Causal-effect structure transformation based on hierarchical representation for biomedical sensing

In general, understanding causality among components in a target system, including a human body, is quite effective and efficient solution since utilisation of the causality helps predicting future system condition, making correct diagnosis and so forth. As for focusing on biomedical sensing, the causality among vital signals obtained from sensors built in measurement equipment should be considered to recognise human's health condition correctly. In addition, effective causality transformation is desired when measurement equipment is improved such as replacing or maintaining components in the equipment. In this article, causality transformation method for improving causality is proposed. It employs a hierarchical representation of the causality based on human-machine collaborative knowledge and its applications of visceral fat area estimation and heart rate monitoring are presented.