SUITA, Japan – Researchers from Osaka University and Nara Institute of Science and Technology have developed a dementia detection system that uses interactive computer avatars and machine learning. Their research showed that it was possible to detect dementia from conversations in human/avatar interaction, where a machine learns the characteristics of sounds of elderly people who answered questions from avatars on a computer. “If this technology is further developed, it will become possible to know whether or not an elderly individual is in the early stages of dementia through conversation with computer avatars at home on a daily basis,” said Takashi Kudo, one of the researchers, in a statement. “It will encourage them to seek medical help, leading to early diagnosis.” The researchers created a model for machine learning based on features of speech, language and faces from recorded dialogues with elderly participants. Through machine learning, a computer was able to distinguish individuals with dementia from healthy controls at a rate of 90% in six questions. It was found that dementia could be distinguished with high accuracy by combining features of dementia, such as delay in response to questions from avatars depending on the content of questions, intonation, articulation rate of the voice and the percentage of nouns and verbs uttered.
You are here: / / Researchers develop dementia detection system with avatars