University of Twente Student Theses
Online travel mode detection on a smartphone
Buist, H.A. (2020) Online travel mode detection on a smartphone.
PDF
3MB |
Abstract: | A classification model for travel mode detection is developed. The input for the model is collected with a triaxial accelerometer integrated in a smartphone. The classification model is based on logistic regression. Four extensions based on logic reasoning are suggested. The developed model is tested using five test cases. Accelerometer based classification does a good job for non-motorized travel modes, such as walking and cycling. However, motorized travel modes are more difficult to classify using only accelerometer data. Using the proposed algorithmic approach, an overall accuracy of 50.0% could be obtained. |
Item Type: | Essay (Master) |
Clients: | Mobidot B.V. |
Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
Subject: | 31 mathematics, 55 traffic technology, transport technology |
Programme: | Applied Mathematics MSc (60348) |
Link to this item: | https://purl.utwente.nl/essays/84922 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page