Innovative and self-driven fast learner and researcher with a curious mind and a passion in Machine Learning and Artificial Intelligence
I am an enthusiastic learner who’s interested in Machine Learning, Artificial Intelligence, and Data Science.
I am a self-motivated graduate with technical experience in computer science. In my journey through undergrad, I have successfully completed six lauded projects, three research publications, and one more research paper accepted for publication. I have presented research publications at national and international conferences. My future goals involve a deeper exploration of interdisciplinary technical skills which will enable me to create cross-functional solutions and products. I am passionate about working towards innovative technologies to help address the unmet needs in the field of science and healthcare. Being born to engineers, I have innate talent to look at things analytically and logically.
August 2020 - June 2021
I am product lead for a conversational AI assistant developed using rasa tech stack and data analysis using time-series prediction. Improved an in-production optimization algorithm which reduced the cycle-time of the automation process. Deployed question generation modules using Machine Learning models (GAN) and OpenAI GPT-3.
June 2019 - July 2020
Interactive earthquake locations plot. The project was implemented in Python. It consists of the dataset of earthquakes with the depth and magnitude, which after preprocessing was plotted in a 3d map in python. It also consists of a simple user interface which will show only those earthquakes with magnitude greater than the user input.
Aug 2018 - December 2018
Developed full stack website for a startup that sells and buys solar panel. Managed user interface framework and perform product analysis and development tasks. Used HTML5, CSS3, Bootstrap, JavaScript, jQuery and MongoDB.
June 2018 - July 2018
Developed computer vision modules using several libraries like Open CV for various other applications. Took an overview of the operations of various departments including Voice & Infrastructure Department (TELECOM), Client service & system management (CSSM), Network Department and Data Centre & Servers (SADC).
Following are projects that I had undertaken during my undergraduate.
Natural Language Processing
An Intelligent Chabot which helps in combating depression in students using cognitive behavioral therapy based on Recurrent Neural Network and Natural Language Processing. It analyzes their emotional quotient and provides them with consistent feedbacks.
Deep Learning
This project aims in classifying tumors from a dataset into Meningioma, Glioma and Pituitary neoplasms while accurately localizing lesions using Deep Convolutional Neural Networks. To reconstruct and denoise the malignant tumor images Autoencoders and Generative Adversarial Networks were deployed.
Machine Learning
The project based on an inductive-based reinforced learning model was implemented using Deep Learning approach. It helped to handle and manage material movement in assembly department. The detection of objects in real time was imposed and made efficient by a web API.
Internet of Things
This project used different sensors like PIR sensors, DHT sensors, Proximity sensors and IR Sensors to collect data using RaspberryPi, Arduino, NodeMCU, PiSmart Camera and Beacons. The Real Time Databases (Firebase, AWS), MQTT protocol and online platforms like Blynk were used to subscribe and publish collected data which was encrypted using cryptographic tools to make the information secure.
2nd International Workshop on Recent advances on Internet of Things: sTechnology and Application Approaches (IoT-T&A 2019)
2019 IEEE 16th India Council International Conference (INDICON)
8th IEEE International Conference on Healthcare Informatics (ICHI 2020)
Here are few of the technical blogs that I had tried to put my hands on.
GANs are a powerful class of machine learning frameworks that use two types of competing neural networks in adversarial environment. The neural networks are generative and discriminative model that both run in competition with each other during the training phase. GANs were developed as a solution against the disadvantage of misclassification by traditional neural networks upon the introduction of noise in the dataset.
IoU or Intersection over Union is a metric used to evaluate the accuracy of any trained model for a particular dataset. It is one of the common evaluation metrics used for semantic image segmentation. IoU is typically used for CNN object detectors which are basically algorithms that can have predicted bounding boxes for performance evaluation.
