System and method for non-destructive rapid food profiling using artificial intelligence
A system and method for non-destructive food rapid profiling in terms of taste, variant classification, adulteration, etc., using artificial intelligence. The system includes: a receptacle configured to move a non-homogenized sample in a path to intersect a volumetric sampling space; a sensor configured to sense reflectance from at least a part of the sample in the volumetric sampling space, the sensor being configured to output a component of the reflectance as captured data, the captured data being characterised by an overtone spectrum over a range of wavelengths; and a computing device configured to apply at least one first machine learning model to the captured data to: predict at least one facet corresponding to predictively determined selected wavelengths; and provide a signature data using the at least one facet.
1. A portable apparatus configured to perform non-destructive taste profiling of a food, the portable apparatus comprising:
a receptacle configured to move a sample of the food in a volumetric sampling space, in which the sample includes the food in a non-homogenized form;
a source configured to direct light towards the volumetric sampling space;
an optical device having an input port and an output port, the input port being configured to sense reflectance from at least a part of the sample in the volumetric sampling space, the reflectance characterized by visible-to-near infra-red light, the optical device being configured to output a component of the reflectance through the output port; and
a detector coupled to the output port, the detector being configured to convert the component of the reflectance into captured data, the captured data being characterized by an overtone spectrum of a measure of the reflectance, the overtone spectrum characterized by gradual changes in intensity over a range of wavelengths; and
a computing device coupled to the detector, the computing device being configured to:
execute at least one first machine learning model using the captured data as input, the at least first machine learning model being configured to:
predict at least one facet corresponding to at least one selected wavelength from the overtone spectrum; and
predict a signature data based on a plurality of the at least one facet, wherein the signature data is characteristic of a taste of the food, and
execute at least one second machine learning model using the signature data as input, the at least one second machine learning model being configured to:
predict at least one descriptor; and
predict a signature characteristic of the food using the at least one descriptor, wherein the signature comprises a cultivar or an origin of the food.
2. The portable apparatus of claim 1 , wherein the computing device is further configured to compare the signature of the food against training data in a database to improve the at least one second machine learning model.
3. The portable apparatus of claim 1 , wherein the signature is an independent variable, and wherein the at least one descriptor is a dependent variable.
4. The portable apparatus of claim 1 , wherein the at least one first machine learning model includes an unsupervised machine learning model, and wherein the at least one second machine learning model includes a supervised machine learning model.
5. The portable apparatus of claim 1 , wherein the receptacle is configured to be rotatable, and wherein the computing device is further configured to output the signature in about 5 seconds from initiating rotation of the receptacle.
6. The portable apparatus of claim 1 , wherein the at least one second machine learning model is configured to predict a blend intended to have a taste associated with the food, and wherein the blend has a composition of ingredients different from a composition of the food.
7. The portable apparatus of claim 1 , wherein the at least one second machine learning model is configured to predict a variant and/or a category of the food.
8. The portable apparatus of claim 1 , wherein the receptable is configured to move relative to the source and/or the optical device to define the volumetric sampling space.
9. The portable apparatus of claim 1 , wherein the optical device is configured to remove spatial information from the reflectance.
10. A system for non-destructive taste profiling of a sample of a food, the system comprising:
a receptacle configured to move the sample in a path so as to intersect a volumetric sampling space, the sample being in a non-homogenized form;
a sensor configured to sense reflectance from at least a part of the sample in the volumetric sampling space, the reflectance characterized by visible-to-near infra-red light, the sensor being configured to output a component of the reflectance as captured data, the captured data being characterised by an overtone spectrum of a measure of the reflectance, the overtone spectrum characterized by gradual changes in intensity over a range of wavelengths; and
a computing device configured to apply at least one first machine learning model to the captured data to:
predictively determine selected wavelengths from the range of wavelengths;
predict at least one facet corresponding to the selected wavelengths; and provide a signature data using the at least one facet, wherein the signature data is characteristic of a taste of the food,
wherein the computing device is further configured to apply at least one second machine learning model to the signature data to predict at least one descriptor; and provide a signature of the sample using the at least one descriptor, wherein the signature comprises a cultivar or an origin of the food.
11. The system of claim 10 , wherein the receptable is configured to move relative to the source and/or the optical device to define the volumetric sampling space.
12. The system of claim 11 , wherein the sensor is configured to remove spatial information from the reflectance.
13. The system of claim 10 , further configured to compare the signature of the food against training data in a database to improve the at least one second machine learning model.
14. The system of claim 10 , wherein the computing device is further configured to apply the at least one second machine learning model to the signature data to predict a blend intended to have a taste associated with the sample, wherein the blend has a composition of ingredients different from a composition of the sample.
15. The system of claim 10 , wherein the computing device is configured to apply the at least one second machine learning model to the signature data to predict a variant and/or a category of the sample.
16. The system of claim 10 , wherein the computing device is configured to apply the at least one second machine learning model to the signature data to predict a degree of purity of the sample.
17. A system, comprising:
memory storing instructions; and
a processor coupled to the memory and configured to process the stored instructions to implement:
a module configured to perform a method of non-destructive taste profiling of a sample of a food, the method comprising:
providing captured data to a computing device, the captured data being characterised by an overtone spectrum of a measure of a reflectance, the reflectance characterized by visible-to-near infra-red light, the overtone spectrum characterized by gradual changes in intensity over a range of wavelengths, wherein the reflectance is sensed from at least a part of the sample in a volumetric sampling space, the sample including non-homogenized food;
predicting at least one facet by applying at least one first machine learning model to the captured data, wherein the at least one facet corresponds to at least one selected wavelength predictively determined from the range of wavelengths;
using the at least one facet to provide a signature data characteristic of the sample, wherein the signature data is characteristic of a taste of the food;
applying at least one second machine learning model to the signature data, wherein the at least one second machine learning model is configured to:
predict at least one descriptor; and
provide the signature of the food using the at least one descriptor, wherein the signature comprises a cultivar or an origin of the food.
18. The system of claim 17 , wherein the method further comprising: comparing the signature of the food against training data in a database to improve the at least one second machine learning model.
19. The system of claim 17 , wherein the method further comprising: predicting a blend intended to have a taste associated with the food, wherein the blend has a composition of ingredients different from a composition of the food.
20. The system of claim 17 , wherein the second machine learning model is at least one selected from a group consisting of: a taste profile prediction module, a variety prediction module, a blend configuration module, an adulteration detection module, and a food grade/quality control module, and a nutritional analysis module.