Scribd
Upload
44 views

Dspend

Uploaded by

Kushal Hiremath
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
44 views

Dspend

Uploaded by

Kushal Hiremath
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

Department of Electronics and Communication Engineering

Development of an ECG Arrhythmia Monitoring System

1. Kushal Hiremath 02FE21BEC038


2. Hrishikesh Kamat 02FE21BEC039
3. Mansi Dandin 02FE22BEC049
4. Prajwal Halgi 02FE21BEC059

Under the Guidance of


Prof. S. B. Kulkarni

Dept. of ECE 1
PROBLEM STATEMENT

Design and develop a system to monitor ECG arrhythmia due to atrial

or ventricular defibrillation.

Dept. of ECE 2
INTRODUCTION

Cardiac arrhythmias pose a significant threat to human health and can


lead to severe complications, including cardiac arrest. Timely detection
and monitoring of arrhythmias, especially those arising from atrial or
ventricular defibrillation, are crucial for patient well-being. To address
this, a comprehensive ECG (Electrocardiogram) monitoring system is
proposed, which focuses on real-time detection and alerting of
arrhythmias to enable swift medical intervention. .

Dept. of ECE 3
Literature Survey:
Sl No. Paper Title Objective Methods/Techniques/ Limitations /Disadvantages/
Algorithm used Remarks

1 Three-Heartbeat Multilead ECG Recognition


Method for Arrhythmia Classification.
The objective of this paper is to introduce and
validate a novel classification method for
The study integrates THML ECG data,
1D-CNN models, and a voting method
1. Data Source Limitation.
2. Generalization to Real- world
arrhythmia using three-heartbeat multi-lead to enhance the accuracy of Clinical Settings.
(THML) Electrocardiogram (ECG) data. arrhythmia classification, providing a 3. Limited Comparative Analysis.
solution to the challenges posed by 4. Clinical Validation.
manual interpretation and insufficient
samples in the context of
cardiovascular disease diagnosis.

2 Arrhythmia Disease Diagnosis Based on ECG


Time–Frequency Domain Fusion and
The objective of this study is to enhance the
diagnostic capabilities of Electrocardiogram
The overall methodology involves a
combination of signal processing
The use of multi-scale wavelet
decomposition, R-wave localization,
Convolutional Neural Network. (ECG) signals by proposing a method that techniques (wavelet decomposition, FFT, and a CNN can make the
effectively fuses both time and frequency FFT), cardiac cycle segmentation (R- proposed method computationally
domain information. wave localization), to effectively utilize intensive.
both time and frequency domain
information for ECG signal diagnosis.

3 ECG Analyzing program for Arrhythmia detection. 1. Algorithm Development for Arrhythmia
Detection.
1. ECG Analyzing Algorithm.
2. MATLAB Implementation.
1. Complexity of Arrhythmia Types.
2. Scalability.
2. User-Friendly Interface. 3. Pre-Screen Test Application.
3. Key Parameters for Analysis.

4 ECG Based Algorithm For Detecting Ventricular


Arrhythmia And Atrial Fibrillation.
1.
2.
Addressing the Global Health Issue.
Focusing on Ventricular Arrhythmia and
1. ECG Signal Processing:-It's likely
that signal processing techniques
1. Generalization to Diverse
Populations.
Atrial Fibrillation. were employed to preprocess and 2. Real-time Processing
3. Introduction of a Simple Algorithm. analyze the ECG signals Requirements.
3. Long-term Monitoring
Challenges.
4. Noise Sensitivity

Dept. of ECE 4
Characteristics of ECG signal
1. P-Wave:
1. Represents atrial depolarization.
2. Usually the first upward deflection in the ECG signal.
3. Normal duration: 0.06 to 0.11 seconds.
2. QRS Complex:
1. Represents ventricular depolarization.
2. Typically the largest and most complex part of the ECG signal.
3. Normal duration: 0.06 to 0.10 seconds.
3. T-Wave:
1. Represents ventricular repolarization.
2. Follows the QRS complex and is typically a smaller, rounded wave.
3. Normal duration: 0.16 seconds.
4. PR Interval:
1. The time from the beginning of the P-wave to the beginning of the QRS complex.
2. Represents the time it takes for the electrical impulse to travel from the atria to the ventricles.
3. Normal duration: 0.12 to 0.20 seconds.
5. QT Interval:
1. The time from the start of the QRS complex to the end of the T-wave.
2. Represents the total time for ventricular depolarization and repolarization.

Dept. of ECE 5
Data set link

https://www.physionet.org/content/?topic=normal

Dept. of ECE 6
Block Diagram:
Load ECG Data from local
Read File
file

Plot Raw ECG Signal

Apply Bandpass Filter to Remove


Noise

Plot Filtered ECG Signal

Set Threshold for Abnormal


Heartbeats

Detect Arrhythmia Peaks by


Comparing R-Peak Amplitudes to
Threshold

Plot ECG Signal with Detected Display Results (ECG Signal and
Arrhythmia
Dept. of ECE Detected Arrhythmia)
7
Implementation steps:-
1. Define Requirements:
1. Clearly define the requirements of the monitoring system.
2. Identify the target audience (medical professionals, patients, etc.).
3. Specify the types of arrhythmias to be monitored (atrial, ventricular, etc.).
4. Determine the acceptable level of accuracy and reliability.
2. Select Hardware Components:
1. Choose suitable ECG monitoring hardware that can acquire and process ECG signals.
2. Consider the type of electrodes and sensors needed for accurate signal acquisition.
3. Ensure compatibility with existing medical equipment and standards.
3. Choose Signal Processing Algorithms:
1. Research and select appropriate signal processing algorithms for detecting arrhythmias.
2. Algorithms may include filtering, feature extraction, and classification methods.
3. Consider incorporating machine learning techniques for improved accuracy.
4. Develop ECG Data Acquisition System:
1. Implement a system to acquire ECG signals from the selected hardware.
2. Ensure proper electrode placement and signal quality.
3. Implement signal conditioning and filtering to remove noise.
5. Implement Signal Processing Algorithms:
1. Develop and integrate signal processing algorithms for arrhythmia detection.
2. Test the algorithms with synthetic and real ECG data.

Dept. of ECE 8
Results:-

Dept. of ECE 9
Conclusion:-
• Developing a comprehensive ECG arrhythmia monitoring
system requires a multidisciplinary approach, involving
expertise in signal processing, machine learning, software
development, and healthcare technology. Regular updates
and collaboration with healthcare professionals can help
improve the system's effectiveness and adaptability to
evolving medical standards and practices.

Dept. of ECE 10

You might also like