Highly accurate and experienced Data Scientist with several years of experience using predictive modeling, Data processing and Data mining algorithms to solve Challenging Medical problems. Currently, most of my work is focused on medical image processing and I have implemented many image processing neural networks such as UNET, etc. (You can also check them in my GitHub). I have also done projects in field of Drug Discovery and implement RNN neural networks to Discover Chemical Structures. In addition, I have done a lot of work in the field of Build and Develop process management software’s And financial resource control. I am very interested in research work in the field of deep learning and intelligent monitoring systems and I have done a lot works in this fields which you can see in my projects section.
researching LSTM networks to generate inhibitor structures for SARS-CoV2 And Research on Unet architecture and its optimization with Metaheuristics.
Work in Salamat20 Startup as a Senior Image processing Expert. Implement OCR system to detect test sheet information, analyze and diagnose patient diseases. In general, the main activity of this startup is in the field of implementing analysis of blood test sheets and disease diagnosis, which they want to implement this system online and using OCR to identify test sheet information.
Work in the administrative and security department of IAU Karaj as Senior C# Developer. Implement Car Identification System, Student Violation Recorder Software and Improve university management systems.
Finantial Mangement Software
Create Fluctuation Control Panel
Create portfolio Panel
Create Price Expectation Panel
IRAN Stock Market Financial Management Software "Cadino"
Covid-19 main Protease Inhibitor
Implement Model Structure
Model Training & Sampling
Fine tuning for Specific Ligand Subsets
Fragment Growing Procedure
Molecular Structure Generation
Target specific Fine tuning
Low data Drug Design
Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short?term memory (LSTM) cells.
Medical Image Processing
Implement Network Structures
Data Augmentation for Training and Testing
Experiments and Results
The process of segmenting tumor from MRI image of a brain is one of the highly focused areas in the community of medical science as MRI is noninvasive imaging. Therefore, I decided to create Brain Tumor Segmentation Launch File that you can easily use the capabilities of this powerful tool. I am currently in the early stages of designing this Launch File and will be constantly updating these files to get to a usable version.
statistical Data Analysis
Implement Geographical Charts
Implement Bubble Geomap
Geographical Charts : Statistical analysis of cities' mortality distribution and implementation of results on geographic maps . Treemap : Analysis of statistical data on the dead, recovered and people with the Corona virus . Bubble Geomap : plot coronavirus Death cases spread on Geomap using Basemap .