CNN-Based Automated Blood Group Classification Using Fingerprint Images
Sentiment Analysis Model
Timeline
BHANU PRASAD MADAKA
Madanapalle
Summary
Detail-oriented AI intern skilled in Python, MySQL, and R programming. Experienced in optimizing machine learning models for accuracy and efficiency. Committed to leveraging analytical skills for impactful contributions in artificial intelligence.
Overview
8
8
years of professional experience
Work History
CAI-Artificial intelligence
Madanapalle Institute of Technology
Madanapalle
01.2021 - Current
CGPA-7.2
AI INTERN
Edu tantr.
06.2024 - 08.2024
This project evaluates and compares various machine learning models to identify the most effective one for a specific dataset. It aims to optimize model performance by analyzing accuracy, efficiency, and adaptability across different algorithms.
Programming Languages - Python, MySQL, Power BI.
IDE/Tools - Jupyter Notebook, Google Colab, Visual Studio, MS Office 360.
M.P.C
Sri madanapalli Junior College
Madanapalle
01.2019 - 01.2021
62%
SSC
Vivekananda Municipal High School
Madanapalle
01.2018 - 01.2019
92%
Education
CAI - Artificial intelligence
Madanapalle Institute of Technology
Madanapalle, AP
09.2025
M.P.C -
Sri madanapalli Junior College
Madanapalle
01.2021
SSC -
Vivekananda Municipal High School
Madanapalle
01.2019
Skills
Python
My SQL
R programming
Power BI
Jupyter Notebook
Google Collab
Visual Studio
MS Office 360
CNN-Based Automated Blood Group Classification Using Fingerprint Images
Designed a CNN model using TensorFlow and Keras to classify ABO and Rh blood groups accurately from fingerprint images with high accuracy
Preprocessed fingerprint images with OpenCV to enhance model performance
Integrated the trained CNN model into a Flask web app, enabling fingerprint upload and blood group prediction.
Sentiment Analysis Model
Designed and implemented a machine learning classification model to predict sentiment (positive or negative) from COVID-19-related tweets, utilizing Python and NLP techniques.
Enhanced model accuracy through iterative testing and tuning, effectively capturing public sentiment trends during the pandemic.
Evaluated and optimized machine learning models on key performance metrics, identifying the most effective algorithms for specific datasets using Python and scikit-learn
Led model refinement through rigorous testing and tuning, enhancing accuracy and adaptability, and presented findings to senior stakeholders