Update index.html

index.html

@@ -222,12 +222,11 @@ <h2>
 										   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 										   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 										   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											Decoding Customer Churn: An Interactive Exploration in the Telco World
+											Gesture-Controlled Autonomous Robot
 										</a>
 									</h2>
 
-									<p>In this project on Telco Customer Churn, we aim to understand the factors influencing churn, such as service quality and pricing. We will analyze customer data to develop effective retention strategies for telcos and reduce revenue loss. The study's focus includes personalized experiences and innovative services to foster customer loyalty.
-									</p>
+									<p>This project enables touchless control of an autonomous vehicle using hand gestures. Utilizing MediaPipe, OpenCV, and deep learning models, it translates real-time gestures into movement commands. The system is designed for harsh environments, ensuring precise navigation without physical contact. Integrated with reinforcement learning, it adapts to dynamic terrains.</p>
 								</header>
 								<a href="https://github.com/sri-dsa/blob/main/machine_learning/tree_ensemble.ipynb" class="image main"><img src="images/telco.png" alt="" /></a>
 								<ul class="actions special">
@@ -245,13 +244,13 @@ <h2>
 											   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 											   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 											   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											   Unleashing Insights with Interactive Feature Engineering on the Ames Dataset
+											   AI-Powered Surveillance & Object Detection
 											</a>
 										  </h2>
 
 									</header>
 									<a href="https://github.com/sri-dsa/blob/main/machine_learning/Feature_engineering.ipynb" class="image fit"><img src="images/ames.png" alt="" /></a>
-									<p>In feature engineering with the Ames dataset, we will create new meaningful features from existing ones, such as combining area measurements to derive total living space. We may handle missing data through imputation techniques and encode categorical variables to prepare the data for machine learning models effectively. Additionally, feature scaling and normalization may be applied to ensure all features contribute equally to the analysis.</p>
+									<p>A real-time AI surveillance system using Facenet, YOLO, and DeepSORT for object and facial recognition. It can detect and track multiple objects, analyze human behavior, and provide security alerts. Works with thermal cameras for low-light conditions, making it suitable for forest and extreme environments.</p>
 									<ul class="actions special">
 										<li><a href="https://github.com/sri-dsa/blob/main/machine_learning/Feature_engineering.ipynb" class="button">View Project</a></li>
 									</ul>
@@ -264,13 +263,13 @@ <h2>
 											   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 											   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 											   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											   Exploring Vehicle Segmentation through Interactive Hierarchical Clustering on the "mpg" Dataset
+											   Multimodal AI (Gesture + Voice Control)
 											</a>
 										  </h2>
 
 									</header>
 									<a href="https://github.com/sri-dsa/blob/main/machine_learning/Hierarchical_clustering.ipynb" class="image fit"><img src="images/mpg.jpeg" alt="" /></a>
-									<p>In hierarchical clustering with the "mpg" dataset, we'll group vehicles based on similarity in fuel efficiency and related features. The algorithm will iteratively merge the closest data points into clusters, forming a hierarchical structure. The resulting dendrogram will illustrate the clustering hierarchy.</p>
+									<p>A dual-control system combining NLP-based voice commands and gesture recognition. If voice commands fail, gestures take over, ensuring uninterrupted control. Uses BERT, GPT, and ASR models for speech processing, integrating seamlessly with robotics for hands-free interaction.</p>
 									<ul class="actions special">
 										<li><a href="https://github.com/sri-dsa/blob/main/machine_learning/Hierarchical_clustering.ipynb" class="button">View Project</a></li>
 									</ul>
@@ -283,13 +282,13 @@ <h2>
 											   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 											   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 											   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											   Predicting Sales with Interactive Linear Regression on the "Advertising" Dataset
+											   AI Navigation & Reinforcement Learning
 											</a>
 										  </h2>
 
 									</header>
 									<a href="https://github.com/sri-dsa/blob/main/machine_learning/linear_regression.ipynb" class="image fit"><img src="images/dataset-card.jpg" alt="" /></a>
-									<p>In this analysis, we will perform linear regression using the "Advertising" dataset. The goal is to predict sales based on advertising expenditures for TV, radio, and newspaper channels. We will build a linear regression model to explore the relationships between these variables and understand their impact on sales.</p>
+									<p>This module optimizes path planning and obstacle avoidance using Reinforcement Learning (RL). Leveraging PPO, SAC, and DQN, it enables autonomous vehicles to learn from environments and improve navigation efficiency. Implemented with AirSim and SLAM for realistic simulation and deployment.</p>
 									<ul class="actions special">
 										<li><a href="https://github.com/sri-dsa/blob/main/machine_learning/linear_regression.ipynb" class="button">View Project</a></li>
 									</ul>
@@ -302,13 +301,13 @@ <h2>
 											   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 											   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 											   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											   Predicting House Prices with KC House Dataset
+											   Edge AI Processing for Real-Time Inference
 											</a>
 										  </h2>
 
 									</header>
 									<a href="https://github.com/sri-dsa/blob/main/machine_learning/knn_regressor.ipynb" class="image fit"><img src="images/how-size-doesnt-make-you-happier-today-main-190614.jpg" alt="" /></a>
-									<p>In this interactive analysis, we will explore the world of K-Nearest Neighbors (KNN) regression using the KC House dataset. By applying the KNN algorithm to this housing data, we aim to predict house prices based on various features, providing valuable insights for buyers and sellers in the real estate market. Get ready to interactively experience the power of KNN in making accurate and dynamic house price predictions.</p>
+									<p>Deploys lightweight AI models on Jetson Nano & Raspberry Pi for low-latency, high-performance inference. Uses TensorRT to optimize CNN-based detection models, allowing on-device AI processing without cloud dependency. Enhances real-time decision-making in constrained environments.</p>
 									<ul class="actions special">
 										<li><a href="https://github.com/sri-dsa/blob/main/machine_learning/knn_regressor.ipynb" class="button">View Project</a></li>
 									</ul>
@@ -321,18 +320,18 @@ <h2>
 											   style="display: inline-block; transition: transform 0.2s ease-in-out, opacity 0.3s ease-in-out;"
 											   onmouseover="this.style.transform='scale(1.1)'; this.style.opacity='0.8';"
 											   onmouseout="this.style.transform='scale(1)'; this.style.opacity='1';">
-											   Unraveling Patterns with SVC on the Mouse Viral Study Dataset
+											   AI Performance Monitoring & Logging
 											</a>
 										  </h2>
 
 									</header>
 									<a href="https://github.com/sri-dsa/blob/main/machine_learning/SVC.ipynb" class="image fit"><img src="images/mouse.webp" alt="" /></a>
-									<p>Join us on an interactive journey as we dive into the world of Support Vector Classification (SVC) using the "mouse_viral_study" dataset. Together, we'll unravel intricate patterns and classify the data to gain deeper insights into the study's viral outcomes. Get ready to actively engage with SVC to unlock valuable discoveries and revolutionize our understanding of this critical research.</p>
+									<p>A real-time AI monitoring system using Prometheus & Grafana for performance tracking. Logs latency, model accuracy, and resource utilization, providing alerts for system failures. Ensures reliability in critical deployments.</p>
 									<ul class="actions special">
 										<li><a href="https://github.com/sri-dsa/blob/main/machine_learning/SVC.ipynb" class="button">View Project</a></li>
 									</ul>
 								</article>
-								<article>
+								<!-- <article>
 									<header>
 										
 										<h2>
@@ -503,6 +502,7 @@ <h2>
 										<li><a href="https://github.com/sri-dsa/blob/main/deep_learning/DCGAN.ipynb" class="button">View Project</a></li>
 									</ul>
 								</article>
+								
 							</section>
 							<div class="text-container">
 								<h3 class="animated-text">Interested in my Analytics Projects Portfolio?</h3>
@@ -553,7 +553,7 @@ <h3 class="animated-text">Interested in my Analytics Projects Portfolio?</h3>
 							  
 							  
 					</div>
-
+					-->
 
 				<!-- Footer -->
 <footer id="footer">