A5052063259- EEG and Brain-Computer Interfaces
- Neural Networks and Applications
- Engineering Applied Research
- Non-Invasive Vital Sign Monitoring
- Blind Source Separation Techniques
- Hearing Loss and Rehabilitation
- Action Observation and Synchronization
- Advanced Memory and Neural Computing
- Winter Sports Injuries and Performance
- ECG Monitoring and Analysis
- Neural dynamics and brain function
- Neurobiology of Language and Bilingualism
University of Ulsan
2022-2024
Explanation-guided learning (EGL) has gained prominence for improving both the explainability and performance of deep neural networks by integrating additional supervision signals based on elucidation model. However, its applicability in analyzing electroencephalography (EEG) remains underexplored. This study attempted to identify evaluate biological features EGL-based EEG analysis using compact convolutional networks. The identified included anatomical location, dipolarity, relative peak...
Remote photoplethysmography (rPPG) is a non-contact technology that monitors heart activity by detecting subtle color changes within the facial blood vessels. It provides an unconstrained and unconscious approach can be widely applied to health monitoring systems. In recent years, research has been actively conducted improve rPPG signals extract significant information from videos. However, vulnerable degradation due in illumination motion of subject, overcoming these challenges remains...
Semantic processing is an essential mechanism in human language comprehension and has profound implications for speech brain-computer interface technologies. Despite recent advances brain imaging techniques data analysis algorithms, the mechanisms underlying semantic representations remain a topic of debate, specifically whether this occurs through activation selectively separated cortical regions or via network distributed overlapping regions. This study investigates spatiotemporal neural...
Auditory prostheses provide an opportunity for rehabilitation of hearing-impaired patients. Speech intelligibility can be used to estimate the extent which auditory prosthesis improves user's speech comprehension. Although behavior-based is gold standard, precise evaluation limited due its subjectiveness. Here, we a convolutional neural network predict from electroencephalography (EEG). Sixty-four-channel EEGs were recorded 87 adult participants with normal hearing. Sentences spectrally...
A linear system identification technique has been widely used to track neural entrainment in response continuous speech stimuli. Although the approach of standard regularization method using ridge regression provides a straightforward solution estimate and interpret responses stimuli, inconsistent results costly computational processes can arise due need for parameter tuning. We developed novel called detrended cross-correlation function, which aims map stimulus features reverse correlation...