Even though The Netherlands is considered as the number 1 cycling country, there are signs that cycling in the country is getting more stressful. The number of cyclists that suffer from severe injury in traffic accidents is increasing – in recent years with almost 30%. And an experiment in Utrecht showed that a substantial amount of woman feels unsafe when cycling alone at night-time.
To understand better when and to what extent cyclists feel mental and bodily stress, wearable wristbands have been used. Several studies showed the potential of using wristband data to understand how much stress cyclists experience. Also, a library for physiological data analysis is available. However, there is no widespread consensus yet about how to use machine learning methods for analysing cycling stress levels.
The main objective of the student is to investigate to what extent various machine learning methods are valuable for classifying wearable stress data into levels of cycling stress. The prospective student is expected to start with creating a short but concise planning for the module. This plan should include a literature review; formulation of definitions, research questions and methods; and a data collection setup. Then, data collection is to be conducted, after which data analysis can start and this analysis should comprise the majority of the work. Earlier work by another student who worked on a similar topic may be re-used. The student should finish with a comprehensive report.
25% theory, 50% practical, 25% report
Mario Boot – email@example.com