A wearable fatigue monitoring system: application of human-computer interaction evaluation

We developed a wearable fatigue monitoring system with a high-sensitivity 2-axis accelerometer and an on-board signal processing microcontroller. The proposed system measures faint motion of the user's head while the user is trying to stand still for 30 seconds. The two axes of the accelerometer were settled parallel to the ground. As one of the candidates for diagnostic parameters, we adopted a time-integral of acceleration trace pattern length, which was defined as the length between the adjacent two acceleration X-Y plots. As artificially introduced physical stress such as running as well as some physically or mentally exhausted situations made consistent changes in the acceleration trace length, the proposed system was shown to have a capability of evaluating the degree of tiredness. Then we applied the proposed system to evaluation of human-computer interaction. We performed experiments on a computer entertainment using immersive display devices such as head-mounted displays and wide-angle plasma displays. As a result, the measured values of the acceleration trace length showed some inconsistency with user-interviews consist of subjective questionnaires about the user's fatigue.