# US 12,005,649 B2 · Aroma detection systems for food and beverage and conversion of detected aromas to natural language descriptors

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,005,649 B2
- Document ID: US12005649B2
- Status: Granted
- Kind: B2
- Application number: 17/483,187
- Filed: 2021-09-23
- Published: 2022-03-24
- Granted: 2024-06-11
- Earliest claimed: 2020-09-23
- Assignees: UT-Battelle, LLC; University of Tennessee Research Foundation; Oak Ridge Associated Universities, Inc.
- Applicants: UT-Battelle, LLC
- Inventors: Ilia N. Ivanov; Eric S. Muckley; Reinaldo C. Reina
- Web page: https://patentgrep.com/patent/US12005649B2

## CPC

- B29C 64/386: Data acquisition or data processing for additive manufacturing
- A61B 5/0004: {characterised by the type of physiological signal transmitted}
- A61B 5/0816: {Measuring devices for examining respiratory frequency (measuring frequency of electric signals G01R23/00)}
- A61B 5/082: {Evaluation by breath analysis, e.g. determination of the chemical composition of exhaled breath (A61B5/083, A61B5/091 take precedence)}
- A61B 5/6891: {Furniture}
- A61B 5/7267: {involving training the classification device}
- B22F 10/18: by mixing binder with metal in filament form, e.g. fused filament fabrication [FFF]
- B22F 10/85: for controlling or regulating additive manufacturing processes
- B22F 12/90: Means for process control, e.g. cameras or sensors
- B29C 64/106: using only liquids or viscous materials, e.g. depositing a continuous bead of viscous material
- B29C 64/364: Conditioning of environment
- B29C 64/393: for controlling or regulating additive manufacturing processes
- B33Y 50/02: for controlling or regulating additive manufacturing processes
- G01N 3/00: Investigating strength properties of solid materials by application of mechanical stress
- G01N 21/25: Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N 27/026: {Dielectric impedance spectroscopy (electrochemical impedance spectroscopy for measuring corrosion G01N17/02)}
- G01N 33/0001: {by organoleptic means}
- G01N 33/0031: {comprising two or more sensors, e.g. a sensor array}
- G01N 33/0063: {using a threshold to release an alarm or displaying means}
- G01N 33/0073: {Control unit therefor}
- G01N 33/02: Food
- G01N 33/497: of gaseous biological material, e.g. breath
- G05B 19/042: using digital processors (G05B19/05 takes precedence)
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G08B 21/14: Toxic gas alarms (G08B21/16 takes precedence)
- G08B 21/16: Combustible gas alarms
- G08B 21/18: Status alarms (G08B21/02 takes precedence)
- A61B 2562/046: in a matrix array
- B33Y 10/00: Processes of additive manufacturing
- B33Y 30/00: Apparatus for additive manufacturing; Details thereof or accessories therefor
- B33Y 50/00: Data acquisition or data processing for additive manufacturing
- G01N 33/0047: {Organic compounds}
- G01N 2203/0094: Visco-elasticity
- G05B 2219/2614: HVAC, heating, ventillation, climate control
- G06N 3/008: based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G08B 13/19697: {Arrangements wherein non-video detectors generate an alarm themselves}
- Y02P 10/25: Process efficiency
- B29C: SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING (making preforms B29B11/00; making laminated products by combining previously unconnected layers which become one product whose layers will remain together B32B37/00 - B32B41/00)
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- B22F: WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER (making alloys by powder metallurgy C22C); APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B33Y: ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A system for determining an age and/or quality of food or beverage based on one or more combinations of outputs from gas sensors input into a deployed machine learning model is provided. The system may comprise an electronic nose which may comprise a housing and the gas sensors. The housing may have an air channel. Each sensor has its active sensor portion in the air channel. A system for predicting one or more natural language descriptors associated with aromas of an item based on one or more outputs of the gas sensors and calculated one or more ratios input into a logistic regression model is also provided.

## Claims

### Claim 1

A system for determining an age and/or quality of food or beverage comprising:
an electronic nose (e-nose) comprising:
a housing having openings on corresponding ends thereof to enable air flow, the housing having an air channel for air to flow between the ends;
a plurality of thin film gas sensors, each having an active sensor portion in the air channel;
at least one of an identification scanner configured to read an identification code of a food or beverage, a touch panel configured to receive user input identifying the food or beverage or an image processor configured to analyze an acquired image of the food or beverage and identify the food or beverage;
a processor configured to:
supply power to the plurality of thin film gas sensors to bias the sensors and receive output from each of the plurality of thin film gas sensors;
predict the age and/or quality of the food or beverage based on one or more combinations of outputs from the plurality of thin film gas sensors and a deployed machine learning model; and
issue a notification of the determination, wherein the received output from the plurality of thin film gas sensors is in response to a food or beverage item or combination of food or beverage items at different times, wherein the processor is further configured to:
generate randomly a first dataset for training and a second dataset for testing a plurality of models using the received output;
train and test a plurality of models using one or more combinations of outputs from the plurality of thin film gas sensors, the plurality of models are generated using a plurality of different machine learning techniques, the training based on the first dataset and the testing based on the second dataset; and
evaluate a prediction accuracy of each of the plurality of models using an evaluation parameter and select a model from among the plurality of models to deploy as the deployed machine learning model based on a comparison of the evaluation parameter for each of the plurality of models.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processor receives information of an expiration date from a package of the food or beverage item and associates one or more combinations of the outputs from the plurality of thin film gas sensors with the expiration date.

### Claim 3 (depends on 2)

The system of claim 2, wherein the processor is configured to determine that the food or beverage item or combination of food or beverage items has expired when a predicted age using the deployed machine learning model is after the expiration date.

### Claim 4

A system for determining an age and/or quality of food or beverage comprising:
an electronic nose (e-nose) comprising:
a housing having openings on corresponding ends thereof to enable air flow, the housing having an air channel for air to flow between the ends;
a plurality of thin film gas sensors, each having an active sensor portion in the air channel;
at least one of an identification scanner configured to read an identification code of a food or beverage, a touch panel configured to receive user input identifying the food or beverage or an image processor configured to analyze an acquired image of the food or beverage and identify the food or beverage;
a processor configured to:
supply power to the plurality of thin film gas sensors to bias the sensors and receive output from each of the plurality of thin film gas sensors;
predict the age and/or quality of the food or beverage based on one or more combinations of outputs from the plurality of thin film gas sensors and a deployed machine learning model; and
issue a notification of the determination, wherein the image processor is configured to receive images of the food or beverage item or combination of items from a plurality of different times, the plurality of different times including a baseline condition, an expired condition and a spoiled condition, and wherein the processor is configured to determine the age of the food or beverage item or combination of items based on a deployed machine learning model determined from the images.

### Claim 5 (depends on 4)

The system of claim 4, further comprising a wireless interface, wherein the processor is configured to obtain the images from the Internet via the wireless interface.

### Claim 6 (depends on 4)

The system of claim 4, further comprising a wireless interface, wherein the processor is configured to obtain information regarding the food or beverage item or combination of items from the Internet via the wireless interface.

### Claim 7 (depends on 4)

The system of claim 4, wherein the processor receives information identifying one or more combinations of the output from the plurality of thin film gas sensors with the spoiled condition.

### Claim 8 (depends on 7)

The system of claim 7, wherein the processor is configured to determine that the food or beverage item or combination of items has expired when a predicted age correlates an age associated with the spoiled condition or is older than an age associated with the spoiled condition.

### Claim 9

A system for determining an age and/or quality of food or beverage comprising:
an electronic nose (e-nose) comprising:
a housing having openings on corresponding ends thereof to enable air flow, the housing having an air channel for air to flow between the ends;
a plurality of thin film gas sensors, each having an active sensor portion in the air channel;
at least one of an identification scanner configured to read an identification code of a food or beverage, a touch panel configured to receive user input identifying the food or beverage or an image processor configured to analyze an acquired image of the food or beverage and identify the food or beverage;
a processor configured to:
supply power to the plurality of thin film gas sensors to bias the sensors and receive output from each of the plurality of thin film gas sensors;
predict the age and/or quality of the food or beverage based on one or more combinations of outputs from the plurality of thin film gas sensors and a deployed machine learning model; and
issue a notification of the determination, wherein the image processor is configured to receive images of the food or beverage item or combination of items from a plurality of different times, the plurality of different times including a baseline condition, an expired condition and a spoiled condition, and wherein the processor is configured to determine the age of the food or beverage item or combination of items based on a deployed machine learning model determined from the images and received output from the plurality of thin film gas sensors for the food or beverage item or combination of items from different times.

### Claim 10 (depends on 9)

The system of claim 9, wherein the housing comprise a magnet configured to mount the housing to a wall or door of a refrigerator.

### Claim 11 (depends on 9)

The system of claim 9, further comprising a base, wherein the housing is configured to be mounted to the base.

### Claim 12 (depends on 9)

The system of claim 9, further comprising a wireless interface, wherein the processor is configured to transmit the notification via the wireless interface to registered device.