Estimating Scalp Moisture in a Hat Using Wearable Sensors

Abstract

Hair quality is easily affected by the scalp moisture content, and hair loss and dandruff will occur when the scalp surface becomes dry. Therefore, it is essential to monitor scalp moisture content constantly. In this study, we developed a hat-shaped device equipped with wearable sensors that can continuously collect scalp data in daily life for estimating scalp moisture with machine learning. We established four machine learning models, two based on learning with non-time-series data and two based on learning with time-series data collected by the hat-shaped device. Learning data were obtained in a specially designed space with a controlled environmental temperature and humidity. The inter-subject evaluation showed a Mean Absolute Error (MAE) of 8.50 using Support Vector Machine (SVM) with 5-fold cross-validation with 15 subjects. Moreover, the intra-subject evaluation showed an average MAE of 3.29 in all subjects using Random Forest (RF). The achievement of this study is using a hat-shaped device with cheap wearable sensors attached to estimate scalp moisture content, which avoids the purchase of a high-priced moisture meter or a professional scalp analyzer for individuals.