Ajay Rathod

About

Artificial Intelligence undergraduate with foundations in machine learning, statistical modeling, and data analysis. Experienced in building predictive models, data preprocessing, feature engineering, and explainable AI solutions using Python and modern ML techniques.

Education

• Qualification
  Narayana Junior College
  2019 – 2021
• Qualification
  Sri Chaitanya
  2018 – 2019
• B.Tech Artificial Intelligence
  Anurag University
  Artificial Intelligence

Skills

• SQL 6 to 12 months
• Angular 6 to 12 months
• C 6 to 12 months
• CSS 6 to 12 months
• Data Preprocessing 6 to 12 months
• HTML 3 to 6 months
• Python 1 to 2 years
• Java 6 to 12 months
• JavaScript 3 to 6 months
• Node.js <3 months
• Feature Engineering 6 to 12 months
• NumPy <3 months
• Pandas 3 to 6 months
• scikit-learn 6 to 12 months
• XGBoost 6 to 12 months
• Express 6 to 12 months
• Lightgbm 6 to 12 months

Tools / apps / platforms

• Eclipse IDE 3 to 6 months
• Git 3 to 6 months
• Google Colab 3 to 6 months
• VS Code 3 to 6 months

Languages

• English Fluent Speak · Read · Write
• Hindi Conversational Speak · Read
• Telugu Native / Bilingual Speak · Read · Write

Projects

• Sleep Apnea Detection using Machine Learning on ECG and SpO2 Signals
  Python, Machine Learning, Signal Processing

  Developed an automated system for detecting sleep apnea using physiological ECG and SpO2 signals. Extracted heart rate variability (HRV) and oxygen desaturation features to identify apnea events. Implemented ensemble machine learning models including Random Forest, AdaBoost, and XGBoost for multi-class classification of sleep apnea severity. Designed a scalable framework for early sleep apnea screening and real-time risk assessment. Improved detection accuracy compared to traditional ML approaches by integrating multi-signal analysis.

• CardioVision – Cardiovascular Risk Prediction using Machine Learning
  Python, XGBoost, LightGBM, Logistic Regression, SHAP

  Developed a machine learning system to predict cardiovascular disease risk using clinical health parameters. Implemented a stacking ensemble model combining XGBoost, LightGBM, and Logistic Regression for improved prediction accuracy. Applied SMOTE for class imbalance handling and Recursive Feature Elimination (RFE) for feature selection. Achieved 99% prediction accuracy with strong precision, recall, and F1-score performance metrics. Integrated SHAP explainable AI to visualize the contribution of health factors such as cholesterol, blood pressure, and heart rate.

⚽ Extracurricular activities

• President — Click Cadets Photography Club, Anurag University
• Member — TechAmuse Club
• Lead — Sportsbout (2024), IEEE CAS T-Hub (2022)
• Participant — Tejas Project Expo2k25
• Organizing Member — Visionova Hackathon (2025)

🎯 Hobbies & interests

• Drone Piloting
• Photography
• Videography
• Cinematography
• Adobe Photoshop