H
Hunkar Can Tunc
Researcher at University of Konstanz
Publications - 7
Citations - 326
Hunkar Can Tunc is an academic researcher from University of Konstanz. The author has contributed to research in topics: Kleene algebra & Mathematical structure. The author has an hindex of 2, co-authored 6 publications receiving 158 citations. Previous affiliations of Hunkar Can Tunc include Bahçeşehir University.
Papers
More filters
Journal ArticleDOI
A comparative analysis of speech signal processing algorithms for Parkinson’s disease classification and the use of the tunable Q-factor wavelet transform
C. Okan Sakar,Gorkem Serbes,Aysegul Gunduz,Hunkar Can Tunc,Hatice Nizam,Betul Erdogdu Sakar,Melih Tutuncu,Tarkan Aydin,M. Erdem Isenkul,Hulya Apaydin +9 more
TL;DR: The results show that TQWT performs better or comparable to the state-of-the-art speech signal processing techniques used in PD classification, and Mel-frequency cepstral and the tunable-Q wavelet coefficients, which give the highest accuracies, contain complementary information inPD classification problem resulting in an improved system when combined using a filter feature selection technique.
Journal ArticleDOI
Estimation of Parkinson’s disease severity using speech features and extreme gradient boosting
Hunkar Can Tunc,Hunkar Can Tunc,Cemal Okan Sakar,Hulya Apaydin,Gorkem Serbes,Aysegul Gunduz,Melih Tutuncu,Fikret Gürgen +7 more
TL;DR: This study aims to estimate the severity of PD from voice recordings of the patients using motor Unified Parkinson's Disease Rating Scale (UPDRS) as the evaluation metric and investigates the effectiveness of using age and years passed since diagnosis as covariates together with speech features.
Proceedings ArticleDOI
Detection of e-Commerce Anomalies using LSTM-recurrent Neural Networks
TL;DR: The results show that constructing a multivariate LSTM by feeding the campaign information as an additional input improves the adaptability of the model to sudden changes occurring in campaign periods, and fits better to the dynamics of e-commerce KPIs than time-series based prediction methods.
Journal ArticleDOI
Explaining safety failures in NetKAT
TL;DR: It is shown how explanations for safety violations can be derived in an equational fashion, according to a modification of the existing NetKAT axiomatisation, and an approach based on the Maude system for actually computing the undesired behaviours witnessing the forwarding of packets from i to e is proposed.