Detection of Involuntary Movement with Wearable Technology

Nowadays, wearable accelerometers have improved the popularity of smartwatches, and physical activity measurements. This article aims to use a smartwatch as a stimulant against hair pulling obsession (Trichotillomania). Data were collected for 4 hours with a user who pulls out his beard at indefinite intervals, and machine learning models were applied to the collected data. A Watch X is preferred as a programmable watch. This smartwatch is programmed to create an alert when the user makes the beard plucking action. Based on this, it is aimed to prevent Trichotillomania obsession by applying positive punishment with an alert (stimulant). CNN and LSTM models were compared to find the most suitable model and it was seen that LSTM had better accuracy than CNN. However, in terms of speed performance, CNN gave better results. As a result of all comparisons, the LSTM model was observed as the most suitable model with an accuracy rate of 91%.