FACULTY OF APPLIED SCIENCE & TECHNOLOGY

DEPARTMENT OF COMPUTER SCIENCE

PROJECT TOPIC:

NUTRITION AND DIET RECOMMENDATION

EXPERT SYSTEM

BY:

GABRIEL BAWA STUBTECH221273

SEKU SEYRAM ETHEL STUBTECH221556
ASI GILBERT SEFAH STUBTECH221215
SEIDU ASEIKU ANI-AM STUBTECH221184
 CHAPTER ONE
INTRODUCTION
This chapter introduces the research study and provides the foundation for the design and
implementation of the Nutrition and Diet Recommendation Expert System. It presents the
background of the study, clearly defines the problem being addressed, outlines the objectives
guiding the project, and discusses the scope, significance, and limitations of the work. The
chapter concludes with the organization of the entire project.

1.1 BACKGROUND OF THE STUDY

Nutrition is one of the most important factors influencing human health and overall well-being.
Poor dietary habits have been strongly linked to chronic conditions such as obesity, diabetes,
hypertension, and cardiovascular diseases. As modern lifestyles become increasingly fast-paced
and food choices more complex, many individuals struggle to maintain healthy eating patterns.
Traditionally, dietary advice has been delivered through general guidelines developed by health
authorities. While these guidelines are valuable, they are often broad and do not fully account for
individual differences such as age, medical history, allergies, cultural preferences, and lifestyle
habits. As a result, many people receive recommendations that may not adequately suit their
specific needs.
Recent advancements in artificial intelligence (AI) have created new opportunities for
personalized nutrition. AI-driven systems can analyze user data and generate customized dietary
recommendations. Research has shown that AI-generated dietary interventions can significantly
improve nutrition-related outcomes when recommendations are tailored to individual profiles
(Wang et al., 2025). Similarly, machine learning techniques such as clustering and classification
have been successfully applied to analyze dietary patterns and user data for improved
personalization (Tsolakidis et al., 2024).
Hybrid systems that combine machine learning with big data analytics have further enhanced the
scalability and effectiveness of dietary recommendation systems (Lambay & Mohideen, 2022).
Additionally, interactive expert systems using rule-based reasoning and forward chaining have
demonstrated improved transparency and interpretability in healthcare-related applications
(Ikawati & Ramadhan, 2026).
Despite these technological advancements, many existing AI-based dietary systems still function
as “black boxes,” offering recommendations without clearly explaining how conclusions are
reached. This lack of transparency can reduce user trust and limit long-term engagement.
Furthermore, research mapping the landscape of nutrition recommendation systems highlights
ongoing challenges related to user engagement, explainability, and integration of professional
expertise (Zhao et al., 2026).
Therefore, there is a clear need for a transparent, explainable, and user-centered Nutrition and
Diet Recommendation Expert System that integrates structured nutritional knowledge, rule-based
reasoning, expert consultation, and administrative oversight into a single platform.

1.2 PROBLEM STATEMENT

Although AI-powered dietary recommendation systems are increasingly available, several
challenges persist.
First, many systems provide generalized or partially personalized recommendations that do not
fully incorporate comprehensive user health data. Second, numerous platforms rely heavily on
complex machine learning algorithms without offering clear explanations of how
recommendations are generated. This lack of explainability reduces user confidence and trust.
Additionally, limited involvement of certified nutrition professionals restricts expert validation of
dietary advice. Many systems also lack integrated administrative tools for managing users,
updating nutritional content, and monitoring system performance.
These issues create a gap in the development of a comprehensive, transparent, and professionally
guided dietary expert system. Therefore, this study seeks to design and implement a Nutrition
and Diet Recommendation Expert System that addresses these limitations by combining rule-
based reasoning, structured knowledge representation, personalized data processing, and expert
consultation within a unified platform.

1.3 OBJECTIVES OF THE STUDY

General Objective
The general objective of this study is to design and implement a transparent, intelligent, and user-
friendly Nutrition and Diet Recommendation Expert System that provides personalized and
explainable dietary guidance based on individual health conditions and lifestyle factors.
Specific Objectives
1. To develop a structured nutrition knowledge base and implement a rule-based reasoning
engine capable of generating accurate and clearly explained personalized diet
recommendations.
2. To design an interactive platform that captures users’ demographic, medical, and lifestyle
information in order to generate tailored meal plans and practical health advice.
3. To develop integrated dashboards for users, certified nutrition experts, and administrators
to support consultation, content management, and effective system monitoring.
1.4 SCOPE OF THE PROJECT
This project focuses on the design and implementation of a Nutrition and Diet Recommendation
Expert System within an academic setting.
The system will include:
 A structured knowledge base built from validated dietary guidelines.
 A rule-based reasoning engine using forward-chaining inference.
 A user module for collecting health and lifestyle information.
 A recommendation module that provides personalized meal plans and explanations.
 Expert and administrative dashboards for consultation and system management.
The study does not include nationwide deployment, integration with hospital systems, or clinical
trials. The system will function as a decision-support and educational tool and will not replace
professional medical diagnosis or treatment.

1.5 SIGNIFICANCE OF THE PROJECT

This study is significant for several reasons.
First, it contributes to the growing field of AI-driven personalized nutrition by integrating
explainable rule-based reasoning with structured expert involvement. While many systems focus
primarily on predictive accuracy, this project emphasizes transparency and user understanding.
Second, it benefits individuals by providing personalized and easy-to-understand dietary
guidance. By explaining how recommendations are derived, the system promotes trust and
encourages informed decision-making.
Third, the project supports nutrition professionals by providing a digital platform for reviewing
cases, refining dietary rules, and interacting with users.
Finally, the framework developed in this study can serve as a foundation for future AI-based
healthcare decision-support systems, particularly in educational and research institutions.

1.6 LIMITATIONS
Scope of Testing
The system will primarily be tested within an academic environment using a limited group of
users. This may restrict the generalizability of findings to larger or more diverse populations.
Additionally, large-scale clinical validation of dietary outcomes will not be conducted within the
timeframe of this project.
Technical Constraints
The accuracy of recommendations will depend heavily on the correctness and completeness of
user-provided data. Inaccurate data entry may affect the quality of outputs. Furthermore, access
to large-scale real-world nutrition datasets and certified experts for extensive validation may be
limited. The system is also designed as a rule-based expert system, which may not incorporate
highly complex machine learning optimization models.

1.7 ORGANIZATION OF WORK

The project is organized as follows:
 Chapter One: Introduction – presents the background, problem statement, objectives,
scope, significance, limitations, and organization of the study.
 Chapter Two: Literature Review – discusses existing research and technologies related
to AI-driven nutrition recommendation systems.
 Chapter Three: System Design – describes the architecture, database structure, and
knowledge base design.
 Chapter Four: System Implementation – explains the development process and
implementation of system components.
 Chapter Five: Testing and Evaluation – presents testing procedures, validation methods,
and performance evaluation.
 Chapter Six: Conclusion and Recommendations – summarizes findings and suggests
areas for future research.

References (APA In-Text Citations Used Above)

Ikawati, Y., & Ramadhan, B. A. (2026). Interactive web-based expert system for personalized
diet and exercise recommendations using forward chaining.
Lambay, M. A., & Mohideen, S. P. (2022). A hybrid approach-based diet recommendation
system using ML and big data analytics.
Tsolakidis, D., Gymnopoulos, L. P., & Dimitropoulos, K. (2024). Artificial intelligence and
machine learning technologies for personalized nutrition: A review.
Wang, X., Sun, Z., Xue, H., & An, R. (2025). Artificial intelligence applications to personalized
dietary recommendations: A systematic review.
Zhao, K., Xue, X., Chen, N., Qi, Y., Gong, J., & Hu, W. (2026). Mapping the landscape of
nutrition recommendation systems: Evidence from peer-reviewed research, apps, and patents.