Predicting odor pleasantness with an electronic nose
AssigneeYeda Research and Development Co. Ltd.
InventorsRafi Haddad, Noam Sobel, David Harel
Life of this patent
Estimating the term…
Abstract
Apparatus and method for assessing odors, comprises an electronic nose, to be applied to an odor and to output a structure identifying the odor; a neural network which maps an extracted structure to a first location on a pre-learned axis of odor pleasantness; and an output for outputting an assessment of an applied odor based on said first location. The assessment may be a prediction of how pleasant a user will consider the odor.
Claims20
A method of assessing odors, comprising:
- providing an electronic nose;
- applying said electronic nose to an odor;
- extracting odor information of said odor using said electronic nose;
- plotting said extracted odor information to a first location on an axis of odor pleasantness via learning-based mapping, said axis of odor pleasantness comprising odor points ordered for pleasantness between a first high pleasance end and a second low pleasance end of said axis;
- and
- outputting an assessment based on said first location.
Apparatus for assessing odors, comprising:
- an electronic nose, configured to be applied to an odor and to output a structure identifying said odor;
- a learning based mapping unit, attached to an axis of odor pleasantness, said mapping unit pretrained with odors and corresponding pleasantness gradings, configured to map an extracted structure to a first location on said axis of odor pleasantness, said axis of odor pleasantness comprising odor points ordered for pleasantness between a first high pleasance end and a second low pleasance end of said axis;
- and
- an output for outputting an assessment of an applied odor based on said first location.
A method of assessing odors, comprising:
- providing an electronic nose;
- applying said electronic nose to an odor;
- extracting odor information of said odor using said electronic nose;
- plotting said extracted odor information to a first location on an axis of odor pleasantness via a learning-based mapping unit;
- minimizing features extracted from sensors of said electronic nose to a minimal set that allows convergence of same odors and divergence of different odors;
- assessing the pleasantness of an odor having odor information not used in setting up said learning based mapping unit, by mapping to said axis using said learning-based mapping unit;
- and
- outputting an assessment based on said first location.
A method of assessing odors, comprising:
- providing an electronic nose;
- providing an axis of odor pleasantness by ordering odor points for pleasantness between a first high pleasance end and a second low pleasance end of said axis and hardwiring a region of said axis to an indication of unpleasantness;
- applying said electronic nose to an odor;
- extracting odor information of said odor using said electronic nose;
- plotting said extracted odor information to a first location on said axis of odor pleasantness via a learning-based mapping unit;
- and
- outputting an assessment based on said first location.
Dependencies are inferred from the claim text.