Hasan Kurban

Hasan Kurban

Computer & Data Scientist

About me

I am a Visiting Associate Professor in the Computer Science Department and Data Science Program at Indiana University, Bloomington, where I received my Ph.D. in Computer Science with a minor in Statistics under the supervision of Dr. M. M. Dalkilic in September 2017. My research focuses on AI and its applications. In particular, my latest research is in the new area of data-centric AI (DCAI): developing improved tools and applications primarily in materials science: nanoparticles and Lithium-ion batteries. Our most recent work, “Rapidly predicting Kohn-Sham total energy using data-centric AI”, is now available in Nature Scientific Reports. Our research on improving the venerable expectation-maximization called EM*, which has received an honorable mention paper award from IEEE International Conference on Data Science and Advanced Analytics (DSAA) in Montreal, Canada and the best poster award from IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT) Austin, Texas, is available as a CRAN R package, called DCEM.

Interests

  • Data Science, Data Mining, Machine Learning, Big Data, Applied AI (Materials Science)

Education

  • Ph.D., Computer Science, Sep 2017

    Indiana University Bloomington, IN, USA

Projects

FEATURED PUBLICATIONS

*

Applying Data-Centric AI to Improve a Single-cell RNA-seq Pipeline

Applying Data-Centric AI to Improve a Single-cell RNA-seq Pipeline

A paired index structure for k-Nearest Neighbor Search Algorithms

A paired index structure for k-Nearest Neighbor Search Algorithms

Cooperative Model Framework with Minimal Viable Theoretical Data

An Efficient and Novel Approach for Predicting Kohn-Sham Total Energy–Bootstrapping a Cooperative Model Framework with Minimal Viable Theoretical Data

ccImpute algorithm to impute dropout events in the single-cell RNA-seq data

ccImpute–an accurate and scalable consensus clustering based algorithm to impute dropout events in the single-cell RNA-seq data

Regeneration of Lithium-ion Battery Impedance

Regeneration of Lithium-ion Battery Impedance using a Novel Machine Learning Framework and Minimal Empirical Data

Data-centric AI

Data Expressiveness and Its Use in Data-centric AI

Machine Learning Systems for Multi-Atoms Structures

CH3NH3PbI3 Perovskite Nanoparticles

Rare-class Learning

Rare-class Learning over Mg-Doped ZnO Nanoparticles

Atom Type Prediction

Predicting Atom Types in Different Temperatures

R Package

Data Clustering with EM (DCEM) for Big Data, an R package

Structural Analysis

Density-functional tight-binding approach for the structural analysis and electronic structure of copper hydride metallic nanoparticles

Public Transportation Optimization

Using Data Analytics to Optimize Public Transportation on a College Campus

Iterative Machine Learning

A Novel Approach to Optimization of Iterative Machine Learning Algorithms

Clustering Big Data

An Expectation Maximization Algorithm for Big Data

Coral Reef Analysis

EMPLOYING SOFTWARE ENGINEERING PRINCIPLES TO CLIMATOLOGICAL DATASETS

Random Forest

Reduced random forest for big data using priority voting & dynamic data reduction

Studying the Milky Way

Studying the milky way galaxy using paraheap-k

Contact

  • 700 N Woodlawn Ave, Bloomington, IN 47408