A Regionally Adaptable Nutrition Centric Food Recommendation System (FR-RANC)

OUR PROPOSED PROJECT TITLE:

A Multi-Factor Personalized Diet Recommendation Model Incorporating Regional and Medical Profiles

IEEE BASE PAPER ABSTRACT:

The regionally adaptable nutrition-centric food recommendation system (FR-RANC) introduces a holistic approach to personalized dietary recommendations that addresses the limitations of existing nutrition systems that often overlook regional food availability, economic conditions, and comprehensive nutrient requirements. Utilizing a decision support system (DSS) and an optimization algorithm, the system integrates user-specific data, including age, gender, health conditions, and socioeconomic status, with region-specific food databases to generate food lists that meet macro-and micronutrient needs. Unlike traditional systems, which focus on a few nutrients or specific medical conditions, FR-RANC provides a holistic solution by considering a broader range of nutrients and adapting them to various regional and economic contexts. The initial evaluation, based on systematically generated test cases, demonstrated the system’s capability to achieve approximately 90% compliance with macronutrient targets. At the same time, micronutrient results exhibit a narrow distribution around the mean, indicating strong alignment with recommended requirements, even across varying health conditions, such as diabetes, cardiovascular issues, and pregnancy. Furthermore, FR-RANC effectively addresses cold-start and scalability issues, as observed in traditional systems. These results underscore its potential as a proactive tool for promoting balanced nutrition, supporting healthcare professionals, and addressing global nutritional disparities.

PROJECT OUTPUT VIDEO:

OUR PROPOSED PROJECT ABSTRACT:

A Regionally Adaptable Nutrition Centric Food Recommendation System (FR-RANC) is designed to address the growing need for personalized, culturally relevant, and health-aware dietary guidance in diverse populations. In recent years, food recommendation platforms have primarily focused on generic calorie counts or global cuisines, often overlooking regional food habits, socioeconomic accessibility, and individual health conditions. India, being culturally and nutritionally diverse, requires a system that can adapt recommendations not only to nutritional needs but also to regional dietary practices and affordability. The increasing prevalence of lifestyle diseases such as diabetes, hypertension, obesity, and anemia further highlight the necessity for an intelligent food recommendation framework that integrates medical suitability with everyday meal planning.

The need for such a system arises from the limitations of the existing diet planning approaches, which are typically manual, non-scalable, and not tailored to individual lifestyles. Many users lack access to professional nutritionists, and even when guidance is available, it may not consider regional cuisines, economic constraints, or cultural food preferences. A nutrition recommendation model that incorporates demographic, physiological, medical, and socioeconomic parameters can significantly enhance adherence to healthy eating practices. Therefore, an automated, regionally adaptable, and nutrition-centric platform becomes essential to bridge the gap between clinical nutrition advice and practical daily food choices.

To fulfill this need, the FR-RANC system has been developed using Java as the core programming language, with JSP, CSS, and JavaScript forming the frontend interface and MySQL serving as the backend database. The system integrates user-specific data, including age, gender, health conditions, and socioeconomic status, with region-specific food databases to generate nutritionally appropriate food lists. It recommends personalized food plans using multiple key user factors, considering age, gender, height, weight, activity level, BMI, economic status, cultural background, and health conditions to create a comprehensive user profile. This multidimensional profiling enables the system to deliver recommendations that are not only nutritionally balanced but also culturally acceptable and economically feasible.

By synthesizing demographic data, nutrition science, regional cuisine knowledge, and expert validation, the FR-RANC system produces tailored food plans that are practical, safe, and nutritionally optimized. This integrated approach enhances user health awareness, supports disease-specific dietary management, and promotes sustainable, personalized nutrition practices across diverse populations.

EXISTING SYSTEM:

The existing system has explored nutrition management using databases, machine learning (ML), sensors, and computer vision. The existing system used RFID sensor chips to assess the nutrient intake in food plates. Recent advancements have focused on computer vision and ML-based methods for identifying foods and nutrients through pattern matching. However, accurate visual food analysis remains challenging because of the irregular characteristics of food images, lack of solid structures, and absence of predefined semantic patterns.
AI4Food-NutritionFW, a framework for food image datasets reflecting diverse eating behaviors. However, this method lacks nutritional quantification, which is a challenge in image-based methods.
In Europe, income-related food insecurity affects at least 10% of the population in 16 of 24 countries, with the situation being worse in Eastern and Southern Europe, where many households cannot afford a healthy diet. Food insecurity is severe in Bangladesh, with 67% of the population facing inadequate food availability by the year 2023. Low-income households, notably the bottom 40%, struggle due to inflation, floods, and limited income and rely heavily on staples such as rice, leading to malnutrition among women and children. By contrast, Canada’s social safety nets and food assistance programs alleviate food insecurity in low-income families, although 16% of households remain affected.
Differences in income, agricultural productivity, and trade drive the disparities in food access between rich and developing nations. Wealthier countries spend less than 10% of their income on food and enjoy diverse and affordable diets, owing to their higher productivity and infrastructure. In comparison, poorer countries spend over 50% of their time relying on staples because of their higher prices and limited options.

DISADVANTAGES OF EXISTING SYSTEM:

Not addressing socioeconomic barriers: In the existing system the socioeconomic barriers are not addressed which is crucial for public health.
Lack of Regional Adaptability: In the existing food recommendation systems are designed using global or generalized food databases that do not adequately represent regional cuisines. They often emphasize western dietary patterns or standardized meal templates, which may not align with the cultural eating habits of diverse populations. As a result, users from specific regions may receive recommendations that are unfamiliar, culturally inappropriate, or impractical to follow in their daily lives.
Limited Consideration of Socioeconomic Factors: In the existing systems rarely account for the economic affordability of food items while generating diet plans. Recommendations are typically based on nutritional value alone, without evaluating whether the suggested foods fall within the user’s budget. This disconnect makes it difficult for individuals from varying economic backgrounds to adopt and sustain the recommended meal plans.
Inadequate Personalization Depth: In the existing system, although they collect basic user information such as age, weight, and gender, they often fail to build a comprehensive user profile. Critical parameters like cultural background, economic status, detailed lifestyle patterns, and combined health conditions are not deeply integrated. Consequently, the recommendations may remain semi-personalized rather than fully tailored to individual needs.
Static and Generic Food Databases: Food repositories in the existing systems are generally static, containing fixed nutritional values and predefined meal combinations. They lack dynamic expansion, expert validation layers, or contextual tagging related to medical suitability, regional classification, or affordability tiers. This limits the system’s ability to evolve with new food knowledge or user requirements.
Insufficient Medical Restriction Mapping: While some systems include disease-based diet suggestions, the mapping between specific foods and multiple medical conditions is often simplistic. They may only categorize foods as “allowed” or “restricted” for a single condition, without considering comorbidities such as a user having both diabetes and hypertension. This reduces the clinical precision of the recommendations.
Absence of Expert Verification Workflow: In many existing platforms, food data and nutritional values are entered directly into the system without undergoing expert review or validation. The absence of a structured expert approval mechanism may affect the authenticity and medical reliability of the nutritional information presented to users.
Minimal Integration of Cultural Food Practices: In the existing system, they do not sufficiently integrate cultural food preparation methods, staple ingredients, or region-specific meal timing practices. This gap reduces user engagement, as individuals are more likely to follow diet plans that resonate with their habitual cuisine and cooking styles.
One-Dimensional Recommendation Logic: Recommendation engines in existing solutions often rely on single-factor filtering such as calorie limits or diet type. They lack multi-factor intelligence that simultaneously evaluates health conditions, nutrition balance, regional compatibility, and affordability. This one-dimensional logic restricts the effectiveness of generated meal plans.
Limited User Trust and Adoption: Because recommendations may not reflect users’ real-life constraints such as budget, food availability, or cultural acceptance users may find it difficult to trust or consistently follow the suggested diets. This ultimately impacts long-term adoption and the practical usefulness of the system.

PROPOSED SYSTEM:

The proposed system, titled A Regionally Adaptable Nutrition Centric Food Recommendation System (FR-RANC), is designed to generate personalized food recommendations by integrating nutritional science, regional food knowledge, socioeconomic factors, and individual health conditions into a unified intelligent framework. The proposed system is developed using Java as the core programming language, with JSP, CSS, and JavaScript for the frontend interface and MySQL as the backend database. It is structured as a web-based platform that supports interactive user participation, administrative food management, and expert nutritional validation.
The proposed system operates by constructing a comprehensive user profile that captures multiple personal and lifestyle parameters. Users begin by registering in the system and subsequently updating their profiles with demographic and physiological information, including age, gender, height in centimeters, and weight in kilograms. Based on height and weight, the system computes Body Mass Index (BMI), which contributes to nutritional assessment. Users also specify their dietary preference, selecting from vegetarian, non-vegetarian, or vegan categories. In addition, they provide their cultural or regional affiliation, such as South India, North India, or West India, enabling the system to align recommendations with familiar cuisines and traditional food practices.
Further, the proposed system incorporates socioeconomic profiling by allowing users to indicate their economic meal preference categorized as low, middle, or high budget. This parameter ensures that recommended foods correspond to affordability levels. Users also record their medical conditions, including diabetes, hypertension, obesity, anemia, or the absence of any health issues. These health inputs are stored and later mapped with food medical suitability rules to ensure that generated food plans adhere to condition-specific dietary considerations.
In the proposed system, the administrative entity functions as the central food data management unit. The admin is responsible for adding and maintaining the food repository within the system. For each food item, the admin enters detailed attributes such as food name, economic cost tier, regional classification, diet type, meal category (breakfast, lunch, or dinner), and descriptive information. This structured food metadata enables multi-dimensional filtering during recommendation generation. However, food items added by the admin are not immediately visible to users, as they undergo an expert evaluation process before activation.
The expert entity introduces a nutritional verification layer within the system. Domain experts log into their interface to review food items submitted by the admin. They analyze each food’s nutritional composition and enrich the database by entering portion size or serving quantity, calorie content, protein values, carbohydrate levels, and fat measurements. Experts also define medical restriction mappings by specifying whether a food is suitable or unsuitable for particular health conditions such as diabetes, hypertension, obesity, or anemia. Upon completing nutritional annotation and medical validation, the expert finalizes and approves the food item. Only after this approval does the food become eligible for recommendation in the user module.
Once user profiles and expert-validated food data are available, the recommendation engine processes the information to generate personalized food plans. The system evaluates multiple parameters simultaneously, including demographic attributes, BMI classification, dietary preference, regional compatibility, economic affordability, and medical restrictions. Based on this integrated analysis, it produces tailored food lists aligned with the user’s complete profile. The generated recommendations are organized according to meal categories such as breakfast, lunch, and dinner, ensuring structured daily diet planning.
Through this multi-entity, multi-parameter architecture, the proposed system establishes a comprehensive framework that combines user profiling, administrative food management, expert nutritional validation, and intelligent recommendation processing to deliver regionally adaptable and nutrition-centric dietary guidance.

ADVANTAGES OF PROPOSED SYSTEM:

Personalized Nutrition Recommendations: The proposed system generates highly personalized food recommendations by considering multiple user-specific parameters such as age, gender, height, weight, BMI, activity level, dietary preference, cultural background, economic status, and health conditions. This multi-factor profiling enables the system to deliver diet plans that closely align with individual nutritional requirements and lifestyle patterns.
Regional Adaptability: The proposed system incorporates region-specific food databases covering cuisines such as South India, North India, and West India. By aligning recommendations with users’ cultural and regional food habits, the platform ensures familiarity, acceptability, and ease of adoption in daily meal practices.
Integration of Socioeconomic Factors: Unlike the existing system diet planners, the proposed system integrates economic meal preferences by categorizing foods into low, middle, and high cost tiers. This allows users to receive recommendations that are nutritionally suitable as well as financially feasible, promoting long-term sustainability of healthy eating habits.
Health Condition–Aware Filtering: The proposed system platform incorporates medical restriction mapping for conditions such as diabetes, hypertension, obesity, and anemia. Foods are filtered based on expert-defined suitability rules, ensuring that recommendations support disease management and preventive healthcare.
Expert-Validated Nutritional Database: In the proposed system, every food item undergoes expert evaluation before being recommended to users. Nutrition specialists analyze portion size, calorie values, protein, carbohydrates, and fat content, along with medical suitability. This expert validation layer enhances the reliability and clinical relevance of the system’s recommendations.
Comprehensive User Profiling: The proposed system builds a holistic user profile by combining demographic, physiological, cultural, medical, and economic attributes. This comprehensive profiling improves recommendation precision and supports the generation of balanced, context-aware meal plans.
Structured Multi-Entity Workflow: The proposed system with three-tier architecture involving Admin, Expert, and User ensures systematic food data management. Admins manage food entries, experts validate nutritional authenticity, and users receive finalized recommendations. This structured workflow improves data quality and operational accountability.
Dynamic and Expandable Food Repository: In the proposed system, the administrative entity allows continuous addition of new food items across regions, diet types, and cost tiers. This dynamic expansion capability ensures that the system evolves over time and remains relevant to changing dietary trends and user needs.
Meal Category-Based Planning: In the proposed system, recommendations are organized into breakfast, lunch, and dinner categories, enabling users to follow structured daily diet schedules rather than receiving unorganized food suggestions.
Improved Healthcare Awareness: In the proposed system, by linking nutrition with medical conditions and BMI assessment, the system promotes preventive healthcare awareness. Users gain insights into how food choices impact their health, encouraging informed dietary decisions.
Web-Based Accessibility: Developed using Java, JSP, CSS, JavaScript, and MySQL, the system operates as a web-based platform accessible through standard browsers. This ensures ease of deployment, scalability, and usability across different user groups.
Support for Multiple Diet Preferences: The proposed system accommodates vegetarian, non-vegetarian, and vegan dietary patterns, making it inclusive and adaptable to diverse lifestyle and ethical food choices.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 20 GB.
Monitor : 15’’ LED.
Input Devices : Keyboard, Mouse.
Ram : 8 GB.

SOFTWARE REQUIREMENTS:

Operating system : Windows 10/11.
Coding Language : JAVA.
Frontend : JSP, CSS, JavaScript.
JDK Version : JDK 23.0.1.
IDE Tool : Apache Netbeans IDE 24.
Tomcat Server Version : Apache Tomcat 9.0.84
Database : MYSQL 8.0.

REFERENCE:

Mushran Siddiqui, Farhana Akther, Gazi M. E. Rahman, and Raqibul Mostafa, “A Regionally Adaptable Nutrition Centric Food Recommendation System (FR-RANC)”, IEEE ACCESS, Volume: 13, 2025.

java ieee projects

A Regionally Adaptable Nutrition Centric Food Recommendation System (FR-RANC)