adarshsankarrs Goto Github PK

adarshsankarrs.github.io

ai-chess-game

To simulate a chess game that advances by determining the optimal move each and every time, the Monte Carlo Tree Search (MCTS) algorithm was employed. The model has the ability to function as a framework for determining the optimal moves in various chess scenarios. Streamlit is used in the deployment of the chess webapp.

classifier-model

Range of outcomes using Decision Tree Classifier

data-analysis

Twitter and Uber Data Analysis

eazypredictai

Experimentation using a bunch of algorithms of ML algorithms on a preprocessed dataset

finitestateautomata-nlp

Investigated the use of finite automata to generate algorithms for typical NLP and genomics tasks such as tokenization, stop word removal, and pattern searching. We have also spoken about each algorithm's efficiency through a variety of test situations.

fsd-campusmanage

fsd-project

mlsa-task

mlsa-task2

photoshopapp

A Python and OpenCV module-built Photoshop web application with multiple filters and image processing features that is operational in bright light.

pixelate

A programme that allows you to play around with different blurs and filters to create various pixelation effects. Streamlit and OpenCV are integrated into Python.

prediction-using-neural-networks

Fruit Prediction using Pretrained CNN Model

spotify-data-analysis---rf-vs-mlp-study

The project involves using machine learning techniques, like RandomForestClassifier and MLP, to predict whether a song will be popular or not based on its acoustic features. The input consists of various acoustic and metadata features, while the output is a binary classification.

sudokusolver

Using OpenCV and Deep Learning to solve sudoku puzzles from photos.

traffic-classification-ovs

A system that can employ machine learning methods involving logistic regression, K-Means clustering, KNN, SVC, Gaussian NB, and Random Forest Classifier to categorize DNS, Telnet, Ping, Voice, Game, and Video traffic flows based on packet and byte information.

uber-data-analysis

Uber predicts trip categories ('Low,' 'Medium,' 'High') based on distances. Features include start point, destination, and purpose. Categorical variables are adapted. A tuned Random Forest Classifier forecasts trip types, providing insights into travel patterns.