Exploiting pretrained CNN models for the development of an EEG-based robust BCI framework.

Identifying motor and mental imagery electroencephalography (EEG) signals is imperative to realizing automated, robust brain-computer interface (BCI) systems. In the present study, we proposed a pretrained convolutional neural network (CNN)-based new automated framework feasible for robust BCI systems with small and ample samples of motor and mental imagery EEG training data. The framework is explored by investigating the implications of different limiting factors, such as learning rates and optimizers, processed versus unprocessed scalograms, and features derived from untuned pretrained models in small, medium, and large pretrained CNN models. The experiments were performed on three public datasets obtained from BCI Competition III. The datasets were denoised with multiscale principal component analysis, and time-frequency scalograms were obtained by employing a continuous wavelet transform. The scalograms were fed into several variants of ten pretrained models for feature extraction and identification of different EEG tasks. The experimental results showed that ShuffleNet yielded the maximum average classification accuracy of 99.52% using an RMSProp optimizer with a learning rate of 0.000 1. It was observed that low learning rates converge to more optimal performances compared to high learning rates. Moreover, noisy scalograms and features extracted from untuned networks resulted in slightly lower performance than denoised scalograms and tuned networks, respectively. The overall results suggest that pretrained models are robust when identifying EEG signals because of their ability to preserve the time-frequency structure of EEG signals and promising classification outcomes.

Effectiveness and safety profiling of zolpidem and acupressure in CKD associated pruritus: An interventional study.

BACKGROUND: Chronic kidney disease (CKD)-associated pruritus (CKD-aP) contributes to poor quality of life, including reduced sleep quality and poor sleep quality is a source of patient stress and is linked to lower health-related quality of life. This study aimed to investigate the effectiveness of zolpidem 10 mg and acupressure therapy on foot acupoints to improve the sleep quality and overall quality of life among hemodialysis patients suffering from CKD-aP. METHOD: A multicenter, prospective, randomized, parallel-design, open label interventional study to estimate the effectiveness of zolpidem (10 mg) oral tablets versus acupressure on sleep quality and quality of life in patients with CKD-aP on hemodialysis. A total of 58 hemodialysis patients having sleep disturbance due to CKD-aP completed the entire 8-week follow-up. The patients were divided into a control (acupressure) group of 28 patients and an intervention (zolpidem) group of 30 patients. RESULTS: A total of 58 patients having CKD-aP and sleep disturbance were recruited. In the control group there was a reduction in the PSQI score with a mean ±â€ŠSD from 12.28 ±â€Š3.59 to 9.25 ±â€Š3.99, while in the intervention group the reduction in PSQI score with a mean ±â€ŠSD was from 14.73 ±â€Š4.14 to 10.03 ±â€Š4.04 from baseline to endpoint. However, the EQ5D index score and EQ-visual analogue scale (VAS) at baseline for the control group with a mean ±â€ŠSD was 0.49 ±â€Š0.30 and 50.17 ±â€Š8.65, respectively, while for the intervention group the values were 0.62 ±â€Š0.26 and 47.17 ±â€Š5.82, respectively. The mean EQ5D index score in the control group improved from 0.49 ±â€Š0.30 to 0.53 ±â€Š0.30, but in the intervention group there was no statistical improvement in mean EQ5D index score from 0.62 ±â€Š0.26 to 0.62 ±â€Š0.27 from baseline to week 8. The EQ 5D improved in both groups and the EQ-VAS score was 2.67 points higher at week 8 as compared to baseline in the control group, while in the intervention group the score was 3.33 points higher at week 8 as compared to baseline. Comparing with baseline, the PSQI scores were significantly reduced after week 4 and week 8 (P =  < .001). Furthermore, at the end of the study, the PSQI scores were significantly higher in the control as compared to the intervention group (P = .012). CONCLUSION: An improvement in sleep quality and quality of life among CKD-aP patients on hemodialysis has been observed in both the control and intervention groups. Zolpidem and acupressure safety profiling showed no severe adverse effect other that drowsiness, nausea and daytime sleeping already reported in literature of zolpidem.