Multimodal Vigilance Estimation With Modality-Pairwise Contrastive Loss

Toward the enhancement of affective brain-computer interfaces using dependence within EEG series

In recent years, electroencephalogram (EEG)-based affective brain-computer interfaces (aBCI) has made remarkable advances.Objective. However, a subtle but crucial problem caused by the sliding window method has long been overlooked, which is the serious quantity mismatch between stimuli and short-term EEG frames. This may be an important factor limiting the performance of aBCIs.Approach. We refer to this mismatch as the quantity-independence imbalance (Q/I imbalance) and we propose the weak independence hypothesis to explain the mismatch. To validate this hypothesis and explore the effects of the Q/I imbalance on short-term EEG frames, we design four experiments from four perspectives, which are visualization, cross-validation, randomness test, and redundancy test.Main results. Inspired by validation experiments, we propose an inference correction (IC) method to enhancing the emotional predictions by leveraging the majority of the classifier's outputs. The proposed IC method is evaluated on two datasets involving 60 subjects using both intra-subject and inter-subject validation protocols. Our IC achieves a significant improvement of 14.97% in classification accuracy.Significance. This study promotes the understanding of the time-dependent nature of EEG signals in aBCI.

Technologies for detecting and monitoring drivers' states: A systematic review

Driver fatigue or drowsiness detection techniques can significantly enhance road safety measures and reduce traffic accidents. These approaches used different sensor technologies to acquire the human physiological and behavioral characteristics to investigate the driver's vigilance state. Although the driver's vigilance detection technique has attracted significant interest recently, few studies have been conducted to review it systematically. These studies provide a thorough overview of the most advanced driver vigilance detection method available today in terms of sensor technology for scholars and specialists. This research is geared towards achieving three main objectives. Firstly, it aims to systematically gather, evaluate, and synthesize information from previous research published between 2014 and May 2024 on driver's state and driving sensors and their implementation on detection algorithms. It aims to provide a thorough review of the present state of research on wearable and unwearable sensor technology for driver fatigue detection, focusing on reporting experimental results in this field. This information will be necessary for experts and scientists seeking to advance their knowledge in this field. Lastly, the research aims to identify gaps in knowledge that require further investigation and recommend future research directions to help address these gaps. This way, it will contribute to the advancement of the field and provide beneficial insights for future researchers.

Classification of EEG Signals Based on Sparrow Search Algorithm-Deep Belief Network for Brain-Computer Interface

In brain-computer interface (BCI) systems, challenges are presented by the recognition of motor imagery (MI) brain signals. Established recognition approaches have achieved favorable performance from patterns like SSVEP, AEP, and P300, whereas the classification methods for MI need to be improved. Hence, seeking a classification method that exhibits high accuracy and robustness for application in MI-BCI systems is essential. In this study, the Sparrow search algorithm (SSA)-optimized Deep Belief Network (DBN), called SSA-DBN, is designed to recognize the EEG features extracted by the Empirical Mode Decomposition (EMD). The performance of the DBN is enhanced by the optimized hyper-parameters obtained through the SSA. Our method's efficacy was tested on three datasets: two public and one private. Results indicate a relatively high accuracy rate, outperforming three baseline methods. Specifically, on the private dataset, our approach achieved an accuracy of 87.83%, marking a significant 10.38% improvement over the standard DBN algorithm. For the BCI IV 2a dataset, we recorded an accuracy of 86.14%, surpassing the DBN algorithm by 9.33%. In the SMR-BCI dataset, our method attained a classification accuracy of 87.21%, which is 5.57% higher than that of the conventional DBN algorithm. This study demonstrates enhanced classification capabilities in MI-BCI, potentially contributing to advancements in the field of BCI.