Temperature Prediction on medicines using machine learning through regression.

Abstract

Temperature control is a mainstay during medicine storage. Drug stores sell some medical items which are kept in fridges. when the frequency of opening and closing the fridge there is a possibility of entering the outside hot air into the fridge. This will increase the inner fridge temperature, and it may go beyond the allowed storage temperature range as well. In this paper, we propose a model that will be used in multiple chamber fridges to keep indicating the time remaining for the inner temperature to go beyond the allowed range, and if the time is short, the system will advise the pharmacist not to open that particular room and instead recommend a room with enough time slots (time to reach the upper limit temperature). We built a multiple linear regression model using training data from a thermo-electric cooler-based fridge to forecast how long it will take for a given space to reach the cut-off temperature if it is opened. This created model is evaluated using the coefficient of determination R² and obtained 77% accuracy, and this helps to develop a smart fridge with multiple rooms for storing sensitive medical productsefficiently.