CyclIST Weight Inference
Problem Statement
Inertial Measurement Units (IMUs) can measure vibration and rotational motion, and have been used on bicycles to get insights about road quality, fall detection, maneuver prediction, etc. IMUs usually not known to contain sensitive data. But how can we know for sure? We believe that with the right combination of data, we could deduce certain sensitive insights such as the weight of the cyclist. Our goal with this research project is to examine to what extent the cyclist's weight can be determined.
Tasks
Analyze IMU data from 2 datasets:
- From 1 cyclist with simulated weights, collected using a weight vest in a controlled experiment. IMUs are placed under the seat, the front frame, and the rear frame (close to the wheel)
- From multiple cyclists, collected in the real world. IMUs are placed on the frame, pedal, and handlebar.
Develop a model that can classify the weights of cyclists based on IMU data. Your tasks are:
Literature study (10%)
Data Analysis (20%)
Building the model(s) (40%)
Evaluation the Writing (30%)
You will be provided with the raw dataset.
Contact
Deepak Yeleshetty (d.yeleshetty@utwente.nl)