Research Intern
Classification
As a Research Intern, I developed advanced machine learning solutions for biomedical signal classification. Using diverse tools and frameworks, I focused on improving accuracy in arrhythmia detection and reducing misclassification in clinical scenarios. My work involved close collaboration in an academic research setting.
• Engineered a GoogleNet-based machine learning model to classify different arrhythmia types.
• Utilized Python, PyTorch, MATLAB, and Kaggle to implement and evaluate the model.
• Achieved a classification accuracy of 99.33%, significantly enhancing diagnostic capabilities.
• Reduced arrhythmia misclassification rates by 40% through rigorous testing and validation.
As a Research Intern, I developed advanced machine learning solutions for biomedical signal classification. Using diverse tools and frameworks, I focused on improving accuracy in arrhythmia detection and reducing misclassification in clinical scenarios. My work involved close collaboration in an academic research setting. • Engineered a GoogleNet-based machine learning model to classify different arrhythmia types. • Utilized Python, PyTorch, MATLAB, and Kaggle to implement and evaluate the model. • Achieved a classification accuracy of 99.33%, significantly enhancing diagnostic capabilities. • Reduced arrhythmia misclassification rates by 40% through rigorous testing and validation.
2024 - 2024