Kaveh Samiee

Ph.D. in Machine Learning & Signal Processing | Expert in Edge AI, Patient Monitoring, and Healthcare Solutions

About Me

I hold a Ph.D. in Signal Processing with a strong focus on Machine Learning and over a decade of professional experience across various industries. My expertise spans time-series analysis, computer vision, machine learning, and large-scale data analytics, with a particular emphasis on applications in the healthcare sector. As a versatile full-stack data scientist with a multidisciplinary educational background and diverse work experience, I excel at integrating knowledge and skills from different domains, leveraging practical problem-solving and critical thinking to deliver impactful solutions.

Key skills: Advanced time-series & Edge-AI, signal processing, statistical analysis, machine vision, representational learning, agentic workflows; Python, C++/C, SQL, Matlab; TensorFlow, PyTorch, Keras, JAX; MLOps (MLflow, Airflow, Azure ML); Azure, AWS, Databricks, Docker, Kubernetes.

Current Research Project

  • Privacy-preserving federated learning architectures for wearable ECGs and digital cardiology

    Mentor, Fatima Institute for Global AI Research · May 2026 – Present

    As a volunteer mentor with the Fatima Institute for Global AI Research, I am guiding a team of three Fatima fellows on this project. Together we are tackling critical, real-world bottlenecks in privacy, drift-adaptation security, and personalized architectures to make clinical medical AI both safe and scalable. The institute brings together a global community committed to inclusive and impactful AI research.

Experience

  • Senior Cloud Developer — Basware

    Mar 2026 – Current

    Building enterprise-centric MLOps and AgentOps.

  • Principal Algorithm and AI Engineer — Doublepoint

    May 2025 – Feb 2026 · Doublepoint has been acquired by Oura

    Built end-to-end ML solutions for gesture recognition in wearable devices. Lead for hardware-agnostic models, model transfer, and signal-processing chain design.

  • Staff Algorithm Software Engineer — GE Healthcare

    Sep 2021 – May 2025

    ECG algorithm development and MLOps engineer in the ECG platform team. Main projects: single-lead analysis, Edge-AI for QRS classification, and black-box optimization of heuristics.

  • Technical Leader — Nokia

    Apr 2021 – Sep 2021

    Local product owner for ML/AI solutions in next-gen cellular networks. Machine learning engineer; supervising juniors and M.Sc. thesis workers.

  • Senior Data Scientist — Fujitsu

    Feb 2019 – Mar 2021

    CleverHealth Network (E-MOM): architect and full-stack developer; walking monitor platform: technical lead; diabetic retinopathy detection and internal recommendation engine: data scientist.

  • Senior Data Scientist — GE Healthcare

    Feb 2018 – Feb 2019

    Team lead for biomedical predictive models; unsupervised/generative approaches for medical data; thesis adviser.

  • Algorithm Developer Software Engineer — GE Healthcare

    Aug 2015 – Feb 2018

    Development of ECG algorithms, unit tests, performance testing, and multi-modal predictive models.

  • Earlier career

    2005 – 2015

    Professionally employed in industry and academia since graduating in 2005. Roles spanned electronics and automation engineering (embedded systems, PCB design, PLC programming), industrial inspection and image-processing software, and research and teaching in EEG/ECG classification, advanced signal processing, and image analysis in academia.

Publications

20+ peer-reviewed articles. Metrics from Google Scholar:

881 citations 10 h-index 10 i10-index
  • Samiee, K. (2025). Spiking QRS Detector: Adaptive Homeostatic Modulation for Continual Unsupervised Learning. 2025 Computing in Cardiology (CinC), 52, 1-4.
  • Samiee, K. (2025). ECG Morphology Representational Learning and Decomposition Via An Adaptive Legendre Mixture Model Variational Autoencoder. 2025 Computing in Cardiology (CinC), 52, 1-4.
  • Samiee, K., & Kovács, P. (2024). On Edge Wearable ECG Signal Quality Assessment using Residual Hermite Projection and Liquid State Machine, a Hierarchical Domain Adaptation Approach. 2024 Computing in Cardiology (CinC), 51, 1-4.
  • Samiee, K., & Kovács, P. (2023). ECG decomposition using cascaded spline projection residual auto encoders. 2023 Computing in Cardiology (CinC), 50, 1-4.
  • Kovács, P., & Samiee, K. (2022). Arrhythmia detection using spiking variable projection neural networks. 2022 Computing in Cardiology (CinC), 49, 1-4.
  • Samiee, K., Kovács, P., & Gabbouj, M. (2017). Epileptic seizure detection in long-term EEG records using sparse rational decomposition and local Gabor binary patterns feature extraction. Knowledge-Based Systems, 118, 228-240.
  • Samiee, K., Iosifidis A., & Gabbouj, M. (2017). On the comparison of random and Hebbian weights for the training of single-hidden layer feedforward neural networks. Expert Systems with Applications, 83, 177-186.
  • Raitoharju, J., Samiee, K., Kiranyaz, S., & Gabbouj, M. (2017). Particle swarm clustering fitness evaluation with computational centroids. Swarm and evolutionary computation, 34, 103-118.
  • Samiee, K., Kiranyaz, S., Gabbouj, M., & Saramäki, T. (2015). Long-term epileptic EEG classification via 2D mapping and textural features. Expert Systems with Applications, 42(20), 7175-7185.
  • Samiee, K., Kovács, P., Kiranyaz, S., Gabbouj, M., & Saramaki, T. (2015). Sleep stage classification using sparse rational decomposition of single channel EEG records. 2015 23rd European Signal Processing Conference (EUSIPCO), 1860-1864.
  • Gilián, Z., Kovács, P., & Samiee, K. (2014). Rhythm-based Accuracy Improvement of Heart Beat Detection Algorithms. Computing in Cardiology Conference (CinC), 269-272.
  • Raitoharju, J., Zhang, H., Ozan, E.C., Waris, M.A., Faisal, M., Cao, G., Roininen, M., Samiee, K., Kiranyaz, S., & Gabbouj, M. (2014). Tut MUVIS image retrieval system proposal for MSR-Bing challenge 2014. 2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 1-6.
  • Samiee, K., Kovacs, P., & Gabbouj, M. (2014). Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform. IEEE transactions on Biomedical Engineering, 62(2), 541-552.
  • Kovacs, P., Samiee, K., & Gabbouj, M. (2014). On application of rational discrete short time Fourier transform in epileptic seizure classification. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
  • Samiee, K. (2009). A replacement algorithm based on weighting and ranking cache objects. International Journal of Hybrid Information Technology, 2(2), 93-104.
  • Samiee, K. (2009). An image segmentation method for detecting objects in images with textural background. 2009 2nd International Workshop on Nonlinear Dynamics and Synchronization.
  • Samiee, K., & Rad, G.A.R. (2008). Wrp: Weighting replacement policy to improve cache performance. International Symposium on Computer Science and its Applications, 38-41.
  • Samiee, K., & Rad, G.A.R. (2008). Textural segmentation of sidescan sonar images based on gabor filters bank and active contours without edges. 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.
  • Rad, G.A.R., & Samiee, K. (2008). Fast and modified image segmentation method based on active contours and gabor filter. 2008 Third International Conference on Information and Communication Technologies: From Theory to Applications.

Patents

  • Samiee, K. (2022). Methods and systems for patient monitoring. US Patent US11432778B2.

Curriculum Vitae

Download the full CV below. Certificates: Microsoft Azure Data Scientist Associate (DP-100, 2023); Microsoft Azure Data Engineer Associate (DP-203, 2024).

Download CV (PDF)

Contact

If you would like to get in touch, please feel free to email me at: kaveh.samiee [at] gmail [dot] com.