Gopal Chitalia

Gopal Chitalia

Mentor
5.0
(82 reviews)
US$20.00
For every 15 mins
227
Sessions/Jobs
ABOUT ME
Data Scientist | Machine Learning Engineer | Algorithmic Trading Developer
Data Scientist | Machine Learning Engineer | Algorithmic Trading Developer

I am Gopal Chitalia, a graduate student at Purdue University and working with Prof. Jan Anders Mansson on fault detection in motors using deep learning in a joint project with Wistron. Additionally, I'm working with Prof. Junjie Qin on transfer learning application using LLMs for optimizing power networks.

I have had the privilege of working at Center for Building Science Lab under the supervision of Prof. Vishal Garg. I have previously been a Research Assistant/Visiting ML Scholar at the Smart Grid Research Unit (SGRU) under Manisa Pipattanasomporn (Adjunct Faculty, Virginia Tech).

In addition to my academic pursuits, I have also contributed to the industry in the domains of Energy Efficiency, IoT, and Machine Learning. I have worked at ClevAir (Norway) as a Data Scientist and Growthworks.ai (CA, USA) as an ML Scientist/Energy Demand Expert.

My research work on predicting short/long-term energy prediction in office/residential buildings using machine learning is published in Applied Energy. The results improve the state-of-the-art results by 20-40%. I am also an active reviewer at Applied Energy. Furthermore, I have collaborated on a building-level dataset paper which has been published in Nature Scientific Data.

Previously, I have also worked with Prof. Jyotirmay Mathur at the Centre for Energy & Environment, MNIT Jaipur on Predicting time ahead heating/cooling energy demand HVAC systems. Moreover, as an independent research student, I also collaborated with Prof. Praveen Paruchuri of Machine Learning Lab, IIIT-H for Reinforcement Learning (RL) applications for controlling HVAC systems.

Hindi, English
Indiana (East) (-05:00)
Joined July 2020
EXPERTISE
5 years experience | 9 endorsements
I have worked on several projects ranging from Computer Vision, Natural Language Processing to Load forecasting. Some of my projects are:...
I have worked on several projects ranging from Computer Vision, Natural Language Processing to Load forecasting. Some of my projects are: 1.) Predicting short/long term energy prediction in office/residential buildings using machine learning. This work has also been published in the Applied Energy Journal [ Impact Factor: 10 ] which is the highest-rated journal in the field of Energy. 2.) Variational Auto-Encoder(VAE) based neural network for image generation. A comparative analysis of this architecture with various parameter tweaks was done on MNIST, CIFAR10, and CALTECH101 datasets. 3.) Sarcastic Hate Detection using a deep recurrent neural network.
5 years experience | 6 endorsements
I have done several projects in python including Web scraping through selenium/beautiful soup/requests library to all the different Datas...
I have done several projects in python including Web scraping through selenium/beautiful soup/requests library to all the different Datascience/Machine Learning/Reinforcement Learning projects.
2 years experience | 1 endorsement
I have been working on controlling HVAC systems for energy efficiency as well as maintaining thermal comfort using Reinforcement Learning...
I have been working on controlling HVAC systems for energy efficiency as well as maintaining thermal comfort using Reinforcement Learning. I have taken relevant courses and have collaborated with Prof. Praveen Paruchuri of Machine Learning Lab, IIIT-H for Reinforcement Learning applications for controlling HVAC systems.
1 year experience | 2 endorsements
2 years experience | 2 endorsements

REVIEWS FROM CLIENTS

5.0
(82 reviews)
Jordan Gurney
Jordan Gurney
August 2024
Very intelligent, he has a stubborness (in a good way) to fix a bug or an issue for his clients that he doesn't want to give up on, or just "sleep on" until the next morning. As a Dev myself, I'm exactly the same way, so I appreciate that kind of dedication and focus to see a challenge all the way through til it's solved!
Jeeva EP
Jeeva EP
August 2024
Gopal Chitalia was very prompt and helped me with the code for my visual analytics project. He did the task perfectly and on time. Will definitely recommend if you're looking for a mentor.
Mark Taylor
Mark Taylor
August 2024
great support
simongillett
simongillett
July 2024
python pipenv
Arnav Lohe
Arnav Lohe
July 2024
Gopal is very helpful - able to guide you how to think about, approach, and execute an ML problem. He was able to get me thinking in the right way about the problems I had and fill in gaps in knowledge and intuition as I needed. Will definitely be scheduling more sessions with him.
Jennifer Davis
Jennifer Davis
July 2024
excellent
Kenyon
Kenyon
June 2024
Gopal is a fantastic tutor who is well worth your time. I had an unconventional Python issue with a module Gopal was not familiar with. He helped me figure it out in less than one hour. Excellent support. He is quick to respond, skilled, and easy to learn from.
George
George
April 2024
Gopal is immensely helpful as a quant developer and with general programming tasks!
George
George
April 2024
Gopal is a highly knowledgeable and effective professional. I absolutely recommend him for your machine learning and data engineering needs. He has vast knowledge of financial markets for quant development too.
Jeffery Wilson
Jeffery Wilson
April 2024
Knew exactly what I needed to make my data science project perform better.
SOCIAL PRESENCE
GitHub
Smart-Bank
a smart contract that will perform most of the functions of a traditional bank written in solidity
1
0
SMAI
Python
0
0
Stack Overflow
432 Reputation
0
4
18
EMPLOYMENTS
Graduate Research Assistant
MD Lab, Purdue University
2024-09-01-Present
  • Research Guide: Prof. Jan Anders Mansson.
  • Working on transfer learning based approach for fault detection in induction motors (Project with Wistron).
  • Working on location selection analysis for establishing a manufacturing industry in USA using advanced technical cost models to analyze and compare various locations
Python
Django
Selenium
View more
Python
Django
Selenium
Machine learning
Deep Learning
TensorFlow
Performance Optimization
PyTorch
Pandas numpy
Large Language Models
View more
Machine Learning Engineer
Growthworks.ai
2022-04-01-2023-07-01
  • Managed a proof-of-concept project utilizing different data analytics, ML methods to do real-time electricity market prediction a...
  • Managed a proof-of-concept project utilizing different data analytics, ML methods to do real-time electricity market prediction at California-ISO region.
  • Implemented deep learning techniques, including auto encoders for better feature representation, achieving an accuracy improvement of 15%.
  • Utilized Apache Spark and Python to design and construct a scalable data pipeline, reducing data processing latency by 20%
Python
C++
SQL
View more
Python
C++
SQL
Bash
Pandas
Machine learning
Data Science
Deep Learning
Airflow
AWS
View more
Data Scientist
ClevAir
2020-03-01-2022-03-01
  • Led the implementation of advanced deep learning models, utilizing LSTM, transformers with attention to forecast HVAC and buildin...
  • Led the implementation of advanced deep learning models, utilizing LSTM, transformers with attention to forecast HVAC and building-level energy consumption, achieving 30% savings.
  • Designed an in house algorithm to automate sensor clustering, resulting in a 50% reduction in time and manual work for the delivery team.
  • Implemented automated fault detection algorithm for HVAC systems, resulting in 15% reduction in costs
Python
C++
Pandas
View more
Python
C++
Pandas
Machine learning
Data Visualization
Dash
Data science/machine learning
Fault Management
AWS
View more
PROJECTS
Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networksView Project
2020
This paper presents a robust short-term electrical load forecasting framework that can capture variations in building operation, regardle...
This paper presents a robust short-term electrical load forecasting framework that can capture variations in building operation, regardless of building type and location. Nine different hybrids of recurrent neural networks and clustering are explored. The test cases involve five commercial buildings of five different building types, i.e., academic, research laboratory, office, school and grocery store, located at five different locations in Bangkok-Thailand, Hyderabad-India, Virginia-USA, New York-USA, and Massachusetts-USA. Load forecasting results indicate that the deep learning algorithms implemented in this paper deliver 20–45% improvement in load forecasting performance as compared to the current state-of-the-art results for both hour-ahead and 24-ahead load forecasting. With respect to sensitivity analysis, it is found that: (i) the use of hybrid deep learning algorithms can take as less as one month of data to deliver satisfactory hour-ahead load prediction, (ii) similar to the clustering technique, 15-min resolution data, if available, delivers 30% improvement in hour-ahead load forecasting, and (iii) the formulated methods are found to be robust against weather forecasting errors. Lastly, the forecasting results across all five buildings validate the robustness of the proposed deep learning framework for the short-term building-level electrical load forecasting tasks.
Python
Machine learning
Web Scraping
View more
Python
Machine learning
Web Scraping
Data Science
Deep Learning
TensorFlow
Keras
View more
Variational Autoencoder (VAE)View Project
2018
The project aimed to construct a Variational Auto-Encoder(VAE) based neural network for image generation. A comparative analysis of this ...
The project aimed to construct a Variational Auto-Encoder(VAE) based neural network for image generation. A comparative analysis of this architecture with various parameter tweaks was done on MNIST, CIFAR10 and CALTECH101 dataset.
Computer Vision
Deep Learning
View more
Computer Vision
Deep Learning
View more