diff --git a/README.md b/README.md index 2df8431d5..a1a2d03fa 100644 --- a/README.md +++ b/README.md @@ -1,72 +1,4 @@ -# Personal Portfolio ⚡️ -> A clean, beautiful, responsive portfolio template for Software Developers! +# Personal Portfolio +This Personal Portfolio template was forked from https://github.com/varadbhogayata/varadbhogayata.github.io -> https://varadbhogayata.github.io - -![GitHub stars](https://img.shields.io/github/stars/varadbhogayata/varadbhogayata.github.io) -![GitHub forks](https://img.shields.io/github/forks/varadbhogayata/varadbhogayata.github.io) -[![Maintenance](https://img.shields.io/badge/maintained-yes-green.svg)](https://github.com/varadbhogayata/varadbhogayata.github.io/commits/master) -[![Website shields.io](https://img.shields.io/badge/website-up-yellow)](http://varadbhogayata.github.io/) -[![Ask Me Anything !](https://img.shields.io/badge/ask%20me-linkedin-1abc9c.svg)](https://www.linkedin.com/in/varadbhogayata/) -[![License](http://img.shields.io/:license-mit-blue.svg?style=flat-square)](http://badges.mit-license.org) - -### Website Preview -

- - - - -

- -:star: Star me on GitHub — it helps! - -## Features 📋 -⚡️ Fully Responsive\ -⚡️ Valid HTML5 & CSS3\ -⚡️ Typing animation using `Typed.js`\ -⚡️ Easy to modify - -## Installation & Deployment 📦 -- Clone the repository and modify the content of index.html according to your requirement. -- Add or remove images from `varadbhogayata.github.io/assets/img/` directory as per your requirement. -- I highly recommend to use [Github Pages](https://create-react-app.dev/docs/deployment/#github-pages) to deploy the website the EASIEST WAY. -- To deploy your website, first you need to create github repository with name `.github.io`. Please don't give any other name. -- Push the generated code to the `master` branch of this repository. -- NOTE: Make sure to set `analyticsId` from your Google Analytics account inside the Google Analytics script tag, if you want to use your own Google Analytics account. - -## Sections 📚 -✔️ About me\ -✔️ Experience\ -✔️ Projects \ -✔️ Skills \ -✔️ Education\ -✔️ Contact Info\ -✔️ Resume - -To view a live example, **[click here](https://varadbhogayata.github.io/)** - -## Tools Used 🛠️ -* [GitHub Pages](https://create-react-app.dev/docs/deployment/#github-pages) - To host my static website (HTML, CSS, JS). -* [Materialize](https://materializecss.com/) - A CSS framework to get Google's Material Design components. -* [Typed.js](https://mattboldt.com/demos/typed-js/) - JavaScript Library - -## Contributing 💡 -#### Step 1 - -- **Option 1** - - 🍴 Fork this repo! - -- **Option 2** - - 👯 Clone this repo to your local machine. - - -#### Step 2 - -- **Build your code** 🔨🔨🔨 - -#### Step 3 - -- 🔃 Create a new pull request. - -## License 📄 -This project is licensed under the MIT License - see the [LICENSE.md](./LICENSE) file for details. +To view a live example: https://ananyadeoghare.github.io diff --git a/assets/img/Accenture-logo.png b/assets/img/Accenture-logo.png new file mode 100644 index 000000000..3e762b530 Binary files /dev/null and b/assets/img/Accenture-logo.png differ diff --git a/assets/img/C.png b/assets/img/C.png new file mode 100644 index 000000000..887c98231 Binary files /dev/null and b/assets/img/C.png differ diff --git a/assets/img/IISc_Master_Seal_Black.jpg b/assets/img/IISc_Master_Seal_Black.jpg new file mode 100644 index 000000000..824b4f5e5 Binary files /dev/null and b/assets/img/IISc_Master_Seal_Black.jpg differ diff --git a/assets/img/POSTER.ppt b/assets/img/POSTER.ppt new file mode 100644 index 000000000..b3ffa6657 Binary files /dev/null and b/assets/img/POSTER.ppt differ diff --git a/assets/img/R.jpeg b/assets/img/R.jpeg new file mode 100644 index 000000000..1717f6602 Binary files /dev/null and b/assets/img/R.jpeg differ diff --git a/assets/img/Screenshot 2022-12-21 at 14.20.15.png b/assets/img/Screenshot 2022-12-21 at 14.20.15.png new file mode 100644 index 000000000..5bc735ab0 Binary files /dev/null and b/assets/img/Screenshot 2022-12-21 at 14.20.15.png differ diff --git a/assets/img/VMG.png b/assets/img/VMG.png new file mode 100644 index 000000000..03498a082 Binary files /dev/null and b/assets/img/VMG.png differ diff --git a/assets/img/Vidmob.jpeg b/assets/img/Vidmob.jpeg new file mode 100644 index 000000000..c878feadf Binary files /dev/null and b/assets/img/Vidmob.jpeg differ diff --git a/assets/img/Vidmob.png b/assets/img/Vidmob.png new file mode 100644 index 000000000..4aae5aeda Binary files /dev/null and b/assets/img/Vidmob.png differ diff --git a/assets/img/arduino.jpeg b/assets/img/arduino.jpeg new file mode 100644 index 000000000..764847ae7 Binary files /dev/null and b/assets/img/arduino.jpeg differ diff --git a/assets/img/arm.png b/assets/img/arm.png new file mode 100644 index 000000000..1d01c1512 Binary files /dev/null and b/assets/img/arm.png differ diff --git a/assets/img/colab.png b/assets/img/colab.png new file mode 100644 index 000000000..6ef1c6ccd Binary files /dev/null and b/assets/img/colab.png differ diff --git a/assets/img/cuda.png b/assets/img/cuda.png new file mode 100644 index 000000000..a3ed01c2b Binary files /dev/null and b/assets/img/cuda.png differ diff --git a/assets/img/detecting_HR.jpeg b/assets/img/detecting_HR.jpeg new file mode 100644 index 000000000..64ce19184 Binary files /dev/null and b/assets/img/detecting_HR.jpeg differ diff --git a/assets/img/eclipse.png b/assets/img/eclipse.png new file mode 100644 index 000000000..cb5842550 Binary files /dev/null and b/assets/img/eclipse.png differ diff --git a/assets/img/eeg.jpeg b/assets/img/eeg.jpeg new file mode 100644 index 000000000..a46a63194 Binary files /dev/null and b/assets/img/eeg.jpeg differ diff --git a/assets/img/firebird.jpeg b/assets/img/firebird.jpeg new file mode 100644 index 000000000..d29a74b4a Binary files /dev/null and b/assets/img/firebird.jpeg differ diff --git a/assets/img/googlehome.jpeg b/assets/img/googlehome.jpeg new file mode 100644 index 000000000..91e836fb7 Binary files /dev/null and b/assets/img/googlehome.jpeg differ diff --git a/assets/img/hardware.png b/assets/img/hardware.png new file mode 100644 index 000000000..b71358c1f Binary files /dev/null and b/assets/img/hardware.png differ diff --git a/assets/img/informatica.png b/assets/img/informatica.png new file mode 100644 index 000000000..f7ec66a37 Binary files /dev/null and b/assets/img/informatica.png differ diff --git a/assets/img/matlab.png b/assets/img/matlab.png new file mode 100644 index 000000000..713fc89ea Binary files /dev/null and b/assets/img/matlab.png differ diff --git a/assets/img/me.jpeg b/assets/img/me.jpeg new file mode 100644 index 000000000..e517283a7 Binary files /dev/null and b/assets/img/me.jpeg differ diff --git a/assets/img/motivation.png b/assets/img/motivation.png new file mode 100644 index 000000000..064acebf5 Binary files /dev/null and b/assets/img/motivation.png differ diff --git a/assets/img/qlik.png b/assets/img/qlik.png new file mode 100644 index 000000000..63cae15dc Binary files /dev/null and b/assets/img/qlik.png differ diff --git a/assets/img/qs.png b/assets/img/qs.png new file mode 100644 index 000000000..c7f741ecc Binary files /dev/null and b/assets/img/qs.png differ diff --git a/assets/img/rpi.png b/assets/img/rpi.png new file mode 100644 index 000000000..4cedbcc85 Binary files /dev/null and b/assets/img/rpi.png differ diff --git a/assets/img/rppg.png b/assets/img/rppg.png new file mode 100644 index 000000000..d82c033ad Binary files /dev/null and b/assets/img/rppg.png differ diff --git a/assets/img/scipy.png b/assets/img/scipy.png new file mode 100644 index 000000000..47e0db6f1 Binary files /dev/null and b/assets/img/scipy.png differ diff --git a/assets/img/tableau.png b/assets/img/tableau.png new file mode 100644 index 000000000..78f721ea8 Binary files /dev/null and b/assets/img/tableau.png differ diff --git a/assets/img/uclalogo.png b/assets/img/uclalogo.png new file mode 100644 index 000000000..713a48220 Binary files /dev/null and b/assets/img/uclalogo.png differ diff --git a/assets/resume/Ananya_Deoghare_Resume.pdf b/assets/resume/Ananya_Deoghare_Resume.pdf new file mode 100644 index 000000000..d21faddfb Binary files /dev/null and b/assets/resume/Ananya_Deoghare_Resume.pdf differ diff --git a/assets/resume/BE275_Project_.pdf b/assets/resume/BE275_Project_.pdf new file mode 100644 index 000000000..144db3525 Binary files /dev/null and b/assets/resume/BE275_Project_.pdf differ diff --git a/assets/resume/ECE239AS_Project.pdf b/assets/resume/ECE239AS_Project.pdf new file mode 100644 index 000000000..799af9f9d Binary files /dev/null and b/assets/resume/ECE239AS_Project.pdf differ diff --git a/assets/resume/ECE247_project_report.pdf b/assets/resume/ECE247_project_report.pdf new file mode 100644 index 000000000..f327426b1 Binary files /dev/null and b/assets/resume/ECE247_project_report.pdf differ diff --git a/assets/resume/report_final.pdf b/assets/resume/report_final.pdf new file mode 100644 index 000000000..fb23c5fb4 Binary files /dev/null and b/assets/resume/report_final.pdf differ diff --git a/examples/filename.txt b/examples/filename.txt new file mode 100644 index 000000000..8cde7829c --- /dev/null +++ b/examples/filename.txt @@ -0,0 +1 @@ +print("hello world") diff --git a/examples/preview.JPG b/examples/preview.JPG deleted file mode 100644 index 2386abe1f..000000000 Binary files a/examples/preview.JPG and /dev/null differ diff --git a/examples/preview.gif b/examples/preview.gif index c4117bb0b..c74c88401 100644 Binary files a/examples/preview.gif and b/examples/preview.gif differ diff --git a/examples/preview.jpg b/examples/preview.jpg new file mode 100644 index 000000000..28e50cfbc Binary files /dev/null and b/examples/preview.jpg differ diff --git a/examples/preview.png b/examples/preview.png new file mode 100644 index 000000000..0af4e51a6 Binary files /dev/null and b/examples/preview.png differ diff --git a/index.html b/index.html index 184162f13..4f9f59e3d 100644 --- a/index.html +++ b/index.html @@ -20,7 +20,7 @@ - Varad Bhogayata | Software Developer + Ananya Deoghare @@ -35,20 +35,15 @@ - - - - - - + + + + + + - - - - - - - + + @@ -85,7 +80,7 @@ @@ -147,7 +142,7 @@ - Resume @@ -158,8 +153,8 @@
- Varad - BhogayataSoftware Developer + Ananya + DeoghareMachine Learning Engineer
@@ -193,8 +188,8 @@ class="mdi-content-mail small">Contact
  • - Resume
    • @@ -209,28 +204,27 @@
    -

    Hi, I'm Varad Bhogayata.

    +

    Hi, I'm Ananya Deoghare.

    A
    Self-driven, quick starter, passionate programmer with a curious mind who enjoys solving a complex and challenging real-world problems.
    +
    Algorithm Engineer
    +
      +
    • + Developed a robust ad-tech platform leveraging Python and machine learning pipelines to analyze creative performance, enabling scalable A/B testing and real-time feedback loops. +
      • +
    • + Designed and optimized an automated simulation testing suite using Cython, achieving 95% fidelity with production environments and significantly improving test coverage and computational efficiency. +
      • +
    • + Engineered high-impact feature sets using domain-specific aggregations, temporal windows, statistical summaries, and one-hot encoding—improving model generalization and reducing overfitting. +
      • +
    • + Implemented advanced supervised learning models (e.g., Gradient Boosting Machines, Logistic Regression), using Bayesian optimization and cross-validation to fine-tune hyperparameters and boost ranking accuracy. +
      • +
    • + Conducted in-depth feature importance analysis (e.g., SHAP, permutation importance), removing low-signal features and reducing model complexity by 30% without sacrificing performance. +
      • +
    • + Delivered production-ready machine learning pipelines in collaboration with product and data engineering teams, improving data-driven decision-making speed by 10% and enhancing metric tracking for advertiser engagement. +
      • +
    • + System Observability & Drift Detection: Established automated monitoring frameworks to track model performance and data drift in real-time, triggering proactive retraining cycles that maintained ranking precision amidst shifting market trends. +
      • +
    • + Advanced Experimentation Frameworks: Developed a custom multi-armed bandit (MAB) framework to optimize creative selection, outperforming static A/B testing by 15% in conversion rate lift while minimizing exploration regret. +
      • +
    • + Low-Latency Inference Optimization: Refined production inference logic to achieve sub-100ms latency for real-time bidding requests, ensuring the ranking system met strict SLA requirements for high-frequency ad-tech environments. +
      • +
    • + Technical Leadership & Architecture: Led cross-functional design reviews for the next-generation ranking engine, aligning data science objectives with infrastructure constraints to support a 50% increase in concurrent user traffic. +
      • +
    • + Tools & Techniques: Python, Scikit-learn, Cython, Redshift, MySQL, Feature Engineering, SHAP, A/B Testing, Cross-Validation, GBM, Data Pipelines, AdTech, Ranking Models +
      • +
    + +
    +
    + June 2023 - Present | CA +
    +
    + -
    +
    - Zhiffy logo + Mtag logo +
    +

    - Zhiffy + UCLA +

    -
    Software Engineer
    +
    Teaching Associate
    • - Developed and managed the backend of an e-commerce platform using Flask, MongoDB, and AWS. -
      • -
    • - Worked on three web applications targeting customers, selling vendors, and admin users; built 50+ RESTful APIs with functionalities -such as login/sign up, view a product, add a product to cart, checkout the order, etc. -
      • -
    • Improved the response time by 20% by refactoring the codebase and changing database design and queries.
      • -
    • Added a bulk upload feature which reduced the manual work of adding products into a database.
      • + TA for the course: +
        +
      • Food Politics in the World of Arts and Culture/Dance Department
        • +
      • Mathematics for Life Scientists in the Life Sciences Department.
        • +
      • Introduction to Archaeology in the Anthropology Department
        • +
      +
    • Evaluated student work and constructively guiding revisions and instructional assistance to students.
      • +
    • Worked with a highly diverse student population and adapting and improving practices based on career development experiences.
      • +
    • Organized and oversaw 2 discussion sections and 2 lab sessions for a course of 30 students, where I guidedstudents to get familiar with mathematical modeling in Python.
      • +
    • Assisted faculty with preparations for the course, including grading and providing feedback on student assignments.
      • +
    • Helped students get familiar with the course work and teach them.
    • - Tools: Python, Flask, MongoDB + Tools: Python, Verbal Communication, Active Listening Skills, Patience
    - July 2020 - Nov 2020 | Hyderabad, India + March 2022 - June 2023 | Los Angeles, USA
    - + + +
    - Meditab logo + Vidmob logo

    - Meditab + Vidmob

    -
    Programmer Analyst
    +
    Machine Learning Intern
      -
    • - Customized a tree-based optimization algorithm that separates drugs into distinct groups to maximize the concurrent execution of drug -dispenser robots; improved an optimization algorithm that reduced the cycle-time of the automation process by 25%. -
      • -
    • - Devised a customized recursion algorithm to extend the functionality of the current environment to a multi-robot and multi-system -environment -
      • -
    • - Built a modular video analytics app using Flask, OpenCV that tracks the location of each human in a multi-camera environment; -utilized perspective transformation, object detection, and object tracking to find the location of a human. -
      • -
    • Increased the speed of the video analytics app by 20% by using a customized YOLOv3 algorithm to perform object detection and - DeepSORT algorithm for multi-object tracking.
      • -
    • - Tools: Python, Flask, OpenCV, Keras, Tensorflow, PyTorch -
      • +
    • + Spearheaded the full-stack development of an ad-tech analytics platform, integrating end-to-end machine learning pipelines in Python for real-time evaluation of ad creative performance. +
      • +
    • + Designed and implemented deep learning models for computer vision tasks—such as object detection and image scoring—resulting in a 25% increase in the accuracy of ad engagement classification. +
      • +
    • + Applied supervised learning and statistical modeling techniques to predict user interaction rates, followed by rigorous A/B testing and performance benchmarking, which led to a 5% boost in overall client satisfaction. +
      • +
    • + Engineered modular, reusable components for data preprocessing, model training, and evaluation, reducing pipeline execution time and improving development efficiency across ML iterations. +
      • +
    • + Collaborated with cross-functional teams (data, product, and engineering) to deploy scalable AI-driven insights into production, contributing to a 15% increase in team efficiency and enhanced business impact through predictive analytics. +
      • +
    • + Tools & Techniques: Python, PyTorch, Scikit-learn, Computer Vision, Deep Learning, MySQL, React, Git, SQL, A/B Testing, Feature Engineering, Full-stack Development +
    - Dec 2018 - July 2019 | Ahmedabad, India + June 2022 - September 2022 | New York, USA
    - + +
    - Mtag logo - + VMG logo
    -

    - Mtag - Innovations + VMG

    -
    Software Developer
    +
    Student Researcher
    • - Programmed a cloud-based web app using Flask and JavaScript aimed at storing, visualizing, and tracking temperature and humidity -of each drug container to estimate the degradation of the drug. -
      • -
    • - Created an alert system to send notifications and emails when the parameters exceed the threshold. -
      • + Wrote 2 chapters for a book on Computational Imaging, which was published by MIT Press. +
    • Collaborated with a team of engineers to develop and implement a state-of-the-art Shift Robust Loss Function for rPPG, resulting in decreased error by 40%
      • +
    • Worked with team to diagnose skin-tone bias in medical application using multimodal fusion between radar and RBG data. As a result, the team was able to develop an algorithm that improved accuracy by 75%. The same work has been published in SIGGRAPH.
      • +
    • - Tools: Python, Flask, JavaScript + Tools: Python, OpenCV, Keras, Tensorflow, PyTorch, Computer Vision, Computational Robotics, Scipy
    - July 2018 - Nov 2018 | Ahmedabad, India + July 2020 - July 2022 | Los Angeles, USA
    - + +
    - Cignex logo + Accenture logo

    - CIGNEX - Datamatics + Accenture

    -
    Project Trainee
    +
    Application Development Analyst
      +
    • Qualified as a semi-finalist in the Global Innovation Challenge held by Accenture after demonstrating exceptional problem-solving skills, creativity, and ability to work under pressure.
      • +
    • Served as a point of contact between client, technical and test teams to ensure smooth communication and progress.
      • +
    • Developed and implemented innovative data analysis techniques to enhance the accuracy of drug sales performance monitoring, resulting in a 20% increase in competitor match rate and recognition from the Australian team.
      • +
    • Successfully trained 10 new engineering graduates on the work done in the team, helping them get familiar with the work and contributing to their success.
      • +
    • Leveraged expertise in ETL and BI tools to represent monthly and weekly effectiveness of client resources, leading to +a 15% boost in productivity.
      • +
    • Developed and implemented agile development methodologies to enhance team productivity, resulting in a 25% increase in project completion rate.
      • +
    • Spearheaded the creation and implementation of automated data cleaning and processing workflows, resulting in a +50% reduction in analysis time for pharma sales data.
    • - Designed a library management system for a local library, where we undertook activities like requirement - elicitation, preparing Data Flow - and Entity-Relationship diagrams. + Tools: Python, SQL, Apache, Hive, Informatica BDM, Qlikview, Data Warehouse, Tableau
      • -
    • - Delivered a solution for a POC involving Automatic Financial Document Classifier using Natural Language - Processing and Support Vector - Machines with 96% accuracy on the company’s data. +
    +
    +
    + June 2019 - July 2021 | Bengaluru, India +
    +
    + + + +
    +
    +
    +
    + IISC logo + +
    + + +
    +

    + IISC + +

    +
    +
    +
    Research Assistant
    +
      +
    • Collaborated with Dr. Sundaram and a team of researchers to pioneer new methods for faster and more accurate +diagnosis of Autism, resulting in improved treatment outcomes.
      • +
    • Successfully cleaned and rearranged ABIDE Dataset (depending on correlation between different regions of the brain) to improve data correlation, leading to more accurate predictions.
      • +
    • Developed and optimized deep neural networks to analyze fMRI scans for early detection of Autism, achieving an 80% +accuracy rate on a large set of cleaned data.
      • +
    • + You can locate the report pertaining to this project here.
    • - Tools: Python, Scikit-learn, NLTK + Tools: Python, Pytorch, tensorflow, OpenCV, MATLAB, Research, Scipy, Pandas
    - June 2017 - July 2017 | Ahmedabad, India + January 2019 - June 2019 | Bengaluru, India
    +
    - - + @@ -469,14 +565,11 @@

    Projects

    - music streaming app + detecting heart beat
    - Music Player Web-AppDetecting Pulse from Head Movement -

    - A music streaming web app based on Django -

    @@ -484,24 +577,14 @@

    Projects

    Accomplishments
      -
    • Tools: Django, HTML, CSS, Bootstrap, SQLite, AWS S3, Heroku
      • -
    • Register/login to the web app(with OAuth-based Google Sign-In).
      • -
    • Search and filter songs based on language and singer.
      • -
    • Create multiple playlists and add/remove songs to/from playlist.
      • -
    • Scroll through recently played/viewed songs.
      • +
    • Tools: Computer Vision, Python, OpenCV, Haar Cascade
      • +
    • Provide a 10-30 seconds video
      • +
    • Process the video using Signal processing
      • +
    • Output is the approximate heart rate of the person in the video
      • +
    • An error rate of 3-4 heartbeats
    -
    - - -
    @@ -509,13 +592,13 @@

    Projects

    - quiz app + Robotics Arm
    - Quiz Web-AppAutomatic Garbage Segregator

    - A quiz playing web app based on Django + An Automatic Garbage Segregator Arm using Raspberry Pi

    @@ -524,242 +607,160 @@

    Projects

    Accomplishments
      -
    • Tools: Django, HTML, CSS, Bootstrap, SQLite, Heroku
      • -
    • Register/login to the web app(with OAuth-based Google Sign-In).
      • -
    • Play Quiz and see the leaderboard
      • - +
    • Tools: Python, OpenCV, Deep Learning, Trasnfer learning, Pytorch, Tensorflow, Pandas
      • +
    • Engineered a crane that could segregate waste into biodegradable, non-biodegradable, electronic waste +with an accuracy of 95.18%.
      • +
    • Tested various Feature Extraction techniques like PCA, LDR and Convolutional Neural Networks.
      • + Report
    -
    - - -
    - - - - - + +
    - Screenshot of web app + Multi-Class EEG Motor Imagery Classification Using Deep Learning Architectures
    - Blog Web-App Deep Learning for EEG Data

    - A simple and extensible blog web-app based on Flask. + Multi-Class EEG Motor Imagery Classification Using Deep Learning Architectures

    - AccomplishmentsAccomplishments
      -
    • Tools: HTML, CSS, Bootstrap, Flask, SQLAlchemy, Postgresql, Python
      • -
    • Users can view posts and contact the admin via Contact Page.
      • -
    • Admin can Add, Delete, Update posts.
      • - - +
    • Tools: Python, Computer Vision, Deep Learning, OpenCV, Keras, Tensorflow, Pandas
      • +
    • This project explores deep learning techniques for multi- class classification of EEG signals for motor imagery tasks.
      • +
    • Various neural network architectures such as CNNs, LSTMs, RNNs, VAEs, Transformers, and attention are implemented and tuned.
      • +
    • Effects of pre-processing and time duration on accuracy are analyzed. Results from training on every subject and the entire dataset are compared.
      • +
    • The project shows the potential of deep learning techniques for EEG signal analysis and classification, highlighting the accuracy of the models and their ability to learn underlying patterns in EEG data.
      • + Report
    -
    - - -
    + -
    - Screenshot of web app + google home
    - Visual Question AnsweringGoogle Home replica

    - An attention-based classification model that aims at generating an answer for a given input image. + Built a small replica of Google Home using various PCBs and Sensors

    - AccomplishmentsAccomplishments
      -
    • Incorporated Convolution Neural Networks (CNN) for extracting image features and Long Short Term - Memory for extracting question - embeddings.
      • -
    • Tested the model on the COCO dataset, abstract scenes images, and got 69% overall accuracy on the - VQA evaluation metric.
      • +
    • Tools: Python, OpenCV, Raspberry-Pi, Sensor tech
      • +
    • Successfully built a Google Home prototype using Raspberry Pi, demonstrating an understanding of various types of communication methods. +
    • Acquired new skills in [Raspberry Pi, Google Home] through self-directed learning and experimentation.
    -
    - -
    - - +
    - Screenshot of web app + quiz app
    - Video SummarizerEye tracker

    - A Seq2Seq model that generates a short summary of the given input video. + Mono-SET: 6-DOF Monocular Slam for +Eye-Tracking

    - AccomplishmentsAccomplishments
      -
    • Incorporated CNN to detect and classify objects in the video frames and Long Short Term Memory for - generating a summary.
      • -
    • Evaluated the model on MSVD (Microsoft Video Description Corpus) dataset; achieved 0.77, 0.71, - 0.52 scores respectively on ROGUE, - BLEU, METEOR evaluation metrics.
      • +
    • Tools: Python, Computational Imaging, OpenCV, Raspberry-Pi, Sensor tech
      • +
    • Studied the effectiveness of indoor tracking for gaze estimation using ORB-SLAM using a custom-built eye-gaze wearable setup. +
    • The gaze of the user is estimated using a modified U-Net architecture to extract pupil parameters from a stationary pose.
      • +
    • An Inertial Measuring Unit (IMU) and Fish-Eye camera uses the ORB-SLAM Feature Extractor and Indoor SLAM Environment to track the orientation and movement of the user. The gaze prediction using the data from the ORB-SLAM estimation is used to calculate the distance between the user and the gaze point which is further compared with the ground truth.
    - -
    - -
    - - -
    + +
    - Screenshot of web app + quiz app
    - Image GeneratorLoss Function for rPPG

    - An image generator based on the concept of adversarial networks (GANs) + Shift Robust Loss Function for remote PhotoPlethysmoGraphy (rPPG)

    - AccomplishmentsAccomplishments
      -
    • Developed system was tested on a human-face database and loss was calculated by comparing the PCAs - of generated and original image.
      • -
    • Calculated difference in PCA was less than 10%, depicting the successful generation of an image by - the generator.
      • - +
    • Tools: Python, OpenCV, Object Detection, Computer Vision, Deep learning
      • +
    • rPPG is a technique that uses slight color changes in a person’s face to find remote-PPG signal and estimates heart rate from this signal using signal processing techniques.
      • +
    • We used an RGB camera to obtain face videos of volunteers and a finger pulse oximeter to obtain the ground truth PPG signal while collecting data from rPPG. These two devices are not hardware triggered, so there is a slight lag between the frames obtained from the camera and PPG signal
      • +
    • State-of-the-art methods require the ground truth data to be exactly aligned with the signals.
      • +
    • To address this problem, we propose a novel shift-robust loss function for regression that enables the network to learn from misaligned data to achieve better results than recent methods
      • + Report
    -
    - -
    - - -
    + + +
    - Screenshot of web app + Stochastic Process
    - Head Counting SystemDynamics of Inequality

    - A system that calculates the attendance of the class from a panoramic image of a live classroom. + Summarized the paper "The Dynamics of Inequality"

    - AccomplishmentsAccomplishments
      -
    • Used Singular Value Decomposition for image compression; applied various image processing - techniques and morphological operations to - detect the number of heads.
      • - +
    • Tools: Stochastic processes, ito's Calculus, Brownian Motion
      • +
    • United states has seen a rapid growth in top inequality in the past forty years, i.e. the rate at which super rich are getting richer is more than the rate at which rich are getting richer, due to which the inequality between the two groups is increasing.
      • +
    • In the two deviations that this paper proposes, they consider two reasons namely, "changes in skill prices" or "rise in superstar entrepreneurs or managers".
      • + Report
    -
    - -
    @@ -782,19 +783,25 @@

    Languages and Databases

    Python
    - HTML5 + MATLAB
    - CSS3 + HTML
    MySQL
    - PostgreSQL + Shell Scripting
    - Shell Scripting + Java +
    +
    + C +
    +
    + R
    @@ -817,7 +824,10 @@

    Libraries

    scikit-learn
    - matplotlib + +
    +
    +
    @@ -829,26 +839,62 @@

    Libraries

    Frameworks

    - Django
    - Flask + Keras
    - Bootstrap + TensorFlow
    - Keras + PyTorch
    +
    + + + + +
    +
    +

    Platforms

    +
    - TensorFlow
    - PyTorch + Google Colab +
    +
    + +
    +
    + +
    +
    + QlikView and QlikSense
    + + +
    +
    +

    Soft Skills

    +
    + + + Accomplishments +

    + 1. Leadership
    + 2. Professional Bharatnatyam Dancer. I have also trained in 10+ dance forms!
    + 3. Communication - Ability to communicate in precise and concise manner.
    + 4. Ability to take a 360 view of the problem and define the problem correctly.
    + 5. I enjoy working with Cross cultural teams, and have worked very well.
    + +

    +
    +
    +
    @@ -864,7 +910,14 @@

    Other

    AWS
    - Heroku + Raspberry Pi +
    +
    + Arduino +
    +
    + Firebird Robot +
    @@ -917,11 +970,11 @@

    Education

    - Arizona State University + University of California, Los Angeles

    -

    Tempe, USA

    +

    Los Angeles, USA

    - Degree: Master of Science in Computer Science + Degree: Master of Science in Electrical and Computer Engineering
    CGPA: 4.0/4.0

    @@ -930,9 +983,16 @@

    Education

    Relevant Courseworks:

      -
    • Distributed Database Systems
      • -
    • Cloud Computing
      • -
    • Foundations of Algorithms
      • +
    • Computer Vision
      • +
    • Large Scale Data Mining
      • +
    • Large scale Social and Complex Networks
      • +
    • Neural Networks and Deep Learning
      • +
    • Machine Learning and Modeling in Bio Engineering
      • +
    • Computational Robotics
      • +
    • Computational Imaging
      • +
    • Decision Making in Stochastic processes
      • +
    • Technology Management
      • +
    • Physics and Informatics of Medical Imaging

    @@ -946,25 +1006,26 @@

    Education

    - School of Engineering and Applied Science, Ahmedabad - University + PES University

    -

    Ahmedabad, India

    +

    Bengaluru, India

    - Degree: Bachelor of Technology in Information and Communication Technology + Degree: Bachelor of Technology in Electronics and Communication Technology
    - CGPA: 3.13/4.33 + CGPA: 3.69/4

      Relevant Courseworks:

        -
      • Data Structures and Algorithms
        • -
      • Database Management Systems
        • -
      • Operating Systems
        • +
      • Introduction to Python, C & Embedded Systems
        • +
      • Probability and Random processes
        • +
      • Linear Algebra
        • +
      • Information Theory and Coding
      • Machine Learning
        • -
      • Computer Vision
        • +
      • Digital Signal Processing
        • +
      • Speech Processing

      @@ -981,29 +1042,17 @@

      Education

      Contact

      - +14805722456 -

      -

      - vbhogayata@gmail.com -

      -

      - github.com/varadbhogayata + anu.deoghare28@gmail.com

      - linkedin.com/in/varadbhogayata + class="fa fa-linkedin">linkedin.com/in/ananyadeoghare

      @@ -1013,7 +1062,7 @@

      Contact