Harsh Agrawal

Harsh Agrawal

Multimodal ML Researcher

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

Transformative Approaches in EEG Analysis

This project focuses on developing deep learning models for the classification of harmful brain activity patterns in EEG data from critically ill patients. By leveraging CNN architectures such as EfficientNetB2, MobileNetV3Large, ResNet V2, and DenseNet, we aim to improve the accuracy and efficiency of automated EEG analysis in neurocritical care settings.

SpotiBot

SpotiBot is a voice-controlled bot-type app designed to control Spotify. Utilizing the Spotify Android SDK, this app supports basic playback commands through voice control, enhancing the user experience for Spotify listeners.

OnlyGIFs

OnlyGIFs is a social media platform dedicated exclusively to GIFs. It allows users to upload, view, and download GIFs with captions, creating a unique space for sharing and enjoying GIF content.

PokePy

PokePy is a Pokémon game developed using Python and the Pygame library. The project aims to recreate the classic Pokémon gameplay experience with features like player movement, battle mechanics, and interactive environments.

Hazard View Bird

This project focuses on developing an on-device Disaster Scene Parsing and Detection system using UAV imagery. By leveraging advanced semantic segmentation models such as EfficientNet, UNet with ResNet18, and deploying on edge devices like the NVIDIA Jetson Nano, the project aims to improve disaster assessment and response efficiency.

Heart Failure Prediction Using Machine Learning

This project involves the development of a machine learning model to predict heart failure in patients. By employing exploratory data analysis (EDA) and various machine learning algorithms, we aim to enhance the early detection and treatment of heart failure, thereby improving patient outcomes.

One-vs-All Methodology Based Cassava Leaf Disease Detection

This project presents a deep learning-based solution for detecting cassava leaf diseases using a one-vs-all classification approach. By employing EfficientNet B4 and deploying the model on Android devices, we aim to provide an accessible tool for farmers to detect diseases early.

Pneumonia Detection Using Image Processing and Deep Learning

This project focuses on detecting pneumonia from chest X-rays using a novel image processing and deep learning approach. By leveraging transfer learning and morphological operations, we aim to improve the accuracy and efficiency of pneumonia diagnosis.

Personalized GIF-based Reply System

This project introduces a methodology to build smarter bots that can reply to conversations using both text and GIFs. By leveraging advanced NLP techniques and a custom recommendation system, we aim to enhance user interactions on social platforms.

Breast Cancer Classification Using Transfer Learning

This project presents a method for classifying breast cancer histopathology images using the concept of transfer learning and several compact Convolutional Neural Networks (CNNs). By leveraging the ResNet50V2 model, we aim to enhance the accuracy of breast cancer diagnosis.

JavaOS

This project is a simulation of a real-world operating system. It provides functionalities like user login, a desktop environment, file navigation, notepad, terminal, and a web browser. Implemented using Java, it aims to mimic basic OS operations and provide a user-friendly interface.

HelpKart

HelpKart is an innovative application designed to facilitate the renting and donation of clothes. By providing a platform for users to rent out unused clothes or donate them to NGOs and organizations, HelpKart aims to reduce waste and support those in need.

publications

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.