Clicky

Priyank Kalgaonkar's Portfolio

Priyank Kalgaonkar

I am a professor in the ECE department at the Acopian Engineering Center at Lafayette College, and graduated from the University of Toledo in Ohio with a B.S. in Computer Science and Engineering, and a M.S. and a Ph.D. in Electrical and Computer Engineering from Purdue University in Indiana. I have also previously served as a Clinical Systems Engineer at The Christ Hospital for Renovo Solutions in Cincinnati, Ohio, and as a Telemetry Developer Intern at Philips North America in Cleveland, Ohio. I was a nominee for the prestigious Elite 50 award and have published two award winning research papers, two thesis and five 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 Pennsylvania, I enjoy mountain biking, hiking, free climbing, kayaking and traveling with friends and family. When forced indoors, I like to watch sci-fi, thriller and sitcom genre movies and TV shows.


Work Experience

Professor

Lafayette College, Easton, PA.

A professor in the department of Electrical and Computer Engineering at the Acopian Engineering Center at Lafayette College.

July 2024 - Present

Adjunct Professor

Purdue Univerisity, Indianapolis, IN.

An instructor (PhD student acting as an adjunct professor) in the department of Electrical and Computer Engineering at the Purdue School of Engineering for C and Python Programming courses.

January 2023 - May 2024

Doctoral Research Fellow

Purdue Univerisity, Indianapolis, IN.

Working independently on R&D of an autonomous robot for IoT Collaboratory at Purdue University Indianapolis, and for military and federal law enforcement agencies (IoT Lab, Advisor: Dr. M. El-Sharkawy).

May 2021 - May 2024

Teaching Assistant

Purdue Univerisity, Indianapolis, IN.

• A teaching assistant and a mentor in the department of Electrical and Computer Engineering at the Purdue School of Engineering for Dr. El-Sharkawy, Dr. Rizkalla, Professor Shayesteh and Professor Chong Chie.
• Working with undergraduate and graduate students in the engineering discipline on their senior design projects, lab and course work.
• TA'ed:
   ◦ ECE 568 - Design with Embedded Systems.
   ◦ ECE 533 - Wireless and Multimedia Computing.
   ◦ ECE 487 - Senior Design I.
   ◦ ECE 261 - Advanced C Programming Lab.
   ◦ ECE 204 - Introduction to Electrical and Electronics Circuits.

August 2019 - December 2023

Graduate Research Assistant

Purdue Univerisity, Indianapolis, IN.

Worked on a research project in the field of robotics, embedded systems and software development along with a Ph.D. student to develop a Semi-Autonomous Robot for a major U.S. Defense contractor in Indiana (IoT Lab, Advisor: Dr. M. El-Sharkawy).

May 2020 - April 2021

Clinical Systems Engineer

The Christ Hospital Health Network for Renovo Solutions, Cincinnati, OH.

• Designed and developed medical technologies including, but not limited to centralized patient monitoring, wireless medical telemetry, and EHR-integrated biomedical devices.
• Worked as part of the TCHHN CE project management team to improve patient care quality/safety, customer efficiency/work-flow usability of medical device technology and customizations that improve these core objectives as well as the adoption of TCHHN applications.
• Assisted in evaluation, recommendation, selection, procurement, integration, installation, and certification of medical devices for TCHHN expansion/renovation projects as well as regulatory inspections.
• Kick-started, trained on-site biomed and technical staff, and helped lead Renovo's Integrated Systems Management (ISM) project through all stages of its lifecycle at over 20 different hospital sites in the US.

September 2016 - May 2019

Telemetry Developer Intern

Philps North America, Cleveland, OH.

• Developed a software prototype to help field-service engineers record different calibration values.
• Developed a database for medical device’s system log files and periodically reviewed the files for instances.
• Assisted local and international software development team by identifying issues and providing a solution.
• Led technical reviews of assigned work packages and helped revise other team members’ technical reviews.

January 2013 - December 2013

Education

Purdue University

Doctor of Philosophy - Ph.D., Electrical and Computer Engineering

• Specialization: Computer Engineering - AI and Robotics.
• Research Thesis: Deep Neural Networks (Advisor: Prof. Dr. M. El-Sharkawy).
• Notable Achievements:
   ◦ Published four scientific first-author scholarly journals in PGScience-AJECE and MDPI Special Edition peer-reviewed journals.
   ◦ Student Ambassador for ECE and OIA departments at IUPUI.


August 2021 - August 2024

Purdue University

Master of Science - M.S., Electrical and Computer Engineering (Thesis)

• Specialization: Computer Engineering - AI and Robotics.
• Research Thesis: AI on the Edge with CondenseNeXt: An Efficient Deep Neural Network for Devices with Constrained Computational Resources (Advisor: Prof. Dr. M. El-Sharkawy).
• Notable Achievements:
   ◦ Published two multi award winning research papers in IEEE conferences.
   ◦ Participated and presented in international conferences: IEMTRONICS in Toronto, Ontario and CCWC 2021 in Las Vegas, NV.
   ◦ Attended Intel Industrial IoT Workshop in Indianapolis.


August 2019 - August 2021

The University of Toledo

Bachelor of Science - B.S., Computer Science and Engineering
• Specialization: Software Development and Database Systems.
• Team leader for the Self-Checkout Shopping Cart capstone project.

August 2011 - May 2016

Skills

  • Programming Languages: C, C++, Embedded C, Python.
  • Embedded Platforms & IDEs: Arm Mbed, Arduino, Pixhawk, Atom, Komodo, Keil μVision & Microsoft Visual Studio.
  • Single-Board Microcontroller: Arduino UNO, Nvidia Jetson SBC, NXP K64F, BlueBox 2.0 & Hexiwear.
  • IoT: AT&T M2X, Google Cloud, Hexiware IoT & Thingspeak IoT Platform.
  • Protocols: I2C, UART, CAN, CAN-FD, BLE, 6LoWPAN, TCP/IP & Thread.
  • Tools/Applications: GitHub, RTMaps, MATLAB & Simulink.
  • Operating Systems: Windows, Ubuntu & Macintosh.
  • PCB Design: Cadence Allegro, OrCAD & EagleCAD.

Academic Projects

Analyzing PCAP files for DDoS Attacks

Purdue Univerisity
Developed an algorithm to parse entropy of flows pertaining to source and destination IP address which is then utilized to detect the actual timing of the DDoS events and to correlate them with the times reported. CAIDA DDoS dataset and Indiana University's Carbonate supercomputer were utilized to test the robustness of our alogirthm. Souce code repo has been published on my GitHub.

  • This project was ranked #1 in class by peer reviews and ratings.

January 2022 - May 2022

Smart Greenhouse Project

Purdue Univerisity
Developed a smart greenhouse system using ESP32 System on Chip (SoC) and FreeRTOS. Temperature and humidity are sensed (measured) using two DHT22 sensors via RMT controller on-board the ESP32 SoC, processed via a software implemented low-pass filter and this data is then periodically reported to the Mosquitto MQTT server Over-The-Air (OTA) via a Wi-Fi network. A central management server is created to remotely adjust the sensing period of the DHT22 sensors. Souce code repo has been published on my GitHub.

  • This project was ranked #1 in class by peer reviews and ratings.

September 2021 - December 2021

Vehicle Detection using Cascade Classifier based on HOG Features

Purdue Univerisity
The objective of our Vehicle Detection using Cascade Classifier (VDCC) based on Histogram of Oriented Gradients (HOG) features project is to detect object of interest (vehicles) in video frames. It combines best practices from real-time image processing and pattern recognition techniques of images captured from an image sensor (camera). Our strategy is to combine a well-established HOG detector with Cascade classifier to train our model using the provided testData and eliminate instances of false detections that do not match our learned motor vehicle detection model.

  • This project was ranked #1 in class by peer reviews and ratings.

March 2020 - April 2020

Adaptive Cruise Control Using LIDAR

Purdue Univerisity
The design of Adaptive Cruise Control system uses two microcontroller units, a Garmin LIDAR module which is compact and high-performance optical distance measurement sensor, and Brushless DC (BLDC) electric motor. The main objective of Adaptive Cruise Control Using LIDAR project is to enable the cruise control system used in road vehicles to automatically slow down or speed up the vehicle up to a speed limit set by the driver. The result is improved driver's comfort, and safety of the vehicle and other traffic on the road by minimizing rear-end collisions.

  • This project was ranked #1 in class by peer reviews and ratings.

February 2020 - March 2020

Advanced Emergency Vehicle Detection using Sound Localization

Purdue Univerisity
Our prototype utilizes an array of microphones pointing in different directions and LED bulbs to display the direction of travel of emergency vehicles. The assumption is that the array of microphones should be receiving the same auditory signals but at different intervals of time. The sound captured by an array of microphones will be sampled. It will then be filtered and angle of the receiving sound-wave that corresponds to the frequency of the emergency vehicles’ sirens will be used to determine the direction of the corresponding sound-wave and light up the LEDs accordingly.

October 2019 - December 2019

Inventory Automation Using Electronically Connected Intelligent Shelves and Machine Learning

Purdue Univerisity
Our design of ECIS system prototype includes an array of ultrasonic sensors, which can be retrofitted in existing shelves with minimal modifications or built-in in to new shelves, connected wirelessly to a central cloud server from where the inventory of goods on the shelf can be monitored in real-time as well as data acquired from these sensors can be used to perform predictive analysis using data mining, feature engineering and machine learning techniques to better predict future product sales and minimize inaccurate forecasting instances.

  • This project was ranked #1 in class by peer reviews and ratings.

October 2019 - December 2019

Self Checkout Shopping Cart - Capstone Project

University of Toledo
The Self-Checkout Shopping Cart uses a shopping cart, computer hardware, and software. The main objective of the Self-Checkout Shopping Cart project is to reduce the time spent during checking out of a store by skipping long checkout lines at traditional checkout counters. The result is intended to facilitate a quick and convenient checkout for customers, and increase the productivity and efficiency throughput for the store by reducing workload on the traditional cashier-staffed checkout counters.

  • Our project was mentioned in the local newspaper in December 2015.

January 2015 - December 2015

Cloud Computing Research

University of Toledo
Researched on the privacy and security issues related to Cloud Computing.

September 2011 - November 2011

Future Automobile Design

University of Toledo
Designed a concept car. Researched on design, features, safety and overall cost of the concept car.

August 2011 - December 2011

Riccia Seeds and Garden Website

Riccia Seeds and Garden
Designed and developed website: www.ricciaseeds.com.

June 2008 - July 2008

Interests & Hackathon

Interests


Apart from being an embedded systems and software developer, I enjoy most of my time being outdoors. During the warmer months here in Pennsylvania, 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. I enjoy exploring different cuisines and I spend a large amount of my free time exploring the latest advancements in the automotive industry.



Hackathon

Massachusetts Institute of Technology - COVID-19 Turn the Tide for India.
By working collaboratively in a team of five, we achieved following milestones in 96 hours:
• Researched and developed an Android UI/UX framework, and proposed the use of a toll-free number for marginalized urban and rural population in India to pick up ration in a slot-based system to prevent crowding and community level COVID transmission.
• Developed predictive modeling prototype built into the Android app to collect data on demand of ration and toll-free number users to estimate rations needs per region based in real-time data.
• Proposed further uses cases such as the predictive modeling system to estimate ration demand during unusual circumstances like natural calamities and pandemics.

Peer-Reviewed Publications

Enhanced 3D Object Detection and Tracking in Autonomous Vehicles: An Efficient Multi-Modal Deep Fusion Approach

Purdue University

This dissertation delves into a significant challenge for Autonomous Vehicles (AVs): achieving efficient and robust perception under adverse weather and lighting conditions. Systems that rely solely on cameras face difficulties with visibility over long distances, while radar-only systems struggle to recognize features like stop signs, which are crucial for safe navigation in such scenarios.

See Publication (DOI): 10.25394/PGS.26009968.v1

Published: August 2024

NeXtFusion: Attention-Based Camera-Radar Fusion Network for Improved Three-Dimensional Object Detection and Tracking

Special Edition of MDPI

This paper presents NeXtFusion, a novel deep Camera-Radar fusion network designed to enhance autonomous vehicle (AV) perception in challenging weather and lighting conditions. By leveraging the rich semantic information from cameras and the X-ray-like capabilities of radars, NeXtFusion improves object detection and tracking accuracy. Extensive testing on the nuScenes dataset shows NeXtFusion outperforms existing methods with a top mAP score of 0.473 and strong performance in other metrics. This demonstrates NeXtFusion's effectiveness in robust, real-time AV perception and safety.

See Publication (DOI): 10.3390/fi16040114

Published: March 2024

An Improved Lightweight Network using Attentive Feature Aggregation for Object Detection in Autonomous Driving

Special Edition of MDPI

This research paper introduces MobDet3, an efficient lightweight object detection network specifically designed for self-driving vehicles. It uses a modified MobileNetV3 as its backbone and incorporates altered computer vision techniques, aiming to achieve high accuracy and fast inference speeds. Extensive tests show that MobDet3 achieves up to 88.92 frames per second, making it ideal for real-time object detection in autonomous driving.

See Publication (DOI): 10.3390/jlpea13030049

Published: August 2023

NextDet: Efficient Sparse-to-Dense Object Detection with Attentive Feature Aggregation

Special Edition of MDPI

This paper introduces NextDet, a modern object detection network specifically designed for efficient monocular sparse-to-dense streaming perception, with a focus on autonomous vehicles and rovers using edge devices. NextDet utilizes CondenseNeXt, a lightweight convolutional neural network algorithm, as its backbone to extract and aggregate image features at different granularities. It also incorporates other novel and modified strategies for object detection and bounding box drawing, adapting to the latest version of the PyTorch framework.

See Publication (DOI): 10.3390/fi14120355

Published: November 2022

CondenseNeXtV2: Light-weight Modern Image Classifier Utilizing Self-Querying Augmentation Policies

MDPI - Journal of Lower Power Electronics and Applications

This paper introduces CondenseNeXtV2, a modern image classifier that is lightweight and ultra-efficient. It is designed to be deployed on local embedded systems (edge devices) for general-purpose usage. Building upon the award-winning CondenseNeXt paper presented at the 2021 IEEE CCWC, this work incorporates a new self-querying augmentation policy technique on the target dataset and adapts to the latest version of the PyTorch framework and activation functions. The result is improved efficiency in image classification computation and accuracy.

See Publication (DOI): 10.3390/jlpea12010008

Accepted: December 2021
Published: January 2022

EffCNet: An Efficient CondenseNet for Image Classification on NXP BlueBox

American Journal of Electrical and Computer Engineering - Science Publishing Group

This paper introduces EffCNet, a novel deep convolutional neural network architecture specifically designed for edge devices with limited computational resources. EffCNet is an improved and efficient version of the CondenseNet CNN, incorporating self-querying data augmentation and depthwise separable convolutional strategies to enhance real-time inference performance and reduce model size, trainable parameters, and Floating-Point Operations (FLOPs). Extensive supervised image classification analyses are conducted on CIFAR-10 and CIFAR-100 benchmarking datasets to verify the CNN's real-time inference performance. Finally, the trained weights are deployed on the NXP BlueBox, an intelligent edge development platform for self-driving vehicles and UAVs, leading to valuable conclusions.

See Publication (DOI): 10.11648/j.ajece.20210502.15
Accepted: August 2021
Published: October 2021

AI on the Edge with CondenseNeXt: An Efficient Deep Neural Network for Devices with Constrained Computational Resources

Purdue University

This Masters Thesis presents a neoteric variant of a deep convolutional neural network architecture called CondenseNeXt, specifically designed for ARM-based embedded computing platforms with limited computational resources. CondenseNeXt is an improved version of CondenseNet, incorporating depthwise separable convolutions and group-wise pruning to reduce redundant elements without compromising network performance. Cardinality and class-balanced focal loss functions are introduced to alleviate the effects of pruning. Extensive analyses on benchmark datasets (CIFAR-10, CIFAR-100, and ImageNet) are conducted using an ARM-based embedded computing platform, NXP BlueBox 2.0, for real-time image classification. CondenseNeXt achieves state-of-the-art performance with significant reductions in forward FLOPs and can efficiently perform image classification without a CUDA-enabled GPU support on ARM-based computing platforms.

See Thesis Publication: Purdue University, 2021.
Accepted: June 2021
Published: August 2021

Image Classification with CondenseNeXt for ARM-Based Computing Platforms

IEEE - International IOT, Electronics and Mechatronics Conference (IEMTRONICS)
Toronto, ON.

This paper showcases the implementation of our ultra-efficient deep convolutional neural network architecture, CondenseNeXt, on the NXP BlueBox platform, specifically designed for self-driving vehicles. We highlight CondenseNeXt's outstanding efficiency in terms of FLOPs, tailored for ARM-based embedded computing platforms with constrained computational resources, allowing image classification without requiring a CUDA enabled GPU.

See Publication (DOI): 10.1109/IEMTRONICS52119.2021.9422541

Accepted: March 2021
Published: May 2021

CondenseNeXt - An Ultra-Efficient Deep Neural Network for Embedded Systems

IEEE - 11th Annual Computing & Communication Workshop and Conference (CCWC)
Las Vegas, NV.

This paper introduces CondenseNeXt, a novel variant of deep convolutional neural network architecture aimed at enhancing the performance of existing CNN architectures for real-time inference on embedded systems with limited computational resources. Based on the PyTorch framework, CondenseNeXt demonstrates remarkable efficiency compared to the baseline architecture, CondenseNet, achieving reduced trainable parameters and FLOPs while maintaining a balance between the trained model size (less than 3.0 MB) and accuracy trade-off. The result is an unprecedented level of computational efficiency, making CondenseNeXt a promising solution for real-time inference on embedded devices.

See Publication (DOI): 10.1109/CCWC51732.2021.9375950

Accepted: December 2020
Published: March 2021

Awards, Licenses & Certifications

Awards
  • Recipient of the IEEE Best Presenter Award at the 2021 IEEE IEMTRONICS International Conference.
  • Recipient of the IEEE Best Paper Award at the 2021 IEEE - 11th Annual Computing & Communication Workshop and Conference.
  • Recipient of the IEEE Best Presenter Award at the 2021 IEEE - 11th Annual Computing & Communication Workshop and Conference.
  • Recipient of Research Block Grant at the Purdue School of Engineeirng and Technology.
  • Recipient of International Student Scholar Scholarship Award by the University of Toledo.
  • Recipient of IUPUI Service Award by Indiana University-Purdue University Indianapolis.
  • Awarded Certificate for Distinctive Performance by National Cyber and Science Olympiad for excellence in Computer Science and Science subjects by the Science Olympiad Foundation.
  • Recipient of the 'SuperKID The Super All-Rounder' title by ICICI Bank and ICICI Lombard General Insurance for being a winner and showing excellence in the SuperKID contest in high school.

Licenses & Certifications

Recommendations and References

Gregory Scott

Director (now Vice President) of Information Technology at Renovo Solutions
"Priyank is truly an incredible person both professionally and personally. His work ethic during our several years working together was nothing short of stellar. He received nothing but exceptional feedback from others that worked with him and even when dropped into unique and undefined roles, he had unrelenting ability to simply tackle whatever was asked of him. I see no limitations in where he can go. I am inspired by his quest to continue to grow and learn and I am very excited for his future and anyone lucky enough to work with him." - LinkedIn Recommendation. Also, check out the Company-Wide Departure Announcement by clicking here.


Richard Toth

District Manager to the East Region at Renovo Solutions
"Priyank was instrumental in the early phases of Renovo Solutions Integrated Systems Management project at Beebe Healthcare in Lewes, Delaware. This project focuses on identification of networked medical devices, capturing system configuration, assessing system risk and working in conjunction with Beebe Healthcare’s IT Department to mitigate existing risks and establish policies and procedures to minimize future risk. The efforts at Beebe were recognized in 2018 by the Association for Advancement of Medical Instrumentation through their Clinical Solutions Award. Priyank accepted and eagerly took to the task of capturing all of the system configuration data, a very large task that was completed accurately and efficiently. Priyank is clearly an example of someone who will perform any given task to the best of his ability with exceptional results. Throughout his years at Renovo Solutions, he has always performed to this level, receiving high praise from Renovo Solutions management throughout the country. I can do nothing but highly recommend Priyank." - LinkedIn Recommendation.


John Kovalchik

Account Manager (now Director of Operations) at Evangelical Hospital for Renovo Solutions
"Priyank is a great team player and would be a great asset to any company. Priyank is a detail orientated individual and goes above and beyond when he is assigned a project. He crosses his T's and dots his I's, and is thorough in what he does. I would have him on my team in a heartbeat." - LinkedIn Recommendation.



Get in touch!