Manifold Learning-Based Common Spatial Pattern for EEG Signal Classification.

EEG signal classification using Riemannian manifolds has shown great potential. However, the huge computational cost associated with Riemannian metrics poses challenges for applying Riemannian methods, particularly in high-dimensional feature data. To address these, we propose an efficient ensemble method called MLCSP-TSE-MLP, which aims to reduce the computational cost while achieving superior performance. MLCSP of the ensemble utilizes a Riemannian graph embedding strategy to learn intrinsic low-dimensional sub-manifolds, enhancing discrimination. TSE uses the Euclidean mean as the reference point for tangent space mapping and reducing computational cost. Finally, the ensemble incorporates the MLP classifier to offer improved classification performance. Classification results conducted on three datasets demonstrate that MLCSP-TSE-MLP achieves significant superior performance compared to various competing methods. Notably, the MLCSP-TSE module achieves a remarkable increase in training speed and exhibits much lower test time compared to traditional Riemannian methods. Based on these results, we believe that the proposed MLCSP-TSE-MLP is a powerful tool for handling high-dimensional data and holds great potential for practical applications.

Di(2-ethylhexyl) phthalate mediates oxidative stress and activates p38MAPK/NF-kB to exacerbate diabetes-induced kidney injury in vitro and in vivo models.

Plasticizer di(2-ethylhexyl) phthalate (DEHP) is employed to make polyethylene polymers. Some studies in epidemiology and toxicology have shown that DEHP exposure over an extended period may be hazardous to the body, including nephrotoxicity, and aggravate kidney damage in the context of underlying disease. However, studies on the toxicity of DEHP in diabetes-induced kidney injury have been rarely reported. Using a high-fat diet (HFD) and streptozotocin (STZ, 35 mg/kg)-induced kidney injury in mice exposed to various daily DEHP dosages, we explored the impacts of DEHP on diabetes-induced kidney injury. We discovered that DEHP exposure significantly promoted the renal inflammatory response and oxidative stress in mice, with increased P-p38 and P-p65 protein levels and exacerbated the loss of podocin. The same findings were observed in vitro after stimulation of podocytes with high glucose (30 mmol/L) and exposure to DEHP. Our results suggest that DEHP exacerbates diabetes-induced kidney injury by mediating oxidative stress and activating p38MAPK/NF-κB.

DW-FBCSP: EEG emotion recognition algorithm based on scale distance weighted optimization.

Emotion calibration is measured by the valence and arousal scales and the ideal center is used to directly divide valence arousal into high scores and low scores. This division method has a big classification and labeling defect, and the influence of emotion stimulation material on the subjects cannot be accurately measured. To address this problem, this paper proposes an EEG emotion recognition algorithm (DW-FBCSP: Distance Weighted Filter Bank Common Spatial Pattern) based on scale distance weighted optimization to optimize the classification according to the distance of the scores from ideal center. This method is a natural extension of CSP that optimize the user's EEG signal projection matrix. Then, the LDA classifier is used to recognize emotions using the features set which fused the selected features and the features extracted by the projection matrix. The results show that the mean correct rate of the valence and arousal achieves 81.14% and 84.45% using the DEAP dataset. The results demonstrate that our proposed method outperforms better than some other results published in recent years.

Validation of Pulse Transit Time Based Blood Pressure Estimation on Atrial Fibrillation Patients.

Pulse transit time (PTT) based continuous cuff-less blood pressure (BP) monitoring has attracted wide interests owing to its potential in improving the control and early prevention for cardiovascular diseases. However, it is still impractical in large-scale clinical application due to the concern of BP measurement accuracy. Since such approach strongly relies on the PTT-BP model under certain theoretical assumptions, the accuracy would be affected by the vessel properties alterations induced by cardiovascular disorders. Atrial fibrillation (AF) is one of the most common cardiac diseases which often coexist with hypertension. The present study sought to examine the Impact of AF on the PTT and BP， validate the capability of PTT based cuff-less methods on AF patients. By investigating the PTT and BP on 74 critically ill patients with AF, we found that parameters including PTT, R-R interval and diastolic BP (DBP) were significantly changed when AF occurs, while the systolic BP (SBP) value and photoplethysmography intensity ratio (PIR) changed little. Further, by performing two cuff-less BP estimation method, we found that the estimated accuracy is decreased on PTT based method when AF occurs, but there is little change on PIR based method. The findings demonstrated that the impact of AF on PTT is significant, which would also influence the PTT-BP relationship. But the PIR would still be a predictive factor for BP estimation for AF patients.

Analysis and Classification of Sleep Stages Based on Common Frequency Pattern From a Single-Channel EEG Signal.

One crucial key of developing an automatic sleep stage scoring method is to extract discriminative features. In this paper, we present a novel technique, termed common frequency pattern (CFP), to extract the variance features from a single-channel electroencephalogram (EEG) signal for sleep stage classification. The learning task is formulated by finding significant frequency patterns that maximize variance for one class and that at the same time, minimize variance for the other class. The proposed methodology for automated sleep scoring is tested on the benchmark Sleep-EDF database and finally achieves 97.9%, 94.22%, and 90.16% accuracy for two-state, three-state, and five-state classification of sleep stages. Experimental results demonstrate that the proposed method identifies discriminative characteristics of sleep stages robustly and achieves better performance as compared to the state-of-the-art sleep staging algorithms. Apart from the enhanced classification, the frequency patterns that are determined by the CFP algorithm is able to find the most significant bands of frequency for classification and could be helpful for a better understanding of the mechanisms of sleep stages.

Tensor Discriminant Analysis for MI-EEG Signal Classification Using Convolutional Neural Network.

Motor Imagery (MI) is a typical paradigm for Brain-Computer Interface (BCI) system. In this paper, we propose a new framework by introducing a tensor-based feature representation of the data and also utilizing a convolutional neural network (CNN) architecture for performing classification of MI-EEG signal. The tensor-based representation that includes the structural information in multi-channel time-varying EEG spectrum is generated from tensor discriminant analysis (TDA), and CNN is designed and optimized accordingly for this representation. Compared with CSP+SVM (the conventional framework which is the most successful in MI-based BCI) in the applications to the BCI competition III-IVa dataset, the proposed framework has the following advantages: (1) the most discriminant patterns can be obtained by applying optimum selection of spatial-spectral-temporal subspace for each subject; (2) the corresponding CNN can take full advantage of tensor-based representation and identify discriminative characteristics robustly. The results demonstrate that our framework can further improve classification performance and has great potential for the practical application of BCI.

Cuffless blood-pressure estimation method using a heart-rate variability-derived parameter.

OBJECTIVE: Cuffless blood-pressure (BP) estimation has attracted widespread interest owing to its potential for long-term, non-invasive BP monitoring. But it is still impractical in clinical settings, mainly owing to ongoing challenges with respect to accuracy in hypertensive patients. To better estimate the BP, the current study proposes a new cuffless estimation method that includes a sympathetic tone, which has been reported with a varied pattern in hypertensive patients. APPROACH: First, the heart-rate variability of all subjects is investigated, and a new parameter, the heart-rate power spectrum ratio (HPSR), is proposed to indicate BP dynamics under sympathetic regulation. Then, a new BP estimation model is constructed by integrating HPSP with the pulse transit time (PTT) and photoplethysmography intensity ratio. The estimation accuracy is further evaluated by making comparisons with the standard sphygmomanometer BP on 60 subjects (29 hypertensive and 31 normotensive). MAIN RESULTS: A significant increase in HPSR was observed in hypertensive patients compared to normotensive subjects. Of the 60 subjects, the estimation accuracy was 0.73 ± 10.04 mmHg for systolic BP (SBP) and 0.90 ± 7.10 mmHg for diastolic BP (DBP) in hypertensive patients, which is comparable to 0.54 ± 7.52 mmHg for SBP and 0.82 ± 6.20 mmHg for DBP in normotensive subjects. Furthermore, the proposed method overperformed the traditional PTT-based algorithm by reducing the 3 mmHg error in the standard deviation in hypertensive patients. SIGNIFICANCE: The results of the current study demonstrate that the inclusion of factors associated with autonomic activities in the BP estimation model would improve the BP estimation accuracy, especially for hypertensive subjects.