Hi! I'm Jillur Rahman Saurav, a PhD student at UT Arlington, working on large-scale generative medical imaging at Luber Lab under the supervision of Dr. Jacob Luber. I earned my degree in Computer Science from Shahjalal University of Science and Technology, Bangladesh.

My journey includes guidance from Professor M. Shahidur Rahman during my bachelor's thesis and working at pipilika.com, the first search engine in Bangladesh. Here, I was mentored by Dr. Farida Chowdhury and Dr. Ruhul Amin on Bangla language technology.

In this portfolio, you'll see my work and what I've learned. Excited to share it with you!

Interests
  • Deep Learning
  • Data Science
  • Natural Language Processing
  • Computer Vision
  • Computational Social Science
Education
  • PhD in Computer Science, (2021 - present)
    University of Texas at Arlington

  • B.Sc. (Engg.) in Computer Science, 2018
    Shahjalal University of Science & Technology

Experience
  • Software engineer, 2018-2021
    pipilika.com

Current Research

A SSIM Guided cGAN Architecture For Clinically Driven Generative Image Synthesis of Multiplexed Spatial Proteomics Channels

Jillur Rahman Saurav , Mohammad Sadegh Nasr, Paul Koomey, Michael Robben, Manfred Huber, Jon Weidanz, Bríd Ryan, Eytan Ruppin, Peng Jiang, and Jacob M. Luber
https://arxiv.org/abs/2205.10373

Clinically Relevant Latent Space Embedding of Cancer Histopathology Slides through Variational Autoencoder Based Image Compression

Mohammad Sadegh Nasr, Amir Hajighasemi, Paul Koomey, Parisa Boodaghi Malidarreh, Michael Robben, Jillur Rahman Saurav , Helen H. Shang, Manfred Huber, Jacob M. Luber
https://arxiv.org/abs/2303.13332

Publications

A Comparative Study of Language Dependent Gender Bias in the Online Newspapers of Conservative, Semi-Conservative and Western Countries

Jillur Rahman Saurav , Kezheng Xiang, Nikhil Deb and Mohammad Ruhul Amin HCII-2021 | HCI INTERNATIONAL 2021

Observing the Unobserved: A Newspaper Based Dengue Surveillance System for the Low-Income Regions of Bangladesh

Nazia Tasnim, Md. Istiak Hossain Shihab, Moqsadur Rahman, Jillur Rahman Saurav , Sheikh Rabiul Islam and Mohammad Ruhul Amin.
FLAIRS-34 | Florida Artificial Intelligence Research Society Conference 2021

Word Completion and Sequence Prediction in Bangla Language Using Trie and a Hybrid Approach of Sequential LSTM and N-gram
Soumik Sarker, Md. Ekramul Islam, Jillur Rahman Saurav, Md Mahadi Hasan Nahid ICAICT'20 | International Conference on Advanced Information and Communication Technology (ICAICT)

Query Expansion for Bangla Search Engine Pipilika
Md. Rezaul Islam, Jillur Rahman Saurav, Mahbubur Rub Talha, Farida Chowdhury TENSYMP'20 | IEEE Region 10 Symposium

End to End Parts of Speech Tagging and Named Entity Recognition in Bangla Language
Jillur Rahman Saurav, Summit Haque, Farida Chowdhury ICBSLP'19 | International Conference on Speech and Language Processing (ICBSLP) 2019

Bangla Speech Recognition for Voice Search
Jillur Rahman Saurav, Shakhawat Amin, Shafkat Kibria, M. Shahidur Rahman ICBSLP'18 | International Conference on Speech and Language Processing (ICBSLP) 2018
pdf

Projects

News aggregator Sercvice for Bangla Newspapers
Performed tasks includes designing architecture,developing generic parser, clustering news, categorizing news, summary extraction.
Technology: Django, Scrapy, Elasticsearch,Keras, Redis, Docker

Knowledge graph based on Bangladesh’s national portals data
Built a knowledge graph using the datafrom Bangladesh’s national portals by analyzing the text of the entities on the websites (5552 web portals) usingK-means clustering and Nearest Neighbour method.
Technology: Python, Elasticsearch, sklearn, Docker

Context-aware spell checker for Bangla language
Worked as a team member for developing Bk-tree, n-gram based spell checker for Bangla language.
Technology: Spring boot, Apache Solr

Query Analysis
Developed a deep-learning-based query classifier to understand search queries, implemented autocomplete and related search features.
Technology: Flask, Keras, Elasticsearch

Data Analytics for COVID-19 self-screening tool
Performed various statistical analysis on a Covid-19self-screening tool’s data (535,291 participents) comprising association analysis among symptoms, symptoms clustering, identifying danger zones, correlation with Covid cases.
Technology: Pandas, Sklearn, Matplotlib

Sentiment Analysis Dataset for Bangla language
Worked as a team member for developing the largest sentiment analysis dataset for Bangla language. The performed tasks included scraping data from various sources, cleaning data, and selecting data for annotation.
Technology: Scrapy, Pandas

Computer Vision Projects
Worked on several computer vision projects. Tasks included real-time object detection, reverse image search, Image captioning in the Bangla language
Technology: OpenCV, Keras