Arijit Nandi - Portfolio

Arijit Nandi, Ph.D

Passionate Machine Learning Engineer & Researcher

Expert in Data Streaming & Affective Computing

Where streaming data meets human emotions

Music Lover

Music, passion, and melody in every note.

❮ ❯

Summary

Passionate AI/ML Engineer and Researcher with a Ph.D. in AI and 5+ years of experience turning cutting-edge concepts into impactful solutions. Skilled in federated learning, data streaming, deep learning, and emotion recognition with hands-on expertise in Python, TensorFlow, and PyTorch. Currently pushing boundaries in explainable AI (XAI) to make AI systems smarter and more transparent. Ready to contribute to exciting projects in a collaborative environment.

Technical Skills

Programming Languages

Python

MATLAB

Data Streaming

Scikit-multiflow

River

Kafka

RabbitMQ

MQTT

MLOps

Docker

Streamlit

MLFlow

Airflow

ML/DL Stack

Keras

Numpy

Pandas

Scikit-Learn

TensorFlow

OpenCV

TF Federated

Explainable AI

SHAP

Innvestigate

Version Control

Git

Work Experience

Eurecat - Technology Center of Catalonia, Barcelona, Spain

AI Researcher, Big Data and Data Science Unit (Dec 2022 – Now)

Worked on the “AI4Drought” project in collaboration with the European Space Agency (ESA), Lobelia Earth, and Barcelona Super Computer (BSC) to improve seasonal climate predictions of drought.
Developed an explainable AI GUI app (XaiSS) using Python, Streamlit, and Docker.

Eurecat - Technology Center of Catalonia, Barcelona, Spain

AI Researcher, Training Unit (Dec 2019 – Dec 2022)

Contributed as an AI expert to design and develop the AIM4YOU MOOC course under the EU project YNSPEED.
Developed an initial version of a collaborative and content-based filtering recommendation system for Moodle LMS.

Tuttify.io, Wesley Chapel, FL, United States

Freelance AI Engineer (Mar 2022 – May 2023)

Designed and developed emotion recognition from facial expressions using TensorFlow 2.0 and FER 2013, CK++.
Implemented pose estimation combined with emotional status to evaluate student engagement.

Projects

Docker based Federated Learning (DFL)

Developed a Docker-enabled Federated Learning framework using TensorFlow and Docker containers for data stream processing in heterogeneous HPC systems. View on GitHub

Federated Learning Method for Real-time Emotion State Classification (Fed-ReMECS)

Created a federated learning framework for real-time emotion classification from multi-modal physiological data streams with privacy in mind. View on GitHub

Tuttify’s Human Pose Estimation as A Service (CaamPose)

Customized pose estimation for student engagement analysis using Openpose models. View Tuttify

Tuttify’s Face Emotion Recognition as A Service (CaamFace)

Developed a face emotion recognition system using TensorFlow 2.0 and FER 2013, CK++ integrated into Tuttify’s backend. View Tuttify

Education

Universitat Politècnica de Catalunya (UPC), Barcelona, Spain

Ph.D. in Artificial Intelligence (Dec 2019 – Sept 2024)

Thesis: Multimodal data stream classification and prediction of e-Learner’s emotional states

National Institute of Technology Durgapur (NIT), West Bengal, India

M.Tech in Computer Science and Engineering (Aug 2017 – Mar 2019)

Thesis: A study of Enhanced Particle Swarm Optimization Trained Neural Network for Classification

Selected Publications

Arijit, Nandi, Fatos Xhafa, and Rohit Kumar. "A docker-based federated learning framework design and deployment for multi-modal data stream classification." Computing, pages 1–35. Springer, 2023.
Arijit Nandi and Fatos Xhafa. "A federated learning method for real-time emotion state classification from multi-modal streaming." Methods, volume 204, pages 340–347, 2022.
Arijit Nandi, Fatos Xhafa, Laia Subirats, and Santi Fort. "Reward-penalty weighted ensemble for emotion state classification from multi-modal data streams." International Journal of Neural Systems, 2022.

Awards & Achievements

Vicente López Award by Eurecat as a Ph.D. research scholar (Dec 2019–Dec 2022), partially funded by ACCIO under the project TutorIA.
M.Tech. Fellowship Award from the Ministry of Human Resource and Development (MHRD) India (Aug 2017–Aug 2019).

Google Scholar Citations

View my Google Scholar profile for detailed citation metrics: My Google Scholar

Loading citation metrics...

Contact

Email: jit.ari172@gmail.com

LinkedIn | GitHub | Google Scholar