Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

Q1 Data mining techniques can be used for prediction of early childhood obesity.

ID: 3595884 • Letter: Q

Question

Q1

Data mining techniques can be used for prediction of early childhood obesity. How?

Which algorithms can be deployed for this purpose? Discuss

Q2

Description:

Discuss Topic:

Explain the use Query graph of query optimization.

Tasks:

1) Write 100 - 150 word response to the above discussion topic.

2) Write a response to one peer in which you respectfully and professionally offer your opinion of his

*note please solve all the question at one time and answer all of the by computer not handwriting because handwriting sometimes hard to read

Explanation / Answer

Q1)

Now a days data mining techniques and capacity have grown very rapidly and became very much usefull in almost all industries where data is residing. And now coming to our problem Yes, data mining techniques can be used for early prediction fo problems in childrens.

Generally obesity will identified by calculating the BMI of the child. If the BMI reading crosses the threshold value then the child will be having obesity otherwise the child doesn't have obesity. In database these details are stored in seperate groups like obesity and non-obesity . And in obesity group all the behaviours and information will be stored .
So that when the child BMI is calculated based on the previously stored and calculated data and values as well as with behaviour it can be possible to predicate the obesity much earlier.

To predicate such behaviour and values first we use some data mining preprosseing methods on the stored data. Preprocessing methods like normalisation,discretizing,feature selection etc like that. After that preprocessing steps we use some data mining techniques such as classification algorithms which includes decision trees and baysian classifiers, clustering and association rule mining. Also we conduct some experiments with SVM Naive baysian classification algorithms to get the more comprehensive analysis.