R M Asif Amin

Me on a late-winter day in Dhaka.

I specialize in building ML systems, with a foundation in academic research as a student researcher. I transitioned to the industry after graduating, where I had the opportunity to apply ML at a national scale, for a substantial user base of over 50 million people. My most recent project facilitated safe and reliable access to the financial mainstream for the youth in my nation.

Driven by the goal of bridging the gap between academic research and practical applications, my unique offering is a blend of technical prowess and creative problem solving. I’ve found myself often connecting seemingly disparate dots to find elegant, minimal solutions to problems. I combine that with compassion towards my peers and thrive in a group setting.

Beyond tech, I dabble in music as a guitarist and songwriter, drawing inspiration from the intricate worlds of Science-Fiction and Techno-Thrillers.

news

Jul 20, 2023	First iteration of Document analysis project done. This will allow 7.5 million people aged 16-22 vital access to the financial system by just scanning their Birth Certificate. Ecstatic!!!
May 10, 2023	I’ve been promoted to the role of Assistant Lead Engineer, Data Science and Machine Learning! 🎉
Apr 20, 2023	POC done for first project involving computer vision- Document Information Extraction. Will allow users to signup with Birth Certificates instead of NIDs. Key Challenges- Birth Certificates not homogenous, are bilingual and not enough data.
Oct 27, 2022	Did some detective work! Identified organized fraud rings by analyzing transaction graphs of known offenders. Combined Neo4j Cypher queries and Louvain community detection algorithm 🕵🏼 Neo4j is a beautiful tool, Cypher is expressive!
Jun 11, 2022	Rebuilt our system for Automated training, batch inference and experiment tracking from scratch with Airflow, Mlflow and Postgres! Integrated event notification capability to Mail and Slack.

latest posts

Aug 30, 2023	Instant Preprocessing and Zero Disk Space Usage — Leveraging Streaming to Train Pytorch…

selected publications

Detection of Exoplanet Systems In Kepler Light Curves Using Adaptive Neuro-Fuzzy System

R M Asif Amin, A. Talha Khan, Z. T. Raisa, and 4 more authors

In 2018 International Conference on Intelligent Systems (IS), 2018

Abs HTML

The paper investigates the usability of fuzzy inference systems, namely ANFIS to assist in the detection of exoplanet transit events from time-series data of Flux intensity values from host stars. We use statistical properties of time curves, principal component analysis, and dynamic time warping (DTW) to extract features from time-series data. We propose the use of aggregated DTW distance to all positive training samples as a feature and show that it significantly increases performance if used along with statistical features and principal components. We propose that fuzzy methods can be used to classify exoplanet systems with a relatively low false positive rate and thus, can be used to filter out possible flux signatures for review by human experts.
Satellite Image Based Characterization for Monitoring Urbanization and Land Cover Change

Farhan Rahman Wasee, R M Asif Amin, Zareen Tasnim Raisa, and 3 more authors

International Journal of Networked and Distributed Computing, 2018

Abs HTML

This study focuses on the temporally evolving geo-environmental characteristics of Dhaka. Dhaka is located at the center of Bangladesh. In the last few decades, it has undergone rapid development in terms of infrastructure and economy. The land use pattern in Dhaka is not the same as it had been previously. The focus has been to analyze the changes that have occurred in Dhaka, which consists of six smaller cities inside it. Using remote sensing techniques and various satellite images, the objects are classified into different categories. Multi spectral characteristics and spectral response patterns are analyzed and studied. Using the information extracted across different decades, changes in land use have been derived. Furthermore, changes in different features e.g. built up, crops, water bodies etc. are analyzed and studied across years to factor out the zones that are experiencing recent urban growth. This generalized pattern of urban growth can be a valuable finding for urban planning and policy for the government of Bangladesh.