Premium
Development of Basic Human Behavior Recognition System Using Plant Bioelectric Potential
Author(s) -
NOMURA KENTA,
NAMBO HIDETAKA,
KIMURA HARUHIKO
Publication year - 2016
Publication title -
electronics and communications in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.131
H-Index - 13
eISSN - 1942-9541
pISSN - 1942-9533
DOI - 10.1002/ecj.11809
Subject(s) - artificial intelligence , computer science
SUMMARY We investigated the influence of basic human behaviors on the plant bioelectric potential. We analyzed four basic human behaviors, namely, touching a plant, opening a door, approaching a plant, and turning on a light. The specific responses in the bioelectric potential were found to be influenced by each behavior. The bioelectric potential has a pulsatile response due to behavior. Therefore, we attempted to learn and recognize human behaviors by extracting characteristics from the planet bioelectric potential. The method of recognizing basic human behaviors that we propose uses a low level of the cepstrum in the plant bioelectric potential. Some data were not recognized correctly because of individual differences in human behaviors. However, the F ‐measure had an average of value 0.76, which shows that the proposed method may be an effective way of recognizing basic human behaviors by using the plant bioelectric potential.