INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Severe Acute Respiratory Syndrome Corona virus-2 is the cause of COVID-19. It is a contagious illness that spreads through tiny droplets of saliva or bodily fluid from an ill person's respiratory system when they cough, snuff, or hack. HIV spreads quickly through close contact with infected individuals or by touching, conserving, or touching surfaces and things exposed to the virus. Another contagious illness known as pneumonia is frequently brought on by contamination brought on by a bacterium in the lungs' alveoli. When a lung tissue that has been infected aggravates, it produces discharge. Professionals perform physical exams and use chest X-rays and lung ultrasounds to diagnose patients to determine whether they have these conditions. In this research, we create a method to recognise pneumonia and Covid-19 infection. The four conditions evaluated were pneumonia, coronavirus pneumonia, non-coronavirus pneumonia, and regular lungs. The proposed framework for computer-based intelligence is divided into two parts. Chest X-ray volumes are classified into pneumonia and non-pneumonia in stage 1. If X-Ray has a spot with pneumonic class and further ranks it into Coronavirus negative and Coronavirus positive, stage 2 receives a contribution from stage 1. Convolutional neural networks (CNNs) in particular have achieved successful outcomes in the categorization and analysis of medical image data using artificial intelligence (AI) approaches. This research proposes a deep CNN architecture for the classification of chest X-ray images in the diagnosis of COVID-19. An efficient and precise CNN classification was difficult due to the need for a chest X-ray image collection that was large enough and of high enough quality. The dataset has been pre-processed in different phases using different techniques to create a practical training dataset for the proposed CNN model to achieve its best performance. This was done to deal with these complexities, such as the availability of a very-small-sized and imbalanced dataset with image-quality issues. Pre-processing of the datasets used in this investigation involved dataset balance, picture interpretation by medical professionals, and data augmentation. The testing findings revealed an overall accuracy of 99.5%, demonstrating the suggested CNN model's strong suit in the relevant application domain. Two situations were used to evaluate the CNN model. Using the 100 X-ray pictures from the original processed dataset, the model was assessed on the first scenario and showed 100% accuracy. The model has been tested using a separate dataset of COVID-19 X-ray pictures in the second scenario. In this test situation, the performance reached 99.5%. A comparison study of the proposed model and several machine learning algorithms has been conducted to demonstrate further that it performs better than other models. When the proposed model was tested using an independent testing set, it outperformed all other models, both generally and specifically.
"Detection of Covid-19 and Pneumonia Using Chest X-Ray", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 2, page no.b795-b799, February-2023, Available :http://www.ijnrd.org/papers/IJNRD2302180.pdf
Downloads:
000118754
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn