Scribd
Upload
36 views

Mini Project

it tells about machine learning classifiers.

Uploaded by

18P557 Nandan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
36 views

Mini Project

it tells about machine learning classifiers.

Uploaded by

18P557 Nandan
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

Contents

1.Domain
2.Abstract
3.Introduction
4.Literature Survey
5.Existing System
6.Disadvantages of Existing system
7.Proposed System
8.Advantages of Proposed System
9.Applications
10.System Architecture
11.Configurations
12.Reference
13.Conclusion
Domain
Machine Learning:
The use and development of computer systems that are able to learn and adapt
without following explicit instructions, by using algorithms and statistical models to
analyze and draw inferences from patterns in data.

Machine Learning Classifiers:


A classifier in machine learning is an algorithm that automatically orders or
categorizes data into one or more of a set of “classes.”
Example: One of the most common examples is an email classifier that scans
emails 

Ensembling:
Ensemble modelling is a process where multiple diverse models are ensembled to
predict an outcome.
Abstract
The predictions and analysis made by the research community for
medical dataset support the people by taking proper care and
precautions by preventing diseases. Through a set of medical datasets,
different methods are used extensively in developing the decision
support systems for disease prediction.
We also discuss various applications of machine learning in the field
of medicine focusing on the prediction of diabetes through machine
learning.
Diabetes is one of the most increasing diseases in the world and it
requires continuous monitoring. To check this we explore various
machine learning algorithms which will help in early prediction of this
disease.
Introduction
 Diabetes is a disease which reduces the body’s capability to produce
insulin. In other words the body can not retaliate to the hormone
insulin production. This results in anomalous metabolism of
carbohydrates and increased blood glucose levels. Early detection of
diabetes becomes very important because of the reasons mentioned
above.
 Many people in the world are getting effected by diabetes and this
number is increasing day by day. This disease can damage many
vital organs hence the early detection will help the medical
organisation in treatment of it.
 Machine Learning is one such technique employed to predict
diabetes.various machine learning techniques such as
prediction,classification,regression are utilized to forecast diabetes.
Literature Survey
 The proposed model gives the best results for diabetic prediction
and the result showed that the prediction system is capable of
predicting the diabetes disease effectively, efficiently and most
importantly, instantly.
 Nonso Nnamoko et al. [13] presented predicting diabetes onset: an
ensemble supervised learning approach they used five widely used
classifiers are employed for the ensembles and a meta-classifier is
used to aggregate their outputs. The results are presented and
compared with similar studies that used the same dataset within the
literature.
 It is shown that by using the proposed method, diabetes onset
prediction can be done with higher accuracy.
Existing System
 In this system we are using only single algorithm for the prediction
and we are not getting the accuracy.
 We use the different algorithms like :
 Linear Discriminant Analysis
 Quadratic Discriminant Analysis
 Naive Bayes
 Random Forest
 These algorithms perfomed with different dimensionality reduction
and cross-validation techniques. They also performed extensive
operations on the outlier rejection but they didn’t provide the
accuracy.
Disadvantages of Existing System
A ML based framework was proposed in where authors
implemented the Linear Discriminant Analysis (LDA) , Quadratic
Discriminant Analysis (QDA), Naive Bayes (NB) , Gaussian
Process Classification (GPC), Support Vector Machine (SVM) ,
Artificial Neural Network (ANN), AdaBoost (AB), Logistic
Regression (LR), Decision Tree (DT), and Random Forest
(RF).Individually we are not getting accuracy,so we are using
ensembling concept.
Proposed System
 To predict diabetes with better accuracy. We experimented with
different classification and ensemble algorithms to predict diabetes.
In the following, we briefly discuss the phase.
- Dataset Description
- Data Preprocessing
 The Techniques are follows-
-Decision Tree
-Navie Bayes
-Logistic Regression
-Support Vector Machine
Advantages of Proposed System
 In this system we are enssembling different algorithms and we
finding the decision.
 Preprocessing, in the proposed pipeline, is the heart of
achieving the state-of-the-art result, which consists of outlier
rejection, filling missing values, data standardization, feature
selection, and K-fold cross-validation.
 We consider the mean value in the missing position of
attribute rather than median value, as it has a more central
tendency toward the mean of that attribute distribution
Applications
 Glucose Monitoring Systems: Machine learning
algorithms help automate the process of monitoring
blood sugar levels and recommend adjustments in care.
 Nutrition Coaching: To help recommend meal options

based on the specific diet criteria of the user.


System Architecture
Configurations
 A. Hardware requirements The following hardware was used for the
implementation of the system:
• 4 GB RAM
• 10GB HDD
• Intel 1.66 GHz Processor Pentium 4
 B. Software requirements The following software was used for the

implementationof the system:


• Windows 7
• Python 3.6.0
• Visual Studio Code
Reference
 A. Misra, H. Gopalan, R. Jayawardena, A. P. Hills, M. Soares, A. A.
Reza-Albarrán, and K. L. Ramaiya, ‘‘Diabetes in developing
countries,’’ J. Diabetes, vol. 11, no. 7, pp. 522–539, Mar. 2019.
 The Emerging Risk Factors Collaboration, ‘‘Diabetes mellitus,
fasting blood glucose concentration, and risk of vascular disease: A
collaborative meta-analysis of 102 prospective studies,’’ Lancet, vol.
375, pp. 2215–2222, Jun. 2010.
 S. Perveen, M. Shahbaz, A. Guergachi, and K. Keshavjee,
‘‘Performance analysis of data mining classification techniques to
predict diabetes,’’ Procedia Compute. Sci., vol. 82, pp. 115–121,
2016.
Conclusion
 Diabetes prediction has been accomplished using the
proposed ensemble model from the PID dataset, where the
preprocessing plays a crucial role in robust and precise
prediction. The quality of the dataset was improved by the
proposed preprocessing scheme, where outlier rejection and
filling missing values was a core concern.
Thank you ....

You might also like