2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

Calories Burned Prediction Using Machine

Learning
Dr. Amol Kadam Dr. Anurag Shrivastava Prof. Sonali K. Pawar
Bharati Vidyapeeth Saveetha School of Bharati Vidyapeeth
College of Engineering Engineering, SIMATS College of Engineering
Pune, India Chennai, India Pune, India
[email protected] [email protected] [email protected]

Vinod H Patil Jacob Michaelson Ashish Singh

Bharati Vidyapeeth SSE, Saveetha Institute of Medical and Lloyd Institute of Management and
2023 6th International Conference on Contemporary Computing and Informatics (IC3I) | 979-8-3503-0448-0/23/$31.00 ©2023 IEEE | DOI: 10.1109/IC3I59117.2023.10397623

College of Engg Technical Sciences Technology

Pune, India Chennai, India Greater Noida, India
[email protected] [email protected] [email protected]

Abstract—In today's world, where people are leading busy rural population and nearly 30% of the urban population in
lives with changes in their lifestyle and work commitments, it India are overweight. Additionally, 2019 research published
has become difficult to prioritize regular physical activity to in Lancet Diabetes and Endocrinology revealed that the
maintain good health. The lack of physical activity and occurrence of obesity in India has tripled among men and
unhealthy food habits can lead to various health issues,
doubled among women in the previous decade. These
including obesity. To maintain a healthy lifestyle, it is crucial to
balance diet and exercise, and knowing calorie intake and burn statistics indicate that a significant number of people in India
is essential. While tracking calorie intake is relatively easy, are concerned about managing their weight. As a result, our
monitoring calorie burn is challenging due to the limited project's calories burned prediction feature will fulfil the
devices available. This research aims to develop a model using growing need for tools and resources that can assist
a Random Forest Regressor machine learning algorithm to individuals in maintaining their weight.
accurately predict the number of calories burned. The model
was trained on more than 15,000 data points and demonstrated II. MOTIVATION OF RESEARCH WORK
a Root Mean Squared Error (RMSE) of 8.3. However, with
additional data, the accuracy of the model can improve over
Food has been essential to human life since ancient times
time. The primary goal of this research is to develop an
accurate and efficient model that can aid people in maintaining and has always held a significant place of interest. Each
a healthy lifestyle by accurately predicting the number of consumes food with varying nutritional values and calorie
calories burned during physical activity. counts, which can be high or low. It is therefore essential to
encourage people to exercise adequately to maintain a
Keywords— Machine Learning, Random Forest Regressor, healthy lifestyle. To achieve this, a calorie detection system
Streamlit, Calories Burned Prediction is necessary that can provide information on the calories
burned during exercise and estimate the calories based on
I. INTRODUCTION parameters such as heart rate, body temperature, age,
When people hear the word "calories", they typically duration of exercise, and gender of the user. Calorie burnt
associate it with food and weight loss. However, calories are estimation can give people useful information about their
units of heat energy, measured as the amount of energy exercise habits and assist them in making health-related
required to raise 1 gram of water by 1°C. While this decisions. Knowing the approximate number of calories
measurement can be used to assess energy-releasing systems burnt during an exercise session allows people to modify
unrelated to the human body, in the context of the human their exercise routine and nutrition to maintain a healthy
body, it refers to the amount of energy required to perform a weight and enhance their general health. Those who want to
task. Food contains varying amounts of energy, with each reduce weight can use this information to their advantage by
item having a distinct calorie count. During exercise, the modifying their caloric intake and exercise regimen
body's temperature and heart rate increase as carbohydrates accordingly. Additionally, being aware of the calories burned
are broken down into glucose and converted to energy with during exercise encourages people to keep up their exercise
the help of oxygen. To predict the amount of energy burned regimens because they can see the obvious benefits of their
during exercise, various parameters such as duration, average efforts. Overall, the ability to anticipate calorie burn properly
heart rate, temperature, height, weight, and gender can be might give people the information and inspiration they need
considered. The prediction can be made using a machine to keep up healthy routines and live a healthy life.
learning Random Forest algorithm fed with data such as
exercise time, temperature, height, weight, and age. As per III. LITERATURE SURVEY
the Indian Council of Medical Research (ICMR) survey
conducted in 2018, around 135 million individuals in India [1] The research article aimed to enhance the accuracy
are obese, and this number is expected to increase to 175 of calorie-burn prediction by incorporating a regression
million by 2025. The study also found that over 20% of the model as one of the machine learning algorithms. The data

1712
979-8-3503-0448-0/22/$31.00 ©2023 IEEE

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.
2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

underwent the requisite preparation, cleaning, and analysis [6] This research paper focuses on leveraging wearable
before being used in the regression models. K-fold sensor data and deep learning models to predict calories
validation was performed to train and test the models and burned during physical activities. The study explores the
identify the most suitable one for the study. The use of convolutional neural networks (CNNs) and recurrent
performance and predictive accuracy of the regression neural networks (RNNs) to extract meaningful features
models were assessed based on the results of model testing from sensor data, such as accelerometers and heart rate
after ten iterations. The mean accuracy was computed, measurements. By training and evaluating these models on
indicating that the Random Forest regression model had the a large dataset, the research aims to provide an accurate and
best performance in the study, with an accuracy of 95.77%. reliable method for estimating calorie expenditure in real-
time, enabling personalized fitness monitoring and
[2] The objective of this research study is to construct a guidance.
system that can guide people to adjust their food choices and
offer instructions for maintaining their bodies effectively. If [7] This research paper presents a novel approach to
the system provides users with the nutritional information of predict calorie expenditure specifically for indoor cycling
a food item and categorizes it as healthy or unhealthy, users activities. The study combines machine learning techniques
can calculate the calorie intake of their daily food items. with sensor fusion, incorporating data from multiple sensors
This suggested system assists users in managing their eating such as heart rate monitors, power meters, and motion
habits and provides information on how to burn calories sensors. By integrating and analyzing these sensor inputs
during their daily routines, which promotes their overall using machine learning algorithms, the research aims to
health. The Convolutional Neural Network model is develop a robust model for accurately estimating calorie
implemented to classify food items from the input image, burn during indoor cycling sessions. The findings have
and the proposed system offers the accuracy of the practical implications for optimizing indoor cycling
classification. workouts and enhancing fitness tracking accuracy.

[3] In this research paper, the Exercise dataset from the [8] Software programs can improve their forecast
UCI Machine Learning repository was used to predict the accuracy without explicit coding thanks to machine
number of calories burned during a workout. Four methods learning, an algorithmic approach. It works on the premise
were employed to predict the rate of burnt calories: pre- that models are built, and algorithms are used to statistically
processing the dataset with feature scaling and addressing analyze input data. These models can be tailored to different
missing values, conducting exploratory feature analysis and domains and trained to fit with management's goals by
visualizing the target variable, fitting the raw dataset to regularly updating outputs with fresh data, enabling precise
various regressors and analyzing the performance before decision-making to meet organizational goals. [9-11] This
and after scaling, and applying feature selection principles research paper's objective is to create a Python-based
such as Anova test, Correlated Feature, Variance-Based, machine learning project to foretell calorie expenditure. The
and KBest Feature methods and fitting the data to different project uses the Xgboost Regression model to achieve this.
regressors while analyzing the performance before and after
scaling. Python was used to execute the study under the A. Machine Learning
Spyder platform with Anaconda Navigator.
The machine learning lesson explains both fundamental
[4] This research paper explores the application of and sophisticated machine learning principles. Our
various machine learning techniques for accurately machine-learning tutorial is useful for both students and
predicting the number of calories burned during different working professionals.
physical activities. The study compares and analyzes the
performance of multiple algorithms, such as decision trees, Currently, it is used for many different things, including
support vector machines, and artificial neural networks, to recommender systems, email filtering, [12-14] Facebook
identify the most effective approach for predicting calorie auto-tagging, image recognition, and speech recognition.
expenditure. The results of the research provide valuable You may learn about machine learning and a variety of
insights into developing accurate and reliable calorie burn machine learning approaches, including supervised,
prediction models. unsupervised, and reinforcement learning, in this video.
Regression and classification models, clustering techniques,
[5] This research paper investigates and compares the hidden Markov models, and other [15]sequential models are
performance of different regression models in predicting among the topics you will study.
calorie expenditure during daily activities. The study
evaluates the effectiveness of linear regression, polynomial B. Existing System
regression, and ridge regression techniques, among others.
The research aims to identify the most suitable regression There are several calorie management applications
model that can accurately estimate calorie burn based on available, each with its downsides. Here are a few examples
various factors such as heart rate, activity duration, and of current system applications.
body mass index. The findings contribute to improving the
accuracy of calorie burn prediction models for personalized 1. MyFitnessPal: MyFitnessPal is a popular fitness
fitness tracking. app that allows users to track their calorie intake
and exercise routines. [16-17] One of the benefits

1713

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.
2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

of the app is its widespread use and extensive web applications with minimal coding. This makes it easy
database of exercises and corresponding calorie for data scientists and developers to create custom
burn estimates. Users can log their workouts and applications that allow users to explore and interact with
receive an estimated calorie burn based on factors data in real-time.
like exercise duration and intensity. Additionally,
the app[18] can connect with fitness tracking One of the most important features of Streamlit is its
devices like Fitbit to automatically monitor user-friendly interface. It is based on Python and provides a
exercise and calorie burn. The MyFitnessPal app is clean and intuitive interface that allows developers to create
widely used, but its calorie burn estimates may not and share applications quickly and easily. Streamlit handles
be accurate for every individual and do not many of the tasks required for building web applications
consider individual differences in metabolism and automatically, such as managing state and user input,
other factors. rendering HTML and CSS, and updating visualizations in
real-time.
2. Noom: The app provides personalized calorie burn
estimates based on factors such as age, weight, and Streamlit supports a wide range of data science tools
fitness level. It allows users to track their exercise and libraries, including NumPy, Pandas, matplotlib, and
and calorie burn through an easy-to-use interface. Plotly. This enables developers to create custom data
The app encourages users to set exercise goals and visualizations and easily integrate them into their
provides motivation and support to help them applications. Streamlit's real-time updates and data stream
achieve their goals. The calorie burns estimates capabilities are also noteworthy. Developers can build
provided by the app may not be completely applications that update in real-time as new data becomes
accurate for every individual, as they are based on available, making it an ideal platform for building
general formulas and assumptions. [19-21]Some applications that monitor and analyze live data feeds. You
users may find the app's coaching and feedback to can install Streamlit into your system using the pip install
be too intensive or overwhelming. The app requires Streamlit from your Command Prompt.
a subscription fee for full access to its features.
B. Scikit-learn
3. HealthifyMe: HealthifyMe has a feature to predict
calorie burn during exercise, which is based on Scikit-learn, also known as sklearn, is a widely used
factors such as intensity and duration. Additionally, open-source machine-learning library in Python. It offers a
the app offers personalized workout plans for comprehensive set of tools for various machine-learning
different parts of the body, making it easy to track tasks, including classification, [27] regression, clustering,
both calorie intake and workouts. HealthifyMe also dimensionality reduction, and model selection. In the project
offers an Immunity Boosting Plan, which helps for predicting calories burned during exercise, sci-kit-learn
users to eat the right food and track daily [22-24] plays a crucial role in multiple aspects.
activities to improve their immune system.
However, similar to other apps, the calorie burns It provides powerful data preprocessing techniques such
estimates provided by HealthifyMe may not be as the Standard Scaler class for normalization or
accurate for all individuals, as they are based on standardization of numerical features like age, BMI, and
general formulas and assumptions. heart rate. It also offers the Label Encoder or One Hot
Encoder classes for encoding categorical features [28] like
VI. SYSTEM DESIGN gender. These preprocessing techniques ensure that the input
data is in the appropriate format for training the Random
The following paper introduces an application designed Forest Regressor model. Scikit-learn encompasses model
to accurately predict the number of calories burned during selection functionalities. The train_test_split function
exercise. The system considers the user's weight, duration, facilitates splitting the dataset into training and testing sets,
heart rate, body temperature, gender, age, and height for enabling robust model evaluation. Additionally, the library
analysis. It also provides motivational insights into the user's offers the GridSearchCV and Randomized [29] SearchCV
calorie burn with that of similar individuals and offers tips classes for hyperparameter tuning. These tools allow an
for burning more calories. The system involves a supervised exhaustive or random search through predefined
learning algorithm, [25-26]specifically the Random Forest hyperparameter values, aiding in identifying the best model
algorithm, for calorie prediction, and the development of the configuration for optimal calorie burn predictions.
application using Streamlit. With the conclusion to our
experiment, we selected the following combinations of Furthermore, sci-kit-learn includes the Random Forest
methodologies for our model. Regressor class, which implements the Random Forest
Regressor algorithm used in the project. This class provides
A. Streamlit a range of parameters to control the behavior of the random
forest model, such as the number of trees and maximum
Streamlit is a widely used open-source framework that depth. The implementation of Random Forest Regressor in
is specifically designed for building data science sci-kit-learn is highly efficient, scalable, and well-
applications. The main advantage of Streamlit is that it optimized, making it suitable for accurate predictions of
simplifies the process of creating and deploying interactive calorie burn based on the given parameters.

1714

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.
2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

comparable calorie expenditures and general information to

Scikit-learn also offers essential evaluation metrics for encourage individuals to exercise regularly and feel
assessing model performance. Metrics like mean squared accomplished.
error (mean_squared_error) and R-squared score (r2_score)
can be computed using sci-kit-learn’s functions, enabling The proposed approach is an efficient, accurate, and
the measurement of accuracy and reliability in predicting scalable method for predicting calories burned during
calorie burn. By evaluating the model's performance, exercise. Random Forest Regressor outperforms other
potential improvements or adjustments can be identified. algorithms, such as linear regressor, in producing more
precise and accurate results. Additionally, using Streamlit
Lastly, sci-kit-learn seamlessly integrates with the enables the creation of high-quality and dependable web
Streamlit web app framework utilized in the project. The applications.
trained RandomForestRegressor model can be easily loaded
into the web app, allowing the generation of predictions A. Implementation
based on user inputs. By leveraging sci-kit-learn’s functions
[30] and methods within the web app, data preprocessing, 1. Dataset Collection: Initially, the dataset is gathered
predictions, and model evaluation can be performed and inspected for missing or duplicated values, as
efficiently, enhancing the user-friendly and interactive well as the distribution of the data.
experience.
2. Data Preprocessing: The dataset undergoes
V. PROPOSED METHODOLOGY column-wise exploratory data analysis and
preprocessing for optimal model output. Pearson
The initial project execution utilized a dataset of 15,000 correlation coefficient is calculated to measure
individuals, wherein only the necessary features, including linear relationships between variables. Learning
BMI, Age, Gender, Heart Rate, Body Temperature, and curves are plotted to evaluate performance and
Duration, were extracted. The following steps form our identify areas for improvement.
proposed methodology for calorie burn prediction:
3. Model Selection: The next step is to select the
most suitable algorithm for our model. Random
Forest Regressor is a powerful ensemble algorithm
that can handle non-linear relationships between
variables and can produce highly accurate
predictions, making it an excellent choice for our
model.

4. Model Training: The preprocessed dataset is used

to train the model, and GridSearchCV, a cross-
validation method, is applied to select
hyperparameters. The three hyperparameters used
are n_estimators, max_features, and max_depth.
The GridSearchCV is performed on five splits, and
the split with the highest accuracy is chosen.

Figure 1. Proposed Methodology 5. Evaluation: To evaluate the model's performance,

we use evaluation metrics such as Mean Absolute
User Input: The user will provide requested information, Error (MAE), Mean Squared Error (MSE), and
including height, weight, age, gender, exercise duration, Root Mean Squared Error (RMSE). Comparing the
heart rate, and body temperature. results of the RandomForestRegressor with those
of the Linear Regression, it is observed that the
Burned Calories Prediction: The proposed model uses RMSE value for the RandomForestRegressor is
the Random Forest Regressor algorithm, which utilizes the lower than that of Linear Regression. This implies
bagging technique and has three hyperparameters - that we can make more accurate predictions using
n_estimators, max_features, and max_depth. The model the RandomForestRegressor.
evaluation results show that it has an MAE of 5.33, MSE of
6. Prediction output: The final step is to display the
68.92, and RMSE of 8.3. The lower RMSE value of the
prediction output and related information, such as
Random Forest Regressor model in comparison to the Linear
similar individuals' data and general exercise
Regression model indicates the model's ability to make more
information, on the Streamlit web application
precise predictions.
VI. FUTURE WORK
Prediction display: The final output of the project
displays the prediction of calories burned during exercise Finally, areas for future work can be identified as one
based on user input, along with data about people who have area to focus on is expanding the range of features that the

1715

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.
2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

model considers improving the accuracy of the predictions. incorporating user feedback and incorporating additional
For example, including data on the user's diet, sleep, stress metrics for evaluation could help to further refine the
levels, and other lifestyle factors that may affect their calorie model's predictions. It could also be beneficial to explore
burn rate could provide a more comprehensive ways to integrate social features, such as user communities
understanding of the user's fitness profile. Additionally, and challenges, to encourage engagement and motivation.
VII. RESULTS

Figure 2. The user input parameters

The user input parameters necessary for the model to entered by the user and the predicted number of calories
anticipate how many calories it will burn are shown in the burned that corresponds
accompanying image. Additionally, it shows the information

Figure 3. Comparable outcomes and general information

The image presented provides comparable outcomes and

general information to encourage individuals and create a The web application design encompassed multiple
sense of achievement. stages, including data preprocessing, model training, and
evaluation. The collected data was carefully prepared,
VIII. CONCLUSION cleaned, and analyzed to ensure its quality and suitability for
the regression models. RMSE and MSE validation was
In conclusion, the project successfully developed a web performed to assess the performance and predictive
application leveraging Streamlit and the Random Forest accuracy of the models, allowing for the selection of the
Regressor algorithm for predicting calories burned during most suitable algorithm for the task.
exercise. By incorporating parameters such as gender, age,
BMI, body temperature, duration of exercise, and heart rate, The successful implementation of the Random Forest
the system aimed to provide accurate predictions of calorie Regressor algorithm demonstrated the capability of machine
expenditure. learning in accurately predicting calorie burn. By
considering multiple factors such as gender, age, BMI, body
Throughout the project, various methodologies and temperature, duration of exercise, and heart rate, the system
techniques were utilized to ensure the effectiveness and provided users with personalized estimates of their calorie
reliability of the calorie burn predictions. The scikit-learn expenditure, enabling them to make informed decisions
library played a crucial role in the implementation of about their exercise routines and overall health.
machine learning algorithms, offering a wide range of tools
for data preprocessing, model selection, and evaluation. Its However, it is important to note that individual
ease of use and extensive documentation made it valuable in variations in metabolism and other factors may still
building predictive models. contribute to discrepancies between predicted and actual

1716

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.
2023 6th International Conference on Contemporary Computing and Informatics (IC3I)

calorie burn. Further research and refinement of the models [16] Hill JO, Wyatt HR, Peters JC. Energy balance and obesity.
could address these individual differences and enhance the Circulation. 2012;126(1):126–32. [PMC free article] [PubMed]
accuracy of the predictions. [Google Scholar]
[17] Pontzer H. Burn: How We Burn Calories, Lose Weight, and Maintain
Health is Blown Away by New Research, New York: Avery
Overall, the project showcased the potential of machine
Publishing Group; 2015.Trevon D. Logan NBER,
learning techniques in the domain of calorie burn prediction [18] Ingmar, “Forecasting Workout Burnt Calories Using Machine
and provided a foundation for the development of a web Learning,” in Qatar Computing Research Institute, January 2016
application that can assist individuals in optimizing their [19] R.N. Dickerson, J. J. Patel, and c. j. McClain, “Protein Needs in
fitness routines and achieving their health goals. With Obese Populations. in Nutr Clin Pract. vol. 32, no. 1, 2017. doi
continuous improvement and feedback, this application 10.1177/0884533617691745.
could serve as a valuable tool in promoting healthier [20] RajSp, Alen and Fister, and Iztok, “A Systematic Review of the
lifestyles and supporting individuals in their fitness Literature on Intelligent Data Analysis Techniques for Smart Sports
journeys. Training,” in Applied Sciences, vol 10, no. 9, 2020,
https://www.mdpi.com/2076-3417/10/9/3013
[21] P. Pouladzadeh, S. Shirmohammadi "Calorie information from image
REFERENCES
of food," in IEEE, vol. 63, no. 8, pp. 1947-1956, Aug. 2014, doi:
[1] Burned Calories Prediction using Supervised Machine Learning: 10.1109/TIM.2014.2303533
Regression Algorithm: IEEE DOI: [22] Dr. Vinod H Patil, Dr. Anurag Shrivastava, Devvret Verma, Dr. A L N
10.1109/ICPC2T53885.2022.9776710 Rao, Prateek Chaturvedi, Shaik Vaseem Akram, “Smart Agricultural
https://ieeexplore.ieee.org/document/9776710 System Based on Machine Learning and IoT Algorithm”, 2nd
[2] Prediction of User’s Calorie Routine using Convolutional Neural International Conference on Technological Advancements in
Network. IJEAST, 2020 Vol. 5, Issue 3, ISSN No. 2455-2143 Computational Sciences (ICTACS), 2022. DOI: DOI:
[3] Feature Selection Intent Machine Learning based Conjecturing- 10.1109/ICTACS56270.2022.9988530
Workout Burnt Calories. Turkish Journal of Computer and [23] Dr. Vinod H Patil, Dr. Pramod A Jadhav, Dr. C. Vinotha, Dr. Sushil
Mathematics Education Vol.12 No.9 (2021), 1729 – 1742 Kumar Gupta, Bijesh Dhyani, Rohit Kumar,” Asset Class Market
[4] W. Wu and Yang J. (2009), Fast food recognition from videos, ICME Investment Portfolio Analysis and Tracking”, 5th International
2009. IEEE International Conference on. IEEE, (pp.1210–1213) Conference on Contemporary Computing and Informatics (IC3I),
[5] Pouladzadeh P., Shirmohammadi S., Bakirov A., Bulut, and Yassine December 2022. DOI: 10.1109/IC3I56241.2022.10072525
.Cloud-based SVM for food categorization, 74(14), 5243–5260, DOI [24] Vinod H Patil, Prasad Kadam, Sudhir Bussa, Narendra Singh Bohra,
10.1007/s11042-014-2116-x Dr. ALN Rao, Professor, Kamepalli Dharani,” Wireless
[6] Ankita Podutwar A., Pragati Pawar D., Abhijeet Shinde V., (2017), A Communication in Smart Grid using LoRa Technology”, 5th
Food Recognition System for Calorie Measurement, International International Conference on Contemporary Computing and
Journal of Advanced Research in Computer and Communication Informatics (IC3I), December 2022, DOI:
Engineering, Vol. 6, Issue 1, January 2017 DOI 10.1109/IC3I56241.2022.10073338
10.17148/IJARCCE.2017.6146 [25] Vinod H. Patil, Dr Shruti Oza, Vishal Sharma, Asritha Siripurapu,
[7] Zhang W., Zhao D., Gong W., Li Z., Lu Q., & Yang S. (2015), Food Tejaswini Patil, “A Testbed Design of Spectrum Management in
Image Recognition with CNN. 2015 IEEE (UIC-ATC-ScalCom), DOI Cognitive Radio Network using NI USRP and LabVIEW”,
10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.139 International Journal of Recent Technology and Engineering (IJRTE)
[8] Muthukrishnan Ramprasath, Vijay M., and Shanmugasundaram ISSN: 2277-3878, Volume-8 Issue-2S8, August 2019.
Hariharan "Image Classification using Convolutional Neural [26] Vinod H. Patil, Shruti Oza, “Green Communication for Power
Networks" in the International Journal of Pure and Applied Distribution Smart Grid”, International Journal of Recent Technology
Mathematics in 2018, Volume 119, No. 17 (pp. 1307-1319). and Engineering™ (IJRTE), ISSN:2277-3878(Online), Reg. No.:
[9] Deepika Jaswal, Sowmya. V, Soman K.P. (2014), "Image C/819981, Volume-8, Issue-1, Page No. 1035-1039, May-19
Classification Using Convolutional Neural Networks", International [27] Lakshmi P., Deepak, A., Muthuvel, S.K., Amarnatha Sarma, C
Journal of Advancements in Research and Technology, Volume 3, Design and Analysis of Stepped Impedance Feed Elliptical Patch
Issue 6, June-2014, Pages 1661-1668. Antenna Smart Innovation, Systems and Technologies, 2023, 334, pp.
[10] Shweta Suryawanshi, Vaishali Jogdande, Ankita Mane (2020), 63
"Animal Classification Using Deep Learning", International Journal [28] Gupta, A., Mazumdar, B.D., Mishra, M., ...Srivastava, S., Deepak, A.,
of Engineering Applied Sciences and Technology, Vol. 4, Issue 11, Role of cloud computing in management and education, Materials
Today: Proceedings, 2023, 80, pp. 3726–3729
ISSN No. 2455-2143, Pages 305-307.
[29] P. William, G. R. Lanke, D. Bordoloi, A. Shrivastava, A. P.
[11] C. Gopalan, B.V. Rama Sastri, and S. C. balasubramaniyam, Srivastavaa and S. V. Deshmukh, "Assessment of Human Activity
"Nutritive-Value of Indian Foods" in T. Longvah, R. Ananthan, K. Recognition based on Impact of Feature Extraction Prediction
Bhaskarachary, and K. Venkaiah, "Indian Food Composition Tables" Accuracy," 2023 4th International Conference on Intelligent
and "Dietary Guidelines for Indians" – A Manual, National Institute Engineering and Management (ICIEM), London, United Kingdom,
of Nutrition, Hyderabad, 2010. 2023, pp. 1-6, doi: 10.1109/ICIEM59379.2023.10166247.
[12] National Food Security Mission, "Operational Guidelines", [30] P. William, G. R. Lanke, V. N. R. Inukollu, P. Singh, A. Shrivastava
and R. Kumar, "Framework for Design and Implementation of Chat
Department of Agriculture and Cooperation, Ministry of Agriculture,
Support System using Natural Language Processing," 2023 4th
Government of India, 2007.Balke B, Ware R..US Armed Forces Med International Conference on Intelligent Engineering and Management
J. 1959;10(6):675–88. [PubMed] [Google Scholar] (ICIEM), London, United Kingdom, 2023, pp. 1-7, doi:
[13] Blundell JE, King Na. (2000) "Exercise, Appetite Control, & Energy." 10.1109/ICIEM59379.2023.10166939.
Nutrition. 16(7–8):519–22. [PubMed] [Google Scholar]
[14] Elbel b, Mijanovich t. Dixon B, et al. Calorie labeling, buying fast
food, and going to restaurants. Obesity. 2013;21(11):2172–9. [PMC
free article] [PubMed] [Google Scholar]
[15] Hall c, Fernhall, Kanaley ja. "Energy Expenditure of
Running/walking” comparison with PE (prediction equation). Med
Sci Sports Exerc. 2004;36(12):2128–34. [PubMed] [Google Scholar]

1717

Authorized licensed use limited to: Vignana Bharathi Institute Of Technology. Downloaded on July 09,2024 at 14:05:50 UTC from IEEE Xplore. Restrictions apply.