parking, energy consumption and ride-sharing information [22].…”

Distributed and adaptive location identification system for mobile devices

“…In fact, mobile devices are no longer used only for conventional communication services, but also to provide advanced sensing capabilities due to powerful sensors equipped within, including motion sensors (e.g., gyroscope and accelerometer) and location sensors (e.g., GPS and Wi-Fi). Hence, the valuable sensed location can be leveraged in many different locationdependent applications and research projects such as mobile-based travel surveys for urban planning [2,3], tracking systems [4], and environmental solutions to estimate emission of CO 2 [5,6]. Indeed, there are endless potential solutions for existing real-life problems.…”