IBM Data Science Capstone Project for Real Estate price prediction with minimal data. This is a model made for prediction of Property with help of UCI Machine Learning Repository Datasets. This model predicts the price of any property from its specific attributes

This is property price production for Boston, Massachusetts by using data as small as 550 rows. However, only 80% of it would be used for training the dataset reducing available data to only 440 rows. Hence, a dataset with 14 attributes including the price of the property was chosen.

Project:- https://sites.google.com/view/prithvieportfolio/project-page/ibm-data-science
GitHub:- https://github.com/prithvi-sharma/IBM-Capstone-Project

The capstone project was a challenge to design a fully automated analyzing arrangement within a single offline script. The automation should even consist un-zipping of the image as well as excel data and direct application. The model was build using multiple neural network techniques including Conv2D (32,63,128), Flatten NN and Dense NN.

The plug load dataset contained current and voltage measurements sampled at 30 kHz from 11 different appliance types present in more than 60 households in Pittsburgh, Pennsylvania. Plus load refers to the energy used by products that are powered utilizing an ordinary AC plug.

Project:- https://sites.google.com/view/prithvieportfolio/project-page/microsoft-professional-capstone-artificial-intelligence
GitHub:- https://github.com/prithvi-sharma/Microsoft-Professional-Capstone-AI

The banking application is a voice automated application for basic facilities like information about current balance, last debit or credit transaction and to do actual transaction within the app.

The application was a challenge to me to test how wide is the spread of python language and can I make an application with just python from backend to cloud to server to visuals.

Project:-https://sites.google.com/view/prithvieportfolio/project-page/basa
GitHub:- https://github.com/prithvi-sharma/BASA

I used OpenAI's GPT2 model and trained it with a dataset of transcripts of all episodes of The Big Bang Theory show. After the model was trained, I experimented each and every characters generated dialogue individually by asking them generating individual conversations.

Then after about 3500 samples the model became decent enough and after 5000 samples it started giving phenomenal result.

Project:- https://sites.google.com/view/prithvieportfolio/project-page/ai-big-bang-theory
GitHub:- https://github.com/prithvi-sharma/AI-Big-Bang-Theory

This is my MPI - Micro-Processor and Interfacing subject project.

The legendary "Pac-Man" was written in Assembly language so I wanted to make something like that but in a simpler and feasible manner hence me and my team made this game.

Github:- https://github.com/prithvi-sharma/Projects/tree/master/Piyu%20-%20Assembly%20Language%20Game

Lip reading, otherwise known as Visual Speech Processing is a technique of perceiving spoken words by visually interpreting the movements of the lips, face, and tongue when actual sound isn't available.

In basic words, it is a visual method of ‘listening’ to someone. Often called ‘The third ear’ lip reading goes beyond simply reading the lips of a speaker to decipher individual words.

It also relies on information provided by the context, knowledge of the language, and any residual hearing additional to it for better subconscious analysis.

Research Paper: https://doi.org/10.5281/zenodo.17385124

Project: https://sites.google.com/view/prithvieportfolio/project-page/lip-reading-using-dl