UGC Approved Journal no 63975(19)

ISSN: 2349-5162 | ESTD Year : 2014
Call for Paper
Volume 11 | Issue 3 | March 2024

JETIREXPLORE- Search Thousands of research papers



WhatsApp Contact
Click Here

Published in:

Volume 8 Issue 10
October-2021
eISSN: 2349-5162

UGC and ISSN approved 7.95 impact factor UGC Approved Journal no 63975

7.95 impact factor calculated by Google scholar

Unique Identifier

Published Paper ID:
JETIR2110348


Registration ID:
316212

Page Number

d389-d396

Share This Article


Jetir RMS

Title

A Classification Of Human Cellular Images As 'Parasitic' Or 'Uninfected' Using Convolutional Neural Networks

Abstract

Malaria is a serious infection transmitted by Plasmodium genus protozoan parasites. It is transferred among people primarily by the female Anopheles mosquito bites, and it mostly attacks red blood cells (RBCs) in human beings. Malaria kills the majority of children in Africa, with new incidents reported every other moment. As per the 2016 World Malaria Report, an around these three billion people across 100 countries are at greater risk of contracting Malaria, with a billion people at very high risk. Malaria claimed the lives of 450,000 people worldwide in 2016, with a projected 214 million people infected. More than two-thirds of all deaths were reported among children aged below 5 in Africa. Africa as a whole contributed to 92% of all deaths caused by Malaria. The symptoms caused by Malaria are painstaking, the likes of which can lead from anything like a fever or headache to something as fatal as death. To get an idea about the severity of the disease and proceed with the diagnosis, is imperative for the count of the parasite to be accurate. This will lead to better testing and measuring of drugs resistance and effectiveness. The process of diagnosis is not standardized in all places of the world, and in some low-resource settings and countries, lagging technological advances hinge on the repertoire of the microscopists who work in isolation. This frequently leads to inaccurate outcomes as a result of poor microscopic assessment decisions. As a result of the misleading consultations, people are often given small concentrations or antibiotics drugs that are otherwise unwarranted, resulting in potential adverse effects such as diarrhoea, nausea, and abdominal pain. As a result, automating the diagnosis process will allow for accurate disease diagnosis and, as a result, will provide dependable universal healthcare to resource-scarce locations. Malaria diagnosis has been computerised using a variety of machine-learning algorithms. This paper details my recent achievement in using deep convolutional neural networks to categorise malaria-infected cells. The presented scheme  goes over the methods for developing an image dataset given by the National Library of Medicine better abbreviated as (NIH). There has been a list of augmentation approaches for data that have been used to enhance the dataset in place to avert the problem of overfitting. The dataset was trained, verified, and tested on a variety of patterns to evaluate the performance of the Convolutional Neural Network in the use-case of classification. Several autoencoders once intrinsically and extrinsically interpolated the resulting set of data.

Key Words

Malaria, RBC, Machine Learning, Data Augmentation, Convolutional Neural Network, Autoencoder

Cite This Article

"A Classification Of Human Cellular Images As 'Parasitic' Or 'Uninfected' Using Convolutional Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 10, page no.d389-d396, October-2021, Available :http://www.jetir.org/papers/JETIR2110348.pdf

ISSN


2349-5162 | Impact Factor 7.95 Calculate by Google Scholar

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 7.95 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Cite This Article

"A Classification Of Human Cellular Images As 'Parasitic' Or 'Uninfected' Using Convolutional Neural Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 10, page no. ppd389-d396, October-2021, Available at : http://www.jetir.org/papers/JETIR2110348.pdf

Publication Details

Published Paper ID: JETIR2110348
Registration ID: 316212
Published In: Volume 8 | Issue 10 | Year October-2021
DOI (Digital Object Identifier): http://doi.one/10.1729/Journal.28397
Page No: d389-d396
Country: Haridwar, Uttarakhand, India .
Area: Science & Technology
ISSN Number: 2349-5162
Publisher: IJ Publication


Preview This Article


Downlaod

Click here for Article Preview

Download PDF

Downloads

000430

Print This Page

Current Call For Paper

Jetir RMS