Kartik A. Shastrakar

A passionate Data Scientist specializing in machine learning, big data, and generative AI. With a strong foundation in Python, cloud platforms, and advanced analytics, I build forecasting models and predictive solutions that drive productivity and enhance decision-making. My experience spans diverse industries, from automotive to healthcare, where I’ve developed impactful projects like vehicle detection systems, video summarization tools, and medical image segmentation solutions.

Certified in deep learning, cloud computing, and data visualization, I combine technical expertise with effective communication to deliver actionable insights. With a B-Tech in Mechanical Engineering and a proven track record of mentoring aspiring data scientists, I’m driven to solve real-world problems and contribute to cutting-edge innovations. Let’s connect to shape a data-driven future together.

Vehicle Detection and Color Project

• Implemented car detection using Background Subtraction technique
• Developed system to extract cars from images/videos using foreground-background segmentation

VideoMash

• Created a video summarization tool that can process both local videos and YouTube URLs
• Implemented NLP algorithms to analyze subtitles and extract important segments
• Allows users to customize summary duration

Healthcare & AI Projects

• Developed Medical Image Segmentation using Monai Label
• Created MCQ Generators using LLM and Langchain
• Built Medical ChatBOT using LLM and Langchain

• Certificates Applied Data Science with Python Level 2 Foundational Generative AI Level 1
• AWS Educate Machine Learning - DeepRacer
• Tableau 10 for Data Scientists
• Deep Learning AWS Educate
• Introduction to Cloud Computing 101
• Deep Learning with TensorFlow

• G2- Member of the reviewer club
• NewtonX- Member

Projects

Vehicle-Detection-and-

Car Detection using Background Subtraction

Background subtraction is a simple yet effective technique to extract objects from an image/video. Consider a highway on which cars are moving, and you want to extract each car. One easy way can be that you take a picture of the highway with the cars (called foreground image) then you also have an image saved in which the highway does not contain any cars (background image) and then you subtract the background image from the foreground to get the segmented mask of the cars and then use that mask to extract the cars. The sample output is shown below.

VideoMash

Summarize your video to any duration.

VideoMash is a video summarizer where in you can upload any video from local system or can provide the YouTube URL for your video to summarize it into any duration which you provide as input. Summarization is done using NLP algorithms which is used to analyze the subtitles of the video to extract the important parts.

Other Project

• Medical Image Segmentation using Monai Label
• MCQ Generators using LLM and Langchain Medical ChatBOT using LLM and Langchain
• Exploratory Data Analysis on Automobile dataset
• Projects on Statistic, Linear and Logistic regression, naive Bayes,