Video Analytics for Real‑Time Fall Detection & Activity Recognition
Building a real‑time fall‑detection and activity recognition system for elderly care using advanced video analytics and on‑device inference.
Building a real‑time fall‑detection and activity recognition system for elderly care using advanced video analytics and on‑device inference.
Question‑Answering chatbot for Bengali using Retrieval‑Augmented Generation 
Multilingual AI-powered support system delivering personalized agricultural guidance to Bangladeshi smallholder farmers.
Fine‑tuned and productionized a mobile/field app that delivers real‑time plant disease predictions to farmers 
Published in 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Tenerife, Canary Islands, Spain, 2023
This paper presents lightweight custom CNNs for corn leaf disease detection using deep learning techniques.
Recommended citation: Arefin, M. Y., Rabbi, R., Turna, I. F., Zannat, Z., & Karim, D. Z. (2023). "Lightweight Custom CNNs Take on Corn Leaf Disease: Deep Learning for Plant Pathology." In Proceedings of the 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), IEEE. 19‑21 July 2023, Tenerife, Canary Islands, Spain. DOI: https://doi.org/10.1109/ICECCME57830.2023.10252315.
Download Paper
Published in 2024 13th International Conference on Electrical and Computer Engineering (ICECE), 2024
This paper presents wildfire prediction using a convolutional Kolmogorov‑Arnold network.
Recommended citation: Rabbi, R., Datta, J., Ahmed, S., & Zereen, A. N. (2024). "Wildfire Prediction using Convolutional Kolmogorov‑Arnold Network." In 2024 13th International Conference on Electrical and Computer Engineering (ICECE) (pp. 667‑672). IEEE. DOI: https://doi.org/10.1109/ICECE64886.2024.11024794.
Download Paper
Published in 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh, 2025
This paper presents a parameter-efficient image classification approach using convolutional spiking neural networks and fast sigmoid surrogate gradient descent.
Recommended citation: Datta, J., Sarwar, F. A., Rabbi, R., Saha, P., Alam, M. G. R., Uddin, J., & Zereen, A. N. (2025). "Parameter‑Efficient Image Classification with Convolutional Spiking Neural Network via Fast Sigmoid Surrogate Gradient Descent." In 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh, pp. 1‑6. IEEE. doi: 10.1109/ECCE64574.2025.11013059.
Download Paper
Published in 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh, 2025
This paper introduces peer-guided optimization, a collaborative learning approach for stochastic optimization in machine learning.
Recommended citation: J. Datta, R. Rabbi, N. I. Rafin, and M. G. R. Alam (2025). "Peer‑Guided Optimization: Incorporating Collaborative Learning into Stochastic Optimization in Machine Learning." In 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh, pp. 1‑6. IEEE. doi: 10.1109/ECCE64574.2025.11013057.
Download Paper
Published in Nature Scientific Reports, 2025
This paper presents deep representation learning using layer-wise VICReg losses.
Recommended citation: Datta, J., Rabbi, R., Saha, P. et al. (2025). "Deep Representation Learning using Layer‑wise VICReg Losses." Nature Scientific Reports. 15, 27049.
Download Paper
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.