Group 1: SMT is collected by one type of transport mode during moving, hence no segmentation
is required. The mechanism of SMT classification based on transport mode has two main steps:
features computation (also called movement parameters computation) and classification. The main
challenge to a successful classification of all GPS data is how to select effective descriptors from a
mass of features and improve the efficiency of classification, as shown in Figure 3.
Group 2: MMT is collected by multiple modes of transport, so it is necessary to recognize the
transition points or activity episodes between modes (see Figure 3). Therefore, MMT classification,
apart from the face of the same challenge of SMT classification, more time is needed to be addressed transition points or activity episodes recognition with high accuracy.
lien :https://www.mdpi.com/1424-8220/18/11/3741/pdf/1
Metedology :we propose a method to identify six different transportation modes including
walking, cycling, driving a car, taking a train and taking subway using GPS data. The main modules
of our methodology for identifying transportation modes is shown in Figure 1 and includes data
preprocessing, feature extraction, model classification and model evaluation. Raw GPS data were
first preprocessed into trajectories, and then global and local features were extracted before using
the ensemble method to classify the different transportation modes. From the ensemble method,
we obtained the important extracted features and removed the unimportant features, before results
were finally obtained. Each step is detailed in the following sections.