Interactive Web-Based Expert System for Personalized Diet and Exercise Recommendations Using Forward Chaining

Abstract

The rapid increase in lifestyle-related diseases such as obesity and hypertension highlight the urgent need for accessible and personalized digital health solutions. This study proposes and evaluates an interactive web-based expert system designed to deliver personalized diet and exercise recommendations using a forward chaining inference mechanism. The system analyzes individual user characteristics, including age, body mass index (BMI), health goals, dietary preferences, and physical activity levels, collected through a structured questionnaire. A knowledge base composed of expert-defined rules is employed to infer suitable diet plans (Mediterranean, low-fat, low-carbohydrate, and DASH diets) and exercise programs (cardio and strength training). The platform was developed using the Laravel framework and MySQL database, with a responsive user interface designed through Figma. System evaluation was conducted using black box testing and the System Usability Scale (SUS), which yielded a score of 78.38. The results demonstrate stable system functionality, fast response times, and high usability, indicating that the proposed system is effective in supporting personalized digital health recommendations. This research contributes to the field of health informatics by demonstrating the applicability of rule-based expert systems for personalized diet and exercise guidance.