Generalizable Sample-Efficient Siamese Autoencoder for Tinnitus Diagnosis in Listeners With Subjective Tinnitus

Electroencephalogram (EEG)-based neurofeedback has been widely studied for tinnitus therapy in recent years. Most existing research relies on experts' cognitive prediction, and studies based on machine learning and deep learning are either data-hungry or not well generalizable to new subjects....

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on neural systems and rehabilitation engineering Ročník 29; s. 1452 - 1461
Hlavní autoři: Liu, Zhe, Yao, Lina, Wang, Xianzhi, Monaghan, Jessica J. M., Schaette, Roland, He, Zihuai, McAlpine, David
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Ablation
Algorithms
Auditory system
Brain modeling
Coders
Cognitive ability
Deep learning
domain alignment
EEG
Electroencephalography
Encoders-Decoders
Feature extraction
Feedback
Fineness
Learning algorithms
Machine learning
Medical diagnosis
Medical treatment
Neurofeedback
Predictive control
siamese autoencoder
subject-independent
Tinnitus
Training
trend descriptor
ISSN:1534-4320, 1558-0210, 1558-0210
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Electroencephalogram (EEG)-based neurofeedback has been widely studied for tinnitus therapy in recent years. Most existing research relies on experts' cognitive prediction, and studies based on machine learning and deep learning are either data-hungry or not well generalizable to new subjects. In this paper, we propose a robust, data-efficient model for distinguishing tinnitus from the healthy state based on EEG-based tinnitus neurofeedback. We propose trend descriptor, a feature extractor with lower fineness, to reduce the effect of electrode noises on EEG signals, and a siamese encoder-decoder network boosted in a supervised manner to learn accurate alignment and to acquire high-quality transferable mappings across subjects and EEG signal channels. Our experiments show the proposed method significantly outperforms state-of-the-art algorithms when analyzing subjects' EEG neurofeedback to 90dB and 100dB sound, achieving an accuracy of 91.67%-94.44% in predicting tinnitus and control subjects in a subject-independent setting. Our ablation studies on mixed subjects and parameters show the method's stability in performance.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1534-4320
1558-0210
1558-0210
DOI:10.1109/TNSRE.2021.3095298