ABSTRACT
Recently, convolutional neural network (CNN)-based classification models have shown good performance for motor imagery (MI) brain-computer interfaces (BCI) using electroencephalogram (EEG) in end-to-end learning. Although a few explainable artificial intelligence (XAI) techniques have been developed, it is still challenging to interpret the CNN models for EEG-based BCI classification effectively. In this research, we propose 3D-EEGNet as a 3D CNN model to improve both the explainability and performance of MI EEG classification. The proposed approach exhibited better performances on two MI EEG datasets than the existing EEGNet, which uses a 2D input shape. The MI classification accuracies are improved around 1.8% and 6.1% point in average on the datasets, respectively. The permutation-based XAI method is first applied for the reliable explanation of the 3D-EEGNet. Next, to find a faster XAI method for spatio-temporal explanation, we design a novel technique based on the normalized discounted cumulative gain (NDCG) for selecting the best among a few saliency-based methods due to their higher time complexity than the permutation-based method. Among the saliency-based methods, DeepLIFT was selected because the NDCG scores indicated its results are the most similar to the permutation-based results. Finally, the fast spatio-temporal explanation using DeepLIFT provides deeper understanding for the classification results of the 3D-EEGNet and the important properties in the MI EEG experiments.
Subject(s)
Artificial Intelligence , Brain-Computer Interfaces , Humans , Electroencephalography , Learning , Neural Networks, Computer , Algorithms , ImaginationABSTRACT
Situated models of emotion hypothesize that emotions are optimized for the context at hand, but most neuroimaging approaches ignore context. For the first time, we applied Granger causality (GC) analysis to determine how an emotion is affected by a person's cultural background and situation. Electroencephalographic recordings were obtained from mainland Chinese (CHN) and US participants as they viewed and rated fearful and neutral images displaying either social or non-social contexts. Independent component analysis and GC analysis were applied to determine the epoch of peak effect for each condition and to identify sources and sinks among brain regions of interest. We found that source-sink couplings differed across culture, situation and culture × situation. Mainland CHN participants alone showed preference for an early-onset source-sink pairing with the supramarginal gyrus as a causal source, suggesting that, relative to US participants, CHN participants more strongly prioritized a scene's social aspects in their response to fearful scenes. Our findings suggest that the neural representation of fear indeed varies according to both culture and situation and their interaction in ways that are consistent with norms instilled by cultural background.
Subject(s)
Emotions , Parietal Lobe , Brain/diagnostic imaging , Brain/physiology , Electroencephalography , Emotions/physiology , Fear , HumansABSTRACT
OBJECTIVE: Using dynamic causal modeling (DCM), we examined how credibility and reliability affected the way brain regions exert causal influence over each other-effective connectivity (EC)-in the context of trust in automation. BACKGROUND: Multiple brain regions of the central executive network (CEN) and default mode network (DMN) have been implicated in trust judgment. However, the neural correlates of trust judgment are still relatively unexplored in terms of the directed information flow between brain regions. METHOD: Sixteen participants observed the performance of four computer algorithms, which differed in credibility and reliability, of the system monitoring subtask of the Air Force Multi-Attribute Task Battery (AF-MATB). Using six brain regions of the CEN and DMN commonly identified to be activated in human trust, a total of 30 (forward, backward, and lateral) connection models were developed. Bayesian model averaging (BMA) was used to quantify the connectivity strength among the brain regions. RESULTS: Relative to the high trust condition, low trust showed unique presence of specific connections, greater connectivity strengths from the prefrontal cortex, and greater network complexity. High trust condition showed no backward connections. CONCLUSION: Results indicated that trust and distrust can be two distinctive neural processes in human-automation interaction-distrust being a more complex network than trust, possibly due to the increased cognitive load. APPLICATION: The causal architecture of distributed brain regions inferred using DCM can help not only in the design of a balanced human-automation interface design but also in the proper use of automation in real-life situations.