Transportation mode detection is one of the major challenges in GPS-based travel surveys. This study presents attempts to impute modes from data collected by smartphone in Hanoi (Vietnam), where the dominant mode is the motorcycle. The inclusion of the motorcycle mode and an imbalance in the modal share of the Hanoi data resulted in the ineffective use of supervised-learning models to detect all modes simultaneously. To gain a high level of accuracy and reasonable interpretability, a hierarchical process was developed. At first, walk, bicycle, and motorized modes were identified by a fuzzy logic-based algorithm. Subsequently, based on the distribution of bus stops and the operation of buses in practice, rules using the average distance between stops that a vehicle passed slowly or stopped at were introduced to detect bus segments. Finally, a random forest model was built to distinguish the modes of motorcycle and car. The proposed hierarchical process achieved an accuracy level of 89.1%. The bus detection, which required coordinates of bus stops solely, achieved a recall of 87.2%. The mode of motorcycle was the main source of misclassification. Including the motorcycle mode has contributed to the diversity of the mode detection field, which has previously focused on walk, bicycle, car, bus/tram, and train. The hierarchy was developed and validated by using a dataset that did not include travel by metro or train and would be biased toward persons working and studying at a university. These limitations emphasize the need to test the process on a more diverse sample with more travel options.