priyankkalgaonkar Goto Github PK

followers: 3.0 following: 3.0 repos: 31.0 gists: 9.0

Name: Priyank Kalgaonkar

Type: User

Company: Purdue University, Indianapolis

Bio: I am a passionate and creative systems engineer in the US and a CE student. I am currently studying and researching on DL technologies. 🤖

Twitter: pkalgaonkar

Location: Indianapolis, IN

Blog: www.priyankkalgaonkar.com

Hey, I'm Priyank 👋

I am a doctoral student and a research fellow at the Purdue School of Engineering (Purdue University, Indianapolis), and graduated from the University of Toledo in Ohio with a B.S. in Computer Science and Engineering, and a M.S. in Electrical and Computer Engineering from Purdue University, Indianapolis. I have also previously served as a Clinical Systems Engineer at The Christ Hospital for Renovo Solutions in Cincinnati and as a Telemetry Developer Intern at Philips North America in Cleveland. I was most recently nominated for the prestigious IUPUI Elite 50 award and have published two award winning research papers and three research journals. My activities are much beyond my stream of education and research. ⚡ Outside of academia, I enjoy most of my time being outdoors. During the warmer months here in Indiana, I enjoy mountain biking, hiking, free climbing, kayaking and traveling with friends and family. When forced indoors, I like to watch sci-fi and sitcom genre movies and TV shows.

😄 Pronouns

He/him/his

🌱 What do I do and What have I done?

Mentor and student ambassador for the ECE department at Purdue University, Indianapolis.
Developed an award-winning deep neural network algorithm for computer vision called CondenseNeXt.
Recipient of an IEEE Best Paper and two IEEE Best Presentation awards for my published peer-reviewed work in international conferences.
Working independently on R&D of a state-of-the-art autonomous rover for military and federal law enforcement agencies globally.
Worked on a research project along with a Ph.D. student to develop a semi-autonomous robot for a major U.S. Defense contractor in Indiana.
Published three scientific first-author scholarly research journals in PGScience-AJECE, MDPI-JLPEA and MDPI-Future Internet.
Served key leadership roles at the University of Toledo, most notably as a team leader for the Self-Checkout Shopping Cart capstone project.
Recipient of IUPUI Service Award awarded by Indiana University-Purdue University Indianapolis.

⚡ One line that describes me best?

An ambitious guy who loves to travel, make new friends, day dream at nights and sometimes code too. 😉😉

📫 How to reach me?

You can ask me anything! I am looking forward to absorb knowledge 🧠, gain experience 🏭, collaborate 🤝 and build amazing products 🏭 for the world 🌍!

Visitors count

Priyank Kalgaonkar's Projects

advanced-emergency-vehicle-detection

Also known as: Emergency Vehicle Detection Using Sound Localization and Digital Processing Techniques. Code was developed in Keil µVision IDE, locally.

comingsoonwebpage.github.io

A coming soon theme with a video background for Bootstrap 4

condensenext

An Ultra-Efficient Deep Neural Network for Embedded Systems

ecissystemproject

ECIS System project (simplified) code migrated to Keil Studio Cloud IDE for ECE568 Design with Embedded Systems course at Purdue.

electronically-connected-intelligent-shelves

Inventory automation prototype using NXP FRDM-K64F MCU, ultrasonic sensors, cloud server and predictive analytics using machine learning techniques.

image-classification-with-condensenext-for-arm-based-computing-platforms

In this paper, we demonstrate the implementation of our ultra-efficient deep convolutional neural network architecture: CondenseNeXt on NXP BlueBox, an autonomous driving development platform developed for self-driving vehicles. We show that CondenseNeXt is remarkably efficient in terms of FLOPs, designed for ARM-based embedded computing platforms with limited computational resources and can perform image classification without the need of a CUDA enabled GPU. CondenseNeXt utilizes the state-of-the-art depthwise separable convolution and model compression techniques to achieve a remarkable computational efficiency. Extensive analyses are conducted on CIFAR-10, CIFAR-100 and ImageNet datasets to verify the performance of CondenseNeXt Convolutional Neural Network (CNN) architecture. It achieves state-of-the-art image classification performance on three benchmark datasets including CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error) and ImageNet (7.91% single model, single crop top-5 error). CondenseNeXt achieves final trained model size improvement of 2.9+ MB and up to 59.98% reduction in forward FLOPs compared to CondenseNet and can perform image classification on ARM-Based computing platforms without needing a CUDA enabled GPU support, with outstanding efficiency.