Hüseyin Kaya
Verified Expert in Engineering
Computational Science Engineer and Developer
Hüseyin is a math major with a master of science and a PhD in computational science and engineering. He has extensive and diverse experience in academia and industry like time series alignment in DNA mutation analysis, direct numerical solution of differential equations, global sensitivity analysis, machine learning in remote sensing images, and reinforcement learning in auto-scaling cloud applications.
Portfolio
Experience
Availability
Preferred Environment
Visual Studio Code (VS Code), Python 3, MacOS, Terminal, Linux, MATLAB
The most amazing...
...moment of my career is when I turned one of my research topics into a Eurostars project and built a multi-national consortium from scratch.
Work Experience
Solution Architect
Payten
- Transformed an idea into a full Eurostars project proposal and built an international consortium of six companies from Turkey and Spain.
- Designed and implemented a reinforcement learning-based autoscaling algorithm.
- Explained the behavior of a long-standing erroneous multitier service via a queue theory-based model.
- Designed time series forecasting models to predict the number of transactions passing through our payment gateway.
- Completed a computer vision-based project about classifying structural/non-structural damages of buildings using post-earthquake images. Designed all the experiments and wrote the TensorFlow programs to execute on a high-performance computing center.
Visiting Researcher
Purdue University
- Implemented an O(n) method for calculating the electrostatic potential of molecular systems.
- Implemented a time-integration solver for molecular dynamics simulation under Coulomb's electrostatic forces.
- Adapted a sparse version of the multi-level summation method for gravitational n-body simulations.
Senior Linux System Administrator
Asseco SEE
- Wrote scripts to maintain the lifecycle of critical logs of the payment gateway system.
- Implemented Ansible and Bash scripts to automate the version update process of the payment gateway system.
- Implemented FreeIPA and Satellite systems to improve user and Linux package management processes.
Project Manager
Iontek
- Designed and implemented a time series classification method suitable for DNA sequencing data to detect mutations in BRCA1 and BRCA2 genes, which are believed to be responsible for breast cancer.
- Prepared and supervised a project to design and manufacture a DNA isolation device with PCR preparation capability.
- Developed and maintained an internal document management system to keep track of all lab and quality control systems based on semantic MediaWiki and custom templates.
Experience
Auto-scaling on Container Platforms
The end-product is designed as a Kubernetes operator to be listed in Kubernetes market places.
Developing an Expert System for Screening and Diagnosis in Familial Cancers
At the core of the project, there is a time series classification algorithm running that takes a query time series and returns the locations of the possible mutations by first aligning the query with the reference time series in the database.
The MATLAB implementation is wrapped and used as a back end for PHP and later provided as a free service in the company's customer portal.
High Performance Bioinformatics Platform
The end product takes multiple DNA sequences—all strings of A, C, G, and T—and returns a primer that matches only a subset of sequences. The implementation is done on the NVIDIA CUDA platform to gain more performance on speed.
I integrated the core CUDA implementation with a Java Swing GUI. The product is used in-house by product developers.
Time Series Classification Utility
https://github.com/hkayabilisim/TSCUThe utility combines the alignment methods with classification methods such as K-NN, linear and nonlinear SVM. I primarily used this utility in Iontek Inc. to classify time series originating from DNA sequencing.
Time Series Forecasting in Payment Gateways
Feature Selection Based on High Dimensional Model Representation for Hyperspectral Images
https://ieeexplore.ieee.org/abstract/document/7886329The selection procedure is based on measuring the effect of each band in classification performance. And this is achieved by using a global sensitivity analysis method called High Dimensional Model Representation.
TomorrowVille Damage Assessment Simulation
https://saltonline.org/en/2565/exhibition-tomorrows-earthquake-resilient-cities?agendaA Structural Damage Ranking Using ConvNeXt for Post-earthquake Image Classification
https://huggingface.co/spaces/hkayabilisim/deprem-hasar-tespitEducation
PhD in Computational Science and Engineering
Istanbul Technical University - Istanbul, Turkey
Master's Degree in Computational Science and Engineering
Istanbul Technical University - Istanbul, Turkey
Bachelor's Degree in Mathematics
Middle East Technical University - Ankara, Turkey
Skills
Languages
Python, Python 3, PHP, C, Bash, Go, Java
Tools
Terminal, MATLAB, Ansible, Dynatrace, Eureka, Jupyter, Mathematica
Paradigms
Data Science, Dynamic Programming
Platforms
Linux, MacOS, CentOS, Red Hat Linux, Visual Studio Code (VS Code), NVIDIA CUDA, Kubernetes, Jupyter Notebook, Amazon Web Services (AWS)
Other
Machine Learning, Scaling, High Dimensional Model Representation (HDMR), Feature Selection, Time Series, Classification, Numerical Analysis, Reinforcement Learning, Particle Systems, Simulations, Artificial Intelligence (AI), Computer Vision, Remote Sensing, Genetic Algorithms, Sensitivity Analysis, Time Series Analysis, Data Engineering, Geospatial Data, Deep Learning, Differential Equations, Scientific Computing, DNA Sequencing, Red Hat SpaceWalk, FreeIPA, SSH, Forecasting, Sequence Alignment, K-nearest Neighbors (KNN), Support Vector Machines (SVM), Amazon Forecast, Autoregressive Integrated Moving Average (ARIMA), Exponential Smoothing, Facebook, Transactions, Satellite Images, Hyperspectral Imaging (HSI), Raster Images, Data Mining, Horizon 2020, IT Project Management, Digital Payments, Commerce, Conda, Mathematics, Solara, Front-end, Back-end, Geospatial Analytics, Convolutional Neural Networks (CNN), Image Processing
Libraries/APIs
TensorFlow, PyTorch, Pandas, Matplotlib, Keras, Fast.ai
Frameworks
Swing
Storage
Auto-scaling Cloud Infrastructure
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
Share your needs
Choose your talent
Start your risk-free talent trial
Top talent is in high demand.
Start hiring