Fitness Trainer Application Using Artificial Intelligence

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 05 | May 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 821
Fitness Trainer Application Using Artificial Intelligence
Sushma V1, Kavya L G2, Kavya G D3, Deekshitha B S4 , Harshitha K G5
1Assistant Professor, Dept. of Computer Science and Engineering, ATME College of Engineering, Karnataka, India
2,3,4,5Students, Dept. of Computer Science and Engineering, ATME College of Engineering, Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Artificial intelligence in fitness is revolutionizing
the fitness industry which is making home workouts smarter
and better. In our work, we introduce DietFit, which is a
combination of diet planner and exercise tracker. This is an
application that detects the user’s exercise pose, counts the
specified exercise repetitions, provides an alert on each set of
repetitions, also alerts how manycaloriesareburntduring the
workout and how the user can improve their form by
providing the user with completedietaryplan. The application
uses the MediaPipe to detect a person’spose, lateranalysesthe
geometry of the pose from the dataset in real-time video and
counts the repetitions of the particular exercise. In this
application we use the Harris-Benedict formula for BMR
calculation and for recommending the diet. In that Breakfast,
Lunch, Dinner all these three things are recommended along
with snacks. We have used TDEE (total daily energy
expenditure) formula to calculate the amount of energy in
calories you burn per day. This application allow users to do
their regular exercise with the help of an AI trainer at home,
also this application is beneficial to users to maintain their
physical fitness and diet in order to get solved their various
health problems.
Key Words: Media Pipe, TensorFlow, Opencv, Harris
Benedict Formula, Total Daily Energy Expenditure
1. INTRODUCTION
In our work, we introduce an application that is useful for
both exercise tracking and diet planning. This is an AI-based
workout assistant and fitness guide to guide people who
don’t have access to a gym but are still willing to work out at
home.
In the 21st century people are moving towardsanunhealthy
nature and bad health. there arevariousreasonsbecause the
people are getting lazy in case of their physical fitness and
getting crazy about food due to the food vloggers for
example, social media is there, then their workload, lack of
motivation, and there are so many people who think that
physical fitness and dietary plans require a lot ofinvestment
in case of a gym or for fitness equipments and may lead to
lack of taste for their tastebuds if they go with dietary plans.
But in fact, if you don't have any equipment andtastydietary
plans, then also you can able to perform the exercise along
with your dietary plans and become fit and healthy.
Our application will be useful for the following categories of
people:
1. People who have a very huge workload: From that
people, we are going to take very lesstimearound20-25
min per day from there 24 hours to make their physical
fitness, healthy and make them feel fresh.
2. People who feel gym fees are not Affordable to them:
For that people, we are making an online AI-based
trainer, which will help them to do the correct exercise
and also alerts them for each set of repetitions along
with to know how many calories burnt to make them
live a comfortable life.
3. People who feel dietician’s fees are not Affordable to
them: For that people, we are makinganonlineAI-based
dietary plans, which will help them to maintain their
dietary plans and keep them healthy.
2. EXISTING SYSTEM
In the current system, people has to go to the gym to keep
their physical health in a balanced state, but many people
cannot afford them, andalsonow a days they maynotbeable
to do workouts in the gym properly due to the huge crowd,
and also forsome people its lack of motivation, andalso ifwe
cometo the dietary plans fortheir food diet, mostofthemare
not able to take dietary plans due to the food cravings, now a
days it happens mostly because of the food vlogs which
tempts the people to their favorite food items and ruin their
food diet and people are not able to maintain the healthy life.
DISADVANTAGES OF EXISTING SYSTEM
1. The requirement of a personal trainer for the workout.
2. The cost is expensive topayforgymtrainersanddieticians.
3. The repetition counts may miss.
4. Hard to remember the diet plan.
3. PROPOSED SYSTEM
The suggested method is detecting postures of the workout
along with displaying repetitions count, set count also
alerting the user with a beep sound for each setandalsogive
information regarding how many calories are burnt during
the workout and the proper dietary food plan is

recommended. Herewedevelopanapplicationinwhichuser
will get artificial intelligence-based trainers with the help of
image processing & video processing. And also dietaryplans
using artificial intelligence without any dieticians.
ADVANTAGES OF PROPOSED SYSTEM
1. There are numerousapplicationsavailableinthemarket
which guide the user about the exercises to be
performed. But through our application, we not only
guide the user regarding which exercise to perform but
also correct the posture and count the repetitions using
computer vision along with alerting system for eachset.
2. Monitor the user in real-time keeping track of the
quality repetitions of a particular exercise, thus keeping
his form intact and correct throughout their workout.
This will educate newbies about different exercise
routines and their correct postures to prevent injuries.
3. The application also offers personalized health advice
and nutrition ideas while keeping the daily calorielogin
the database.
4. The application can not only be used by individuals at
home but by increasing the scope canbeused ingymsas
smart trainers thus reducing human intervention.
5. Our main motive is to spread awareness about the
importance of good health and fitness among the
common people.
4. SYSTEM ARCHITECTURE
Fig -1: System Architecture of dietary plan
Fig -2: System Architecture of exercise
5. METHEDOLOGY
Our project is divided into two modules namely
1. Dietary Plan
2. Exercise Corrector and repetition counter
5.1 Dietary Plan
For dietary plan implementation we will use the TDEE (total
daily energy expenditure) formula.
TDEE, total daily energy expenditure,istheamountofenergy
in calories you burn per day. TDEE is best calculated by
factoring in your BMR, or basal metabolic rate, and your
activity level. BMR is the amount of calories you would burn
per day at rest.
Harris-Benedict formula
Male: BMR = 66 + (13.7 x weight in kg) + (5 x height in cm) –
(6.8 x age in years)
Female: BMR = 655 + (9.6 x weight in kg) + (1.8 x height in
cm) – (4.7 x age in years)
TDEE is calculated by multiplying BMR with Activity Factor
depending on Physical Activity.
1. Sedentary = BMR x 1.2 (little or no exercise, desk job)
2. Lightly active = BMR x 1.375 (light exercise/ sports 1-3
days/week)
3.Moderately active = BMR x 1.55 (moderate exercise/
sports 6-7 days/week)
4. Very active = BMR x 1.725 (hard exercise every day, or
exercising 2 xs/day)
5. Extremely active = BMR x 1.9 (hard exercise 2 or more
times per day)
5.2 Exercise Corrector and repetition counter
Pose estimation is a machinelearning task that estimatesthe
pose of a person from an image or a video by estimating the
spatial locations of specific body parts (key points). Pose
estimation is a computer vision technique to track the
movements of a person or an object. This is usually
performed by finding the location of key points for the given
objects. Based on these key points we can compare various
movements and postures and draw insights.

Fig -3: 33 Landmarks detected on the human body using
MediaPipe
1. Media pipe
Media pipe is an open-source cross-platform framework for
building multimodal machine learning pipelines. It can be
used to implement cutting-edge models like human face
detection, multi-hand tracking, hair segmentation, object
detection and tracking, and so on.
2. TensorFlow
TensorFlow is an end-to-end open source platform for
machine learning. It is a rich system for managingall aspects
of a machine learning system. However, this classfocuseson
using a particular TensorFlow API to develop and train
machine learning models.
6. DATA FLOW DIAGRAM
The DFD is also called as bubble chart. It is a simple
graphical formalism that can be used to represent a system
in terms of input data to the system, various processing
carried out on this data, and the output data is generated by
this system.
The data flow diagram (DFD) is one of the most important
modeling tools. It is used to model the system components.
These components are the system process, the data used by
the process, an external entity that interacts withthesystem
and the information flows in the system.
DFD shows how the information moves through the system
and how it is modified by a series of transformations. It is a
graphical technique that depicts information flow and the
transformations that are appliedasdata movesfrominputto
output.
DFD is also known as bubble chart. A DFD may be used to
represent a system at any level of abstraction. DFD may be
partitioned into levels that representincreasinginformation
flow and functional detail.
Fig -4: Data flow diagram
7. ACTIVITY DIAGRAM
Activity diagrams are graphical representations of
workflows of stepwiseactivitiesandactionswithsupport for
choice, iteration and concurrency. In the Unified Modeling
Language, activity diagrams can be used to describe the
business and operational step-by-step workflows of
components in a system. An activity diagram shows the
overall flow of control.
Fig -5: Activity diagram
8. LIMITATIONS
1. The application can estimate the poses and count
repetitions for a limited number of exercises.
2. The application is limited with single-person
compatibility at a time.

9. CONCLUSIONS
There are several applications for pose detection in real-life.
Here, we develop into one such application to learn more
about pose detection. We present an application for
monitoring workouts without any involvementofa personal
trainer. The application offers features like pose estimation,
real-time workout analysis and is getting the best results.
The emerging technologies like machine learning and
artificial intelligence playing a important part in the
development of the IT (Information Technology)industries.
We have made use of these technologies and create a
website for people who are consultabouttheirdietand want
to lead a healthy life. The importance of nutritional guidance
is increasing day by day to lead a healthy and fit life and by
accepting the user’s preferences and a user’s profile in the
system a healthy diet plan is generated.
FUTURE ENHANCEMENT
In future we can improve this project by adding more
exercises and also linking both the modules. This web
application can be implemented as mobile application so
that the user finds it easier to use and operate. Further, our
work can also be enhanced by introducing real time voice
instructions to the user so that the user can follow those
instructions and do workouts more accurately.
ACKNOWLEDGEMENT
Special thanks to our team guide, Mrs. Sushma V for all of
her support and direction, which helped the project to be
successfully completed and yield positive results at the end.
SNAPSHOTS OF DIET RECOMMENDATION
Fig -6: Home Page
Fig -7: User registration
Fig -8: User registration successful
Fig -9: User login
Fig -10: User home page
Fig -11: Taking user input
Fig -12: Diet recommendation

Fig -13: Preview of previous diet plan
Fig -14: Contact details
SNAPSHOTS OF EXERCISE POSE DETECTION
Fig -15: Starting position of bicep curl
Fig -16: User performing bicep curl
Fig -17: User completed 1 set of bicep curl
Fig -18: User performing bicep curl correctly
Fig -19: User completed 2 sets of bicep curl
Fig -20: Starting position of squat
Fig -21: User performing squat

Fig -22: User performing squat correctly
Fig -23: User completed 1 set of squat
Fig -24: User completed 3 sets of squat
REFERENCES
1. “PersonLab: Person Pose Estimation & Instance
Segmentation with a Bottom-Up, Part-Based,
Geometric EmbeddingModel”G.Papandreou,T.Zhu,
L.-C.Chen, S.Gidaris, J.Tompson, K.Murphy
2. “Deep Learning-based Human Pose Estimation
using OpenCV” By V Gupta.
3. “Pose Trainer: Correcting Exercise Posture using
Pose Estimation”. By S.Chen, R.R. Yang Department
of CS., Stanford University.
4. “MediaPipe Hands: On-device Real-time Hand
Tracking.” F.Zhang, V.Bazarevsky, A.Vakunov,
A.Tkachenka, G.Sung, C.L. Chang, M.Grundmann.
5. “Composite fields for human pose estimation” by S
Kreiss, L Bertoni, and A Alah, IEEE Conference on
Computer Vision and Pattern Recognition pages
11977–11986, 2019.
6. https://www.omnicalculator.com/health/bmr-
harris-benedict-equation#how-can-you-calculate-
your-bmr
BIOGRAPHIES
Sushma V has been awarded with B.E
and M.Tech degree from Visvesvaraya
Technological University.Currentlyshe
is working as Assistant Professor in
ATME College of Engineering, Mysuru.
Her research interests include
optimization in sensor networks, data
transmission and security in cloud
computing.
Kavya L G is a UG student currently
pursuing B.E. in the department of
computer science and engineering in
Kavya G D is a UG student currently
pursuing B.E. in the department of
computer science and engineering in
Deekshitha B S is a UG student
currently pursuing B.E. in the
department of computer science and
engineering in ATME College of
Engineering, Mysuru.
Harshitha K G is a UG student
currently pursuing B.E. in the
department of computer science and
engineering in ATME College of
Engineering, Mysuru.

Fitness Trainer Application Using Artificial Intelligence

More Related Content

Similar to Fitness Trainer Application Using Artificial Intelligence (20)

More from IRJET Journal (20)

Recently uploaded (20)

Fitness Trainer Application Using Artificial Intelligence