Hello, I'm Datta D

Loves Coding, breathes science.

Education

New York University

Masters in Computer Sciences
August 2016 - May 2018

CPGA: 3.97 (Academic Achievement Award)
Courses: Machine Learning, Neural Networks, Big Data, Computer Vision

Jawaharlal Nehru Technological University

Bachelors in Electronics & Communication Engineering
September 2012 - May 2016

CPGA: 3.9
Courses: Analog & Digital Communications, Digital Signal Processing, Radars & Cellular Communications, VLSI

I worked at some great places!

Work Experience

I love developing products which have great impact on people.

Amazon Web Services
Rekognition & Video

SDE

May 2018 - Present
Develop and scale Amazon Rekognition Video products.

NYU: Center for Data Science

Teaching Assistant

September 2017 - May 2018
Develop and teach lab sessions for Advanced Python for Data Science course.

Amazon Web Services
Market Place

SDE Intern

June 2017 - September 2017
Implement various APIs to support a version controlled document store from a dashboard.

Bharat Heavy Electricals Ltd.

Summer Intern

May 2015 - June 2015
Performed an academic study on the CNC machines used in this company.

Electronics Corporation of India Ltd.

Summer intern

March 2014 - April 2014
Designed and constructed a PIC-Based IR Remote Control Moving Robot which has a huge scope for carrying out human rescue missions.

I love publishing papers too!

Publications

Published papers in Electronics & Computer Science Domains

Efficiency of LiDAR Speed Gun

Reasearched various techniques which can be helpful in achieving the correct velocity of the target and help security and police forces to maintain law and order, enforce vehicular speed limit and help citizens travel safe.

VIBGYOR BOX: Hybrid Password

Designed an innovative authentication method, which is easy to remember by user and tough to crack by the intruders who use various methods.

Analysis and Construction of a Robot controlled by a Universal Remote Control

Designed a robot that is a tank like vehicle which can be controlled by a universal infrared remote. Used for rescue missions.

I have done lot of projects too!

Projects

Tell me and I forget. Teach me and I remember. Involve me and I learn
-Benjamin Franklin.

Detection of Wrong Direction Driving Vehicles

Python & OpenCV

Determine efficient positions of emergency response teams in NYC

Big Data

Twitter Bot Detection

Machine Learning

Optical Character Recognization

Machine Learning

Generation of Biphase coded sequences using particle swarm optimization algorithm

Eveloutionary algorithm analysis

Traffic Analysis and Control

Digital Image Processing (MATLAB)

Go shopper

Software Engineering

Alexa Skill: Breast Cancer Facts

Application

Intelligent Traffic Light Systems

IOT (Raspberry Pi & Python)

Want to know more in detail about me!

Timeline

Listing important awards received, projects & courses completed.

1994

Landed on earth

2011 & 2012

Chemistry Years

2011 & 2012: Distinction in Australian National Chemistry Quiz.
September 2012: Started Bachelors in Electronics & Communications Engineering in JNTU.

September 2013

Presented Paper for the first time

Published efficiency of lidar speed gun paper(later in early 2014).
Secured second position in first year of college

2014

Online courses
and first internship at ECIL

March 2014: Started Summer Internship at ECIL
May 2014: Distinction in General Game Playing, Stanford University (Coursera)
May 2014: The Datascientist Toolbox, John Hopkins University (Coursera)
June 2014: Distinction in Programming for Everybody Course, University of Michigan (Coursera)
July 2014: Started as student trainee in Bharath Sanchar Nigam Limited
Secured first in the second year of college

2015

IOT Projects

April 2015: Intelligent Traffic Light System (IOT)
May 2015: Summer Intern at Bharath Heavy Electricals Ltd.
July 2015: Optical Character Recognization Project
November 2015: Traffic Control using DIP
December 2015: Generation of Biphase Coded Sequences for Radars
Secured second in the third year of college

2016

Silver Medal &
New beginning of CS at NYU

May 2016: Received Silver Medal for my academic performance in Bachelors.
August 2016: Started Masters in CS in NYU.
September 2016: Started Go shopper project

2017

Machine Learning projects
Internship at Amazon

.
January 2017: Twitter Bot Detection
February 2017: Alexa Skill published
September 2017: Efficient Position of ERS in NYC
November 2017: Received Academic Acheivement Award

2018

Graduated!
Back with Amazon

April 2018: Detection of Wrong Direction Driving Vehicle Detection.

May 2018: Completed Masters in CS in NYU.

May 2018: Back with Amazon (AWS Rekognition Team)

November 2018: Launched Textract

Awesome
Life
Ahead!

Look into my resume!

Resume

Resume

Connect with me

GitHub

LinkedIn

Facebook

Instagram

Quora

YouTube Channel

Copyright © Datta D Website 2018

Determine efficient positions of emergency response teams in NYC

Big Data

The primary objective of the project is to derive statistical techniques for analyzing data typically collected in fire departments. As improved resource allocation and statistical analysis of emergency medical calls can determine the impact of providing another paramedic unit in the field. The other goal of the project is to visualize incidents in an area and find the most efficient position for future fire stations.

GitHub Link: Efficient Position of ERS Teams

Project Duration: September 2017 to December 2017

Twitter Bot Detection

Machine Learning

In this project we used our own algorithm to determine a Twitter account as a legitimate user account or a bot. There is tremendous work been done in this domain. Bots can be used to generate live scores, weather and news. They can also be used to distribute malicious tweets which have huge consequence on society.

We used different algorithms to train out data:

Bernoullis' Naive Bayes on Tweets of accounts

Multinominal Naive Bayes on Tweets of accounts

Logistic Regression on major attributes of an account

OUR NEW ALGORITHM

GitHub Link: Twitter Bot Detection

Project Duration: January 2017 to May 2017

Intelligent Traffic Light Systems

IOT (Raspberry Pi & Python)

The traffic congestion can be caused by large Red light delays, etc. The delay of respective light is hard coded in the traffic light and it is not dependent on traffic. Therefore for simulating and optimizing traffic control to better accommodate this increasing demand arises. In this project we shall study about the optimization of traffic light controller in a city using a microcontroller and proximity sensors. By employing this technology we can reduce the possibilities of traffic jams, caused by traffic lights, to an extent.

Advanced Modes:
The Intelligent Traffic Light control system made in this project will be employed to work in three modes. The first mode shall use the real time information, the second mode will be using the machine learning techniques to give the present output in cases the first mode cannot be run by the system and the third mode shall be used in case of emergency.

GitHub Link: Traffic Control using IOT

Project Duration: April 2015 to June 2015

Optical Character Recognition

Machine Learning

The goal of Optical Character Recognition (OCR) is to classify optical patterns (often contained in a digital image) corresponding to alphanumeric or other characters. Character recognition techniques associate a symbolic identity with the image of character. In a typical OCR system, input characters are digitized by an optical scanner. Each character is then located and segmented, and the resulting character image is fed into a pre-processor for noise reduction and normalization. Certain characters are then extracted from the character for classification. The feature extraction is critical and many different techniques exist, each having its own strengths and weaknesses. After classification the identified characters are grouped to reconstruct the original symbol strings, and context may then be applied to detect and correct errors. Both hand written and computer printed characters may be recognized, but the performance is directly dependent upon the quality of the input documents as well as on the type and quality of the templates created.

GitHub Link: OCR

Project Duration: July 2015 to November 2015

Generation of Biphase coded sequences using particle swarm optimization algorithm

Eveloutionary Algorithm Analysis

The aim of this project is to generate best autocorrelation sequences for signal lengths from 60 to 69 using PSO (Particle Swarm Optimization) Algorithm.

Binary phase codes with good autocorrelation and low side lobe levels are useful in such diverse applications as radar pulse compression, communication systems, and theoretical physics. Knowledge of minimum achievable side lobe levels for given code lengths can help inform searches for low side lobe level codes. Sets of codes that achieve the minima can provide new dimensions to trade studies supporting code selection tasks. This project adds to advance the upper bound on code lengths for which the optimal PSL is known. This project tries to make a detailed analysis for signal lengths 60 to 69.

Github Link: Biphases Sequences Code

Project Duration: December 2015 to May 2016

Traffic Analysis & Control

Digital Image Processing (MATLAB)

I proposed a system for controlling the traffic light by image processing. The vehicles are detected by the system through images instead of using electronic sensors embedded in the pavement. A camera will be placed alongside the traffic light. It will capture image sequences. Image processing is a better technique to control the state change of the traffic light. It shows that it can decrease the traffic congestion and avoids the time being wasted by a green light on an empty road. It is also more reliable in estimating vehicle presence because it uses actual traffic images. It visualizes the practicality, so it functions much better than those systems that rely on the detection of the vehicles’ metal content.

Finally, I implemented the digital image processing technique using MATLAB

GitHub Link: Traffic Control using DIP

Project Duration: November 2015 to January 2016

Go Shopper

Software Engineering

The purpose of this project is to save money and time for people who take lot of pain to buy groceries from different stores or end up paying an exorbitant amount by buying overpriced goods. Often, the consumers are not able to find all the groceries at the same place. Thus there is a need for an application that could inform customer (user) where the items in his list are available (Location of store) and also list its price. That way people could select which store they should be visiting for economical purchases. There are quite a few services and apps like Gasbuddy, Google Express, and other grocery store specific websites, which allow people to go through their list of items and buy them. Google express is even in the business of delivering these items as well. However, this application will be streamlined to use those services as well as develop an algorithm in this application for economical purchases.

GitHub Link: Software Deliverables

Project Duration: September 2016 to December 2016

Breast Cancer Facts
(Amazon Alexa Skill)

Application

The main intention of creating this skill is to create awareness of breast cancer. By going through this skill, we can realize how deeply cancer has penetrated into our society. By knowing about the facts and statistics of breast cancer, one can get enough awareness of this social evil. Lead a happy and joyful life.

Amazon App Store: You can try this skill here!

Project Duration: February 2017 to March 2017

Detection of Wrong Direction Driving Vehicles

Python & OpenCV

Need of a system which can detect the vehicles driving in the wrong direction is very important for developing countries like India where one-third of the accidents occur due to the wrong direction driving vehicles. Not only people driving in the wrong direction suffer during the accidents but also people driving in the right direction suffer too as the people driving in the wrong direction crash into them. So, I wanted to design a system which can alert the vehicles whenever it detects any vehicles moving in the wrong direction. This can be a very good system as it alerts the people moving in right direction and enforces them to be extra careful.

GitHub Link: Wrong Direction Driving Vehicle Detection

Project Duration: January 2018 to April 2018

Education

Work Experience

I love developing products which have great impact on people.

Publications

Published papers in Electronics & Computer Science Domains

Efficiency of LiDAR Speed Gun

VIBGYOR BOX: Hybrid Password

Analysis and Construction of a Robot controlled by a Universal Remote Control

Projects

Tell me and I forget. Teach me and I remember. Involve me and I learn -Benjamin Franklin.

Detection of Wrong Direction Driving Vehicles

Determine efficient positions of emergency response teams in NYC

Twitter Bot Detection

Optical Character Recognization

Generation of Biphase coded sequences using particle swarm optimization algorithm

Traffic Analysis and Control

Go shopper

Alexa Skill: Breast Cancer Facts

Intelligent Traffic Light Systems

Timeline

Listing important awards received, projects & courses completed.

1994

Landed on earth

2011 & 2012

Chemistry Years

September 2013

Presented Paper for the first time

2014

Online courses and first internship at ECIL

2015

IOT Projects

2016

Silver Medal & New beginning of CS at NYU

2017

Machine Learning projects Internship at Amazon

2018

Graduated! Back with Amazon

Awesome Life Ahead!

Resume

Tell me and I forget. Teach me and I remember. Involve me and I learn
-Benjamin Franklin.

Online courses
and first internship at ECIL

Silver Medal &
New beginning of CS at NYU

Machine Learning projects
Internship at Amazon

Graduated!
Back with Amazon

Awesome
Life
Ahead!