IoT

Model Parallelism for Inference at edge

Explored distributing model components across different devices to enable running large models on edge with multiple smaller devices

Spatial AI

Analysed and predicted the behaviour of visitors in NYC's Bryant Park, building a digital twin spatial model for 4D simulations

Distributed Edge Compute

Built and deployed distributed edge compute on edge with fractional device usage for higher device efficiency using load balancing and micro kubernetes engine

Occupancy Detection

Built a solution for anonymised occupancy detection inside office space using LIDARs with features including social bubble breach detection and zone-based real-time occupancy counts and tracking

Factory Intelligence

A smart factory solution with unplanned machine downtime detection and industry-standard OEE calculations using cost-effective sensors and a dashboard with key KPIs

Fingervein Detection

Designed end-to-end biometric system with user registration and verification as a replacement for fingerprint technology

Cross-country Asset Tracking

Tracked cargo shipment using cost-effective sensors along its cross-country journey from factory to distribution center ascertaining possible locations of damage for effective preventive steps

Implementation of live models on edge

Implemented and optimised multiple live models (eg. action recognition on something something dataset with over 200 classes) on edge devices (eg. Jetson TX2, Raspberry Pi)