Object Detection in IoT‐Based Smart Refrigerators Using CNN: Intelligent Analytics for Predictive Maintenance

With advancements in IoT, the research and development of smart homes have reached a new level. There are many instances where homes with smart technology have been built in the recent years. With the need for speed, comfort, and efficiency, smart homes are sure to make a huge impact in the future. The proposed smart fridge module is based on open-source, low-cost hardware design. The proposed framework can be added to already existing fridges. The framework has a camera that captures an image of the interior of the fridge. From this image, the different products present and their quantity are determined. The proposed system also contains various sensors that help in determining the presence of different products and their quantity. A food quality monitoring module that helps in reducing the waste generated from the fridge is also incorporated. In expansion, the framework incorporates an Android application that lets clients effortlessly check a basic need list from their mobile gadgets. The smart refrigerator module allows the refrigerator to communicate with a remote device like a mobile phone. It can determine what is present in the fridge and count the number of each object with the help of image processing. The YOLO algorithm has been used for this as it is fast and is good for real-time processing. A snap of the items in the fridge is taken every time a product is placed in or removed from the fridge. This is monitored by the PIR motion sensor. The ultrasonic sensor installed on top of the bottle measures the distance from the liquid and then the quantity of liquid can be calculated by this. The gas sensor detects if any gasses are emitted by rotten fruits. All the details are updated to the database. These can be viewed from the app. If the quantities of products are less than a predefined threshold, then a notification is sent to the mobile app