Scopus
🔓 Açık Erişim YÖKSİS DOI Eşleşti
SJR -
GKP signal processing using deep CNN and SVM for tongue-machine interface
Traitement Du Signal · Ağustos 2019
YÖKSİS Kayıtları
GKP Signal Processing Using Deep CNN and SVM for Tongue-Machine Interface
Traitement du Signal · 2019 SCI-Expanded
Prof. Dr. MUHAMMET SERDAR BAŞÇIL →
GKP Signal Processing Using Deep CNN and SVM for Tongue-Machine Interface
Traitement du Signal · 2019 SCI-Expanded
Prof. Dr. MUHAMMET SERDAR BAŞÇIL →
YÖKSİS Kayıtları — ISSN Eşleşmesi
GKP Signal Processing Using Deep CNN and SVM for Tongue-Machine Interface
2019 ISSN: 0765-0019 SCI-Expanded
Prof. Dr. MUHAMMET SERDAR BAŞÇIL →
Classification of Medical Thermograms Belonging Neonates by Using Segmentation, Feature Engineering and Machine Learning Algorithms
2020 ISSN: 0765-0019 SCI-Expanded
Doç. Dr. MURAT KONAK →
Comparison of the Effects of Mel Coefficients and Spectrogram Images via Deep Learning in Emotion Classification
2020 ISSN: 0765-0019 SCI-Expanded Q3
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
Quantitative Analysis of EEG Slow Wave Activity Based on MinPeakProminence Method
2021 ISSN: 0765-0019 SCI-Expanded
Öğr. Gör. SEMA YILDIRIM →
Quantitative Analysis of EEG Slow Wave Activity Based on MinPeakProminence Method
2021 ISSN: 0765-0019 SCI-Expanded Q2
Prof. Dr. HASAN ERDİNÇ KOÇER →
Using a Deep Learning System That Classifies Hypertensive Retinopathy Based on the Fundus Images of Patients of Wide Age
2021 ISSN: 0765-0019 SCI-Expanded Q2
Prof. Dr. ŞAKİR TAŞDEMİR →
Diagnosing Epilepsy from EEG Using Machine Learning and Welch Spectral Analysis
2024 ISSN: 0765-0019 SCI-Expanded Q3
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
Prediction of Epileptic Seizures Using Deep Learning: A Brief Review of Current Methods and Emerging Trends
2024 ISSN: 0765-0019 SCI-Expanded
Prof. Dr. HUMAR KAHRAMANLI ÖRNEK →
Makale Bilgileri
Dergi
Traitement Du Signal
ISSN07650019
Yayın TarihiAğustos 2019
Cilt / Sayfa36 · 319-329
Scopus ID2-s2.0-85074333923
Erişim🔓 Açık Erişim
Özet
The tongue is one of the few organs with high mobility in the case of severe spinal cord injuries. However, most tongue-machine interfaces (TMIs) require the patient to wear obtrusive and unhygienic devices in and around the mouth. This paper aims to develop a TMI based on the glossokinetic potentials (GKPs), i.e. the electrical signals generated by the tongue when it touches the buccal walls. Ten participants were recruited for this research. The GKP patterns were classified by convolutional neural network (CNN) and support vector machine (SVM). It was observed that the CNN outperformed the SVM in individual and average scores for both raw and preprocessed datasets, reaching an accuracy of 97~99%. The CNN-based GKP processing method makes it easy to build a natural, appealing and robust TMI for the paralyzed. Being the first attempt to process GKPs with the CNN, our research offers an alternative to the traditional brain-computer interfaces (BCIs), which suffers from the instability and low signal-to-noise ratio (SNR) of electroencephalography (EEG).
Yazarlar (4)
1
Kutlucan Gorur
2
Mehmet Recep Bozkurt
3
Muhammet Serdar Bascil
4
Feyzullah Temurtas
Anahtar Kelimeler
Brain-computer interface (BCI)
Convolutional neural network (CNN)
Glossokinetic potential signals (GKPs)
Support vector machine (SVM)
Tongue-machine interface (TMI)
Kurumlar
Bandırma Onyedi Eylül University
Bandirma Turkey
Bozok Üniversitesi
Yozgat Turkey
Sakarya Üniversitesi
Serdivan Turkey
Scimago Dergi (ISSN Eşleşmesi)
Traitement du Signal (discontinued)
-
H-Index31
YayıncıInternational Information and Engineering Technology Association
ÜlkeFrance
Electrical and Electronic Engineering
Metrikler
39
Atıf
4
Yazar
5
Anahtar Kelime