- Celal Bayar Üniversitesi Fen Bilimleri Dergisi
- Vol: 16 Issue: 1
- Comparative Evaluation for PCA and ICA on Tongue-Machine Interface Using Glossokinetic Potential Res...
Comparative Evaluation for PCA and ICA on Tongue-Machine Interface Using Glossokinetic Potential Responses
Authors : Kutlucan Görür, Mehmet Recep Bozkurt, Muhammed Serdar Başçil, Feyzullah Temurtas
Pages : 35-46
View : 18 | Download : 6
Publication Date : 2020-03-27
Article Type : Research
Abstract :Click here for manuscript sample template The tongue-machine interface (TMI) between the paralyzed person and computer makes possible to manage assistive technologies. Severely disabled individuals caused by traumatic brain and spinal cord injuries need continuous help to carry out everyday routines. The cranial nerve is arisen directly from the brain to connect the tongue that is one of the last affected organs in neuromuscular disorders. Besides, the tongue has highly capable of mobility located in the oral cavity which also provides cosmetic advantages. These crucial skills make the tongue to be an odd organ employed in the human-machine interfaces. In this study, it was aimed to investigate 1-D extraction and develop a novel tongue-machine interface using the glossokinetic potential responses (GKPs). This rare used bio-signs are occurred by contacting the buccal walls with the tip of the tongue in the oral cavity. Our study, named as GKP-based TMI measuring the glossokinetic potential responses over the scalp may serve paralyzed persons an unobtrusive, natural and reliable communication channel. In this work, 8 males and 2 females, aged between 22-34 naive healthy subjects have participated. Linear discriminant analysis and support vector machine were implemented with mean-absolute value and power spectral density feature extraction process. Moreover independent component analysis (ICA) and principal component analysis (PCA) were used to evaluate the reduced dimension of the data set for GKPs in machine learning algorithms. And the highest result was obtained as 97.03%.Keywords : Assistive Technologies, Glossokinetic Potential Responses, Independent Component Analysis, Principal Component Analysis, Tongue-Machine Interface