Souvik

Author: since 25 Jul, 2022 Article: 1 Claps: 0

An innate problem solver, once interested in VLSI field, drifted permanently into the field of Digital Technologies after realizing the true essence of solving real world problems and delivering business demands utilizing Data Science, Artificial Intelligence and Cloud Computing.
I try to lead others around me towards feeling the same :)

My profile reflects discipline and respect towards deadlines; delivering my responsibilities on time along with learning continuously for personal growth.

My interests and experience converge primarily in - Python (Programming Language), Data Science, Machine Learning, Deep Learning (TensorFlow), Cloud Computing (Microsoft Azure, AWS).

Other Skills - Programming Languages (C, C++), DBMS (SQL), Web Development (HTML, CSS, JavaScript)

At present, I am working as a Data Scientist in the AI Team of Advanta Development at Siemens.

Previously, I have interned at TCS (Digital Cadre); an opportunity that I got with my full-time offer of 'Systems Engineer' role at Tata Consultancy Services in Digital Profile. Utilized my problem solving and team working skills to develop a project named "Video-Bin: AI-Driven Video Search" aiming at solving a business problem statement while growing my hands-on knowledge in Data Science, AI/ML and Cloud Computing.

Apart from work experience, I with my team have published a research paper named "Arrhythmic Heartbeat Classification using Ensemble of Random Forest and Support Vector Machine" in the reputed IEEE Journal: "Transactions on Artificial Intelligence". We developed a completely new approach/model using niche Feature Extraction Techniques, Feature Selection Algorithms, Data Balancing, and the best Machine Learning algorithms applicable for the particular ECG dataset to retrieve an overall accuracy of 98.21%, which was better than the previously published state-of-the-art approach.

A long way to go, a lot to learn, working towards that everyday :)

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details