A Rule-Based Expert Advisory System for Restaurants Using Machine Learning and Knowledge-Based Systems Techniques

Khalid M. O. Nahar, Mustafa Banikhalaf, Firas Ibrahim, Mohammed Abual-Rub, Ammar Almomani, Brij B. Gupta

Source Title: International Journal on Semantic Web and Information Systems (IJSWIS)19(1)

ISSN: 1552-6283|EISSN: 1552-6291|EISBN13: 9781668479094|DOI: 10.4018/IJSWIS.333064

MLA

Nahar, Khalid M. O., et al. "A Rule-Based Expert Advisory System for Restaurants Using Machine Learning and Knowledge-Based Systems Techniques." IJSWIS vol.19, no.1 2023: pp.1-25. http://doi.org/10.4018/IJSWIS.333064

APA

Nahar, K. M., Banikhalaf, M., Ibrahim, F., Abual-Rub, M., Almomani, A., & Gupta, B. B. (2023). A Rule-Based Expert Advisory System for Restaurants Using Machine Learning and Knowledge-Based Systems Techniques. International Journal on Semantic Web and Information Systems (IJSWIS), 19(1), 1-25. http://doi.org/10.4018/IJSWIS.333064

Chicago

Nahar, Khalid M. O., et al. "A Rule-Based Expert Advisory System for Restaurants Using Machine Learning and Knowledge-Based Systems Techniques," International Journal on Semantic Web and Information Systems (IJSWIS) 19, no.1: 1-25. http://doi.org/10.4018/IJSWIS.333064

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

A healthy diet and daily physical activity are a cornerstone in preventing serious diseases and conditions such as heart disease, diabetes, high blood pressure, and hypertension. They also play an important role in the healthy growth and cognitive development for young and old people. Thus, this paper presents a new restaurant advisory system (RAS) using artificial intelligence (AI) techniques such as machine learning, decision tree, and rule-based methods. The proposed system makes a smart decision based on the user's input information to generate a list of appropriate meals that fit his/her health condition. For accuracy and efficiency measurement procedure in the decision-making process, a dataset from 1100 participants suffering from several diseases such as allergy, age, and body has been created and validated. The performance of the RAS was tested using Visual Basic.net Framework and prolog language. The RAS achieves an accuracy of 100% by testing 30 different live cases.