Article ID: IJAE-D-24-00042
The demand for the customization of tactile sensations in rotary encoders is increasing to align with individual user preferences. In light of this objective, this study aimed to construct a tactile inference model that considers individuality with the goal of regulating targeted factor perceptions. An experimental evaluation was performed involving 17 participants to assess the tactile sensations of rotary encoders across 50 parameter settings, utilizing 30 adjective pairs. A comprehensive factor analysis of the experimental data revealed the extraction of four key factors. Subsequently, an inference model tailored to each participant was developed using neural networks and transfer-learning techniques. Furthermore, through the application of personalized tactile inference models adjusted for individual participants, we showcase the potential of selectively influencing impressions of specific factors by manipulating various physical parameters.
