<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Projects |</title><link>https://aroraanshu26.github.io/projects/</link><atom:link href="https://aroraanshu26.github.io/projects/index.xml" rel="self" type="application/rss+xml"/><description>Projects</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Sat, 26 Apr 2025 00:00:00 +0000</lastBuildDate><image><url>https://aroraanshu26.github.io/media/icon_hu_da05098ef60dc2e7.png</url><title>Projects</title><link>https://aroraanshu26.github.io/projects/</link></image><item><title>EMG Controlled Prosthetic Arm</title><link>https://aroraanshu26.github.io/projects/pandas/</link><pubDate>Sat, 26 Apr 2025 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/projects/pandas/</guid><description>&lt;p&gt;Prosthetic arm that can recoganize three gestures - pinch, grasp and release from EMG signals. I focussed on the machine learning model to classify the different guestures, and coding the microcontroller.&lt;/p&gt;
&lt;video controls style="width:100%; border-radius:12px; margin-top:1rem;"&gt;
&lt;source src="edl.mp4" type="video/mp4"&gt;
Your browser does not support the video tag.
&lt;/video&gt;
&lt;p&gt;Everything in this video (except for the laptop, electrodes and OpenBCI module) has been made in house! The hand is 3D printed and the PCB was printed at IITB. Notice how the probabilities of different motions (seen in red, green and blue on the computer screen) fluctuate as the motion is changed!&lt;/p&gt;</description></item><item><title>Hands-on Reinforcement Learning</title><link>https://aroraanshu26.github.io/projects/scikit/</link><pubDate>Mon, 03 Jun 2024 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/projects/scikit/</guid><description>&lt;p&gt;This is my exploratory project in Reinforcement Learning, where I have implemented common learning algorithms such as Q-learning, to play the mountain car game. I have also implemented different greedy, epsilon greedy, UCB sampling strategy, and have plotted their regret versus number of samples.&lt;/p&gt;</description></item><item><title>Trading Bot</title><link>https://aroraanshu26.github.io/projects/trading-bot/</link><pubDate>Wed, 27 Dec 2023 00:00:00 +0000</pubDate><guid>https://aroraanshu26.github.io/projects/trading-bot/</guid><description>&lt;p&gt;Developed a machine learning pipeline for stock trend prediction using technical analysis indicators on NIFTY50 data. The project involved extracting and preprocessing market data, engineering features using indicators such as MACD, RSI, Bollinger Bands, ADX, and Aroon, handling missing values and normalization, and training models to predict short-term gains and trading positions (buy, sell, or hold).&lt;/p&gt;</description></item></channel></rss>