Abstract
Proof of concept automatic detection
This report summarizes a proof-of-concept study of the feasibility of developing a smart
Dual Air blow-dryer that automatically provides feedback on its use. We successfully
demonstrated feasibility by automatically identifying the right and wrong use of Dual Air
by using machine learning on data from IMU sensors mounted on the blow-dryer. Video
pose estimation from the study also documented that the Dual Air hairdryer allows
hairdressers to perform similar blow-drying operations with a significantly lower arm
elevation angle than with conventional hair dryers. A data collection protocol with
hairdressers, a comprehensive dataset, and a framework for analysis and further testing
and model development was built to serve as a starting point for a more robust product ready usage-prediction tool
This report summarizes a proof-of-concept study of the feasibility of developing a smart
Dual Air blow-dryer that automatically provides feedback on its use. We successfully
demonstrated feasibility by automatically identifying the right and wrong use of Dual Air
by using machine learning on data from IMU sensors mounted on the blow-dryer. Video
pose estimation from the study also documented that the Dual Air hairdryer allows
hairdressers to perform similar blow-drying operations with a significantly lower arm
elevation angle than with conventional hair dryers. A data collection protocol with
hairdressers, a comprehensive dataset, and a framework for analysis and further testing
and model development was built to serve as a starting point for a more robust product ready usage-prediction tool