AN IOT BASED FOOD SPOILAGE DETECTION SYSTEM

Abstract

The present invention relates to an IOT based food spoilage detection system designed for real-time detection of food spoilage and contaminants in fruits and vegetables. Utilizing a network of sensors, including MQ-135, MQ-3, and pH sensors, the system monitors parameters indicative of spoilage, such as ammonia, alcohol, and pH levels. An Arduino Uno board processes sensor data, triggering alerts on an LCD display and via a GSM sensor for remote monitoring. The system's versatility enables applications in diverse settings, including households, restaurants, and cold storage facilities. By addressing food safety concerns and reducing wastage, this invention contributes to sustainable practices and resource conservation. The integration of connectivity protocols ensures seamless communication between components, facilitating secure data exchange and compliance with regulatory standards. Overall, this IOT based solution offers a proactive approach to food management, enhancing food safety standards and minimizing environmental impact

Specification

Description:
TECHNICAL FIELD OF INVENTION

The present invention is related to the field of electronic engineering. More specifically, it relates to an IOT based food spoilage detection system.

BACKGROUND OF THE INVENTION

The background information herein below relates to the present disclosure but is not necessarily prior art.

US11435333B2 related to a nanoparticles and compositions thereof are provided for detecting and/or preventing food spoilage. Methods of making the nanoparticles and compositions, and methods of using the nanoparticles and compositions, e.g. in food packaging, are also provided. The nanoparticles can have a hydrophobic core containing a hydrophobic active agent, e.g. a hydrophobic dye and/or an antimicrobial agent, for detecting and/or preventing food spoilage. The nanoparticles can also have a copolymer of a hydrophobic polymer repeat unit, e.g. styrene or lactic acid, and a pH responsive dendrimer repeat unit. The pH responsive dendrimer repeat unit can have a pH responsive amine core having a plurality of branched acrylate arms extending therefrom. The nanoparticles can be chemically stable at neutral pH, and then release the hydrophobic active agent at a pH range indicative of food spoilage. By releasing the hydrophobic dye and/or antimicrobial agent, the nanoparticles can detect and/or inhibit food spoilage.

US20140300891A1 a method detects the degree of spoilage of food by exposing a food sample to an excitation wave having a first wavelength of about 340 nm or about 380 nm, wherein the excitation wave has a bandwidth of 40 nm or less. The excitation wave is permitted to interact with the food sample and return emission spectra. A detector detects the emission spectra. A predetermined threshold value is established which defines when a food sample is or is not spoiled. The emission spectra is analysed at a second wavelength of about 400 nm, about 450 nm or about 530 nm to provide a test or measured value of the emission spectra indicative of the degree of spoilage of the food sample. Whether or not a food sample is spoiled beyond the predetermined threshold is determined by comparing the measured value to the predetermined threshold value.

Food deterioration during storage is a major concern worldwide. Oxidation is another major cause of the degradation of materials and food. This project focuses on preventing food waste from spoilage in "cold" and "refrigerated" storage. Food spoilage, particularly in cold storage facilities and refrigerators, constitutes a significant global challenge. The quantity of discarded food in certain nations could nourish those in need elsewhere. Food wastage becomes a threatening problem nowadays. Around 1.3 billion tons of food is wasted each year. That is enough to feed 3 billion hungry people each year at a cost of $990 billion.

Apple, scientifically known as Malus domestica, are rich in fiber, antioxidants, and essential nutrients, promoting digestive health, heart health, and potentially reducing the risk of chronic diseases like heart disease and diabetes. However, apples are susceptible to pathogenic fungi contamination during storage.

Gull et al. did a thorough research about the presence of hidden fungal diseases specifically in Pomegranates using machine learning algorithms like LDA (Linear Discriminant Analysis, BPNN and SVM for detection. Their results successfully detected 100% accuracy for healthy and infected samples using LDA. Nouri et al. implemented a smart eNose food waste management system, which camouflaged with research and projects. They made use of Arduino UNO, and various MQ series sensors, in the prototype.

This literature review explores the use of Arduino-based technology and sensor systems in detecting food spoilage, emphasizing the integration of computer vision algorithms for proactive identification and alerting users via mobile devices, contributing to food safety and waste reduction efforts. One study employs sensors and IOT technology, integrated with machine learning, to detect early signs of food spoilage by analysing emitted gasses. Leveraging a convolutional neural network (CNN) alongside various sensors, achieving 89% accuracy in detecting ripe fruit and 96% accuracy in identifying rotten fruit, the system provides an efficient means to determine food freshness, enhancing food safety and minimizing waste in the industry.

Addressing the global issue of food waste, Haidawati Nasir, et al. highlighted the staggering annual wastage of 1.3 billion tons worldwide, emphasizing the 222 million tons discarded in affluent nations. The integration of Internet of Things (IoT) technology into smart kitchen systems introduces a solution. Through a smart refrigerator system comprising sensing, control, and transmission modules - including load cells, odor sensors, Arduino UNO, and Wi-Fi connectivity - users can now monitor food freshness and quantity. This system proactively alerts users via SMS or email, mitigating food spoilage and unnecessary expenses caused by undetected expiration dates, thereby revolutionizing food management in households.

Thakur et al. addressed the pressing issue of food wastage by introducing a simple yet effective model using sensors and machine learning to predict fruit quality and potential spoilage. By harnessing the emitted gasses, particularly from fruits, the model, incorporating MQ3 & MQ7 gas sensors and an Arduino Uno, distinguishes between fresh and rotten fruits. Leveraging Principal Component Analysis (PCA) and a linear Support Vector Machine (SVM), the system achieves a remarkable cumulative variance of 99.1% over a week and an impressive 99.96% accuracy in fruit spoilage prediction. Its standout feature lies in real-time spoilage assessment and deployment of a cost-effective, versatile model applicable across various fruits and environments, offering a promising solution to curb food deterioration.

Dager et al explored an IoT's application in agriculture, addressing crop management, resource optimization, cost efficiency, and enhanced quality/quantity through sensors like air temperature, soil pH, moisture, humidity, and water volume. The proposed IoT model offers a straightforward architecture where sensors gather data transmitted via Wi-Fi to a server, enabling responsive actions based on collected information for improved farming practices. Vijaykumar et al. introduces a cost-effective IoT-based system employing various sensors to monitor real-time water quality parameters, processed by a Raspberry Pi B+ core controller, enabling remote data access via cloud computing-a pivotal step towards ensuring safe drinking water.

Karim at al. addresses food safety concerns in cold storage by proposing an IoT-based real-time monitoring system using DHT-11 sensor and ESP-8266 NodeMCU module, aiming to reduce human monitoring while ensuring temperature and humidity control, offering a comparison between traditional and IoT-centric approaches for food storage management. Ganjewar et al. proposes a sensor-based system in poultry slaughtering to detect and notify food safety officers of biological and chemical hazards, aiming to enhance product safety and align with evolving food safety standards for this. They aimed for the food agro industry, as waste conservation plays a very crucial role there. So, with the help of iot and internet monitoring these wastage levels can be reduced.

OBJECTIVE OF THE INVENTION

The primary objective of the present invention is to provide an IOT based food spoilage detection system.

Yet another objective of the invention is to tackle the alarming rise in food wastage, which has emerged as a critical global challenge.

Yet another objective of the invention is to enhance food safety standards by implementing a system capable of detecting harmful chemical contaminants in fruits and vegetables.

Yet another objective of the invention is to offer a versatile solution that can cater to a diverse range of settings, including hospitals, office pantries, restaurants, manufacturers, home cold storages, and refrigerators.
SUMMARY OF THE INVENTION

Accordingly the following invention provides an IOT based food spoilage detection system designed for real-time detection of food spoilage and contaminants in fruits and vegetables. Utilizing a network of sensors, including MQ-135, MQ-3, and pH sensors, the system monitors parameters indicative of spoilage, such as ammonia, alcohol, and pH levels.

An Arduino Uno board processes sensor data, triggering alerts on an LCD display and via a GSM sensor for remote monitoring. The system's versatility enables applications in diverse settings, including households, restaurants, and cold storage facilities. By addressing food safety concerns and reducing wastage, this invention contributes to sustainable practices and resource conservation.

The integration of connectivity protocols ensures seamless communication between components, facilitating secure data exchange and compliance with regulatory standards. Overall, this IOT based solution offers a proactive approach to food management, enhancing food safety standards and minimizing environmental impact.

BRIEF DESCRIPTION OF DRAWING

Figure 1 of Sheet 1 illustrates the circuit diagram of the present invention.

DETAILED DESCRIPTION OF THE INVENTION

As used in the description herein and throughout the claims that follow, the meaning of "a," "an," and "the" includes plural reference unless the context
clearly dictates otherwise. Also, as used in the description herein, the meaning of "in" includes "in" and "on" unless the context clearly dictates otherwise.

The present invention is related to an IOT based food spoilage detection system designed for real-time detection of food spoilage and contaminants in fruits and vegetables. Food spoilage involves a range of chemical transformations as the food degrades. Microbial growth leads to the production of byproducts like organic acids, altering taste, odor, and texture.

Proteins degrade, changing texture and introducing off-flavors. Lipid oxidation results in rancid flavors and odors, while enzymatic browning causes undesirable color changes. Fermentation by microorganisms generates acids, alcohols, and gasses, influencing taste and texture. Gas production, pH changes, and off-flavor formation further indicate spoilage. Mold growth can produce harmful mycotoxins, and preservative breakdown diminishes their effectiveness.

Monitoring sensory changes is vital in identifying spoiled food, and adherence to food safety guidelines is paramount to prevent the consumption of spoiled items. The current study focuses on spoilage detection for apples and banana. Thus, the encapsuling factors that are considered for the same are as follows:

For Apple: Ethylene Production: Apples emit ethylene gas during the ripening process, which acts as a natural hormone triggering further ripening. However, excessive ethylene exposure can lead to accelerated spoilage. Acidity and pH Change: As apples ripen, their acidity decreases, resulting in a sweeter taste. This shift is accompanied by a gradual increase in pH levels. Softening and Aroma Changes: Enzymatic activity in apples leads to the breakdown of cell walls, causing the fruit to soften. Simultaneously, changes in aroma compounds contribute to the distinctive scent of ripened apples. The standard levels of Alcohol for healthy apple are 610 to 640 ppm. The pH of a healthy apple lies between 3.3 to 4 but when it starts spoiling it shifts above 5.

For Banana: Ethylene Production: Bananas are prolific producers of ethylene gas, a natural ripening agent. Overexposure to ethylene can cause bananas to ripen quickly, potentially resulting in a mushy texture. Starch to Sugar Conversion: Unripe bananas contain higher levels of starch, which gradually converts to simpler sugars like glucose and fructose during ripening. This conversion contributes to the sweeter taste of ripe bananas. Aroma Changes: As bananas ripen, they develop a characteristic aroma attributed to the breakdown of various volatile compounds. This aroma is a key indicator of the fruit's ripeness. The standard levels of Ammonia for healthy banana are 610-640ppm. The standard levels of Alcohol for healthy banana are ppm. In bananas, the pH of a healthy banana is around 4.5 to 5.2 while when it starts to spoil it even reaches around seven.

There are numerous sensors that could be used in this invention. The primary emphasis lies in addressing food spoilage, specifically in the context of apples and bananas. This system is designed to integrate various sensors that can effectively detect a range of parameters, particularly gasses emitted by diverse food items. The goal is to establish a comprehensive solution applicable to a wide array of foods, ensuring a unified and versatile approach to spoilage detection.

The MQ135 sensor is commonly used for detecting a variety of gasses, including ammonia, nitrogen oxides, benzene, smoke, and CO2. There are several alternatives for this sensor as well, but due to reasons like cost-effectiveness, wide range of gas detection, ease of use, availability and accessibility, wide range of temperature sustenance and low power consumption the use of the MQ135 sensor has been opted.

Fruits, mainly citrus fruits during spoilage, shift their pH level in a significant manner. When fruits start to spoil the acidity decreases resulting in increased pH levels. Hence, pH is a notable criterion for detecting the spoilage of food. This backs up the use of embedding a pH sensor in this project. An easily available alternative is the soil moisture sensor.

The last sensor that is used is the MOS sensor (Metal Oxide Semiconductor). Metal-Oxide-Semiconductor (MOS) Gas Sensor: MOS gas sensors are used to detect the presence of various gasses in the environment. These sensors typically consist of a thin metal-oxide film deposited on a semiconductor material. When a specific gas interacts with the metal-oxide film, it causes changes in the electrical conductivity of the sensor, which can be measured. MOS sensors are commonly used for detecting gasses like carbon monoxide (CO), methane (CH4), and volatile organic compounds (VOCs).

But again, getting hands-on was a challenge which is why an alternative- the MQ-3 sensor has been opted. The key highlight here is that all these sensors work efficiently in cold environments. The range of these sensors is from -10 to 45°C which enables them to perform Proficiently for our vision mission in essence compatible with cold food storages and refrigerators.

This invention aims to monitor the environment around fruits and vegetables to detect changes that indicate spoilage or contamination. The MQ-135 gas sensor detects various gasses, including harmful volatile organic compounds (VOCs). The organic vapor sensor (pH sensor) and the MQ-3 alcohol sensor provide additional sensitivity to different contaminants. The Arduino Uno processes the sensor data and triggers alerts on an LCD display if abnormal readings are detected. Later, to supervise locally, a GSM sensor is integrated so that alerting text messages can be sent to the user.

Connect the MQ-135, pH sensor, and MQ-3 sensor to the analogue pins (A0, A1, A2) of the Arduino Uno. Connect the LCD display to the appropriate pins on the Arduino Uno. Set up the Arduino Uno with the necessary libraries for the sensors and LCD. Read data from the sensors at regular intervals and process the readings. Implement threshold values for gas concentrations and other parameters to indicate spoilage or contamination. Display real-time data and alerts on the LCD display. When abnormal readings are detected, trigger visual alerts on the LCD screen.

Additionally, an IOT module IFTTT, to send alerts to a remote server or smartphone app for monitoring from a distance is implemented. One of the features of the system is to detect alcohol gas and MQ3 sensor is used for the same within a detection range of 0.05mg/L to 10 mg/L. Requires a preheating duration of 20 seconds and operates on 5V power supply.

This system also intends for detecting ammonia gas for which the MQ135 sensor is used. Operates on 5V power supply and requires 20 seconds of preheating for higher accuracy. The third parameter used is pH level detection for which pH sensor is used.

It has a wide measurement range of 0-14pH.It operates effectively within a temperature range of 0 to 60 degree Celsius. The pH of a healthy apple lies between 3.3 to 4 but when it starts spoiling it shifts above 5. In bananas, the pH of a healthy banana is around 4.5 to 5.2 while when it starts to spoil it even reaches around seven.

A comprehensive SPICE macro model for ISFET pH sensors, utilizing LSTM, GRU, and their variants to compensate for temporal drift, achieving an RMSE below 0.212 ph. Additionally, MLPs effectively address temperature drift, yielding an average RMSE of less than 0.286 pH in predicting pH levels. The developed a base to the integration of a pH sensor in our project and helped with the range modulations.

IFTTT, which stands for "If This Then That," is a web-based service that allows users to create chains of simple conditional statements, called applets. These applets are triggered based on changes that occur within other web services, such as social media, productivity tools, smart devices, and more. The basic premise is if this event happens, then do that action.

A novel system merging IFTTT-like capabilities with real-time event processing for IOT services, leveraging Esper's CEP engine to classify and manage diverse data streams efficiently was approached. It addresses the limitations of traditional database-centric approaches in handling the vast influx of real-time IOT data by organizing it into formal and informal categories, enabling user-defined conditions for device data and service applications. The conclusions and hands on approach from this attempt was our initial motivation to add IFTTT in the system.
Integrating IOT and Big Data technologies, this study proposes a unified platform for real-time data monitoring and contextual services, demonstrating its efficacy through preliminary experiments in a real-case scenario. This research found the use of IFTTT module the most compatible and hence was implemented. For the testing of the developed system, different samples of the apples and bananas are selected which are lying in the different stages of the ripening process.

Table 1 For Apple kept in an open environment the results or values displayed on the console are:
Sample Number Test Parameter Observation Remark
Sample.1 Ammonia 213 ppm Healthy.
Alcohol 617 ppm Healthy.
pH 4 Healthy.
Sample.2 Ammonia 392 ppm Fully Rotten.
Alcohol 849 ppm Fully Rotten.
pH 13 Fully Rotten.
Sample.3 Ammonia 182 ppm Raw Apple
Alcohol 562 ppm Raw Apple
pH 3 Raw Apple
Sample.4 Ammonia 360 ppm Partially Rotten
Alcohol 725 ppm Partially Rotten
pH 7 Partially Rotten




















Table 2 For Apple kept in a refrigerated environment, the results or values displayed on the console are:

Sample Number Test Parameter Observation Remark
Sample.1 Ammonia 220 ppm Healthy
Alcohol 624 ppm Healthy.
pH 4 Healthy.
Sample.2 Ammonia 378 ppm Fully Rotten.
Alcohol 835 ppm Fully Rotten.
pH 12 Fully Rotten.
Sample.3 Ammonia 170 ppm Raw Apple
Alcohol 529 ppm Raw Apple
pH 3 Raw Apple
Sample.4 Ammonia 284 ppm Partially Rotten
Alcohol 311 ppm Partially Rotten
pH 7 Partially Rotten

The presence of ammonia in bananas is not as pronounced as in apples, making it a less significant parameter to consider in this context. Consequently, the implementation of MQ135 sensors has not been pursued, and the corresponding values remain undeciphered.

Table 3 For Banana kept in an open environment, the results or values displayed on the console are:

Sample Number Test Parameter Observation Remark
Sample.1 Alcohol 615 ppm Healthy.
pH 5 Healthy.
Sample.2 Alcohol 880 ppm Fully Rotten.
pH 11 Fully Rotten.
Sample.3 Alcohol 559 ppm Raw Banana.
pH 4 Raw Banana.
Sample.4 Alcohol 822 ppm Partially Rotten
pH 7 Partially Rotten

Table 4 For Banana kept in a fridge, the results or values displayed on the console are:

Sample Number Test Parameter Observation Remark
Sample.1 Alcohol 611 ppm Healthy.
pH 5 Healthy.
Sample.2 Alcohol 875 ppm Fully Rotten.
pH 10 Fully Rotten.
Sample.3 Alcohol 544 ppm Raw Banana.
pH 4 Raw Banana.
Sample.4 Alcohol 810 ppm Partially Rotten
pH 7 Partially Rotten

While various embodiments of the present disclosure have been illustrated and described herein, it will be clear that the disclosure is not limited to these embodiments only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the disclosure, as described in the claims.
, Claims:

1. An IOT based food spoilage detection system, comprising of;

a network of sensors including MQ-135, MQ-3, and pH sensors, configured to monitor parameters indicative of food spoilage and contamination, wherein said parameters include gas emissions, alcohol content, and pH levels;

an Arduino Uno board for processing sensor data received from said network of sensors;

an LCD display connected to said Arduino Uno board for providing local monitoring of sensor readings and displaying alerts triggered by abnormal readings;

a GSM sensor integrated with said Arduino Uno board for enabling remote monitoring via text alerts sent to a user's mobile device;

wherein a temperature-compatible sensors enabling effective performance in cold environments, with a range of -100C to 450C, suitable for deployment in refrigerators and cold storage facilities;

and an integration of alternative sensors such as soil moisture sensors for flexibility and adaptability to diverse environmental conditions.

Documents