FOUNDRY JOURNAL[ISSN:1001-4977] VOLUME 27 ISSUE 4
FOOD DIET RECOMMENDATION SYSTEM
USING MACHINE LEARNING
1st Ms. D. Sasi Rekha(M. Tech)
dept of COMPUTER SCIENCE and ENGINEERING
SRI VASAVI ENGINEERING COLLEGE
Pedatadepalli, INDIA
nd
2 S.Vinay Kumar 3rd K.Tammi Reddy
dept of COMPUTER SCIENCE and ENGINEERING
dept of COMPUTER SCIENCE and ENGINEERING
SRI VASAVI ENGINEERING COLLEGE
SRI VASAVI ENGINEERING COLLEGE
Pedatadepalli, INDIA
Pedatadepalli, INDIA
[email protected]
[email protected]
4th A.Yaswanth Kumar 5th Ch.Siddhu Vinayak
dept of COMPUTER SCIENCE and ENGINEERING
dept of COMPUTER SCIENCE and ENGINEERING
SRI VASAVI ENGINEERING COLLEGE
SRI VASAVI ENGINEERING COLLEGE
Pedatadepalli, INDIA
Pedatadepalli, INDIA
[email protected] [email protected] 6th S.V.Karthikeya 7th V.Kushal Ram
dept of COMPUTER SCIENCE and ENGINEERING
dept of COMPUTER SCIENCE and ENGINEERING
SRI VASAVI ENGINEERING COLLEGE
SRI VASAVI ENGINEERING COLLEGE
Pedatadepalli, INDIA
Pedatadepalli, INDIA
[email protected] [email protected] Abstract—In today’s modern world people all around the globe Our system stands as a beacon of tailored assistance, analyzing
are becoming more interested in their health and lifestyle. But just individual preferences, nutritional requirements, and health
avoiding junk food and doing exercise is not enough, we require a objectives to deliver customized recommendations. Unlike generic
balanced diet. The ” Food Diet Recommendation System ” is a
smart guide for healthy eating. By taking user-specific dietary plans, which often overlook personal nuances, our system
information such as your age, weight, height, dietary, and food dynamically adjusts to each user’s unique characteristics, fostering
preferences, it creates an automatic diet plan just for you and it the adoption of healthier eating habits and overall well-being. By
suggests specific foods that match your preferences. The system harnessing the power of machine learning algorithms, we empower
also provides a customized diet plan by focusing on achieving a
users to make informed dietary decisions, accounting for factors
balanced intake of essential nutrients, including proteins,
carbohydrates, fats, vitamins, and minerals, to meet individual such as dietary restrictions and cultural preferences. Throughout
health goals and nutritional requirements. It’s like having a this comprehensive report, we delve into the intricate details of our
friendly and clever nutrition assistant who understands your methodology, encompassing data collection methodologies,
unique needs. The main aim is to guide you towards making feature engineering techniques, and the selection of optimal
informed and enjoyable choices for a healthier life. The
machine learning models. Furthermore, we present empirical
recommendation engine is built using the KNN(K- Nearest
Neighbors) algorithm which is a supervised learning for evidence through experimental results, showcasing the efficacy
implementing neighbor searches among all the machine learning and reliability of our system. We firmly believe that our Food Diet
algorithms KNN is best suited for automatic and customized Recommendation System represents a pivotal advancement in the
recommendations. realm of personalized nutrition, poised to positively impact public
health by fostering sustained adherence to healthier dietary
Index Terms—Machine Learning techniques, KNN (K-Nearest
Neighbors) algorithm, Unsupervised Learning, Prediction, Fast
practices.
API framework, food dataset.
I. INTRODUCTION II.LITERATURE REVIEW
Our final year project presents a Food Diet Recommendation The burgeoning interest in personalized health and nutrition
System that utilizes cutting-edge machine learning techniques guidance has spurred the development of various machine
to offer personalized dietary guidance. In a modern landscape learning-based systems for diet recommendations. These
inundated with dietary options and health concerns, systems leverage user-specific data, dietary preferences, and
PAGE health
NO : 137goals to offer tailored meal plans. In this section, we
FOUNDRY JOURNAL[ISSN:1001-4977] VOLUME 27 ISSUE 4
review existing literature that explores similar themes in the well-being while catering to diverse dietary needs and
realm of food diet recommendation systems. preferences.
1. "e-Health Monitoring System with Diet and Fitness III.OBJECTIVES
Recommendation using Machine Learning" by D. Mogaveera, . The objective of this study is to consider various important
V. Mathur, and S. Waghela aspects of the user’s lifestyle and ensure that these factors are
In their work presented at the 2021 6th International incorporated while the system works on a solution to build and
Conference on Inventive Computation Technologies (ICICT), recommend a healthy and nutritious diet for the user.
Mogaveera et al. delve into an e-Health Monitoring System that
2. A good nutritious healthy diet and a moderate amount of
not only tracks health metrics but also provides personalized
diet and fitness recommendations. By employing machine physical activity can help in maintaining a healthy weight. But
learning algorithms, the system considers factors such as the the benefits of good nutrition have a lot more to do than just
user's activity levels, dietary habits, and fitness goals. This managing the weight. 3. Being fit is all about the 70/30 rule.
aligns closely with our project's aim of incorporating user Here’s how it goes, for a person to stay healthy he/she must
preferences and health objectives into our Food Diet focus 70 percent of his dietary intake and 30 percent on his
Recommendation System. physical activity device/exercise/exercise.
2. "Food Recommendation using Machine Learning for
Chronic Kidney Disease Patients" by A. Banerjee, A. Noor, N. IV. Existing system
Siddiqua, and M. N. Uddin Prediction is done using the KNN Model: This means the
Banerjee et al. present a study focusing on dietary system relies on the KNN algorithm to make recommendations
recommendations for a specific health condition - Chronic about food choices for the user. Machine Learning Model: It
Kidney Disease (CKD). Their work, showcased at the 2019 emphasizes that the system is trained using machine learning
International Conference on Computer Communication and techniques. In this case, KNN is the specific algorithm chosen.
Informatics (ICCCI), highlights the importance of personalized Takes inputs from the user: The system collects information
food recommendations for individuals with unique health from the user, which could include: Personal details like age,
challenges. The system discussed in their research tailors meal weight, and height. Activity level and lifestyle habits. Dietary
plans based on the specific nutritional needs and restrictions of restrictions and preferences. Trains the dataset using the KNN
CKD patients. This illustrates the potential of machine learning Algorithm: Based on the collected user data and existing
algorithms in catering to diverse dietary requirements, much
information, the system trains the KNN model: The data is
like our system's goal.
likely a collection of past user profiles and their corresponding
3. "Diet Recommendation System based on Different Machine
dietary recommendations. KNN identifies ”nearest
Learners: A Review" by M. Shah, S. Degadwala, and D. Vyas
neighbours” based on user information and existing data points.
Shah et al.'s review, presented at the 2022 Second International
Conference on Artificial Intelligence and Smart Energy These are the most similar individuals in the dataset to the
(ICAIS), provides an overview of diet recommendation current user. Using the dietary recommendations of these
systems employing various machine learning techniques. The nearest neighbors, the KNN model predicts new dietary
review discusses different algorithms used in these systems, suggestions for the current user.
including K-nearest neighbors (KNN), Support Vector
Machines (SVM), and Random Forests. Their comparative V. KNN ALGORITHM
analysis sheds light on the strengths and weaknesses of each
approach, offering insights into the selection of an optimal K-Nearest Neighbour is one of the simplest Machine
algorithm for personalized diet recommendations. This aligns Learning algorithms based on the Supervised Learning
with our project's methodology of utilizing the KNN algorithm technique. The K-NN algorithm assumes the similarity
for its suitability in automatic and customized food suggestions. between the new case/data and available cases and puts the new
4. "Website on Diet Recommendation Using Machine case into the category that is most similar to the available
Learning" by Shubham Singh Kardam, Pinky Yadav, Raj categories. The K-NN algorithm stores all the available data
Thakkar, and Prof Anand Ingle and classifies a new data point based on the similarity. This
Kardam et al.'s work, described in the 2021 International means when new data appears then it can be easily classified
Research, emphasizes the role of websites in delivering diet into a well-suited category by using the K- NN algorithm. The
recommendations powered by machine learning. Their system, K-NN algorithm can be used for Regression as well as for
akin to ours, focuses on user inputs such as age, weight, height, Classification but mostly it is used for Classification problems.
and activity levels to generate personalized diet plans. By K-NN is a non-parametric algorithm, which means it does not
providing a platform for users to access expert advice and track make any assumption on underlying data.It is also called a lazy
progress, their website aims to promote healthier dietary habits. learner algorithm because it does not learn from the training set
This resonates with our project's objective of empowering immediately instead it stores the dataset and at the time of
individuals to make informed decisions about their nutrition
classification, it performs an action on the dataset.KNN
through technology.
algorithm at the training phase just stores the dataset and when
PROBLEM STATEMENT it gets new data, then it classifies that data into a category that
Design and develop a machine learning-based food diet is much similar to the new data.
recommendation system that analyzes user preferences, dietary
restrictions, and nutritional requirements to suggest
personalized meal plans, aiming to improve overall health
PAGE and NO : 138
FOUNDRY JOURNAL[ISSN:1001-4977] VOLUME 27 ISSUE 4
The system processes the user-provided nutrition values to
tailor a custom diet plan. The model constructs a diet plan
according to the user’s preferences and requirements. The
system then presents the personalized diet plan to the user.
VI. IMPLEMENTATION AND DESIGN
Import necessary packages into the Notebook. For
implementation, we need a data set. So, Load the Data set.
Preprocess the loaded data set Users should enter inputs. Enter
the inputs to the Machine Learning Algorithm. As per the data
the model suggests the Diet model Add shows the Diet plan.
End of process.
VIII. RESULT
We have created a website which recommends the food items
in which we have implemented BMR by taking input age,
gender, and how much activities user’s do regularly. For
training of the system, the initial process involves the
segregation of food items depending upon the meal for which
they are consumed i.e. Breakfast, Lunch and Dinner. The
clustering of various nutrients depending upon which are
VII. SYSTEM ARCHITECTURE essential for weight loss, weight gain and health is performed.
After the clustering is performed, using Random Forest
FOOD DIET RECOMMENDATION: classifier, the nearest food items are predicted which
best suited for the appropriate diet. Our diet recommendation
• Option 1: Users provide personal information such as system allows users to basically get the desired healthy diet on
name, age, height, weight, level of daily exercise, number the basis of BMI to get balanced diet plans..
of meals per day, and weight plan.
The system internally generates a personalized diet plan based IX. CONCLUSION
on the provided information. The system calculates accurate Emerging technologies such as machine learning and
nutrition values for the recommended diet plan. Additionally, artificial intelligence are significantly shaping the landscape of
the system calculates the user’s Body Mass Index (BMI) based the IT industry. Leveraging these advancements, we’ve
on the input data. Finally, the system outputs the personalized developed a website dedicated to providing nutritional
food diet plan for the user. guidance for individuals striving to lead healthier lives. The
Custom Food Diet Recommendation: demand for such guidance is escalating as people increasingly
• Option 2: Users input nutrition values including calories,
fat content, carbohydrates, protein, sugar, fiber, sodium,
cholesterol, and saturated fats.
PAGE NO : 139
FOUNDRY JOURNAL[ISSN:1001-4977] VOLUME 27 ISSUE 4
prioritize their well-being. By integrating user preferences and
profiles into our system, we generate personalized diet plans
tailored to each individual’s needs. This approach not only
promotes better health outcomes but also enhances user
satisfaction by offering customized solutions. Through our
platform, users can access expert advice, track their progress,
and make informed decisions about their dietary habits. By
harnessing the power of technology, we aim to empower
individuals to take control of their health and embark on a
journey towards a fitter and happier lifestyle.
X. REFERENCE
1) 1. Shubham Singh Kardam, Pinky Yadav, Raj
Thakkar, Prof Anand Ingle,” Website on Diet
Recommendation Using Machine Learning,”2021
International Research
Journal of Engineering and Technology (IRJET),e-ISSN:
2395-0056.
2) 2.D. Mogaveera, V. Mathur and S. Waghela, ”e-
Health Monitoring System with Diet and Fitness
Recommendation using Machine Learning,” 2021 6th
International Conference on Inventive Computation
Technologies (ICICT), Coimbatore, India, 2021, pp. 694-
700, doi: 10.1109/ICICT50816.2021.9358605.
3) 3. A. Banerjee, A. Noor, N. Siddiqui and M. N. Uddin,
”Food Recommendation using Machine Learning for
Chronic Kidney Disease Patients,” 2019 International
Conference on Computer Communication and Informatics
(ICCCI), Coimbatore, India, 2019, pp. 1-5, doi:
10.1109/ICCCI.2019.8821871.
4) 4.M. Shah, S. Degadwala and D. Vyas, ”Diet
Recommendation System based on Different Machine
Learners: A Review,” 2022 Second International
Conference on Artificial Intelligence and Smart Energy
(ICAIS), Coimbatore, India, 2022, pp. 290-295, doi:
10.1109/ICAIS53314.2022.9742919.
PAGE NO : 140
