Projects

Technology Domains: Software Development, Data Science, Machine Learning, Deep Learning, Blockchain, Web Development

Disciplines:  Healthcare, Society, Supply Chain and Logistics, Crime, Nature, Differently Abled, Cosmetics

Tech Stack: HTML, JavaScript, CSS, Boostrap, Materialize CSS, Python, Flask, Numpy, Pandas, Seaborn, Matplotlib, MySQL, MongoDB,  DynamoDB, SQLite, Angular JS, Solidity, Web3, Sklearn, Keras, Tensorflow, Sensors, Arduino, IBM Cloud, Google Cloud Vision, Spacy,

fastai, Plotly, Chart.js

SAKSHY: TOWARDS CRIME FREE INDIA

Problem Statement Title : Converting handwritten documents as scanned images or photos (in any format) to legible text document using AI extracting important and critical information into database.

Ship it: BLOCKCHAIN IN LOGISTICS

Logistics is a service industry where Time and cost the critical factors. There are numerous parties involved in transport of goods from origin to final destination, which includes many processes .Many of the processes are manual and time consuming resulting in delay in delivering of goods chain.

SUVARGA: PROMOTING A HEALTHY SOCIETY

In a country like India, poverty is one of the major issues. Over 22 percent of the population is below poverty line. This poverty pushes people on streets which in future transform to slums. These slums, as are not planned lack certain necessities like electricity, sanitary services and basic hygiene resources.Our primary aim is to identify the leading causes of diseases in slum areas of Mumbai using data, and alert the concerned civic authorities regarding the same so that necessary action can be taken.We will even present a topographical representation of the diseases in a particular region. 

AI FOR SKIN CANCER

Detection and Classification of skin cancer from dermatoscopic images with Computer Vision.

Electronic Health Record for the patient to track medical history.

Description and Preventive measures for different kinds of skin cancer

PATANGA ABHIDANI: PORTAL FOR BUTTERFLY ENTHUSIASTS

A Cross-platform website for Hesperiidae Family of butterflies.
Detail Analysis of butterflies in a visual format based on distribution of the skipper family of butterflies.
Image Recognition to identify the Butterflies species of Hesperiidae integrated in the website.

OPTIMIZED WAREHOUSE MANAGEMENT OF PERISHABLE GOODS FOR A FOOD DELIVERY COMPANY

A food delivery service has to deal with a lot of perishable raw materials which makes it all, the most important factor for such a company is to accurately forecast daily and weekly demand. Too much inventory in the warehouse means more risk of wastage, and not enough could lead to out-of-stocks - and push customers to seek solutions from your competitors. The replenishment of majority of raw materials is done on weekly basis and since the raw material is perishable, the procurement planning is of utmost importance.

DISEASE PREDICTOR AND FALL DETECTOR FOR ELDERLY

Elderly people are prone to fainting in public places where they don't get any assistance. At the same time there is no way for their relatives and close ones to know about the incident. To counter this problem, the Fall Detector uses Raspberry Pi and an accelerometer to nofity the nearest hospitals and contact the patient's relative incase of a fall. The system also predicts diseases based on the symptoms using Machine Learning algorithms.

AUTONOMOUS DRONE DELIVERY

The project undertaken is an attempt to channelize cutting edge technologies like Computer Vision, Aerial Robotics, Image Processing and Artificial Intelligence to combat the loopholes in the traditional logistic and supply chain systems that involve extensive human intervention and are much slower while causing deterring effects on the environment The system developed by our team uses Drones to facilitate cost-effective, less time-consuming delivery to even the most rural parts of the country to uplift those devoid of essential services. The USP of our system that differentiates it from the rest is that it autonomously delivers goods directly from the warehouse to the destination with minimal manual control. Other drone-delivery systems are not intelligently programmed to identify the product in the warehouse.

comparing cosmetics by ingredients

 In this notebook, we are going to create a content-based recommendation system where the 'content' will be the chemical components of cosmetics. Specifically, we will process ingredient lists for 1472 cosmetics on Sephora via word embedding, then visualize ingredient similarity using a machine learning method called t-SNE and an interactive visualization library called Bokeh.

AMERICAL SIGN LANGUAGE DETECTION FOR DEAF

American Sign Language (ASL) is the primary language used by many deaf individuals in North America, and it is also used by hard-of-hearing and hearing individuals. The language is as rich as spoken languages and employs signs made with the hand, along with facial gestures and bodily postures. The project uses Convolutional Neural Networks to classify different letters of the ASL