Temporal complexity of EEG encodes human alertness

Evaluation of traffic signs information volume at highway tunnel entrance zone based on the visual sample entropy of novice and experienced drivers

OBJECTIVE

Traffic signs play a crucial role in ensuring road traffic safety, particularly in high-risk driving zones like the entrance zone of highway tunnels. However, the impact of traffic signs information volume (TSIV) on the performance of experienced and novice drivers in this specific zone remains unclear. This study aims to investigate the influence of TSIV on the visual sample entropy (SampEn) of both experienced and novice drivers in the entrance zone of highway tunnels.

METHODS

A real vehicle driving trial was conducted with 60 participants approaching tunnels under various TSIV conditions. Fixation duration SampEn, saccade duration SampEn, and saccade amplitude SampEn were analyzed for both driver groups.

RESULTS

As both driver groups approached the tunnel entrance, fixation duration SampEn, saccade duration SampEn, and saccade amplitude SampEn gradually increased. Initially, visual SampEn declined, followed by an increase as the TSIV level increased. The lowest value of visual SampEn was observed under the T3 TSIV condition (48.31 bits). Experienced drivers exhibited lower visual SampEn compared to novice drivers under similar TSIV conditions.

CONCLUSIONS

TSIV and driving experience significantly influence the visual SampEn of drivers approaching the tunnel entrance. Optimal visual search patterns and performance were observed under the T3 TSIV condition (48.31 bits), which is critical for ensuring driving safety in the entrance zone of highway tunnels. Additionally, experienced drivers demonstrate better adaptation to tunnel environments and TSIV, while novice drivers may benefit from additional training to enhance their visual perception and performance.

Spatial-temporal features-based EEG emotion recognition using graph convolution network and long short-term memory

Objective. Emotion recognition on the basis of electroencephalography (EEG) signals has received a significant amount of attention in the areas of cognitive science and human-computer interaction (HCI). However, most existing studies either focus on one-dimensional EEG data, ignoring the relationship between channels, or only extract time-frequency features while not involving spatial features.Approach. We develop spatial-temporal features-based EEG emotion recognition using a graph convolution network (GCN) and long short-term memory (LSTM), named ERGL. First, the one-dimensional EEG vector is converted into a two-dimensional mesh matrix, so that the matrix configuration corresponds to the distribution of brain regions at EEG electrode locations, thus to represent the spatial correlation between multiple adjacent channels in a better way. Second, the GCN and LSTM are employed together to extract spatial-temporal features; the GCN is used to extract spatial features, while LSTM units are applied to extract temporal features. Finally, a softmax layer is applied to emotion classification.Main results. Extensive experiments are conducted on the A Dataset for Emotion Analysis using Physiological Signals (DEAP) and the SJTU Emotion EEG Dataset (SEED). The classification results of accuracy, precision, and F-score for valence and arousal dimensions on DEAP achieved 90.67% and 90.33%, 92.38% and 91.72%, and 91.34% and 90.86%, respectively. The accuracy, precision, and F-score of positive, neutral, and negative classifications reached 94.92%, 95.34%, and 94.17%, respectively, on the SEED dataset.Significance. The above results demonstrate that the proposed ERGL method is encouraging in comparison to state-of-the-art recognition research.

EEG frequency band analysis in chronic neuropathic pain: A linear and nonlinear approach to classify pain severity

BACKGROUND AND OBJECTIVE

Chronic neuropathic pain (NP) is a chronic pain condition that severely impacts a patient's life. Pain management has proved to be inefficient due to a lack of a simple clinical tool that may identify and monitor NP. A low-cost, noninvasive tool that provides relevant information on NP is the electroencephalogram (EEG). However, the commonly used linear EEG features have proved to be limited in characterizing NP pathophysiology. This study sought to determine whether nonlinear EEG features such as approximate entropy (ApEn) would better differentiate pain severity than absolute band power.

METHODS

A non-parametric statistical approach based on the Brief Pain Inventory (BPI), along with linear and nonlinear EEG features, is proposed in this study. For this purpose, thirty-six chronic NP patients were recruited, and 22 channels were registered. Additionally, a control database of 13 participants with no NP was used as a reference, where 19 channels were registered. For both groups, EEG was recorded for 10 min in a resting state: 5 min with eyes open (EO) and 5 min with eyes closed (EC). Absolute band power and ApEn EEG features in the five clinical frequency bands (delta, theta, alpha, beta, and gamma) were estimated for all channels in both groups. As a result, 220-dimensional and 190-dimensional feature vectors were obtained for experimental and control classes respectively. For the experimental class, NP patients were grouped according to their BPI evaluation in three groups: low, moderate, and high pain. Finally, feature vectors were compared between groups using Kruskal Wallis and post-hoc Dunn's tests.

RESULTS

ApEn revealed significant statistical difference (p <=0.0001) in most frequency bands and conditions among the groups. In contrast, power had less significant differences between groups, particularly with EO. Furthermore, NP groups were notably clustered using only ApEn in theta, alpha, and beta bands.

CONCLUSIONS

The results indicate that ApEn effectively characterizes the different severities of chronic NP rather than the commonly used linear features. ApEn and other nonlinear techniques (e.g., spectral entropy, Shannon entropy) might be a more suitable methodology to monitor chronic NP experience.