VISVESVARAYA TECHNOLOGICAL UNIVERSITY

“Jnana Sangama”, Belagavi-590018, Karnataka

AI&ML Application Development Laboratory (18AIL76)

Mini Project Report
on
“IMU-based Human Activity Recognition and Payload
Estimation for Low-Back Exoskeletons”

Submitted in partial fulfillment for the award of the degree of

Bachelor of Engineering in
Artificial Intelligence & Machine Learning

Submitted by

USN Name
1BI20AI023 Kumar Shivansh Vimal

for the academic year 2023-24

Under the Guidance of

Mr. Manjunatha P B
Assistant Professor

Department of Artificial Intelligence & Machine Learning

Bangalore Institute of Technology
K.R. Road, V.V.Pura, Bengaluru-560 004
 VISVESVARAYA TECHNOLOGICAL UNIVERSITY
“Jnana Sangama”, Belagavi-590018, Karnataka

BANGALORE INSTITUTE OF TECHNOLOGY

Department of Artificial Intelligence & Machine Learning
K.R. Road, V.V.Pura, Bengaluru-560 004

Certificate

This is to certify that AI&ML Application development Laboratory Mini

project work entitled “IMU-based Human Activity Recognition and Payload
Estimation for Low-Back Exoskeletons” carried out by

USN Name
1BI20AI023 Kumar Shivansh Vimal

bonafide student of Bangalore Institute of Technology in partial fulfillment

for the award of degree of Bachelor of Engineering in Artificial Intelligence
& Machine Learning under Visvesvaraya Technological University,
Belagavi, during the academic year 2023-24 is true representation of mini
project work completed satisfactorily.

Mr. Manjunatha P B Dr. Jyothi D. G. Dr. Aswath M. U.

Assistant Professor Professor & HoD Principal
Dept. of AI&ML Dept. of AI&ML BIT
BIT, Bengaluru BIT, Bengaluru. Bengaluru.

Name of the Examiners, Signature with date

1.

2.
 ACKNOWLEDGEMENT

The satisfaction and euphoria that accompany the completion of a task would be
incomplete without crediting the people who made it possible, whose constant guidance
and encouragement crowned the efforts with success.

We would like to profoundly thank Management of Bangalore Institute of Technology for

providing such a healthy environment for successful completion of mini project work.

We would like to express our thanks to the Principal Dr. Aswath M.U. for his
encouragement that motivates us for the successful completion of mini project work.

It gives us immense pleasure to thank Dr. Jyothi D.G. Professor & Head, Department of
Artificial Intelligence & Machine Learning for her constant support and encouragement.

We would like to express our deepest gratitude to our mini project guide
Mr. Manjunatha P.B for his constant support and guidance throughout the Mini Project
work.

We are very much pleasured to express our sincere gratitude to the friendly co-operation
showed by all the staff members of Artificial Intelligence and Machine Learning
Department, BIT.
Last but not the least, we would here by acknowledge and thank our friends and family
who have been our source of inspiration always instrumental in successful completion of
the Project work.

Date: 19-12-2023 Kumar Shivansh Vimal

Place: Bengaluru

i
 ABSTRACT

‘IMU-based Human Activity Recognition (HAR) and Payload Estimation for Low-
Back Exoskeletons’ involve using Inertial Measurement Units (IMUs) to monitor and analyze
human movements, particularly focused on the lower back region. Understanding the payload
is crucial for the exoskeleton to provide appropriate support without causing discomfort or
injury to the wearer. IMUs, particularly accelerometers, can be used to measure the
accelerations experienced by the lower back or other relevant parts of the body. By analyzing
these acceleration data, it's possible to estimate the forces and loads applied to the body,
helping to determine the payload and adapt the exoskeleton's assistance accordingly.
Combining IMU-based HAR and Payload Estimation for Low-Back Exoskeletons can lead to
more intelligent and adaptive exoskeleton systems. These systems can recognize the user's
activities and dynamically adjust the level of assistance provided by the exoskeleton based on
the detected activities and the estimated payload.
In summary, this technology aims to enhance the usability and efficiency of low-back
exoskeletons by leveraging IMUs to recognize human activities and estimate the load on the
lower back, allowing for more personalized and adaptive support.
We will use LSTM’s(Long Short Term Memory) Networks as deep learning method ,
to create a model that can learn to predict movements based on time series data.

ii
INDEX

Acknowledgement ............................................................................................................... i

Abstract ............................................................................................................................... ii

1. Introduction ......................................................................................................................1

2. Literature Review .............................................................................................................3

2.1 Existing system ..........................................................................................................4

2.2 Problem statement......................................................................................................4

2.3 Proposed System ........................................................................................................5

3. System Requirements Specification .................................................................................7

3.1 Hardware Requirements ............................................................................................7

3.2 Software Requirement ...............................................................................................7

4. System Architecture .........................................................................................................8

4.1 Diagram of LSTM ......................................................................................................8

4.2 Working of LSTM ......................................................................................................8

4.3 Neural Network Architecture .....................................................................................9

4.4 Methodology………………………………………………………………………...9

4.5 Algorithm…………………………………………………………………………...11

5. Implementation and Testing……………………………………………………………12

6. Results ............................................................................................................................16

Conclusion & Future Enhancement

References
 LIST OF FIGURES

Figure Figure name Page no.

no.
01 Diagram of LSTM 08
02 Neural Network Architecture 09
03 Decreasing loss during 20 epochs of training 16
04 Graph of loss plotted with each epoch of 16
training
05 Accuracy , precision , f1 score 16