aviralchharia's Projects
To develop an autonomous vehicle using Arduino (Atmega-328p) & remote wireless supervisory control (using, XCTU & XBee or C#) with capability of ultrasonic obstacle detection & avoidance, self-parking, stopping at gantries in its path & safely co-existing with other vehicles. The Infra-Red module, Transmitter & Receiver circuits were designed & fabricated on a PCB from scratch to develop the vehicle.
Developed a computer vision system for an autonomous vehicle capable of lane changing, avoiding vehicle collision by calculating relative vehicle speeds, etc. Used Hough Transform, Canny edge detection & ED-lines algorithm. Applied CNN on German traffic sign database for identifying traffic-signs & implemented behavioral cloning on a simulator. Tested the model’s performance in different weather conditions.
An end-to-end Self-driving car using CNN to map pixels from front-camera to steering angles on a simulator. This deep learning approach required minimum training data & the system learned to steer, with or without lane markings, on both local roads & highways, even with unclear visual guidance in various weather conditions. The vehicle could identify traffic signs & avoid collisions. Implemented NVIDIA's End-to-End Deep Learning Model for Self-Driving Car.
Aim of this project is to use Computer Vision techniques of Deep Learning to correctly identify & map Brain Tumor for assistance in Robotic Surgery.
Foreseeing Survival Through ‘Fuzzy Intelligence’: A Cognitively-Inspired Incremental Learning Based de novo Model for Breast Cancer Prognosis by Multi-Omics Data Fusion
cAPTured: Neural Reflex Arc-Inspired Fuzzy Continual Learning for Capturing in Silico Aptamer-Target Protein Interactions
Research Project for Detection of COVID-19 from X-Ray using Deep Learning methods. Implemented convolutional neural network for classification of X-Ray Images into COVID & non-COVID cases.
We propose a new class of Computer-aided diagnosis models, i.e., Deep-Precognitive Diagnosis, wherein artificial agents are enabled to identify unknown diseases that have the potential to cause a pandemic in the future.
In this project, we use a Deep Recurrent Architecture, which uses CNN (VGG-16 Net) pretrained on ImageNet to extract 4096-Dimensional image feature Vector and an LSTM which generates a caption from these feature vectors.
This project aims to automatically detect surface defects in Hot-Rolled Steel Strips such as rolled-in scale, patches, crazing, pitted surface, inclusion and scratches. A CNN is trained on the NEU Metal Surface Defects Database which contains 1800 grayscale images with 300 samples of each of the six different kinds of surface defects.