Scribd
Upload
89 views2 pages

Shankar Chavan: Data Scientist

Uploaded by

Satyajeet Rai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
89 views2 pages

Shankar Chavan: Data Scientist

Uploaded by

Satyajeet Rai
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Shankar chavan

Data Scientist
[email protected] 9921xxxxxx GitHub HackerRank Linkedin

Profile
Data Scientist with 1.5+ years of experience comprising Deep learning, Computer vision and Machine learning. Strong
willingness to exhibit my proficiency in Deep learning and Machine Learning Algorithms in professional environment.

Professional Experience
11/2021 – present
Banglore, India Jr. Data Scientist, iNeuron.ai
Processing, cleansing and verifying the integrity of data used for analysis. Doing
analysis and presenting results in a clear manner.
Working on building and optimizing the state-of-the-art Machine learning and Deep learning
models.
Working and learning on how to create and automate the project lifecycle with the help of
creating data pipelines.
04/2021 – 11/2021
Banglore, India Data Science Intern, iNeuron.ai

Projects
Aerial Image Mismatch, iNeuron.ai
The objective of this project is to detect the changes in the geographical co-ordinates in the different areas of the earth. We
used Instance segmentation to extract the mask and polygons of the objects present in the satellite images.
Decided to use U-net architecture and Detectron 2's Mask_RCNN_R_50_FPN_3x model for image segmentation.
There were 5 objects I have segmented using Detectron 2 library.
Mask Detection
The objective of the project is to determine whether a person has worn a mask or not.
Collected 500 + 500 (Mask, No mask) images to train the model.
Firstly, trained Faster RCNN model, but the FPS was very low (i.e. < 1 FPS) then used SSD with Mobilenet to get better
accuracy and achieved good FPS rate i.e. 5 FPS.
In this project I am detecting the person in the frame first. For this I have used pre-trained model – SSD-Mobilenet, then I am
detecting whether the person is wearing a mask or not.
For training the model used Nvidia Quadro P-4000 GPU.
Face Recognition, iNeuron.ai
The objective of this project is to use face recognition for door security.
Most doors are controlled by persons with the use of keys, security cards, password or pattern to open the door. The purpose of
building this kind of system for improvement of the door security of sensitive locations by using face detection and
recognition.
The Database used in the project was MonogDB.
Custom CNN model and transfer learning algorithm was used during this project.
Companies Data was used to create this project.

Brand Measure
The objective of this project is to give exact Marketing solution to a company.
We collected data in the form of Surveys. (Voice call data).
We then converted those recordings into text form and applied spelling corrector. Then
we used Key-word spotting to extract the meaning of the sentence.
Finally on the basis of the key words, we are generating BI report to show in which area/region company should more focus
on spending.
Skills
Programming languages : Machine learning algorithms :
Python Linear regression, Logistic regression, Decision tree,
Random forest, XGBoost
Deep learning algorithms :
ANN, CNN, RNN Computer Vision :
Image Classification, Object Detection, Image
Database Segmentation, OpenCV
MySQL, MongoDB, Cassandra Frameworks
Cloud Tensorflow, PyTorch
Heroku, AWS MLops
Docker, Kubernetes

Education
2015 – 2017 Master Degree, SPPU University
Pune, India
2012 – 2015 Bachelors Degree, SPPU University
Pune, India

Certificates
HackerRank Problem Solving Data Science (DLCVNLP)
iNeuron.ai

Achievements
Conducted 7 days workshop on Python Programming language in KIET college, Kakinada, Andhra Pradesh.
Successfully conducted career guidance drive multiple times in current organization as a community event.

You might also like