A fish meat freshness detector for IOT- based seafood market application
ABSTARCT : To help consumers enjoy healthy food, technology investigation for food freshness sensing is conducted. In this study meat is selected as the detection target based on a consumer survey CO2, TVOC, and MQ135 are investigated.
The results showed that CO2 and TVOC could be a used for food freshness sensing in a closed space such as box. In today's world, food spoilage is a crucial problem as consuming spoiled food is harmful for consumers.
Our project aims at detecting spoiled food using appropriate sensors and monitoring gases released by the food item. A micro controller that senses this, issues an alert using internet of things, so that appropriate action can be taken. This has widescale application in food industries where food detection is done manually.
We plan on implementing machine learning to this model so we can estimate how likely a food is going to get spoiled and in what duration, if brought from a particular vendor.
This will increase competition among retailers to sell more healthy and fresh food and create a safe world for all consumers alike.
We also developing a digester. The digester is designed in a such a way that biomethenization process will take place and food waste will be converted to methane and liquid manure.
Liquid manure can be used as bio fertilizer by diluting it with equal quantity of water.
Thus, this system proposes a design of a seafood freshness detector combining an electrochemical sensor and microcontroller system, using the TGS2603 gas sensor to detect the TMA gas concentration and to detect the TMA released by fish sensitively and quickly.
The TGS2603 gas sensor used in the detector is a metal oxide semiconductor type sensor with a sensitive element consisting of an integrated heater and a metal oxide on an alumina substrate, and the higher the TMA concentration is, the higher the conductivity of the gas sensor is during the testing of TMA [2,3,4] .
The test validation results show that the detector design can achieve TMA concentration measurement and complete data calibration and display of fish freshness.
Cost: Implementing IoT sensors and technology can be expensive. Initial setup costs and ongoing maintenance can be prohibitive for smaller vendors.
Technical Complexity: The technology may be complex to install and operate, requiring specialized knowledge that some seafood market vendors might lack.
Power Dependence: Many IoT devices rely on power sources, which could be an issue in markets without reliable electricity. Battery life and recharging can also be a concern.
Data Security and Privacy: With IoT devices, there are risks related to data security and privacy. Sensitive information could be vulnerable to hacking or unauthorized access.
Consumer Trust: Customers may be skeptical of technology-based freshness indicators, preferring traditional methods of assessing seafood quality.
Machine learning model uses trained model to predict if the given food item is spoilt or not based on the TVOC and ammonia content.
? ESP32 (microcontroller) sounds a buzzer when it encounters a spoilt food item. This data is sent to a cloud platform.
? Number of spoilt food occurrences can be monitored, and machine learning model can be deployed again to predict average shelf life of given food items.
Cloud Platform Integration Popular Cloud platforms like Amazon AWS can used for cloud analysis of data. For applications in food industries, we can obtain insights like:
? Occurrences of spoilt food items in a day.
? Peak time duration, in which most food items are found spoilt (day, afternoon, evening).
? How may spoilt food items are successfully separated. ? A sample plot on Amazon AWS is shown below, which shows the number of spoilt food items on different days of the month, providing easy analysis.
Enhanced Freshness Monitoring: Continuous real-time monitoring of fish freshness can help ensure high-quality seafood, reducing spoilage and waste.
Improved Supply Chain Management: IoT sensors can track freshness from the point of harvest to the market, allowing for better inventory management and minimizing losses.
Data-Driven Insights: Collecting and analyzing data on fish freshness can help vendors make informed decisions about pricing, promotions, and stock management
Quality Assurance: Implementing freshness detectors can build consumer trust by assuring them that the seafood they purchase is fresh and safe to eat.
Reduced Labor Costs: Automation of freshness checks can decrease the need for manual inspections, freeing up staff to focus on other critical tasks.
|