About me


Bhanuchander Udhayakumar

Data Science | Artificial Intelligence | Machine Learning | Programmer | RF Design | PC Gamer

Hi there, I am currently working as a Software Engineer in chennai. I love to develop full stack applications using Python, Java, Groovy, R and JavaScript. I am working on Data mining and AI / ML based projects mostly around Sequence models and Computer Vision. Also I work in devops side around docker, kubernetes for developing / releasing cloud natured full stack application (GCP, AWSand Azure). I like to use text editor sublime, also the IDEs PyCharm and IntelliJ.

During my academics, I have worked as an graduate intern for the Automotive Embedded Wireless based projects and designed lot of Patch Antennas and RF filters by familiarized with the RF Tools such as ADS and CST.

In my free time, I develop github pages from my random thoughts / ideas. As a master degree graduate in Wireless technology, I am continuing to contribute for the development of Antennas / RF Design based codes and content posts.





  • Higher Secondary Schools on Bio-Maths - 93.75 % - Devangar Higher Secondary School, Aruppukottai .


  • SSLC - 94.4 % - Devangar Higher Secondary School, Aruppukottai.



GitHub Hobby Projects


  • Published a open source python package patch_antenna in PyPI. Downloads

  • This package used to design a rectangular patch antenna for both inset feed and normal feed types. Gerber file genration support also included for the design for fabrication.


  • Patch Antenna Util - For Online design, 3D simulation and Gerber generation
  • For the purpose of ease availability and to reduce the need of big EDA Tools, Patch antenna design, 3D Simulation and Gerber support are combined in this one tool. Using this tool, one can design and get a gerber file of a Patch antenna in few seconds even with a awesome 3D view.

  • Naruto Eye Classifier using Deep Learning - Live
  • Online based deep learning classification hobby project, created by basic convolutional neural networks like CNN1, CNN2, CNN3, LeNet with locally trained data set for the purpose of understanding neural networks from scratch.