Transportation Mode Detection by Using Smartphones and Smartwatches with Machine Learning

Application of machine learning to predict transport modes from GPS, accelerometer, and heart rate data

“…Deep learning methods require more pre-processing, have complex training processes, and are computationally expensive compared to RF. According to Hasan et al RF was the most accurate in identifying different transport modes when comparing Extreme Gradient Boosting, RF, SVM, and ANN in their study, where they used GPS, accelerometer, and heart rate data at trip level [ 41 ]. They employ a similar web-based application for trip generation as we used to identify trips and trip stages in the GPS-based mobility survey.…”

“…We examined the added impact of heart rate in the prediction, assessed the impact of splitting observations at the participant level rather than at the observation level during the estimation procedure, and we investigated the influence of bandwidth size during the post-processing moving average on the final prediction rate. Various recent studies have approached transport mode detection with different methods like classical machine learning techniques (RF, SVM) [40,41], Convolutional Neural Network (CNN) [42], Long Short-Term Memory (LSTM) [43], Temporal Convolutional Network (TCN) [44], Multilayer Perceptron (MLP) [45]. Some have used multiple algorithms as an evaluation of their chosen method in their study [40][41][42][44][45][46].…”

“…Various recent studies have approached transport mode detection with different methods like classical machine learning techniques (RF, SVM) [40,41], Convolutional Neural Network (CNN) [42], Long Short-Term Memory (LSTM) [43], Temporal Convolutional Network (TCN) [44], Multilayer Perceptron (MLP) [45]. Some have used multiple algorithms as an evaluation of their chosen method in their study [40][41][42][44][45][46]. For example, Alotaibi, in their article, presents an ensemble method that utilized a combination of three different machine learning algorithms for classification or model learning [45].…”

“…We attempted to overcome this problem by using heart rate data, which Mantellos et al [47] report as a potential improvement for their future work by following a hierarchical classification approach like RF, and for classifying different motorized and non-motorized transportation modes. Some recent studies have also used shorter window sizes (ranging from 5 to 8.7 s) [43,44,46] while others used trips [40][41][42] for the transport mode detection in their study.…”

Kick-scooters identification in the context of transportation mode detection using inertial sensors: Methods and accuracy

“…Recent TMD surveys can be found in Sadeghian, Håkansson, and Zhao (2021), Kamalian, Ferreira, and Jul (2022), Ahmed and Diaz (2022). Historically, the main devices used were first GPS loggers Biancat, Brighenti, and Brighenti (2014), Roy, Fuller, Nelson, and Kedron (2022) and then smartphones Carpineti, Lomonaco, Bedogni, Di Felice, and Bononi (2018), Sharma, Singh, Udmale, Singh, and Singh (2021), Wang, Luo, Zhao, and Qin (2021), Liu (2022), which are still in use at the present, although a recent study has explored the use of smartwatches to perform TMD, see Hasan, Irshaid, Alhomaidat, Lee, and Oh (2022). The chosen technologies used for TMD purposes, regardless of the device, have evolved from the use of standalone GPS receivers Zheng, Liu, Wang, and Xie (2008), often fused with Geographical Information Systems (GIS) Gong, Chen, Bialostozky, and Lawson (2012), Shah, Wan, Lu, and Nachman (2014), in favor of proprioceptive low-cost sensors due to their energy-efficiency and availability in off-the-shelf devices such as smartphones, see Yu, Yu, Wang, Lin, and Chang (2014).…”