I am a Computer Science PhD student at the University of California, Davis . My research domain is AI for Health and I am working under the supervision of Dr. Vladimir Filkov . My research interests include but not limited to Deep Learning, Natural Language Processing, Computer Vision, and Health Informatics.
When I am not working, I love to travel, read books, and play video games.
CGPA: 4.00/4.00
13 September 2024 — Present
Davis, California, USA
CGPA: 3.92/4.00
January 2019 - March 2023
Dhaka, Bangladesh
13 September 2024 — Present
22 October 2023 — 31 August 2024
January 2022 - February 2022
Raiyan Jahangir, Muhammad Nazrul Islam, Md. Shofiqul Islam, Md. Motaharul Islam
A Multilingual Handwriting Learning System for Visually Impaired People
Muhammad Nazrul Islam, Raiyan Jahangir, Nasif Shahriar Mohim, Md. Wasif-Ul-Islam, Anika Ashraf, Nafiz Imtiaz Khan, Mohammad Ratul Mahjabin, Abu Saleh Musa Miah, Jungpil Shin
Raiyan Jahangir, Vladimir Filkov
Mammo-Find: An LLM-based Multi-channel Tool for Recommending Public Mammogram Datasets
Raiyan Jahangir, Vladimir Filkov
Raiyan Jahangir, Tanjim Sakib, Riasat Haque, Mahedi Kamal
Proposing Novel Recurrent Neural Network Architectures for Infant Cry Detection in Domestic Context
Raiyan Jahangir, Nasif Shahriar Mohim, Nafiz Imtiaz Khan, Md Akhtaruzzaman, Muhammad Nazrul Islam
Development of a Smart Infant Monitoring System for Working Mothers
Raiyan Jahangir, Nasif Shahriar Mohim, Afnan Alauddin Mumu, Mahapara Naim, Anika Ashraf, Md Abu Syed, Muhammad Nazrul Islam
Brain Tumor Classification on MRI Images with Big Transfer and Vision Transformer: Comparative Study
Raiyan Jahangir, Tanjim Sakib, Md Fahmid-Ul-Alam Juboraj, Shejuti Binte Feroz, Md Munkaser Islam Sharar
Smart Infant Monitoring System
Stack: Raspberry Pi, Dart, Flutter, Firebase, Pulse Sensor, Temperature Sensor, GPS Module
An embedded system that measures vital health parameters (pulse rate and temperature) and tracks the real-time location of an infant. The system’s hardware includes a Raspberry Pi as the processor and other sensors to monitor the infant. The system has a set of RNN models deployed in it, which detects the infant’s cry and notifies the parents instantly. The software of the system is a mobile app developed using Flutter, which provides an easy-to-use interface for the parents. All the data exchanged between the hardware and software was managed and stored in Firebase cloud database.
Stack: Python, Tensorflow, Keras, Pytorch
A set of extended deep-learning frameworks constituting pretrained CNN models and stack classifiers to classify potato leaf diseases. These frameworks can be utilized in real-time monitoring systems to detect leaf diseases early and take necessary actions, considering the time and memory complexity.
Online Blood Bank Management System
Stack: PHP, Oracle, Xampp, HTML, CSS, Javascript
A Blood Bank Management System implemented using PHP and Oracle database for easing the process of blood donation and management during the COVID-19 pandemic. The system enables smooth and efficient management of blood bank operations, from donor registration to blood collection and distribution, with privacy and confidentiality.
Stack: Java, Jar, Swing
This system was developed for storing patient data, scheduling appointments, and managing doctor schedules. It utilized Java language to provide a secure and user-friendly platform for hospitals to manage their patient and doctor information. With the implementation of this system, the time and effort required for manual appointment scheduling and data management are significantly reduced, resulting in improved efficiency and a better patient experience.
Sustainability Forecasting from PRs in OSS Projects
Stack: Python, Pydrill
This study analyzes how pull request (PR) activity influences the sustainability of Apache Incubator projects. Results show that sustainable projects have higher merge ratios, fewer unresolved PRs, and faster resolution of core developer contributions. Using RNN models with PR-based features, the work highlights unresolved PRs and developer activity as key predictors of long-term project viability.