Making sense of the world with code and curiosity! Because why not? Hi! I am Devjyoti, think of it as a blend of 'dev' for developer and 'jyoti' for a spark of innovation, just like in Sanskrit. Welcome to my corner of curiosity, where I research, innovate, and explore at the CIDCOM and CeSIP Lab @UoS.
Projects
Computer Vision
-
Federated Learning Optimised for Remote Assessment of Species in Agricultural Grassland Ecosystems [FLORA-SAGE]
This project, leverages Sentinel satellite data and diffusion models to create high spatio-temporal datasets for preprocessing, enabling deep learning models to accurately identify plant and soil biodiversity in agricultural grasslands.
-
Digital Dairy Chain (DDC) - UKRI
Developing advanced deep learning and computer vision architectures for accurate cattle recognition, 3D object tracking, and multi-camera handoff systems to enhance automated precision livestock management.
-
Transport for London (TFL)
This project leverages point cloud data from Amberg trolley scans, converted into depth maps, to develop an automated system for detecting and classifying track features, enabling efficient maintenance and renewal planning for Transport for London's rail network.
-
Machine Learning for Spectral Analysis on System on Chip
This research project develops a CNN-based model for real-time RF signal detection using AI on the AMD-Xilinx RFSoC platform, optimizing performance through Quantization analysis with Vitis AI for efficient signal recognition and processing.
Software Engineering
-
Management of Google Cloud Platform
Optimized GCP account performance by analyzing 300+ customer accounts monthly, improving database recovery speed, and enhancing cloud security measures to reduce rogue admin risks.
Publications
Computer Vision
-
Data Study Group Final Report: Transport for London
[Paper] [Code]
Object Detection for RF Signal Classification: A Comparative Study for Spectrogram-Based Detection in RFML Applications
[Paper] [Code]
xAI
Converging Ethics and Sustainability in Engineering Through Collective Intelligence
[Poster]
IoT
Multi-band multi-location RF power survey and ambient RF energy harvesting circuit
[Paper] [Code]
Sensor Technology
Online Personal Health Monitoring System
[Paper] [Blog]
Media
Flora Sage
Transforming environmental science with the power of AI
Image recognition technology is delivering autonomous, continuous, detailed and unbiased data at scale, saving money and enabling more effective action on biodiversity.
European Space Agency: Commercial Applications of Space-Enabled Robotics: Agriculture
ESA seek proposals for services that combine the use of satellite technologies and robotics for Agriculture applications.
Digital Dairy Chain
Using existing on-farm sensor technologies to study cow welfare
Innovate UK-funded feasibility study run by University of Strathclyde using First Milk farms is being amplified through the Strength in Places Digital Dairy Chain project.
Making moo-ves: Sainsbury’s first retailer to milk the benefits of new AI “vet tech” to improve animal welfare and efficiency on dairy farms
New AI veterinary technology used to measure and enhance positive animal welfare on dairy farms, which could revolutionise the approach to cattle care.
Lely Smart Feeding System: Automation in Dairy Industry
AI Calving Monitor and AI Barn Monitor, a Yellow Revolution concept called Lely Zeta
Empowering Ethical AI:For Sustainable Livestock, Companions, and Wildlife Welfare
Cutting-edge AI and computer vision technologies to address critical challenges in animal welfare.
AMD Versal AI
Mastering Scalable Radar Signal Processing with AMD Versal Devices
AMD has demonstrated the effectiveness of combining expertise in radar technology and advanced signal processing.
AMD announces ‘Fire Range’ and Ryzen AI Max, its most potent laptop chips yet
AMD is also announcing two new X3D desktop chips today, declaring that it now has a CPU that’s “the world’s best processor for gamers and creators.”
Subscribe to my Newsletter
-
-
-
-
-