A neuro fuzzy embedded agent approach towards the development of an intelligent refrigerator

This paper aims to investigate the development of an intelligent refrigerator through embedding intelligent agents in normal refrigerators. The proposed intelligent refrigerator will be able to recognize various food items and learn user consumption habits via the proposed intelligent agent. The system incorporates a low-cost camera which feeds its input to the fuzzy agent in order to classify different food items and track their amounts. Using this information, consumption patterns representing the amount of items taken by users are generated and fed into a neural network system which is aimed to learn user habits and provide feedback to the user in cases where he/she consumes an unusual number of items. The system employs a second camera to distinguish between different users so that user specific information such as items consumed and calories taken can be stored separately. The resulting system has an accuracy of ≃ 90% for item identification and shows a very good performance for learning the habits of different users. The system also provides a graphical interface to display available items which allows users to generate an automated shopping list.