Convolutional neural network based on recurrence plot for EEG recognition

Significance of gender, brain region and EEG band complexity analysis for Parkinson's disease classification using recurrence plots and machine learning algorithms

Parkinson Disease (PD) is a complex neurological disorder attributed by loss of neurons generating dopamine in the SN per compacta. Electroencephalogram (EEG) plays an important role in diagnosing PD as it offers a non-invasive continuous assessment of the disease progression and reflects these complex patterns. This study focuses on the non-linear analysis of resting state EEG signals in PD, with a gender-specific, brain region-specific, and EEG band-specific approach, utilizing recurrence plots (RPs) and machine learning (ML) algorithms for classification. For this an open EEG dataset consisting of 14 PD and 14 healthy (HC) subjects is utilized. Recurrence plots and cross-recurrence plots (CRPs) were constructed for each frequency band and brain region, extracting complexity measures such as determinism (DET) and entropy (ENT). The interpretability of the ML model decisions is investigated using explainability technique. The scattered distribution of points in RPs of male PD individuals reflects the complex and dynamic nature of abnormal brain function. Also, CRPs confirms the enhanced effect of Beta Gamma synchronization during PD in the Parietal region. Low DET and high ENT corresponds to the complex non-linear characteristics of EEG signals and brain neuronal circuits during PD condition in male subjects. The extracted recurrence features served as inputs to the ML models, which achieved high classification performance, across all the scenarios. This study demonstrates the potential of recurrence plot-based complexity analysis combined with machine learning for the gender-specific, region-specific, and band-specific assessment of EEG signals during resting state in Parkinson's disease.

A hybrid dual-branch model with recurrence plots and transposed transformer for stock trend prediction

Stock trend prediction is a significant challenge due to the inherent uncertainty and complexity of stock market time series. In this study, we introduce an innovative dual-branch network model designed to effectively address this challenge. The first branch constructs recurrence plots (RPs) to capture the nonlinear relationships between time points from historical closing price sequences and computes the corresponding recurrence quantifification analysis measures. The second branch integrates transposed transformers to identify subtle interconnections within the multivariate time series derived from stocks. Features extracted from both branches are concatenated and fed into a fully connected layer for binary classification, determining whether the stock price will rise or fall the next day. Our experimental results based on historical data from seven randomly selected stocks demonstrate that our proposed dual-branch model achieves superior accuracy (ACC) and F1-score compared to traditional machine learning and deep learning approaches. These findings underscore the efficacy of combining RPs with deep learning models to enhance stock trend prediction, offering considerable potential for refining decision-making in financial markets and investment strategies.

Diagnosis of middle cerebral artery stenosis using the transcranial Doppler images based on convolutional neural network

BACKGROUND

The purpose of this study was to explore the diagnostic value of convolutional neural networks (CNNs) in middle cerebral artery (MCA) stenosis by analyzing the transcranial Doppler (TCD) images.

METHODS

Overall 278 patients who underwent cerebral vascular TCD and cerebral angiography were enrolled and classified into stenosis and non-stenosis groups based on cerebral angiography findings. Manual measurements were performed on TCD images. The patients were divided into a training set and a test set, and the CNNs architecture was used to classify TCD images. The diagnostic accuracies of manual measurements, CNNs, and TCD parameters for MCA stenosis were calculated and compared.

RESULTS

Overall, 203 patients without stenosis and 75 patients with stenosis were evaluated. The sensitivity, specificity, and area under the curve (AUC) for manual measurements of MCA stenosis were 0.80, 0.83, and 0.81, respectively. After 24 iterations of the running model in the training set, the sensitivity, specificity, and AUC of the CNNs in the test set were 0.84, 0.86, and 0.80, respectively. The diagnostic value of CNNs differed minimally from that of manual measurements. Two parameters of TCD, peak systolic velocity and mean flow velocity, were higher in patients with stenosis than in those without stenosis; however, their diagnostic values were significantly lower than those of CNNs (P < 0.05).

CONCLUSIONS

The diagnostic value of CNNs for MCA stenosis based on TCD images paralleled that of manual measurements. CNNs could be used as an auxiliary diagnostic tool to improve the diagnosis of MCA stenosis.