Background: Alzheimer’s disease (AD) is the most common neurogenerative disorder, making up 70% of total dementia cases with a prevalence of more than 55 million people. Electroencephalogram (EEG) has become a suitable, accurate, and highly sensitive biomarker for the identification and diagnosis of AD.Methods: In this study, a public database of EEG resting state-closed eye recordings containing 36 AD subjects and 29 normal subjects was used. And then, three types of signal features of resting-state EEG, i.e., spectrum, complexity, and synchronization, were performed by applying various signal processing and statistical methods, to obtain a total of 18 features for each signal epoch. Next, the supervised machine learning classification algorithms of decision trees, random forests, and support vector machine (SVM) were compared in categorizing processed EEG signal features of AD and normal cases with leave-one-person-out cross-validation.Results: The results showed that compared to normal cases, the major change in EEG characteristics in AD cases was an EEG slowing, a reduced complexity, and a decrease in synchrony. The proposed methodology achieved a relatively high classification accuracy of 95.65, 95.86, and 88.54% between AD and normal cases for decision trees, random forests, and SVM, respectively, showing that the integration of spectrum, complexity, and synchronization features for EEG signals can enhance the performance of identifying AD and normal subjects.Conclusion: This study recommended the integration of EEG features of spectrum, complexity, and synchronization for aiding the diagnosis of AD.

Sleep staging is the basis of sleep assessment and plays a crucial role in the early diagnosis and intervention of sleep disorders. Manual sleep staging by a specialist is time-consuming and is influenced by subjective factors. Moreover, some automatic sleep staging algorithms are complex and inaccurate. The paper proposes a single-channel EEG-based sleep staging method that provides reliable technical support for diagnosing sleep problems. In this study, 59 features were extracted from three aspects: time domain, frequency domain, and nonlinear indexes based on single-channel EEG data. Support vector machine, neural network, decision tree, and random forest classifier were used to classify sleep stages automatically. The results reveal that the random forest classifier has the best sleep staging performance among the four algorithms. The recognition rate of the Wake phase was the highest, at 92.13%, and that of the N1 phase was the lowest, at 73.46%, with an average accuracy of 83.61%. The embedded method was adopted for feature filtering. The results of sleep staging of the 11-dimensional features after filtering show that the random forest model achieved 83.51% staging accuracy under the condition of reduced feature dimensions, and the coincidence rate with the use of all features for sleep staging was 94.85%. Our study confirms the robustness of the random forest model in sleep staging, which also represents a high classification accuracy with appropriate classifier algorithms, even using single-channel EEG data. This study provides a new direction for the portability of clinical EEG monitoring.

This study investigates the changes in soldiers' brain executive function at different altitude environments and their relationship with blood oxygen saturation. Stratified sampling was conducted in different altitude 133 active-duty soldiers who were stationed in Weinan (347 m, n = 34), Nyingchi (2,950 m, n = 32), Lhasa (3,860 m, n = 33), and Nagqu (4,890 m, n = 34) for 2 years. The Go/NoGo paradigm with event-related potentials (ERPs) and event-related oscillations (EROs) was used to explore the time and neural oscillation courses of response inhibition. Behavioral results revealed that at the 4,890-m altitude area, the soldiers had the highest false alarm rate, the longest reaction time, and the slowest information transmission rate. The electrophysiological results revealed that NoGo-N2 and N2d decreased with increasing altitude, with significant changes at 3,860 m; the amplitudes of NoGo-P3 and P3d in plateau groups were significantly more negative than the plain and changed significantly at 2,950 m. The results of correlation analysis showed that NoGo-P3 was negatively correlated with altitude (r = −0.358, p = 0.000), positively correlated with SpO₂ (r = 0.197, p = 0.041) and information translation rate (ITR) (r = 0.202, p = 0.036). P3d was negatively correlated with altitude (r = −0.276, p = 0.004) and positively correlated with ITR (r = 0.228, p = 0.018). N2d was negatively correlated with ITR (r = 0.204, p = 0.034). The power spectrum analysis of NoGo-N2 and NoGo-P3 showed that the power of δ and θ bands at the plateau area was significantly lower than the plain area and showed a significant step-by-step decrease; the α-band power increases significantly only in the area of 4,890 m. The effect of chronic hypoxia exposure at different altitudes of the plateau on the response inhibition of soldiers was manifested: 3,860 m was the altitude at which the brain response inhibition function decreased during the conflict monitoring stage, and 2,950 m was the altitude at which it dropped during the response inhibition stage. In addition, the soldier's brain's executive function was closely related to SpO₂, and a reduction in SpO₂ may lead to a decline in response inhibition.

The EEG features of different emotions were extracted based on multi-channel and forehead channels in this study. The EEG signals of 26 subjects were collected by the emotional video evoked method. The results show that the energy ratio and differential entropy of the frequency band can be used to classify positive and negative emotions effectively, and the best effect can be achieved by using an SVM classifier. When only the forehead and forehead signals are used, the highest classification accuracy can reach 66%. When the data of all channels are used, the highest accuracy of the model can reach 82%. After channel selection, the best model of this study can be obtained. The accuracy is more than 86%.

Background: While the effects of sleep deprivation on cognitive function are well-documented, its impact on high-intensity endurance performance and underlying neural mechanisms remains underexplored, especially in the context of search and rescue operations where both physical and mental performance are essential. This study examines the neurophysiological basis of sleep deprivation on high-intensity endurance using electroencephalography (EEG). In this crossover study, twenty firefighters were subjected to both sleep deprivation (SD) and normal sleep conditions, with each participant performing endurance treadmill exercise the following morning after each condition. EEG signals were recorded before and after high-intensity endurance exercise, and power spectrum analysis and functional connectivity analysis were performed on sleep related frequency bands rhythm: δ (0.5–4 Hz) and θ (4–8 Hz). The EEG power spectral and functional connectivity were measured by repeated measure analysis of variance. Results: The SD condition had an average sleep duration of 3.78 ± 0.69 h, while the duration for normal sleep was 7.63 ± 0.52 h. After high-intensity endurance exercise, the SD condition had a higher maximum heart rate (p < 0.05) and shorter exercise time (p < 0.05) than normal sleep. Compared with before exercise, the δ band in the left parietal lobe P7 channel increased significantly (p < 0.01), and the θ band in the central Cz channel and the left and right parietal lobe P7 and P8 channel increased significantly (p < 0.01 & p < 0 0.05) in SD and normal sleep conditions after exercise. After exercise, compared with normal sleep, the δ band power in occipital O1 and Oz channels and parietal P7 and TP7 channels in SD significantly decreased (p < 0.05 & p < 0.01); the power of the θ band decreased significantly in the occipital O1 channel, central CZ channel and the left and right parietal P7 and P8 channel (p < 0.05 & p < 0.01). Whole connectivity showed a significant increase (p = 0.001) in the δ band for the SD condition at post-exhaustion. Local connectivity analysis identified a localized network in the δ band with reduced (p < 0.001) post-exhaustion in the SD condition displaying inter-hemispheric differences in certain connections (FP1-CP4, T7-C4, T7-TP8, and O1-FT8) and intra-hemispheric (C3-CPz and Pz-P4) variations. Conclusions: Sleep deprivation significantly reduced maximum endurance performance, indicating decreased neural activity in the central and parietal brain regions. Alterations in δ and θ frequency band power, along with disrupted connectivity, may highlight the neurophysiological basis underlying this decline.

The present study aimed to investigate the effects of stimulus time duration on central nervous odor processing. Twenty-one young healthy males participate in our study. There are three odor mixtures in this study and every odor mixture has two different duration time (300 ms; 500 ms). The odor was presented via a computer - controlled olfactometer and EEG was recorded from 64 scalp locations. At behavioral level, the longer the odor stimulus was presented, the greater the concentration was perceived by participants. Electrophysiological data showed that longer duration time lengthened the latency of Negative waves of about 200 ms appeared in stimulation (N2) and Positive waves of about 300 ms appeared in stimulation (P3) components, besides, have a larger N2 amplitude than the shorter duration time condition in the mid-frontal and left frontal-temporal areas. These results revealed that duration time of odor mixture do have an influence on the central nervous odor processing.