Companies

Domains: API Design and Implementation, Database Management, Backend Development
Project Overview: This project involves the development of a robust backend system for a recommendation engine, including APIs, a dynamic website, and a user-friendly admin panel. The goal is to create a scalable and secure system using Python and FastAPI/Django, with Cassandra as the database. The system will be documented and tested using Swagger, and version control will be managed via GitHub with CI/CD pipelines using GitHub Actions.

Domains: App Development, Network Management, Matching Algorithms

Project Overview: 
The project aims to develop an app that helps people make new social connections and find matches using their existing contact network. It will include features like secure sign-in, building and mapping networks, a smart matching system, daily suggestions for new connections, likes, matches, in-app messaging, and ways to keep users engaged and generate revenue.
 

Partner: AlgoBulls

Domains: UI/UX Development

Project Overview: This project focuses on developing a user-friendly UI/UX design for a chatbot that analyzes your trading account. The chatbot reviews transactions and offers you recommendations and reviews based on your trading history.

Partner: Lechler

Domains: Desktop Application Development

Project Overview: The project involves packaging an existing spray analysis tool into an .exe application with a functional GUI. The software will be provided as an executable that can be run on a Windows desktop, along with an instruction manual for downloading and using the software.

Partner: BP Wealth
Domains: Quantitative Trading
Project Overview: This project aims to develop trading alphas specifically for the Indian and US equity markets, focusing on medium to high-frequency trading strategies. Our objective is to create and test these alphas to enhance trading performance.

Partner: Lechler

Domains: Optimization, Automation in Mechanical Design

Project Overview: This project aims to make designing circular droplet separators easier and faster. The goal is to develop a clever mathematical model to organize profiles efficiently, and create scripts to automatically generate 3D models in Autodesk Inventor based on specific requirements. Ultimately, we're aiming to simplify the process of creating these separators for any disk specification, saving time and effort.

Partner: Mosaic Asset Management
Domains: Econometric Modelling, Data analysis
Project Overview: The project aims to predict whether certain sectors will perform better or worse compared to the benchmark index. This prediction is based on modeling global and local economic variables and analyzing how they relate to each sector.

Domains: Machine Learning, Big Data, Cloud Computing
Project Overview: The project aims to develop and deploy an advanced recommender system for using state-of-the-art algorithms. It involves data gathering, algorithm selection and optimization, performance evaluation, and deployment on AWS with Hadoop and Spark integration. The goal is to improve user experience and increase sales by providing personalized product recommendations.

Partner: Lechler

Domains: Computer Vision, Software Development

Project Overview: 
The project aims to develop a tool that measures the amount of water reaching any point (x, y) of a nozzle spray per unit time using a patternator. The goal is to analyze the spray pattern distribution accurately and generate a 3-D representation of the water spray pattern at a specific height which will help in further experimentation of the patterns and client verification.

Partner: Lechler

Domains: Computer Vision, Software Development

Project Overview: 
The project focuses on developing a test bench to measure voltage levels between two points (amplifier and receiver). Using the fact that voltage level is inversely proportional to water density levels between two points, the aim is to find nozzles that have suffered some damage and are in need of maintenance.
 

Domains: Computational Fluid Dynamics, CAD Modeling
Description: The objective of this project is to evaluate the durability of a spray-based dust separation system. Currently, there is a risk for water droplets generated by the nozzle to escape and enter a sensitive dust filter, compromising the system in place; this risk must be measured and eliminated. We will use Solidworks and Ansys Fluent to design and simulate different water spray conditions, optimizing for safety by varying droplet size, speed and orientations if necessary.

Domains: Database Management, Software Development
Partner: AlgoBulls
Description: The objective of this project is to design and implement a database management system for managing business operations for a financial services firm. Tasks include database schema design, user access control, statistical analysis and general web deployment tasks. The application will have a backend built with Django, a frontend using React, and will include features like role-based access control, Excel sheet-based data loading, and interactive dashboards for data analysis.

Domains: AI in Education, Software Development

Project Overview: Sherpa aims to develop an AI-powered Oral Conversation tool that provides a better learning experience for the student and improved plagiarism-checking practices. The project includes the development of an AI-powered conversation tool and surrounding Sherpa Learning Management System (LMS), allowing students to chat with a bot with regards to reading material and assignments. The responses will be continuously evaluated by the system, making this a near viva-like experience for students in school.

Domains: Web Scraping, NLP, APIs for Communication, Database Management

Project Overview: The project aims at creating techno-sales products for the financial firm AlgoBulls. To begin with, we must create a repository of active traders by extracting information available on social media platforms, especially LinkedIn and Twitter. Once ready, people's social profiles will be extracted through certain classical and NLP tools, and a communication system will be set up to auto-follow up with them through email. Prototypical AI-based chat bots will also be explored as an additional feature.

Domains: Software Development, C++ Programming, LabVIEW Integration, Data Visualization

Project Description: The Project aims to enhance the real-time data visualization capabilities for camera feeds by creating a more efficient and responsive user interface. The project involves developing a new UI using LightningChart in C++ and integrating it seamlessly into LabVIEW for streamlined data capture and visualization.

Domains: Image processing, Computer vision, 3D geometry and point clouds, Surgical navigation

Project Overview: The project aims to develop markerless tracking algorithms for surgical navigation, utilizing Intel Realsense cameras to capture RGB and Depth images of a mock bone in a non-surgical environment. The process involves two real-time CNN-based algorithms for ROI detection and point cloud segmentation. The ultimate goal is to register a virtual 3D model of the bone with the physical bone using 3D-3D point registration algorithms.

Project Name: Agricultural Field Analysis and Modeling using Satellite Time Series Imagery

Partner: Google Research

Sectors: Agriculture, Remote Sensing

Category: Computer Vision, Satellite Imagery, Machine Learning

Current Team:

1. Professor Milind Sohoni
2. Aaryan Dangi
3. Lisan Kadivar
4. Sameer Mannava
5. Aditya Torne

Description: The project aims to use satellite imagery and various other data sources such as weather and soil quality to improve agricultural field analysis and inference. Key objectives include developing a robust model for crop presence, creating a confidence-based classification system for crop cycles, and implementing time series-based crop classification using attention-based neural networks. The project also involves incorporating region-specific data, soil information, and other relevant parameters to enhance the accuracy of predictions. Our end goal is to create an agri-IT stack that will help India assess farmer-specific cropping data: yields, crop health and overall farm history.

Project Name: Using Geospatial Algorithms to Modernize Land Records

Partners: Directorate of Land Records (DoLR), Govt. of Maharashtra and Google Research

Sector: Land Records

Categories: GIS Data Structures and Algorithms

Current Team:

1. Professor Milind Sohoni
2. Professor Bharat Adsul
3. Aaryan Dangi
4. Lisan Kadivar
5. Shashwat Prakash

Description: The Government of Maharashtra is looking to modernize land records, and create geo-referenced (latitude-longitude) ownership plots that are as close a match to ground reality as possible. There are several resources we have at our disposal: village paper maps that often date back to the 1800s, satellite images segmented into polygons that represent distinct farm plots (provided by Google), and some other textual/geometric data for each survey plot.

The central problem we face is that the old paper-based maps don’t match the actual farm boundaries that currently exist; rivers have changed paths, ownership of land has been subdivided, and, most importantly, the old techniques of mapping weren’t precise at all, especially by today’s standards. Hence, there is no one legal map for any village: this is not good news, given the number of legal disputes currently awaiting resolution.

Hence, our task is to take the space partitions of polygons, that is the survey map, first digitized and scaled appropriately, and transform it mathematically (using operations such as rotations, translations, node shifts, etc) to match farm plot boundaries while ensuring minimum deviation in parameters such as area/shape index. We are also looking to explore similar areas, such as creating crop water deficit models for insurance and food agencies.

Project Name: Extracting Data from Spray Pattern Images
Partner: Lechler India Private Limited
Category: Image Analysis
Description:
The project requires processing images derived from nozzle spray experiments and deriving plots for further analysis. Standard image processing task, requires the usage of Computer Vision libraries in Python and finally exporting the detected objects as excel plots.
 

Project Name: Developing a marketplace for landscaping and lawn maintaining services
Partner: AP Landscaping
Category: App Development
Description: AP Landscaping is a professional landscaping company situated in the USA, that is looking to expand and digitize its operations. To do so, it would require a platform that can connect clients seeking lawn services with providers offering landscaping services. Hence, the primary goal of this project is to develop a user-friendly mobile application with features such as registration, payment integration, a chat interface, integration with maps, AI-based image processing, etc.
 

Project Name: Advancing cancer screening through big data: a national initiative

Partners: Tata Memorial Center (TMC), GISE Hub IITB

Sectors: Healthcare, Data Analysis, Web Development

Description: 

The global burden of cancer incidence and mortality is on the rise, necessitating the use of large-scale data handling and multi-dimensional analysis for the crucial first step in combating cancer: early-stage detection through screening. Although substantial data exists in the form of Hospital Based Cancer Registries (HBCRs) and Population Based Cancer Registries (PBCRs), there is a pressing need to centralize and reconcile this data for meaningful outcomes in the field.

The project’s central purpose is thus to develop analysis-ready cancer registries so as to improve cancer screening capabilities across India. The work will involve developing API-based access to cancer data, designing analysis tools for clinical significance, analyzing genomic data, and creating visualization dashboards. The collaborative effort of the project partners seeks to improve cancer research, prevention, early detection, clinical practice, and healthcare infrastructure development in India.

Project Name: AR-Based Bone Tracking

Partner: AlgoSurg

Sector: Healthcare Technology

Category: Augmented Reality (AR), Medical Imaging

Description: This project aims to develop a prototype for AR glasses (Microsoft HoloLens 2/Vuzix M400) using Unity-3D, for augmented reality-based bone tracking. Users will wear AR glasses, allowing them to view a physical bone model with an attached optical marker. Through the AR glasses, users must see a virtual 3D model of the same bone, morphed onto the physical bone. As the physical bone moves (with the marker attached), the virtual 3D bone model should move in sync, providing a real-time augmented view. This technology has potential applications in medical education, surgery planning, and other medical fields.