Abstract
Comfortable human interfaces are required for advanced systems. This paper aims at developing a Kansei product design system to support designing keyboard switches based on Kansei. We investigate how each reaction force of switches effects the touch feeling of switches via Kansei evaluation experiments. Each feeling described by each evaluation word is directly evaluated by reaction force or vice versa on dual scales. The dual scale for reaction forces and degree of feeling can be directly used for designing comfortable switch. Finally, we trained artificial netural 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.
