Estimation of reaction force of a keyboard switch based on Kansei information using neural networks

Products with comfortable human interface are required. Devices for human interface such as switches must take fine feeling into account in design. Kansei engineering provides elegant methods to design comfortable interfaces or products for users. This study aims to develop a product design system whose inputs are Kansei data expressed a degree of evaluation words and outputs are parameters to design keyboard switches. We used a keyboard switch simulator to cover new and uncommon characteristics in our Kansei evaluation experiments. We trained artificial neural network using Kansei data obtained by Kansei evaluation experiments. When we input Kansei data expressed dual scale value, the neural network can output reaction forces to give feeling the inputted Kansei.