OMKAR NITSURE's Projects
This repository has the code files written by me for all labs of the Microprocessors Lab(EE337) Course
I have designed the control solution for ball on a plate control system problem in Python. It makes use of the scipy.integrate utility from the scipy library and pygame which is a cross-platform set of Python modules used for writing video games.
Bubble Trouble, an interactive bubble shooter game designed in C++ with optimizations for more frames and visually appealing look
This repository contains codes written by me for all the labs of Digital Circuits Laboratory(EE214) course
Designed Bandpass and Bandstop IIR filters using the Butterworth, Chebyschev and Elliptic approximation. Also designed Bandpass and Bandstop FIR filters using the Kaiser Window to compute the coefficients of impulse response
Trained a Variational AutoEncoder Model to reconstruct the image and then sampled the latent space in order to get newly generated face images
We designed a High current sourcing sine wave generator capable of generating sine waves of amplitudes upto 30V and currents of upto 3A completely from scratch
This is a novel Transformer network based approach to distinguish ChatGPT generated Text from Human text. The model was also deployed on local server using Flask where Docker was used to manage all dependencies.
In this project, we do image classification on the MNIST dataset with 10 classes using compressive measurements. This involves sampling the image using a sensing matrix and then using the cluster centers computed on the training data to execute a kmeans-based algorithm to do final classification.
Simulated the Inverted pendulum control system using Matlab Software and plotted various system parameters as a function of time to understand and thus improve the current state using feedback control
Used different Transformer based and LSTM based models for forecasting rainfall in different areas of Mumbai. Employed different smart training techniques to improve correlation with the true time-series.
Created a Neural network based architecture which is able to generate an image having contents of a content image drawn in the style of a style image
Designed a Single Cycle 6-stage pipelined Processor which can execute 26 different instructions and implemented it in code in VHDL
Trained a generative Adverserial Network (GAN) which when given the satellite image of a place as input, outputs the Map image of that same location. It was trained using standard adverserial training.