FORM 2
THE PATENT MIT 1970
(39 of 1970)
&
The Patent: Rules. 2003
PROVISIONAL COMPLETE SPECIFICATION
(See section 10 and rule 13)

!ITLEOFI SVEETION
REVOLUTIONIZING CARDIAC DIAGNOSTICS: EAR-CONTACTLESS
STETHOSCOPE AND ENHANCED CNNS FOR HEART SOUND
CLASSIFICATION
AEEL!CAE!1$I
Name Nationality Address
hariharan Indian UG Student
Department of Computational Technologies
SRMIST,Kattankulathur,
Tamilnadu, India.
Rohit karthik Indian UG Student
Department of Computational Technologies
SRMIST,Kattankulathur,
Tamilnadu, India.
Dr. P. Madhavan Associate Professor
Indian Department of Computing Technologies
SRM Institute of Science and Technology
Kattankulathur, Tamilnadu, India
a. classification ofthe system
b. Pre-processing of data
c. training and validation
d. user interface
6. integration layer

The There are five stages in this proposed work, which are explained in more detail below
FIG 1 illustrates a system for the proposed architecture of feature selection model using sparrow

PREAMBLE TO THE DESCRIPTION

[0001] The following specification particularly describes the invention and the manner in which
it is to be performed.

DESCRIPTION
Technical Field of Invention:
The creation and use of cutting-edge machine learning methods, in particular Convolutional
Neural Networks (CNN), for the classification and examination of cardiac sound data is at the
heart of the invention's technological domain.

Summary of the invention:

A ground-breaking ear-contactless stethoscope and improved convolutional neural networks [CNNs) for classifying heart sounds are the two new inventions. It includes the creation of an ear-contactless voltmeter for heart sound analysis
and the application of cutting-edge machine learning methods, such as CNNs, for the classification of cardiovascular sounds. The stethoscope's wireless and portable design allows it to be used in a variety of healthcare settings, including emergency rooms, primary care clinics, and telemedicine consultations. Using deep learning algorithms and cutting-edge computational tools can help to increase diagnostic accessibility, speed, and accuracy in cardiac diagnostics. By developing more powerful and deep learning models that can identify and categorize cardiac irregularities, the innovation seeks to improve patient outcomes and diagnostic accuracy in clinical practice.

Brief description of drawing:

The There are five stages in this proposed work, which are explained in more detail below
a. classification ofthe system
b. Pre-processing ofdata
0. training and validation
d. user interface
6. integration layer

FIG 1 illustrates a system for the proposed architecture of feature selection model using sparrow search algorithm

Detailed description of the invention:

An ear-contactless stethoscope provides a non-invasive method of recording heart sounds without
coming into direct contact with the body, according to the invention's thorough description. This novel technology improves patient comfort and hygiene while making cardiac tests more
accessible, particularly in remote or resource-constrained settings. It records high—fidelity heart rhythms without the discomfort or hygiene problems associated with using a traditional
stethoscope by utilizing state-of-the—art sensor technology. Modern machine learning and signal
processing techniques are also used into the innovation to enhance the accuracy and caliber of
heart sound analysis.

I/Weclaim:
* The project‘s claim is that more powerful and effective deep learning models can be made
by incorporating advancements into CNN-based structures for heart sound categorization.
* In the end, this will 'improve patient outcomes and diagnostic accuracy in clinical practice
by precisely detecting and classifying cardiac anomalies.
* Furthermore, the study shows how combining cutting-edge sensor technology and deep
learning algorithms might revolutionize the diagnosis and monitoring of cardiac illnesses,
especially in the development of an ear-contactless stethoscope idea.

* These developments are intended to improve patient outcomes and increase the precision
with which heart disease is identified.