Claims:WE CLAIM:

1. A system (10) to detect quality of a food commodity, the system (10) comprising:
an array of one or more sensors (40) housed in a casing (30), wherein the one or more sensors (40 A-N) are in proximity with one or more food commodities, and wherein the one or more sensors (40 A-N) are configured to:
detect presence of one or more gases as sensor readings from the one or more food commodities stored in a storage (20), wherein the one or more gases comprises quantity range of at least one of: ethylene, carbon-di-oxide, oxygen, ammonia, hydrogen sulphide, dimethyl sulphide and trimethylamine;
transmit the detected presence of the one or more gases as the sensor readings and a location information associated with each of the one or more sensors (40) to a cloud server (80);
the cloud server (80) communicatively coupled to the one or more sensors (40 A-N) via a network and wherein the cloud server (80) is configured to:
obtain the detected presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors (40 A-N);
identify type of the one or more sensors (40 A-N) based on the obtained presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors (40 A-N);
determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors (40 A-N) by using an artificial intelligence-based predictive model;
predict quality of the one or more food commodities stored in the storage (20) based on the determined gaseous concentration; and
output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors (40 A-N) on a display unit.
2. The system (10) as claimed in claim 1, wherein the casing (30A-N) comprises a plurality of exhaust fans (50 A-N) mounted below the one or more sensors (40 A-N), wherein the plurality of exhaust fans (50 A-N) is configured to circulate the one or more gases within the casing (30A-N) for detecting the sensor readings.
3. The system (10) as claimed in claim 1, wherein the casing (30A-N) is positioned at multiple points inside the storage (20).
4. The system (10) as claimed in claim 1, wherein the one or more sensors (40) are also configured to detect presence of humidity of the storage (20) and temperature value within the storage (20).
5. The system (10) as claimed in claim 1, wherein in outputting the predicted quality of the one or more food commodities, the cloud server (80) is configured to:
generate a heat map corresponding to the storage (20) based on pre-stored layout information of the storage (20); and
superimpose the location information of the identified type of the one or more sensors (40 A-N) on the generated heat map.
6. The system (10) as claimed in claim 1, wherein in determining gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors (40 A-N) by using an artificial intelligence-based predictive model, the cloud server (80) is configured to:
classify the obtained sensors readings into one or more type of gaseous concentrations;
determine whether the classified type of gaseous concentrations match with pre-stored threshold levels of corresponding gaseous concentrations;
classify the identified type of the one or more sensors (40 A-N) based on the type of the one or more gases;
generate artificial intelligence based predictive model for the classified type of gaseous concentrations and the classified type of one or more sensors (40 A-N) based on the determination, wherein the artificial intelligence based predictive model represents corelation between the classified type of gaseous concentrations with the pre-stored threshold levels and the classified type of one or more sensors (40 A-N).
7. The system (10) as claimed in claim 1, wherein the cloud server (80) is also configured to generate a warning message indicating predicted quality of the one or more food commodities to one or more user devices (85).
8. The system (10) as claimed in claim 1, wherein in predicting quality of the one or more food commodities stored in the storage (20), the cloud server (80) is configured for:
generating food quality scores for each of the determined gaseous concentration based on the generated artificial intelligence based predictive model; and
predicting the quality of the one or more food commodities stored in the storage (20) based on the generated food quality scores.
9. A computing system (150) to detect quality of a food commodity, the computing system (150) comprising:
a hardware processor (190); and
a memory (160) coupled to the hardware processor (190), wherein the memory (160) comprises a set of program instructions in the form of a plurality of subsystems, configured to be executed by the hardware processor (190), wherein the plurality of subsystems comprises:
a data capturing subsystem (200) configured to:
obtain detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors (40 A-N); and
identify type of the one or more sensors (40 A-N) and the location information associated with each of the one or more sensors (40 A-N);
a food quality analysing subsystem (210) configured to
determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors (40 A-N) by using an artificial intelligence-based predictive model;
predict quality of the one or more food commodities stored in the storage (20) based on the determined gaseous concentration;
an output subsystem (220) configured to output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors (40 A-N) on a display unit.
10. A method (230) for detecting quality of a food commodity, the method (230) comprising:
obtaining, by a processor (190), detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors (40 A-N) (240);
identifying, by the processor (190), type of the one or more sensors (40 A-N) based on the obtained presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors (250);
determining, by the processor (190), gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors (40 A-N) by using an artificial intelligence-based predictive model (260);
predicting, by the processor (190), quality of the one or more food commodities stored in the storage (20) based on the determined gaseous concentration (270); and
outputting, by the processor (190), the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors (40 A-N) on a display unit (280).
11. The method (230) as claimed in claim 10, wherein in determining gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors (40 A-N) by using an artificial intelligence-based predictive model comprises:
classifying the obtained sensors readings into one or more type of gaseous concentrations;
determining whether the classified type of gaseous concentrations match with pre-stored threshold levels of corresponding gaseous concentrations;
classifying the identified type of the one or more sensors based on the type of the one or more gases;
generating artificial intelligence based predictive model for the classified type of gaseous concentrations and the classified type of one or more sensors (40 A-N) based on the determination, wherein the artificial intelligence based predictive model represents corelation between the classified type of gaseous concentrations with the pre-stored threshold levels and the classified type of one or more sensors (40 A-N).
12. The method (230) as claimed in claim 10, further comprising generating a warning message indicating predicted quality of the one or more food commodities to one or more user devices (85).
13. The method (230) as claimed in claim 10, wherein the one or more sensors (40 A-N) also enables detecting presence of humidity of the storage (20) and temperature value within the storage (20).
14. The method (230) as claimed in claim 10, wherein for outputting of the predicted quality comprises:
generating a heat map corresponding to the storage (20) based on pre-stored layout information of the storage (20); and
superimposing the location information of the identified type of the one or more sensors (40 A-N) on a generated heat map.
15. The method (230) as claimed in claim 10, wherein for predicting quality of the one or more food commodities stored in the storage (20) comprises
generating food quality scores for each of the determined gaseous concentration based on the generated artificial intelligence based predictive model; and
predicting the quality of the one or more food commodities stored in the storage (20) based on the generated food quality scores.
Dated this 08th day of September 2021

Vidya Bhaskar Singh Nandiyal
Patent Agent (IN/PA-2912)
Agent for applicant
, Description:FIELD OF INVENTION
[0001] Embodiments of the present disclosure relates to quality assessment systems, and more particularly to a system and a method for detecting quality of a food commodity.
BACKGROUND
[0002] Consumers generally purchase perishable food items which are furthest from their expiry dates, such that the perishable food items are suitable for their intended purpose at the time of purchase. Storage units are built to preserve such perishable food items and thereby prevent the perishable food items from getting spoilt. Such perishable food items are maintained with high quality in such storage units.
[0003] However, due to many factors such as lack of demand, diseased food, improper maintenance, and the like, stored perishable food items get spoilt in the storage units. Conventional systems allow detection of the spoilt perishable food items through monitoring of gases released in real time. However, such conventional systems are limited to detection of specific type of gases and fail to detect any type of gases released by the perishable food items.
[0004] In general, the quality of whole batch of the perishable food items may be preserved by segregating single spoilt food item from the remaining perishable food items. However, such process of manually locating and segregating the single spoilt food item after detection of presence of certain kind of gases is prone to human errors and may consume huge amount of time. Moreover, none of the conventional systems are capable of detecting early stages of spoilage relating to the perishable food items.
[0005] Hence, there is a need for an improved system to detect quality of a food commodity and a method to operate the same and therefore address the aforementioned issues.
BRIEF DESCRIPTION
[0006] In accordance with one embodiment of the disclosure, a computing system to detect quality of a food commodity is disclosed. The computing system includes an array of one or more sensors housed in a casing. The one or more sensors are in proximity with one or more food commodities. The one or more sensors are configured to detect presence of one or more gases as sensor readings from the one or more food commodities stored in a storage.
[0007] The one or more sensors are also configured to transmit the detected presence of the one or more gases as the sensor readings and a location information associated with each of the one or more sensors to a cloud server.
[0008] The cloud server is communicatively coupled to the one or more sensors via a network. The cloud server is configured to obtain the detected presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors. The cloud server is also configured to identify type of the one or more sensors based on the obtained presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors. The cloud server is also configured to determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors by using an artificial intelligence-based predictive model. The cloud server is also configured to predict quality of the one or more food commodities stored in the storage based on the determined gaseous concentration. The cloud server is also configured to output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors on a display unit.
[0009] In accordance with one embodiment of the disclosure, a computing system to detect quality of a food commodity is disclosed. The computing system includes a hardware processor. The computing system also includes a memory coupled to the hardware processor. The memory comprises a set of program instructions in the form of a plurality of subsystems, configured to be executed by the hardware processor. The plurality of subsystems includes a data capturing subsystem. The data capturing subsystem is configured to obtain detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors. The data capturing subsystem is also configured to identify type of the one or more sensors and the location information associated with each of the one or more sensors.
[0010] The plurality of subsystems also includes a food quality analysing subsystem. The food quality analysing subsystem is configured to determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors by using an artificial intelligence-based predictive model. The food quality analysing subsystem is also configured to predict quality of the one or more food commodities stored in the storage based on the determined gaseous concentration. The plurality of subsystem includes an output subsystem. The output subsystem is configured to output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors on a display unit.
[0011] In accordance with one embodiment of the disclosure, a method for detecting quality of a food commodity is disclosed. The method includes obtaining detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors. The method also includes identifying type of the one or more sensors based on the obtained presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors.
[0012] The method also includes determining gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors by using an artificial intelligence-based predictive model. The method also includes predicting quality of the one or more food commodities stored in the storage based on the determined gaseous concentration. The method also includes outputting the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors on a display unit.
[0013] To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.
BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which:
[0015] FIG. 1 is a block diagram illustrating an exemplary computing system to detect quality of a food commodity in accordance with an embodiment of the present disclosure;
[0016] FIG. 2 is an exploded view illustrating a casing associated with one or more sensors in accordance with an embodiment of the present disclosure;
[0017] FIG. 3 is an exploded view illustrating the one or more sensors deployed within the casing in accordance with an embodiment of the present disclosure;
[0018] FIG. 4 is a system architecture diagram depicting placement of the one or more sensors within the casing in accordance with an embodiment of the present disclosure;
[0019] FIG. 5 A and B is a graphical representation depicting change in concentration of volatile organic compounds versus change in concentration of carbon dioxide for a specific period in accordance with an embodiment of the present disclosure;
[0020] FIG. 6 A and B is a graphical representation depicting change in level of humidity versus change in level of temperature for a specific period in accordance with an embodiment of the present disclosure;
[0021] FIG. 7 is a graphical representation depicting change in concentration of ethylene for a specific period in accordance with an embodiment of the present disclosure;
[0022] FIG. 8 is a block diagram illustrating an exemplary computing system to detect quality of the food commodity in accordance with an embodiment of the present disclosure; and
[0023] FIG. 9 is a process flowchart illustrating an exemplary method for detecting quality of the food commodity in accordance with an embodiment of the present disclosure.
[0024] Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.
DETAILED DESCRIPTION
[0025] For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated online platform, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure.
[0026] The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or subsystems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, subsystems, elements, structures, components, additional devices, additional subsystems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.
[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.
[0028] In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.
[0029] A computer system (standalone, client or server computer system) configured by an application may constitute a “subsystem” that is configured and operated to perform certain operations. In one embodiment, the “subsystem” may be implemented mechanically or electronically, so a subsystem may comprise dedicated circuitry or logic that is permanently configured (within a special-purpose processor) to perform certain operations. In another embodiment, a “subsystem” may also comprise programmable logic or circuitry (as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations.
[0030] Accordingly, the term “subsystem” should be understood to encompass a tangible entity, be that an entity that is physically constructed permanently configured (hardwired) or temporarily configured (programmed) to operate in a certain manner and/or to perform certain operations described herein.
[0031] FIG. 1 is a block diagram illustrating an exemplary computing system 10 to detect quality of a food commodity in accordance with an embodiment of the present disclosure. As used herein, the term “quality of a food” is quality characteristics of one or more food commodities that is acceptable to consumers. The quality includes judging factors such as appearance, texture, flavour and the like for each of the one or more food commodity. In a storage 20, the computing system 10 uses one or more sensors 40 to detect presence of different types of gases and further track spoilt food items within the storage 20. In one such embodiment, the storage 20 may include any food commodity storing space such as warehouse, stockroom, cold storages, refrigerators and the like. In another such embodiment, the food commodities may include any perishable food items such as fruits, vegetables, meat, and the like.
[0032] The computing system 10 includes an array of one or more sensors 40 housed in a casing 30. The one or more sensors 40 A-N are located specifically within casings 30A-N. The casing 30A-N is positioned at multiple points within the storage 20. In one specific embodiment, the casing 30A-N is positioned near to/on a food stack 60 A-N. In such embodiment, the one or more sensors 40 A-N positioned inside the casings 30A-N captures sensor readings from the one or more food commodities. The sensor readings are analysed for quality of the one or more food commodities.
[0033] The casing 30A-N is Internet of things (IoT) module 55 A-N enabled. Internet of things (IoT) module 55 A-N is enabling Internet of things (IoT) communication between the casing 30 A-N and a cloud server 80. In an exemplary embodiment, the Internet of things (IoT) module may communicate via a Wi-Fi communication protocols like 802.11 b/g/n/e/I Wi-Fi which includes ESP32, TI CC3200 and the like. In an alternative exemplary embodiment, the Internet of things (IoT) module may communicate via cellular communication protocols such as Long-Term Evolution/Global System for Mobile Communications (LTE/GSM) modules which includes Simcon SIM7600G, Quectel EC200 and the like.
[0034] After detecting the spoilage of the food commodity, the computing system 10 allows easy segregation of the one or more spoilt food commodities from the other perishable food commodities by indicating accurate location information of the one or more sensors 40A-N associated with the casing 30A-N. The location information may be overlayed on a heat map of the storage 20.
[0035] In one specific embodiment, the casing 30A-N may be a perforated casing allowing flow of the one or more gases. The casing 30A-N further enables interaction with each of the one or more sensors 40 A-N present in a neighbouring casing 30A-N placed at some other point within the storage 20. For example, each of the one or more sensors 40 A-N of the neighbouring casing 30 may be used to re-confirm the sensor readings as captured by the casing 30 at particular point. The casing 30A-N also includes a plurality of exhaust fans 50 A-N coupled below the one or more sensors 40 A-N. The plurality of exhaust fans 50 A-N is configured to circulate the one or more gases inside the casing 30A-N.
[0036] The one or more sensors 40 A-N are configured to detect presence of the one or more gases as sensor readings from the one or more food commodities stored in the storage 20. In one embodiment, the one or more gases comprises detected quantity range of at least one of or a combination of: ethylene, carbon-di-oxide, oxygen, ammonia, hydrogen sulphide, dimethyl sulphide and trimethylamine and the like. In such embodiment, Internet of things (IoT) enabled casing 30A-N works on the principle of olfaction, whereby a combination of the one or more sensors 40 A-N sense the volatile compounds released from the one or more food commodities.
[0037] In an exemplary embodiment, the one or more sensors 40 A-N may include Electrochemical sensor oxygen (EC410) sensor, Industrial ammonia sensor (SGX-4NH3) sensor, Industrial lead-free oxygen (SGX-4OX-ROHS) sensor and the like. The one or more sensors 40 A-N are also configured to detect presence of humidity within the storage 20 and temperature of the storage 20. Such humidity and temperature values are used for analysis and predicting quality of the one or more food commodities. In one embodiment, the plurality of exhaust fans 50 A-N allow maximum flow of gases across the one or more sensors 40 A-N, thereby introducing a sniffing method for the one or more sensors 40 A-N.
[0038] The one or more sensors 40 A-N are also configured to transmit the captured sensor readings of the detected presence of the one or more gases and a location information of each of the one or more sensors 40 A-N to the cloud server 80. In one exemplary embodiment, maximum detected quantity of volatile organic compounds in storage was 0.275 ppm. Similarly, in another exemplary embodiment, maximum detected quantity of carbon dioxide in storage was 0.7 ppm.
[0039] In one embodiment, the location information comprises X, Y and Z coordinates of the casing 30A-N placed at a specific point within the storage 20. The computing system 10 uses Global Positioning System (GPS) technology to capture X, Y and Z coordinates of the casing 30A-N placed at the specific point within the storage 20. In such embodiment, the location information refers to the positional details, which is determined by the storage 20 and the casings 30 A-N placed inside the storage 30. Location is taken using Global Positioning System (GPS) technology if storage 20 is a big place or else using X, Y and Z coordinates of small storage map.
[0040] The cloud server 80 is communicatively coupled to the one or more sensors 40 A-N via a network 70. The network 70 may include any wireless network such as Wi-Fi, Internet of things (IoT), a Bluetooth , or the like. The cloud server 80 is configured to obtain detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors 40 A-N via the network 70. In such embodiment, the cloud servers 80 may include Amazon Elastic Compute Cloud (EC2) instances, Microsoft Azure instances, Google Compute Engine instances, and the like.
[0041] The cloud server 80 is also configured to identify type of the one or more sensors 40 A-N and the location information associated with each of the one or more sensors 40 A-N.
[0042] The cloud server 80 is also configured to determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors 40 A-N by using an artificial intelligence-based predictive model. In such embodiment, the cloud server 80 determines whether the classified type of gaseous concentrations match with pre-stored threshold levels of corresponding gaseous concentrations. For example, if the identified type of gas corresponds to CO2, the cloud server 80 determines whether the CO2 concentrations match with pre-stored threshold levels of CO2. In such embodiment, the pre-stored threshold levels correspond to allowed concentration level of particular type of gases. The threshold levels are defined by data collection in controlled environment or pre-decided industry standards.
[0043] In another embodiment, the cloud server 80 classifies the identified type of the one or more sensors 40 A-N based on the type of the one or more gases.
[0044] An artificial intelligence predictive model is generated for the classified type of gaseous concentrations and the classified type of one or more sensors 40 A-N based on the determination. The artificial intelligence based predictive model represents corelation between the classified type of gaseous concentrations with the pre-stored threshold levels and the classified type of one or more sensors 40 A-N. In one embodiment, the artificial intelligence predictive model includes time series forecasting technique. In another embodiment, the artificial intelligence predictive model may include time forecasting clubbed with classification technique.
[0045] In one specific embodiment, the artificial intelligence predictive model is based on historic time series data of quality. In such embodiment, the sensors readings are used as data. The artificial intelligence predictive model predicts by looking at patterns and performing time series forecasting.
[0046] The cloud server 80 is also configured to predict quality of the one or more food commodities stored in the storage 20 based on the determined gaseous concentration. In one embodiment, food quality scores are generated for each of the determined gaseous concentration using the generated artificial intelligence based predictive model. The quality of the one or more food commodities stored in the storage 20 is predicted based on the generated food quality scores.
[0047] The cloud server 80 is also configured to output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensor 40 A-N on a display unit. The display unit may be any handheld device, laptop, computer, desktop and the like associated with the user. In outputting the predicted quality of the one or more food commodities, the cloud server 80 is configured to generate a heat map corresponding to the storage 20 based on pre-stored layout information of the storage 20. and superimpose the location information of the identified type of sensor on the generated heat map. As used herein, the term “heat map” refers to a data visualization technique that shows magnitude of a phenomenon as colour in two dimensions. The cloud server 80 is also configured to generate a warning message indicating predicted quality of the one or more food commodities for one or more user devices 85.
[0048] FIG. 2 is an exploded view illustrating a casing 30A-N associated with the one or more sensors 40 A-N in accordance with an embodiment of the present disclosure. In one specific embodiment, the casing 30A-N is cuboidal in shape with specific height, width, and length. The top cover 33 of the casing 30A-N is perforated for entry and exit of flow of air. The base of the lower half 34 of the casing 30A-N is fabricated with an oval cut 32 to hold in position the plurality of exhaust fan 50.
[0049] FIG. 3 is an exploded view illustrating the one or more sensors deployed within the casing 90 in accordance with an embodiment of the present disclosure. In one embodiment, the one or more sensors 40 A-N are arranged in an array fashion. In such embodiment, each of the one or more sensors 40 have no specific positioning and have random positions within the casing 90. Each of the one or more sensors 40 A-N is tightly packed inside the casing 30A-N.
[0050] FIG. 4 is a system architecture diagram depicting placement of the one or more sensors 40 A-N within the casing 30A-N in accordance with an embodiment of the present disclosure. The one or more sensors 40 A-N may include an ESP-WROOM-32 module. The one or more sensors 40 A-N may include sensors 40 such as SCD41-D (for carbon dioxide) sensor, SHT41-AD1B (for humidity and temperature) sensor, ZMOD4450 (for dimethyl sulphide and trimethylamine) sensor, ME3-C2H4 (for ethylene) sensor, SGX-4NH3 (for ammonia) sensor, MQ136 (for hydrogen sulphide) sensor and SGX-4OX-EC410 (for oxygen) sensor and the like.
[0051] In one exemplary such embodiment, a gas sensor module, such as a ZMOD4450 Integrated Chip (IC), is designed for detecting the one or more gases released during a food ripening stage and rotting stage of the food commodity. The ZMOD4450 module is a 12-pin Land Grid Area assembly (3.0 * 3.0 * 0.7 mm) which consists of a gas sense element and a Complementary metal–oxide–semiconductor signal conditioning Integrated Circuit. The ZMOD4450 module’s sense element consists of a heater element on a silicon-based microelectromechanical system structure and a metal temperature sensor. The ZMOD4450 module measures the MOx conductivity, which is a function of gas concentration.
[0052] FIG. 5 A and B is a graphical representation depicting change in concentration of volatile organic compounds versus change in concentration of carbon dioxide for a specific period 100 and 110 for a specific period in accordance with an embodiment of the present disclosure. FIG 5 A shows the quantity of volatile organic compounds (parts per million) 100 present in the environment gas over a period of eight hours. Maximum detected quantity of volatile organic compounds in storage was 0.275 ppm. FIG 5 B shows the quantity of carbon dioxide (parts per million) 110 present in the environment gas over a period of eight hours. Maximum detected quantity of carbon dioxide in storage was 0.7 ppm.
[0053] FIG. 6 A and B is a graphical representation depicting change in level of humidity versus change in level of temperature for a specific period 120 and 130 for a specific period in accordance with an embodiment of the present disclosure. FIG 6 A shows the quantity of humidity (in percentage) 120 present in the environment over a period of eight hours. Maximum detected quantity of humidity in storage was 69.6 percent. FIG 6 B shows the temperature (degree Celsius) 130 of the environment over a period of eight hours. Lowest detected temperature the storage was 24.70 ºC.
[0054] FIG. 7 is a graphical representation depicting change in concentration of ethylene 140 for a specific period in accordance with an embodiment of the present disclosure. FIG. 7 shows the quantity of ethylene (parts per million) 140 present in the environment gas over a period of eight hours.
[0055] FIG. 8 is a block diagram illustrating an exemplary computing system 150 to detect quality of the food commodity in accordance with an embodiment of the present disclosure. The computing system 150 includes a hardware processor 190. The computing system 150 also includes a memory 160 coupled to the hardware processor 190. The memory 160 comprises a set of program instructions in the form of a plurality of subsystems, configured to be executed by the hardware processor 190.
[0056] The hardware processor(s) 190, as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof.
[0057] The memory 160 includes a plurality of subsystems stored in the form of executable program which instructs the processor via bus 170 and storage subsystem 180 to perform the method steps illustrated in FIG 1. The plurality of subsystem has following subsystems: a data capturing subsystem 200, a food quality analysing subsystem 210 and an output subsystem 220.
[0058] Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the hardware processor(s) 190.
[0059] The plurality of subsystems includes a data capturing subsystem 200. The data capturing subsystem 200 is configured to obtain detected presence of one or more gases as sensor readings and a location information associated with each of one or more sensors 40 A-N. The data capturing subsystem 200 is also configured to identify type of the one or more sensors 40 A-N and the location information associated with each of the one or more sensors. In one embodiment, a global positioning system may be used to provide the location information, whereby longitude is an X value and latitude is a Y value.
[0060] The plurality of subsystems includes a food quality analysing subsystem 210. The food quality analysing subsystem 210 is configured to determine gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors 40 A-N by using an artificial intelligence-based predictive model.
[0061] In one embodiment, the obtained sensors readings are classified into one or more type of gaseous concentrations. In such embodiment, the food quality analysing subsystem 210 determines whether the classified type of gaseous concentrations match with pre-stored threshold levels of corresponding gaseous concentrations.
[0062] In another embodiment, the identified type of the one or more sensors 40 A-N is classified based on the type of the one or more gases.
[0063] The artificial intelligence predictive model is generated for the classified type of gaseous concentrations and the classified type of one or more sensors 40 A-N based on the determination. The artificial intelligence based predictive model represents corelation between the classified type of gaseous concentrations with the pre-stored threshold levels and the classified type of one or more sensors 40 A-N.
[0064] The food quality analysing subsystem 210 is also configured to predict quality of the one or more food commodities stored in the storage based on the determined gaseous concentration. In one embodiment, food quality scores are generated for each of the determined gaseous concentration based on the generated artificial intelligence based predictive model. The quality of the one or more food commodities stored in the storage 20 is predicted based on the generated food quality scores.
[0065] The plurality of subsystem also includes an output subsystem 220. The output subsystem is configured to output the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors 40 A-N on a display unit.
[0066] In one exemplary embodiment, a stack of apples is kept at a particular location at a storage 20. A casing 30 equipped with one or more sensors 40 A-N is kept near the stack of apples.
[0067] The one or more sensors 40 A-N detect presence of one or more gases as sensor readings from the stack of apples stored in the storage 20. Such sensor readings along with location information of the casing 30 are then transmitted to the cloud server 80. The location information is in the form of X, Y and Z coordinate.
[0068] The data capturing subsystem 200 obtains the sensor readings of the detected presence of the one or more gases and location information. The type of one or more sensors 40 A-N and location information of each of the one or more sensors 40 A-N is identified
[0069] The food quality analysing subsystem 210 determines gaseous concentration associated with the obtained sensor readings by using artificial intelligence-based predictive models. The obtained sensors readings are classified into one or more type of gaseous concentrations. Then, the sensor readings are matched with pre-stored threshold level. For example, x ppm concentration of a gas is detected by a particular type of sensor 40. The system determines whether the gas concentration matches with the pre-stored threshold level. An artificial intelligence predictive model represents corelation between the classified sensor readings and the pre-stored threshold levels.
[0070] The food quality analysing subsystem 210 then generates food quality scores for each of the determined gaseous concentration. In such embodiment, for x ppm concentration of gas a specific food quality score is generated. Based on the food quality score, the food quality analysing subsystem 210 predicts the quality of the stack of apples as positioned near the casing 30. For example, if the generated food quality score is more than a targeted score, the quality of the stack of apples is declared as spoilt. In such exemplary embodiment, the predicted quality is displayed to any user via a display unit. In such embodiment, if the generated food quality score is lower than the targeted score, the quality of the stack of apples is declared as good.
[0071] FIG. 9 is a process flowchart illustrating an exemplary method 230 for detecting quality of the food commodity in accordance with an embodiment of the present disclosure. At step 240, presence of one or more gases as sensor readings and location information of one or more sensors 40 A-N is obtained from the one or more sensors 40 A-N. In one aspect of the present embodiment, the sensor readings and the location information are obtained by the data capturing subsystem 200.
[0072] At step 250, type of the one or more sensors 40 A-N based on the obtained presence of the one or more gases as the sensor readings and the location information associated with associated with each of the one or more sensors are identified. In one aspect of the present embodiment, the type of the one or more sensors 40 A-N based on the obtained presence of the one or more gases as the sensor readings and the location information associated with each of the one or more sensors are identified by the data capturing subsystem 200.
[0073] At step 260, gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors 40 A-N by using an artificial intelligence-based predictive model is determined. In one aspect of the present embodiment, gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors 40 A-N by using an artificial intelligence-based predictive model is determined by a food quality analysing subsystem 210.
[0074] In gaseous concentration associated with the obtained presence of the one or more gases as the sensor readings and the identified type of the one or more sensors 40 A-N by using an artificial intelligence-based predictive model ,the method 230 includes classifying the obtained sensors readings into one or more type of gaseous concentrations. In such embodiment, the classified type of gaseous concentrations is matched with pre-stored threshold levels of corresponding gaseous concentrations. In such embodiment, the method 230 includes generating artificial intelligence predictive model for the classified sensor readings based on the determination, whereby the artificial intelligence predictive model represents corelation between the classified sensor readings and the pre-stored threshold levels and the classified type of one or more sensors.
[0075] At step 270, quality of the one or more food commodities stored in the storage 20 are predicted based on the determined gaseous concentration. In one aspect of the present embodiment, quality of the one or more food commodities stored in the storage 20 are predicted by the food quality analysing subsystem 210. In another aspect of the present embodiment, for predicting quality of the one or more food commodities stored in the storage, the method 250 generates food quality scores for each of the determined gaseous concentration. In such embodiment, the quality of the one or more food commodities stored in the storage 20 is predicted based on the generated food quality scores.
[0076] At step 280, the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors 40 is outputted on a display unit. In one aspect of the present embodiment, the predicted quality of the one or more food commodities and the location information of the identified type of the one or more sensors 40 A-N is outputted by an output subsystem 220.
[0077] The method 230 further includes generating a warning message indicating predicted quality of the one or more food commodities for one or more user devices 85. The method 230 also includes generating a heat map corresponding to the storage 20 based on pre-stored layout information of the storage and superimposing the location information of the identified type of the one or more sensors 40 A-N on the generated heat map.
[0078] A computing system 10 to detect quality of a food commodity is disclosed. The computing system 10 with help of one or more sensors 40 A-N positioned within the casing 30 detects the gaseous concentration level of gases. Such gaseous concentration levels are analysed in real time to detect quality of the food commodity by predictive analysis. Such predictive analysis is performed by artificial intelligence-based predictive models as implemented by a cloud server. The disclosed computing system 10 thereby digitizes quality for usage. The disclosed computing system 10 also provide location information of the food commodity when implemented in a storage 20. The system 10 monitors freshness of the food commodity during storage or logistics. In such embodiment, the whole process is transparent as the decision making of the freshness of the food commodity is data driven.
[0079] The one or more sensors 40 A-N used here are an array of olfactory gaseous sensors. The casing 30 uses nozzle mechanism, which helps in getting the maximum volatile concentration to each of the one or more sensors 40. Using artificial intelligence-based predictive models, quality of the one or more food commodities is predicted as well as early-stage food spoilage is detected. Wastage of the food is reduced by detecting shelf life of the specific food commodity. Artificial intelligence-based predictive models is implemented with comparison technique, which in turn gives accurate grade of quality for the food commodities.
[0080] The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependant on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.