Hiroki Koda

DiverScan is a deep-learning framework that uses attention mechanisms to analyze animal behavior data, identifying condition-specific features across diverse experiments.

The paper evaluates the effectiveness of mel spectrograms for individual identification and age-class classification of wild female macaque vocalizations using machine learning on small datasets.

This study shows rats can spontaneously categorize familiar and unfamiliar conspecifics using a habituation-dishabituation task with multiple stimuli.

This study examines vocal exchange temporal patterns in Java sparrows, finding no significant difference between inter- and intra-individual intervals, contrasting with social mammals.

This study investigates how auditory feedback linked to locomotion affects rats' spontaneous movement, finding increased locomotion distance when feedback matches movement velocity, but the effect is short-lived.

This study shows that rats prefer joint feeding with unfamiliar non-cagemates over solitary feeding, indicating a high degree of social tolerance and prosocial behavior.