Discover @souvik0306 Open Source projects

Souvik Datta (@souvik0306)

souvik0306

Stars
39
Global Rank 406,458 (Top 15 %)
Followers 9
Following 1
Registered about 5 years ago
Most used languages

Jupyter Notebook
37.5 %

Python
25.0 %

MATLAB
18.8 %

C++
12.5 %

HTML
6.3 %
Location 🇮🇳 India
Country Total Rank 23,307
Country Ranking

MATLAB
343

Jupyter Notebook
2,798

C++
6,500

Python
6,512

Book-Bot

This is a robot with Barcode + QR Code scanning capabilities designed for collecting books and navigation across a campus. The robot will mould the use of Computer Vision for ensuring safe collection and identification of books, all this while being powered by a Raspberry Pi for faster processing.

Path-Navigator-Robot

Path Planner Robot for effective route discovery

Soil-Type-Classification

• Designed a classification model with 5 classes and 98% testing accuracy using a Convolutional Neural Network. • Applied Data Augmentation and reduced validation losses by 30% by applying MobileNetV2 Architecture.

Jupyter Notebook

computer-vision

Repo containing basic computer vision modules

3D-Object-Detection

Reviewed literature for Object Depth Estimation using 2D Images using NYU Depth Dataset and used Google’s MediaPipe Objectron dataset to estimate object poses using ML models.

Thermal-imaging-using-MATLAB

Creating a thermal image of a given picture by breaking it down into its RGB components and comparing it with a processed color bar

Semantic-Segmentation-of-Satellite-Imagery

• Devised a U-Net-based Image Segmentation Model for land cover analysis on 5 classes from LandCover Dataset. • Developed a network based on the ResNet34 Architecture and achieved 0.72 mean Intersection over Union (IoU).

Jupyter Notebook

Traffic-Sign-Classifier

An autonomous braking system that uses sensor data from Radar and Computer Vision to localize the accurate position of an object around a vehicle using Neural Networks. An algorithm to fuse the data from sensors and camera to perform odometry operations

Jupyter Notebook

3D-Point-Cloud-Map

• Produced 3D point cloud data maps from 2D monocular RGB image-based depth maps using Open3D functions. • Exploited a PointNet based Object Detection model to classify 3D point cloud data with 81% training accuracy.

Jupyter Notebook

Jet-Engine-Health-Prediction

• Predicted Remaining Useful Life (RUL) for turbofan jet engines using a Random Forest Classifier Model. • Performed Exploratory Data Analysis on NASA’s Dataset and analyzed feature correlation using Seaborn. • Applied hyperparameter optimization using Randomized Search CV and increased F1-Score to an overall 91.2%.

Jupyter Notebook

YuMi-Robot-Modelling-and-Control

YuMi Robot Modelling using MATLAB

Earthquake-Prediction

Convolutional-Neural-Network

Jupyter Notebook

Cash-Sanitation-Model-for-COVID-19

A model that can sanitize currency notes by projecting Ultra Violet-C Light (UV-C) of 254nm to deactivate the COVID-19 virus.

Reinforcement-Learning-Robot

• Programmed a quadruped robot to exhibit walking gait using PyTorch-based Reinforcement Learning model. • Optimized learning rate and other hyperparameters to marginally enhance Mean Reward of the model by 14%.

Automated-Anaesthesia-Control-System

(Bio-Medical Instrumentation Project 2020-21)-Automated Anaesthesia Control System interfaced with a Mobile Application to allow the exchange of real-time body vitals using Internet of Things (IoT) and help reduce human errors encountered during manual administration of anaesthesia