A Systematic Review of Using Deep Learning Technology in the Steady-State Visually Evoked Potential-Based Brain-Computer Interface Applications: Current Trends and Future Trust Methodology

Abstract

The significance of deep learning techniques in relation to steady-state visually evoked potential- (SSVEP-) based brain-computer interface (BCI) applications is assessed through a systematic review. Three reliable databases, PubMed, ScienceDirect, and IEEE, were considered to gather relevant scientific and theoretical articles. Initially, 125 papers were found between 2010 and 2021 related to this integrated research field. After the filtering process, only 30 articles were identified and classified into five categories based on their type of deep learning methods. The first category, convolutional neural network (CNN), accounts for 70% ( n = 21 / 30 ). The second category, recurrent neural network (RNN), accounts for 10% ( n = 3 / 30 ). The third and fourth categories, deep neural network (DNN) and long short-term memory (LSTM), account for 6% ( n = 30 ). The fifth category, restricted Boltzmann machine (RBM), accounts for 3% ( n = 1 / 30 ). The literature’s findings in terms of the main aspects identified in existing applications of deep learning pattern recognition techniques in SSVEP-based BCI, such as feature extraction, classification, activation functions, validation methods, and achieved classification accuracies, are examined. A comprehensive mapping analysis was also conducted, which identified six categories. Current challenges of ensuring trustworthy deep learning in SSVEP-based BCI applications were discussed, and recommendations were provided to researchers and developers. The study critically reviews the current unsolved issues of SSVEP-based BCI applications in terms of development challenges based on deep learning techniques and selection challenges based on multicriteria decision-making (MCDM). A trust proposal solution is presented with three methodology phases for evaluating and benchmarking SSVEP-based BCI applications using fuzzy decision-making techniques. Valuable insights and recommendations for researchers and developers in the SSVEP-based BCI and deep learning are provided.

Multimodal Deep Learning in Early Autism Detection—Recent Advances and Challenges

“…Relevant articles were short keywords like "Deep Learning" and "Autism Spectrum Disorder". Figure 3 flow and the number of articles identified through different sources, which research goals [10]. Deep learning (DL) methods are increasingly used i tection and for analyzing data from neuroimaging, behavioral observati [11].…”

“…Deep learning techniques are increasingly used for ASD detection, and integrate data from various sources to enhance accuracy [9]. The choice of modalities depends on available data and research goals [10]. Deep learning (DL) methods are increasingly used in early ASD detection and for analyzing data from neuroimaging, behavioral observations, and speech [11].…”

“…research goals [10]. Deep learning (DL) methods are increasingly used in ear tection and for analyzing data from neuroimaging, behavioral observations, [11].…”

Generalized Time Domain Prediction Model for Motor Imagery-based Wheelchair Movement Control

“…Principally, MI pattern recognition schemes include raw MI EEG signal preprocessing feature extraction [22], and classification [23,24]. The MI pattern recognition model correlates the effectiveness of intelligent processes such as feature extraction and classification with the effectiveness of the preprocessing (segmentation) of the EEG signal [25,26]. Feature extraction is another critical step in MI pattern recognition.…”

The Considerations of Trustworthy AI Components in Generative AI; A Letter to Editor

“…This involves educating users, developers, and decision-makers on ethical considerations, potential biases, and mechanisms ensuring transparency and accountability in AI systems [5] [6]. Additionally, other theories such as Multi-Criteria Decision-Making (MCDM) and fuzzy sets can be applied and/or integrated with AI to achieve trustworthiness in decision-making [7]. For example, in the problem of datasets without labeling (target), MCDM can assign and process the appropriate target for these cases in the dataset based on the formulation of several models using subjective judgment from experts [8].…”