Preprocessing of Streaming Data using Genetic Algorithm

Desale, Ketan Sanjay; Ade, Roshani

doi:10.5120/21319-4324

Cited by 4 publications

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SA node spontaneously depolarizes between 60 and 100 times per minute when it is at rest, and the tone of the vagal (parasympathetic) nerve is predominant. The HisPurkinje system, AV node, residual atrial tissue, left and right ventricular myocardium, and SA node are the successive targets of the depolarization wave as shown in Figure 1 [3]. The AV node's modest conduction velocity allows the atria to complete its contraction prior to the ventricular muscles.…”

Section: Purposementioning

confidence: 99%

Classification Of Arrhythmia by Using Deep Learning With 2-D Ecg Spectral Image Representation

2023

JPTCP

View full text Add to dashboard Cite

We are classifying the ECG into six categories based on grayscale Deep two-dimensional convolutional neural networks are used to create ECG images (CNN). Out of these categories, one is normal and the other five represent various types of arrhythmias. Users can select the image they wish to categorize through a web application that we are creating. Please note that there are additional issues with your writing, such as punctuation and spelling, which need to be addressed. Once the image is inputted into the trained model, the resulting class will be displayed on the webpage. Arrhythmia is a prevalent cardiac condition that can lead to severe health problems. Accurate detection and classification of arrhythmia are crucial for effective treatment and management. Please note that there were additional writing issues, such as repetitive sentence structures and the use of the passive voice, which have been revised for clarity and conciseness. The accuracy of categorizing arrhythmias has increased thanks to recent research in deep learning employing 2-D spectral picture representation. ECG signals are converted using the Fourier Transform into 2-D spectral pictures, which are then input into a convolutional neural network, one type of deep neural network (CNN). From the spectral images, the CNN model learns to identify relevant features that can be used to categorize arrhythmia. The CNN model's performance can be improved through data augmentation, dropout regularization, and transfer learning, among other methods. Using standard metrics like precision, sensitivity, specificity, and the ROC curve's area, one can evaluate the model's efficacy. This approach has the potential to improve the accuracy of arrhythmia detection and classification. However, further research is required to determine its applicability in clinical settings.

show abstract

Section: Purposementioning

confidence: 99%