Building astronaut.sh, app.fitcam.io, numcast.io

Sahil Malhotra  • Peerlist

Ripeness Classification Model, to measure the ripeness of tomato using Computer Vision techniques (and ongoing: spectroscopy), projected to impact 169M tonnes of food wasted in India due to maturity factors at harvest time.

Automated Grading System to Evaluate Ripeness

Fine-Grained Named Entity Recognition, a stack of models to infer benefit details from lengthy Insurance Contracts and Booklets.

Benefit Booklet Information Extraction

Every year, the city of Detroit issues millions of dollars in fines to residents and every year, many of these fines remain unpaid. Enforcing unpaid blight fines is a costly and tedious process, so the city wants to know: how can we increase blight ticket compliance? ML project to predict whether a given blight ticket will be paid on time.

Blight Ticket Compliance

Building an In-house Data & ML Compute Platfo

Building an In-house Feature Store Platform a

The linked blog describes all the Design Decisions to everything behind the scenes

Building and Deploying a Real-Time Stream Pro

Student-Teacher location based app. Anyone with a knack can earn part-time.

EduPinger

An automated and power-saving light and fan system built using Arduino which is controlled via a static web page. The lighting system depends on surrounding light intensity and the speed of fan varies according to the surrounding temperature. Main Components: Arduino Uno, WiFi Module flashed with AT firmware, DC Motor(Fan), LED(Light), LDR(Light sensor), Temperature sensor Programming Language: C/C++

Power Saving Home Automation System

The face recognition implementation is both accurate and capable of being executed in real-time with or without a GPU. Deep metric learning is performed by outputting a real valued feature vector of an image to quantify the face.

Real Time Face Recognition

Built an home automation prototype using arduino and esp8266. Fans and light were toggled using a web app on a device which can be operated wirelessly. Temperature sensor and LDR was used to regulate fans and light smartly.

Smart Home Automation

Created a stock market simulation app where one can buy and sell stocks, get quotes, add funds, check their portfolios and history of their transactions. Implemented all these features using PHP. For database used SQL. Designed using HTML and CSS and scripted using JavaScript. Followed the MVC approach.

Stock Market Simulator

Analyzing sentiment scores from tweets related to relevant stocks and predicting the sentiment impact on the market for the next day. Used state-of-art RNNs to evaluate scores.