Abstract:
People in every walk of life have need for good recommendations to aid them in decision
making hence the need for computer-based recommender systems which are developed to
make up for human inadequacies and solve the information overload problem. Systems like
these are also being deployed in the area of diet and nutrition. However, the area of child
nutrition in recommender systems is still under researched with very few research works found
in this area. This research work employs a switching hybrid recommendation technique to give
healthy meal recommendations to both healthy and malnourished children. This will cater for
the nutrition needs of children on a large and much improved scale while being accessible and
available to children, parents and care-givers in different locations at the same time.
A background work of visiting schools to interact with school pupils precedes this work as
child food interests, likes, dislikes and allergies with respect to food had to be learned. Open
ended and dichotomous questions were used to obtain vital information for the system build;
and these responses are incorporated as initial user and food database to check the cold-start
problem. Waterlows’ classification equation is used to profile/classify users into their health
classes/status and user-based collaborative filtering algorithm is used to recommend meals to
the users based on user-user similarity. Human expert knowledge from interaction with
nutritionist is incorporated into the system as human expert database; and is used in the
recommendation process for both healthy and malnourished children. System evaluation results show the overall optimal performance and acceptance of the system. This research work
provides a platform that can help check malnutrition in Nigerian children through healthy diet
provisioning through an automated process.
