I'm an electircal engineer and PhD student. I am specialized in but not limited to:
- Digital signal processing
- Biomedical signal (EEG, ECG, etc) processing
- Pre-processing signals for machine learning algorithm
- Features extraction for machine learning algorithm
- Classification with k nearest neighbor (kNN)
- Classification, regression, modeling and prediction with Artificial
neural network (ANN)
- Classification, regression, modeling and prediction with Support
vector machines (SVM)
- Image/signal transformation and representation for deep learn.
- Image to label classification with CNN
- Image to image regression with CNN
- Object detection with R-CNN, fast R-CNN, faster R-CNN and YOLO
- Image denoising with DnCNN
- Image generation with GAN and VAE and etc.
- Time series prediction with LSTM
- Sequence to label classification with LSTM
- Sequence to sequence classification with LSTM
Lecturer at Vocational School, Electricity and Energy Department
Okosis Automation and Control Systems
Jun 2012 - Sep 2015 (3 years, 3 months)
Commissioning, testing, designing, implementing and troubleshooting of several Siemens Sicam 230, Sicam WinCC systems,
Sicam 1703 RTU Systems and Siprotec Relays with DIGSI software
for SCMS (Substation Control and Monitoring Systems).
Master of Science
Dicle Üniversitesi, Turkey 2016 - 2018
Bachelor of Science
Istanbul Teknik Üniversitesi, Turkey 2007 - 2012
Detection of Pathological Heart Sound by Using SVM, kNN and Ensemble Methods of Classification
Dicle Engineering Journal
In this work, Training set of Physionet.org 2016 challenge is used to develop, train and test an algorithm that can detect pathological or abnormal heart sounds.
Abnormal Heart Sound Detection Using Ensemble Classifiers
The goal of this study is to develop a classification method for heart sounds collected from different databases. For this purpose two level classification is employed. Firstly, recordings are segregated as per their databases. Then, in second level recordings are classified with respect to pathology by using two classifier per database. With final decision rule, proposed algorithm achieved an accuracy of 98.9%, a sensitivity of 93.75% and a specify of 99.5%.
Classification of EEG Signals Using Hilbert-Huang Transform-Based Deep Neural Networks
Hilbert-Huang transform is applied to EEG signals and they are represented as image files. Then, generated images are fed into deep neural networks with five different structures for classification. Accuracy is calculated for all cases to asses performance of proposed method. it is clear that successful results could be obtained using Hilbert-Huang transform along with deep learning networks.