Search Results for author: Ozan Ozyegen

Found 5 papers, 0 papers with code

Text Classification for Predicting Multi-level Product Categories

no code implementations2 Sep 2021 Hadi Jahanshahi, Ozan Ozyegen, Mucahit Cevik, Beste Bulut, Deniz Yigit, Fahrettin F. Gonen, Ayşe Başar

In our experiments, we investigate the generalizability of the trained models to the products of other online retailers, the dynamic masking of infeasible subcategories for pretrained language models, and the benefits of incorporating product titles in multiple languages.

Classification Pretrained Language Models +2

Word-level Text Highlighting of Medical Texts for Telehealth Services

no code implementations21 May 2021 Ozan Ozyegen, Devika Kabe, Mucahit Cevik

The first method uses TF-IDF scores directly to highlight important parts of the text.

Evaluation of Local Explanation Methods for Multivariate Time Series Forecasting

no code implementations18 Sep 2020 Ozan Ozyegen, Igor Ilic, Mucahit Cevik

In this study, we propose two novel evaluation metrics for time series forecasting: Area Over the Perturbation Curve for Regression and Ablation Percentage Threshold.

BIG-bench Machine Learning Multivariate Time Series Forecasting +1

An empirical study on using CNNs for fast radio signal prediction

no code implementations16 Jun 2020 Ozan Ozyegen, Sanaz Mohammadjafari, Karim El mokhtari, Mucahit Cevik, Jonathan Ethier, Ayse Basar

We compare deep learning-based prediction models including RadioUNET and four different variations of the UNET model for the power prediction task.

Cannot find the paper you are looking for? You can Submit a new open access paper.