Projects

PoseNet: Real-Time Human Pose Estimation

Implemented both Single and Multiple Body Keypoints Detection Algorithm using MobileNet Architecture of CNN which resulted in 96.87% accuracy of the model.

GitHub

Hand-Written Digit Recognition Using Deep Learning

Developed a Deep Learning Model to recognize the hand-written digits efficiently with a testing accuracy of 98.8% and training accuracy of 99.84% and compared with other models.

GitHub

Artistic Neural Style Transfer Using PyTorch

Implement the style transfer method using VGG19 that is outlined in the paper, Image Style Transfer Using Convolutional Neural Networks, by Gatys in PyTorch.

aggle

Histopathologic Cancer Detection

Developed a Deep Learning Model for the Identification of Metastatic Tissue in Histopathologic Scans of Lymph Node Sections which provided 0.94 ROC AUC Value. Assessed the performance of deep learning algorithms at detecting metastases in hematoxylin and eosin–stained tissue sections of lymph nodes of women with breast cancer.

aggle

Smart Building using IoT

Designed prototype that used an Arduino Uno microcontroller and PIR sensors to check the entries and exits of people to a room and controlled the electric equipment available in the room accordingly and also upload the data to cloud for further analysis under the guidance of Skyfi Labs.

Demo

Google Assistant App: Daily Roaster

Designed, Developed and Published globally (225 counties) a Google Assistant Action named “Daily Roster”. This app keeps track of the academic schedule, canteen menu of students and teachers. Implemented Natural Language Understanding (NLU) using DialogFlow API and Firebase with GCP.

Assistant

Virtual Blood Bank : JeevanRakht

This project is a web application named “JeevanRakht” dedicated to locate blood donors across a region and also who needs blood mentored by Google and Udacity Team. Worked as a UI/UX Lead of the Community-driven Project and managed 30+ contributors with my team.

GitHub