Since 2018, I have been learning in Vishwakarma Institute of Technology,Pune.I consider myself as a Skilled-IT Engineer with profound work experience in Programming, Neural Networks, CNN, Machine Learning,and automation technologies.Developed projects using CNN algorithm for Mute and Blind people and Research Paper for the same is about to get accepted by ICMLIP headed by Springer Foundations. Seeking to leverage the first-hand Experience with Machine Learning and Neural Networks Technology and integrated systems to become the LEAD ML Developer at a Young Age.
I am a keen Tech Enthusiast aimed at evolving, growing myself as a person and to make myself better at what I'm doing right now. Aparts, I'm a very passionate individual when it comes to follow my deep-rooted beliefs. Building the models, right from scratch and generating accuracy is what drives me.
I've completed my,
XII Boards in CBSE from Macro Vision Academy, during the period of 2016-2018 with a proficient score of 84% Aggregate and MATHS SCORE- 90/100 . .
Before this, I've completed my X CBSE BOARDS from Christ Jyoti Sr. Sec School SATNA, during the period of 2012 - 2016 with an aggregate pointer of 9.6/10 CGPA.
When I’m not in front of a computer I enjoy travelling or meeting new people to grow out my soft skills. Aparts, I'm a profound Blog writer on MEDIUMS PLATFORM. Recently, I've started my Youtube Channel as well where I'll be giving the explanation of the projects which I'll be accomplishing. Aparts,Competitive Programming Do excites me as well.
I have been fortunate to learn and having new experiences in general.
Working in the field of AI and ML with Computer Vision.
Carried the responsibility of Developing and Deploying the ML model on miniaturised edge-end device.
Explored the domain of Facial Sentimental Analysis with Deep Learning
Research Intern at
Carnegie Mellon UniversityExploring the field of Computer Vision with Deep Learning.
Performing Object Detection on a molecular level.
Utilizing Transformer Network for detecting cellular objects on Cryo-EM data.
Deep Learning Intern at
Indian Institute of Technology, KharagpurExplored the field of Natural Language Processing with Hybrid Neural Network Architecture
Developed a ML model with 90% accuracy and with Average Weighted F1 score as 0.87.
Have surpassed several research papers Achievements.
Construced an Analytical Study to avoid onsite Construction Accidents
Directing smooth and interactive conduction of Technical Workshops.
Accelerating Hands-on-Learning experience
SUMMER INTERN focussed on generating Solutions to the challenges provided in Technical vivid Domains
Conducting technical workshops in the field of Machine Learning, Deep Learning and Neural Networks
Mentoring Students with Industry Based ML and DL Applications
Coordinatng cross-domain Responsibilities
Head Incharge of creating On-field Campus Marketing Strategy for the Kshitij Event.
Was leading with the role of Leads Generation via campus table tents,social media promotions and developed Marketing Strategy.
Developed an Analysis model for accelerating drive in sales
Used several correlation and Heatmap plotting techniques to carry out analysis
Learnt to deal with Data Preprocessing Schemes
Awarded as "Best Mind of Satna" by Rotary Club, Satna
1st Place - Intra School Science Project Competition
SIGN TO Speech Conversion for Mute People: The purpose of this project is to contribute in recognizing American sign languages(ASL) to the field of automatic sign language recognition with maximum efficiency.This model basically focuses on the real time static gestures which are collected from Laptop Webcam and then convert into corresponding Sign Language with the help of voice modules.With the design of a good classifier it can classify the input static gestures with high accuracy. The system trained CNNs for the classification of twenty five(5) alphabets using 150-200 images. The system has trained the classifier with different parameter configurations and tabulated the results. Compared to previous literature the proposed work attained an efficiency of 99.35% for our classifier .The result shows that accuracy improves as we include more data from different subjects during training.
Read MoreReal Time Object Detection deals with capturing real-time frames and will send it to a laptop based Networked Server where all the computations take place.The Laptop Based Server will be using a pre-trained SSD detection model trained on COCO DATASETS. It will then test and the output class will get detected with an accuracy metrics. The voice modules will generate the class of the object in a converted voice notes which will then be sent to the blind victims for their assistance. Along with the object detection , we have used an alert system where approximate distance will get calculated. If that Blind Person is very close to the frame or is far away at a safer place , it will generate voice-based outputs along with distance units.
Read More