Sat - 13.Pdf - Child Mortality Prediction Using Machine Learning
Sat - 13.Pdf - Child Mortality Prediction Using Machine Learning
Sat - 13.Pdf - Child Mortality Prediction Using Machine Learning
Children Mortality refers to mortality of children under the age of five. The child
mortality rate, also under-five mortality rate, refers to the probability of dying
between birth and exactly five years of age. The mortality of children also happens
in fetus. The aim is to investigate machine learning based techniques for
classification of mortality fetal health classification results in best accuracy. The
analysis of dataset by supervised machine learning technique (SMLT) to capture
several information’s like, variable identification, uni-variate analysis, bi-variate
and multi-variate analysis, missing value treatments and analyze the data
validation, data cleaning/preparing and data visualization will be done on the entire
given dataset. Our analysis provides a comprehensive guide to sensitivity analysis
of model parameters with regard to performance in the classification of fetal
health. To propose a machine learning-based and additionally, to compare and
discuss the performance of various machine learning algorithms for the given
dataset.
V
TABLE OF CONTENTS
CHAPTER NO TITLE PAGE NO
ABSTRACT V
LIST OF FIGURES Viii
LIST OF ABBREVATIONS viii
1. INTRODUCTION 1
MODEL IDE 3
OBJECTIVE 3
2. LITERATURE SURVEY 5
PRESENT INVESTIGATION
SYSTEM ARCHITECTURE 7
WORKFLOW DIAGRAM 9
EXISTING SYSTEM 9
PROPOSED SYSTEM 10
SYSTEM REQUIREMENTS 10
4. METHODOLOGY AND 11
ALGORITHMS USED
INTRODUCTION TO MACHINE 11
LEARNING
PACKAGES 14
ALGORITHMS USED IN 23
THE PROJECT
PERFORMANCE ANALYSIS
REFERENCES 38
APPENDIX
A. SOURCE CODE
B. SCREENSHOTS
REPORT
FIGURE.NO NAME OF THE FIGURE PAGE.NO
LIST OF FIGURES
1. SYSTEM ARCHITECTURE 07
2. WORK FLOW DIAGRAM 09
LIST OF ABBREVATIONS
AI - ARTIFICIAL INTELLIGENCE
ML - MACHINE LEARNING
KNN - K-NEAREST NEIGHBOUR
CHAPTER-1
INTRODUCTION
Artificial intelligence (AI) is the study of how to get computers
to do things on their own, without being explicitly programmed to do so.
In the last decade, AI has brought us self-driving cars, feasible discourse
acknowledgment, strong web search, and a vastly improved
understanding of the human genome. AI is so pervasive today that you
probably use it without even realising it on a daily basis. There are many
experts who believe this is the greatest way to progress toward human-
level AI. In this course, you will learn about the most effective AI
techniques and practise putting them into action and getting them to
function on their own. Furthermore, you'll study about the theoretical
foundations of learning while also developing the practical skills
necessary to apply these tactics to new situations. Finally, you'll learn
about some of Silicon Valley's best practises for AI and AI development.
1
The global under-five mortality rate declined by 61 per cent, from 93
deaths per 1,000 live births in 1990 to 37 in 2020. Despite this
considerable progress, improving child survival remains a matter of
urgent concern. In 2020 alone, roughly 13,800 under-five deaths
occurred every day, an intolerably high number of largely preventable
child deaths.
2
products, deals, and reminders relevant to them. It uses the results to
reveal relevant advertisements to them. No human intervention
needed (automation). With ML, you don’t need to babysit your project
every step of the way. Since it means giving machines the ability to learn,
it lets them make predictions and also improve the algorithms on their
own. A common example of this is anti-virus softwares; they learn to filter
new threats as they are recognized. ML is also good at recognizing spam.
Continuous Improvement.As ML algorithms gain experience, they keep
improving in accuracy and efficiency. This lets them make better
decisions. Say you need to make a weather forecast model. As the
amount of data you have keeps growing, your algorithms learn to make
more accurate predictions faster.Handling multi-dimensional and multi-
variety data.Machine Learning algorithms are good at handling data that
are multi-dimensional and multi-variety, and they can do this in dynamic
or uncertain environments.Wide Applications.You could be an e-tailer or
a healthcare provider and make ML work for you. Where it does apply, it
holds the capability to help deliver a much more personal experience to
customers while also targeting the right customers.
1.1.MODEL IDE:
1.2 OBJECTIVE:
4
CHAPTER-2
LITERATURE SURVEY
Using Public Health Data from Sao Paulo, Brazil, Machine Learning to
Predict Neonatal MortalityLuciana Correia Alves.The mortality rate of
newborn children is a major financial and well-being quality indicator. It
is estimated that 70% of newborn deaths in Brazil are due to neonatal
deaths. Despite its importance, newborn mortality is on the rise, raising
concerns about the need for effective methods that can assist reduce this
incidence of death. In this study, a new approach is offered to categorise
infants at high risk of neonatal mortality by utilising AI algorithms to
monitor their overall health. 15 858 entries from the SINASC and SIM
databases in Sao Paulo city (Brazil) from the SP Neo Death dataset are
used to illustrate the concept in this paper. As a result, an average AUC
of 0.96 was achieved while using SVM, XGBoost, Logistic Regression,
and Random Forests AI algorithms to classify tests as either defenceless
to death or not. In addition, the SHAP technique was used to identify the
factors that had the greatest impact on the final results of the
calculations.Mortality and Morbidity. Anne Case claims that Angus
Deaton The mortality and gloominess rates among white non-Hispanic
Americans in their mid-fifties have been steadily rising since the turn of
the century, according to our latest research (Case and Deaton 2015).
More deaths from drug overdoses, suicides, and liver disease caused by
alcohol are to blame for the rise in the overall mortality rate among
whites, especially among those with only a high school diploma or less.
Among white non-Hispanics (people and women), mortality rises for
those without a general preparation, whereas it declines for those who
have a master's degree in education. Death rates among blacks and
Hispanics have continued to reduce, despite the fact that educational
achievements have been made in this area. It used to be that death rates
in the United States were depicted as high as they are in other wealthy
5
countries. The results of helpless death cannot be fully explained by
current levels of assets, particularly those that are slowly growing old,
stale, and, in any case, diminishing. While it is possible that this is just a
beginning point, we believe it is a plausible scenario in which the
deterioration of employment opportunities for whites with low levels of
education is a catalyst for a chain reaction that affects the lives of both
parents and their children. An important piece of data is shown to have
terrible effects, even if the methodology in question is successful in
promoting pay.Youngster mortality and richness decreaseAccording to
Matthias Doepke. According to Barro and Becker, children's mortality and
fruitfulness are linked in three distinct ways. “The ripeness choice is
constant in the pattern model, and the number of enduring children is not
a vulnerability. Stochastic mortality and an arrangement with consecutive
fruitfulness decisions distinguish the pattern model, which is expanded
from discrete ripeness decision. The models' quantitative forecasts are
quite similar. Despite the fact that the hard and fast ready rate declines
in each model due to an increase in child mortality, the number of
suffering young people increases. Net generation rates in industrialised
nations have dropped dramatically over the previous century due to a
variety of variables other than decreased infant and youngster
mortality..Analysis and Prediction of Child Mortality in IndiaAccording to
Rushikesh Gawande. One of the responsibilities of progress coordinators
and pioneers is to lower the mortality rate and broaden the scope of
prosperity care. There must be a breakdown of the death rates and the
reasons for the variability in order to come up with effective strategies.
There are several factors that influence the rate of child mortality, such
as the rate of birth, the rate of foetuses born, the proficiency of the
mother, and the level of undernourishment. Additionally, a thorough
examination of diseases such as jungle fever, loose bowels, and others
that affect newborns and their contribution to infant mortality is carried
out. Keeping up good health and reducing death rates necessitates an
analysis of PHCs that meet the requirements. Geographical analysis of
6
specific PHC locations can also be utilised to determine the demand for
more PHCs and to predict their locations.
CHAPTER-3
SYSTEM ARCHITECTURE: