AI-based Dynamic Shelf-life Prediction System for Packaged Foods

Author(s)	B. Ramyasri, M. Sai Akshita, K. Mokshitha, G. Keerthana, K. Vyshnavi
Country	India
Abstract	Food wastage is an inclining problem food supply chains and households, majorly because expiry dates printed on packaging are fixed and they do not consider the actual storage conditions [1],[9]. Temperature and humidity directly impact on how fast the food spoils, yet most of the people rely on the printed date. This study introduces FreshSense, an AI-Based dynamic shelf-life prediction system that uses real-time sensor data to estimate the actual remaining shelf-life of packaged food items. An Arduino Uno is linked to a DHT22 sensor to continuously track humidity and temperature. That collected data is then fed into a Random Forest Regression model trained on food-specific baseline data. Predictions are shown on a real-time web dashboard that also allows mobile access and sets off visual, audio and email warnings. The system showed excellent predicted accuracy in a range of storage settings, with an R2 score of 0.964.
Field	Engineering
Published In	Volume 17, Issue 4, April 2026
Published On	2026-04-12
Cite This	AI-based Dynamic Shelf-life Prediction System for Packaged Foods - B. Ramyasri, M. Sai Akshita, K. Mokshitha, G. Keerthana, K. Vyshnavi - IJTAS Volume 17, Issue 4, April 2026. DOI 10.71097/IJTAS.v17.i4.1257
DOI	https://doi.org/10.71097/IJTAS.v17.i4.1257
Short DOI	https://doi.org/hbxc4s

About IJTAS Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijtas.com

International Journal of Technology and Applied Science