Extended Interactive Evolutionary Computation using heart rate variability as fitness value for composing music chord progression

Interactive Evolutionary Computation (IEC) is known as an effective method to create media contents suited to each user. To reduce the user's fatigue, which remains as a serious problem in IEC, an extended IEC that utilizes physiological information as fitness value have been proposed. As a new extended IEC, this study proposed an extended IEC using heart rate variability (HRV), which reflects autonomic nervous activity. High frequency component of HRV was used as a fitness value. Through two listening experiments, the efficacy of the proposed method was investigated. In the experiment 1, with a concrete system of the proposed method creating music chord progression, change in the fitness value was observed. In the experiment 2, representative created music chord progressions were evaluated subjectively. The change in the fitness value did not show gradual increase, however, lowest fitness value was observed in the initial generation in subjective evaluation. These results of subjective evaluation showed a possibility of the proposed method.