Skip to content
View hkayann's full-sized avatar
🌏
Turns fast.
🌏
Turns fast.

Block or report hkayann

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
hkayann/README.md

πŸ‘‹ Hi, I'm Hakan Kayan (@hkayann)

πŸš€ Final Year PhD Student at Cardiff University specializing in Embedded Machine Learning (TinyML), Anomaly Detection, and Predictive Maintenance.


πŸ” My Focus Areas

  • 🎯 Embedded Machine Learning (TinyML):
    Optimizing models for edge devices using techniques like quantization, pruning, and compression.
  • πŸ”§ Anomaly Detection:
    Leveraging AI/ML for real-time detection on IoT and resource-constrained hardware.
  • βš™οΈ IoT and Edge Computing:
    Building scalable edge-to-cloud architectures integrating BLE and sensor fusion.
  • πŸ› οΈ Adversarial Robustness:
    Enhancing the reliability of ML models against adversarial challenges.

πŸ›  Tech Stack

Python C++ TensorFlow Lite Micro PyTorch
BLE
Linux macOS


πŸ’Ό Current Projects

  • Edge AI for Anomaly Detection:
    Real-time anomaly detection on IoT devices using LSTM, 1D-CNN, and 2D-CNN models.
  • Optimizing TinyML Models:
    Applying quantization and compression for resource-constrained hardware like STM32-based PCBs.
  • Adversarial Robustness:
    Improving ML model resilience on edge devices against adversarial attacks.

πŸ“« Get in Touch

🌐 Portfolio Website
πŸ’» GitHub
πŸ“§ Email
πŸ‘” LinkedIn


Popular repositories Loading

  1. node-red-contrib-ble-sense node-red-contrib-ble-sense Public

    Node-RED module for Bluetooth Low Energy (BLE) devices.

    JavaScript 6 4

  2. Real-time-Anomaly-Detection-in-Industrial-Robotic-Arms-via-TinyML Real-time-Anomaly-Detection-in-Industrial-Robotic-Arms-via-TinyML Public

    Repository that contains most of the work of detection anomalies on an industrial robotic arm via Nicla Sense ME.

    Jupyter Notebook 5 1

  3. CASPER-PerCom CASPER-PerCom Public

    This repo contains the work of the demo paper presented in **The 21st International Conference on Pervasive Computing and Communications (PerCom 2023)**.

    Jupyter Notebook 2

  4. hkayann.github.io hkayann.github.io Public

    Personal Website.

    JavaScript 1

  5. TinyML-autoencoder-accelerometer TinyML-autoencoder-accelerometer Public

    TinyML example of autoencoder applied on accelerometer data.

    Jupyter Notebook 1

  6. 1D-CNN-Anomaly-Detection-via-CASPER 1D-CNN-Anomaly-Detection-via-CASPER Public

    Jupyter Notebook 1