ECG Classification

An electrocardiogram (ECG) measures the electric activity of the heart and has been widely  used for detecting heart diseases due to its simplicity and non-invasive nature. By analyzing the electrical signal of each heartbeat, i.e., the combination of action impulse wave forms produced by diffe

Project Title

ECG Classification

Project Area of Specialization

Artificial Intelligence

Project Summary

An electrocardiogram (ECG) measures the electric activity of the heart and has been widely  used for detecting heart diseases due to its simplicity and non-invasive nature. By analyzing the electrical signal of each heartbeat, i.e., the combination of action impulse wave forms produced by different specialized cardiac tissues found in the heart, it is possible to detect some of its abnormalities. In the last decades, several works were developed to produce automatic ECG-based heartbeat classification methods. In this work, we survey the current state-of-the-art methods of ECG-based automated abnormalities heartbeat classification by presenting the ECG signal preprocessing, the heartbeat segmentation techniques, the feature description methods and the learning algorithms used. Finally, we discuss limitations and drawbacks of the methods in the literature presenting concluding remarks and future challenges, and also we propose an evaluation process workflow to guide authors in future works.

There are various types of arrhythmias and each type is associated with a pattern, and as such, it is possible to identify and  classify its type. The arrhythmias can be classified into two major categories. The first category consists of arrhythmias formed by a single irregular heartbeat, herein called morpho-logical arrhythmia. The other category consists of arrhythmias formed by a set of irregular heartbeats, herein called rhythmic arrhythmias. The classification of normal heartbeats and the ones composing the former group are on the focus of this sur-vey. These heartbeats produce alterations in the morphology or wave frequency, and all of these alterations can be identified by the ECG exam.                                           

The process of identifying and classifying arrhythmias can be very troublesome for a human being because some times it is necessary to analyze each heartbeat of the ECG records, acquired by a holter monitor for instance, during hours, or even days. In addition, there is the possibility of human error during the ECG records analysis, due to fatigue. An alternatives to use computational techniques for automatic classification.

Project Objectives

The goal of this project is machine learning which 0ffer powerful advantages in sensing systems, enabling the creation and adaption of high order signals model by exploiting the sensed data. We present a general purpose processor that employs configurable machine learning accelerators to analyze physiological signals at low energy levels for a broad range of biomedical application

Following are some objectives:

1. To develop a system that can store ECG Signals through machine learning algorithms.

2. Pre-Processes (Signal Enhancement/De-noising) on the collected data.

3. Classify and analyze the pre-processed data based on machine learning algorithm.

4. Evaluate the patients problems based on the classification.

5. Check the types of Arrhythmias( Normal, abnormal etc ) present in ECG signal

We will use our machine learning techniques for ECG signals ,that how to analyze it and how to diagnose it.

Project Implementation Method

The following contents we will use in methodology.

Data Sets:

In this research, we use MIT-BIH arrhythmia database from physionet [2]. This database contains 48 recordings from 47 subjects studied by the BIH Arrhythmia Laboratory between 1975 and 1979. Each record contains two 30-min ECG lead signal, mostly MLII lead and lead V1/V2/V4/V5. The frequency of the ECG data was 360Hz. For this research, we only use 2 channels as our source data. The first step of ECG data preprocessing is baseline noise reduction. Original ECG contains irregular distance between peaks, irregular peak form, presence of low-frequency component in ECG due to patient breathing etc. To solve the task the processing pipeline should contain particular stages to reduce influence of those factors.

Pre-Processing:

The input ECG data is initially pre-processed, i.e., noise and other artifacts are removed, followed by component detection. Once component detection is performed, the characteristics of the components are extracted. In this work, the R-R intervals and the morphology of ECG signal are used for arrhythmia detection. This is followed by arrhythmia detection process. We propose two different solutions with one based on machine learning (neural networks) and other with self-learning. We represented the processes for two methods. This data will be used by artificial neural network for arrhythmia detection. there is no need to implement PCA. Based on the extracted characteristics and the learned characteristics.

CLASSIFICATION

For the classification of the data to be processed and to classify the data, we will use different approaches of Machine Learning. These approaches will be investigated and most suitable and relevant will be applied to the model. we will trained the structure as to give us data about normal and abnormal patients. suppose If the value of node output of output layer was logic-1, we interpreted this as arrhythmia. If the value was logic-0, this was considered as normal.

Benefits of the Project

Our future scope will be further fine tuning design of MLP and pre-processing of ECG signal data so that classification results for other classes will be improved and design of MLP model to classify all 16 arrhythmia classes in one MLP design only. We hope that this system can further developed and fine-tuned for practical application.

Technical Details of Final Deliverable

Tasks

Letrature review

minutes of meeting

Read papers

learn machine language

monthly reports writing

progress reports

prepare final proposal

prepare presentation

Final Deliverable of the Project

Software System

Core Industry

Health

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Internet of Things (IoT)

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com