Skills

R
python
sql
tableau
command line
Visual Studio
html
css
azure
excel
latex
Word
scikitlearn
tensorflow
numpy
plotly
pandas
Jupyter
dplyr
ggplot2
rmarkdown
ubuntu
rvest
tidyr
dplyr
dplyr
rmarkdown
ubuntu
rvest
tidyr
ggplot2
ggplot2
rmarkdown
ubuntu
rvest
tidyr

Experience

 
 
 
 
 

Research Assistant

The Pennsylvania State University

Aug 2017 – Present University Park

Responsibilities include:

  • Supported the development of a multi-criteria optimization model for selecting the type and number of sensors to improve the health and performance of complex engineering systems
  • Conducted a failure modes mechanisms and effects analysis (FMMEA) for 2 manufacturing systems to create a fault-sensor dependency matrix
  • Developed ordered clustering algorithm for sensor selection by ranking performance metrics
  • Currently developing a 3-d network model for optimal sensor placement on a digital twin to improve failure diagnostics and prognostics

Ongoing Projects:

  • SmartPathway: An accessible tool that aids students in planning their course schedule based on degree requirements, course offerings, and career interests. A part of this project work involves identifying the gap in technical skills between retail, healthcare and service industries and academia.
  • Demand chain optimization of perishable products. This project focuses on minimizing wastage of meal kits within retail stores.

Additional Responsibilities:

  • Maintaining undergraduate research website (Aug - 2018 to Jan -2020)
  • Mentoring undergraduate Capstone Projects such as

    • Occupancy Analytics: The main objective of this project was to use IoT technologies to develop a system of sensors and microcontrollers networked to persist data in a database, so that users can view the occupancy status using a GUI over the internet on any standard browser. Data accumulated was then be used to drive decisions, such as optimized scheduling of cleaning and sanitization services
    • Organ allocation/Distribution: The capstone project was to develop a model that takes in the list of donors and potential recipients and the distances between them to return the maximal cardinality matching with the least net distance between the donors and the recipients
    • System Health Monitoring: The project grouped were tasked with developing a system health index to outline the ideal conditions for running the testing process and provide quantitative predictions to aid in maintenance decisions
  • Mentoring summer projects

    • PPE- supply chain for Covid-19
    • Tracking the spread of covid-19 in Nursing Homes
    • Penn State ITS-UPS maintenance
  • Other Research projects mentored

    • Li-ion battery state of charge prediction

 
 
 
 
 

Graduate Research & Teaching Assistant

Penn State Smeal College of Business

Jan 2017 – May 2017 University Park
Responsibilities include:

  • Development of cases and exercises for an online professional master’s course in marketing analytics
  • Assist with creating lecture materials related to marketing analytics, assisting students with technical questions/issues, and general research support for various cases/projects related to marketing analytics
 
 
 
 
 

Consultant

Centre Tech Services

Dec 2016 – Jan 2017 State College
Responsibilities include:

  • Built and deployed a model to perform panel data analysis on customer data, assisting 48 students in career development and online learning
  • Automating Data Visualization process used ”ggplot2” package in R to generate report ready plots
  • Developing and deploying econometric models using ”plm” package in R for Panel Data Analysis
  • Automated the process of choosing between Fixed and Random effects model using Hausmann Test
 
 
 
 
 

CFD Analyst

Tata Consultancy Services

Sep 2013 – Jul 2015 Bengaluru

Responsibilities include:

  • Performed analysis on static oil slosh and engine pan designs to identify pressure differences between oil and atmosphere
  • Studied oil spills from different power trains to estimate the volume of oil spilled on critical components
  • Measured the oil volume flow for each degree of rotation within crankshafts
  • Calculated piston pressures and power losses in various engines through a crankcase breathing analysis
  • Analyzed the conjugate heat transfer of exhaust systems to predict manifold temperatures and the impacts of different regions’ temperatures
  • Led a flow analysis of the entire power train coolant system for different engine families, estimating pressure drop and flow rates across each component

Key Process Improvements:

  • Reduced analysis completion time by 70% by identifying a process bottleneck during a simulation, then architecting and implementing automation for the process
  • Lowered completion time for another analysis by 60% by producing an Excel script to automatically calculate the volume of oil flowing through crankshaft oil tubes

Professional Development

The Data Science Fellowship

The Data Incubator is a highly selective, intensive 7 week fellowship that prepares scientists and engineers with advanced degrees to work as data scientists and quants. It identifies those who already have the 90% difficult-to-learn skills and equips them with the last 10%: the tools and technology stack (e.g. machine learning algorithms and big-data ecosystems) that make them self-sufficient, productive contributors.
See certificate

Data Cleaning and Analysis

See certificate

The Analytics edge

This is a challenging class, which prepares its students for a career in data analytics using R. Several real world case studies of how analytics have been used to significantly improve a business or industry are reviewed. The case studies include Moneyball, eHarmony, the Framingham Heart Study, Twitter, IBM Watson, and Netflix. Through these examples and many more, students learn the following analytics methods: linear regression, logistic regression, trees, text analytics, clustering, visualization, and optimization. The contents of this course are essentially the same as those of the corresponding MIT class (The Analytics Edge). It is a challenging class, but it enables anyone who takes the course to apply analytics to real-world applications.
See certificate

Regression Models

Regression Models represents a both fundamental and foundational component of the series, and it presents the single most practical data analysis toolset. This course equips students with the fundamentals for the application and practice of regression. It also focused on providing the students with the following (1) an introduction to the key ideas behind working with data in a scientific way that will produce new and reproducible insight, (2) an introduction to the tools that will allow you to execute on a data analytic strategy, from raw data in a database to a completed report with interactive graphics, and (3) on giving you plenty of hands on practice so students can learn the techniques for themselves.

I finished the course in 2016. However, I paid for the certification in 2021 which accounts for the discrepancy in the date on the certificate

See certificate

Achievements

Publications

Identifying failure modes is an important task to improve the design and reliability of a product and can also serve as a key input in …

In a world of rapidly changing technologies, reliance on complex engineered systems has become substantial. Interactions associated …

The present work delineates a novel and scalable approach to characterization of defects in additively manufactured components. The …

Surface defects can be extremely detrimental to performance of fabricated components due to strain concentrations that are known to …

Understanding interactions between components is fundamental in the design of products. Design Structure Matrices (DSMs) are often used …