The causes of mental disorders are complex, and early recognition and early intervention are recognized as effective way to avoid irreversible brain damage over time. The existing computer-aided recognition methods mostly focus on multimodal data fusion, ignoring the asynchronous acquisition problem of multimodal data. For this reason, this paper proposes a framework of mental disorder recognition based on visibility graph (VG) to solve the problem of asynchronous data acquisition. First, time series electroencephalograms (EEG) data are mapped to spatial visibility graph. Then, an improved auto regressive model is used to accurately calculate the temporal EEG data features, and reasonably select the spatial metric features by analyzing the spatiotemporal mapping relationship. Finally, on the basis of spatiotemporal information complementarity, different contribution coefficients are assigned to each spatiotemporal feature and to explore the maximum potential of feature so as to make decisions. The results of controlled experiments show that the method in this paper can effectively improve the recognition accuracy of mental disorders. Taking Alzheimer's disease and depression as examples, the highest recognition rates are 93.73% and 90.35%, respectively. In summary, the results of this paper provide an effective computer-aided tool for rapid clinical diagnosis of mental disorders.
Due to the high complexity and subject variability of motor imagery electroencephalogram, its decoding is limited by the inadequate accuracy of traditional recognition models. To resolve this problem, a recognition model for motor imagery electroencephalogram based on flicker noise spectrum (FNS) and weighted filter bank common spatial pattern (wFBCSP) was proposed. First, the FNS method was used to analyze the motor imagery electroencephalogram. Using the second derivative moment as structure function, the ensued precursor time series were generated by using a sliding window strategy, so that hidden dynamic information of transition phase could be captured. Then, based on the characteristic of signal frequency band, the feature of the transition phase precursor time series and reaction phase series were extracted by wFBCSP, generating features representing relevant transition and reaction phase. To make the selected features adapt to subject variability and realize better generalization, algorithm of minimum redundancy maximum relevance was further used to select features. Finally, support vector machine as the classifier was used for the classification. In the motor imagery electroencephalogram recognition, the method proposed in this study yielded an average accuracy of 86.34%, which is higher than the comparison methods. Thus, our proposed method provides a new idea for decoding motor imagery electroencephalogram.
The electroencephalogram (EEG) signal is a general reflection of the neurophysiological activity of the brain, which has the advantages of being safe, efficient, real-time and dynamic. With the development and advancement of machine learning research, automatic diagnosis of Alzheimer’s diseases based on deep learning is becoming a research hotspot. Started from feedforward neural networks, this paper compared and analysed the structural properties of neural network models such as recurrent neural networks, convolutional neural networks and deep belief networks and their performance in the diagnosis of Alzheimer’s disease. It also discussed the possible challenges and research trends of this research in the future, expecting to provide a valuable reference for the clinical application of neural networks in the EEG diagnosis of Alzheimer’s disease.
ObjectiveThe purpose of the research is to study the distribution and early warning of electroencephalogram (EEG) in acute mountain sickness (AMS). MethodsA total of 280 healthy young men were recruited from September 2016 to October 2016. The basic data were collected by the centralized flow method, the general situation of the division of the investigators after the training, the Lewis Lake score, the computer self-rating anxiety scale and depression scale, and the collection of EEG. Follow up in three months. Results94 of the patients with AMS, morbidity is 33%, 21 (22.34%) of the patients are moderate to severe, 73 (77.66%) are mild, morbidity is 26.67%. The abnormal detection rate of electrogram was 7.9% (22/280), which were mild EEG, normal EEG abnormal rate was 8.6% (16/186), abnormal detection rate of mild AMS was 4.1% (3/73), and the abnormal detection rate was 14.3% (3/21) in the medium / heavy AMS. The latter was significantly different from the previous (P < 0.05). Three months follow-up of this group of patients with 0 case of high altitude disease. Conclusions The EEG in AMS is mainly a rhythm irregular, unstable, poor amplitude modulation; or two hemisphere volatility difference of more than 50% or slightly increased activity. The result is statistically significant, suggesting that EEG distributions has possible early warning of AMS.
Attention level evaluation refers to the evaluation of people's attention level through observation or experimental testing, and its research results have great application value in education and teaching, intelligent driving, medical health and other fields. With its objective reliability and security, electroencephalogram signals have become one of the most important technical means to analyze and express attention level. At present, there is little review literature that comprehensively summarize the application of electroencephalogram signals in the field of attention evaluation. To this end, this paper first summarizes the research progress on attention evaluation; then the important methods for electroencephalogram attention evaluation are analyzed, including data preprocessing, feature extraction and selection, attention evaluation methods, etc.; finally, the shortcomings of the current development in the field of electroencephalogram attention evaluation are discussed, and the future development trend is prospected, to provide research references for researchers in related fields.
Objective To explore the effect of chloral hydrate on sleep Electroencephalogram (EEG) in children. Methods A total of 250 children under the age of 5 underwent EEG examination in West China Second University Hospital from Nov.8, 2019 to Sep.1,2021 were enrolled and divided into medication group or non-medication group according to whether they took chloral hydrate before the examination. Among them, 167 patients, the average age of whom was (30.78±17.43) months, were in the medication group, with a male to female ratio of 113:54. 83 cases were in the unmedicated group, the ratio of male to female was 60:23, and the average age was (33.12±17.10) months. There were no statistical difference in age and gender between the two groups. Quantitative EEG method was used to compare and analyze the percentages of the power of various EEG waveforms in the two groups. Results The proportion of EEG beta waves in the medication group was (2.76±4.03)%, and the proportion of EEG beta waves in the non-medication group was (1.59±1.21)%. There was a significant difference between the two groups. The proportion of sleep EEG beta waves in the medication group is higher. Conclusions Chloral hydrate may cause the increase of β fast waves in sleep EEG, which may affect the interpretation of EEG and the diagnosis of diseases.
ObjectiveWe report two family and one sporadic case with dyssynergia cerebellaris myoclonica, investigate the clinical and neural electrophysiological features. MethodsThe proband and sporadic patient was examined by clinical, neuroimaging, video-EEG and synchronous electromyography. ResultsThere were 6 patients with dyssynergia cerebellaris myoclonica of the 27 family members in the first family(3 male and 3 female). There were 4 patients with dyssynergia cerebellaris myoclonica of the 20 family members in the second family(2 male and 2 female). All patiens had disproportionately myoclonus, epilepsy and progressive cerebellar ataxia. EEG showed bursts of spike-slow wave, polyspilke-slow wave distributing in the bilateral brain both in ictal and interictal period, sometimes it is especially in central, parietal and frontal area. EEG showed bursts of spike-slow wave, polyspilke-slow wave distributing in the central, parietal and frontal area in interictal period. Pathology of the skin and muscles are normal. ConclusionThe diagnosis of dyssynergia cerebellaris myoclonica was mainly based on typical clinical manifestations, brain MRI and EEG changes.Long time video EEG and synchronous EMG is important for the diagnosis. Skin and muscles pathology can be normal.
Purpose To analyze the clinical characteristicsand prognostic factors of Status epilepticus (SE) in children. Methods The clinical data of 33 children with SE treated in Jinan Central Hospital Affiliated of Shandong University from January 2014 to June 2021 were collected, and their clinical characteristics were analyzed. Then, according to Glasgow prognosis scale, the children were divided into good prognosis group (n=20) and poor prognosis group (n=13). The age of first attack, duration of attack, type of attack and SE classification, EEG, cranial imaging and etiology were used to analyze the influencing factors of SE prognosis. Results 75.7% were 0 ~ 6 years old in the age of first attack, and 29 cases of convulsive status epilepticus accounted for 87.9% in the classification of seizure types. There were significant differences in age of first attack, duration of attack, EEG, history of mental retardation and etiology between the two groups (P<0.05); Logistic regression analysis showed that the age of first attack, duration of attack, history of mental retardation and EEG were independent factors affecting the prognosis. Conclusion Low age, especially ≤ 6 years old, is the high incidence of SE in children at first attack. Most children are symptomatic and have obvious incentives. Convulsive SE is the main type of SE in children. The age of first onset, duration of epilepsy, history of mental retardation, and EEG can affect the prognosis of SE.
There are two modes to display panoramic movies in virtual reality (VR) environment: non-stereoscopic mode (2D) and stereoscopic mode (3D). It has not been fully studied whether there are differences in the activation effect between these two continuous display modes on emotional arousal and what characteristics of the related neural activity are. In this paper, we designed a cognitive psychology experiment in order to compare the effects of VR-2D and VR-3D on emotional arousal by analyzing synchronously collected scalp electroencephalogram signals. We used support vector machine (SVM) to verify the neurophysiological differences between the two modes in VR environment. The results showed that compared with VR-2D films, VR-3D films evoked significantly higher electroencephalogram (EEG) power (mainly reflected in α and β activities). The significantly improved β wave power in VR-3D mode showed that 3D vision brought more intense cortical activity, which might lead to higher arousal. At the same time, the more intense α activity in the occipital region of the brain also suggested that VR-3D films might cause higher visual fatigue. By the means of neurocinematics, this paper demonstrates that EEG activity can well reflect the effects of different vision modes on the characteristics of the viewers’ neural activities. The current study provides theoretical support not only for the future exploration of the image language under the VR perspective, but for future VR film shooting methods and human emotion research.
To accurately capture and effectively integrate the spatiotemporal features of electroencephalogram (EEG) signals for the purpose of improving the accuracy of EEG-based emotion recognition, this paper proposes a new method combining independent component analysis-recurrence plot with an improved EfficientNet version 2 (EfficientNetV2). First, independent component analysis is used to extract independent components containing spatial information from key channels of the EEG signals. These components are then converted into two-dimensional images using recurrence plot to better extract emotional features from the temporal information. Finally, the two-dimensional images are input into an improved EfficientNetV2, which incorporates a global attention mechanism and a triplet attention mechanism, and the emotion classification is output by the fully connected layer. To validate the effectiveness of the proposed method, this study conducts comparative experiments, channel selection experiments and ablation experiments based on the Shanghai Jiao Tong University Emotion Electroencephalogram Dataset (SEED). The results demonstrate that the average recognition accuracy of our method is 96.77%, which is significantly superior to existing methods, offering a novel perspective for research on EEG-based emotion recognition.