FlowCV Logo
Education

Maturi Venkata Subba Rao Engineering College - B.Tech(CSE)

CGPA : 8.18

2020 – 2024

Kakatiya Junior College - Intermediate

Percentage : 95.5%

2018 – 2020

Vignan High School - SSC

GPA : 8.70

2008 – 2018
Work Experience

Wielabs Software Development Company

Junior software developer (Full time)
  • •I am building a receipt classification model using YOLOv5 for data analysis for over a year of receipts.
    • 04/2024 – presentHyderabad, India
  • •Enhancing the model upon newly added data from the database, handling the MongoDB database.

    • Eizen.AI

    Machine learning engineer (Intern)
  • •Built multi-object detection using pre-trained YOLO v4.
    • 08/2023 – 10/2023Hyderabad, India
  • •Built featured APIs using the Python FastAPI and moviePY library.

    • Suntek Corp Solutions Pvt Ltd

    DSA technical teaching assistant (Intern)

    Collaborated with faculty to refine the curriculum for data structures, incorporating real-world problems ensuring alignment with industry standards updates positively impacted 150+ enrolled students.

    03/2023 – 07/2023Hyderabad, India
    Projects

    Receipt text classifier using YOLOv5 (Python)

  • •The receipt text classifier using YOLOv5 is about classifying the information of receipts by extracting from the receipts using OCR.
  • • Using extracted classified information, further data analysis like increase in GST%, monthly expenses, and visualizing the data.

    • Abusive Language Classifier for Low-resource Telugu (Python)

  • •The Abusive Language Classifier for Low-Resource Telugu detects abusive content in text, trained on 14,000 instances with supervised learning, deep learning, and transformer-based models.
  • •It achieves 87% accuracy and is integrated with a front-end for practical application.

    • Emotion Detection - Machine learning (Python)

  • •Emotion Detection is a machine learning model that classifies emotions 7 different human emotions by analyzing facial expressions from a live camera feed.
  • •Acheived accuracy of 83%, processes approximately 30fps, effectively classifying emotions in real-time.
    • Publications

    Boosting Sentiment Analysis Accuracy in Telugu with Data Augmentation

    Our objective is to enrich the Telugu dataset, enhancing ability for effective sentiment analysis. We construct, evaluate sentiment analysis models using Supervised learning models on both original and augmented datasets, closely examining key performance metrics to assess the impact of these techniques.

    03/2024