Scribd
Upload
50 views1 page

Programming Assignment-1

The document describes an assignment to cluster a dataset using K-means and DBSCAN clustering techniques in MATLAB. Students must visualize the dataset, implement and run K-means with k=2, implement and run DBSCAN by choosing parameters, and report the true positive rate of each cluster for both techniques to show DBSCAN performs better.

Uploaded by

a.vidhya 12345
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
50 views1 page

Programming Assignment-1

The document describes an assignment to cluster a dataset using K-means and DBSCAN clustering techniques in MATLAB. Students must visualize the dataset, implement and run K-means with k=2, implement and run DBSCAN by choosing parameters, and report the true positive rate of each cluster for both techniques to show DBSCAN performs better.

Uploaded by

a.vidhya 12345
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

------------------------------------------------------------------------------------------------

BT3041 : Analysis and interpretation of Biological data Given on: 15 Feb 17


Programming Assignment #1 Due on : 30 Feb 17, 10pm
-------------------------------------------------------------------------------------------------
The goal of this assignment is to experiment with K-means and DBSCAN
clustering techniques.
This is an individual assignment and you need to use MATLAB.
You need to send code along with precise report of your observations and results.
Submit a single tarball /zip file containing code and report files. Use the following
naming convention: 'BT3041pa1rollno.tar.gz'.

------------------------------------------------------------------------------------------------

(i). Visualize the given dataset' PA1.txt'. First two columns represent the position
of data point in two dimensional space and the third column represents the cluster
label to which the specific data point belongs to (1- denotes cluter1, 2- denotes
cluster2 and 0- denotes noise point).

(ii). Implement and run K- means clustering algorithm on given dataset with k=2.

(iii). Implement and run DBSCAN algorithm by choosing appropriate values for
min points and epsilon.

Report the true positive rate of each cluster (using the formula given in the class)
for each clustering technique. Show that DBSCAN perform better than K-means
on given dataset.

(% of data points assigned to cluter1 through algorithm)


True positive rate = ----------------------------------------------------------------------------
(Actual data points belongs to cluster1 in given dataset)

--------- o ---------

You might also like