Anda di halaman 1dari 11

PES institution of technology and man

agement
Department of Computer Science and Engineering
A PRESENTATION ON
DISEASE PREDICTION MODEL
Presented By
AJITH H
4PM13CS003
BHARGAVA BHAT U 4PM13CS018
DEEPAK N 4PM14CS403
VINAY A
4PM13CS112
Project Guide

Mr. SUNIL M E
Asst. Professor,
Computer Science and Engineering ,
PESITM

INTRODUCTION
Machine learning is a branch of science that deals
with programming the systems in such a way that t
hey automatically learn and improve with experien
ce. Here, learning means recognizing and understa
nding the input data and making wise decisions bas
ed on the supplied data.

EXAMPLE : Mango Shopping

Suppose you go shopping for mangoes one day. The vend


or has laid out a cart full of mangoes and you pay accordin
g to fixed rate as per kg.
Obviously, you want to pick the sweetest, most ripe mango
es for yourself. How do you choose the mangoes?
You assuming that bright yellow mangoes are sweetest.
Now, Some of them are not sweet as you would like. After
lot pondering you conclude that the bigger mango is sweet
est.
Now, you are happy with your findings, and you keep the
m in mind the next time you go for mango shopping pick t
he bigger mango and yellow color.

Now we are writing a computer program to


help you
choose your mangoes. You would
write a rules:
if(color is yellow and bigger in size): mango
is sweet.
else if(smaller and soft): write some
statement.
You would use these rules to choose the
mangoes. You could even send your friends with
this list of rules to buy the mangoes, and you
would be assured that he will pick only the
mangoes of your choice.
But every time you make a new observation

Machine learning Algorithm

Machine Learning algorithms are an evolution over


normal algorithms. They make your programs
"smarter", by allowing them to automatically learn
from the data you provide.
Take a randomly selected specimen of mangoes
from the market (training data).
Make a table of all the physical characteristics of
each mango, like color, size, shape, grown in which
part of the country, sold by which vendor, etc
(features).
Along with the sweetness, juicyness, ripeness of

You feed this data to the machine learning


algorithm (classification/regression) and it learns
a model of the correlation between an average
mango's physical characteristics, and its quality.

PROPOSED SYSTEM

Classification problems are met considerably more freque


ntly in medical applications, and hence we focus exclusive
ly on those cases.
Focusing on the suitable machine learning algorithm for d
isease symptoms classification and enhance the efficiency
of the classification.
Classification of symptoms and behavior of patients suffer
ing from the disease and using predictive analysis to forec
ast further complications in the existing health status.
And finally evaluation processes are proposed to measure
the performance of the model by calculating the accuracy,
precision and recall.

TOOLS

Python: Python is a widely used high-level, general


purpose, interpreted, dynamic programming langu
age. Its design philosophy emphasizes code readab
ility, and its syntax allows programmers to express
in fewer lines of code than would be possible in lan
guages such as C++ or Java.

Cassandra: Cassandra is a highly scalable, high-per


formance distributed database designed to handle l
arge amounts of data across many commodity serv
ers, providing high availability with no single point
of failure. It is a type of NoSQL database.

Elastic Search: Elastic search is a real-time


distributed and open source full-text search and
analytics engine. It is accessible from Restful
web service interface and uses schema less
JSON (JavaScript Object Notation) documents to
store data. It is built on Java programming
language, which enables Elastic search to run
on different platforms. It enables users to
explore very large amount of data at very high
speed.

Kibana:

Kibana is a data visualization plug-in


for Elastic search. It provides visualization
capabilities on top of the content indexed on an
Elastic search cluster. User can create bar line
and scatter plots, or pie charts and maps on top

Any Questions?

THANK YOU

Anda mungkin juga menyukai