Ege Ozkoc

Ege Ozkoc

PhD Student, Electrical and Computer Engineering
University of Pittsburgh

I work on machine learning and signal processing for biomedical data, with experience in efficient AI systems and embedded inference.

Email · CV · Google Scholar · GitHub · LinkedIn

Research

2025–present

University of Pittsburgh

I am developing evidence-grounded methods for explaining AI-ECG model outputs with LLMs. The explanations are constrained by model evidence, including saliency maps and SHAP attributions, rather than used for independent clinical diagnosis.

2024

Fraunhofer IIS

I developed a lightweight 1D CNN for Parkinson's tremor detection from wrist-worn IMU data. Under subject-independent validation, the model achieved an AUC above 0.90; quantization and structured pruning reduced its size by about 75%.

2020–2022

Inverse electrocardiography

At Middle East Technical University, I worked on noninvasive electrocardiographic imaging, Bayesian MAP estimation, and prior-model selection for ECG reconstruction.

Selected software

  • mini-numpy — a NumPy-like N-dimensional array library in modern C++, with Python bindings through pybind11.
  • Deep learning from scratch — a NumPy/SciPy neural-network framework with manually implemented forward and backward passes.
  • Murmur — a local macOS dictation application built around Whisper and MLX.

Publications

  1. E. Ozkoc, T. S. Zech, N. Pfeiffer, S. Gobl, and J. Frickel. “Compressed and Lightweight CNN for Real-Time Parkinson's Tremor Detection from Wearable IMU Data.” IEEE MLSP, 2025. DOI
  2. E. Ozkoc and Y. Serinagaoglu Dogrusoz. “Bayesian MAP Solution of the Inverse ECG Problem with Sinus Rhythm Data: Evaluation of Simulated Training Sets.” IEEE SIU, 2022. DOI
  3. E. Ozkoc, E. Sunger, K. Ugurlu, and Y. Serinagaoglu Dogrusoz. “Prior Model Selection in Bayesian MAP Estimation-Based ECG Reconstruction.” Measurement, 2021. DOI

Education

  • University of Pittsburgh, PhD in Electrical and Computer Engineering, 2025–present
  • FAU Erlangen-Nurnberg, MSc in Medical Engineering, 2022–2024
  • Middle East Technical University, BSc in Electrical and Electronics Engineering, 2016–2022