top of page

DEEP LEARNING METHODS FOR LTE TRAFFIC DATA CLASSIFICATION

Screen Shot 2019-08-13 at 6.36.21 PM.png
ABOUT US

MEET THE TEAM

Click on our pictures to connect with us on LinkedIn

​

Screen Shot 2019-08-13 at 7.19.16 PM.png

KARTIK RATTAN

Masters Student

Electrical and Computer Engineering

Rutgers University, New Brunswick

​

IMG_2571 2.jpg

KUHU HALDER

Incoming Freshman

Computer Science

School of Arts and Sciences

Rutgers University, New Brunswick

​

​

​

OVERVIEW

In this research project, we intend to collect real-time network traffic data and run machine learning algorithms to see whether non-overlapping clusters exist. If distinct clusters do exist, we continue to find the optimal number of clusters and assign labels to the data points that will be used for classification. We use three methods of classification: KNN Classifier, Artificial Neural Networks, and Decision Tree. Labeling and classifying our dataset is essential for scheduling purposes.   

Screen Shot 2019-08-14 at 1.51.56 AM.png
OBJECTIVE

WEEKLY PRESENTATIONS

WEEK 1 

View

WEEK 2

View

WEEK 3

View

WEEK 4

WEEK 5

WEEK 6

WEEK 7

WEEK 8

WEEK 9

WEEK 10

WEEK 11

WEEK 12

View
WEEKLY PRESENTATIONS
CONTACT
bottom of page