Balaji Sai Charan Jalukuru

Data Scientist/Machine Learning Engineer with 3 years of experience developing Deep Learning models, Training systems and transforming data science prototypes to production-grade solutions. Consistently employs statistical methods and designs to yield real gains from model changes. Good team player and excellent work history with regards to work ethics, dependability, and willingness to go the extra mile.

* Python (DSA) * Tensorflow * Pytorch. * Fast.ai

*Java Script. *System Design * SQL * HADOOP

*Spark *GCP. * AWS

MLOPS(Machine Learning Operations)

Product Name : Event extraction for audio signals

Charan Jalukuru, 2022 . product name A Method and System for Extracting Cough Sequences with in an Audio Signal of Abnormal Cough filed October 30, 2022 (pending)

• Project Swaasa AI Platform for Healthcare, Abstract got selected as an e-poster for The Union World Conference on Lung Health 2022
• Semifinalists in Solve- MIT 2022 (Massachusetts Institute of Technology) challenge (ongoing).
• Awarded as High performance and High Growth Professional 3 times By zensark
• Finalist AEGIS GRAHAM BELL AWARD in the category Combat COVID19 with A.I. as a Machine learning Engineer

• Development and clinical validation of Swaasa AI platform for screening and prioritization of pulmonary TB (Mar 23,2023 Scientific reports)
• A Bi-Level Cascaded Ensemble Framework for Effective Disease Diagnosis publication date Dec 12, 2019 publication description (IEEE)
• Rule Extraction Algorithms on Type-2 Diabetes Data publication date Jun 1, 2019 publication description (IJRITEE)
• CoviScan: An accelerated COVID19 diagnosis using interpretable deep learning.(yet to be published)

Covid Classification Using Streamlit and GCP Jan 2023

• Developed a ML model for Covid Classficiation and Deployed in GCP Cluster Containing 2 Master and 8 Slave nodes.
• Creatred a Webapp linking ML model from GCP through Streamlit
• Technologies used : GCP, Streamlit, Pyspark , Python

Tuberculosis Detection Using Xrays Jan 2019

• Developed a CNN (convolutional neural network) for classification of TB using Xrays as input
• Augmented Data using different techniques like rotating increasing contrast etc obtained 79% accuracy on the Kaggle dataset

Artificial Neural Network Feb 2019

• Developed a basic ANN with 3 hidden layers and backpropagation in Python Obtained accuracy of 91% on combined cycle power plant dataset from University of California, Irvine's(UCI) ML Repository

Decision Trees Oct 2018

• Implemented a decision tree algorithm in Python to classify banknote authentication; used entropy and information gain to split attributes at each node.
• Obtained 80% accuracy on banknote authentication dataset from UCI ML Repository