Interested in Research Opportunities
New Delhi, Delhi 110035, India
Artificial Intelligence, Neural Networks, Computer Vision, Image Processing, Machine Learning, and Robotics.
- Netaji Subhas Institute of Technology (NSIT),
University of Delhi, New Delhi, India
B.E., Instrumentation and Control Engineering (elective: AI), Aug 2011 - June 2015.
- Grade 77.16%, First Class with Distinction (rank: 7/165).
- Awarded annual merit scholarship (top 10%) for four successive years for exhibiting academic excellence at college.
- Campus ambassador for AIESEC campus activities and events - increased students' membership by 300%.
- Relevant Coursework:
- Linear Algebra, Calculus, Differential Equations, Matrix Theory, Discrete Mathematics (Mathematics I-II) (IC 102, IC 113)
- Physics I-II (IC 103, IC 155)
- Statistics, Probability, Vector Calculus (Mathematics III) (IC 205)
- Artificial Intelligence (elective III) (IC 412)
- Digital Signal Processing (elective IV) (IC 413)
- Introduction to Programming (IC 114)
- Numerical Algorithms, Data Structures and Algorithms (Programming I-II) (IC 210, IC 222)
- Analysis and Design of Algorithms, Advanced Data Structures and Algorithms, Software Engineering (Programming III-V) (IC 309, IC 319, IC 410)
- Computer Networking (IC 315)
- Computer Graphics (IC 217)
- Digital Logic & System Design (IC 303, IC 402)
- Control Systems I & II (IC 314, IC 401)
- Microprocessors I (808x Architecture) & II (elective II) (IC 311, IC 405)
- Transducers (IC 215)
- Biomedical Instrumentation (elective I) (IC 404)
- Computer Aided Design (IC 312)
- Electronics I-II (IC 201, IC 211)
- System engineering and analysis with LABVIEW, Winter Training, NSIT (Prof. K.P.S. Rana), New Delhi, 2012.
- System engineering and analysis with MATLAB, Winter Training, NSIT (Prof. K.P.S. Rana), New Delhi, 2013.
- Related Online Courses:
- Machine Learning , Stanford University, Coursera
- Computational Photography, Georgia Institute of Technology, Coursera
- Introduction to Data Science, University of Washington, Coursera
- Statistics One, Princeton University, Coursera
- Algorithms: Design and Analysis 1, Stanford University, Coursera.
- AUTONAVx - Autonomous Navigation for Flying Robots, TUM, edX
- 6.00x - Intro to Computer Science and Programming using Python, MIT, edX
- CS50x - Introduction to Computer Science, Harvard University, edX
- CS1 - Compilers, Stanford University
- 6.033 - Operating Systems, MIT
- Class XII (2010), CBSE - 88% (rank: 3/250)
- Class X (2008), CBSE - 88.4% (rank: 3/200 with 99% in Mathematics)
Research and Work Experience
- Wipro Technologies Ltd., Bengaluru, India, July 2015 - Present
Software Engineer, Man-machine interface division, Chief Technology Office (CTO)
Key member of a small research & development lab working on a vision problem about real-time recognition, detection (including depth estimation) and tracking of 3D objects in live dynamic environment on a mobile platform. Responsibilities entailed the survey and analysis of different algorithms, their implementation and optimization; development of the functional specifications.
Completed STAR (special recruitment program for premier colleges in the country) batch training on “Algorithms and Data Structures with Core Java” with 100% grade at Wipro Technologies Office.
Also, leading the development of a webRTC based peer-to-peer ( p2p) assistance tool.
Visual Field Assist: Intelligent visual assistance for field technicians, used by 10+ international enterprise clients.
- Implemented bag-of-features classification algorithm with supervised learning for mobile platforms, replacing the cascaded classifier and boosting the accuracy to ~85% for the desired recognition use-case.
- Analyzed, implemented and benchmarked feature detectors (Harris, FAST), descriptors (ORB, AKAZE, BRISK) with detection/tracking algorithms (template matching, CMT, correlational, CAMshift, optical flow) for efficiency and accuracy on mobile platforms, resulting in ~25% performance boost while maintaining the accuracy.
- Investigated and optimized existing implementations with multithreading, improving performance by ~15%.
- Proposed Convolutional Neural Networks based approach for superior object recognition in the solution.
- Collected positive and negative samples to create an extensive training & testing dataset used in the solution.
- Working on paper “Real-time object recognition, detection & tracking in dynamic environment: A survey”.
Peer Field Assist: Peer-to-peer video & augmented assistance to field technicians by remote experts, used by 6000+ users.
- Developed the end-to-end cross-platform compatible application on web/desktop platform using the webRTC protocol including design of SIP protocol for SDP exchange, setting up STUN and TURN servers.
- Implemented real-time augmented assistance during video communication using context-sharing & tracking.
- Developed a desktop application for real-time video library management using Firebase and MEAN stack.
mLabs Research Inc., New Delhi, India, December 2013 - July 2014
Research Intern (winter ‘13 and summer ‘14)
Presented at the prestigious CNNA ’14 conference, University of Notre Dame, USA & published in IEEE Xplore.
- Implemented Cellular Neural Networks for image processing in Python on desktop/raspberry-pi and prototyped plug-n-play memristor characterization kit using raspberry-pi.
- Developed the internet of things architecture to enable the above discussed real-time image processing & virtual characterization via internet.
- Proposed a privacy-centered architecture for internet of things, the paper is presently in draft (to be submitted).
mLabs Research Inc., New Delhi, India, Aug 2012 - April 2015
Software Lead (Part-time)
Responsible for the design, development & outreach of the company’s flagship products, Funstore and Bit by Bit.Funstore: An application store for internet of things (IoT); used by 3000+ users.
- Designed and managed the web-architecture, & customized Linux OS distribution for connected devices.
- Developed multi-language deployment for IoT applications with graphical interface, and visual-blocks to C++ compiler.
- Implemented the dashboard architecture, machine learning & natural language processing plugins.
- Designed tutorials & implemented IoT applications such as personal bot, home automation & burglar alarm.
Bit by Bit: An educational platform to build actual internet enabled embedded systems with a virtual wire-less breadboard; used at 10+ schools.
- Developed virtual implementation of 3d-printed patented wire-less breadboard using raspberry-pi on web 2.0.
- Launched a crowdsourcing and outreach campaign on Indiegogo, boosting engagement by 400%.
A. Aggarwal and G. Gandhi, "B3: A plug-n-play Internet enabled platform for real time image processing," in 14th International Workshop on Cellular Nanoscale Networks and their Applications, USA, 2014. IEEE Xplore.[pdf]
A. Aggarwal and G. Gandhi, "Internet based electronic prototyping system for memristor characterization," in 14th International Workshop on Cellular Nanoscale Networks and their Applications, USA, 2014. IEEE Xplore.[pdf]
[In Draft] [To Be Submitted] A. Aggarwal and G. Gandhi, "Privacy-centered architecture for smart internet of things".[pdf]
Academic and Personal Projects
Social Network of Internet of Things (SNIoT), B.E. Thesis (Project Lead), Jan – May 2015
Advisor: Dr. Prerna Gaur, Professor, NSIT
- Proposed and presented the architecture to create an intelligent network of connected devices capable of acting together to make decisions with or without human interaction.
- Defended thesis in front of the panel comprising of faculty members of NSIT.
- Demonstrated the proof-of-concept on a cloud-based implementation. Best thesis with highest grade (90%).
FaceGrab, Artificial Intelligence (Author), Jan – April 2015
Advisor: Dr. Vijander Singh, Professor, NSIT
- Developed a python tool to collect public images from Facebook and create a face dataset to aid in learning about face detection, or gender recognition applications of machine learning.
- Implemented Eigenface and K-means algorithm in python for gender recognition using the dataset from above tool as part of an assignment in AI class and achieved ~80% accuracy. Received 80% grade in this class.
PyCNN, Research Intern (Author), May – Aug 2014
Advisor: Dr. Gaurav Gandhi, CEO, mLabs Research Inc.
- Developed cross-platform library for image processing with cellular neural networks; 500+ active users.
- Maintained and managed the project on GitHub with 250+ contributions from 20+ contributing developers.
- Cited in the research published on Using Python and Julia for Efficient Implementation of Natural Computing and Complexity Related Algorithms and B3: A plug-n-play Internet enabled platform for real time image processing.
- Trended on Hacker News front-page and GitHub.
PiScope, Student, NSIT (Author), July – Aug 2014
- Developed cross-platform library to turn a raspberry-pi into an oscilloscope/XY-plotter; 200+ active users.
- Used for characterization of different electronic elements and boards, and as a DAQ for various sensors and devices.
Instrumentation Oscilloscope, Student, NSIT (Project Lead), Aug 2013 – June 2014
Advisor: Aditya Kumar, Associate Professor, NSIT
- Designed and built a portable, low-cost oscilloscope for laboratory and educational usage.
- Implemented the system software including data-acquisition, processing and display logic in embedded C.
Sentiment Analysis of Twitter in Python, Intro to Data Science, Coursera, April – June 2014
- Estimated the sentiment of a particular term or phrase and analyzed the relationship between location and mood based on twitter sample data. Received 100% grade for this assignment.
EKF & PID controller, Autonomous Navigation for Flying Robots, edX, May – July 2014
- Implemented extended Kalman filter (EKF) and PID controller for autonomous navigation on a flying robot simulator in Python. Received 100% grade for this assignment.
Hand-written Digit Recognition, Machine Learning, Coursera, Nov 2013 – Jan 2014
- Implemented artificial neural network in MATLAB and achieved ~95% accuracy with the given hand-written digits dataset. Received 100% grade for this assignment.
Image Processing Filters, Computational Photography, Coursera, March – May 2013
- Implemented gaussian, sharpen, median, and sobel filters in python. Received 100% grade for this assignment.
Twitter Popularity, Introduction to Computer Science, edX, Feb – April 2013
- Developed a real-time web application using PHP to determine the more popular trend on twitter out of the two given trends. Received100% grade for this finals project.
Honors and Achievements
- Invited for onsite Google interview after securing All India rank 17 and Asia-pacific rank 122 in Google APAC ‘15.
- Top 100 out of 1800 national proposals in Texas Instruments Analog Design Contest 2014 and Top 50 out of 1000 national proposals in Freescale Design Contest 2014 for the submission of the project Instrumentation Oscilloscope.
- Ranked 15,016 in the All India Engineering Entrance Examination ( AIEEE 2011) taken by nearly 12,000,000
- Top 75 out of 3000+ participants in HackerEarth IndiaHacks hackathon 2016 in machine learning track.
- Top 50 out of 1000+ in TagMe! 2014 by IISc, Bengaluru, a machine learning contest to categorize an image dataset.
- Gold medalist in school (Intl. - 1004) for International Math Olympiad 2008 by Science Olympiad Foundation.
- Awarded the “Excellence Badge” for eight successive years at school for exhibiting consistent academic excellence.
- OpenCV - Open Source Computer Vision Library.
- Electron by GitHub - Build cross platform desktop apps with web technologies.
- Atom by GitHub - The hackable text editor.
- FreeCodeCamp - The open source codebase and curriculum. Learn to code and help nonprofits.
- learnxinyminutes-docs - Code documentation written as code!
- tota11ly by Khan Academy - An accessibility (a11y) visualization toolkit.
- Technical reviewer of the book “Getting Started with Python and Raspberry Pi” by Dan Nixon, Packt Publishing and the book “Mobile Web Performance Optimization” by S. S. Niranga, Packt Publishing.
- Platforms: Linux, Windows, Raspberry Pi, Intel Edison, Arduino, TI MSP430, FRDM KL25Z.
- Software: OpenCV, Torch, Theano, WebRTC, Electron, MySQL, MongoDB, jQuery, Bootstrap, AngularJS, WordPress, J2EE, Tomcat, Hibernate, Spring, Eclipse, Android Studio, Visual Studio, Eagle CAD, SketchUp, Photoshop, MS Office.
- Delivered Spoken English classes at an NGO to underprivileged learners under the social initiative “Teach India” by British Council and Times of India. 7 out of 20 learners in my batch completed the 3-month training program in 2010-11 resulting in their successful employment with the help of improved English language skills.
- Coordinated a social initiative to create employment for rag-pickers under Project Pratham, ENACTUS at NSIT in 2012-13.
- Participated in an exclusive Social Innovation Hackathon by Code for India at Rastrapathi Bhavan, New Delhi as part of Festival of Innovations 2016 in the presence of the President of India “Shri Pranab Mukherjee”. The solutions developed during the hackathon are now being used by the Government of Delhi to tackle social challenges.
- Participated regularly in competitive programming contests on Google Code Jam (2014, Round 1, Rank - 2196 (Top 4%)), TopCoder Open (2015, Qualification Round, Rank - 693 (Top 5%)), Facebook Hacker Cup (2015, Qualification round, Rank - 528 (Top 5%)), Codeforces, and Codechef.
- Audited offices and campus across New Delhi encouraging sustainability and low-carbon footprint practices (~5% money saved with ~10% less energy) under The Eco-Audit program by Indian Youth Climate Network (IYCN) in 2012.
- Volunteered with Delhi Photo Festival 2011 as an amateur videographer covering events of 13-day long festival.